Intelligent device control method based on multi-dimensional environment perception

Abstract

The application discloses a kind of intelligent device control methods based on multi-dimensional environment perception, it is related to the technical field of smart home, the method comprises: generating target adjustment demand of target object to the environmental parameter of target space according to the object information of target object;According to the target device information of each reference intelligent device in the intelligent device set in target space, detect the target device parameter of reference intelligent device under target adjustment demand;From the target intelligent device that the target device parameter meets target condition is filtered out in intelligent device set;Control target intelligent device adjusts the environmental parameter of target space according to target adjustment demand, using the above technical scheme, the control efficiency of intelligent device is lower in related art etc. Problem, the technical effect of improving the control efficiency of intelligent device is realized.

Description

Technical Field

[0001] This application relates to the field of smart home technology, and more specifically, to a smart device control method based on multi-dimensional environmental perception. Background Technology

[0002] With the rapid development of Internet of Things (IoT) technology and the continuous improvement of AI voice interaction capabilities, smart home voice control systems have become a core interaction portal in smart home scenarios. Currently, voice-based smart device control is widely adopted. In this method, users need to output control commands to smart devices via voice. This voice command must carry clear control information, such as the device to be controlled and the operation to be performed.

[0003] However, in many cases, users may not be able to effectively output voice commands containing all the control information required by the smart device. As a result, when users have a need for the smart device, there may be no response from the smart device or the smart device may respond incorrectly, which greatly affects the user's control experience of the smart device.

[0004] There is still no effective solution to the problem of low control efficiency of smart devices in related technologies. Summary of the Invention

[0005] This application provides a method for controlling intelligent devices based on multi-dimensional environmental perception, which at least solves the problem of low control efficiency of intelligent devices in related technologies.

[0006] According to one embodiment of this application, a smart device control method based on multi-dimensional environmental perception is provided, comprising:

[0007] The target adjustment requirements of the target object for the environmental parameters of the target space are generated based on the object information of the target object, wherein the object information is used to indicate the comfort level of the target object in the target space;

[0008] Based on multiple target device information of each reference smart device in the set of smart devices in the target space, the target device parameters of the reference smart device under the target adjustment requirements are detected. The multiple target device information is used to reflect the adaptation relationship between the environmental parameter adjustment attributes of the corresponding reference smart device and the target adjustment requirements from multiple feature dimensions. The target device parameters are used to indicate the probability of the target object selecting the reference smart device under the target adjustment requirements.

[0009] Select target smart devices from the set of smart devices whose target device parameters meet the target conditions, wherein the target conditions are determined based on the target object's usage habits of the smart devices in the set of smart devices;

[0010] The target intelligent device is controlled to adjust the environmental parameters of the target space according to the target adjustment requirements.

[0011] Optionally, detecting the target device parameters of the reference intelligent device under the target adjustment requirement based on multiple target device information of each reference intelligent device in the set of intelligent devices in the target space includes:

[0012] The reference device parameters corresponding to each target device information of the reference smart device under the target adjustment requirement are determined. The reference device parameters indicate the adaptability of the reference smart device to the target adjustment requirement in the feature dimension to which the target device information belongs. The target device information includes at least two of the following: energy efficiency parameters, rate parameters, environmental adaptation parameters, and user preference parameters. The energy efficiency parameters indicate the energy efficiency during the adjustment of environmental parameters using the reference smart device. The rate parameters indicate the adjustment rate of the environmental parameters by the reference smart device. The environmental adaptation parameters indicate the difference between the current environmental parameters of the target space and the maximum and minimum parameters included in the target parameter range. The target parameter range is the range of parameters to which the target object needs to adjust its environmental parameters, as indicated by the target adjustment requirement. The user preference parameters indicate the frequency of the target object's use of the reference smart device in the target space before the current time.

[0013] The target device parameters are obtained by fitting multiple reference device parameters of the reference smart device using weight parameters. The weight parameters are used to indicate the influence of device information of each feature dimension in the multiple feature dimensions on the target object in selecting the corresponding reference smart device in the target adjustment requirement. The multiple reference device parameters correspond one-to-one with the multiple target device information.

[0014] Optionally, the step of using the weight parameters of the target smart device to perform parameter fitting on multiple reference device parameters of the reference smart device to obtain the target device parameters includes:

[0015] The target device parameters are calculated using the following formula:

[0016] Scorei=W1 Ai+W2 Ei+W3 Pi+W4 Ri;

[0017] Wherein, Scori represents the target device parameter of the reference smart device; Ai indicates the difference between the current environmental parameters of the target space and the maximum and minimum parameters included in the target parameter range; the target parameter range is the range of parameters to which the target object needs to adjust its environmental parameters according to the target adjustment requirement; Ai is negatively correlated with the difference between the current environmental parameters of the target space and the maximum and minimum parameters included in the target parameter range; Ei indicates the energy efficiency of the reference smart device after adjusting the environmental parameters according to the target adjustment requirement; Ei is positively correlated with the energy efficiency of the reference smart device; Pi characterizes the frequency of the target object's use of the reference smart device in the target space before the current time; Pi is positively correlated with the frequency of the target object's use of the reference smart device; and Ri indicates the reference... The intelligent device adjusts the environmental parameters at a rate that meets the target adjustment requirements. There is a positive correlation between Ri and the adjustment rate of the reference intelligent device to the environmental parameters. The reference device parameters include Ai, Ei, Pi, and Ri. W1 indicates the degree of influence of the deviation between the current environmental parameters and the target parameter range on the target object's selection of the reference intelligent device. W2 indicates the degree of influence of energy efficiency on the target object's selection of the reference intelligent device. W3 indicates the degree of influence of the frequency of the target object's use of the reference intelligent device in the target space before the current time on the target object's selection of the reference intelligent device. W4 indicates the degree of influence of the intelligent device's adjustment rate to the environmental parameters on the target object's selection of the reference intelligent device. The weighting parameters include W1, W2, W3, and W4.

[0018] Optionally, after controlling the target intelligent device to adjust the environmental parameters of the target space according to the target adjustment requirements, the method further includes:

[0019] Detect the candidate smart devices actually used by the target object under the target adjustment requirements;

[0020] Obtain multiple candidate device information of the candidate smart device, wherein the multiple candidate device information is used to reflect the adaptation relationship between the environmental parameter adjustment attributes of the candidate smart device and the target adjustment requirements from the multiple feature dimensions, and the feature dimensions of the multiple candidate device information correspond one-to-one with the feature dimensions of the multiple target device information;

[0021] Detect the target similarity between multiple candidate device information and multiple target device information;

[0022] The weight parameters of the target device are adjusted based on the target similarity.

[0023] Optionally, adjusting the weight parameters of the target device based on the target similarity includes:

[0024] For the target feature dimension among the plurality of feature dimensions, a weight adjustment amount corresponding to the sub-similarity between the candidate device information and the target device information of the target feature dimension is determined, wherein the target similarity includes the sub-similarity corresponding to each feature dimension among the plurality of feature dimensions;

[0025] The sub-weight parameters of the target feature dimension are adjusted using the weight adjustment amount, wherein the sub-weight parameters are used to indicate the influence of the device information of the corresponding feature dimension on the target object in selecting the reference smart device in the target adjustment requirement, and the weight parameters include the sub-weight parameters.

[0026] Optionally, before selecting target smart devices from the set of smart devices whose target device parameters meet the target conditions, the method further includes:

[0027] Obtain the reference number of smart devices used by the target object during the historical time period when adjusting environmental parameters in the target space;

[0028] The target number of smart devices that the target smart device needs to control under the current target adjustment requirements is detected based on the reference number.

[0029] Configure the target conditions according to the target quantity.

[0030] Optionally, generating the target adjustment requirements of the target object for the environmental parameters of the target space based on the object information of the target object includes one of the following:

[0031] The process involves: acquiring the target speech output by the target object, wherein the target speech carries feedback information regarding the comfort level of the target object in the target space, and the object information includes the target speech; adjusting the initial parameter range based on the feedback information to obtain a target parameter range, wherein the initial parameter range is the environmental parameters of the target space set by the target object before the current moment; and determining that the target adjustment requirement is a request from the target object to adjust the environmental parameters in the target space to the target parameter range.

[0032] Obtain the target physiological parameters of the target object in the target space, wherein the target physiological parameters are used to characterize the physiological characteristics of the target object, and the object information includes the target physiological parameters; adjust the initial parameter range according to the target physiological parameters to obtain the target parameter range, wherein the initial parameter range is the environmental parameters of the target space set by the target object before the current time; determine the target adjustment requirement as the target object requesting that the environmental parameters in the target space be adjusted to the target parameter range.

[0033] Optionally, adjusting the initial parameter range based on the target physiological parameter to obtain the target parameter range includes:

[0034] Obtain the target parameter difference between the target physiological parameter and the preset physiological parameter threshold of the target object;

[0035] The target parameter adjustment amount corresponding to the target parameter difference is determined from the corresponding parameter differences and parameter adjustment amounts;

[0036] The initial parameter range is adjusted according to the target parameter adjustment amount to obtain the target parameter range.

[0037] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer-readable storage medium, and the computer program is configured to execute the above-described intelligent device control method based on multi-dimensional environmental perception when it is run.

[0038] According to another aspect of the embodiments of this application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above-described intelligent device control method based on multi-dimensional environmental perception through the computer program.

[0039] In this embodiment, the target object's environmental parameter adjustment requirements are generated based on its comfort level in the target space. Furthermore, the adaptation relationship between the environmental parameter adjustment attributes of multiple characteristic dimensions of the smart device and the target adjustment requirements is comprehensively considered. This reflects the likelihood of the target object selecting each smart device under the target adjustment requirements. Furthermore, based on the target device parameters, target smart devices that meet the target conditions are selected from among the smart devices, enabling the target smart devices to effectively adapt to the target object's actual needs in the current control scenario. By adopting the above technical solution, the problem of low control efficiency of smart devices in related technologies is solved, achieving the technical effect of improving the control efficiency of smart devices. Attached Figure Description

[0040] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0041] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a schematic diagram of the hardware environment of an intelligent device control method based on multi-dimensional environmental perception according to an embodiment of this application;

[0043] Figure 2 This is a flowchart of an intelligent device control method based on multi-dimensional environmental perception according to an embodiment of this application;

[0044] Figure 3 This is an optional device control schematic diagram according to an embodiment of this application;

[0045] Figure 4 This is a structural block diagram of an intelligent device control device based on multi-dimensional environmental perception, according to an embodiment of this application. Detailed Implementation

[0046] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0047] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0048] According to one aspect of the embodiments of this application, a method for controlling intelligent devices based on multi-dimensional environmental perception is provided. This method is widely applicable to whole-house intelligent digital control application scenarios such as smart homes, smart home ecosystems, and intelligence house ecosystems. Optionally, in this embodiment, Figure 1 This is a schematic diagram of the hardware environment for a smart device control method based on multi-dimensional environmental perception according to an embodiment of this application. The above method can be applied to, for example... Figure 1 The hardware environment shown consists of terminal device 102 and server 104. For example... Figure 1 As shown, server 104 is connected to terminal device 102 via a network and can be used to provide services (such as application services) to the terminal or clients installed on the terminal. A database can be set up on the server or independently of the server to provide data storage services for server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data processing services for server 104.

[0049] The aforementioned network may include, but is not limited to, at least one of the following: wired network, wireless network. The aforementioned wired network may include, but is not limited to, at least one of the following: wide area network, metropolitan area network, local area network. The aforementioned wireless network may include, but is not limited to, at least one of the following: Wi-Fi (Wireless Fidelity), Bluetooth. The terminal device 102 may not be limited to PC, mobile phone, tablet computer, smart air conditioner, smart range hood, smart refrigerator, smart oven, smart stove, smart washing machine, smart water heater, smart washing equipment, smart dishwasher, smart projector, smart TV, smart clothes rack, smart curtains, smart audio-visual equipment, smart socket, smart speaker, smart speaker box, smart fresh air equipment, smart kitchen and bathroom equipment, smart bathroom equipment, smart robot vacuum cleaner, smart window cleaning robot, smart mopping robot, smart air purifier, smart steam oven, smart microwave oven, smart water heater, smart air purifier, smart water dispenser, smart door lock, etc.

[0050] This embodiment provides a smart device control method based on multi-dimensional environmental perception, applied to the aforementioned device terminal. Figure 2 This is a flowchart of a smart device control method based on multi-dimensional environmental perception according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps:

[0051] Step S202: Generate the target adjustment requirements of the target object for the environmental parameters of the target space based on the object information of the target object, wherein the object information is used to indicate the comfort level of the target object in the target space;

[0052] Step S204: Detect the target device parameters of the reference smart device under the target adjustment requirement based on multiple target device information of each reference smart device in the set of smart devices in the target space. The multiple target device information is used to reflect the adaptation relationship between the environmental parameter adjustment attributes of the corresponding reference smart device and the target adjustment requirement from multiple feature dimensions. The target device parameters are used to indicate the probability that the target object will select the reference smart device under the target adjustment requirement.

[0053] Step S206: Select target smart devices from the smart device set whose target device parameters meet the target conditions, wherein the target conditions are determined based on the target object's usage habits of the smart devices in the smart device set;

[0054] Step S208: Control the target intelligent device to adjust the environmental parameters of the target space according to the target adjustment requirements.

[0055] Through the above steps, the target object's environmental parameter adjustment requirements are generated based on its comfort level in the target space. Further, the adaptation relationship between the environmental parameter adjustment attributes of the smart devices across multiple characteristic dimensions and the target adjustment requirements is comprehensively considered. This reflects the likelihood of the target object selecting each smart device under the target adjustment requirements. Furthermore, based on the target device parameters, target smart devices that meet the target conditions are selected from among the smart devices, enabling the target smart devices to effectively adapt to the target object's actual needs in the current control scenario. This technical solution solves the problem of low control efficiency of smart devices in related technologies, achieving the technical effect of improving the control efficiency of smart devices.

[0056] In the technical solution provided in step S202 above, the object information is information used for output that reflects the comfort level of the target object in the target space. The object information can be, but is not limited to, the user's output speech, which carries information about the user's comfort level in the target space. For example, if the user outputs the speech "It's so hot," it reflects that the user feels the current ambient temperature is high. In addition, the object information can also be physiological parameters reflecting the user's physiological state, reflecting the user's perception of the environment and their comfort level in the environment, such as body temperature data, heart rate, blood oxygen saturation, etc. This solution does not limit this aspect.

[0057] Optionally, in the embodiments of this application, the target adjustment requirement is used to indicate the environmental parameter conditions required by the target object. The target adjustment requirement may be, but is not limited to, the adjustment amount of the environmental parameters or the range of environmental parameters currently preferred by the target object. This solution does not limit this.

[0058] In the technical solution provided in step S204 above, the target device information may include, but is not limited to, at least two of the following: environmental adaptation parameters, energy efficiency parameters, response rate parameters, and user preference parameters. The environmental adaptation parameters are used to indicate the degree of deviation between the current environmental parameters in the target space and the environmental parameters expected by the user as indicated by the target adjustment requirements of the target object. The energy efficiency parameters are used to reflect the energy efficiency of the intelligent device during the environmental parameter adjustment process. The response rate is used to characterize the parameter adjustment rate of the intelligent device during the environmental parameter adjustment process. The user preference parameters are used to reflect the device usage of the target object in scenarios matching the target environmental parameter adjustment requirements in historical event segments.

[0059] Optionally, in this embodiment, the method of detecting target device parameters based on multiple target device information may include, but is not limited to, the following: filtering multiple target feature dimensions from the multiple feature dimensions based on multiple first device information of a first smart device used by the target object during a historical time period, wherein the first smart device is the smart device actually used by the target object after generating a reference adjustment requirement for the environment during the historical time period, the multiple first device information corresponds one-to-one with the multiple feature dimensions, and the influence of the device information of the target feature dimension on the target object's selection of smart devices is greater than a preset threshold; determining second device information of multiple target feature dimensions from the multiple target device information; obtaining first information parameters for each second device information, wherein the first information parameters are used to characterize the adaptability of the reference smart device to the target adjustment requirement under the corresponding target feature dimension; and performing weighted fusion calculation on the multiple first information parameters using the weight parameters of the target feature dimension to obtain the target device parameters.

[0060] The above method of filtering multiple target feature dimensions from multiple feature dimensions based on multiple first device information of the first smart device used by the target object within a historical time period can be as follows: for each reference feature dimension among the multiple feature dimensions, calculate the second information parameter of the first device information of the reference feature dimension of each first smart device, wherein the second information parameter is used to indicate the fit between the first smart device corresponding to the reference feature dimension and the reference adjustment requirement; detect the target dispersion among the second information parameters of the reference feature dimensions of the multiple first smart devices; and determine the reference feature dimension whose target dispersion is less than or equal to the target dispersion threshold as the target feature dimension.

[0061] In the technical solution provided in step S206 above, the target condition is used to characterize the target number of intelligent devices that the target object habitually uses when performing environmental control. The target intelligent device can be one or more. The method for selecting target intelligent devices whose target device parameters meet the target condition from the intelligent device set can be as follows: sort the intelligent devices in the intelligent device set in descending order of the target device parameters to obtain a target sequence; starting from the beginning of the target sequence, select the target number of intelligent devices as target intelligent devices.

[0062] Optionally, in this embodiment of the application, the configuration method of the target quantity may be to obtain a first number of smart devices used by the target object under the candidate adjustment requirements within a historical event segment, wherein the similarity between the candidate adjustment requirements and the target adjustment requirements is greater than or equal to the target similarity; and determine the target quantity based on the first quantity.

[0063] Furthermore, determining the target quantity based on the first quantity can be achieved by averaging multiple first quantities. Alternatively, determining the target quantity based on the first quantity can also involve: detecting the initiation time of each candidate adjustment request from the target object; detecting the time interval between the initiation time and the current time; assigning a first weight parameter to each candidate adjustment request according to the time interval, wherein the longer the time interval, the smaller the assigned first weight parameter; and using the first weight parameter to perform a weighted summation of multiple first quantities to obtain the target quantity.

[0064] As an optional instance, detecting the target device parameters of the reference intelligent device under the target adjustment requirement based on multiple target device information of each reference intelligent device in the set of intelligent devices in the target space includes:

[0065] The reference device parameters corresponding to each target device information of the reference smart device under the target adjustment requirement are determined. The reference device parameters indicate the adaptability of the reference smart device to the target adjustment requirement in the feature dimension to which the target device information belongs. The target device information includes at least two of the following: energy efficiency parameters, rate parameters, environmental adaptation parameters, and user preference parameters. The energy efficiency parameters indicate the energy efficiency during the adjustment of environmental parameters using the reference smart device. The rate parameters indicate the adjustment rate of the environmental parameters by the reference smart device. The environmental adaptation parameters indicate the difference between the current environmental parameters of the target space and the maximum and minimum parameters included in the target parameter range. The target parameter range is the range of parameters to which the target object needs to adjust its environmental parameters, as indicated by the target adjustment requirement. The user preference parameters indicate the frequency of the target object's use of the reference smart device in the target space before the current time.

[0066] The target device parameters are obtained by fitting multiple reference device parameters of the reference smart device using weight parameters. The weight parameters are used to indicate the influence of device information of each feature dimension in the multiple feature dimensions on the target object in selecting the corresponding reference smart device in the target adjustment requirement. The multiple reference device parameters correspond one-to-one with the multiple target device information.

[0067] Optionally, in this embodiment, the method of fitting the reference device parameters using weight parameters can be as follows: The target device parameters are obtained by weighting and summing multiple reference device parameters using weight parameters. Specifically, the environmental adaptability parameters, energy efficiency parameters, user preference parameters, and response speed parameters of each reference smart device are calculated separately; the four types of parameters are then weighted and summed using preset weight parameters to obtain the comprehensive score parameters of each reference smart device, which are then used as the target device parameters.

[0068] Optionally, in this embodiment, the method of fitting the reference device parameters using the weight parameters can be as follows: normalize the multiple reference device parameters respectively, mapping each reference device parameter to a preset value range; and use the weight parameters to perform a weighted operation on the normalized reference device parameters to obtain the target device parameters.

[0069] As an optional instance, the step of using the weight parameters of the target smart device to perform parameter fitting on multiple reference device parameters of the reference smart device to obtain the target device parameters includes:

[0070] The target device parameters are calculated using the following formula:

[0071] Scorei=W1 Ai+W2 Ei+W3 Pi+W4 Ri;

[0072] Wherein, Scori represents the target device parameter of the reference smart device; Ai indicates the difference between the current environmental parameters of the target space and the maximum and minimum parameters included in the target parameter range; the target parameter range is the range of parameters to which the target object needs to adjust its environmental parameters according to the target adjustment requirement; Ai is negatively correlated with the difference between the current environmental parameters of the target space and the maximum and minimum parameters included in the target parameter range; Ei indicates the energy efficiency of the reference smart device after adjusting the environmental parameters according to the target adjustment requirement; Ei is positively correlated with the energy efficiency of the reference smart device; Pi characterizes the frequency of the target object's use of the reference smart device in the target space before the current time; Pi is positively correlated with the frequency of the target object's use of the reference smart device; and Ri indicates the reference... The intelligent device adjusts the environmental parameters at a rate that meets the target adjustment requirements. There is a positive correlation between Ri and the adjustment rate of the reference intelligent device to the environmental parameters. The reference device parameters include Ai, Ei, Pi, and Ri. W1 indicates the degree of influence of the deviation between the current environmental parameters and the target parameter range on the target object's selection of the reference intelligent device. W2 indicates the degree of influence of energy efficiency on the target object's selection of the reference intelligent device. W3 indicates the degree of influence of the frequency of the target object's use of the reference intelligent device in the target space before the current time on the target object's selection of the reference intelligent device. W4 indicates the degree of influence of the intelligent device's adjustment rate to the environmental parameters on the target object's selection of the reference intelligent device. The weighting parameters include W1, W2, W3, and W4.

[0073] As an optional instance, after controlling the target intelligent device to adjust the environmental parameters of the target space according to the target adjustment requirements, the method further includes:

[0074] Detect the candidate smart devices actually used by the target object under the target adjustment requirements;

[0075] Obtain multiple candidate device information of the candidate smart device, wherein the multiple candidate device information is used to reflect the adaptation relationship between the environmental parameter adjustment attributes of the candidate smart device and the target adjustment requirements from the multiple feature dimensions, and the feature dimensions of the multiple candidate device information correspond one-to-one with the feature dimensions of the multiple target device information;

[0076] Detect the target similarity between multiple candidate device information and multiple target device information;

[0077] The weight parameters of the target device are adjusted based on the target similarity.

[0078] Optionally, in this embodiment, the weight parameter can be a dynamically adjustable parameter. After recommending a target smart device for the target object each time, the candidate smart devices actually used by the target object are detected. Based on the differences between the recommended target smart devices and the actual candidate smart devices used, the weight parameter is dynamically adjusted according to the device differences, ensuring the accuracy and reliability of the weight parameter.

[0079] As an optional instance, adjusting the weight parameters of the target device based on the target similarity includes:

[0080] For the target feature dimension among the plurality of feature dimensions, a weight adjustment amount corresponding to the sub-similarity between the candidate device information and the target device information of the target feature dimension is determined, wherein the target similarity includes the sub-similarity corresponding to each feature dimension among the plurality of feature dimensions;

[0081] The sub-weight parameters of the target feature dimension are adjusted using the weight adjustment amount, wherein the sub-weight parameters are used to indicate the influence of the device information of the corresponding feature dimension on the target object in selecting the reference smart device in the target adjustment requirement, and the weight parameters include the sub-weight parameters.

[0082] Optionally, in this embodiment, the adjustment amount of the weight parameter is related to the self-similarity between the candidate device information and the target device information of the corresponding feature dimension. The greater the similarity, the better the device information of the feature dimension can reflect the target object's need for using smart devices, and the higher the importance, the greater the increase in the weight parameter.

[0083] Optionally, in this embodiment, the weight parameter adjustment amount can be positive or negative. When it is positive, it indicates that the weight parameter of the corresponding feature dimension needs to be increased. When it is negative, it indicates that the weight parameter of the corresponding feature dimension needs to be decreased.

[0084] Furthermore, the method for determining the weight parameter adjustment amount can be as follows: compare the magnitude relationship between the sub-similarity and the preset similarity threshold, and determine the adjustment direction of the weight parameter based on the magnitude relationship. Specifically, when the sub-similarity is greater than the preset similarity, the adjustment direction is upward, and when the sub-similarity is less than the preset similarity, the adjustment direction is downward. Calculate the target absolute value of the difference between the sub-similarity and the preset similarity threshold, and determine the target parameter adjustment value corresponding to the target absolute value from the absolute values ​​and parameter adjustment values ​​that have a corresponding relationship. The weight parameter adjustment amount includes the adjustment direction and the parameter adjustment value.

[0085] As an optional instance, before selecting target smart devices from the set of smart devices whose target device parameters meet the target conditions, the method further includes:

[0086] Obtain the reference number of smart devices used by the target object during the historical time period when adjusting environmental parameters in the target space;

[0087] The target number of smart devices that the target smart device needs to control under the current target adjustment requirements is detected based on the reference number.

[0088] Configure the target conditions according to the target quantity.

[0089] Optionally, in this embodiment, the target condition is to select a target number of smart devices from the set of smart devices in descending order of target device parameters.

[0090] Optionally, in this embodiment, the method of detecting the target number of smart devices that the target smart device needs to control under the current target adjustment requirement based on the reference number can also be: the target number can be obtained by averaging the reference number.

[0091] Optionally, in this embodiment, the method for detecting the target number of smart devices that the target smart device needs to control under the current target adjustment requirement based on the reference quantity can also be: detecting the frequency parameter corresponding to each reference quantity; and determining the reference quantity whose frequency parameter is greater than or equal to a preset frequency parameter as the target quantity. That is, the frequency parameter of the reference quantity can reflect the user's selection habit for the number of smart devices. When the frequency parameter is larger, the user prefers to use the corresponding number of smart devices at the same time.

[0092] As an optional instance, generating the target adjustment requirements of the target object for the environmental parameters of the target space based on the object information of the target object includes one of the following:

[0093] The process involves: acquiring the target speech output by the target object, wherein the target speech carries feedback information regarding the comfort level of the target object in the target space, and the object information includes the target speech; adjusting the initial parameter range based on the feedback information to obtain a target parameter range, wherein the initial parameter range is the environmental parameters of the target space set by the target object before the current moment; and determining that the target adjustment requirement is a request from the target object to adjust the environmental parameters in the target space to the target parameter range.

[0094] Obtain the target physiological parameters of the target object in the target space, wherein the target physiological parameters are used to characterize the physiological characteristics of the target object, and the object information includes the target physiological parameters; adjust the initial parameter range according to the target physiological parameters to obtain the target parameter range, wherein the initial parameter range is the environmental parameters of the target space set by the target object before the current time; determine the target adjustment requirement as the target object requesting that the environmental parameters in the target space be adjusted to the target parameter range.

[0095] Optionally, in this embodiment, adjusting the initial parameter range according to the target feedback information to obtain the target parameter range includes: inputting the target feedback information into the target generation model to obtain the target parameter adjustment intention output by the target generation model, wherein the target generation model records the conversion relationship between the object's feedback information to the environment and the parameter adjustment intention of the environment parameters; adjusting the initial parameter range according to the parameter adjustment method indicated by the target parameter adjustment intention to obtain the target parameter range.

[0096] Optionally, in this embodiment, the target physiological parameters may include, but are not limited to, the target object's heart rate, body temperature, blood oxygen saturation, blood pressure, etc., and this solution does not limit them.

[0097] As an optional example, adjusting the initial parameter range according to the target physiological parameter to obtain the target parameter range includes:

[0098] Obtain the target parameter difference between the target physiological parameter and the preset physiological parameter threshold of the target object;

[0099] The target parameter adjustment amount corresponding to the target parameter difference is determined from the corresponding parameter differences and parameter adjustment amounts;

[0100] The initial parameter range is adjusted according to the target parameter adjustment amount to obtain the target parameter range.

[0101] This application aims to construct an intelligent voice control method and system based on multi-dimensional environmental perception, breaking through the limitations of traditional voice control that relies solely on semantic commands. By collecting real-time data on the status of home devices, environmental parameters (temperature, humidity, air quality, light intensity, time, and user location), and historical behavior data, a dynamic decision-making model is constructed. When the user issues vague or unspecified commands, the system automatically evaluates the comprehensive scores of multiple possible response schemes and selects the optimal action that best matches the user's true intentions and environmental needs, achieving a natural, efficient, energy-saving, and personalized voice interaction experience that is "what you think is what you get."

[0102] To address this issue, this application incorporates a speech processing layer for intent recognition, an environment-intent fusion decision engine, an execution and feedback layer, and an adaptive learning module.

[0103] Speech processing and intent recognition layer: Based on the ASR engine, speech is converted into text, input into an intent classification model (such as a lightweight BERT), output a set of candidate intents (such as "cooling", "dehumidifying", "ventilating", "comfort", etc.), and a confidence score is given.

[0104] Environment-Intent Fusion Decision Engine: Constructs a multi-dimensional scoring matrix. Based on the user's target adjustment needs for environmental parameters, the formula for calculating the "execution value score" (target device parameter) of each smart device under the target adjustment needs is as follows:

[0105] Scorei=w1 Ai+w2 Ei+w3 Pi+w4 Ri;

[0106] Scorei represents the target device parameters for the smart device.

[0107] Ai is the environmental comfort parameter (normalized score, 0~1): it is calculated based on the deviation between the current temperature and humidity and the user's comfort threshold (e.g., 22–26℃, 40–60%RH), and the greater the deviation, the more compensation is needed;

[0108] Ei is the energy efficiency parameter (normalized score, 0~1): Prioritize low power consumption schemes (e.g., opening windows for ventilation scores > turning on the air conditioner scores).

[0109] Pi is a user preference parameter (normalized score, 0~1): based on historical instruction learning (e.g., 80% of users choose to open the window rather than the air conditioner when the temperature is 30℃).

[0110] Ri is the rate parameter (normalized score, 0~1): it evaluates the equipment startup delay (e.g., the fresh air system starts up slower than the curtains).

[0111] w1 w4: A dynamically adjustable weighting coefficient that satisfies w1+w2+w3+w4=1. The initial value can be set to (0.4, 0.3, 0.2, 0.1).

[0112] The detailed calculation logic for the parameters of each dimension of device information is as follows:

[0113] (1) Environmental adaptation parameter Ai:

[0114] Definition: Measures the degree of deviation between current environmental parameters and the user's comfort threshold; the greater the deviation, the more compensation is needed.

[0115] Calculation steps:

[0116] Collect current environmental parameters: temperature T, humidity H, PM2.5 concentration Q, noise N, and light intensity L;

[0117] User comfort threshold range (configurable):

[0118] Temperature: [T] min ,T max For example, 22~26℃;

[0119] Humidity: [H min H max For example, 40%~60%;

[0120] PM2.5: Q max For example, 35 μg / m³;

[0121] Calculate the deviation of a single item (taking temperature as an example):

[0122] ;

[0123] Where T low T high Extreme environmental boundaries (such as 10℃ and 35℃) are used for normalization.

[0124] Similarly, calculate d H d Q d N d L .

[0125] The environmental adaptability score (Ai) is calculated by taking the maximum deviation across all dimensions, or a weighted average.

[0126] Ai=min(1,αT dT+αH dH+αQ dQ+…);

[0127] α represents the weight of each environmental parameter (e.g., temperature 0.5, humidity 0.3, air quality 0.2).

[0128] (2) Energy efficiency weight Ei:

[0129] Definition: Measures the energy efficiency of the devices / actions used to perform the intent, and encourages low-power solutions.

[0130] Table 1 is a calculation table of pre-calculated energy efficiency score (taking "ventilation" as an example) according to the embodiments of this application, as shown in Table 1:

[0131] Table 1

[0132]

[0133] Calculation formula:

[0134] ;

[0135] Where Pi is the estimated power of the preferred action to execute the intention, P min P max The power range for all candidate actions.

[0136] The calculation methods for other dimensions are similar and will not be elaborated here.

[0137] For example: When a user says "I feel so bored," the system detects:

[0138] Environmental data:

[0139] Temperature 28℃, humidity 75%, PM2.5=15, windows closed, air conditioner off, living room;

[0140] Candidate purpose: cooling, ventilation, dehumidification.

[0141] Table 2 is a device parameter calculation table according to an embodiment of this application. The table gives the scores (example values) of device information in each dimension, as shown in Table 2:

[0142] Table 2

[0143]

[0144] Decision: Select "Ventilation" (score 0.958), and execute "Open windows + low-speed fresh air".

[0145] Execution and Feedback Layer:

[0146] After executing the optimal action, the system will announce the result via voice (e.g., "The windows and fresh air have been opened to improve indoor air circulation") and record the decision result for online learning.

[0147] Adaptive learning module:

[0148] After each execution, record whether the user manually corrects the decision (e.g., "No, turn on the air conditioner") and feed this information back to the decision model to dynamically adjust the weights (w1–w4) to achieve increasing accuracy with repeated use.

[0149] Figure 3 This is an optional device control schematic diagram according to an embodiment of this application, such as... Figure 3 As shown: The user outputs feedback information on environmental parameters in the target space via voice, including the user's comfort level in the target space; further, based on the user's feedback information, the system detects the user's target adjustment needs for the environment; the system calculates multi-dimensional device information of each smart device through a positioning decision engine to obtain the target device parameters for each smart device; then, based on the target device parameters, the system selects target smart devices that meet the target conditions from all devices deployed in the target space; and finally, the system controls the target smart devices to perform environmental parameter adjustment operations according to the target adjustment needs.

[0150] In this embodiment of the application, the following method is adopted to realize intelligent device control based on the user's fuzzy intent:

[0151] 1. Multidimensional environmental parameters and voice intent fusion decision model: For the first time, non-semantic information such as temperature and humidity, air quality, device status, user location, and time are used as decision variables and jointly scored with voice intent to form a "context-intent" driven control logic, rather than based solely on semantic matching.

[0152] 2. Dynamically Adjustable Execution Value Scoring Formula: A weighted scoring mechanism consisting of four dimensions—environmental adaptability, energy efficiency weight, user preference, and response speed—is proposed. The weights can be adaptively adjusted online through user feedback to achieve a balance between personalization and universality.

[0153] 3. A decision-making paradigm based on “optimal response” rather than “most matching intent”: Unlike the traditional linear process of “identifying intent → executing corresponding action”, this invention constructs a multi-option evaluation system to proactively select the action that “best meets the user’s real needs”, even if the action is not directly mentioned in the instruction (e.g., “suffocating” → open the window, rather than “turn on the air conditioner”).

[0154] 4. Two-way closed-loop feedback mechanism for environmental perception and voice control: After the system executes, it collects and corrects behavior through voice feedback, forming a continuous learning closed loop to improve the long-term interaction accuracy.

[0155] 5. Lightweight deployment architecture: The decision model can be deployed on edge gateways (such as home AI boxes), supporting offline operation, ensuring privacy, and synchronizing user preference models with the cloud only when necessary.

[0156] The above embodiments achieve at least the following effects: 1. Significantly improved accuracy of intent understanding: By using environmental context to assist semantic disambiguation, the system resolves the problem of erroneous execution of ambiguous commands such as "It's too hot," "It's a bit stuffy," and "I want to be more comfortable," with an estimated improvement in system response accuracy of over 40%. 2. Achievement of energy saving and sustainable experience: The system intelligently selects low-power solutions (such as prioritizing ventilation over cooling), reducing household energy consumption by 15-30% while maintaining the same level of comfort, aligning with the trend of green smart homes. 3. Enhanced personalized and emotional interaction: The system can learn and adapt to different users' definitions of "comfort" (such as the elderly preferring dryness, and children preferring warmth), achieving "understanding your thoughts and doing what you need." 4. Reduced cognitive burden on users: There is no need to memorize device names or precise commands; users only need to express their feelings, and the system automatically completes complex decisions, truly achieving "seamless control." 5. Compatibility with existing ecosystems: The system can be integrated into mainstream smart home platforms, serving as an enhancement layer for intelligent voice control without requiring hardware replacement, demonstrating strong practicality.

[0157] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0158] Figure 4 This is a structural block diagram of an intelligent device control device based on multi-dimensional environmental perception, according to an embodiment of this application; as shown... Figure 4 As shown, it includes:

[0159] The generation module is used to generate the target adjustment requirements of the target object for the environmental parameters of the target space based on the object information of the target object, wherein the object information is used to indicate the comfort level of the target object in the target space;

[0160] The first detection module is used to detect the target device parameters of the reference intelligent device under the target adjustment requirement based on multiple target device information of each reference intelligent device in the set of intelligent devices in the target space. The multiple target device information is used to reflect the adaptation relationship between the environmental parameter adjustment attributes of the corresponding reference intelligent device and the target adjustment requirement from multiple feature dimensions. The target device parameters are used to indicate the probability of the target object selecting the reference intelligent device under the target adjustment requirement.

[0161] A filtering module is used to filter out target smart devices whose target device parameters meet the target conditions from the set of smart devices, wherein the target conditions are determined based on the target object's usage habits of the smart devices in the set of smart devices;

[0162] The control module is used to control the target intelligent device to adjust the environmental parameters of the target space according to the target adjustment requirements.

[0163] Through the above embodiments, the target object's environmental parameter adjustment requirements are generated based on its comfort level in the target space. Furthermore, the adaptation relationship between the environmental parameter adjustment attributes of multiple characteristic dimensions of the smart device and the target adjustment requirements is comprehensively considered. This reflects the likelihood of the target object selecting each smart device under the target adjustment requirements. Furthermore, based on the target device parameters, target smart devices that meet the target conditions are selected from among the smart devices, enabling the target smart devices to effectively adapt to the target object's actual needs in the current control scenario. By adopting the above technical solution, the problem of low control efficiency of smart devices in related technologies is solved, achieving the technical effect of improving the control efficiency of smart devices.

[0164] Optionally, the first detection module includes:

[0165] The first determining unit is configured to determine reference device parameters corresponding to each target device information of the reference smart device under the target adjustment requirement, wherein the reference device parameters are used to indicate the adaptability of the reference smart device to the target adjustment requirement in the feature dimension to which the target device information belongs, and the target device information includes at least two of the following: energy efficiency parameters, rate parameters, environmental adaptation parameters, and user preference parameters. The energy efficiency parameters are used to indicate the energy efficiency during the process of adjusting environmental parameters using the reference smart device. The rate parameters are used to indicate the adjustment rate of the environmental parameters by the reference smart device. The environmental adaptation parameters are used to indicate the difference between the current environmental parameters of the target space and the maximum and minimum parameters included in the target parameter range. The target parameter range is the parameter range to which the target object needs to adjust the environmental parameters as indicated by the target adjustment requirement. The user preference parameters are used to indicate the frequency of use of the reference smart device by the target object in the target space before the current time.

[0166] The fitting unit is used to fit multiple reference device parameters of the reference smart device using weight parameters to obtain the target device parameters. The weight parameters are used to indicate the influence of the device information of each feature dimension in the multiple feature dimensions on the target object in selecting the corresponding reference smart device in the target adjustment requirement. The multiple reference device parameters correspond one-to-one with the multiple target device information.

[0167] Optionally, the fitting unit is used for:

[0168] The target device parameters are calculated using the following formula:

[0169] Scorei=W1 Ai+W2 Ei+W3 Pi+W4 Ri;

[0170] Wherein, Scori represents the target device parameter of the reference smart device; Ai indicates the difference between the current environmental parameters of the target space and the maximum and minimum parameters included in the target parameter range; the target parameter range is the range of parameters to which the target object needs to adjust its environmental parameters according to the target adjustment requirement; Ai is negatively correlated with the difference between the current environmental parameters of the target space and the maximum and minimum parameters included in the target parameter range; Ei indicates the energy efficiency of the reference smart device after adjusting the environmental parameters according to the target adjustment requirement; Ei is positively correlated with the energy efficiency of the reference smart device; Pi characterizes the frequency of the target object's use of the reference smart device in the target space before the current time; Pi is positively correlated with the frequency of the target object's use of the reference smart device; and Ri indicates the reference... The intelligent device adjusts the environmental parameters at a rate that meets the target adjustment requirements. There is a positive correlation between Ri and the adjustment rate of the reference intelligent device to the environmental parameters. The reference device parameters include Ai, Ei, Pi, and Ri. W1 indicates the degree of influence of the deviation between the current environmental parameters and the target parameter range on the target object's selection of the reference intelligent device. W2 indicates the degree of influence of energy efficiency on the target object's selection of the reference intelligent device. W3 indicates the degree of influence of the frequency of the target object's use of the reference intelligent device in the target space before the current time on the target object's selection of the reference intelligent device. W4 indicates the degree of influence of the intelligent device's adjustment rate to the environmental parameters on the target object's selection of the reference intelligent device. The weighting parameters include W1, W2, W3, and W4.

[0171] Optionally, the device further includes:

[0172] The second detection module is used to detect the candidate smart devices actually used by the target object under the target adjustment requirements after the target smart device is controlled to adjust the environmental parameters of the target space according to the target adjustment requirements.

[0173] The first acquisition module is used to acquire multiple candidate device information of the candidate smart device, wherein the multiple candidate device information is used to reflect the adaptation relationship between the environmental parameter adjustment attributes of the candidate smart device and the target adjustment requirements from the multiple feature dimensions, and the feature dimensions of the multiple candidate device information correspond one-to-one with the feature dimensions of the multiple target device information.

[0174] The third detection module is used to detect the target similarity between the multiple candidate device information and the multiple target device information;

[0175] An adjustment module is used to adjust the weight parameters of the target device based on the target similarity.

[0176] Optionally, the adjustment module includes:

[0177] The second determining unit is configured to determine, for a target feature dimension among the plurality of feature dimensions, a weight adjustment amount corresponding to the sub-similarity between the candidate device information and the target device information of the target feature dimension, wherein the target similarity includes the sub-similarity corresponding to each feature dimension among the plurality of feature dimensions;

[0178] An adjustment unit is used to adjust the sub-weight parameters of the target feature dimension using the weight adjustment amount, wherein the sub-weight parameters are used to indicate the influence of the device information of the corresponding feature dimension on the target object in selecting the reference smart device in the target adjustment requirement, and the weight parameters include the sub-weight parameters.

[0179] Optionally, the device further includes:

[0180] The second acquisition module is used to acquire, before filtering out the target smart devices whose target device parameters meet the target conditions from the set of smart devices, the reference number of smart devices used by the target object when adjusting the environmental parameters in the target space during a historical time period.

[0181] The detection module is used to detect, based on the reference quantity, the target number of smart devices that the target smart device needs to control under the current target adjustment requirements;

[0182] A configuration module is used to configure the target conditions according to the target quantity.

[0183] Optionally, the generation module includes one of the following:

[0184] A first processing unit is configured to acquire target speech output by the target object, wherein the target speech carries feedback information on the comfort level of the target object in the target space, and the object information includes the target speech; adjust an initial parameter range according to the feedback information to obtain a target parameter range, wherein the initial parameter range is the environmental parameters of the target space set by the target object before the current moment; and determine that the target adjustment requirement is a request from the target object to adjust the environmental parameters in the target space to the target parameter range.

[0185] The second processing unit is configured to acquire target physiological parameters of the target object in the target space, wherein the target physiological parameters are used to characterize the physiological characteristics of the target object, and the object information includes the target physiological parameters; adjust an initial parameter range according to the target physiological parameters to obtain a target parameter range, wherein the initial parameter range is the environmental parameters of the target space set by the target object before the current time; and determine that the target adjustment requirement is that the target object requests to adjust the environmental parameters in the target space to the target parameter range.

[0186] Optionally, the second processing unit is used for:

[0187] Obtain the target parameter difference between the target physiological parameter and the preset physiological parameter threshold of the target object;

[0188] The target parameter adjustment amount corresponding to the target parameter difference is determined from the corresponding parameter differences and parameter adjustment amounts;

[0189] The initial parameter range is adjusted according to the target parameter adjustment amount to obtain the target parameter range.

[0190] Embodiments of this application also provide a storage medium including a stored program, wherein the program executes any of the above-described intelligent device control methods based on multi-dimensional environmental perception.

[0191] Optionally, in this embodiment, the storage medium may be configured to store program code for performing the following steps:

[0192] The target adjustment requirements of the target object for the environmental parameters of the target space are generated based on the object information of the target object, wherein the object information is used to indicate the comfort level of the target object in the target space;

[0193] Based on multiple target device information of each reference smart device in the set of smart devices in the target space, the target device parameters of the reference smart device under the target adjustment requirements are detected. The multiple target device information is used to reflect the adaptation relationship between the environmental parameter adjustment attributes of the corresponding reference smart device and the target adjustment requirements from multiple feature dimensions. The target device parameters are used to indicate the probability of the target object selecting the reference smart device under the target adjustment requirements.

[0194] Select target smart devices from the set of smart devices whose target device parameters meet the target conditions, wherein the target conditions are determined based on the target object's usage habits of the smart devices in the set of smart devices;

[0195] The target intelligent device is controlled to adjust the environmental parameters of the target space according to the target adjustment requirements.

[0196] Embodiments of this application also provide an electronic device, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the embodiments of the intelligent device control method based on multidimensional environmental perception described above.

[0197] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0198] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0199] The target adjustment requirements of the target object for the environmental parameters of the target space are generated based on the object information of the target object, wherein the object information is used to indicate the comfort level of the target object in the target space;

[0200] Based on multiple target device information of each reference smart device in the set of smart devices in the target space, the target device parameters of the reference smart device under the target adjustment requirements are detected. The multiple target device information is used to reflect the adaptation relationship between the environmental parameter adjustment attributes of the corresponding reference smart device and the target adjustment requirements from multiple feature dimensions. The target device parameters are used to indicate the probability of the target object selecting the reference smart device under the target adjustment requirements.

[0201] Select target smart devices from the set of smart devices whose target device parameters meet the target conditions, wherein the target conditions are determined based on the target object's usage habits of the smart devices in the set of smart devices;

[0202] The target intelligent device is controlled to adjust the environmental parameters of the target space according to the target adjustment requirements.

[0203] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0204] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0205] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0206] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for controlling intelligent devices based on multi-dimensional environmental perception, characterized in that, include: The target adjustment requirements of the target object for the environmental parameters of the target space are generated based on the object information of the target object, wherein the object information is used to indicate the comfort level of the target object in the target space; Based on multiple target device information of each reference smart device in the set of smart devices in the target space, the target device parameters of the reference smart device under the target adjustment requirements are detected. The multiple target device information is used to reflect the adaptation relationship between the environmental parameter adjustment attributes of the corresponding reference smart device and the target adjustment requirements from multiple feature dimensions. The target device parameters are used to indicate the probability of the target object selecting the reference smart device under the target adjustment requirements. Select target smart devices from the set of smart devices whose target device parameters meet the target conditions, wherein the target conditions are determined based on the target object's usage habits of the smart devices in the set of smart devices; The target intelligent device is controlled to adjust the environmental parameters of the target space according to the target adjustment requirements.

2. The method according to claim 1, characterized in that, The step of detecting the target device parameters of the reference intelligent device under the target adjustment requirement based on multiple target device information of each reference intelligent device in the set of intelligent devices in the target space includes: The reference device parameters corresponding to each target device information of the reference smart device under the target adjustment requirement are determined. The reference device parameters indicate the adaptability of the reference smart device to the target adjustment requirement in the feature dimension to which the target device information belongs. The target device information includes at least two of the following: energy efficiency parameters, rate parameters, environmental adaptation parameters, and user preference parameters. The energy efficiency parameters indicate the energy efficiency during the adjustment of environmental parameters using the reference smart device. The rate parameters indicate the adjustment rate of the environmental parameters by the reference smart device. The environmental adaptation parameters indicate the difference between the current environmental parameters of the target space and the maximum and minimum parameters included in the target parameter range. The target parameter range is the range of parameters to which the target object needs to adjust its environmental parameters, as indicated by the target adjustment requirement. The user preference parameters indicate the frequency of the target object's use of the reference smart device in the target space before the current time. The target device parameters are obtained by fitting multiple reference device parameters of the reference smart device using weight parameters. The weight parameters are used to indicate the influence of device information of each feature dimension in the multiple feature dimensions on the target object in selecting the corresponding reference smart device in the target adjustment requirement. The multiple reference device parameters correspond one-to-one with the multiple target device information.

3. The method according to claim 2, characterized in that, The step of fitting multiple reference device parameters of the reference smart device with the weight parameters of the target smart device to obtain the target device parameters includes: The target device parameters are calculated using the following formula: Scorei=W1 Ai+W2 Ei+W3 Pi+W4 Ri; Wherein, Scori represents the target device parameter of the reference smart device; Ai indicates the difference between the current environmental parameters of the target space and the maximum and minimum parameters included in the target parameter range; the target parameter range is the range of parameters to which the target object needs to adjust its environmental parameters according to the target adjustment requirement; Ai is negatively correlated with the difference between the current environmental parameters of the target space and the maximum and minimum parameters included in the target parameter range; Ei indicates the energy efficiency of the reference smart device after adjusting the environmental parameters according to the target adjustment requirement; Ei is positively correlated with the energy efficiency of the reference smart device; Pi characterizes the frequency of the target object's use of the reference smart device in the target space before the current time; Pi is positively correlated with the frequency of the target object's use of the reference smart device; and Ri indicates the reference... The intelligent device adjusts the environmental parameters at a rate that meets the target adjustment requirements. There is a positive correlation between Ri and the adjustment rate of the reference intelligent device to the environmental parameters. The reference device parameters include Ai, Ei, Pi, and Ri. W1 indicates the degree of influence of the deviation between the current environmental parameters and the target parameter range on the target object's selection of the reference intelligent device. W2 indicates the degree of influence of energy efficiency on the target object's selection of the reference intelligent device. W3 indicates the degree of influence of the frequency of the target object's use of the reference intelligent device in the target space before the current time on the target object's selection of the reference intelligent device. W4 indicates the degree of influence of the intelligent device's adjustment rate to the environmental parameters on the target object's selection of the reference intelligent device. The weighting parameters include W1, W2, W3, and W4.

4. The method according to claim 2, characterized in that, After controlling the target intelligent device to adjust the environmental parameters of the target space according to the target adjustment requirements, the method further includes: Detect the candidate smart devices actually used by the target object under the target adjustment requirements; Obtain multiple candidate device information of the candidate smart device, wherein the multiple candidate device information is used to reflect the adaptation relationship between the environmental parameter adjustment attributes of the candidate smart device and the target adjustment requirements from the multiple feature dimensions, and the feature dimensions of the multiple candidate device information correspond one-to-one with the feature dimensions of the multiple target device information; Detect the target similarity between multiple candidate device information and multiple target device information; The weight parameters of the target device are adjusted based on the target similarity.

5. The method according to claim 4, characterized in that, The step of adjusting the weight parameters of the target device based on the target similarity includes: For the target feature dimension among the plurality of feature dimensions, a weight adjustment amount corresponding to the sub-similarity between the candidate device information and the target device information of the target feature dimension is determined, wherein the target similarity includes the sub-similarity corresponding to each feature dimension among the plurality of feature dimensions; The sub-weight parameters of the target feature dimension are adjusted using the weight adjustment amount, wherein the sub-weight parameters are used to indicate the influence of the device information of the corresponding feature dimension on the target object in selecting the reference smart device in the target adjustment requirement, and the weight parameters include the sub-weight parameters.

6. The method according to claim 1, characterized in that, Before selecting target smart devices whose target device parameters meet the target conditions from the set of smart devices, the method further includes: Obtain the reference number of smart devices used by the target object during the historical time period when adjusting environmental parameters in the target space; The target number of smart devices that the target smart device needs to control under the current target adjustment requirements is detected based on the reference number. Configure the target conditions according to the target quantity.

7. The method according to claim 1, characterized in that, The step of generating the target adjustment requirements of the target object for the environmental parameters of the target space based on the object information of the target object includes one of the following: The process involves: acquiring the target speech output by the target object, wherein the target speech carries feedback information regarding the comfort level of the target object in the target space, and the object information includes the target speech; adjusting the initial parameter range based on the feedback information to obtain a target parameter range, wherein the initial parameter range is the environmental parameters of the target space set by the target object before the current moment; and determining that the target adjustment requirement is a request from the target object to adjust the environmental parameters in the target space to the target parameter range. Obtain the target physiological parameters of the target object in the target space, wherein the target physiological parameters are used to characterize the physiological characteristics of the target object, and the object information includes the target physiological parameters; adjust the initial parameter range according to the target physiological parameters to obtain the target parameter range, wherein the initial parameter range is the environmental parameters of the target space set by the target object before the current time; determine the target adjustment requirement as the target object requesting that the environmental parameters in the target space be adjusted to the target parameter range.

8. The method according to claim 7, characterized in that, The step of adjusting the initial parameter range according to the target physiological parameters to obtain the target parameter range includes: Obtain the target parameter difference between the target physiological parameter and the preset physiological parameter threshold of the target object; The target parameter adjustment amount corresponding to the target parameter difference is determined from the corresponding parameter differences and parameter adjustment amounts; The initial parameter range is adjusted according to the target parameter adjustment amount to obtain the target parameter range.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the method of any one of claims 1 to 8.

10. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the method of any one of claims 1 to 8 through the computer program.

Images