Disclosure of Invention
The invention aims to provide a voice control method, a voice control device, a storage medium and an intelligent home system aiming at the defects, so as to solve the problem that voice control commands cannot carry out intelligent linkage control on various types of household appliances in the intelligent home system, so that the use is inconvenient, and the effect of improving the use convenience is achieved.
The invention provides a voice control method, which comprises the following steps: acquiring voice data; determining an equipment control command for performing linkage control on more than one equipment in the equipment system to be controlled according to the voice data and the set equipment knowledge graph; and controlling more than one device in the device system to be controlled to jointly act according to the device control command.
Optionally, the obtaining voice data comprises: acquiring voice data acquired by voice acquisition equipment; wherein, pronunciation collection equipment includes: a microphone array; and/or the voice data is used for performing voice control on more than one device in the to-be-controlled device system so as to enable the more than one device to respond in a linkage manner; the voice data includes: at least one of voice wake-up words and voice commands.
Optionally, determining, according to the voice data and the set device knowledge graph, a device control command for performing linkage control on more than one device in the device system to be controlled, including: determining semantic information according to the voice data; determining a use scene currently required by a user according to the semantic information; and determining more than one equipment and equipment control commands of linkage response relations thereof under the using scene according to the equipment knowledge graph.
Optionally, wherein determining semantic information according to the voice data includes: performing semantic analysis on the voice data to obtain semantic information contained in the voice data; and/or determining the use scene currently required by the user according to the semantic information, wherein the use scene comprises the following steps: determining a set scene corresponding to set semantic information which is the same as the semantic information in the corresponding relation as a use scene currently required by a user according to the corresponding relation between the set semantic information and the set scene; and/or determining the equipment control command of more than one equipment and the linkage response relation thereof under the use scene according to the equipment knowledge graph, wherein the equipment control command comprises the following steps: determining more than one device corresponding to the use scene in the device knowledge graph and the linkage response relationship among the more than one device according to the linkage response relationship among different devices under different scenes in the device knowledge graph; and generating a device control command of the more than one device and the linkage response relation thereof in the use scene based on the semantic information, the more than one device corresponding to the use scene and the linkage response relation between the more than one device.
Optionally, the method further comprises: collecting equipment data of the equipment system to be controlled and control data for controlling each equipment in the equipment system to be controlled; determining each device in the device system to be controlled and the incidence relation between the devices according to the device data and the control data; and performing knowledge mapping processing based on the equipment entities and the association relationship between the equipment entities to obtain the equipment entities and the linkage response relationship between the equipment entities as an equipment knowledge map of the equipment system to be controlled.
Optionally, determining, according to the device data and the control data, each device in the device system to be controlled and an association relationship therebetween includes: preprocessing the equipment data and the control data to obtain current information; and extracting the equipment entities in the equipment system to be controlled and the incidence relation among different equipment entities from the current information to be used as the incidence relation among the equipment entities in the equipment system to be controlled.
Optionally, the device data includes: at least one of a device name, a device MAC address, and an IP address; and/or, the control data comprises: controlling command texts and corresponding operations; and/or, the pre-treatment, comprising: at least one of a missing value process, a normalization process, and a noise reduction process; and/or, the knowledge mapping process comprises: and at least one of knowledge representation, knowledge fusion and knowledge inference is carried out.
In accordance with the above method, another aspect of the present invention provides a voice control apparatus, including: an acquisition unit configured to acquire voice data; the control unit is used for determining an equipment control command for performing linkage control on more than one equipment in the equipment system to be controlled according to the voice data and the set equipment knowledge graph; and the control unit is also used for controlling the joint action of more than one device in the device system to be controlled according to the device control command.
Optionally, the acquiring unit acquires voice data, including: acquiring voice data acquired by voice acquisition equipment; wherein, pronunciation collection equipment includes: a microphone array; and/or the voice data is used for performing voice control on more than one device in the to-be-controlled device system so as to enable the more than one device to respond in a linkage manner; the voice data includes: at least one of voice wake-up words and voice commands.
Optionally, the determining, by the control unit, an apparatus control command for performing linkage control on more than one apparatus in the apparatus system to be controlled according to the voice data and the set apparatus knowledge graph includes: determining semantic information according to the voice data; determining a use scene currently required by a user according to the semantic information; and determining more than one equipment and equipment control commands of linkage response relations thereof under the using scene according to the equipment knowledge graph.
Optionally, wherein the determining, by the control unit, semantic information according to the voice data includes: performing semantic analysis on the voice data to obtain semantic information contained in the voice data; and/or the control unit determines the use scene currently required by the user according to the semantic information, and the method comprises the following steps: determining a set scene corresponding to set semantic information which is the same as the semantic information in the corresponding relation as a use scene currently required by a user according to the corresponding relation between the set semantic information and the set scene; and/or the control unit determines the equipment control command of more than one equipment and the linkage response relation thereof under the use scene according to the equipment knowledge graph, and the control command comprises the following steps: determining more than one device corresponding to the use scene in the device knowledge graph and the linkage response relationship among the more than one device according to the linkage response relationship among different devices under different scenes in the device knowledge graph; and generating a device control command of the more than one device and the linkage response relation thereof in the use scene based on the semantic information, the more than one device corresponding to the use scene and the linkage response relation between the more than one device.
Optionally, the method further comprises: the acquisition unit is also used for collecting equipment data of the equipment system to be controlled and control data for controlling each equipment in the equipment system to be controlled; the control unit is further configured to determine, according to the device data and the control data, each device in the device system to be controlled and an association relationship between the devices; and the control unit is also used for carrying out knowledge mapping processing based on the equipment entities and the association relationship between the equipment entities to obtain linkage response relationship between the equipment entities and the linkage response relationship between the equipment entities, and the linkage response relationship is used as the equipment knowledge mapping of the equipment system to be controlled.
Optionally, the determining, by the control unit, each device in the device system to be controlled and an association relationship between the devices according to the device data and the control data includes: preprocessing the equipment data and the control data to obtain current information; and extracting the equipment entities in the equipment system to be controlled and the incidence relation among different equipment entities from the current information to be used as the incidence relation among the equipment entities in the equipment system to be controlled.
Optionally, the device data includes: at least one of a device name, a device MAC address, and an IP address; and/or, the control data comprises: controlling command texts and corresponding operations; and/or, the pre-treatment, comprising: at least one of a missing value process, a normalization process, and a noise reduction process; and/or, the knowledge mapping process comprises: and at least one of knowledge representation, knowledge fusion and knowledge inference is carried out.
In another aspect, the present invention provides an intelligent home system, including: the voice control device described above.
In accordance with the above method, a further aspect of the present invention provides a storage medium comprising: the storage medium has stored therein a plurality of instructions; the instructions are used for loading and executing the voice control method by the processor.
In match with the above method, another aspect of the present invention provides an intelligent home system, including: a processor for executing a plurality of instructions; a memory to store a plurality of instructions; wherein the instructions are stored in the memory, and loaded by the processor and used for executing the voice control method.
According to the scheme, the control information map of the household appliance is established by the knowledge map method, so that timely and accurate response can be given to various voice control commands, the intelligent degree of the intelligent household system can be improved, and the convenience in use of a user can be improved.
Furthermore, according to the scheme of the invention, the household appliance interconnection system based on the knowledge graph is built, so that interconnection and intelligent knowledge service can be provided, and the convenience of use of a user is improved.
Furthermore, according to the scheme of the invention, the household appliance control knowledge graph is integrated into the household system, so that the equipment can sense different scenes, and give out corresponding joint response operation after performing semantic analysis on the voice control command, and the intelligent degree of the intelligent household system can be improved.
Furthermore, the scheme of the invention carries out linkage response among the devices through the relation graphs among various devices in the knowledge graph, can meet various control requirements of users, and has good user experience.
Furthermore, according to the scheme of the invention, on the basis of the knowledge map technology, the interconnection and control system is constructed by using the related data of the household appliances, the voice data is analyzed in real time, the joint response of the household appliances is accurately given in time, the diversification of the connection and control modes can be realized, the intelligent degree of the household appliances and even the intelligent household system can be improved, and the user experience is improved.
Therefore, according to the scheme provided by the invention, the household appliance control information map is integrated into the household system by building the household appliance control information map, so that the equipment can sense different scenes, and give out corresponding combined response operation after performing semantic analysis on the voice control command, and the problem that the voice control command cannot perform intelligent linkage control on various types of household appliances in the intelligent household system is solved, and the problem of inconvenience in use is solved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the specific embodiments of the present invention and the accompanying drawings. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. 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.
According to an embodiment of the present invention, a method for controlling speech is provided, as shown in fig. 1, which is a flow chart of an embodiment of the method of the present invention. The voice control method may include: step S110 to step S130.
At step S110, voice data is acquired. The voice data may be voice data that can be used for voice control of any device in a to-be-controlled device system (e.g., an intelligent home system). The voice data may include voice information such as voice wakeup words, voice instructions, etc.
Optionally, the acquiring of the voice data in step S110 may include: and acquiring voice data acquired by the voice acquisition equipment.
Specifically, the voice collecting device may include: an array of microphones.
Therefore, the voice data are acquired through the microphone array, the acquisition mode is flexible, and the acquisition result is accurate and reliable.
Specifically, the voice data may be voice data that is used to perform voice control on one or more devices in the to-be-controlled device system so that the one or more devices respond in a linkage manner. The voice data may include: at least one of voice wake-up words and voice commands.
For example: voice data, which may include: voice audio data.
Therefore, through the voice data in various forms, the voice control under various user requirements can be realized, and the method is high in universality and good in flexibility.
In step S120, an equipment control command for performing linkage control on more than one equipment in the equipment system to be controlled is determined according to the voice data and the set equipment knowledge graph.
Optionally, with reference to the flowchart of an embodiment of determining an apparatus control command for performing linkage control on one or more apparatuses in the apparatus system to be controlled according to the voice data and the set apparatus knowledge graph in the method shown in fig. 2, a specific process of determining an apparatus control command for performing linkage control on one or more apparatuses in the apparatus system to be controlled according to the voice data and the set apparatus knowledge graph in step S120 may further include: step S210 to step S230.
Step S210, determining semantic information according to the voice data.
More optionally, the determining semantic information according to the voice data in step S210 may include: and carrying out semantic analysis on the voice data to obtain semantic information contained in the voice data. The semantic information may include: and (5) semantic keywords.
For example: semantic parsing may be converting voice data into text data. Semantic parsing: and converting the voice data into text data, and extracting and identifying the equipment entity and the control entity.
Therefore, the semantic information of the voice data is determined by performing semantic analysis on the voice data, so that the determination of the semantic information of the voice data is accurate and reliable.
Step S220, determining the use scene currently required by the user according to the semantic information.
For example: knowledge graph of household electrical appliance: and searching and matching in the knowledge graph according to the analyzed semantics.
More optionally, the step S220 of determining the usage scenario currently required by the user according to the semantic information may include: and determining a set scene corresponding to the set semantic information which is the same as the semantic information in the corresponding relation as a use scene currently required by the user according to the corresponding relation between the set semantic information and the set scene.
Therefore, the use scene corresponding to the semantic information of the voice data is determined according to the corresponding relation between the set semantic information and the set scene, and the determination mode is simple, convenient and reliable.
And step S230, determining more than one equipment and equipment control commands of linkage response relations thereof under the using scene according to the equipment knowledge graph.
For example: the household appliance control knowledge graph is integrated into a household system, so that the household appliance can sense different scenes, and give corresponding combined response operation after performing semantic analysis on a voice control command.
Therefore, the current use scene required by the user is determined based on the semantic information of the voice data, and the equipment control command of more than one equipment and the linkage response relation of the equipment in the use scene is further determined according to the equipment knowledge map, so that the equipment control command of more than one equipment in linkage response is accurately and reliably determined.
More optionally, with reference to a flowchart of an embodiment of the method shown in fig. 3, which is an embodiment of a device control command for determining more than one device and its linkage response relationship in the usage scenario according to the device knowledge graph, further describing a specific process of determining the device control command for determining more than one device and its linkage response relationship in the usage scenario according to the device knowledge graph in step S230, the specific process may include: step S310 and step S320.
Step S310, determining more than one device corresponding to the use scene in the device knowledge graph and the linkage response relationship among the more than one device according to the linkage response relationship among different devices under different scenes in the device knowledge graph.
Step S320, generating a device control command of the at least one device and the linkage response relationship thereof in the usage scenario based on the semantic information and the at least one device corresponding to the usage scenario and the linkage response relationship between the at least one device. For example: and determining more than one device corresponding to the use scene in the device knowledge graph and the linkage response relationship between the more than one device according to the linkage response relationship between different devices in different scenes in the device knowledge graph, and generating a device control command of the more than one device and the linkage response relationship thereof in the use scene.
Therefore, the more than one device to be controlled and the linkage response relationship thereof in the use scene are determined according to the linkage response relationship between different devices in different scenes, and the device control command for the more than one device and the linkage response relationship thereof in the use scene is determined by combining the semantic information of the voice data, so that the reliability is high, and the control convenience is good.
In step S130, according to the device control command, controlling one or more devices in the to-be-controlled device system to perform joint action, so as to realize linkage control of the one or more devices in the to-be-controlled device system.
For example: the device control command may include: device control class commands extracted from textual data (e.g., semantic textual data); the household appliance jointly responds: the plurality of devices are controlled in an interlocking manner by the device control command shown in fig. 8. For another example: device control commands: wait for joint control commands of the devices. Device association response: and the corresponding equipment performs linkage response.
For example: giving a joint response of the home devices, comprising: and performing linkage response among the devices through the relation graphs among various devices in the knowledge graph. The household appliance control information map is built by the knowledge map method, timely and accurate response can be given to various voice control commands, the intelligent degree of the intelligent home system is improved, the user requirements are met, and the experience effect is improved; the household appliance knowledge map can be a knowledge map formed by combining household appliance data. Voice data are collected in real time through a household appliance control platform, real-time semantic analysis is carried out, and corresponding equipment combination and intelligent response are achieved; according to the voice intention of the user, the corresponding operation is accurately and efficiently completed.
Therefore, the equipment control command for linkage control of more than one equipment in the equipment system to be controlled is determined based on the voice data and the set equipment knowledge graph of the equipment system to be controlled, and then the joint action of more than one equipment in the equipment system to be controlled is controlled according to the equipment control command, so that the linkage control of more than one equipment in the equipment system to be controlled is realized, the intelligent degree is high, and the convenience in use of a user is good.
In an alternative embodiment, the method may further include: and (3) building an equipment knowledge graph of the equipment system to be controlled.
The following further describes a specific process of building an apparatus knowledge graph of the apparatus system to be controlled with reference to a flowchart of an embodiment of building an apparatus knowledge graph of the apparatus system to be controlled in the method shown in fig. 4, which may include: step S410 to step S430.
Step S410, collecting device data of the device system to be controlled and control data (e.g. historical data of control commands) for controlling each device in the device system to be controlled.
The device data may include: at least one of a device name, a device MAC address, and an IP address; and/or, the control data may include: control command text and corresponding operations. For example: data of the household electrical appliance: device name, device MAC address, IP address; control command history data: control command text and corresponding operations.
Therefore, accuracy and reliability of construction of the equipment knowledge graph of the equipment system to be controlled are improved beneficially through the equipment data in various forms.
Step S420, determining each device in the device system to be controlled and the incidence relation between the devices according to the device data and the control data.
For example: and collecting data on the household electrical appliance interconnection platform, and establishing a database. Collecting data may include: and acquiring equipment data in the intelligent home system through the equipment interconnection platform. The collected data may include, among other things: home device data and control command history data. Data of the household electrical appliance: device name, device MAC address, IP address; control command history data: control command text and corresponding operations. The operation corresponding to the control command text may include: an operation command to the device. For example: the operation command corresponding to "turn on the air conditioner" is "air conditioner _ control _ on".
Optionally, with reference to a flowchart of an embodiment of determining each device in the device system to be controlled and the association relationship between the devices in the device system to be controlled according to the device data and the control data in the method shown in fig. 5, a specific process of determining each device in the device system to be controlled and the association relationship between the devices in the device system to be controlled according to the device data and the control data in step S420 is further described, and the specific process may include: step S510 and step S520.
Step S510, pre-processing the device data and the control data to obtain current information.
Wherein, the pretreatment may include: at least one of missing value processing, normalization processing, and noise reduction processing.
For example: and collecting historical data of the historical equipment and the control command. Data preprocessing: and preprocessing the data such as missing value processing, standardization, noise reduction and the like.
Therefore, the accuracy and the reliability of the equipment data and the control data are improved by preprocessing the equipment data and the control data in various forms.
Step S520, extracting the device entities in the device system to be controlled and the association relationship between different device entities from the current information, and using the extracted association relationship as the association relationship between each device in the device system to be controlled and the device entities.
For example: information extraction: and extracting entities and relations from the preprocessed data.
Therefore, the equipment entity and the incidence relation thereof are extracted after the equipment data and the control data of the equipment system to be controlled are preprocessed and used as the incidence relation among the equipment in the equipment system to be controlled, and the processing accuracy is good and the reliability is high.
And step S430, performing knowledge mapping processing based on the equipment entities and the association relationship between the equipment entities to obtain linkage response relationship between the equipment entities as an equipment knowledge map of the equipment system to be controlled.
For example: by building a household appliance interconnection system based on the knowledge graph: related knowledge data of the equipment is automatically or semi-automatically acquired from a home system, and a knowledge graph of the household appliance is constructed to provide interconnection and intelligent knowledge services.
For example: the knowledge facts are extracted by utilizing the database through a series of automatic or semi-automatic technical means and are stored in a data layer and a mode layer of the knowledge base, and a knowledge graph of the household appliance is built. Establishing a database may include: and combining the data of the household electrical appliance and the corresponding control relation into a ternary body to be stored in a graph database by utilizing a graph database building technology. The knowledge base comprises a database, and the database only stores data. The data layer is composed of a series of facts, and the facts are mainly expressed by triples; the mode layer is above the data layer and is used for managing the data layer.
From this, through collecting the equipment data and the control data of waiting to control equipment system, and then carry out the equipment knowledge map that knowledge map ization was handled and is obtained waiting to control equipment system based on this equipment data and control data to can set up the equipment knowledge map of waiting to control equipment system in advance, so that realize the linkage voice control of this equipment more than one equipment in waiting to control equipment system based on this equipment knowledge map, promote convenience and the reliability that the user used greatly.
The knowledge mapping process may include: and at least one of knowledge representation, knowledge fusion and knowledge inference is carried out.
For example: knowledge representation: knowledge representation is performed using attribute maps (graph databases) of entities and relationships. And (3) knowledge fusion: and fusing the description information of the entity and the relationship to determine the equivalent attribute and the equivalent relationship. Knowledge reasoning: and reasoning the implicit knowledge, enriching the knowledge map, and cleaning the knowledge to obtain the knowledge map of the household appliance.
Therefore, accuracy and reliability of the knowledge graph of the obtained equipment can be improved by means of knowledge graph processing in various forms.
Through a large number of tests, the technical scheme of the embodiment is adopted, the household appliance control information map is built through the knowledge map method, timely and accurate response can be given to various voice control commands, the intelligent degree of the intelligent home system can be improved, and the use convenience of a user is improved.
According to the embodiment of the invention, a voice control device corresponding to the voice control method is also provided. Referring to fig. 6, a schematic diagram of an embodiment of the apparatus of the present invention is shown. The voice control apparatus may include: an acquisition unit 102 and a control unit 104.
In an alternative example, the obtaining unit 102 may be configured to obtain voice data. The voice data may be voice data that can be used for voice control of any device in a to-be-controlled device system (e.g., an intelligent home system). The voice data may include voice information such as voice wakeup words, voice instructions, etc. The specific functions and processes of the acquiring unit 102 are referred to in step S110.
Optionally, the acquiring unit 102 acquires voice data, which may include: the obtaining unit 102 may be further specifically configured to obtain voice data obtained by the voice collecting device.
Specifically, the voice collecting device may include: an array of microphones.
Therefore, the voice data are acquired through the microphone array, the acquisition mode is flexible, and the acquisition result is accurate and reliable.
Specifically, the voice data may be voice data that is used to perform voice control on one or more devices in the to-be-controlled device system so that the one or more devices respond in a linkage manner. The voice data may include: at least one of voice wake-up words and voice commands.
For example: voice data, which may include: voice audio data.
Therefore, through the voice data in various forms, the voice control under various user requirements can be realized, and the method is high in universality and good in flexibility.
In an optional example, the control unit 104 may be configured to determine an equipment control command for performing coordinated control on more than one equipment in the equipment system to be controlled according to the voice data and the set equipment knowledge map. The specific function and processing of the control unit 104 are referred to in step S120.
Optionally, the determining, by the control unit 104, an apparatus control command for performing linkage control on more than one apparatus in the to-be-controlled apparatus system according to the voice data and the set apparatus knowledge graph may include:
the control unit 104 may be further configured to determine semantic information according to the voice data. The specific functions and processes of the control unit 104 are also referred to in step S210.
More optionally, the determining, by the control unit 104, semantic information according to the voice data may include: the control unit 104 may be further configured to perform semantic analysis on the voice data to obtain semantic information included in the voice data. The semantic information may include: and (5) semantic keywords.
For example: semantic parsing may be converting voice data into text data. Semantic parsing: and converting the voice data into text data, and extracting and identifying the equipment entity and the control entity.
Therefore, the semantic information of the voice data is determined by performing semantic analysis on the voice data, so that the determination of the semantic information of the voice data is accurate and reliable.
The control unit 104 may be further configured to determine a usage scenario currently required by the user according to the semantic information. The specific functions and processes of the control unit 104 are also referred to in step S220.
For example: knowledge graph of household electrical appliance: and searching and matching in the knowledge graph according to the analyzed semantics.
More optionally, the determining, by the control unit 104, a usage scenario currently required by the user according to the semantic information may include: the control unit 104 may be further configured to determine, according to a correspondence between set semantic information and set scenes, that a set scene corresponding to the set semantic information that is the same as the set semantic information in the correspondence is a use scene currently required by a user.
Therefore, the use scene corresponding to the semantic information of the voice data is determined according to the corresponding relation between the set semantic information and the set scene, and the determination mode is simple, convenient and reliable.
The control unit 104 may be further configured to determine, according to the device knowledge map, a device control command of more than one device and its linkage response relationship in the usage scenario. The specific function and processing of the control unit 104 are also referred to in step S230.
For example: the household appliance control knowledge graph is integrated into a household system, so that the household appliance can sense different scenes, and give corresponding combined response operation after performing semantic analysis on a voice control command.
Therefore, the current use scene required by the user is determined based on the semantic information of the voice data, and the equipment control command of more than one equipment and the linkage response relation of the equipment in the use scene is further determined according to the equipment knowledge map, so that the equipment control command of more than one equipment in linkage response is accurately and reliably determined.
More optionally, the determining, by the control unit 104, the device control command of more than one device and its linkage response relationship under the usage scenario according to the device knowledge graph may include:
the control unit 104 may be further configured to determine, according to the linkage response relationship between different devices in different scenes in the device knowledge graph, one or more devices in the device knowledge graph corresponding to the usage scene and the linkage response relationship between the one or more devices. The specific functions and processes of the control unit 104 are also referred to in step S310.
The control unit 104 may be further specifically configured to generate a device control command of the at least one device and the linkage response relationship thereof in the usage scenario based on the semantic information and the at least one device corresponding to the usage scenario and the linkage response relationship between the at least one device. For example: and determining more than one device corresponding to the use scene in the device knowledge graph and the linkage response relationship between the more than one device according to the linkage response relationship between different devices in different scenes in the device knowledge graph, and generating a device control command of the more than one device and the linkage response relationship thereof in the use scene. The specific functions and processes of the control unit 104 are also referred to in step S320.
Therefore, the more than one device to be controlled and the linkage response relationship thereof in the use scene are determined according to the linkage response relationship between different devices in different scenes, and the device control command for the more than one device and the linkage response relationship thereof in the use scene is determined by combining the semantic information of the voice data, so that the reliability is high, and the control convenience is good.
In an optional example, the control unit 104 may be further configured to control, according to the device control command, joint action of more than one device in the to-be-controlled device system, so as to realize linkage control of more than one device in the to-be-controlled device system. The specific function and processing of the control unit 104 are also referred to in step S130.
For example: the device control command may include: device control class commands extracted from textual data (e.g., semantic textual data); the household appliance jointly responds: the plurality of devices are controlled in an interlocking manner by the device control command shown in fig. 8. For another example: device control commands: wait for joint control commands of the devices. Device association response: and the corresponding equipment performs linkage response.
For example: giving a joint response of the home devices, comprising: and performing linkage response among the devices through the relation graphs among various devices in the knowledge graph. The household appliance control information map is built by the knowledge map method, timely and accurate response can be given to various voice control commands, the intelligent degree of the intelligent home system is improved, the user requirements are met, and the experience effect is improved; the household appliance knowledge map can be a knowledge map formed by combining household appliance data. Voice data are collected in real time through a household appliance control platform, real-time semantic analysis is carried out, and corresponding equipment combination and intelligent response are achieved; according to the voice intention of the user, the corresponding operation is accurately and efficiently completed.
Therefore, the equipment control command for linkage control of more than one equipment in the equipment system to be controlled is determined based on the voice data and the set equipment knowledge graph of the equipment system to be controlled, and then the joint action of more than one equipment in the equipment system to be controlled is controlled according to the equipment control command, so that the linkage control of more than one equipment in the equipment system to be controlled is realized, the intelligent degree is high, and the convenience in use of a user is good.
In an alternative embodiment, the method may further include: the process of establishing the equipment knowledge graph of the equipment system to be controlled specifically comprises the following steps:
the obtaining unit 102 may also be configured to collect device data of the device system to be controlled and control data (e.g., historical data of control commands) for controlling each device in the device system to be controlled. The specific functions and processes of the acquisition unit 102 are also referred to in step S410.
The device data may include: at least one of a device name, a device MAC address, and an IP address; and/or, the control data may include: control command text and corresponding operations. For example: data of the household electrical appliance: device name, device MAC address, IP address; control command history data: control command text and corresponding operations.
Therefore, accuracy and reliability of construction of the equipment knowledge graph of the equipment system to be controlled are improved beneficially through the equipment data in various forms.
The control unit 104 may be further configured to determine, according to the device data and the control data, each device in the device system to be controlled and an association relationship between the devices. The specific function and processing of the control unit 104 are also referred to in step S420.
For example: and collecting data on the household electrical appliance interconnection platform, and establishing a database. Collecting data may include: and acquiring equipment data in the intelligent home system through the equipment interconnection platform. The collected data may include, among other things: home device data and control command history data. Data of the household electrical appliance: device name, device MAC address, IP address; control command history data: control command text and corresponding operations. The operation corresponding to the control command text may include: an operation command to the device. For example: the operation command corresponding to "turn on the air conditioner" is "air conditioner _ control _ on".
Optionally, the determining, by the control unit 104, the association relationship between each device in the device system to be controlled and the device in the device system to be controlled according to the device data and the control data may include:
the control unit 104 may be further configured to perform preprocessing on the device data and the control data to obtain current information. The specific functions and processes of the control unit 104 are also referred to in step S510.
Wherein, the pretreatment may include: at least one of missing value processing, normalization processing, and noise reduction processing.
For example: and collecting historical data of the historical equipment and the control command. Data preprocessing: and preprocessing the data such as missing value processing, standardization, noise reduction and the like.
Therefore, the accuracy and the reliability of the equipment data and the control data are improved by preprocessing the equipment data and the control data in various forms.
The control unit 104 may be further configured to extract, from the current information, an equipment entity in the equipment system to be controlled and an association relationship between different equipment entities, where the association relationship is used as an association relationship between each equipment in the equipment system to be controlled and the equipment entity in the equipment system to be controlled. The specific functions and processes of the control unit 104 are also referred to in step S520.
For example: information extraction: and extracting entities and relations from the preprocessed data.
Therefore, the equipment entity and the incidence relation thereof are extracted after the equipment data and the control data of the equipment system to be controlled are preprocessed and used as the incidence relation among the equipment in the equipment system to be controlled, and the processing accuracy is good and the reliability is high.
The control unit 104 may also be configured to perform a knowledge mapping process based on the device entities and the association relationship therebetween to obtain a linkage response relationship between the device entities and the linkage response relationship therebetween, which is used as a device knowledge map of the device system to be controlled. The specific functions and processes of the control unit 104 are also referred to in step S430.
For example: by building a household appliance interconnection system based on the knowledge graph: related knowledge data of the equipment is automatically or semi-automatically acquired from a home system, and a knowledge graph of the household appliance is constructed to provide interconnection and intelligent knowledge services.
For example: the knowledge facts are extracted by utilizing the database through a series of automatic or semi-automatic technical means and are stored in a data layer and a mode layer of the knowledge base, and a knowledge graph of the household appliance is built. Establishing a database may include: and combining the data of the household electrical appliance and the corresponding control relation into a ternary body to be stored in a graph database by utilizing a graph database building technology. The knowledge base comprises a database, and the database only stores data. The data layer is composed of a series of facts, and the facts are mainly expressed by triples; the mode layer is above the data layer and is used for managing the data layer.
From this, through collecting the equipment data and the control data of waiting to control equipment system, and then carry out the equipment knowledge map that knowledge map ization was handled and is obtained waiting to control equipment system based on this equipment data and control data to can set up the equipment knowledge map of waiting to control equipment system in advance, so that realize the linkage voice control of this equipment more than one equipment in waiting to control equipment system based on this equipment knowledge map, promote convenience and the reliability that the user used greatly.
The knowledge mapping process may include: and at least one of knowledge representation, knowledge fusion and knowledge inference is carried out.
For example: knowledge representation: knowledge representation is performed using attribute maps (graph databases) of entities and relationships. And (3) knowledge fusion: and fusing the description information of the entity and the relationship to determine the equivalent attribute and the equivalent relationship. Knowledge reasoning: and reasoning the implicit knowledge, enriching the knowledge map, and cleaning the knowledge to obtain the knowledge map of the household appliance.
Therefore, accuracy and reliability of the knowledge graph of the obtained equipment can be improved by means of knowledge graph processing in various forms.
Since the processes and functions implemented by the apparatus of this embodiment substantially correspond to the embodiments, principles and examples of the method shown in fig. 1 to 5, the description of this embodiment is not detailed, and reference may be made to the related descriptions in the foregoing embodiments, which are not repeated herein.
Through a large number of tests, the technical scheme of the invention can provide interconnection and intelligent knowledge services by building the household appliance interconnection system based on the knowledge graph, and improve the convenience of use of users.
According to the embodiment of the invention, the invention further provides the intelligent home system corresponding to the voice control device. This intelligent home systems can include: the voice control device described above.
With the development of deep learning (deep learning is a method for performing characterization learning on data in machine learning) technology in the field of natural language processing, intelligent voice control of various household devices becomes possible. For example: the Knowledge map (also called scientific Knowledge map) is a series of different graphs displaying Knowledge development process and structure relation, and is a Knowledge domain visualization or Knowledge domain mapping map in the book intelligence field, and uses visualization technology to describe Knowledge resources and carriers thereof, and excavates, analyzes, constructs, draws and displays Knowledge and mutual relation between the Knowledge resources and the carriers, and can carry out Knowledge organization on large-scale, heterogeneous and multi-element household appliances with loose organization architecture in a household system by using strong semantic processing capability and development organization capability. The technology can realize various types and combined control of the equipment in the home system.
In an optional embodiment, the present invention provides a method for interconnecting and controlling home appliances based on a knowledge graph, where various devices, sensors, radio frequency identification, and the like in an intelligent home system may form an intelligent home device network, and are managed by an intelligent management system (e.g., an intelligent gateway, a cloud gateway, and the like) to provide an intelligent service for a user. Therefore, in the intelligent home system based on voice control, the problems that the voice control command cannot meet the user requirements of various household appliances, intelligent linkage control cannot be realized, the existing connection mode is single, the effect is not intelligent enough, new equipment is difficult to add, the centralized control difficulty is high and the like can be solved.
Therefore, the interconnection and systematic control problem of the household appliances is a technical difficulty, the household appliance control information map is established by a knowledge map method, timely and accurate response can be given to various voice control commands, the intelligent degree of the intelligent household system is improved, the user requirements are met, and the experience effect is improved.
In an optional example, the scheme of the invention comprises the following steps of building a household appliance interconnection system based on a knowledge graph: related knowledge data of the equipment is automatically or semi-automatically acquired from a home system, and a knowledge graph of the household appliance is constructed to provide interconnection and intelligent knowledge services.
Alternatively, a fully automated approach is one that does not require human intervention or assistance, and a semi-automated approach is the other way around.
Optionally, the relevant knowledge data may include: data of the household electrical appliance: device name, device MAC address, IP address; control command history data: control command text and corresponding operations.
In an optional example, the scheme of the invention designs a home appliance combined control method, which comprises the following steps: the household appliance control knowledge graph is integrated into a household system, so that the household appliance can sense different scenes, and give corresponding combined response operation after performing semantic analysis on a voice control command.
The different scenes sensed by the equipment mainly refer to scenes formed by various household appliances in a home system. For example: the device senses different scenes, and may be used to identify which home devices and related information of the devices, such as names, types, functions, and the like, exist in the home system. After each household appliance is networked, an appliance network is formed, and an appliance networking scene is formed, so that the scheme of the invention can sense and draw an appliance networking system scene.
In an alternative embodiment, reference may be made to the examples shown in fig. 7 and 8 to illustrate specific implementation procedures of the scheme of the present invention.
In an alternative embodiment, the scheme of the invention mainly comprises: the related technologies in the aspects of knowledge graph, big data processing, edge computing, cloud computing and the like are divided into three functional modules: household electrical appliances interconnection platform, household electrical appliances control platform.
In the system for interconnecting and controlling home appliances based on the knowledge graph shown in fig. 7, the home appliance data may include: device name, device MAC address, IP address, etc.; the control command history data may include: controlling command texts and corresponding operations; knowledge graph building technology, see the example shown in fig. 8; the home appliance knowledge map can be a knowledge map formed by combining home appliance data; voice data, which may include: voice audio data; semantic analysis, which can be converting voice data into text data; the device control command may include: device control class commands extracted from textual data (e.g., semantic textual data); the household appliance jointly responds: the plurality of devices are controlled in an interlocking manner by the device control command shown in fig. 8.
Referring to the example shown in fig. 7, the principle of implementing the method for interconnecting and controlling home appliances based on the knowledge graph according to the present invention may include:
and 11, collecting data on the household electrical appliance interconnection platform and establishing a database.
Optionally, collecting data may include: and acquiring equipment data in the intelligent home system through the equipment interconnection platform.
The collected data may include, among other things: home device data and control command history data. Data of the household electrical appliance: device name, device MAC address, IP address; control command history data: control command text and corresponding operations. The operation corresponding to the control command text may include: an operation command to the device. For example: the operation command corresponding to "turn on the air conditioner" is "air conditioner _ control _ on".
And step 12, extracting knowledge facts by utilizing the database through a series of automatic or semi-automatic technical means, storing the knowledge facts into a data layer and a mode layer of a knowledge base, and building a knowledge graph of the household appliance.
Optionally, establishing the database may include: and combining the data of the household electrical appliance and the corresponding control relation into a ternary body to be stored in a graph database by utilizing a graph database building technology.
The knowledge base comprises a database, and the database only stores data. The data layer is composed of a series of facts, and the facts are mainly expressed by triples; the mode layer is above the data layer and is used for managing the data layer.
And step 13, acquiring voice data in real time through the household appliance control platform, and performing real-time semantic analysis to realize corresponding combined and intelligent response of the appliances. According to the voice intention of the user, the corresponding operation is accurately and efficiently completed.
In an alternative specific example, referring to the example shown in fig. 8, the appliance interconnection and control algorithm flow based on the knowledge graph according to the present invention may include:
step 21, knowledge graph building technology, which may specifically include:
and step 31, collecting historical data of the historical equipment and the control command.
Step 32, data preprocessing: and preprocessing the data such as missing value processing, standardization, noise reduction and the like.
For example: the missing value is processed by filling the data items which may be missing with an overall average or other methods. Normalization is to normalize or isometrize the data to allow different data to be similar, such as audio data and location data to be of the same type.
Step 33, information extraction: and extracting entities and relations from the data.
Step 34, knowledge representation: knowledge representation is performed using attribute maps (graph databases) of entities and relationships.
Step 35, knowledge fusion: and fusing the description information of the entity and the relationship to determine the equivalent attribute and the equivalent relationship.
Step 36, knowledge reasoning: and reasoning the implicit knowledge, enriching the knowledge map, and cleaning the knowledge to obtain the knowledge map of the household appliance.
Step 22, real-time voice: and monitoring the voice of the air conditioner in real time.
Step 23, semantic analysis: and converting the voice data into text data, and extracting and identifying the equipment entity and the control entity.
Step 24, knowledge graph of the household appliance: and searching and matching in the knowledge graph according to the analyzed semantics.
Step 25, device control command: wait for joint control commands of the devices.
Step 26, device joint response: and the corresponding equipment performs linkage response.
Therefore, in consideration of the fact that in the process of controlling other devices by using the voice of the intelligent home system, various voice control commands need to be responded accurately, efficiently and in real time in a combined manner, an intelligent, efficient, high-accuracy and high-reliability household appliance interconnection and control system is needed. The voice control of other devices in the current market is mainly realized by single control in a matching mode, intelligent linkage of the devices cannot be realized, and a high-accuracy and reliable device combined control method is not available for the moment. Therefore, the scheme of the invention constructs an interconnection and control system by using the related data of the household appliances on the basis of the knowledge map technology, analyzes the voice data in real time, accurately gives the joint response of the household appliances in time and provides an intelligent household system which meets the user requirements and integrates the voice control in an intelligent manner.
Wherein giving a joint response of the home devices comprises: and performing linkage response among the devices through the relation graphs among various devices in the knowledge graph. For example: after the semantic analysis, the related device commands such as a window curtain opening command, an air conditioner opening command, an electric lamp opening command, lamp _ control _ on and the like are generated according to the device relation in the map, and the combined response of the household devices is formed.
Since the processes and functions implemented by the smart home system of this embodiment substantially correspond to the embodiment, the principle, and the example of the apparatus shown in fig. 6, reference may be made to the related descriptions in the foregoing embodiments without being detailed in the description of this embodiment.
After a large number of tests and verifications, by adopting the technical scheme of the invention, the household appliance control knowledge graph is integrated into the household system, so that the equipment can sense different scenes, perform semantic analysis on the voice control command, and then give out corresponding combined response operation, thereby improving the intelligent degree of the intelligent household system.
According to an embodiment of the present invention, there is also provided a storage medium corresponding to the voice control method. The storage medium may include: the storage medium has stored therein a plurality of instructions; the instructions are used for loading and executing the voice control method by the processor.
Since the processing and functions implemented by the storage medium of this embodiment substantially correspond to the embodiments, principles, and examples of the methods shown in fig. 1 to fig. 5, details are not described in the description of this embodiment, and reference may be made to the related descriptions in the foregoing embodiments, which are not described herein again.
Through a large number of tests, the technical scheme of the invention is adopted to carry out linkage response among the devices through the relation graphs among various devices in the knowledge graph, so that various control requirements of users can be met, and the user experience is good.
According to the embodiment of the invention, the invention further provides the intelligent home system corresponding to the voice control method. This intelligent home systems can include: a processor for executing a plurality of instructions; a memory to store a plurality of instructions; wherein the instructions are stored in the memory, and loaded by the processor and used for executing the voice control method.
Since the processes and functions implemented by the smart home system of this embodiment substantially correspond to the embodiments, principles, and examples of the methods shown in fig. 1 to fig. 5, reference may be made to the related descriptions in the foregoing embodiments for details which are not described in detail in the description of this embodiment, and further description is not repeated here.
Through a large number of tests, the technical scheme of the invention is adopted, and on the basis of the knowledge map technology, the interconnection and control system is constructed by utilizing the relevant data of the household appliances, the voice data is analyzed in real time, the joint response of the household appliances is accurately given in time, the diversification of the connection and control modes can be realized, the intelligent degree of the household appliances and even the intelligent household system can be improved, and the user experience is improved.
In summary, it is readily understood by those skilled in the art that the advantageous modes described above can be freely combined and superimposed without conflict.
The above description is only an example of the present invention, and is not intended to limit the present invention, and it is obvious to those skilled in the art that various modifications and variations can be made in the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.