A smart home control method, device, equipment and medium

Abstract

The application provides a smart home control method and device, equipment and medium, obtains a target user feature vector corresponding to a target user and other user feature vectors corresponding to each other user of other families in advance, determines a target other user with the highest similarity to the target user according to the target user feature vector and each other user feature vector, and controls according to a saved first target smart home control scheme executed by the target other user in the current scene. Since the server can control the local smart device according to the saved first target smart home control scheme executed by the target other user with the highest similarity to the target user in the current scene, it is not necessary for the user to input the control scheme in advance, the automatic control of the smart device by the server is improved, and the use experience of the user is improved.

Description

Technical Field

[0001] This application relates to the field of smart home technology, and in particular to a smart home control method, device, equipment and medium. Background Technology

[0002] With the development of Internet of Things (IoT) technology, smart homes are being used more and more widely, and their convenience and intelligence bring great benefits to users.

[0003] In existing smart home control solutions, in addition to users actively controlling smart devices, there are also servers that automatically control smart devices based on the current environment, enabling the devices to provide services. Specifically, the server senses environmental changes through smart devices, determines the current scene, and automatically executes the corresponding control actions, thereby effectively improving the comfort and security of the home environment and comprehensively enhancing the user experience.

[0004] However, in existing technologies, when a server controls a smart device based on the current environment, the user needs to pre-configure various scenarios and control schemes for each smart device on the server. This results in high limitations in the server's automated control of smart devices, affecting the user experience. Summary of the Invention

[0005] This application provides a smart home control method, device, equipment, and medium to solve the problems of high limitations and poor user experience in the automation control of smart devices by servers in the prior art.

[0006] In a first aspect, embodiments of this application provide a smart home control method, the method comprising:

[0007] If the triggering conditions for smart home control for the target user are met, then obtain the pre-saved target user feature vector corresponding to the target user, and the pre-saved other user feature vectors corresponding to each other user in other households;

[0008] Determine the first similarity between the target user feature vector and each of the other user feature vectors;

[0009] Based on the first similarity corresponding to each other user, determine the target other user with the highest similarity to the target user, obtain the saved first target smart device control scheme executed by the target other user in the current scenario, and use the first target smart device control scheme for control.

[0010] Secondly, embodiments of this application also provide an electronic device, the electronic device including a processor, the processor being configured to execute a computer program stored in a memory to implement the steps of the smart home control method as described above.

[0011] In this embodiment, if the triggering conditions for smart home control targeting a target user are met, the system obtains a pre-saved target user feature vector and pre-saved other user feature vectors for each other user in other households. It then determines the first similarity between the target user feature vector and each other user feature vector. Based on the first similarity for each other user, it identifies the target other user with the highest similarity to the target user and obtains a first target smart device control scheme executed by the target other user in the current scenario. The system then uses this first target smart device control scheme for control. In this embodiment, the server can determine the target other user with the highest similarity to the target user based on the saved target user feature vector and the saved other user feature vectors. It then controls the local smart devices according to the first target smart home control scheme executed by the target other user in the current scenario. This eliminates the need for the user to input a control scheme in advance, improving the server's automated control of smart devices and enhancing the user experience. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic diagram of the smart home control process provided in an embodiment of this application;

[0014] Figure 2 A schematic diagram of a family knowledge graph provided in an embodiment of this application;

[0015] Figure 3 This is a schematic diagram of the target family knowledge graph corresponding to the target user provided in the embodiments of this application;

[0016] Figure 4 A schematic diagram of the target other family knowledge graph corresponding to the target other users provided in the embodiments of this application;

[0017] Figure 5 A schematic diagram of a server intelligent decision-making process provided in an embodiment of this application;

[0018] Figure 6A schematic diagram illustrating another server-side intelligent decision-making process provided in this application embodiment;

[0019] Figure 7 A schematic diagram of a smart home control process provided in an embodiment of this application;

[0020] Figure 8 This is a schematic diagram of the overall process of smart home control provided in the embodiments of this application;

[0021] Figure 9 This is a schematic diagram of the structure of a smart home control device provided in an embodiment of this application;

[0022] Figure 10 This is a schematic diagram of an electronic device structure provided in an embodiment of this application. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] To improve the automated control of smart devices by the server and enhance the user experience, this application provides a smart home control method, device, equipment, and medium.

[0025] In this embodiment, if the server currently meets the triggering conditions for smart home control of the target user, it obtains the target user feature vector corresponding to the pre-saved target user and the other user feature vector corresponding to each other user in other households, determines the first similarity between the target user feature vector and each other user feature vector, determines the target other user with the highest similarity to the target user based on the first similarity corresponding to each other user, obtains the first target smart device control scheme executed by the target other user in the current scenario, and uses the first target smart device control scheme for control.

[0026] Figure 1 This application provides a schematic diagram of a smart home control process for one or more embodiments, the process including the following steps:

[0027] S101: If the triggering conditions for smart home control for the target user are met, then obtain the target user feature vector corresponding to the target user that is saved in advance, and the other user feature vectors corresponding to each other user in other households that are saved in advance.

[0028] This application provides a smart home control method applied to a server.

[0029] In this embodiment, if the triggering conditions for smart home control targeting a target user are met, the server will control the smart home system. These triggering conditions might include the target user turning on a smart device, the server detecting a change in the environment, or the server detecting the target user's presence in the room.

[0030] In this embodiment of the application, if the server determines that the triggering conditions for smart home control for the target user are met, the server can perform smart home control on the smart device.

[0031] Specifically, in this embodiment, the server obtains a pre-saved target user feature vector corresponding to the target user and pre-saved other user feature vectors corresponding to each other user in other households. The server then determines a smart home control scheme based on the target user feature vector and the other user feature vectors.

[0032] In this embodiment, the user feature vector includes, but is not limited to, basic attributes such as gender, age, weight, and height, as well as user interests and preferences such as temperature preference, humidity preference, and water temperature preference. Each attribute corresponds to a dimension in the user feature vector. When saving the user feature vector, for attributes with numerical data types, the server can normalize the numerical value and determine the normalized value as the value of the dimension containing that attribute in the user feature vector, such as user temperature preference, humidity preference, and water temperature preference. For attributes with text data types, the server must convert the text into numerical form. The server can use methods such as enumeration or defuzzification to convert text into numerical values.

[0033] For example, if one dimension of a user's feature vector represents the user's gender, the server can use an enumeration method to convert the text into numerical values, such as using the value 1 to represent female and the value 0 to represent male.

[0034] S102: Determine the first similarity between the target user feature vector and each of the other user feature vectors.

[0035] In this embodiment of the application, after the server determines the target user feature vector corresponding to the target user and other feature vectors corresponding to other users, the server can determine the smart home control scheme based on each first similarity between the target user feature vector and each other user feature vector.

[0036] In this embodiment, the server may use the Pearson correlation coefficient algorithm to determine the first similarity between the target user's feature vector and each other user's feature vector. Of course, the server may also use other methods to determine each first similarity.

[0037] Specifically, in this embodiment, if the server uses the Pearson correlation coefficient algorithm to determine the first similarity between the target user's feature vector and each other user's feature vector, the server can calculate it using the following formula:

[0038]

[0039] Where u represents the target user feature vector, v represents the other user feature vectors, and sim u (u,v) represents the first similarity, u k v represents the value of the k-th dimension of the target user feature vector. k This represents the numerical value corresponding to the k-th dimension of other users' feature vectors. This represents the average value of each dimension of the target user's feature vector. This represents the average value of each dimension of the feature vectors of other users.

[0040] S103: Based on the first similarity corresponding to each other user, determine the target other user with the highest similarity to the target user, and obtain the first target intelligent device control scheme executed by the target other user in the current scenario, and use the first target intelligent device control scheme for control.

[0041] In this embodiment, after determining the first similarity between each other user feature vector and the target user feature vector, the server identifies the target other user with the highest similarity to the target user based on each first similarity. Then, the server controls the local smart device according to the first target smart device control scheme executed by this target other user in the current scenario.

[0042] Specifically, in this embodiment, the server can compare the numerical values ​​of each first similarity score and identify the other user corresponding to the first similarity score with the largest value as the target other user. The server obtains the saved first target smart device control scheme executed by the target other user in the current scenario, and controls the local smart device according to the target smart device notification scheme.

[0043] It should be noted that if the server does not store the smart device control scheme executed by another user in the current scenario corresponding to the highest first similarity score, the server will select the other user with the highest first similarity score, excluding the target user, as the target user. If the server stores multiple smart device control schemes executed by the target user in the current scenario, the smart device control scheme executed most frequently by the target user in the current scenario will be selected as the first target smart device control scheme.

[0044] In this embodiment, the server can determine the target other user with the highest similarity to the target user based on the saved target user feature vector and the saved other user feature vectors. Then, according to the saved first target smart home control scheme corresponding to the target other user in the current scenario, the server can control the local smart devices without the need for the user to input the control scheme in advance. This improves the server's automated control of smart devices and enhances the user experience.

[0045] To improve the accuracy of the server's automated control of smart devices, based on the above embodiments, in this embodiment, before determining the target other user with the highest similarity to the target user according to the first similarity corresponding to each other user, the method further includes:

[0046] Obtain the saved target environment vector corresponding to the target user, and the saved other environment vectors corresponding to each other user;

[0047] Determine the second similarity between the target environment vector and each other environment vector;

[0048] The step of determining the target other user with the highest similarity to the target user based on the first similarity corresponding to each other user includes:

[0049] Based on the first similarity and second similarity of each other user, the target other user with the highest similarity to the target user is determined.

[0050] In this embodiment, since different users have different preferences, determining the similarity between the target user and other users solely based on the user feature vectors of the target user and other users may result in a final result with discrepancies from reality. Therefore, in this embodiment, in addition to determining the first similarity between the user feature vectors of the target user and other users, the server further determines the similarity between the target user and each other user based on the stored target environment vector corresponding to the target user and other environment vectors corresponding to other users.

[0051] Specifically, in this embodiment of the application, the server obtains the target environment vector corresponding to the target user and the other environment vectors corresponding to each other user, and determines the second similarity between the target environment vector and each other environment vector.

[0052] In this embodiment of the application, when the server determines the second similarity between the target environment vector and each other environment vector, it may use the Pearson correlation coefficient algorithm or the cosine similarity algorithm for calculation.

[0053] However, since the environmental attributes of users don't change significantly within the same season, the differences between the environmental vectors of the target user and other users are not substantial. If the server uses the Pearson correlation coefficient algorithm or the cosine similarity algorithm to calculate the second similarity, the differences between each calculated second similarity will be very small. This results in high similarity values ​​for the target user's environmental vector with any other user, affecting the server's accuracy in determining the similarity between the target user and other users.

[0054] Based on this, in the embodiments of this application, when the server determines the second similarity between the target user and each other user, the server will use a distance-based exponential calculation method to amplify the impact of the distance difference on the second similarity, thereby improving the accuracy of the server in determining the similarity between the target user and other users.

[0055] Specifically, in this embodiment, the server can determine the second similarity between the target user and other users using the following formula:

[0056]

[0057] Where a is the target environment vector, b is other environment vectors, and sim e (a,b) represents the second similarity, where a i b represents the value of the i-th dimension of the target environment vector. i This represents the value corresponding to the i-th dimension of other environment vectors, where I represents the total number of dimensions of the environment vectors.

[0058] In this embodiment of the application, the environmental vector includes, but is not limited to, season, weather, and the orientation of the user's room.

[0059] To further improve the accuracy of the server's automated control of smart devices, based on the above embodiments, in this embodiment, before determining the target other user with the highest similarity to the target user according to the first similarity corresponding to each other user, the method further includes:

[0060] Obtain each target smart device that has a connection relationship with the target user in the target family knowledge graph corresponding to the target user, and determine the target smart device vector corresponding to the target user based on the pre-configured position of each type of smart device in the smart device vector and each target smart device;

[0061] Obtain each other smart device that has a connection relationship with the other user in the other family knowledge graph corresponding to the other user, and determine the other smart device vector corresponding to the other user based on the pre-configured position of each type of smart device in the smart device vector and each other smart device;

[0062] For each other user, the other user feature vector and other environment vectors corresponding to that other user are concatenated into a first vector in a preset order; the target user feature vector and target environment vector corresponding to the target user are concatenated into a second vector in a preset order; a first target dimension is determined where both the other smart device vector and the target smart device vector corresponding to that other user have values, and a third vector is determined based on the first target dimension; a second target dimension is determined where both the first vector and the second vector have values, and a fourth vector is determined based on the second target dimension; the target user's trust level towards that other user is determined based on the third vector and the fourth vector.

[0063] The step of determining the target other user with the highest similarity to the target user based on the first similarity corresponding to each other user includes:

[0064] Based on the first similarity, second similarity, and trust value of each other user, the total similarity of each other user is determined, and the other user with the highest total similarity is identified as the target other user.

[0065] In this embodiment of the application, in order to further improve the accuracy of the server's automated control of smart devices, in addition to determining the first similarity of the user feature vectors of the target user and other users, and the second similarity of the target environment vector and other environment vectors, the server also further determines the target user's trust level towards each other user based on the user feature vector, environment vector, entities in the family related to the user's device, and the relationship between the user and the entity carried in the stored family knowledge graph.

[0066] Specifically, in this embodiment, the server obtains each target smart device that has a connection relationship with the target user in the target family knowledge graph corresponding to the target user, and determines the target smart device vector corresponding to the target user based on the pre-configured position of each type of smart device in the smart device vector and each target smart device.

[0067] The server will also obtain each other smart device that has a connection relationship with other users in the other family knowledge graph corresponding to other users, and determine the other smart device vector corresponding to other users based on the pre-configured position of each type of smart device in the smart device vector and each other smart device.

[0068] Specifically, in this embodiment, the server stores the type of smart device represented by each dimension of the smart device vector. The server can determine the target smart vector corresponding to the target user based on each target smart device that has a connection relationship with the target user in the target family knowledge graph, and determine the other smart device vector corresponding to each other user based on each other smart device that has a connection relationship with other users in each other family knowledge graph.

[0069] In this embodiment of the application, for each other user, the server can determine the target user's trust level towards that other user based on the other user feature vector, other environment vector, other smart device vector corresponding to that other user, and the target user feature vector, target environment vector, and target smart device vector corresponding to the target user.

[0070] Specifically, in this embodiment, the server concatenates the other user feature vector and other environment vectors corresponding to the other user into a first vector in a preset order, and concatenates the target user feature vector and target environment vector corresponding to the target user into a second vector in a preset order; determines a first target dimension that has values ​​in both the other smart device vector and the target smart device vector corresponding to the other user, and determines a third vector based on the first target dimension; determines a second target dimension that has values ​​in both the first vector and the second vector, and determines a fourth vector based on the second target dimension; and determines the target user's trust level in the other user based on the third vector and the fourth vector.

[0071] In this embodiment of the application, the server can determine the target user's trust level towards other users according to the following formula:

[0072]

[0073] Among them, tru u (c,d) represents the degree of trust that target user c has in other users d, I c I represents the target user feature vector. d E represents the feature vectors of other users. c E represents the target environment vector. d For other environment vectors, r c Let r represent the target intelligent device vector. dI represents other smart device vectors. d ∪E d Let I represent the first vector. c ∪E c Let r represent the second vector. c ∩r d tru represents the third vector. u (c,d) represents the level of trust.

[0074] In this embodiment of the application, the formula represents the proportion of the same attributes, entities and relationships between target user c and other users d in the entities and relationships of target user u. The larger the proportion, the more characteristics target user u has that are the same as other users v, and the more target user u trusts other users v.

[0075] In this embodiment of the application, after determining the trust level between the target user and each other user, the server determines the total similarity between the target user and each other user based on the first similarity, the second similarity, and the trust level between the target user and the other user.

[0076] To achieve automated control of smart devices by the server, based on the above embodiments, in this embodiment of the application, before obtaining the pre-saved target user feature vector corresponding to the target user and the pre-saved other user feature vectors corresponding to each other user in other households, the method further includes:

[0077] Obtain the pre-saved target family knowledge graph corresponding to the target user, as well as other family knowledge graphs;

[0078] Based on the user feature vectors carried in the target family knowledge graph and other family knowledge graphs, the target family knowledge graph and the other family knowledge graphs are clustered, and other target family knowledge graphs that are in the same class as the target family knowledge graph are identified.

[0079] Obtaining the pre-saved feature vectors of other users for each other user in other households includes:

[0080] Obtain the feature vectors of other users corresponding to the other users from the target other family knowledge graph.

[0081] In this embodiment, the server stores a family knowledge graph corresponding to each family. The family knowledge graph classifies family service domain data into three main categories: environment, user, and device, and their respective subcategories. The environment category includes the external and home environments. The external environment includes features such as region and season. The home environment includes information about the rooms in the family and the attributes within the rooms. The user category includes all users in the family, as well as their attributes and preferences. The device category includes all controllable devices in the family and their functional attributes. Furthermore, the family knowledge graph establishes relationships between classes, such as device-room relationships and user-room relationships.

[0082] Figure 2 This is a schematic diagram of a family knowledge graph provided in an embodiment of this application, as shown below. Figure 2 As shown, this family knowledge graph includes three main categories: users, environment, and devices. The environment category includes external and internal elements; the external element includes region and season, while the internal element includes rooms. The knowledge graph reveals relationships between users and devices, and between devices and rooms.

[0083] After determining the target family knowledge graph corresponding to the target user and the other family knowledge graphs corresponding to other users, in order to reduce the computational burden on the server in calculating the similarity between the target user and other users, in this embodiment of the application, the server will filter other users based on the family knowledge graph and select other users with high similarity to the target user.

[0084] Specifically, in this embodiment, the server obtains the target user feature vector corresponding to the target user carried in the target family knowledge graph, obtains the feature vector of each other user carried in each other family knowledge graph, and clusters the target family knowledge graph and other family knowledge graphs according to the user feature vector and each other user feature vector, and determines the target other family knowledge graphs that are in the same category as the target family knowledge graph.

[0085] In this embodiment of the application, when the server clusters the target family knowledge graph and other family knowledge graphs based on the user feature vector and each other user feature vector, the clustering method used can be the k-means algorithm or other algorithms, which are not limited here.

[0086] In this embodiment of the application, after the server determines the target other family knowledge graph, the server will obtain the other user feature vector corresponding to the other user from the target other family knowledge graph.

[0087] Figure 3 This is a schematic diagram of the target family knowledge graph corresponding to the target user provided in the embodiments of this application. Figure 3As shown, the family knowledge graph includes the target user Zhang San, as well as the user characteristic attributes corresponding to Zhang San (preferring warm temperatures, 60 years old, male, arthritis), the environmental attributes corresponding to Zhang San (elderly room, south-facing room, temperature 32 degrees Celsius, humidity 65%), and electronic devices (air conditioner, fresh air system) that are related to Zhang San.

[0088] Figure 4 This is a schematic diagram of the target other users' corresponding target other families provided in the embodiments of this application, as shown in the diagram. Figure 4 As shown, the family knowledge graph includes the target user Li Si, as well as the user characteristics attributes corresponding to Li Si (preferring warmth, 60 years old, male, rheumatoid arthritis), the environmental attributes corresponding to Li Si (elderly room, room facing south, temperature 30 degrees, humidity 60%), and electronic devices (air conditioner, fresh air system) that are related to Li Si.

[0089] To alleviate the computational burden on the server, based on the above embodiments, in this embodiment, determining the total similarity for each other user according to the first similarity, second similarity, and trust level includes:

[0090] The total similarity for each other user is determined based on the pre-configured first weight, second weight, first similarity, second similarity, and trust level for each other user.

[0091] In this embodiment of the application, the server stores a pre-configured first weight and a second weight. The server can determine the total similarity between the target user and each other user based on the first weight and the second weight, as well as the first similarity, the second similarity, and the trust level between the target user and each other user.

[0092] Specifically, in this embodiment, the server can determine the total similarity using the following formula:

[0093] Trust u (u,v)=α(βsim u (u,v)+(1-β)sim e (u,v))+(1-α)tru u (u,v)

[0094] Among them, Trust u (u,v) represents the total similarity between target user u and other users v, sim u (u,v) represents the first similarity, sim e (u,v) represents the second similarity, tru u (u,v) represents the trust level, α represents the first weight, and β represents the second weight.

[0095] To further achieve automated control of smart devices by the server, based on the above embodiments, in this application embodiment, the method further includes:

[0096] If an end command is received, the execution time of the control scheme for the first target intelligent device is obtained;

[0097] If the execution time is less than a preset time threshold, the first target intelligent device control scheme is added to the scheme blacklist.

[0098] The number of smart device control schemes corresponding to the target other users in the scheme blacklist is counted. If the number exceeds a preset threshold, the target other users are added to the user blacklist.

[0099] In this embodiment of the application, the server stores a time threshold. If the execution time of the first target smart device control scheme by the server does not reach the time threshold, the server will consider that the first target smart device control scheme does not meet the preferences of the target user.

[0100] Specifically, in this embodiment, after executing the first target smart device control scheme, if the server receives an input end command, the server will obtain the execution time of the first target smart device control scheme. If the server determines that the execution time is less than the time threshold, the server determines that the first target smart device control scheme does not meet the target user's preferences, and the server adds the first target smart device control scheme to the scheme blacklist to avoid recommending the first target smart device control scheme to the target user again.

[0101] Furthermore, in this embodiment, the server also counts the number of smart device control schemes corresponding to the target user in the scheme blacklist. If the number exceeds a preset threshold, the target user is added to the user blacklist. Specifically, in this embodiment, if the number of smart device control schemes of the target user in the scheme blacklist exceeds the preset threshold, it means that although the target user is very similar to the target user, the target user's habits and preferences differ significantly from the target user. Therefore, the server adds the target user to the user blacklist to avoid recommending the target user's smart device control scheme to the target user again.

[0102] To further achieve automated control of smart devices by the server, based on the above embodiments, in this application embodiment, before controlling the device using the smart device control scheme, the method further includes:

[0103] Determine whether the smart device control scheme is included in the user blacklist;

[0104] If not, determine whether the intelligent device control scheme is included in the scheme blacklist;

[0105] If not, proceed with the subsequent steps of using the intelligent device control scheme.

[0106] In this embodiment, before using the smart device control scheme for control, the server determines whether the user blacklist contains the first target smart device control scheme, and also determines whether the scheme blacklist contains the first target smart device control scheme. If the user blacklist does not contain the first target smart device control scheme, and the scheme blacklist does not contain the first target smart device control scheme, then the server uses the first target smart device control scheme for control.

[0107] Figure 5 This is a schematic diagram of a server intelligent decision-making process provided in an embodiment of this application. Figure 5 As shown, the process includes:

[0108] S501: The server is controlled using the first target intelligent device control scheme.

[0109] S502: If an input end command is received, the execution time of the first target intelligent device control scheme is obtained. If the execution time is less than the preset time threshold, the first target intelligent device control scheme is added to the scheme blacklist.

[0110] S503: Count the number of smart device control schemes corresponding to other target users in the blacklist. If the number exceeds the preset threshold, add other target users to the user blacklist.

[0111] To further reduce the load on the server, based on the above embodiments, in this embodiment of the application, the method further includes:

[0112] If the execution time exceeds a preset time threshold, the first target intelligent device control scheme will be saved in relation to the current scenario.

[0113] In this embodiment of the application, if the server determines that the execution time of the first target smart device control scheme for other target users has reached a preset time threshold, the server considers that the first target smart device control scheme meets the preferences of the target users, and the server will save the first target smart device control scheme corresponding to the current scenario.

[0114] Figure 6This is a schematic diagram of another server intelligent decision-making process provided in an embodiment of this application, as shown below. Figure 6 As shown, the process includes:

[0115] S601: The server is controlled using the first target intelligent device control scheme.

[0116] S602: If the execution time exceeds the preset time threshold, the control scheme of the first target intelligent device will be saved in relation to the current scene.

[0117] To further reduce the server load, based on the above embodiments, in this embodiment, before obtaining the pre-saved target user feature vector corresponding to the target user, the method further includes:

[0118] Determine whether the target user's smart home control scheme for the current scenario is stored locally;

[0119] If not, proceed with the next step of obtaining the pre-saved target user feature vector corresponding to the target user;

[0120] If so, then obtain the second target smart device control scheme for the target user in the current scenario, which is stored locally, and use the second target smart device control scheme for control.

[0121] To further reduce the computational burden on the server, in this embodiment, after the server determines that the triggering conditions for smart home control for the target user are met, the server will further determine whether the target user's smart home control scheme for the current scenario is stored locally.

[0122] Specifically, in this application embodiment, if the triggering conditions for smart home control of the target user are met, and the smart home control scheme for the target user in the current scenario is not stored locally, the server will obtain the target user feature vector corresponding to the pre-stored target user, as well as the other user feature vectors corresponding to each other user in other households, and determine the first target smart home control scheme to be executed based on the target user feature vector and the other user feature vectors.

[0123] Furthermore, in this embodiment, if the triggering conditions for smart home control of the target user are met and the target user's smart home control scheme in the current scenario is stored locally, the server will obtain the second target smart device control scheme of the target user in the current scenario stored locally and use the second target smart device control scheme for control.

[0124] Figure 7 This is a schematic diagram of a smart home control process provided in an embodiment of this application, as shown below. Figure 7 As shown, the process includes:

[0125] S701: Determine the current trigger conditions that meet the smart home control requirements for the target user.

[0126] S702: Determine whether the target user's smart home control scheme for the current scenario is stored locally. If so, execute S703.

[0127] S703: Obtain the second target smart device control scheme for the target user in the current scenario, which is stored locally, and use the second target smart device control scheme for control.

[0128] Figure 8 This is a schematic diagram of the overall process of smart home control provided in the embodiments of this application, as shown below. Figure 8 As shown, the process includes:

[0129] S801: Determine the current trigger conditions that meet the smart home control requirements for the target user.

[0130] S802: Determine whether the target user's smart home control scheme for the current scenario is stored locally. If yes, execute S803; otherwise, execute S804.

[0131] S803: Obtain the second target smart device control scheme for the target user in the current scenario, which is saved locally, and use the second target smart device control scheme for control.

[0132] S804: Determine the total similarity between the target user and each other user, and identify the other target users with the highest similarity to the target user.

[0133] S805: Obtain the saved target smart device control scheme executed by other users in the current scenario.

[0134] S806: Determine whether the user blacklist contains the first target smart device control scheme. If not, execute S807.

[0135] In this embodiment of the application, if the user blacklist contains the first target smart device control scheme, then the default smart device control scheme is used for control.

[0136] S807: Determine whether the first target intelligent device control scheme is included in the scheme blacklist. If not, execute S808.

[0137] In this embodiment of the application, if the blacklist of schemes includes the first target smart device control scheme, then the default smart device control scheme is used for control.

[0138] S808: Control is performed using the first target intelligent device control scheme.

[0139] Figure 9 This application provides a schematic diagram of a smart home control device, which includes:

[0140] The acquisition module 901 is used to acquire, if the triggering conditions for smart home control for the target user are met, the pre-saved target user feature vector corresponding to the target user and the pre-saved other user feature vectors corresponding to each other user in other households.

[0141] The processing module 902 is used to determine the first similarity between the feature vector of the target user and the feature vector of each of the other users; based on the first similarity corresponding to each other user, determine the target other user with the highest similarity to the target user, and obtain the first target smart device control scheme executed by the target other user in the current scenario.

[0142] The control module 903 is used to control the first target intelligent device using the control scheme.

[0143] In one possible implementation, the acquisition module 901 is further configured to acquire the target environment vector corresponding to the target user, and the other environment vectors corresponding to each other user;

[0144] The processing module 902 is further configured to determine the second similarity between the target environment vector and each other environment vector; and to determine the target other user with the highest similarity to the target user based on the first similarity and the second similarity corresponding to each other user.

[0145] In one possible implementation, the acquisition module 901 is further configured to acquire each target smart device in the target family knowledge graph corresponding to the target user that has a connection relationship with the target user;

[0146] The processing module 902 is further configured to determine the target smart device vector corresponding to the target user based on the pre-configured position of each type of smart device in the smart device vector and each target smart device.

[0147] The acquisition module 901 is further configured to acquire each other smart device that has a connection relationship with the other user in the other family knowledge graph corresponding to the other user;

[0148] The processing module 902 is further configured to: determine the other smart device vector corresponding to the other user based on the pre-configured position of each type of smart device in the smart device vector and each other smart device; for each other user, concatenate the other user feature vector and other environment vectors corresponding to the other user in a preset order to form a first vector, and concatenate the target user feature vector and target environment vector corresponding to the target user in a preset order to form a second vector; determine a first target dimension in which both the other smart device vector and the target smart device vector corresponding to the other user have values, and determine a third vector based on the first target dimension; determine a second target dimension in which both the first vector and the second vector have values, and determine a fourth vector based on the second target dimension; determine the target user's trust level with respect to the other user based on the third vector and the fourth vector; determine the total similarity for each other user based on the first similarity, the second similarity, and the trust value corresponding to each other user, and determine the other user with the highest total similarity as the target other user.

[0149] In one possible implementation, the processing module 902 is specifically used to determine the total similarity of each other user based on the pre-configured first weight, second weight, and the first similarity, second similarity, and trust level corresponding to each other user.

[0150] In one possible implementation, the acquisition module 901 is further configured to acquire a pre-saved target family knowledge graph corresponding to the target user and other family knowledge graphs;

[0151] The processing module 902 is further configured to cluster the target family knowledge graph and the other family knowledge graphs based on the user feature vectors carried in the target family knowledge graph and the other family knowledge graphs, and determine the other target family knowledge graphs that are in the same class as the target family knowledge graph;

[0152] The acquisition module 901 is specifically used to acquire the feature vectors of other users corresponding to the other users from the target other family knowledge graph.

[0153] In one possible implementation, the processing module 902 is further configured to: if an input end command is received, obtain the execution duration of the first target smart device control scheme; if the execution duration is less than a preset duration threshold, add the first target smart device control scheme to the scheme blacklist; count the number of smart device control schemes corresponding to the target other users in the scheme blacklist; if the number exceeds a preset number threshold, add the target other users to the user blacklist.

[0154] In one possible implementation, the processing module 902 is further configured to determine whether the user blacklist contains the first target smart device control scheme; if not, determine whether the scheme blacklist contains the first target smart device control scheme; if not, execute the subsequent steps of using the first target smart device control scheme for control.

[0155] In one possible implementation, the processing module 902 is further configured to save the first target intelligent device control scheme corresponding to the current scene if the execution time exceeds a preset time threshold.

[0156] In one possible implementation, the processing module 902 is further configured to determine whether the target user's smart home control scheme in the current scenario is stored locally.

[0157] The acquisition module 901 is also configured to, if not, execute the subsequent step of acquiring the target user feature vector corresponding to the pre-saved target user; if yes, acquire the second target smart device control scheme of the target user in the current scenario that is stored locally.

[0158] The control module 903 is also used to control the target intelligent device using the second target intelligent device control scheme.

[0159] Based on the above embodiments, one or more embodiments of the present invention also provide an electronic device. Figure 10 A schematic diagram of an electronic device structure is provided for one or more embodiments of the present invention, such as... Figure 10 As shown, it includes: processor 1001, communication interface 1002, memory 1003 and communication bus 1004, wherein processor 1001, communication interface 1002 and memory 1003 communicate with each other through communication bus 1010.

[0160] The memory 1003 stores a computer program. When the program is executed by the processor 1001, the processor 1001 performs the following steps:

[0161] If the triggering conditions for smart home control for the target user are met, then obtain the pre-saved target user feature vector corresponding to the target user, and the pre-saved other user feature vectors corresponding to each other user in other households;

[0162] Determine the first similarity between the target user feature vector and each of the other user feature vectors;

[0163] Based on the first similarity corresponding to each other user, determine the target other user with the highest similarity to the target user, obtain the saved first target smart device control scheme executed by the target other user in the current scenario, and use the first target smart device control scheme for control.

[0164] The processor is also used for:

[0165] Obtain the saved target environment vector corresponding to the target user, and the saved other environment vectors corresponding to each other user;

[0166] Determine the second similarity between the target environment vector and each other environment vector;

[0167] The step of determining the target other user with the highest similarity to the target user based on the first similarity corresponding to each other user includes:

[0168] Based on the first similarity and second similarity of each other user, the target other user with the highest similarity to the target user is determined.

[0169] The processor is also used for:

[0170] Obtain each target smart device that has a connection relationship with the target user in the target family knowledge graph corresponding to the target user, and determine the target smart device vector corresponding to the target user based on the pre-configured position of each type of smart device in the smart device vector and each target smart device;

[0171] Obtain each other smart device that has a connection relationship with the other user in the other family knowledge graph corresponding to the other user, and determine the other smart device vector corresponding to the other user based on the pre-configured position of each type of smart device in the smart device vector and each other smart device;

[0172] For each other user, the other user feature vector and other environment vectors corresponding to that other user are concatenated into a first vector in a preset order; the target user feature vector and target environment vector corresponding to the target user are concatenated into a second vector in a preset order; a first target dimension is determined where both the other smart device vector and the target smart device vector corresponding to that other user have values, and a third vector is determined based on the first target dimension; a second target dimension is determined where both the first vector and the second vector have values, and a fourth vector is determined based on the second target dimension; the target user's trust level towards that other user is determined based on the third vector and the fourth vector.

[0173] The processor is also used for:

[0174] Based on the first similarity, second similarity, and trust value of each other user, the total similarity of each other user is determined, and the other user with the highest total similarity is identified as the target other user.

[0175] The processor is also used for:

[0176] The total similarity for each other user is determined based on the pre-configured first weight, second weight, first similarity, second similarity, and trust level for each other user.

[0177] The processor is also used for:

[0178] Obtain the pre-saved target family knowledge graph corresponding to the target user, as well as other family knowledge graphs;

[0179] Based on the user feature vectors carried in the target family knowledge graph and other family knowledge graphs, the target family knowledge graph and the other family knowledge graphs are clustered, and other target family knowledge graphs that are in the same class as the target family knowledge graph are identified.

[0180] The processor is also used for:

[0181] Obtain the feature vectors of other users corresponding to the other users from the target other family knowledge graph.

[0182] The processor is also used for:

[0183] If an end command is received, the execution time of the control scheme for the first target intelligent device is obtained;

[0184] If the execution time is less than a preset time threshold, the first target intelligent device control scheme is added to the scheme blacklist.

[0185] The number of smart device control schemes corresponding to the target other users in the scheme blacklist is counted. If the number exceeds a preset threshold, the target other users are added to the user blacklist.

[0186] The processor is also used for:

[0187] Determine whether the user blacklist contains the first target smart device control scheme;

[0188] If not, determine whether the blacklist of the proposed solutions contains the first target smart device control solution;

[0189] If not, then proceed with the subsequent steps of using the first target intelligent device control scheme for control.

[0190] The processor is also used for:

[0191] If the execution time exceeds a preset time threshold, the first target intelligent device control scheme will be saved in relation to the current scenario.

[0192] The processor is also used for:

[0193] Determine whether the target user's smart home control scheme for the current scenario is stored locally;

[0194] If not, proceed with the next step of obtaining the pre-saved target user feature vector corresponding to the target user;

[0195] If so, then obtain the second target smart device control scheme for the target user in the current scenario, which is stored locally, and use the second target smart device control scheme for control.

[0196] Since the principle behind the problem-solving of the above-mentioned electronic devices is similar to that of smart home control methods, the implementation of the above-mentioned electronic devices can be found in the embodiments of the method, and repeated details will not be repeated.

[0197] The communication bus mentioned in the aforementioned electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not indicate that there is only one bus or one type of bus. The communication interface 1002 is used for communication between the aforementioned electronic device and other devices. The memory can include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory can also be at least one storage device located remotely from the aforementioned processor.

[0198] The processors mentioned above can be general-purpose processors, including central processing units, network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits, field-programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0199] Based on the above embodiments, this invention also provides a computer-readable storage medium storing a computer program executable by a processor. When the program runs on the processor, it causes the processor to perform the following steps:

[0200] If the triggering conditions for smart home control for the target user are met, then obtain the pre-saved target user feature vector corresponding to the target user, and the pre-saved other user feature vectors corresponding to each other user in other households;

[0201] Determine the first similarity between the target user feature vector and each of the other user feature vectors;

[0202] Based on the first similarity corresponding to each other user, determine the target other user with the highest similarity to the target user, obtain the saved first target smart device control scheme executed by the target other user in the current scenario, and use the first target smart device control scheme for control.

[0203] In one possible implementation, before determining the target other user with the highest similarity to the target user based on the first similarity corresponding to each other user, the method further includes:

[0204] Obtain the saved target environment vector corresponding to the target user, and the saved other environment vectors corresponding to each other user;

[0205] Determine the second similarity between the target environment vector and each other environment vector;

[0206] The step of determining the target other user with the highest similarity to the target user based on the first similarity corresponding to each other user includes:

[0207] Based on the first similarity and second similarity of each other user, the target other user with the highest similarity to the target user is determined.

[0208] In one possible implementation, before determining the target other user with the highest similarity to the target user based on the first similarity corresponding to each other user, the method further includes:

[0209] Obtain each target smart device that has a connection relationship with the target user in the target family knowledge graph corresponding to the target user, and determine the target smart device vector corresponding to the target user based on the pre-configured position of each type of smart device in the smart device vector and each target smart device;

[0210] Obtain each other smart device that has a connection relationship with the other user in the other family knowledge graph corresponding to the other user, and determine the other smart device vector corresponding to the other user based on the pre-configured position of each type of smart device in the smart device vector and each other smart device;

[0211] For each other user, the other user feature vector and other environment vectors corresponding to that other user are concatenated into a first vector in a preset order; the target user feature vector and target environment vector corresponding to the target user are concatenated into a second vector in a preset order; a first target dimension is determined where both the other smart device vector and the target smart device vector corresponding to that other user have values, and a third vector is determined based on the first target dimension; a second target dimension is determined where both the first vector and the second vector have values, and a fourth vector is determined based on the second target dimension; the target user's trust level towards that other user is determined based on the third vector and the fourth vector.

[0212] The step of determining the target other user with the highest similarity to the target user based on the first similarity corresponding to each other user includes:

[0213] Based on the first similarity, second similarity, and trust value of each other user, the total similarity of each other user is determined, and the other user with the highest total similarity is identified as the target other user.

[0214] In one possible implementation, determining the total similarity for each other user based on the first similarity, second similarity, and trust level for each other user includes:

[0215] The total similarity for each other user is determined based on the pre-configured first weight, second weight, first similarity, second similarity, and trust level for each other user.

[0216] In one possible implementation, before obtaining the pre-saved target user feature vector corresponding to the target user and the pre-saved other user feature vectors corresponding to each other user in other households, the method further includes:

[0217] Obtain the pre-saved target family knowledge graph corresponding to the target user, as well as other family knowledge graphs;

[0218] Based on the user feature vectors carried in the target family knowledge graph and other family knowledge graphs, the target family knowledge graph and the other family knowledge graphs are clustered, and other target family knowledge graphs that are in the same class as the target family knowledge graph are identified.

[0219] Obtaining the pre-saved feature vectors of other users for each other user in other households includes:

[0220] Obtain the feature vectors of other users corresponding to the other users from the target other family knowledge graph.

[0221] In one possible implementation, the method further includes:

[0222] If an end command is received, the execution time of the control scheme for the first target intelligent device is obtained;

[0223] If the execution time is less than a preset time threshold, the first target intelligent device control scheme is added to the scheme blacklist.

[0224] The number of smart device control schemes corresponding to the target other users in the scheme blacklist is counted. If the number exceeds a preset threshold, the target other users are added to the user blacklist.

[0225] In one possible implementation, before controlling the device using the first target intelligent device control scheme, the method further includes:

[0226] Determine whether the user blacklist contains the first target smart device control scheme;

[0227] If not, determine whether the blacklist of the proposed solutions contains the first target smart device control solution;

[0228] If not, then proceed with the subsequent steps of using the first target intelligent device control scheme for control.

[0229] In one possible implementation, the method further includes:

[0230] If the execution time exceeds a preset time threshold, the first target intelligent device control scheme will be saved in relation to the current scenario.

[0231] In one possible implementation, before obtaining the pre-saved target user feature vector corresponding to the target user, the method further includes:

[0232] Determine whether the target user's smart home control scheme for the current scenario is stored locally;

[0233] If not, proceed with the next step of obtaining the pre-saved target user feature vector corresponding to the target user;

[0234] If so, then obtain the second target smart device control scheme for the target user in the current scenario, which is stored locally, and use the second target smart device control scheme for control.

[0235] Since the principle of the computer-readable storage medium in solving the problem is similar to that of the smart home controller, the implementation of the computer-readable storage medium can be found in the embodiments of the method, and repeated details will not be repeated.

[0236] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0237] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0238] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0239] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0240] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A smart home control method, characterized in that, The method includes: If the triggering conditions for smart home control for the target user are met, then obtain the pre-saved target user feature vector corresponding to the target user, and the pre-saved other user feature vectors corresponding to each other user in other households; Determine the first similarity between the target user feature vector and each of the other user feature vectors; Obtain each target smart device that has a connection relationship with the target user in the target family knowledge graph corresponding to the target user, and determine the target smart device vector corresponding to the target user based on the pre-configured position of each type of smart device in the smart device vector and each target smart device; Obtain each other smart device that has a connection relationship with the other user in the other family knowledge graph corresponding to the other user, and determine the other smart device vector corresponding to the other user based on the pre-configured position of each type of smart device in the smart device vector and each other smart device; For each other user, the other user feature vector and other environment vectors corresponding to that other user are concatenated into a first vector in a preset order; the target user feature vector and target environment vector corresponding to the target user are concatenated into a second vector in a preset order; a first target dimension is determined where both the other smart device vector and the target smart device vector corresponding to that other user have values, and a third vector is determined based on the first target dimension; a second target dimension is determined where both the first vector and the second vector have values, and a fourth vector is determined based on the second target dimension; the target user's trust level towards that other user is determined based on the third vector and the fourth vector. Based on the first similarity, second similarity, and trust level of each other user, the total similarity of each other user is determined, and the other user with the highest total similarity is identified as the target other user; and the first target intelligent device control scheme executed by the target other user in the current scenario is obtained and controlled using the first target intelligent device control scheme.

2. The method according to claim 1, characterized in that, Before determining the target other user with the highest similarity to the target user based on the first similarity corresponding to each other user, the method further includes: Obtain the saved target environment vector corresponding to the target user, and the saved other environment vectors corresponding to each other user; Determine the second similarity between the target environment vector and each other environment vector; The step of determining the target other user with the highest similarity to the target user based on the first similarity corresponding to each other user includes: Based on the first similarity and second similarity of each other user, the target other user with the highest similarity to the target user is determined.

3. The method according to claim 1, characterized in that, The determination of the total similarity for each other user based on the first similarity, second similarity, and trust level includes: The total similarity for each other user is determined based on the pre-configured first weight, second weight, first similarity, second similarity, and trust level for each other user.

4. The method according to claim 1, characterized in that, Before obtaining the pre-saved target user feature vector corresponding to the target user, and the pre-saved other user feature vectors corresponding to each other user in other households, the method further includes: Obtain the pre-saved target family knowledge graph corresponding to the target user, as well as other family knowledge graphs; Based on the user feature vectors carried in the target family knowledge graph and other family knowledge graphs, the target family knowledge graph and the other family knowledge graphs are clustered, and other target family knowledge graphs that are in the same class as the target family knowledge graph are identified. Obtaining the pre-saved feature vectors of other users for each other user in other households includes: Obtain the feature vectors of other users corresponding to the other users from the target other family knowledge graph.

5. The method according to claim 1, characterized in that, The method further includes: If an end command is received, the execution time of the control scheme for the first target intelligent device is obtained; If the execution time is less than a preset time threshold, the first target intelligent device control scheme is added to the scheme blacklist. The number of smart device control schemes corresponding to the target other users in the scheme blacklist is counted. If the number exceeds a preset threshold, the target other users are added to the user blacklist.

6. The method according to claim 5, characterized in that, Before using the first target intelligent device control scheme for control, the method further includes: Determine whether the user blacklist contains the first target smart device control scheme; If not, determine whether the blacklist of the proposed solutions contains the first target smart device control solution; If not, then proceed with the subsequent steps of using the first target intelligent device control scheme for control.

7. The method according to claim 5, characterized in that, The method further includes: If the execution time exceeds a preset time threshold, the first target intelligent device control scheme will be saved in relation to the current scenario.

8. The method according to claim 1, characterized in that, Before obtaining the pre-saved target user feature vector corresponding to the target user, the method further includes: Determine whether the target user's smart home control scheme for the current scenario is stored locally; If not, proceed with the next step of obtaining the pre-saved target user feature vector corresponding to the target user; If so, then obtain the second target smart device control scheme of the target user in the current scenario that is stored locally, and use the second target smart device control scheme for control.

9. An electronic device, characterized in that, The electronic device includes a processor that executes a computer program stored in a memory to implement the steps of the smart home control method as described in any one of claims 1-8.

Images