CN106713083B - Intelligent household equipment control method, device and system based on knowledge graph - Google Patents
Intelligent household equipment control method, device and system based on knowledge graph Download PDFInfo
- Publication number
- CN106713083B CN106713083B CN201611050982.0A CN201611050982A CN106713083B CN 106713083 B CN106713083 B CN 106713083B CN 201611050982 A CN201611050982 A CN 201611050982A CN 106713083 B CN106713083 B CN 106713083B
- Authority
- CN
- China
- Prior art keywords
- determining
- nodes
- node
- service path
- knowledge
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/2803—Home automation networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/24—Multipath
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Selective Calling Equipment (AREA)
Abstract
The embodiment of the invention relates to the technical field of intelligent control, in particular to a method, a device and a system for controlling intelligent household equipment based on a knowledge graph. Wherein the method comprises the following steps: extracting each keyword from an interactive command input by a user; determining nodes corresponding to the keywords in the knowledge graph network; determining each service path formed by the node corresponding to each keyword in the knowledge graph network according to the sequence of each keyword in the interactive command; determining the cost value of each service path according to the connecting edges between the nodes in each service path and the weight values on the corresponding connecting edges; and determining the minimum value in the cost values, and determining the intelligent household equipment controlled by the interactive command according to the service path corresponding to the minimum value. The intelligent home equipment control method and device based on the knowledge graph can solve the problem of determining the service path when the intelligent home equipment is controlled by using a knowledge graph network.
Description
Technical Field
The embodiment of the invention relates to the technical field of intelligent control, in particular to a method, a device and a system for controlling intelligent household equipment based on a knowledge graph.
Background
The intelligent home is characterized in that a home is used as a platform, and the technologies such as a comprehensive wiring technology, a network communication technology, a safety precaution technology and the like are utilized to integrate facilities related to home life, so that an efficient management system for home facilities and family schedule affairs is constructed. With the rapid development of smart homes, various smart home devices enter thousands of households, such as smart lighting devices, smart televisions, smart refrigerators, smart air conditioners, and the like. In the process of using the intelligent household equipment, for convenience in operation, a user can control the intelligent household equipment through voice. For example, the user can control the opening of the intelligent refrigerator by voice 'open the refrigerator'.
In the prior art, there are two main methods for a user to control smart home devices through voice: when the microphone on the intelligent household equipment receives the voice information, the voice information is forwarded to the voice recognition device on the intelligent household equipment. The voice recognition device recognizes the voice information and generates a control instruction, and the control instruction is used for indicating the intelligent household equipment to execute corresponding operation.
In the process of implementing the invention, the inventor finds that the prior art has at least the following problems:
in the prior art, if a user wants to control smart home devices by voice, each smart home device must be equipped with a microphone and a voice recognition device, which results in an excessive cost for controlling smart home devices by voice. Meanwhile, in order to enable the microphone on the intelligent household equipment to smoothly receive the voice information sent by the user, the position of the user needs to be kept near the intelligent household equipment when the user sends the voice information, and the flexibility of controlling the intelligent household equipment through voice is reduced.
In order to reduce the cost of controlling the smart home devices by voice and increase the flexibility of control, the prior art also provides another method for controlling the smart home devices by voice: the method comprises the steps that the intelligent household equipment is connected to the control equipment in a wired or wireless mode, when a microphone on the control equipment receives voice information, the voice information is forwarded to a voice recognition device on the control equipment, the voice recognition device recognizes the received voice, the controlled intelligent household equipment is determined according to a recognition result, and a control instruction is generated, wherein the control instruction is used for indicating the determined controlled intelligent household equipment to execute corresponding operation.
In the process of implementing the invention, the inventor finds that: in the scene of controlling the intelligent household equipment through the control equipment, each intelligent household equipment does not need to be additionally provided with a microphone and a voice recognition device for voice recognition, the cost of the voice control intelligent household equipment can be reduced, and because the control equipment is connected with the intelligent household equipment in a wireless or wired mode, a user does not need to keep nearby the intelligent household equipment when controlling the intelligent household equipment, and the flexibility of the voice control intelligent household equipment is improved.
It should be noted that, although there are many advantages in the above scheme of controlling the smart home devices through the control device, the inventor finds that: when a user wants to control the smart home device through the control device by voice, the user is required to clearly indicate a controlled object in the voice information input by the user, and if the user does not clearly indicate which smart home device to control, the control device may not determine the controlled smart home device, and thus the control of the smart home device cannot be completed. For example, the voice information input by the user in the control device is "what the indoor temperature is at present", the smart home devices capable of responding to the voice information may have various types, such as an air conditioner, a temperature and humidity sensor, an electronic thermometer, and the like, and since the controlled object is not indicated in the voice information input by the user, the main control device cannot determine which smart home device executes the user's command.
Therefore, in an intelligent home control scene, when the controlled object information is missing from the voice information input by the user, how to determine the controlled intelligent home device becomes an urgent problem to be solved.
Disclosure of Invention
The embodiment of the invention provides a method and a device for controlling intelligent household equipment based on a knowledge graph, and aims to solve the problem that the controlled intelligent household equipment is determined when the information of a controlled object is lost in control information input by a user.
In a first aspect, an embodiment of the present invention provides a method for controlling smart home devices based on a knowledge graph, including:
extracting each keyword from an interactive command input by a user;
determining a corresponding node of the keyword in a knowledge graph network;
determining each service path formed by the node corresponding to each keyword in the knowledge graph network according to the sequence of each keyword in the interactive command;
determining the cost value of each service path according to the connecting edges between the nodes in each service path and the weight values on the corresponding connecting edges;
and determining the minimum value in the cost values, and determining the intelligent household equipment controlled by the interactive command according to the service path corresponding to the minimum value.
In a second aspect, an embodiment of the present invention provides an intelligent home device control apparatus based on a knowledge graph network, including: the system comprises a processor, a memory and a communication interface, wherein the processor, the memory and the communication interface are connected through a communication bus;
the communication interface is used for receiving an interactive command input by a user;
the memory for storing program code;
the processor is configured to read the program codes stored in the memory and execute the method for controlling smart home devices based on the intellectual graph network according to any one of claims 1 to 8.
In a third aspect, an embodiment of the present invention provides an intelligent home system, including: the intelligent household equipment comprises a plurality of pieces of intelligent household equipment and control equipment, wherein the control equipment is provided with the control device;
the control device is connected with the plurality of smart home devices respectively, and controls the plurality of smart home devices according to the method of any one of claims 1 to 8.
In the intelligent home equipment control scheme of the embodiment of the invention, a knowledge graph technology is introduced, namely, a network formed by intelligent home equipment is abstracted into a knowledge graph network, nodes in the knowledge graph network represent the intelligent home equipment or related data of the intelligent home equipment, connecting edges between the nodes in the knowledge graph network represent the incidence relation between the intelligent home equipment, after a control device of the intelligent home equipment receives an interactive command input by a user, each keyword is extracted from the interactive command input by the user, and the corresponding node of each keyword in the knowledge graph network is determined; after determining the nodes corresponding to the keywords, the control device determines each service path formed by the nodes corresponding to the keywords in the knowledge graph network according to the sequence of the keywords in the interaction command, then determines the cost value of each service path according to the connection edges between the nodes in each service path and the weight values on the corresponding connection edges, and determines the intelligent home equipment controlled by the interaction command according to the service path with the minimum cost value.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of embodiments of the invention.
Drawings
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.
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
FIG. 1 is a schematic diagram of an architecture of a knowledge-graph network in accordance with an embodiment of the present invention;
fig. 2 is a flowchart of a method for selecting a service path according to an embodiment of the present invention;
FIG. 3 is a flow chart of a second service path selection method according to an embodiment of the present invention;
FIG. 4 is a flowchart of a specific example of processing according to a second embodiment of the present invention;
FIGS. 5A-5D are schematic diagrams of nodes corresponding to respective keywords;
FIG. 6 is a schematic view of a knowledge-graph network of the located nodes of FIGS. 5A-5D;
FIG. 7 is a schematic illustration of a traffic path formed by the nodes of FIG. 6;
fig. 8 is a schematic structural diagram of a traffic path selecting apparatus according to an embodiment of the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the drawings in the embodiment of the present invention, and it is obvious that the described embodiment is only a part of the embodiment of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
FIG. 1 is a schematic diagram of a knowledge-graph network. As shown in fig. 1, the knowledge-graph network is a network that uses nodes (corresponding to dots in fig. 1) and connecting edges between the nodes (corresponding to connecting lines between dots in fig. 1) to represent association between the nodes. In the knowledge graph network, nodes can be any information bodies needing to be represented, if the two nodes have an incidence relation, the two nodes are connected by a connecting edge, and the connecting edge can be distributed with a weight value to represent the probability of the incidence relation between the two nodes; if the two nodes have no association relationship, no connecting edge is connected between the two nodes.
Fig. 2 is a schematic structural diagram of an intelligent home system according to an embodiment of the present invention. As shown in fig. 2, the smart home system includes: the intelligent home system comprises a control device 101, and various intelligent home devices such as a television 102, an air conditioner 103, a refrigerator 104, a temperature and humidity sensor 105 and the like which are respectively connected with the control device 101. Optionally, the control device 101 may be a computer, a mobile phone, or another device with an operation control function, and further, the control device 101 may also be a controlled device 101 in the smart home system, that is, one or more smart home devices in the smart home system may be used as both a controlled device and a master control device.
In order to realize control over the intelligent home devices, a knowledge graph technology is introduced into the intelligent home device control method provided by the embodiment of the invention, that is, a network formed by the intelligent home devices is abstractly represented into a knowledge graph network as shown in fig. 1.
For example, in the smart home system shown in fig. 2, the knowledge graph network shown in fig. 1 may be used to represent each smart home device and data associated with each smart home device in the smart home system.
For example, the nodes in fig. 1 may represent devices such as the television 102, the air conditioner 103, the refrigerator 104, and the temperature and humidity sensor 105, and the nodes in fig. 1 may also represent data nodes such as the channel, temperature, humidity, and operation time of the television 102. When the control device 101 receives control information input by a user and a definite controlled object is absent in the control information, the control device 101 may have a plurality of nodes capable of responding to a user command, which are queried according to the knowledge graph network shown in fig. 1, for example, an interaction command input by the user is "how much the current indoor temperature is", the nodes capable of being found in the knowledge graph network and related to the temperature may include device nodes such as an air conditioner 103, a temperature and humidity sensor 105, and may also include data nodes such as various temperature data, how to determine a service path for performing service processing by using the found corresponding nodes, for example, how to determine an intelligent home device responding to the "how much the indoor temperature is", which is a technical problem that can be solved by the embodiment of the present invention.
Fig. 3 is a flowchart of a smart home device control method based on a knowledge graph according to an embodiment of the present invention. The execution subject of the method shown in fig. 3 may be the control device in fig. 2. The processing steps of the control method shown in fig. 3 include:
step S201: and acquiring an interactive command input by a user.
The user can input interactive data in the control device through input modes such as voice, a keyboard or a touch screen, and the interactive data input by the user can be voice data or text data. Optionally, the voice collecting device on the control device receives voice interaction data input by the user, for example, the voice interaction data input by the user is "what indoor temperature is", and the control device performs voice recognition on the voice data input by the user to obtain an interaction command "what indoor temperature is" input by the user.
Step S202: each keyword is extracted from an interactive command input by a user.
The control equipment can adopt a natural language word segmentation method to segment words of the interactive command input by the user to obtain a word segmentation result corresponding to the interactive command, wherein the word segmentation result comprises all keywords corresponding to the interactive command; further, the obtained word segmentation results are filtered, for example, only the keywords in the word segmentation results, which are consistent with or have an association relation with the node names in the pre-generated knowledge graph network, are output as the keywords extracted from the interactive commands input by the user.
For example, in the smart home control scenario, only the node words appearing in the smart home domain knowledge graph network are filtered out and output as the keywords extracted from the interactive commands input by the user.
For example, for the interactive command "what the indoor temperature is now", the extracted keywords are [ "indoor", "temperature", "what" ].
Step S203: and determining the corresponding nodes of the keywords in the knowledge graph network.
In the knowledge graph network corresponding to the intelligent home system to be controlled by the method of the embodiment of the invention, the nodes corresponding to the keywords are determined, for example, the extracted keywords are ' indoor ', ' temperature ', ' what ' and the like, and the nodes with the node names of ' indoor ', ' temperature ', ' what ' and the like ' are searched in the knowledge graph network.
Step S204: and determining each service path formed by the node corresponding to each keyword in the knowledge graph network according to the sequence of each keyword in the interactive command.
Optionally, determining a service path of a node corresponding to each keyword in the knowledge graph network includes:
determining the sequence of each keyword in the interactive command, wherein the sequence is the sequence of each keyword in the interactive command;
and sequentially mapping each service path formed by the interactive command in the knowledge graph network according to the sequence of the nodes corresponding to each keyword.
For example, three indoor nodes, two temperature nodes and three number of the temperature nodes are determined in the knowledge-graph network, the nodes are arranged and combined according to the sequence of indoor-temperature-number of the temperature nodes, and the result of each arrangement is determined as a service path formed in the knowledge-graph network.
Step S205: and determining the cost value of each service path according to the connecting edges between the nodes in each service path and the weight values on the corresponding connecting edges.
In the embodiment of the present invention, determining the cost value of any one of the service paths includes: determining the descendant value between two adjacent nodes in a service path, wherein the descendant value between the two adjacent nodes has a positive correlation with the product of the weight value B of a connecting edge between the two nodes and the probability C that the two nodes belong to the same subgraph in the knowledge graph network corresponding to the service path, namely A ═ x ═ B × C, and x is any positive number; and accumulating and summing the sub-cost values included in the service path to obtain the cost value of the service path.
When determining the descendant value between two adjacent nodes in the service path, specifically, the descendant value may be: (1) determining a weight value between two adjacent nodes in the service path; (2) determining the probability that two adjacent nodes in the service path belong to the same sub-graph in the knowledge graph network corresponding to the service path; (3) determining a product of the weight value between the two adjacent nodes and the probability that the two nodes belong to the same sub-graph in the indication graph network corresponding to the service path as a descendant value between the two adjacent nodes.
In the step (3), determining the probability that two adjacent nodes in the service path belong to the same sub-graph in the knowledge-graph network corresponding to the service path includes:
step A: determining a first sub-graph in the knowledge graph network corresponding to the service path; optionally, for two adjacent nodes, determining a corresponding sub-graph of the first node in the knowledge-graph network, and determining the corresponding sub-graph of the first node in the knowledge-graph network as a first sub-graph; the first node is one of the two adjacent nodes, the other of the two adjacent nodes is a second node, and the input time of the keyword corresponding to the second node in the interactive command is later than that of the keyword corresponding to the first node.
And B: determining that an outgoing direction connecting edge of the first node belongs to a first proportion of the first sub-graph, wherein the outgoing direction connecting edge is a connecting edge of the first node pointing to other nodes in the knowledge-graph network;
specifically, determining that the outgoing direction connecting edge of the first node belongs to the first proportion of the first sub-graph includes: judging whether the number of each path from each first target node to the second node is more than two, wherein each first target node is the node except the second keyword connected to the outgoing direction connecting edge of the first node; counting the number of the first target nodes of which the number of the paths of the second nodes is greater than two; dividing the number of the first target nodes with the number of the paths corresponding to the second nodes larger than two by the number of the outgoing direction connecting edges of the first nodes to obtain the first proportion.
And C: and determining a second proportion that an incoming direction connecting edge of a second node in two adjacent nodes in the service path belongs to the first subgraph, wherein the incoming direction connecting edge is a connecting edge of the second node pointing to other nodes in the knowledge-graph network.
Specifically, determining that the incoming direction connecting edge of the second node belongs to the second proportion of the first sub-graph includes: judging whether the number of paths from each second target node to the first node is greater than two, wherein each second target node is connected with each node except the first node in the incoming direction connecting edge of the second node; counting the number of second target nodes with the number of paths of the first node larger than two; and dividing the number of the second target nodes of which the number of the paths to the first node is more than two by the number of the connecting edges of the second nodes in the incoming direction to obtain the second proportion.
Step D: and determining the probability that the two adjacent nodes belong to the first subgraph according to the first proportion and the second proportion, wherein the probability and the product of the first proportion and the second proportion form a positive correlation relationship.
Optionally, the probability that two adjacent nodes belong to the first sub-graph is a product of the first proportion and the second proportion.
Step S206: and determining the minimum value in the cost values of all the service paths, and determining the intelligent home equipment controlled by the interactive command according to the service path corresponding to the minimum value.
In the scheme of the embodiment of the invention, when the control device of the intelligent household equipment receives an interactive command input by a user and the interactive command does not contain explicit information of the controlled intelligent household equipment, the control device extracts each keyword from the interactive command input by the user and determines the node corresponding to each keyword in the knowledge graph network; after determining the nodes corresponding to the keywords respectively, the control device determines each service path formed by the nodes corresponding to the keywords respectively in the knowledge graph network according to the sequence of the keywords in the interaction command, then determines the cost value of each service path according to the connection edges between the nodes in each service path and the weight values on the corresponding connection edges, and determines the intelligent home equipment controlled by the interaction command according to the service path with the minimum cost value.
Fig. 4 is a flowchart of a smart home device control method based on a knowledge graph according to a second embodiment of the present invention. The execution subject of the method shown in fig. 4 may be the control device in fig. 2. The processing steps of the method shown in fig. 4 include:
step S301: for example, in an intelligent home control scene, the interactive command acquired by the control device is "what the indoor temperature is at present", and a specific acquisition method may refer to embodiment one, which is not described herein again.
Step S302, extracting each keyword from the interactive command input by the user, wherein for the interactive command "what the indoor temperature is now" in the above example, the extracted keywords are [ "indoor", "temperature", "what" in the example ], and the method for extracting the keywords from the interactive command is referred to as embodiment one and is not described herein again.
Step S303: and determining the corresponding nodes of the keywords in the knowledge graph network.
For example, when the keyword is [ "indoor", "temperature", "what", etc. ], nodes corresponding to the keywords "indoor", "temperature", and "what", respectively, are extracted from the knowledge-graph network.
As shown in fig. 5A to 5D, schematic diagrams of nodes corresponding to "indoor", "temperature", and "what" are shown, in fig. 5A to 5D, connection relationships between "indoor" nodes, "temperature" nodes, and "what" nodes are shown, and certain weight values are pre-assigned to respective connection edges, specifically, the weight values on the connection edges between the nodes represent the relevance of the association relationships between the two nodes, the greater the weight value, the stronger the relevance between the two nodes, and the smaller the weight value, the weaker the relevance between the two nodes.
Step S304: and generating a node matrix corresponding to each keyword according to the node corresponding to each keyword.
In the scheme of the embodiment of the invention, the nodes corresponding to each keyword can form a node matrix; the node elements in the node matrix of any keyword are represented by AiBjIs represented by AiBjIs taken as value AiNode and BjWeight value on connecting edge between nodes, AiThe node represents the node corresponding to the current keyword, BjThe node is the AiA neighbor node of the node, and the BjNode inputThe time of arrival is later than AiThe values of the input time of the node, i and j are positive integers.
For example, the keywords "indoor", "temperature" and "what" in the above example are represented by R, P, Q according to the input order in the interactive command, and the nodes corresponding to the keywords searched in the knowledge-graph network are: r (R1, R2, R3), P (P1, P2), Q (Q1, Q2, Q3), wherein R, P and Q are nodes in the knowledge graph network corresponding to the keywords respectively.
By using the above method for generating the node matrix, the node matrices corresponding to the obtained keyword R, P, Q are:
the node matrix corresponding to the keyword R is
The node matrix corresponding to the keyword P is
The node matrix corresponding to the keyword Q is
In the three matrices, the cost value is a weight value of a connecting edge between two adjacent nodes, and the two adjacent nodes in the embodiment of the present invention mean that keywords corresponding to the two nodes are adjacent in the input sequence.
Step S305: and sequencing each node matrix.
Specifically, for each node matrix, calculating a sum of node elements in each row; and adjusting the sequence of the nodes in each row according to the sequence of the element sum values of the nodes in each row from large to small.
For example for R: line1 ═ cost (r1, p1) + cost (r1, p 2); line2 ═ cost (r2, p1) + cost (r2, p 2); line3 ═ cost (R3, p1) + cost (R3, p2), and R ═ line3, line2, line1, if line1< line2< line 3. And similarly, sequencing P, Q node matrix rows to obtain node matrixes P 'and Q'.
Step S306: and determining each service path formed by the node corresponding to each keyword section in the knowledge graph network according to the sequence of each keyword in the interactive command.
Specifically, a node may be selected from the node matrix corresponding to each keyword, and the selected nodes are sequentially mapped according to the input sequence in the interactive command to form a service path. According to the method, all the service paths which can be combined by each node matrix can be obtained. For example, an indoor node, a temperature node, and a number of nodes are selected from R ', P ', Q ', respectively, and mapped to a traffic path in the order of indoor-temperature-number.
Step S307: and determining the cost value of each service path according to the connecting edges between the nodes in each service path and the weight values on the corresponding connecting edges.
In the embodiment of the present invention, the method for calculating the cost value of each service path comprises:
cost of a traffic path
Wherein i and j are two nodes adjacent to each other in input time, and the input time of j is later than that of i;
the probability that the node i and the node j belong to the same subgraph represents the product of the proportion of the output edge of the starting point i in the subgraph and the input edge of the end point j in the subgraph in a triple consisting of one edge and two vertexes, and the physical meaning represented by the probability is the strength value that the two vertexes in the triple belong to the same subgraph.
Taking (r1, p1) as an example in FIG. 6,
wherein r1 chainThe judgment method of the number of edges connected to other subgraphs is that for r1 and p1, there are 4 (X, Y, Z and p1) connecting edges in the outgoing direction of r 1. For the X node, r1 has an outgoing direction connecting edge to X, but p1 to X has no other path except through r1, then the edge (r1, X) is considered as an edge connecting edge connected to other subgraphs, and Y, Z nodes can reach p1 through nodes except r1,
similarly, all the beginning of the connecting edge in the incoming direction of p1 has access to r1,
and calculating the cost values of all the service paths by using the formula, wherein when the cost value of each service path is calculated, the weight value between two adjacent nodes is obtained from the corresponding node matrix, and if the row of the weight value between two adjacent nodes in one service path is zero, the calculation of the subsequent service path is not carried out, so that the calculation number of the service paths is reduced, and the positioning efficiency of the service paths is improved. For example, when the traffic paths r2-p2-q2 are calculated, the weight values between r2-p2, the weight values between p2-q2 and the weight values of q2 in the row of node elements are all zero, and the cost values of the traffic paths corresponding to the r2-p2, the weight values between p2-q2, the row of q2 and the node elements in the subsequent row are not calculated.
Step S308: and determining the minimum value in the cost values of all the service paths, and determining the intelligent home equipment controlled by the interactive command according to the service path corresponding to the minimum value.
In order to more clearly illustrate the control method of the embodiment of the present invention, the present application further provides a more specific embodiment, including:
(1) the interactive command input by the user is "what the indoor temperature is now", and the keywords extracted from the interactive command are [ "indoor", "temperature", "what" ].
(2) As shown in fig. 6, the nodes corresponding to the keywords respectively found from the pre-generated knowledge-graph network include: the number of the indoor nodes is3, and the nodes are represented by R, and the set is R; 2 temperature nodes are provided, wherein the node is P, and the node set is P; the number of the nodes is3, the node is represented by Q, the set is Q, and the node matrix corresponding to each keyword is as follows:
the node matrix corresponding to the keyword R is
The node matrix corresponding to the keyword P is
The node matrix corresponding to the keyword Q is
Assigning values to node elements of each node matrix and assuming that the ordered node matrices are:
indoor use
Temperature of
What is
The result is indoor after the sum of each row of each matrix is sorted respectively
Temperature of
What is
(3) Using the "indoor" keyword as the starting point of the service path, the nodes found from FIG. 6 can be composedThe traffic path is shown in fig. 7, where in fig. 7, the connecting edges with weight values of 0 between nodes are indicated by dashed lines. According to the formula
In fig. 7, the cost values of all traffic paths are calculated, and 0/0 ∞ is defined, where the cos t value is the weight value of the edge between nodes.
Specifically, the initial mincost is 0, if the tempdisi is greater than the mincost, the mincost is greater than the tempdisi, and finally, the service path represented by the value with the minimum path cost, that is, the maximum mincost, is selected as the target service path.
In this case
And (3) selecting the paths to be calculated according to the node matrix sorting result in the step (2) as follows:
dis 1-r 1-p1-q 1-0.86 (3/4) × (3/3) +0.66 (3/3) × (2/2) -0.645 + 0.66-1.305; since 1.305> mincost, mincost is 1.305
dis 2-r 1-p2-q 1-0 (0/4) × (0/1) +0 (0/1) × (0/2) ═ 0; since 0< mincost, the mincost value is not changed
dis 3-r 2-p1-q 1-0 (0/2) +0.66 (3/3) (2/2) -0 + 0.66-0.66; since 0.66< mincost, the mincost value is not changed
dis 4-r 2-p2-q 1-0 (0/2) (0/1) +0 (0/1) (0/2) -0; since 0< mincost, the mincost value is not changed
(4) The minimum cost value mincost is selected to be 1.305, the path represented by r1-p1-q1 is the path with the minimum link value and all nodes appearing in the first sub-graph, and therefore the first sub-graph is selected to enter the service.
Fig. 8 is a schematic structural diagram of a traffic path selection processing apparatus according to an embodiment of the present invention, where the processing apparatus 400 includes: at least one processor (processor)401, memory 402, peripheral interface 403, input/output subsystem 404, power lines 405, and communication lines 406.
In fig. 8, arrows indicate that communication and data transfer between components of the computer system are possible, and that the communication and data transfer may be implemented using a high-speed serial bus (high-speed serial bus), a parallel bus (parallel bus), a Storage Area Network (SAN), and/or other suitable communication technology.
The memory 402 may include an operating system 412 and a traffic routing processing routine 422. For example, memory 402 may include high-speed random access memory (high-speed random access memory), magnetic disks, static random access memory (SPAM), Dynamic Random Access Memory (DRAM), Read Only Memory (ROM), flash memory, or non-volatile memory. The memory 402 may store program code for the operating system 412 and the traffic routing processing routine 422, which may include software modules, instruction set architectures, or a variety of data other than those required for the operation of the processing device 400. In this case, the access to the memory 402 and other controllers such as the processor 401 and the peripheral interface 406 may be controlled by the processor 401.
The power line 405 may supply power to all or part of the circuit elements of the terminal device. For example, the power line 405 may include, for example, a power management system, a battery or an Alternating Current (AC) power source for more than one cycle, a charging system, a power failure detection circuit (power failure detection circuit), a power converter or inverter, a power status flag, or any other circuit element for power generation, management, distribution.
The communication line 406 may utilize at least one periodic interface to communicate with other computer systems, such as with a host control system.
The processor 401 may perform various functions of the processing device 400 and process data by executing software modules or an instruction set architecture stored in the memory 402. That is, the processor 401 may be configured to process commands of a computer program by performing basic arithmetic, logic, and input/output operations of a computer system.
The embodiment of fig. 8 is only one example of the processing means 400 in the terminal device, and the processing means 400 may have the following structure or configuration: some of the circuit elements shown in fig. 8 are omitted, or additional circuit elements not shown in fig. 8 are further provided. The processing device shown in fig. 8 may execute the traffic path selection method according to various embodiments of the present invention.
The processing device shown in fig. 8 may be applied to an intelligent home control system, for example, the processing device shown in fig. 8 is deployed in a computer, and in the intelligent home control system, the computer is connected to home devices such as a television, an air conditioner, a refrigerator, an entrance guard, a mobile phone, a monitoring camera, a temperature and humidity sensor, and the like, and controls each terminal device according to the control methods shown in fig. 3 and 4.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the units may be implemented in the same cycle or in multiple cycles of software and/or hardware in practicing the invention.
The cycle embodiments in the present specification are all described in a progressive manner, and the same and similar parts among the cycle embodiments are referred to each other, and each cycle embodiment focuses on the differences from the other embodiments. In particular, for apparatus or system embodiments, since they are substantially similar to method embodiments, they are described in relative terms, as long as they are described in partial descriptions of method embodiments. The above-described embodiments of the apparatus and system are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one period, or may be distributed on a plurality of period network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort. The foregoing is merely a detailed description of the invention, and it should be noted that modifications and adaptations by those skilled in the art may be made without departing from the principles of the invention, and should be considered as within the scope of the invention.
Claims (9)
1. A control method of intelligent household equipment based on a knowledge graph is characterized by comprising the following steps:
extracting each keyword from an interactive command input by a user;
determining a corresponding node of the keyword in a knowledge graph network;
determining each service path formed by the node corresponding to each keyword in the knowledge graph network according to the sequence of each keyword in the interactive command;
determining descendant values between two adjacent nodes in the service paths according to the connecting edges between the nodes in each service path and the corresponding weight values on the connecting edges, wherein the descendant values between the two adjacent nodes are in positive correlation with the product of the weight values of the connecting edges between the two nodes and the probability that the two nodes belong to the same subgraph in the knowledge graph network corresponding to the service path;
accumulating and summing the descendant values included in the service path to obtain the cost value of the service path;
and determining the minimum value in the cost values, and determining the intelligent household equipment controlled by the interactive command according to the service path corresponding to the minimum value.
2. The method of claim 1, wherein extracting the keywords from the interactive command input by the user further comprises:
receiving voice interaction data input by a user;
and carrying out voice recognition on the voice interaction data input by the user to obtain an interaction command input by the user.
3. The method of claim 1, wherein determining, according to the order of the keywords in the interactive command, each traffic path formed in the knowledge-graph network by the node corresponding to the keyword comprises:
determining the sequence of each keyword in the interactive command, wherein the sequence is the sequence of each keyword in the interactive command;
and the nodes corresponding to the keywords are sequentially mapped according to the sequence to form each service path formed by the interactive command in the knowledge graph network.
4. The method of claim 1, wherein determining the descendant value between two adjacent nodes in the traffic path comprises:
determining a weight value between two adjacent nodes in the service path;
determining the probability that two adjacent nodes in the service path belong to the same sub-graph in the knowledge graph network corresponding to the service path;
determining a product of the weight value between the two adjacent nodes and the probability that the two nodes belong to the same sub-graph in the knowledge-graph network corresponding to the service path as a descendant value between the two adjacent nodes.
5. The method of claim 4, wherein determining the probability that two adjacent nodes in the traffic path belong to the same sub-graph in the knowledgegraph network to which the traffic path corresponds comprises:
determining a first sub-graph in the knowledge graph network corresponding to the service path;
determining a first proportion that an outgoing direction connecting edge of a first node in two adjacent nodes in the service path belongs to the first subgraph, wherein the outgoing direction connecting edge is a connecting edge of the first node pointing to other nodes in the knowledge-graph network;
determining a second proportion that an incoming direction connecting edge of a second node in two adjacent nodes in the service path belongs to the first sub-graph, wherein the incoming direction connecting edge is a connecting edge of the second node pointing to other nodes in the knowledge graph network, and the input time of a keyword corresponding to the second node in the interactive command is later than the input time of the keyword corresponding to the first node in the interactive command;
and determining the probability that the two adjacent nodes belong to the first subgraph according to the first proportion and the second proportion, wherein the probability and the product of the first proportion and the second proportion form a positive correlation relationship.
6. The method of claim 5, wherein determining a first sub-graph in the knowledge-graph network to which the traffic path corresponds comprises:
determining a corresponding subgraph of the first node in the knowledge-graph network;
and determining a corresponding sub-graph of the first node in the knowledge-graph network as a first sub-graph.
7. The method of claim 5 or 6, wherein determining the probability that the two adjacent nodes belong to the first subgraph according to the first proportion and the second proportion comprises:
and determining the probability that the two adjacent nodes belong to the first subgraph as the product of the first proportion and the second proportion.
8. The utility model provides an intelligent household equipment controlling means based on knowledge map network which characterized in that includes: the system comprises a processor, a memory and a communication interface, wherein the processor, the memory and the communication interface are connected through a communication bus;
the communication interface is used for receiving an interactive command input by a user;
the memory for storing program code;
the processor is used for reading the program codes stored in the memory and executing the intelligent household equipment control method based on the knowledge-graph network according to any one of claims 1 to 7.
9. The utility model provides an intelligent home systems which characterized in that includes: the intelligent home furnishing system comprises a plurality of intelligent home furnishing devices and control equipment, wherein the control equipment is provided with a control device according to claim 8;
the control device is connected with the plurality of smart home devices respectively, and controls the plurality of smart home devices according to the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611050982.0A CN106713083B (en) | 2016-11-24 | 2016-11-24 | Intelligent household equipment control method, device and system based on knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611050982.0A CN106713083B (en) | 2016-11-24 | 2016-11-24 | Intelligent household equipment control method, device and system based on knowledge graph |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106713083A CN106713083A (en) | 2017-05-24 |
| CN106713083B true CN106713083B (en) | 2020-06-26 |
Family
ID=58933748
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611050982.0A Active CN106713083B (en) | 2016-11-24 | 2016-11-24 | Intelligent household equipment control method, device and system based on knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106713083B (en) |
Families Citing this family (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10536294B2 (en) * | 2017-07-17 | 2020-01-14 | Midea America Corp. | Computer-based platform for quality management of home devices |
| CN108829858B (en) * | 2018-06-22 | 2021-09-17 | 京东数字科技控股有限公司 | Data query method and device and computer readable storage medium |
| CN109446700A (en) * | 2018-11-09 | 2019-03-08 | 福州大学 | Modeling and the method for execution when operation towards smart home context-aware services |
| CN109740026A (en) * | 2019-01-11 | 2019-05-10 | 深圳市中电数通智慧安全科技股份有限公司 | Smart city edge calculations platform and its management method, server and storage medium |
| CN109754804A (en) * | 2019-02-21 | 2019-05-14 | 珠海格力电器股份有限公司 | Voice control method and device, storage medium and intelligent home system |
| CN111831797B (en) * | 2019-04-19 | 2024-06-14 | 广东省智能制造研究所 | Management and recommendation system for manufacturing industry processing equipment model |
| CN111949758A (en) * | 2019-05-16 | 2020-11-17 | 北大医疗信息技术有限公司 | Medical question and answer recommendation method, recommendation system and computer readable storage medium |
| CN110263183A (en) * | 2019-06-20 | 2019-09-20 | 珠海格力电器股份有限公司 | Intelligent home decision support system and decision support method |
| CN110246496A (en) * | 2019-07-01 | 2019-09-17 | 珠海格力电器股份有限公司 | Speech recognition method, system, computer device and storage medium |
| CN110286602A (en) * | 2019-07-02 | 2019-09-27 | 珠海格力电器股份有限公司 | Intelligent home control method, control equipment and system based on knowledge graph |
| CN110333663B (en) * | 2019-07-02 | 2021-04-23 | 珠海格力电器股份有限公司 | Method and system for setting intelligent household management authority and computer storage medium |
| CN110262273A (en) * | 2019-07-12 | 2019-09-20 | 珠海格力电器股份有限公司 | Household equipment control method and device, storage medium and intelligent household system |
| CN110457489A (en) * | 2019-08-12 | 2019-11-15 | 珠海格力电器股份有限公司 | Resource scheduling method and system, and computer readable storage medium |
| CN110361982A (en) * | 2019-08-14 | 2019-10-22 | 珠海格力电器股份有限公司 | Household equipment control method, storage medium and intelligent household equipment |
| CN110598916A (en) * | 2019-08-23 | 2019-12-20 | 宁波智轩物联网科技有限公司 | Method and system for constructing user behavior model |
| CN110703614B (en) * | 2019-09-11 | 2021-01-22 | 珠海格力电器股份有限公司 | Voice control method and device, semantic network construction method and device |
| CN112583865A (en) * | 2019-09-27 | 2021-03-30 | 阿里巴巴集团控股有限公司 | Control method, control equipment and storage medium |
| CN110909169A (en) * | 2019-09-30 | 2020-03-24 | 珠海格力电器股份有限公司 | Control method, system, electronic device and storage medium based on knowledge graph |
| CN110989370B (en) * | 2019-11-06 | 2021-12-14 | 珠海格力电器股份有限公司 | Intelligent household interaction control method and system |
| CN113138673A (en) * | 2020-01-17 | 2021-07-20 | 华为技术有限公司 | Prompting method based on command line interface and related equipment |
| CN113255347B (en) * | 2020-02-10 | 2022-11-15 | 阿里巴巴集团控股有限公司 | Method and equipment for realizing data fusion and method for realizing identification of unmanned equipment |
| CN111367188B (en) * | 2020-03-09 | 2023-11-03 | 京东方科技集团股份有限公司 | Control method and device for intelligent home, electronic equipment and computer storage medium |
| CN113488034A (en) * | 2020-04-27 | 2021-10-08 | 海信集团有限公司 | Voice information processing method, device, equipment and medium |
| WO2022061925A1 (en) * | 2020-09-28 | 2022-03-31 | 西门子股份公司 | Method and apparatus for generating control chart of automatic control system, and computer readable medium |
| CN112151035B (en) * | 2020-10-14 | 2023-08-11 | 珠海格力电器股份有限公司 | Voice control method and device, electronic equipment and readable storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101630314B (en) * | 2008-07-16 | 2011-12-07 | 中国科学院自动化研究所 | Semantic query expansion method based on domain knowledge |
| CN101937436B (en) * | 2009-06-29 | 2013-09-25 | 华为技术有限公司 | Text classification method and device |
| CN103593792B (en) * | 2013-11-13 | 2016-09-28 | 复旦大学 | A kind of personalized recommendation method based on Chinese knowledge mapping and system |
| CN104090955A (en) * | 2014-07-07 | 2014-10-08 | 科大讯飞股份有限公司 | Automatic audio/video label labeling method and system |
| US10146875B2 (en) * | 2014-12-19 | 2018-12-04 | International Business Machines Corporation | Information propagation via weighted semantic and social graphs |
| CN106126503B (en) * | 2016-07-12 | 2020-02-11 | 海信集团有限公司 | Service field positioning method and terminal |
-
2016
- 2016-11-24 CN CN201611050982.0A patent/CN106713083B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106713083A (en) | 2017-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106713083B (en) | Intelligent household equipment control method, device and system based on knowledge graph | |
| CN109447288A (en) | Multiple-energy-source operation management method and terminal device | |
| CN104915351A (en) | Picture sorting method and terminal | |
| Muppala et al. | Composite performance and availability analysis using a hierarchy of stochastic reward nets | |
| CN113111578B (en) | Power load prediction method, power load prediction device, computer equipment and storage medium | |
| CN111813517B (en) | Task queue allocation method and device, computer equipment and medium | |
| CN108961267A (en) | Image processing method, picture processing unit and terminal device | |
| CN102722610A (en) | Method and device for automatically generating coverage rate codes by flow chart | |
| CN105631404A (en) | Method and device for clustering pictures | |
| CN112988383A (en) | Resource allocation method, device, equipment and storage medium | |
| CN113779269A (en) | Power grid load data display method and device, electronic equipment and storage medium | |
| KR101273646B1 (en) | Method and system for indexing and searching in multi-modality data | |
| Velik | Cognitive Architectures as Building Energy Management System for Future Renewable Energy Scenarios; A Work in Progress Report | |
| CN116581798B (en) | Energy supply display control system of internet of things based on bay window fixing structure | |
| CN112001300A (en) | Building monitoring method and device based on cross entropy according to position and electronic equipment | |
| CN105335267A (en) | Server temperature prediction method, apparatus and system | |
| CN115275975A (en) | Method and device for determining electric power data matching degree of optical storage charging station | |
| CN115131597A (en) | Data processing method and device, electronic equipment and storage medium | |
| KR20220117432A (en) | Power system, method and apparatus for clustering of power system | |
| CN113194292A (en) | Coordination management method, device, equipment and storage medium for intelligent equipment | |
| CN118298201B (en) | Equipment identification matching model training method, equipment identification matching method and equipment | |
| CN116540990B (en) | Code integration method and device for realizing electronic product based on embedded mode | |
| CN109376290A (en) | The method of processing display and processing display device of house data | |
| CN114237915B (en) | Data restoration method, device and equipment based on machine learning in distributed environment | |
| CN117553808B (en) | Deep learning-based robot positioning navigation method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |