Scene control method and control device of smart home system, and storage medium

Abstract

The invention discloses a scene control method of a smart home system, a scene control device of the smart home system and a storage medium. The method comprises the following steps: acquiring scene feature information of a target indoor space; sequentially determining matching conditions of various preset scenes in at least two preset scenes and the scene feature information, and obtaining at least two recognition results; determining a target scene in the at least two preset scenes according to the at least two recognition results; and controlling at least one intelligent electric appliance in the target indoor space to operate according to the target scene. The invention aims to improve the scene recognition accuracy and improve the equipment control accuracy.

Description

Technical Field

[0001] The present invention relates to the field of smart home technology, and in particular to a scene control method, a scene control device and a storage medium of a smart home system. Background Art

[0002] In the application process of smart home, many scenes can be recognized for indoor environment, and the operation of equipment can be controlled based on the recognized scenes. Among them, smart home system generally has multiple scenes pre-set, and it identifies whether the monitoring parameters corresponding to the indoor environment meet the conditions corresponding to each scene in a certain order. After identifying the matching scene, it will stop identifying other scenes, which can easily lead to inaccurate scene recognition results and affect the accuracy of equipment control. Summary of the invention

[0003] The main purpose of the present invention is to provide a scene control method for a smart home system, a scene control device for a smart home system and a storage medium, aiming to improve the accuracy of scene recognition and the accuracy of device control.

[0004] To achieve the above object, the present invention provides a scene control method for a smart home system, the scene control method for the smart home system comprising the following steps:

[0005] Obtain scene feature information of the target indoor space;

[0006] sequentially determining a match between each of at least two preset scenes and the scene feature information to obtain at least two recognition results;

[0007] Determining a target scene among the at least two preset scenes according to the at least two recognition results;

[0008] At least one smart appliance in the target indoor space is controlled to operate according to the target scene.

[0009] Optionally, the step of sequentially determining a matching situation between each preset scene in at least two preset scenes and the scene feature information to obtain at least two recognition results includes:

[0010] It is sequentially identified whether the preset scene information of each preset scene in the at least two preset scenes matches the scene feature information to obtain the at least two recognition results.

[0011] Optionally, the step of sequentially determining a matching situation between each preset scene in at least two preset scenes and the scene feature information to obtain at least two recognition results includes:

[0012] When there are user setting parameters corresponding to the preset scene, determining preset scene information corresponding to the preset scene according to the user setting parameters, and sequentially identifying whether the preset scene information of each preset scene in the at least two preset scenes matches the scene feature information, to obtain the at least two recognition results;

[0013] When there are no user setting parameters corresponding to the preset scenes, the scene feature information is respectively input into the scene recognition model corresponding to each of the preset scenes to obtain the output result of each scene recognition model, the recognition result includes the output result, and the scene recognition model is generated based on machine learning.

[0014] Optionally, the step of sequentially determining a matching situation between each preset scene in at least two preset scenes and the scene feature information to obtain at least two recognition results includes:

[0015] The scene feature information is respectively input into the scene recognition model corresponding to each of the preset scenes to obtain the output result of each of the scene recognition models, wherein the recognition result includes the output result, and the scene recognition model is generated based on machine learning.

[0016] Optionally, the scene recognition model includes a first model or a second model, and the step of respectively inputting the scene feature information into the scene recognition model corresponding to each of the preset scenes to obtain an output result corresponding to each of the scene recognition models includes:

[0017] Inputting the scene feature information to the first model corresponding to each of the preset scenes respectively, obtaining a first output result corresponding to each of the first models, the first output result including whether the current scene represented by the scene feature information is the corresponding preset scene;

[0018] Alternatively, the scene feature information is respectively input into a second model corresponding to each of the preset scenes to obtain a second output result corresponding to each of the second models, wherein the second output result includes a probability that the current scene represented by the scene feature information is the corresponding preset scene.

[0019] Optionally, the step of respectively inputting the scene feature information into a scene recognition model corresponding to each of the preset scenes to obtain an output result corresponding to each of the scene recognition models comprises:

[0020] Acquire the location type of the target indoor space;

[0021] When the place type is the first type, inputting the scene feature information into the first model corresponding to each of the preset scenes respectively, and obtaining a first output result corresponding to each of the first models;

[0022] When the place type is the second type, inputting the scene feature information into the second model corresponding to each of the preset scenes respectively, and obtaining a second output result corresponding to each of the second models;

[0023] Wherein, a first similarity between the at least two preset scenes corresponding to the first type is smaller than a second similarity between the at least two preset scenes corresponding to the second type.

[0024] Optionally, the step of determining a target scene among the at least two preset scenes according to the at least two recognition results includes:

[0025] When there is more than one recognition result satisfying the preset condition among the at least two recognition results, determining the target scene according to the priorities or predicted probabilities corresponding to all the preset scenes corresponding to all the recognition results satisfying the preset condition;

[0026] Among them, the preset condition indicates that the preset scene matches the scene feature information, and the predicted probability is the probability that the current scene represented by the scene feature information is the corresponding preset scene.

[0027] Optionally, the recognition result includes whether the current scene represented by the scene feature information is a corresponding preset scene, and the preset condition includes that the recognition result is that the current scene represented by the scene feature information is a corresponding preset scene;

[0028] Alternatively, the recognition result includes the predicted probability, and the preset condition includes that the predicted probability is greater than the first preset probability.

[0029] Optionally, after the step of determining the target scene among the at least two preset scenes according to the at least two recognition results, the method further includes:

[0030] Outputting switching prompt information corresponding to the target scene;

[0031] When confirmation information corresponding to the target scene is received, the step of controlling the operation of at least one smart appliance in the target indoor space according to the target scene is executed.

[0032] Optionally, after the step of determining the target scene among the at least two preset scenes according to the at least two recognition results, the method further includes:

[0033] When the predicted probability corresponding to the target scene is greater than a second preset probability, executing the step of controlling the operation of at least one smart appliance in the target indoor space according to the target scene;

[0034] When the predicted probability corresponding to the target scene is less than or equal to the second preset probability, outputting switching prompt information corresponding to the target scene, and when receiving confirmation information corresponding to the target scene, executing the step of controlling the operation of at least one smart appliance in the target indoor space according to the target scene;

[0035] The predicted probability is the probability that the current scene represented by the scene feature information is the target scene.

[0036] In addition, in order to achieve the above-mentioned purpose, the present application also proposes a scene control device for a smart home system, wherein the scene control device for the smart home system comprises: a memory, a processor, and a scene control program for the smart home system stored on the memory and executable on the processor, wherein when the scene control program for the smart home system is executed by the processor, the steps of the scene control method for the smart home system as described in any one of the above items are implemented.

[0037] In addition, in order to achieve the above-mentioned purpose, the present application also proposes a storage medium, on which a scene control program of a smart home system is stored. When the scene control program of the smart home system is executed by a processor, the steps of the scene control method of the smart home system as described in any of the above items are implemented.

[0038] The present invention proposes a scene control method for a smart home system. The method determines the matching situation of each preset scene in at least two preset scenes and the scene feature information of a target indoor space in turn, obtains at least two recognition results, determines the target scene according to the at least two recognition results, and controls the operation of at least one smart appliance in the target indoor space according to the target scene. In this process, the recognition of the target scene comprehensively considers the matching situation of all preset scenes, and there will be no unrecognized scenes. The accuracy of the scene recognition results can be effectively improved, and accurate regulation of the smart appliances based on the recognized target scenes can be ensured, thereby effectively improving the accuracy of device control. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A schematic diagram of the hardware structure involved in the operation of an embodiment of a smart appliance of the present invention;

[0040] Figure 2 A schematic diagram of a flow chart of an embodiment of a scene control method for a smart home system of the present invention;

[0041] Figure 3 A schematic diagram of a flow chart of another embodiment of a scene control method for a smart home system of the present invention;

[0042] Figure 4 A schematic diagram of a flow chart of another embodiment of a scene control method for a smart home system of the present invention;

[0043] Figure 5 The figure is a flow chart of another optional embodiment of the scene control method of the smart home system of the present invention.

[0044] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0045] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0046] An embodiment of the present invention provides a scene control device 1 for a smart home system.

[0047] In an embodiment of the present invention, the scene control device 1 of the smart home system is applied to the smart home system, and the smart home system includes one or more smart appliances 2 in the target space. Figure 1 , the scene control device 1 of the smart home system is communicatively connected with each smart appliance 2 in the smart home system.

[0048] In this embodiment, the target space is the whole house. In other embodiments, the target space can also be a combination of preset designated areas or a certain area, such as a room or a living room.

[0049] Among them, more than one smart appliance 2 can be connected based on a connection module to form a smart home system, and the connection module may include WIFI, Bluetooth, infrared, wiring, etc.

[0050] The smart home system may include a perception module 3, which is connected to the scene control device 1 of the smart home system. The perception module 3 can be used to receive perception information. In this embodiment, the perception module 3 may include an environmental sensor, a human sensor, and an equipment monitoring module, etc., to detect perception information such as environmental information, human information, and equipment information.

[0051] The environmental sensor includes a sensor for detecting at least one environmental parameter such as temperature, humidity, PM2.5, carbon dioxide, formaldehyde, etc.

[0052] The human body sensor may include at least one sensor such as an infrared sensor, a radar sensor, and a WIFI sensor for detecting human body information. The human body information includes at least one information such as the number of people, the position of the person, breathing, heartbeat, and body movement amplitude.

[0053] The environmental information detected by the equipment monitoring module includes at least one type of information such as power on / off status, setting mode, setting temperature, etc.

[0054] In the embodiment of the present invention, the scene control device 1 of the smart home system can be a server that is independent of the smart appliance 2 and connected to the smart appliance 2, or it can be a functional module built into the smart appliance 2. Figure 1 The scene control device 1 of the smart home system includes: a processor 1001, such as a CPU, a memory 1002, and a timer 1003. Among them, these components are connected and communicated through a communication bus. The memory 1002 can be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1002 can also be a storage device independent of the aforementioned processor 1001.

[0055] Those skilled in the art will understand that Figure 1 The device structure shown in the figure does not constitute a limitation of the device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0056] like Figure 1 As shown, the memory 1002 as a computer storage medium may include a scene control program of the smart home system.

[0057] exist Figure 1 In the device shown, the processor 1001 can be used to call the scene control program of the smart home system stored in the memory 1002, and execute the relevant steps of the scene control method of the smart home system in the following embodiments.

[0058] An embodiment of the present invention further provides a scene control method for a smart home system, which is applied to the scene control device of the smart home system.

[0059] Reference Figure 2 , an embodiment of a scene control method of a smart home system of the present application is proposed. In this embodiment, the scene control method of the smart home system includes:

[0060] Step S10, obtaining scene feature information of the target indoor space;

[0061] The target indoor space is an indoor space equipped with a smart home system.

[0062] The scene feature information is information related to the scene requirements in the target indoor space. The scene feature information can be detected by sensors in the target indoor space and / or collected by modules outside the target indoor space.

[0063] Scene feature information includes but is not limited to at least one of the following information: environmental information, human information, weather information, regional information, and time information. Among them, environmental information includes indoor environmental information (such as indoor temperature, indoor humidity, indoor PM2.5, etc.) and / or outdoor environmental information (such as outdoor temperature, outdoor humidity, outdoor PM2.5, etc.). Human information includes at least one information such as the number of people, personnel position, breathing, heartbeat, and body movement amplitude. Weather information includes sunny days, rainy days, foggy days, or snowy days. Regional information includes country regions, provinces and cities, geographical divisions (such as the north, the south, North China, Huanghuai, etc.) and building climate zones (such as hot summer, warm winter, cold, etc.). Time information includes year and month, day and night time periods (such as morning or afternoon or day or night, etc.), solar terms (such as white dew, light snow, etc.), etc.

[0064] Step S20, sequentially determining the matching conditions between various preset scenes in at least two preset scenes and the scene feature information, and obtaining at least two recognition results;

[0065] The preset scene can be a scene set by the user or set according to the user's needs before the system leaves the factory. The at least two preset scenes may include but are not limited to at least two of the following scenes: a rainy day scene, a sleeping scene, a dining scene, a meeting scene, etc.

[0066] Among them, at least two preset scenes can be pre-set fixed scenes; or, at least two preset scenes are obtained here according to the place type of the target indoor space, and different place types correspond to different at least two preset scenes; or, at least two preset scenes are obtained here according to the types of all smart appliances in the target indoor space, and so on.

[0067] The matching situation includes the matching degree or whether there is a match. The recognition result may include but is not limited to one of the following: the current scene represented by the scene feature information matches the preset scene, the current scene represented by the scene feature information does not match the preset scene, the current scene represented by the scene feature information is the preset scene, the current scene represented by the scene feature information is not the preset scene, the probability that the current scene represented by the scene feature information is the preset scene, etc.

[0068] The preset scene can be set with corresponding recognition rules (using conditional recognition or algorithm model recognition, etc.). In this embodiment, the recognition rules corresponding to different preset scenes are the same. In other embodiments, the recognition rules corresponding to different preset scenes may be different.

[0069] The scene feature information is analyzed according to the recognition rules corresponding to each preset scene to obtain the matching situation between the current scene represented by the scene feature information and the preset scene to obtain the corresponding recognition result. Each preset scene corresponds to one recognition result, and the number of preset scenes is the same as the number of recognition results.

[0070] Step S30, determining a target scene among the at least two preset scenes according to the at least two recognition results;

[0071] The target scene is the scene that best matches the current scene of the target indoor space among at least two preset scenes. The number of the determined target scenes may be one.

[0072] In one implementation, the at least two recognition results including a current scene matching a corresponding preset scene or a current scene being a corresponding preset scene are determined as target recognition results, and the target scene is determined according to the target recognition results corresponding to the preset scenes.

[0073] In another implementation, the recognition result in which the probability that the current scene corresponds to the preset scene is greater than the preset probability among at least two recognition results is determined as the target recognition result, and the target scene is determined according to the preset scene corresponding to the target recognition result.

[0074] In yet another implementation, the recognition result among at least two recognition results having the highest probability that the current scene is a preset scene is determined as the target recognition result, and the target scene is determined according to the preset scene corresponding to the target recognition result.

[0075] Step S40: controlling the operation of at least one smart appliance in the target indoor space according to the target scene.

[0076] Each preset scene sets a corresponding preset scene parameter, and different preset scenes correspond to different preset scene parameters. The preset scene parameters include the preset electrical appliances to be turned on and the preset operating parameters of the preset electrical appliances. The number of preset electrical appliances included in the preset scene parameters can be adapted to one or more than one according to the corresponding scene requirements. Based on this, the preset electrical appliances in the preset scene parameters corresponding to the target scene are determined as target electrical appliances, and the preset operating parameters corresponding to the preset electrical appliances are the target operating parameters, and all target electrical appliances corresponding to the target operating parameters are controlled to operate according to the corresponding target operating parameters.

[0077] For example, when the target scene is the return of south wind scene, the corresponding target appliance is the air conditioner, which can be controlled to run at the maximum dehumidification gear; when the target scene is the plum rain scene, the corresponding target appliance is the air conditioner, which can be controlled to run at the maximum dehumidification gear; when the target scene is the sleep scene, the corresponding target appliance is the air conditioner, which can be controlled to increase the set temperature according to the preset amplitude at preset time intervals until the total running time of the target scene reaches the target time; when the target scene is the dining scene, the corresponding target appliance is the air conditioner, which can be controlled to run at a preset set temperature (for example, 24 degrees) and control the air conditioner to turn on fresh air, and so on.

[0078] Furthermore, after step S40, the process may return to step S10.

[0079] A scene control method for a smart home system proposed in an embodiment of the present invention determines in turn the matching situation of each preset scene in at least two preset scenes with scene feature information of a target indoor space, obtains at least two recognition results, determines the target scene according to the at least two recognition results, and controls the operation of at least one smart appliance in the target indoor space according to the target scene. In this process, the recognition of the target scene comprehensively considers the matching situation of all preset scenes, and there will be no unrecognized scenes. The accuracy of the scene recognition results can be effectively improved, and accurate regulation of the smart appliances based on the recognized target scenes can be ensured, thereby effectively improving the accuracy of device control.

[0080] In this embodiment, the above step S10 is performed during the process of controlling the operation of the smart appliance according to one of at least two preset scenes. When it is recognized that the target scene is different from the scene in which the smart scene is running, automatic switching of the scene can be achieved.

[0081] In other embodiments, step S10 may also be executed when the smart appliance is turned on.

[0082] Further, based on the above embodiment, another embodiment of the scene control method of the smart home system of the present application is proposed. Figure 3 , the step S20 comprises:

[0083] Step S21, sequentially identifying whether the preset scene information of each preset scene in the at least two preset scenes matches the scene feature information, and obtaining the at least two recognition results.

[0084] The preset scene information is specifically the preset conditions that the scene feature information of the corresponding preset scene needs to meet, and the preset scene information may include the target value range and / or target information that the scene feature information needs to reach. The preset scene information can be set by the user according to actual needs, or it can be obtained by the system analyzing the user needs according to certain rules.

[0085] The preset scene information includes but is not limited to at least one of the following information: preset environment information, preset human information, preset weather information, preset regional information, and preset time information. Among them, the preset environment information includes preset indoor environment information (such as the target interval required to be reached for indoor temperature, indoor humidity, indoor PM2.5, etc.) and / or preset outdoor environment information (such as the target interval required to be reached for outdoor temperature, outdoor humidity, outdoor PM2.5, etc.). The preset human body information includes at least one information such as the preset number of people, the preset personnel position range, the preset breathing rate range, the preset heartbeat range, and the preset body movement range. The preset weather information includes sunny days, rainy days, foggy days, or snowy days. The preset regional information includes preset countries and regions, preset provinces and cities, preset geographical divisions (such as the north, the south, North China, Huanghuai, etc.), and building climate zones (such as hot summer, warm winter, cold, etc.). The preset time information includes the target range required to be met by the year and month, the target range required to be met by the day and night period (such as morning or afternoon or day or night, etc.), and the target solar terms (such as Bailu, Xiaoxue, etc.).

[0086] The preset scene information of each preset scene may include preset conditions corresponding to at least two preset dimensions in the corresponding preset scene, and the at least two preset dimensions corresponding to different preset scenes may be different. The corresponding sub-information in the scene feature information is extracted according to the at least two preset dimensions corresponding to the preset scene, and it is determined whether each sub-information meets the preset conditions of the corresponding preset dimension, and the sub-judgment result corresponding to each preset dimension is obtained, and the corresponding recognition result is determined according to all the sub-judgment results corresponding to all the preset dimensions corresponding to each preset scene.

[0087] For example, the first preset scene is the return of the south wind scene, and the preset scene information includes: South China, time from February to April, temperature 10 degrees higher than the previous three days, humidity ≥ 80%; the second preset scene is the plum rain scene, and the preset scene information includes the southern region, time from March to May, humidity ≥ 70%. Based on this, when the current scene feature information includes Guangzhou, April 25, temperature 28, and humidity 86%, the matching result corresponding to the first preset scene is that the current scene matches the first preset scene, and the matching result corresponding to the second preset scene is that the current scene matches the second preset scene.

[0088] In this embodiment, the scene feature information is matched with the preset scene information of each preset scene respectively to ensure that the obtained recognition result can accurately reflect the matching degree between the current scene represented by the scene feature information and the preset scene, which is conducive to further improving the accuracy of the scene recognition result.

[0089] Further, based on any of the above embodiments, another embodiment of the scene control method of the smart home system of the present application is proposed. Figure 4 , the step S20 comprises:

[0090] Step S22, respectively input the scene feature information into the scene recognition model corresponding to each of the preset scenes to obtain the output result of each of the scene recognition models, wherein the recognition result includes the output result, and the scene recognition model is generated based on machine learning.

[0091] A scene recognition model is set corresponding to each preset scene. The scene recognition model is generated based on machine learning and may include at least one type of a machine learning classification model, a machine learning regression model, and a machine learning clustering model. In this embodiment, the types of scene recognition models corresponding to different preset scenes are the same. In other embodiments, the types of scene recognition models corresponding to different preset scenes may be different.

[0092] The output result of the scene recognition model includes the probability that the current scene represented by the scene feature information is the corresponding preset scene, or that the current scene represented by the scene feature information is not the corresponding preset scene, or that the current scene represented by the scene feature information is the corresponding preset scene.

[0093] Before the current moment, a large amount of scene sample data in indoor space scenes is collected, the scene sample data is classified according to the preset scenes and the corresponding scene identification is performed, the positive sample data and negative sample data corresponding to each preset scene are determined based on the scene identification, and the target model corresponding to the preset scene is obtained according to the training preset machine learning model, and the target model can be used as the scene recognition model corresponding to the preset scene. Among them, the positive sample data is the sample data belonging to the corresponding preset scene, and the negative sample data is the sample data that does not belong to the corresponding preset scene.

[0094] In this embodiment, the scene recognition model includes a first model or a second model, the first model is used to identify whether the current scene represented by the scene feature information is the corresponding preset scene, and the second model is used to identify the probability that the current scene represented by the scene feature information is the corresponding preset scene.

[0095] In one implementation of this embodiment, the scene feature information is respectively input into the first model corresponding to each of the preset scenes, and a first output result corresponding to each of the first models is obtained, wherein the first output result includes whether the current scene represented by the scene feature information is the corresponding preset scene. In this embodiment, the first model is a machine learning classification model. In other embodiments, the first model may also be a machine learning model that outputs the same type of results.

[0096] For example, the preset scene is a sleep scene, and the scene feature information includes: 24 o'clock, breathing rate 14 times / minute, and heart rate 75 times / minute. The scene feature information is input into the first model corresponding to the sleep scene. The output result of the first model is yes, then the corresponding recognition result is that the current scene represented by the scene feature information is a sleep scene.

[0097] In another implementation of this embodiment, the scene feature information is respectively input into the second model corresponding to each of the preset scenes to obtain a second output result corresponding to each of the second models, and the second output result includes the probability that the current scene represented by the scene feature information is the corresponding preset scene. In this embodiment, the second model is a machine learning regression model. In other embodiments, the second model may also be a machine learning model that outputs the same type of results.

[0098] For example, the preset scene is a dinner scene, and the scene feature information includes: time 11:00-14:00, number of people >8 minutes, and the scene feature information is input into the second model corresponding to the dinner scene. The probability that the current scene represented by the scene feature information in the output result of the second model is a dinner scene is 0.7, and the corresponding recognition result is 0.7.

[0099] In this embodiment, scene feature information is input into the machine learning model of each preset scene for matching, ensuring that the obtained recognition result can accurately reflect the degree of matching between the current scene represented by the scene feature information and the preset scene, which is conducive to further improving the accuracy of the scene recognition result.

[0100] Further, in this embodiment, step S22 includes: obtaining the place type of the target indoor space; when the place type is the first type, respectively inputting the scene feature information into the first model corresponding to each of the preset scenes, and obtaining the first output result corresponding to each of the first models; when the place type is the second type, respectively inputting the scene feature information into the second model corresponding to each of the preset scenes, and obtaining the second output result corresponding to each of the second models; wherein the first similarity between the at least two preset scenes corresponding to the first type is less than the second similarity between the at least two preset scenes corresponding to the second type.

[0101] In one implementation of this embodiment, the place type is obtained by obtaining parameters input by a user. In another implementation of this embodiment, the place type can be determined by obtaining an image of the target indoor space and based on the types of objects placed in the image.

[0102] The place type includes a living room, a bedroom, a game room, a dining room, a conference room, etc. Different place types have different at least two preset scenes. The at least two preset scenes corresponding to the first type are different from the at least two preset scenes corresponding to the second type.

[0103] In at least two preset scenes corresponding to the first type, similarities between the preset scenes are determined respectively, and a first similarity is determined based on all the determined similarities. In at least two preset scenes corresponding to the second type, similarities between the preset scenes are determined respectively, and a second similarity is determined based on all the determined similarities.

[0104] In this embodiment, when the similarity between at least two preset scenes corresponding to the target indoor space is small, the first model is used to perform scene matching analysis, which is beneficial to ensure the accuracy of scene recognition while improving the efficiency of scene recognition; when the similarity between at least two preset scenes corresponding to the target indoor space is large, the second model is used to perform scene matching analysis, which is beneficial to accurately distinguish similar scenes and further improve the accuracy of scene recognition.

[0105] In other embodiments, one of the first model and the second model can be determined as the scene recognition model according to user-set parameters, and the scene feature information can be input into the scene recognition model corresponding to each of the preset scenes to obtain the corresponding recognition result.

[0106] Furthermore, in the present embodiment, after the step of controlling the operation of at least one smart appliance in the target indoor space according to the target scene, it also includes: when receiving a scene correction instruction input by the user, correcting the scene recognition model according to the preset scene corresponding to the scene correction instruction, the scene feature information and the target scene.

[0107] Furthermore, in this embodiment, after S10, it also includes: obtaining the operating status parameters of all electrical appliances in the smart home system corresponding to the target indoor space during the scene feature information detection process, and correcting the target model trained based on the scene sample data according to the operating status parameters and the preset scene to obtain a scene recognition model corresponding to the preset scene.

[0108] Further, based on any of the above embodiments, another embodiment of the scene control method of the smart home system of the present application is proposed. In this embodiment, step S20 includes: when there are user setting parameters corresponding to the preset scene, determining the preset scene information corresponding to the preset scene according to the user setting parameters, and executing step S21; when there are no user setting parameters corresponding to the preset scene, executing step S22.

[0109] Among them, the preset scenes with corresponding user setting parameters can determine the corresponding preset scene information according to the user setting parameters, and the preset scenes without corresponding user setting parameters can read the pre-stored scene information in the memory as the corresponding preset scene information. In other words, the preset scene information corresponding to each preset scene can be determined according to the user setting parameters, or the preset scene information corresponding to some preset scenes can be set by the user, and the preset scene information corresponding to other preset scenes can be pre-stored parameters.

[0110] In this embodiment, the accuracy of scene recognition using a scene recognition model generated by machine learning will be higher than the accuracy of scene recognition using preset scene information comparison. Based on this, using a machine learning model for scene recognition when the user has not set the scene by themselves is beneficial to improving the accuracy of the scene recognition results; when the user sets the scene by themselves, the pre-trained machine learning model will deviate from user needs. At this time, performing scene recognition according to the preset scene information set by the user is beneficial to ensuring that the target scene obtained by scene recognition can accurately match user needs, thereby further improving the accuracy of scene recognition.

[0111] Further, based on any of the above embodiments, another optional embodiment of the scene control method of the smart home system of the present application is proposed. Figure 5 , step S30 comprises:

[0112] Step S31, when there is more than one recognition result that meets the preset condition among the at least two recognition results, determining the target scene according to the priorities or predicted probabilities corresponding to all the preset scenes corresponding to all the recognition results that meet the preset condition;

[0113] Among them, the preset condition indicates that the preset scene matches the scene feature information, and the predicted probability is the probability that the current scene represented by the scene feature information is the corresponding preset scene.

[0114] In one implementation of this embodiment, the recognition result includes whether the current scene represented by the scene feature information is a corresponding preset scene, and the preset condition includes that the recognition result is that the current scene represented by the scene feature information is a corresponding preset scene. The recognition result here can be the recognition result obtained by the analysis in step S21 above or the recognition result obtained based on the analysis of the first model above.

[0115] In another implementation of this embodiment, the recognition result includes the predicted probability, and the preset condition includes that the predicted probability is greater than the first preset probability. The recognition result here may be the recognition result obtained by the analysis in step S22 above.

[0116] In this embodiment, the preset scene corresponding to the recognition result that meets the preset conditions is the candidate scene, and the preset scene with the highest priority among all the candidate scenes is used as the target scene; the preset scene with the highest probability among all the candidate scenes is used as the target scene.

[0117] The priority level corresponding to each candidate scene may be a preset fixed priority level, or may be variable according to actual conditions. For example, the priority level of each candidate scene may be determined according to the different combined features of all the determined candidate scenes, and the priorities of the candidate scenes may be different if the scenes included in all the determined candidate scenes are different. For another example, the priority level corresponding to each current candidate scene may be determined according to the types of all the smart appliances that are not turned on in the current scene in the smart home system.

[0118] The predicted probability corresponding to the alternative scene can be obtained by inputting the scene feature information into the above-mentioned second model for analysis. When the recognition result includes the predicted probability, the predicted probability in the device result can be directly used.

[0119] In this embodiment, when there is more than one preset scene matching the current scene represented by the scene feature information based on at least two recognition results, the target scene ultimately used for scene control of the smart home system is determined based on the priority or predicted probability corresponding to the preset scene that meets the preset conditions, thereby ensuring that when the determined target scene controls the operation of the smart appliances, the environmental state of the target indoor space can be accurately matched with user needs, thereby further improving the accuracy of scene recognition and device control.

[0120] In other embodiments, all alternative scenes may also be used as target scenes, and corresponding preset scene parameters of more than one target scenes are obtained, and a set of preset electrical appliances contained in more than one preset scene parameters is used as a set of target electrical appliances to be turned on. When there is a first electrical appliance in the target electrical appliance set, the first electrical appliance is an electrical appliance with different preset operating parameters in different target scenes. The weight value of the preset scene parameter corresponding to each target scene is determined according to the priority or predicted probability corresponding to each target scene, and all preset operating parameters corresponding to the first electrical appliance are weighted averaged according to the weight value to obtain the target operating parameters corresponding to the first electrical appliance. When the target electrical appliance set includes a second electrical appliance, the second electrical appliance has corresponding preset operating parameters in a single target scene or the corresponding preset operating parameters in different target scenes are the same, then the preset operating parameters corresponding to the second electrical appliance are used as the target operating parameters corresponding to the second electrical appliance.

[0121] Further, based on any of the above embodiments, another optional embodiment of the scene control method of the smart home system of the present application is proposed. In this embodiment, after step S30, it also includes: outputting switching prompt information corresponding to the target scene; when receiving confirmation information corresponding to the target scene, executing the step of controlling the operation of at least one smart appliance in the target indoor space according to the target scene.

[0122] The switching prompt information can be output in at least one of the following ways: text, sound, vibration, light, etc.

[0123] The switching prompt information is used to prompt the user to confirm whether to switch the current operating scene of the smart appliance to the target scene.

[0124] The confirmation information is input by the user based on the switching prompt information.

[0125] In addition, when cancellation information corresponding to the target scene is received or confirmation information corresponding to the target scene is not received within a preset time period, the smart appliance can be controlled to maintain operation in the current state.

[0126] In this embodiment, after the target scene is determined, the user is prompted by switching prompt information. When the confirmation information input by the user is received, the smart appliance is switched to the target scene for operation. This is conducive to ensuring the accuracy of the operation control of the smart appliance and ensuring that the state of the target indoor space can accurately meet user needs.

[0127] In other embodiments, after step S30, step S40 may also be directly executed.

[0128] Furthermore, in the present embodiment, after step S30, it also includes: when the predicted probability corresponding to the target scene is greater than the second preset probability, executing the step of controlling the operation of at least one smart appliance in the target indoor space according to the target scene; when the predicted probability corresponding to the target scene is less than or equal to the second preset probability, outputting the switching prompt information corresponding to the target scene, and when the confirmation information corresponding to the target scene is received, executing the step of controlling the operation of at least one smart appliance in the target indoor space according to the target scene; wherein the predicted probability is the probability that the current scene represented by the scene feature information is the target scene.

[0129] The second preset probability here is greater than the first preset probability mentioned above.

[0130] In this embodiment, when the current scene is most likely the target scene, the smart appliance directly switches to the target scene; when the current scene is less likely to be the target scene, a switching prompt message is output, and after receiving the confirmation message, the smart appliance switches to the target scene, which is conducive to ensuring the accuracy of the scene switching of the smart appliance and ensuring the accurate satisfaction of user needs.

[0131] In addition, an embodiment of the present invention further proposes a storage medium, on which a scene control program of a smart home system is stored. When the scene control program of the smart home system is executed by a processor, the relevant steps of any embodiment of the scene control method of the smart home system as described above are implemented.

[0132] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0133] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0134] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, smart appliance, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0135] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A scene control method for a smart home system, characterized in that: The scene control method of the smart home system comprises the following steps: Obtain scene feature information of the target indoor space; sequentially determining a match between each of at least two preset scenes and the scene feature information to obtain at least two recognition results; Determining a target scene among the at least two preset scenes according to the at least two recognition results; At least one smart appliance in the target indoor space is controlled to operate according to the target scene.

2. The scene control method of the smart home system according to claim 1, characterized in that: The step of sequentially determining the matching conditions between various preset scenes in at least two preset scenes and the scene feature information to obtain at least two recognition results comprises: It is sequentially identified whether the preset scene information of each preset scene in the at least two preset scenes matches the scene feature information to obtain the at least two recognition results.

3. The scene control method of the smart home system according to claim 2, characterized in that: The step of sequentially determining the matching conditions between various preset scenes in at least two preset scenes and the scene feature information to obtain at least two recognition results comprises: When there are user setting parameters corresponding to the preset scene, determining preset scene information corresponding to the preset scene according to the user setting parameters, and sequentially identifying whether the preset scene information of each preset scene in the at least two preset scenes matches the scene feature information, to obtain the at least two recognition results; When there are no user setting parameters corresponding to the preset scenes, the scene feature information is respectively input into the scene recognition model corresponding to each of the preset scenes to obtain the output result of each scene recognition model, the recognition result includes the output result, and the scene recognition model is generated based on machine learning.

4. The scene control method of the smart home system according to claim 1, characterized in that: The step of sequentially determining the matching conditions between various preset scenes in at least two preset scenes and the scene feature information to obtain at least two recognition results comprises: The scene feature information is respectively input into the scene recognition model corresponding to each of the preset scenes to obtain the output result of each of the scene recognition models, wherein the recognition result includes the output result, and the scene recognition model is generated based on machine learning.

5. The scene control method of the smart home system according to claim 4, characterized in that: The scene recognition model includes a first model or a second model, and the step of respectively inputting the scene feature information into the scene recognition model corresponding to each of the preset scenes to obtain an output result corresponding to each of the scene recognition models includes: Inputting the scene feature information to the first model corresponding to each of the preset scenes respectively, obtaining a first output result corresponding to each of the first models, the first output result including whether the current scene represented by the scene feature information is the corresponding preset scene; Alternatively, the scene feature information is respectively input into a second model corresponding to each of the preset scenes to obtain a second output result corresponding to each of the second models, wherein the second output result includes a probability that the current scene represented by the scene feature information is the corresponding preset scene.

6. The scene control method of the smart home system according to claim 5, characterized in that: The step of respectively inputting the scene feature information into the scene recognition model corresponding to each of the preset scenes to obtain the output result corresponding to each of the scene recognition models comprises: Acquire the location type of the target indoor space; When the place type is the first type, inputting the scene feature information into the first model corresponding to each of the preset scenes respectively, and obtaining a first output result corresponding to each of the first models; When the place type is the second type, inputting the scene feature information into the second model corresponding to each of the preset scenes respectively, and obtaining a second output result corresponding to each of the second models; Wherein, a first similarity between the at least two preset scenes corresponding to the first type is smaller than a second similarity between the at least two preset scenes corresponding to the second type.

7. The scene control method of the smart home system according to claim 1, characterized in that: The step of determining the target scene among the at least two preset scenes according to the at least two recognition results comprises: When there is more than one recognition result satisfying the preset condition among the at least two recognition results, determining the target scene according to the priorities or predicted probabilities corresponding to all the preset scenes corresponding to all the recognition results satisfying the preset condition; Among them, the preset condition indicates that the preset scene matches the scene feature information, and the predicted probability is the probability that the current scene represented by the scene feature information is the corresponding preset scene.

8. The scene control method of the smart home system according to claim 7, characterized in that: The recognition result includes whether the current scene represented by the scene feature information is a corresponding preset scene, and the preset condition includes that the recognition result is that the current scene represented by the scene feature information is a corresponding preset scene; Alternatively, the recognition result includes the predicted probability, and the preset condition includes that the predicted probability is greater than the first preset probability.

9. The scene control method of the smart home system according to any one of claims 1 to 8, characterized in that: After the step of determining the target scene among the at least two preset scenes according to the at least two recognition results, the method further includes: Outputting switching prompt information corresponding to the target scene; When confirmation information corresponding to the target scene is received, the step of controlling the operation of at least one smart appliance in the target indoor space according to the target scene is executed.

10. The scene control method of the smart home system according to claim 9, characterized in that: After the step of determining the target scene among the at least two preset scenes according to the at least two recognition results, the method further includes: When the predicted probability corresponding to the target scene is greater than a second preset probability, executing the step of controlling the operation of at least one smart appliance in the target indoor space according to the target scene; When the predicted probability corresponding to the target scene is less than or equal to the second preset probability, outputting switching prompt information corresponding to the target scene, and when receiving confirmation information corresponding to the target scene, executing the step of controlling the operation of at least one smart appliance in the target indoor space according to the target scene; The predicted probability is the probability that the current scene represented by the scene feature information is the target scene.

11. A scene control device for a smart home system, characterized in that: The scene control device of the smart home system includes: a memory, a processor, and a scene control program of the smart home system stored in the memory and executable on the processor. When the scene control program of the smart home system is executed by the processor, the steps of the scene control method of the smart home system as described in any one of claims 1 to 10 are implemented.

12. A storage medium, characterized in that: The storage medium stores a scene control program of the smart home system, and when the scene control program of the smart home system is executed by the processor, the steps of the scene control method of the smart home system according to any one of claims 1 to 10 are implemented.

Images