A home device control method and device based on scenario control

Abstract

The present invention discloses a home device control method and device based on scene control. The method includes: obtaining scene broadcast search information; the scene broadcast search information includes several home device information to be searched; based on the scene broadcast search information, determining target home device information; the target home device information includes several target controlled home device information; based on the target home device information, determining target device control information; the target device control information includes several target audio control information.

Description

Technical Field

[0001] The present invention relates to the field of control technologies, and particularly to a home device control method and device based on scenario control. Background Art

[0002] Classified by business forms, the scenarios of the KNX gateway itself include built-in scenarios in the gateway and user-defined scenarios. The user-defined scenarios are created by the user through the Zhuhui+ App, and the built-in scenarios are configured into the gateway through the configuration App. The built-in scenarios are further divided into KNX scenarios and configuration scenarios. The difference between the two is that one is implemented based on the KNX native protocol, and the other is to implement the scenario logic through the configuration App. Classified by scenario implementation, the scenarios of the KNX gateway can be divided into KNX protocol scenarios and custom protocol scenarios. The KNX protocol scenarios do not support modification. The principle is to send group addresses to the KNX bus. The custom protocol scenarios support modification. The principle is to record the devices and device functions that need to execute the scenario, and the function key-value pairs of the device model are sent during execution. When controlling scenarios, it is necessary to pay attention to the classification of scenario implementation. Since the custom protocol scenarios support user modification, there may be scenarios stored in the current gateway where the devices do not belong to this gateway. In the above situation, when the App controls the scenario, it is necessary to distinguish whether it is a KNX protocol scenario or a custom protocol scenario. If it is a KNX protocol scenario, the scenario Id can be directly sent for control. Otherwise, the App needs to disassemble the protocol content and then broadcast the control instruction. The control of devices and scenarios themselves is not complicated, but the devices within the local area network are complex. How to accurately control the corresponding devices, such as how to control sub-devices and how to control the KNX scenarios built into the gateway, etc., is one of the current research hotspots. Therefore, a home device control method and device based on scenario control are provided to improve the control efficiency and accuracy of home devices, and thus improve the user experience. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a home device control method and device based on scenario control, which is beneficial to improving the control efficiency and accuracy of home devices, and thus improving the user experience.

[0004] To solve the above technical problem, in the first aspect of the embodiments of the present invention, a home device control method based on scenario control is disclosed. The method includes:

[0005] Obtaining scenario broadcast search information; the scenario broadcast search information includes several home device information to be searched;

[0006] Based on the scenario broadcast search information, determining target home device information; the target home device information includes several target controlled home device information;

[0007] Determine target device control information based on the target home device information; the target device control information includes a number of target audio control information.

[0008] The second aspect of the embodiments of the present invention discloses a home device control device based on scene control, and the device includes:

[0009] An acquisition module, configured to acquire scene broadcast search information; the scene broadcast search information includes a number of home device information to be searched.

[0010] A first determination module, configured to determine target home device information based on the scene broadcast search information; the target home device information includes a number of target controlled home device information.

[0011] A second determination module, configured to determine target device control information based on the target home device information; the target device control information includes a number of target audio control information.

[0012] The third aspect of the present invention discloses another home device control device based on scene control, and the device includes:

[0013] A memory storing executable program code;

[0014] A processor coupled to the memory;

[0015] The processor calls the executable program code stored in the memory and executes some or all of the steps in the home device control method based on scene control disclosed in the first aspect of the embodiments of the present invention.

[0016] The fourth aspect of the present invention discloses a computer-readable storage medium. When the computer instructions stored in the computer-readable storage medium are called, they are used to execute some or all of the steps in the home device control method based on scene control disclosed in the first aspect of the embodiments of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 is a schematic diagram of a scene of a home device control system based on scene control provided by an embodiment of the present invention;

[0019] Figure 2 is a flowchart of a home device control method based on scene control disclosed in an embodiment of the present invention;

[0020] Figure 3 It is a schematic structural diagram of a home appliance control device based on scenario control disclosed in an embodiment of the present invention;

[0021] Figure 4 It is a schematic structural diagram of another home appliance control device based on scenario control disclosed in an embodiment of the present invention. Detailed implementation manners

[0022] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts belong to the scope of protection of the present invention.

[0023] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or equipment.

[0024] Referring to "embodiment" herein means that a specific feature, structure or characteristic described in connection with the embodiment can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0025] In this application, the term "exemplary" is used to mean "serving as an example, illustration, or instance". Any embodiment described as "exemplary" in this application is not necessarily to be construed as more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. In the following description, details are set forth for the purpose of explanation. It should be understood that those of ordinary skill in the art can recognize that this application can be implemented without these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of this application with unnecessary details. Therefore, this application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

[0026] It should be noted that since the method of the embodiment of this application is executed in a computer device, the processing objects of each computer device exist in the form of data or information. For example, time, which is actually time information. It can be understood that in subsequent embodiments, if dimensions, quantities, positions, etc. are mentioned, they are all corresponding data existences for the computer device to process, and specific details are not elaborated here.

[0027] A brief description of the artificial intelligence-related technologies that may be involved in this application is provided. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a way similar to human intelligence. Artificial intelligence also studies the design principles and implementation methods of various intelligent machines to enable the machines to have the functions of perception, reasoning, and decision-making.

[0028] Artificial intelligence technology is an interdisciplinary subject that involves a wide range of fields, including both hardware-level technologies and software-level technologies. The basic technologies of artificial intelligence generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation / interaction systems, and mechatronics. The software technologies of artificial intelligence mainly include several major directions such as computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0029] Computer Vision Technology (CV) Computer vision is a science that studies how to enable machines to "see". More specifically, it refers to using cameras and computers to replace human eyes for tasks such as object recognition and measurement in machine vision, and further performing graphics processing to make the images processed by the computer more suitable for human eyes to observe or be transmitted to instruments for detection. As a scientific discipline, computer vision studies related theories and technologies, and attempts to build artificial intelligence systems that can obtain information from images or multi-dimensional data. Computer vision technology usually includes image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content / behavior recognition, three-dimensional object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping, etc. technologies, and also includes common biometric recognition technologies such as face recognition and fingerprint recognition.

[0030] Single-modal information is data of only one type, such as one of the data information of text, image, audio, video, electromagnetic signal, etc. Multi-modal information is data information that includes at least two types of single-modal information. Further, multi-modal information is applicable to complex tasks that require integrating multiple information sources, such as sentiment analysis, robot interaction, autonomous driving, etc. By integrating information of multiple modalities, higher performance and accuracy can usually be achieved in tasks.

[0031] A large model refers to an artificial neural network model with a very large number of parameters. In the field of artificial intelligence, a large model usually refers to a model with hundreds of millions to trillions of parameters. The model usually needs to be trained on a large-scale dataset and requires a large amount of computing resources for optimization and adjustment. Large models are usually used to solve complex natural language processing, computer vision, and speech recognition tasks. Generative AI is a type of AI that can create new content and ideas, including conversations, stories, images, videos, and music. In the embodiments of this application, the large model can be large language models such as ChatGPT, BERT, XLNet, Zhipu Model, Claude, Moonshot AI Model, ChatGLM Model, Qianyitongwen Model, MiniMax Model, Spark Model, Llama Model, 360GPT Model, Qwen Model, Baichuan Model, Yunque Model, vivoLM Model, and Wenxin Yiyan, and the embodiments of this application do not make any limitations.

[0032] The embodiments of this application provide a home device control method, device, computer device, and computer-readable storage medium based on scene control, which will be described in detail below.

[0033] Please refer to Figure 1 , Figure 1A scene schematic diagram of the home device control system based on scene control provided by an embodiment of the present application. The home device control system based on scene control may include a computer device 100, and a home device control device based on scene control is integrated in the computer device 100, such as Figure 1 the computer device in

[0034] In an embodiment of the present application, the computer device 100 is mainly used to obtain scene broadcast search information; the scene broadcast search information includes several home device information to be searched;

[0035] Based on the scene broadcast search information, determine the target home device information; the target home device information includes several target controlled home device information;

[0036] Based on the target home device information, determine the target device control information; the target device control information includes several target audio control information.

[0037] It can improve the control efficiency and accuracy of home devices, thereby improving the user experience.

[0038] In an embodiment of the present application, the computer device 100 may be an independent server, or a server network or server cluster composed of servers. For example, the computer device 100 described in the embodiment of the present application includes, but is not limited to, a computer, a network host, a single network server, a set of multiple network servers, or a cloud server composed of multiple servers. Among them, the cloud server is composed of a large number of computers or network servers based on cloud computing.

[0039] It can be understood that the computer device 100 used in the embodiment of the present application may be a device that includes both receiving and transmitting hardware, that is, a device having receiving and transmitting hardware capable of performing two-way communication on a two-way communication link. Such devices may include: cellular or other communication devices, which have a single-line display or a multi-line display, or cellular or other communication devices without a multi-line display. Specifically, the computer device 100 may specifically be a desktop terminal or a mobile terminal, and the computer device 100 may specifically also be one of a mobile phone, a tablet computer, a laptop computer, etc.

[0040] Those skilled in the art can understand that Figure 1 the application environment shown in Figure 1 is only one application scenario of the solution of the present application, and does not constitute a limitation on the application scenario of the solution of the present application. Other application environments may also include more or fewer computer devices than those shown in Figure 1Only 1 computer device is shown. It can be understood that the home device control system based on scenario control may further include one or more other services, which are not specifically limited herein.

[0041] In addition, as Figure 1 shown, the home device control system based on scenario control may further include a memory 200 for storing data, such as image data, location information, etc.

[0042] It should be noted that Figure 1 the scenario schematic diagram of the home device control system based on scenario control shown is only an example. The home device control system and scenario described in the embodiments of the present application are for more clearly explaining the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those of ordinary skill in the art know that with the evolution of the home device control system based on scenario control and the emergence of new business scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0043] The present invention discloses a method and device for controlling home devices based on scenario control, which is beneficial to improving the control efficiency and accuracy of home devices, and further improving the user experience. The following will be described in detail respectively.

[0044] Embodiment 1

[0045] Please refer to Figure 2 , Figure 2 which is a flowchart of a method for controlling home devices based on scenario control disclosed in an embodiment of the present invention. Among them, Figure 2 the method for controlling home devices based on scenario control described is applied to a management system, such as a local server or a cloud server for management, etc., which is not limited in the embodiments of the present invention. As Figure 2 shown, the method for controlling home devices based on scenario control may include the following operations:

[0046] 101. Obtain scenario broadcast search information.

[0047] In the embodiments of the present invention, the scenario broadcast search information includes several home device information to be searched.

[0048] 102. Based on the scenario broadcast search information, determine the target home device information.

[0049] In the embodiments of the present invention, the target home device information includes several target controlled home device information.

[0050] 103. Based on the target home device information, determine the target device control information.

[0051] In the embodiments of the present invention, the target device control information includes a plurality of target audio control information.

[0052] It should be noted that the above-mentioned target audio control information represents the control instruction information that the smart home device can execute. Its form can be a binary instruction or other recognizable instructions, which are not limited in the embodiments of the present invention.

[0053] It should be noted that the above-mentioned home device information to be searched represents various types of smart home devices in the home scene, such as smart TVs, smart air conditioners, smart speakers, smart curtains, etc., which are not limited in the embodiments of the present invention.

[0054] It can be seen that implementing the home device control method based on scene control described in the embodiments of the present invention is beneficial to improving the control efficiency and accuracy of home devices, and thus improving the user experience.

[0055] In an alternative embodiment, the above-mentioned determining the target home device information based on the scene broadcast search information includes:

[0056] For any home device information to be searched in the scene broadcast search information and any smart home information to be controlled in the scene home library, use the feature matching model to calculate and process the search home feature information corresponding to the home device information to be searched and the smart home feature information corresponding to the smart home information to be controlled, and obtain the feature matching value corresponding to the smart home information to be controlled;

[0057] Among them, the feature matching model is:

[0058]

[0059] Among them, PPZ is the feature matching value; A is the search home feature information, B is the smart home feature information; L is the number of element values in the search home feature information; a i is the i-th element value in the search home feature information; b i is the i-th element value in the smart home feature information; x, y, and z are the first matching parameter, the second matching parameter, and the third matching parameter respectively;

[0060] Judge whether the feature matching value is less than or equal to the matching threshold, and obtain the matching judgment result corresponding to the smart home information to be controlled;

[0061] When the matching judgment result is yes, determine the smart home information to be controlled as a backup smart home information;

[0062] When the matching judgment result is no, end the processing flow corresponding to the smart home information to be controlled;

[0063] Based on the backup smart home information, determine the target controlled home device information corresponding to the home device information to be searched.

[0064] It should be noted that the above first matching parameter, second matching parameter, and third matching parameter are all values between [0, 1], and are not limited in the embodiments of the present invention. Further, the sum of the above first matching parameter, second matching parameter, and third matching parameter is 1, and is not limited in the embodiments of the present invention.

[0065] It should be noted that all possible smart home devices that the user intends to control can be found through the calculation and analysis of the above feature matching values. For example, if the user intends to control smart home devices of the TV category, then TVs such as Xiaomi Smart TV, TCL Smart TV, Hisense Smart TV, etc. will be included in the alternative range, and are not limited in the embodiments of the present invention.

[0066] It should be noted that the above matching threshold can be set by the user, or can be a default value given by the system, or can be obtained by averaging the historical matching thresholds, and is not limited in the embodiments of the present invention.

[0067] It can be seen that implementing the home device control method based on scenario control described in the embodiments of the present invention is beneficial to improving the control efficiency and control accuracy of home devices, and thus improving the user experience.

[0068] In another optional embodiment, based on the backup smart home information, determining the target controlled home device information corresponding to the home device information to be searched includes:

[0069] Judge whether the number of backup smart home information is equal to 1 to obtain a number judgment result;

[0070] When the number judgment result is yes, determine the backup smart home information as the target controlled home device information corresponding to the home device information to be searched;

[0071] When the number judgment result is no, determine the backup smart home information corresponding to the largest feature matching value among all the backup smart home information corresponding to the home device information to be searched as the target controlled home device information corresponding to the home device information to be searched.

[0072] It should be noted that the above analysis and judgment of the number of backup smart home information can ensure that each home device information to be searched can control the smart home device with the highest degree of association with it, and is not limited in the embodiments of the present invention.

[0073] It can be seen that implementing the home device control method based on scenario control described in the embodiments of the present invention is beneficial to improving the control efficiency and control accuracy of home devices, and thus improving the user experience.

[0074] In yet another alternative embodiment, based on the target home device information, the target device control information is determined, including:

[0075] For any target control home device information in the target home device information, establish a local area network communication channel between the smart mobile terminal and the smart home corresponding to the target control home device information;

[0076] Detect whether the smart mobile terminal displays the channel signal corresponding to the local area network communication channel to obtain a signal detection result;

[0077] When the signal detection result is negative, trigger the execution of establishing a local area network communication channel between the smart mobile terminal and the smart home corresponding to the target control home device information;

[0078] Detect whether a voice control message input by the user is received to obtain a voice detection result;

[0079] When the voice detection result is negative, obtain the prompt interval corresponding to the target control home device information;

[0080] Trigger the execution of detecting whether a voice control message input by the user is received at an interval of one prompt interval to obtain a voice detection result;

[0081] When the voice detection result is positive, based on the voice control information, determine the target audio control information corresponding to the target control home device information.

[0082] It should be noted that the above-mentioned establishment of the local area network communication channel between the smart mobile terminal and the smart home corresponding to the target control home device information can be established by Bluetooth, or a temporary wired connection established by the local area network, or a local area network communication channel established by other means, which is not limited in the embodiments of the present invention.

[0083] It should be noted that the above-mentioned channel signal indicates that the local area network communication channel has been established, such as a Bluetooth connection symbol, which is not limited in the embodiments of the present invention.

[0084] It should be noted that the above-mentioned voice control information represents a voice control instruction for controlling furniture devices, which is not limited in the embodiments of the present invention.

[0085] It should be noted that the above-mentioned prompt interval corresponding to the target control home device information is set according to the device type. Further, the setting of the prompt interval according to the device type is set according to the user's attention response degree to the device type. For example, the user has a higher attention response degree to the TV type and requires a faster feedback time, and the interval time should be shorter. For example, the prompt interval for the air conditioner type is 1 minute, and the prompt interval for the TV type is 30 seconds, which is not limited in the embodiments of the present invention.

[0086] It can be seen that implementing the home device control method based on scenario control described in the embodiments of the present invention is beneficial to improving the control efficiency and accuracy of home devices, and thus improving the user experience.

[0087] In yet another alternative embodiment, based on the voice control information, determining the target audio control information corresponding to the target controlled home device information includes:

[0088] Performing noise reduction processing on the voice control information to obtain first voice feature information;

[0089] Performing feature extraction processing on the first voice feature information to obtain second voice feature information;

[0090] Using the target voice conversion model to perform voice conversion processing on the second voice feature information to obtain the target audio control information corresponding to the target controlled home device information.

[0091] It should be noted that the above-mentioned feature extraction processing on the first voice feature information can be implemented based on a trained BERT model or based on a BiLSTM model, and the embodiments of the present invention do not make any limitations.

[0092] In this alternative embodiment, as an alternative implementation manner, the above-mentioned performing noise reduction processing on the voice control information to obtain first voice feature information includes:

[0093] Performing low-frequency filtering processing on the voice control information to obtain first processing feature information;

[0094] Performing time-domain feature extraction on the first processing feature information to obtain second processing feature information;

[0095] Judging whether the data length of the second processing feature information is equal to a preset length value to obtain a length judgment result;

[0096] When the length judgment result is negative, padding the data length to the length value at the rear of the second processing feature information with binary symbol 0 to obtain the first voice feature information;

[0097] When the length judgment result is positive, determining the second processing feature information as the first voice feature information.

[0098] It should be noted that the frequency of the above-mentioned low-frequency filtering processing does not exceed 3 Hz, and the embodiments of the present invention do not make any limitations.

[0099] It should be noted that the above-mentioned length value does not exceed 100, and the embodiments of the present invention do not make any limitations.

[0100] It can be seen that implementing the home device control method based on scenario control described in the embodiments of the present invention is beneficial to improving the control efficiency and accuracy of home devices, thereby enhancing the user experience.

[0101] In an alternative embodiment, the above-mentioned target voice conversion model is obtained based on the following steps:

[0102] Obtain initial training sample information; the initial training sample information includes a number of initial voice training samples;

[0103] Based on the initial training sample information, determine the target training sample information; the target training sample information includes a number of target training samples;

[0104] Use the target training sample information to train the initial voice conversion model to obtain a trained voice conversion model and training result information;

[0105] Use the loss function model to calculate and process the training result information to obtain the target training parameter information; the loss function model includes a first loss function model and a second loss function model;

[0106] Judge whether the target training parameter information meets the training termination condition to obtain a training judgment result;

[0107] When the training judgment result is no, use the trained voice conversion model to perform parameter update processing on the initial voice conversion model, and trigger the execution of determining the target training sample information based on the initial training sample information;

[0108] When the training judgment result is yes, determine the trained voice conversion model as the target voice conversion model.

[0109] It should be noted that the above-mentioned target voice conversion model is constructed by a Transformer encoder including multiple Attention mechanisms, and it can also be obtained by fine-tuning based on a large model. The embodiments of the present invention do not make any limitations.

[0110] It should be noted that the above-mentioned training termination condition includes that the loss function value and the historical loss function value in the target training parameter information converge, and / or the number of training times in the target training parameter information reaches 100 times. The embodiments of the present invention do not make any limitations.

[0111] It should be noted that the above-mentioned determining the target training sample information based on the initial training sample information is to randomly select a number of samples as the target training samples. The embodiments of the present invention do not make any limitations. Further, the number of the above-mentioned target training samples is not less than 10. The embodiments of the present invention do not make any limitations.

[0112] It should be noted that the above initial voice training samples can be marked by users' recordings or downloaded from the Internet, and the embodiments of the present invention do not make any limitations in this regard.

[0113] It can be seen that implementing the home appliance control method based on scenario control described in the embodiments of the present invention is beneficial to improving the control efficiency and accuracy of home appliances, thereby enhancing the user experience.

[0114] In another alternative embodiment, a loss function model is used to calculate and process the training result information to obtain target training parameter information, including:

[0115] Using a first loss function model to calculate and process the training result information to obtain first training parameter information;

[0116] Among them, the first loss function model is:

[0117]

[0118] In the formula, L1 represents the first training parameter information; YC kk represents the k-th predicted label in the training result information; SJ kk represents the true label corresponding to the k-th target training sample;

[0119] Using a second loss function model to calculate and process the training result information to obtain second training parameter information;

[0120] Performing a weighted sum processing on the first training parameter information and the second training parameter information to obtain the target training parameter information.

[0121] It should be noted that each of the above predicted labels corresponds to a true label, and the embodiments of the present invention do not make any limitations in this regard.

[0122] It should be noted that the above second loss function model is a cross-entropy loss function, and the embodiments of the present invention do not make any limitations in this regard.

[0123] It should be noted that the weight coefficients for performing the weighted sum processing on the first training parameter information and the second training parameter information are both 0.5, and the embodiments of the present invention do not make any limitations in this regard.

[0124] It can be seen that implementing the home appliance control method based on scenario control described in the embodiments of the present invention is beneficial to improving the control efficiency and accuracy of home appliances, thereby enhancing the user experience.

[0125] Embodiment 2

[0126] Please refer to Figure 3 , Figure 3It is a schematic structural diagram of a home device control device based on scenario control disclosed in an embodiment of the present invention. Among them, Figure 3 The described device can be applied to a management system, such as a local server or a cloud server for management, etc., which is not limited in the embodiments of the present invention. Such as Figure 3 As shown, the device may include:

[0127] An acquisition module 201, configured to acquire scenario broadcast search information; the scenario broadcast search information includes several to-be-searched home device information;

[0128] A first determination module 202, configured to determine target home device information based on the scenario broadcast search information; the target home device information includes several target controlled home device information;

[0129] A second determination module 203, configured to determine target device control information based on the target home device information; the target device control information includes several target audio control information.

[0130] It can be seen that implementing Figure 3 The described home device control device based on scenario control is beneficial to improving the control efficiency and accuracy of home devices, thereby improving the user experience.

[0131] In another optional embodiment, as Figure 3 As shown, the first determination module 202 determines the target home device information based on the scenario broadcast search information, including:

[0132] For any to-be-searched home device information in the scenario broadcast search information and any to-be-controlled smart home information in the scenario home library, the search home feature information corresponding to the to-be-searched home device information and the smart home feature information corresponding to the to-be-controlled smart home information are calculated and processed by using a feature matching model to obtain a feature matching value corresponding to the to-be-controlled smart home information;

[0133] Among them, the feature matching model is:

[0134]

[0135] Among them, PPZ is the feature matching value; A is the search home feature information, B is the smart home feature information; L is the number of element values in the search home feature information; a i is the i-th element value in the search home feature information; b i is the i-th element value in the smart home feature information; x, y, and z are the first matching parameter, the second matching parameter, and the third matching parameter respectively;

[0136] Determine whether the feature matching value is less than or equal to the matching threshold, and obtain the matching judgment result corresponding to the smart home information to be controlled;

[0137] When the matching judgment result is yes, determine the smart home information to be controlled as a backup smart home information;

[0138] When the matching result is no, end the processing flow corresponding to the smart home information to be controlled;

[0139] Based on the backup smart home information, determine the target controlled home device information corresponding to the home device information to be searched.

[0140] It can be seen that implementing Figure 3 The home device control device based on scene control described is beneficial to improving the control efficiency and accuracy of home devices, thereby improving the user experience.

[0141] In another alternative embodiment, as Figure 3 shown, the first determination module 202 determines the target controlled home device information corresponding to the home device information to be searched based on the backup smart home information, including:

[0142] Judge whether the number of backup smart home information is equal to 1, and obtain the quantity judgment result;

[0143] When the quantity judgment result is yes, determine the backup smart home information as the target controlled home device information corresponding to the home device information to be searched;

[0144] When the quantity judgment result is no, determine the backup smart home information corresponding to the largest feature matching value among all the backup smart home information corresponding to the home device information to be searched as the target controlled home device information corresponding to the home device information to be searched.

[0145] It can be seen that implementing Figure 3 The home device control device based on scene control described is beneficial to improving the control efficiency and accuracy of home devices, thereby improving the user experience.

[0146] In another alternative embodiment, as Figure 3 shown, the second determination module 203 determines the target device control information based on the target home device information, including:

[0147] For any target controlled home device information in the target home device information, establish a local area network communication channel between the smart mobile terminal and the smart home corresponding to the target controlled home device information;

[0148] Detect whether the smart mobile terminal displays the channel signal corresponding to the local area network communication channel, and obtain the signal detection result;

[0149] When the signal detection result is negative, trigger the execution of establishing a local area network communication channel for the smart home corresponding to the information of the target controlled home device with the smart mobile terminal;

[0150] Detect whether voice control information input by the user is received to obtain a voice detection result;

[0151] When the voice detection result is negative, obtain the corresponding prompt interval time for the information of the target controlled home device;

[0152] Trigger the execution of detecting whether voice control information input by the user is received at an interval of one prompt interval time to obtain a voice detection result;

[0153] When the voice detection result is positive, based on the voice control information, determine the target audio control information corresponding to the information of the target controlled home device.

[0154] It can be seen that implementing Figure 3 the described home device control device based on scenario control is beneficial to improving the control efficiency and accuracy of home devices, thereby improving the user experience.

[0155] In another alternative embodiment, as Figure 3 shown, the second determination module 203 determines the target audio control information corresponding to the information of the target controlled home device based on the voice control information, including:

[0156] Perform noise reduction processing on the voice control information to obtain first voice feature information;

[0157] Perform feature extraction processing on the first voice feature information to obtain second voice feature information;

[0158] Use the target voice conversion model to perform voice conversion processing on the second voice feature information to obtain the target audio control information corresponding to the information of the target controlled home device.

[0159] It can be seen that implementing Figure 3 the described home device control device based on scenario control is beneficial to improving the control efficiency and accuracy of home devices, thereby improving the user experience.

[0160] In another alternative embodiment, as Figure 3 shown, the target voice conversion model is obtained by the second determination module 203 performing the following steps:

[0161] Obtain initial training sample information; the initial training sample information includes a number of initial voice training samples;

[0162] Based on the initial training sample information, determine the target training sample information; the target training sample information includes a number of target training samples;

[0163] Use the target training sample information to train the initial speech conversion model to obtain a trained speech conversion model and training result information;

[0164] Use the loss function model to calculate and process the training result information to obtain target training parameter information; the loss function model includes a first loss function model and a second loss function model;

[0165] Judge whether the target training parameter information meets the training termination condition to obtain a training judgment result;

[0166] When the training judgment result is no, use the trained speech conversion model to perform parameter update processing on the initial speech conversion model, and trigger the execution of determining the target training sample information based on the initial training sample information;

[0167] When the training judgment result is yes, determine the trained speech conversion model as the target speech conversion model.

[0168] It can be seen that implementing Figure 3 The described home device control device based on scenario control is beneficial to improving the control efficiency and accuracy of home devices, thereby improving the user experience.

[0169] In another alternative embodiment, as Figure 3 shown, the second determination module 203 uses the loss function model to calculate and process the training result information to obtain target training parameter information, including:

[0170] Use the first loss function model to calculate and process the training result information to obtain first training parameter information;

[0171] Among them, the first loss function model is:

[0172]

[0173] In the formula, L1 represents the first training parameter information; YC kk represents the k-th predicted label in the training result information; SJ kk represents the true label corresponding to the k-th target training sample;

[0174] Use the second loss function model to calculate and process the training result information to obtain second training parameter information;

[0175] Perform weighted summation processing on the first training parameter information and the second training parameter information to obtain target training parameter information.

[0176] It can be seen that implementingFigure 3 The described home appliance control device based on scenario control is conducive to improving the control efficiency and accuracy of home appliances, thereby enhancing the user experience.

[0177] Embodiment III

[0178] Please refer to Figure 4 , Figure 4 which is a schematic structural diagram of another home appliance control device based on scenario control disclosed in the embodiments of the present invention. Among them, Figure 4 the described device can be applied to a management system, such as a local server or a cloud server for management, etc., which is not limited in the embodiments of the present invention. As Figure 4 shown, the device may include:

[0179] A memory 301 storing executable program code;

[0180] A processor 302 coupled to the memory 301;

[0181] The processor 302 calls the executable program code stored in the memory 301 to execute the steps in the home appliance control method based on scenario control described in Embodiment I.

[0182] Embodiment IV

[0183] The embodiments of the present invention disclose a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to execute the steps in the home appliance control method based on scenario control described in Embodiment I.

[0184] Embodiment V

[0185] The embodiments of the present invention disclose a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the steps in the home appliance control method based on scenario control described in Embodiment I.

[0186] The above-described device embodiments are merely illustrative. The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0187] Through the specific descriptions of the above embodiments, those skilled in the art can clearly understand that each implementation can be realized by means of software plus a necessary general hardware platform. Of course, it can also be realized by hardware. Based on such an understanding, the above technical solutions, 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 can be stored in a computer-readable storage medium, which includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc memories, magnetic disk memories, tape memories, or any other medium that can be used to carry or store data and is computer-readable.

[0188] Finally, it should be noted that: What is disclosed in an embodiment of a home appliance control method and device based on scenario control of the present invention is only a preferred embodiment of the present invention, and is only used to illustrate the technical solution of the present invention, rather than to limit it; Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: They can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A home device control method based on scenario control, characterized in that, The method includes: Obtaining scene broadcast search information; the scene broadcast search information includes several home device information to be searched; Based on the scene broadcast search information, determining target home device information; the target home device information includes several target controlled home device information; Based on the target home device information, determining target device control information; the target device control information includes several target audio control information; Among them, the determining the target home device information based on the scene broadcast search information includes: For any of the home device information to be searched in the scene broadcast search information, and for any of the smart home information to be controlled in the scene home library, using a feature matching model to calculate and process the search home feature information corresponding to the home device information to be searched and the smart home feature information corresponding to the smart home information to be controlled, to obtain a feature matching value corresponding to the smart home information to be controlled; Among them, the feature matching model is: Wherein, PPZ is the feature matching value; A is the searched home feature information, B is the smart home feature information; L is the number of element values in the searched home feature information; a i is the i-th element value in the searched home feature information; b i is the i-th element value in the smart home feature information; x, y, and z are the first matching parameter, the second matching parameter, and the third matching parameter respectively; Judging whether the feature matching value is less than or equal to a matching threshold, to obtain a matching judgment result corresponding to the smart home information to be controlled; When the matching judgment result is yes, determining the smart home information to be controlled as a backup smart home information; When the matching judgment result is no, ending the processing flow corresponding to the smart home information to be controlled; Based on the backup smart home information, determining the target controlled home device information corresponding to the home device information to be searched.

2. The home appliance control method based on scenario control according to claim 1, wherein The determining the target controlled home device information corresponding to the home device information to be searched based on the backup smart home information includes: Judging whether the number of the backup smart home information is equal to 1, to obtain a number judgment result; When the number judgment result is yes, determining the backup smart home information as the target controlled home device information corresponding to the home device information to be searched; When the number judgment result is no, determining the backup smart home information corresponding to the maximum feature matching value among all the backup smart home information corresponding to the home device information to be searched as the target controlled home device information corresponding to the home device information to be searched.

3. The home appliance control method based on scenario control according to claim 1, wherein The determining the target device control information based on the target home device information includes: For any of the target controlled home device information in the target home device information, establishing a local area network communication channel between the smart mobile terminal and the smart home corresponding to the target controlled home device information; Detecting whether the smart mobile terminal displays a channel signal corresponding to the local area network communication channel, to obtain a signal detection result; When the signal detection result is no, triggering the execution of establishing a local area network communication channel between the smart mobile terminal and the smart home corresponding to the target controlled home device information; Detecting whether voice control information input by the user is received, to obtain a voice detection result; When the voice detection result is no, obtaining a prompt interval time corresponding to the target controlled home device information; Triggering the execution of detecting whether voice control information input by the user is received at an interval of one such prompt interval time, to obtain a voice detection result; When the voice detection result is "yes", based on the voice control information, determine the target audio control information corresponding to the target control home device information.

4. The home appliance control method based on scenario control according to claim 3, wherein, The determining the target audio control information corresponding to the target control home device information based on the voice control information includes: Perform noise reduction processing on the voice control information to obtain first voice feature information; Perform feature extraction processing on the first voice feature information to obtain second voice feature information; Use a target voice conversion model to perform voice conversion processing on the second voice feature information to obtain the target audio control information corresponding to the target control home device information.

5. The home device control method based on scenario control according to claim 4, wherein The target voice conversion model is obtained based on the following steps: Obtain initial training sample information; the initial training sample information includes a number of initial voice training samples; Based on the initial training sample information, determine target training sample information; the target training sample information includes a number of target training samples; Use the target training sample information to train an initial voice conversion model to obtain a trained voice conversion model and training result information; Use a loss function model to perform calculation processing on the training result information to obtain target training parameter information; The loss function model includes a first loss function model and a second loss function model; Judge whether the target training parameter information meets the training termination condition to obtain a training judgment result; When the training judgment result is "no", use the trained voice conversion model to perform parameter update processing on the initial voice conversion model, and trigger the execution of determining the target training sample information based on the initial training sample information; When the training judgment result is "yes", determine the trained voice conversion model as the target voice conversion model.

6. The home appliance control method based on scenario control according to claim 5, characterized in that, The using the loss function model to perform calculation processing on the training result information to obtain target training parameter information includes: Use the first loss function model to perform calculation processing on the training result information to obtain first training parameter information; Wherein, the first loss function model is: Wherein, L1 represents the first training parameter information; YC kk represents the kk-th prediction label in the training result information; SJ kk represents the true label corresponding to the kk-th target training sample; Use the second loss function model to perform calculation processing on the training result information to obtain second training parameter information; Perform weighted summation processing on the first training parameter information and the second training parameter information to obtain target training parameter information.

7. A home appliance control device based on scene control, characterized in that, The device includes: An acquisition module, configured to acquire scenario broadcast search information; the scenario broadcast search information includes a number of home devices to be searched for information; A first determination module, configured to determine target home device information based on the scenario broadcast search information; the target home device information includes a number of target control home device information; A second determination module, configured to determine target device control information based on the target home device information; the target device control information includes a number of target audio control information; Wherein, the determining the target home device information based on the scenario broadcast search information includes: For any of the to-be-searched home device information in the scenario broadcast search information, and for any of the to-be-controlled smart home information in the scenario home library, use the feature matching model to calculate and process the search home feature information corresponding to the to-be-searched home device information and the smart home feature information corresponding to the to-be-controlled smart home information, so as to obtain the feature matching value corresponding to the to-be-controlled smart home information; Among them, the feature matching model is: Among them, PPZ is the feature matching value; A is the searched home feature information, B is the smart home feature information; L is the number of element values in the searched home feature information; a i is the i-th element value in the searched home feature information; b i is the i-th element value in the smart home feature information; x, y, and z are the first matching parameter, the second matching parameter, and the third matching parameter respectively; Judge whether the feature matching value is less than or equal to the matching threshold, and obtain the matching judgment result corresponding to the to-be-controlled smart home information; When the matching judgment result is yes, determine the to-be-controlled smart home information as a standby smart home information; When the matching judgment result is no, end the processing flow corresponding to the to-be-controlled smart home information; Based on the standby smart home information, determine the target control home device information corresponding to the to-be-searched home device information.

8. A home appliance control device based on scene control, characterized in that, The device includes: A memory storing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory and executes the home device control method based on scenario control according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, which are used to execute the home device control method based on scenario control according to any one of claims 1-6 when the computer instructions are called.

Images