Smart home control method and system based on knowledge graph

Abstract

The invention discloses a smart home control method and system based on a knowledge graph, and belongs to the field of data processing, and the method comprises the steps: obtaining the demand information of a user; collecting user family member information, household equipment and equipment attribute information, and carrying out data preprocessing; carrying out entity identification on the smart home system, and mapping home equipment and equipment attributes to entities and attributes in a knowledge graph to be constructed; extracting the relationship between entities in the smart home system to obtain a complete knowledge graph; the demand information is converted into query information, and a corresponding query result is obtained by using a knowledge graph, so that the household equipment is controlled; optimizing the knowledge graph according to the use habits of the user and the equipment attributes; and regularly updating and managing the knowledge graph. According to the smart home control method and system based on the knowledge graph, the knowledge graph is utilized to realize more intelligent control and management of the smart home, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a smart home control method and system based on a knowledge graph. Background Art

[0002] Knowledge Graph is a semantic network that describes various entities and their relationships in the real world in a graph mode. Through the knowledge graph, not only can the information on the Internet be expressed in a form closer to the human cognitive world, but it also provides a better way to organize, manage and utilize massive information. By using the knowledge graph in the search engine, it is possible to better query complex related information, understand user intent from a semantic level, and improve search quality.

[0003] As people's living standards improve, smart home devices are becoming more and more commonly used in people's daily life and study.

[0004] In the existing technology, smart home devices can connect various devices in the home through the Internet of Things technology, and then provide functions such as home appliance control, lighting control, anti-theft alarm, and environmental monitoring. In the process of realizing the functions, a large amount of business data will be involved, and different business data are interrelated. However, existing smart home solutions often have problems such as independent operation of devices and cumbersome operations. The coordination between devices is not smooth enough, and the control relationship between them is not clear enough. Summary of the invention

[0005] The purpose of the present invention is to provide a smart home control method and system based on knowledge graph to solve the problems mentioned in the above background technology.

[0006] To achieve the above object, the present invention provides a smart home control method based on knowledge graph, comprising the following steps:

[0007] S1. Obtain user demand information;

[0008] S2. Collect information about the user's family members, home devices and device attributes, and perform data preprocessing;

[0009] S3, perform entity recognition on the smart home system, and map home devices and device attributes to entities and attributes in the knowledge graph to be constructed;

[0010] S4. Extract the relationships between entities in the smart home system, establish the edges of the knowledge graph to be constructed, and obtain a complete knowledge graph;

[0011] S5. Analyze the user's demand information, convert the demand information into query information, and use the knowledge graph to obtain the corresponding query results, and then control the home devices;

[0012] S6. Optimize the knowledge graph based on user usage habits and device attributes;

[0013] S7. Regularly update and manage the knowledge graph.

[0014] Preferably, in S3, the preprocessed user family member information, home devices and device attribute information are used to train a convolutional neural network to obtain the characteristics and relationships of the entities, and the formula is as follows:

[0015] y=f(W*x+b)

[0016] Where y is the output, f is the activation function, W is the weight matrix, x is the input, b is the bias vector, and * is the convolution operation.

[0017] Preferably, S4 is specifically:

[0018] Define the application areas and goals of smart home systems, and collect knowledge and information related to the application areas and goals;

[0019] Design entities and relationships in the knowledge graph based on knowledge information, and define attributes and attribute values ​​for each entity and relationship;

[0020] Establish associations and hierarchies between entities and relationships, import the collected knowledge information into the associations and hierarchies, and build a knowledge graph by integrating and cleaning the knowledge.

[0021] Preferably, S5 is specifically:

[0022] Real-time monitoring of query language information input by users;

[0023] Perform semantic analysis on the query language information input by the user, obtain semantic analysis results, and conduct analysis;

[0024] Set up the knowledge graph question-answering interface;

[0025] Input the analysis information corresponding to the semantic analysis result into the knowledge graph, use the knowledge graph to search, and obtain the query result corresponding to the semantic analysis result;

[0026] Feedback the query results corresponding to the semantic analysis results to the user.

[0027] Preferably, entities include devices, scenes and users in the smart home system; relationships include relationships between devices and relationships between devices and scenes.

[0028] Preferably, the knowledge information includes specifications, functions, interaction methods, working modes and applicable scenarios of home devices in the smart home system.

[0029] A smart home control system based on knowledge graph, including the following modules:

[0030] An acquisition module, used to acquire information;

[0031] An entity recognition module, used to map entities in the smart home system;

[0032] The entity extraction module is used to extract the relationship between entities;

[0033] The knowledge graph update module is used to update the initial knowledge graph.

[0034] Therefore, the present invention adopts the above-mentioned smart home control method and system based on knowledge graph, which has the following beneficial effects:

[0035] (1) Knowledge graphs help smart home systems better understand user needs and achieve more intelligent control and management;

[0036] (2) Knowledge graphs help smart home systems provide more personalized recommendations and suggestions to improve user experience;

[0037] (3) Knowledge graphs help smart home systems process and analyze device data more efficiently, achieving more efficient device management.

[0038] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a schematic diagram of the overall process of an embodiment of the present invention;

[0040] Figure 2 Schematic diagram of a system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] Example

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.

[0043] Reference Figure 1 The present invention discloses a smart home control method based on knowledge graph, comprising the following steps:

[0044] S1. Obtain user demand information;

[0045] S2. Collect information about the user's family members, home devices and device attributes, and perform data preprocessing; home devices are all IoT devices.

[0046] S3, perform entity recognition on the smart home system, and map home devices and device attributes to entities and attributes in the knowledge graph to be constructed;

[0047] The preprocessed user family member information, home devices and device attribute information are used to train the convolutional neural network to obtain the characteristics and relationships of the entities. The formula is as follows:

[0048] y=f(W*x+b)

[0049] Where y is the output, f is the activation function, W is the weight matrix, x is the input, b is the bias vector, and * is the convolution operation.

[0050] S4. Extract the relationships between entities in the smart home system, establish the edges of the knowledge graph to be constructed, and obtain a complete knowledge graph; through the knowledge graph, the system can understand the user's query, identify IoT devices and information, and provide intelligent control according to user needs, such as controlling the status of IoT devices or obtaining relevant information.

[0051] Specifically:

[0052] Define the application areas and goals of smart home systems, and collect knowledge and information related to the application areas and goals;

[0053] Design entities and relationships in the knowledge graph based on knowledge information, and define attributes and attribute values ​​for each entity and relationship;

[0054] Establish associations and hierarchies between entities and relationships, import the collected knowledge information into the associations and hierarchies, and build a knowledge graph by integrating and cleaning the knowledge.

[0055] Entities include devices, scenarios, and users in the smart home system; relationships include relationships between devices and relationships between devices and scenarios.

[0056] Knowledge information includes the specifications, functions, interaction methods, working modes and applicable scenarios of home devices in the smart home system.

[0057] S5. Analyze the user's demand information, convert the demand information into query information, and use the knowledge graph to obtain the corresponding query results, and then control the home devices; by converting the query language information into machine-understandable query information, users can interact with the system using natural language or specific query language without writing complex commands or codes. Due to the existence of the knowledge graph, the system can understand the user's query and needs more accurately, provide more accurate query results, and improve the user experience.

[0058] Specifically:

[0059] Real-time monitoring of query language information input by users;

[0060] Perform semantic analysis on the query language information input by the user, obtain semantic analysis results, and conduct analysis;

[0061] Set up the knowledge graph question-answering interface;

[0062] Input the analysis information corresponding to the semantic analysis result into the knowledge graph, use the knowledge graph to search, and obtain the query result corresponding to the semantic analysis result;

[0063] The query results corresponding to the semantic analysis results are fed back to the user.

[0064] S6. Optimize the knowledge graph based on user usage habits and device attributes;

[0065] S7. Regularly update and manage the knowledge graph. Regularly update and manage the knowledge graph to ensure that the system can provide the latest information and data to reflect changes in the IoT environment.

[0066] The knowledge graph model can be continuously expanded, and new entities and relationships can be added to meet changing needs as the IoT field develops.

[0067] like Figure 2 , a smart home control system based on knowledge graph, including the following modules:

[0068] An acquisition module, used to acquire information;

[0069] An entity recognition module, used to map entities in the smart home system;

[0070] The entity extraction module is used to extract the relationship between entities;

[0071] The knowledge graph update module is used to update the initial knowledge graph.

[0072] By building a knowledge graph, the diverse data in the field of IoT is integrated into a unified structure, making the associations between different data sources clear and visible. The knowledge graph gives the system powerful query and retrieval capabilities, and users can easily find information related to the IoT, whether it is device information, sensor data, or other related data. After the knowledge graph is built, intelligent applications can be developed based on it for monitoring, control, optimization, and decision support of IoT devices, thereby improving the intelligence and automation of IoT systems. The knowledge graph makes the associations between different entities and data clearer, helps to better understand the complex relationships in the IoT, and supports data analysis and insights. It can be updated and maintained regularly to ensure that it reflects the latest status of the IoT environment and maintains accuracy and availability.

[0073] Therefore, the present invention adopts the above-mentioned knowledge graph-based smart home control method and system, and uses the knowledge graph to achieve more intelligent control and management of the smart home, thereby improving the user experience.

[0074] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A smart home control method based on knowledge graph, characterized in that: The following steps are involved: S1. Obtain user demand information; S2. Collect information about the user's family members, home devices and device attributes, and perform data preprocessing; S3, perform entity recognition on the smart home system, and map home devices and device attributes to entities and attributes in the knowledge graph to be constructed; S4. Extract the relationships between entities in the smart home system, establish the edges of the knowledge graph to be constructed, and obtain a complete knowledge graph; S5. Analyze the user's demand information, convert the demand information into query information, and use the knowledge graph to obtain the corresponding query results, and then control the home devices; S6. Optimize the knowledge graph based on user usage habits and device attributes; S7. Regularly update and manage the knowledge graph.

2. According to claim 1, a smart home control method based on knowledge graph is characterized in that: In S3, the preprocessed user family member information, home devices and device attribute information are used to train the convolutional neural network to obtain the characteristics and relationships of the entities. The formula is as follows: y=f(W*x+b) Where y is the output, f is the activation function, W is the weight matrix, x is the input, b is the bias vector, and * is the convolution operation.

3. According to claim 1, a smart home control method based on knowledge graph is characterized in that: S4 is specifically: Define the application areas and goals of smart home systems, and collect knowledge and information related to the application areas and goals; Design entities and relationships in the knowledge graph based on knowledge information, and define attributes and attribute values ​​for each entity and relationship; Establish associations and hierarchies between entities and relationships, import the collected knowledge information into the associations and hierarchies, and build a knowledge graph by integrating and cleaning the knowledge.

4. According to claim 1, a smart home control method based on knowledge graph is characterized in that: S5 is as follows: Real-time monitoring of query language information input by users; Perform semantic analysis on the query language information input by the user, obtain semantic analysis results, and conduct analysis; Set up the knowledge graph question-answering interface; Input the analysis information corresponding to the semantic analysis result into the knowledge graph, use the knowledge graph to search, and obtain the query result corresponding to the semantic analysis result; The query results corresponding to the semantic analysis results are fed back to the user.

5. The method for controlling a smart home based on a knowledge graph according to claim 3, characterized in that: Entities include home devices, scenarios, and users in the smart home system; relationships include the relationships between home devices and the relationships between home devices and scenarios.

6. The method for controlling a smart home based on a knowledge graph according to claim 3, characterized in that: Knowledge information includes the specifications, functions, interaction methods, working modes and applicable scenarios of home devices in the smart home system.

7. A system using a knowledge graph-based smart home control method as described in any one of claims 1 to 6, characterized in that: Includes the following modules: An acquisition module, used to acquire information; An entity recognition module, used to map entities in the smart home system; The entity extraction module is used to extract the relationship between entities; The knowledge graph update module is used to update the initial knowledge graph.

Images