Control method of smart home device, computer device and storage medium

Abstract

The present invention relates to the field of smart home / smart family technology, and specifically provides a control method, computer device and storage medium for smart home devices, aiming to solve the problem of improving the control convenience and intelligence of smart home devices. To this end, the method provided by the present invention includes predicting the control information of the current user on the smart home devices under the current environment information based on the historical control information of different users on the smart home devices under different historical environment information, outputting prompt information on whether to control the smart home devices according to the predicted control information, and then controlling the smart home devices according to the predicted control information based on the user feedback information. Through the above method, the control intention of the current user on the smart home devices can be predicted in advance, and the user can be prompted in advance to control the smart home devices to meet their control intentions, thereby significantly improving the control convenience and intelligence of the smart home devices.

Description

Technical Field

[0001] The present invention relates to the field of smart home / intelligent family technology, and in particular to a control method, computer equipment and storage medium for smart home equipment. Background Art

[0002] At present, in order to improve the convenience and intelligence of controlling home appliances, smart home appliances are mainly controlled through voice technology, such as controlling the start of smart home appliances according to the device start-up instructions issued by the user through voice. However, this method actually only replaces the traditional device control instructions (such as the device control instructions generated by pressing physical buttons) with voice instructions, and can only passively receive the device control instructions issued by the user, which cannot really improve the convenience and intelligence of controlling home appliances.

[0003] Accordingly, the art needs a new technical solution to solve the above problems. Summary of the invention

[0004] In order to overcome the above-mentioned defects, the present invention is proposed to provide a control method, computer device and storage medium for smart home devices that solve or at least partially solve the technical problem of how to improve the convenience and intelligence of controlling smart home devices.

[0005] In a first aspect, a method for controlling a smart home device is provided, the method comprising:

[0006] Based on historical control information of different users on the smart home device under different historical environment information, predicting the control information of the current user on the smart home device under current environment information;

[0007] Outputting prompt information on whether to control the smart home device according to the predicted control information and receiving user feedback information regarding the prompt information;

[0008] According to the user feedback information, the smart home device is controlled according to the predicted control information.

[0009] In a technical solution of the above-mentioned method for controlling smart home devices, before the step of "predicting the control information of the current user on the smart home device under the current environment information based on the historical control information of different users on the smart home device under different historical environment information", the method further includes:

[0010] Based on the historical control information of the smart home device by different users under different historical environment information, a knowledge graph of control information and environment information is established;

[0011] Using a knowledge graph reasoning algorithm to train the knowledge graph to determine a reasoning model for control information and environmental information;

[0012] The step of “predicting the control information of the current user on the smart home device under the current environment information based on the historical control information of different users on the smart home device under different historical environment information” specifically includes:

[0013] The inference model of the control information and the environmental information is used to predict the control information of the current user on the smart home device under the current environmental information.

[0014] In a technical solution of the control method of the above-mentioned smart home device, the step of "establishing a knowledge graph of control information and environmental information based on historical control information of the smart home device by different users under different historical environmental information" specifically includes:

[0015] Based on the historical control information of the smart home device by different users under different historical environment information and the user attributes of each user, a knowledge graph of user attributes, control information and environment information is established;

[0016] The step of “using a knowledge graph reasoning algorithm to train the knowledge graph to determine a reasoning model of control information and environmental information” specifically includes using a knowledge graph reasoning algorithm to train the knowledge graph to determine a reasoning model of user attributes, control information and environmental information; the step of “using the reasoning model of control information and environmental information to predict the control information of the current user on the smart home device under the current environmental information” specifically includes using the reasoning model of user attributes, control information and environmental information and predicting the control information of the current user on the smart home device under the current environmental information based on the user attributes of the current user;

[0017] and / or,

[0018] The knowledge graph reasoning algorithm at least includes a Translating Embedding algorithm.

[0019] In a technical solution of the above-mentioned method for controlling the smart home device, the method further includes respectively determining the environment category, control category and user category when different users control the smart home device in the following manner:

[0020] Acquire historical control information of different users on the smart home device under different historical environment information and user attributes of each user;

[0021] Cluster analysis is performed on the historical environment information, the historical control information and the user attributes respectively, so as to respectively determine the environment category, control category and user category when different users control the smart home device.

[0022] In a technical solution of the control method of the above-mentioned smart home device, the step of "respectively performing cluster analysis on the historical environment information, the historical control information and the user attributes to respectively determine the environment category, control category and user category when different users control the smart home device" specifically includes:

[0023] Based on the historical control information of the smart home device by different users under different historical environment information and the user attributes of each user, a knowledge graph of user attributes, control information and environment information is established;

[0024] Vectorizing the knowledge graph of the user attributes, control information, and environment information to respectively determine the environment vector of the historical environment information, the control vector of the historical control information, and the user attribute vector of the user attributes;

[0025] Cluster analysis is performed on the environment vector, the control vector and the user attribute vector respectively, so as to respectively determine the environment category, control category and user category when different users control the smart home device.

[0026] In a technical solution of the above-mentioned control method of smart home devices, the historical environment information and the current environment information both include at least environment attribute information and spatiotemporal attribute information.

[0027] In a technical solution of the above-mentioned control method of the smart home device, the environmental attribute information includes at least temperature and / or humidity and / or light brightness, and the spatiotemporal attribute information includes at least time information and spatial position information.

[0028] In a technical solution of the above-mentioned smart home device control method, the user attributes include at least the user's age and / or gender.

[0029] In a second aspect, a computer device is provided, which includes a processor and a storage device, wherein the storage device is suitable for storing multiple program codes, and the program codes are suitable for being loaded and run by the processor to execute the control method of the smart home device described in any of the technical solutions of the above-mentioned smart home device control method.

[0030] In a third aspect, a computer-readable storage medium is provided, which stores a plurality of program codes, wherein the program codes are suitable for being loaded and run by a processor to execute the method for controlling a smart home device described in any one of the technical solutions of the method for controlling a smart home device.

[0031] The above one or more technical solutions of the present invention have at least one or more of the following beneficial effects:

[0032] In a technical solution for implementing the present invention, the control information of the current user on the smart home device under the current environment information can be predicted based on the historical control information of different users on the smart home device under different historical environment information, and then prompt information on whether to control the smart home device according to the predicted control information is output according to the prediction result, and user feedback information on the prompt information is received. Finally, according to the user feedback information, the smart home device is controlled according to the predicted control information; if the user feedback information is to control according to the predicted control information, the smart home device is controlled according to the predicted control information; otherwise, the smart home device is not controlled according to the predicted control information.

[0033] Through the above implementation, the current user's control intention for smart home devices can be predicted in advance, and when the user confirms that the control can be performed according to the predicted control information, the smart home devices can be automatically controlled according to the predicted control information, which significantly improves the convenience and intelligence of controlling home devices. In addition, the above implementation combines the historical control information and historical environmental information when controlling smart home devices for prediction, which can significantly improve the accuracy of the prediction compared to just predicting according to the historical control information.

[0034] Furthermore, in another technical scheme for implementing the present invention, in order to further improve the accuracy and reliability of control information prediction, a knowledge graph of control information and environmental information can be established based on the historical control information of smart home devices by different users under different historical environmental information, and then the knowledge graph can be trained using a knowledge graph reasoning algorithm to determine the reasoning model of control information and environmental information. Finally, the reasoning model of control information and environmental information is used to predict the control information of the current user on the smart home device under the current environmental information. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0037] Figure 1 is a schematic diagram of a hardware environment of a smart home device method according to an embodiment of the present invention;

[0038] Figure 2 is a flowchart of main steps of a smart home device method according to an embodiment of the present invention;

[0039] Figure 3 is a flowchart of main steps of a method for determining an inference model of control information and environmental information according to an embodiment of the present invention;

[0040] Figure 4 is a schematic diagram of the vector relationship between the head entity vector, the tail entity vector and the relationship vector in a triple vector according to an embodiment of the present invention;

[0041] Figure 5 It is a flowchart diagram of main steps of a method for determining environment categories, control categories and user categories when different users control smart home devices according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0043] It should be noted that the term "comprises" and any variations thereof in the specification and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method or apparatus comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods or apparatuses.

[0044] According to one aspect of an embodiment of the present invention, a control method for a smart home device is provided. The control method for a smart home device is widely used in smart home (Smart Home), smart home, smart home device ecology, smart residential (Intelligence House) ecology and other whole-house intelligent digital control application scenarios. Optionally, in this embodiment, the control method for the smart home device can be applied to Figure 1 In the hardware environment composed of the terminal device 102 and the server 104 shown in FIG. Figure 1 As shown, the server 104 is connected to the terminal device 102 via a network, and can be used to provide services (such as application services, etc.) for the terminal or a client installed on the terminal. A database can be set on the server or independently of the server to provide data storage services for the server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data computing services for the server 104.

[0045] The network may include but is not limited to at least one of the following: wired network, wireless network. The wired network may include but is not limited to at least one of the following: wide area network, metropolitan area network, local area network, and the wireless network may include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth. The terminal device 102 may be but is not limited to a PC, a mobile phone, a tablet computer, a smart air conditioner, a smart range hood, a smart refrigerator, a smart oven, a smart stove, a smart washing machine, a smart water heater, a smart washing device, a smart dishwasher, a smart projection device, a smart TV, a smart clothes drying rack, a smart curtain, a smart audio and video, a smart socket, a smart speaker, a smart fresh air device, a smart kitchen and bathroom device, a smart bathroom device, a smart sweeping robot, a smart window cleaning robot, a smart mopping robot, a smart air purification device, a smart steamer, a smart microwave oven, a smart kitchen treasure, a smart purifier, a smart water dispenser, a smart door lock, etc.

[0046] See attached Figure 2 , Figure 2 FIG. 1 is a flow chart showing the main steps of a method for controlling a smart home device according to an embodiment of the present invention. Figure 2 As shown, the control method of the smart home device in the embodiment of the present invention mainly includes the following steps S101 to S103.

[0047] Step S101: predicting the control information of the current user on the smart home device under the current environment information based on the historical control information of different users on the smart home device under different historical environment information.

[0048] Control information refers to information for controlling smart home devices to perform certain operations or actions. For example, if the control information of a smart air conditioner is to switch the cooling mode to the air supply mode, then under the control of this control information, the smart air conditioner will switch the cooling mode to the air supply mode. The historical environment information is the control information of users (including the current user and other users) controlling smart home devices before the current moment.

[0049] Environmental information refers to the environmental information of the environment in which the smart home device is located when the smart home device is controlled, and historical environmental information refers to the environmental information of the environment in which the smart home device is located when the user (including the current user and other users) controlled the smart home device before the current moment.

[0050] Environmental information may include environmental attribute information and spatiotemporal attribute information. Environmental attribute information refers to information that can represent the natural environment state of the environment in which the smart home device is located, and spatiotemporal attribute information refers to information that can represent the time and space of the environment in which the smart home device is located. In this way, when predicting the control information of the current user on the smart home device based on environmental information, predictions can be made from multiple dimensions, including the natural environment state, time, and space, so as to accurately obtain control information that meets the current user's control intention.

[0051] In some embodiments, the environmental attribute information may include at least information such as the temperature and / or humidity and / or light brightness of the environment, and the spatiotemporal attribute information may include at least time information and spatial location information, wherein the spatial location information refers to the geographical location of the smart home device. Specifically, the information value of the temperature, humidity, and light brightness of the environment may be the specific value of the temperature, humidity, and light brightness, or the value range of the specific value of the temperature, humidity, and light brightness. Similarly, the information value of the time information may be the specific moment value of the time information, or the time range of the specific moment value of the time information. The spatial location information may be the specific coordinates of the geographical location of the smart home device, or the regional range of the specific coordinates.

[0052] For example, if the temperature range formed by 0°C to 100°C is divided into 5 continuous sub-temperature ranges, and the 5 sub-temperature ranges are represented by 1, 2, 3, 4 and 5 temperature gears respectively in order from low to high temperature, then the temperature in the environmental attribute information can be the temperature gear. For another example, if a year is divided into four seasons of spring, summer, autumn and winter, then the time information in the spatiotemporal attribute information can be the season information; if the time is divided into working days and holidays, then the time information in the spatiotemporal attribute information can also be working days or holidays. For another example, if a country is divided into administrative regions based on provinces as administrative units, then the spatial location information can be the province corresponding to the geographical location of the smart home device.

[0053] In the embodiment of the present invention, for each type of environment information, historical control information of most users on smart home devices under the environment information can be selected as candidate control information for smart home devices under this environment information, so that candidate control information for smart home devices under each type of environment information can be obtained. When it is necessary to predict the control information of the current user on the smart home device under the current environment information, the candidate control information can be matched according to the current environment information, and the matched candidate control information can be used as the predicted control information.

[0054] Step S102: outputting prompt information on whether to control the smart home device according to the predicted control information and receiving user feedback information on the prompt information.

[0055] The prompt information may include at least voice prompt information and / or image prompt information and / or text prompt information, etc. In the embodiment of the present invention, those skilled in the art may flexibly set the type of prompt information according to actual needs, as long as the prompt information can remind the user whether to control the smart home device according to the predicted control information.

[0056] The user feedback information includes whether to control the smart home device according to the control information specified in the prompt information. For example, the user feedback information can be "not executed", that is, the smart home device is not controlled according to the control information specified in the prompt information; the user feedback information can also be "executed", that is, the smart home device is controlled according to the control information specified in the prompt information. In addition, the information type of the user feedback information can be voice, image, text, etc., that is, the user can confirm whether to control the smart home device according to the control information specified in the prompt information by inputting voice, image and text.

[0057] Step S103: Control the smart home device according to the predicted control information based on the user feedback information.

[0058] Specifically, if the user feedback information confirms that the smart home device can be controlled according to the predicted control information, the smart home device will be controlled according to the predicted control information; if the user feedback information is not to control the smart home device according to the predicted control information, the smart home device will not be controlled according to the predicted control information.

[0059] Based on the method described in steps S101 to S103, the current user's control intention for the smart home device can be predicted in advance, and when the user confirms that the control can be performed according to the predicted control information, the smart home device can be automatically controlled according to the predicted control information, which significantly improves the convenience and intelligence of controlling the home device. In addition, the above method combines the historical control information and historical environment information when controlling the smart home device to make predictions, which can significantly improve the accuracy of the prediction compared to only making predictions according to the historical control information.

[0060] The following is a further description of step S101 in the above method embodiment.

[0061] In some implementations of the above step S101, a knowledge graph reasoning method may be used to predict the control information of the current user on the smart home device under the current environment information, so as to further improve the prediction accuracy of the control information. Figure 3 In this embodiment, a reasoning model of control information and environmental information can be established and trained through the following steps S1001 to S1002, and then when executing step S101, this reasoning model of control information and environmental information can be used to predict the control information of the current user on the smart home device under the current environmental information.

[0062] Step S1001: Based on the historical control information of smart home devices by different users under different historical environmental information, a knowledge graph of control information and environmental information is established.

[0063] Specifically, first determine the triple data consisting of user information, environmental information and control information, that is, (user information, environmental information, control information). Among them, the user information can at least include identity information that can indicate which user the current user is, such as the user's ID number or mobile phone number. After determining the triple data, a knowledge graph of control information and environmental information can be established based on these triple data. In this embodiment, a conventional knowledge graph establishment method in the field of knowledge graph technology can be used to establish a knowledge graph of control information and environmental information based on the above triple data. This embodiment does not elaborate on the specific method of establishing the above knowledge graph.

[0064] Step S1002: Use the knowledge graph reasoning algorithm to train the knowledge graph to determine the reasoning model of control information and environmental information.

[0065] Since the knowledge graph is established based on the historical control information of smart home devices by different users under different historical environmental information, and this information can truly show the user's control intention of smart home devices under different environmental information, the reasoning model of control information and environmental information obtained by knowledge graph training can accurately learn the reasoning relationship between control information and environmental information, so as to accurately infer which control information should be used to control smart home devices under different environmental information.

[0066] In this embodiment, a conventional knowledge graph reasoning algorithm in the field of knowledge graph technology can be used to train the knowledge graph to determine the reasoning model of control information and environmental information. In some preferred embodiments, the TransE algorithm in the knowledge graph reasoning algorithm can be used to train the knowledge graph to determine the reasoning model of control information and environmental information. Specifically, based on the TransE algorithm, the user information, environmental information and control information in the knowledge graph can be converted into vector information, namely, user vector, environmental vector and control vector, respectively. Based on these vector information, a triple vector (h, r, t) is established, where h and t represent the head entity vector and the tail entity vector of the triple vector, respectively, and r represents the relationship vector between the head entity vector and the tail entity vector. In addition, h and t are environment vectors, respectively, and r is the control vector. Finally, the model is trained with the vector relationship of h+r=t as the target to obtain the reasoning model of control information and environmental information. Among them, the vector relationship of h+r=t can be as follows Figure 4 As shown, the vector sum of vector h and vector r is equal to vector t.

[0067] Based on the method described in steps S1001 to S1002 above, the reasoning model of control information and environmental information can learn the accurate reasoning relationship between the control information and environmental information. In this way, when it is necessary to predict the control information of the current user on the smart home device under the current environmental information, the current environmental information can be input into the reasoning model of control information and environmental information, so as to obtain the control information of the smart home device conveniently and accurately.

[0068] The above is a detailed description of an implementation of the above step S101. The following is a description of another implementation of the above step S101.

[0069] In another implementation of the above step S101, the knowledge graph reasoning method can also be used to predict the control information of the current user on the smart home device under the current environmental information, so as to further improve the prediction accuracy of the control information. However, the main difference from the implementation described in the above steps S1001 to S1002 is that when establishing the knowledge graph, not only the control information and environmental information are considered, but also the user attributes of the user are considered, that is, the knowledge graph is established based on the user attributes, control information and environmental information at the same time, and the reasoning model is obtained by training the knowledge graph that considers the user attributes. Specifically, in this implementation, a reasoning model of control information and environmental information can be established and trained through the following steps S1003 to S1004, and then when executing step S101, this reasoning model of control information and environmental information can be used to predict the control information of the current user on the smart home device under the current environmental information.

[0070] Step S1003: Based on the historical control information of smart home devices by different users under different historical environment information and the user attributes of each user, a knowledge graph of user attributes, control information and environment information is established.

[0071] User attributes refer to information that can represent the user's physiological information and / or social information. Among them, the user attributes representing the user's physiological information can at least include the user's age and / or gender. The user attributes representing the user's social information can at least include the user's occupation and / or address. In this way, when predicting the current user's control information on the smart home device based on the user attributes and environmental information, it is possible to simultaneously predict from the user's physiological information and / or social information, as well as the natural environment state, time and space in multiple dimensions, to obtain control information that is more in line with the current user's control intention.

[0072] In this embodiment, the method of establishing a knowledge graph of user attributes, control information, and environmental information is similar to the method of establishing a knowledge graph of control information and environmental information described in step S1001 in the aforementioned embodiment, and will not be repeated here.

[0073] Step S1004: Use the knowledge graph reasoning algorithm to train the knowledge graph to determine the reasoning model of user attributes, control information and environmental information.

[0074] In this embodiment, a knowledge graph reasoning algorithm is used to train the knowledge graph to determine the reasoning model of user attributes, control information and environmental information. The method is similar to the method described in step S1012 in the aforementioned embodiment and will not be repeated here.

[0075] Based on the method described in steps S1003 to S1004 above, the inference model of user attributes, control information and environmental information can learn the accurate inference relationship between user attributes, control information and environmental information. Therefore, when it is necessary to predict the control information of the current user on the smart home device under the current environmental information, the user attributes and current environmental information of the current user can be input into the inference model of user attributes, control information and environmental information. Through this inference model, predictions can be made from both environmental information and user attributes to accurately obtain control information that meets the current user's control intention.

[0076] The above is a detailed description of another implementation of step S101.

[0077] The following is combined with Figure 5 , another embodiment of a control method for a smart home device provided by the present invention is described. In the embodiment of the present invention, in addition to steps S101 to S103 described in the above method embodiment, the control method for a smart home device may also include: Figure 5 Steps S201 to S202 shown determine the environment category, control category and user category when different users control the smart home devices, so that the control method and / or marketing method of the smart home devices can be improved according to the environment category, control category and user category.

[0078] Step S201: Acquire historical control information of different users on smart home devices under different historical environment information and user attributes of each user.

[0079] User attributes refer to information that can represent the user's physiological information and / or social information. Among them, the user attributes representing the user's physiological information may at least include the user's age and / or gender. The user attributes representing the user's social information may at least include the user's occupation and / or address.

[0080] Step S202: performing cluster analysis on the historical environment information, historical control information and user attributes respectively, so as to respectively determine the environment category, control category and user category when different users control the smart home devices.

[0081] By clustering the historical environmental information, similar historical environmental information can be classified into one category. For example, taking the historical environmental information when controlling the smart air conditioner as an example, the historical environmental information can be classified into categories such as high temperature in summer and low temperature in winter.

[0082] By clustering the historical control information, similar historical control information can be classified into one category. For example, taking the smart washing machine and the smart clothes rack as an example, the time when the smart washing machine and the smart clothes rack are controlled each time is relatively close, so it can be determined that the smart washing machine and the smart clothes rack are usually started at the same time, so the smart washing machine and the smart clothes rack can be classified into the linkage control category. Taking the smart audio and video as an example, the time when the smart audio and video is controlled each time is not close to the control time of other smart home devices, so it can be determined that the smart audio and video is usually started separately, so the smart audio and video can be classified into the separate control category.

[0083] By performing cluster analysis on user attributes, similar user attributes can be grouped into one category. Specifically, if the user attributes include multiple attributes such as the user's age, gender, and occupation, the multiple attributes that are similar can be grouped into one category.

[0084] In the embodiment of the present invention, conventional data clustering methods in the field of data processing technology may be used to perform cluster analysis on historical environment information, historical control information, and user attributes, thereby determining environment categories, control categories, and user categories, respectively.

[0085] Based on the method described in steps S201 to S202 above, after determining the control category of each smart home device, the control method of the smart home device can be improved according to the control category. For example, taking a smart washing machine as an example, after predicting that the control information of the current user for the smart washing machine under the current environmental information is a start instruction through step S101 described in the above method embodiment, when executing step S102, not only the prompt information of whether to start the smart washing machine can be output, but also the prompt information of whether to start the smart clothes rack can be output, thereby further improving the control convenience and intelligence of the smart clothes rack. After determining the environmental category, the marketing method of the smart home device can be improved according to the environmental category containing spatial location information. For example, taking a smart washing machine as an example, if the spatial location information in the environmental category containing spatial location information is mainly distributed in area A and area B, it means that the customer group of the smart washing machine is mainly distributed in area A and area B, and the marketing of the smart washing machine can be strengthened in area A and area B. Similarly, after determining the user category, the marketing method of the smart home device can also be improved according to the user category.

[0086] The above step S202 is further explained below.

[0087] In some implementations of the above-mentioned step S202, in order to improve the accuracy of cluster analysis of historical environmental information, historical control information and user attributes, the historical environmental information, historical control information and user attributes can be clustered and analyzed respectively through the following steps S2021 to S2023 to respectively determine the environmental category, control category and user category when different users control the smart home devices.

[0088] Step S2021: Based on the historical control information of smart home devices by different users under different historical environmental information and the user attributes of each user, a knowledge graph of user attributes, control information and environmental information is established.

[0089] The method for establishing a knowledge graph of user attributes, control information, and environmental information is the same as the method described in step 11 of the aforementioned method embodiment, and will not be repeated here.

[0090] Step S2022: vectorize the knowledge graph of user attributes, control information and environmental information to respectively determine the environmental vector of historical environmental information, the control vector of historical control information and the user attribute vector of user attributes.

[0091] In this embodiment, conventional vectorization representation methods in the field of knowledge graph technology can be used to vectorize the knowledge graphs of user attributes, control information, and environmental information, respectively, so as to determine the environmental vector of historical environmental information, the control vector of historical control information, and the user attribute vector of user attributes, respectively. In some preferred embodiments, if the inference model trained by the TransE algorithm is used when determining the inference model of user attributes, control information, and environmental information, since the user information, environmental information, and control information in the knowledge graph have been converted into vector information respectively by the TransE algorithm, there is no need to vectorize the knowledge graph of user attributes, control information, and environmental information again at this time, and the user vector, environmental vector, and control vector obtained by the TransE algorithm are directly used as the user attribute vector of user attributes, the environmental vector of historical environmental information, and the control vector of historical control information, respectively.

[0092] Step S2023: performing cluster analysis on the environment vector, the control vector and the user attribute vector respectively, so as to respectively determine the environment category, the control category and the user category when different users control the smart home device.

[0093] In the embodiment of the present invention, conventional data clustering methods in the field of data processing technology can be used to perform cluster analysis on the environment vector, control vector and user attribute vector respectively, so as to determine the environment category, control category and user category respectively. For example, a clustering method based on Euclidean distance is used.

[0094] Compared with directly performing cluster analysis on user attributes, control information and environmental information, cluster analysis on vectorized user attributes, control information and environmental information based on the method described in steps S2021 to S2023 can significantly improve the efficiency and accuracy of cluster analysis.

[0095] The above is a detailed description of step S202.

[0096] It should be pointed out that although the various steps in the above embodiments are described in a specific order, those skilled in the art can understand that in order to achieve the effects of the present invention, different steps do not have to be performed in such an order. They can be performed simultaneously (in parallel) or in other orders. These changes are within the scope of protection of the present invention.

[0097] It is understood by those skilled in the art that the present invention implements all or part of the processes in the method of the above embodiment, and can also be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device, medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal and software distribution medium that can carry the computer program code. It should be noted that the content contained in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable storage media do not include electric carrier signals and telecommunication signals.

[0098] Furthermore, the present invention also provides a computer device.

[0099] In an embodiment of a computer device according to the present invention, the computer device includes a processor and a storage device, the storage device can be configured to store a program for executing the control method of the smart home device of the above method embodiment, and the processor can be configured to execute the program in the storage device, which includes but is not limited to the program for executing the control method of the smart home device of the above method embodiment. For ease of explanation, only the part related to the embodiment of the present invention is shown, and for specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The computer device can be a control device device formed by various electronic devices.

[0100] Furthermore, the present invention also provides a computer device.

[0101] In an embodiment of a computer device according to the present invention, the computer device includes a processor and a storage device, the storage device can be configured to store a program for executing the control method of the smart home device of the above method embodiment, and the processor can be configured to execute the program in the storage device, which includes but is not limited to the program for executing the control method of the smart home device of the above method embodiment. For ease of explanation, only the part related to the embodiment of the present invention is shown, and for specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The computer device can be a control device device formed by various electronic devices.

[0102] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A control method for a smart home device, characterized in that: The method comprises: Based on historical control information of different users on the smart home device under different historical environment information, predicting the control information of the current user on the smart home device under current environment information; Outputting prompt information on whether to control the smart home device according to the predicted control information and receiving user feedback information regarding the prompt information; According to the user feedback information, controlling the smart home device according to the predicted control information; in, The predicting the control information of the current user on the smart home device under the current environment information includes: using an inference model of control information and environment information to predict the control information of the current user on the smart home device under the current environment information; The inference model is obtained in the following way: Based on the historical control information of the smart home device by different users under different historical environmental information, a knowledge graph of control information and environmental information is established; and the knowledge graph is trained using a knowledge graph reasoning algorithm to determine a reasoning model of control information and environmental information; The adopting of a knowledge graph inference algorithm to train the knowledge graph includes: Based on the TransE algorithm, the environmental information and control information in the knowledge graph are converted into an environmental vector and a control vector respectively; a triple vector (h, r, t) is established according to the environmental vector and the control vector, where h and t represent the head entity vector and the tail entity vector of the triple vector respectively, and r represents the relationship vector between the head entity vector and the tail entity vector. h and t are respectively the environmental vectors, and r is the control vector; model training is performed with the vector relationship of h+r=t as the goal to obtain an inference model of the control information and the environmental information.

2. The control method of the smart home device according to claim 1, characterized in that: The step of "establishing a knowledge graph of control information and environmental information based on historical control information of the smart home device by different users under different historical environmental information" specifically includes: Based on the historical control information of the smart home device by different users under different historical environment information and the user attributes of each user, a knowledge graph of user attributes, control information and environment information is established; The step of "using a knowledge graph reasoning algorithm to train the knowledge graph to determine a reasoning model of control information and environmental information" specifically includes using a knowledge graph reasoning algorithm to train the knowledge graph to determine a reasoning model of user attributes, control information, and environmental information; The step of "using the inference model of the control information and environmental information to predict the control information of the current user on the smart home device under the current environmental information" specifically includes using the inference model of the user attributes, control information and environmental information and predicting the control information of the current user on the smart home device under the current environmental information based on the user attributes of the current user.

3. The control method of the smart home device according to claim 1, characterized in that: The method further includes determining the environment category, control category and user category when different users control the smart home device respectively in the following manner: Acquire historical control information of different users on the smart home device under different historical environment information and user attributes of each user; Cluster analysis is performed on the historical environment information, the historical control information and the user attributes respectively, so as to respectively determine the environment category, control category and user category when different users control the smart home device.

4. The control method of the smart home device according to claim 3, characterized in that: The step of "respectively performing cluster analysis on the historical environment information, the historical control information and the user attributes to respectively determine the environment category, control category and user category when different users control the smart home device" specifically includes: Based on the historical control information of the smart home device by different users under different historical environment information and the user attributes of each user, a knowledge graph of user attributes, control information and environment information is established; Vectorizing the knowledge graph of the user attributes, control information, and environment information to respectively determine the environment vector of the historical environment information, the control vector of the historical control information, and the user attribute vector of the user attributes; Cluster analysis is performed on the environment vector, the control vector and the user attribute vector respectively, so as to respectively determine the environment category, control category and user category when different users control the smart home device.

5. The control method of the smart home device according to any one of claims 1 to 4, characterized in that: The historical environment information and the current environment information both include at least environment attribute information and time-space attribute information.

6. The control method of the smart home device according to claim 5, characterized in that: The environmental attribute information at least includes temperature and / or humidity and / or light brightness, and the spatiotemporal attribute information at least includes time information and spatial position information.

7. The control method of the smart home device according to any one of claims 2 to 4, characterized in that: The user attributes include at least the user's age and / or gender.

8. A computer device comprising a processor and a storage device, wherein the storage device is suitable for storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by the processor to execute the control method of the smart home device according to any one of claims 1 to 7.

9. A computer-readable storage medium storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by a processor to execute the control method of the smart home device according to any one of claims 1 to 7.

Images