Equipment control method and device, electronic equipment and readable storage medium

Abstract

The embodiment of the invention provides an equipment control method and device, electronic equipment and a readable storage medium, and the method comprises the steps: carrying out the analysis of a target voice instruction under the condition that first node equipment in an equipment cluster receives the target voice instruction, and obtaining the instruction information indicated by the target voice instruction; under the condition that the instruction information does not meet the response condition of the first node equipment, the first node equipment forwards the target voice instruction to other node equipment in the equipment cluster based on the MESH network; and when any second node device in the other node devices receives the target voice instruction and detects that the target voice instruction satisfies a response condition of the second node device, the second node device responds to the target voice instruction and executes a target control operation indicated by the target voice instruction. Therefore, the equipment control cost is reduced, and the voice signal does not need to be uploaded to the cloud for identification, so that the risk of secret leakage is reduced, and the equipment control security is improved.

Description

Technical Field

[0001] The present invention relates to the field of smart home technology, and in particular to a device control method, device, electronic device and readable storage medium. Background Art

[0002] With the rapid development of science and technology, the field of smart home has ushered in unprecedented changes, among which voice intelligent control technology has become an important force driving this change. By integrating advanced voice recognition and processing technology, the smart home system realizes efficient and convenient interaction between users and home devices.

[0003] In related technologies, smart home systems often set up a home host (central controller) to receive, process and execute voice commands from users. After the voice signal collected by the home host is recognized in the cloud, the home host sends it to the corresponding smart device through the network for execution, thereby realizing online voice recognition and intelligent control of smart home devices. However, this smart device control method is costly and there is a risk of leakage when voice is uploaded to the cloud. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the present invention provides a device control method, an apparatus, an electronic device and a readable storage medium.

[0005] In a first aspect, the present invention provides a device control method, the method comprising:

[0006] When the first node device in the device cluster receives the target voice instruction, the target voice instruction is parsed to obtain instruction information indicated by the target voice instruction;

[0007] When the instruction information does not meet the response condition of the first node device, the first node device forwards the target voice instruction to other node devices in the device cluster based on the MESH network;

[0008] When any of the second node devices among the other node devices receives the target voice instruction and detects that the instruction information of the target voice instruction meets the response condition of the second node device, the second node device responds to the target voice instruction and performs the target control operation indicated by the target voice instruction.

[0009] Optionally, the method further comprises:

[0010] In a case where the instruction information satisfies a response condition of the first node device, the first node device responds to the target voice instruction and performs a target control operation indicated by the target voice instruction.

[0011] Optionally, the method further comprises:

[0012] When the first node device detects a target trigger factor, acquiring trigger information corresponding to the target trigger factor;

[0013] When the trigger information meets a preset trigger condition, the first node device is started.

[0014] Optionally, parsing the target voice instruction to obtain instruction information indicated by the target voice instruction includes:

[0015] Performing voice recognition on the target voice command to obtain text information corresponding to the target voice command;

[0016] Based on the text information, the instruction information is determined; the instruction information includes control information, device information and space information.

[0017] Optionally, the determining the instruction information based on the text information includes:

[0018] Extracting keywords from the text information to obtain target keywords; the target keywords at least include control keywords;

[0019] determining the control information based on the control keyword;

[0020] In a case where the target keyword includes a device keyword and a space keyword, determining the device information and the space information based on the device keyword and the space keyword;

[0021] In a case where the target keyword does not include a device keyword, determining the device information based on a first device identifier corresponding to the first node device;

[0022] In a case where the target keyword does not include a spatial keyword, the spatial information is determined based on a first spatial identifier corresponding to the first node device.

[0023] Optionally, the response condition of the first node device includes that the device information in the instruction information matches the first device identifier corresponding to the first node device and the space information matches the first space identifier corresponding to the first node device;

[0024] The response condition of the second node device includes that the device information in the instruction information matches the second device identifier of the second node device and the space information matches the second space identifier of the second node device.

[0025] Optionally, the target control operation is determined based on the control information.

[0026] In a second aspect, the present invention provides a device control apparatus, the apparatus comprising:

[0027] A first parsing module, configured to parse the target voice instruction when the first node device in the device cluster receives the target voice instruction, and obtain instruction information indicated by the target voice instruction;

[0028] A first forwarding module, configured to forward the target voice command to other node devices in the device cluster based on the MESH network by the first node device if the command information does not meet the response condition of the first node device;

[0029] The first execution module is used for the second node device to respond to the target voice instruction and execute the target control operation indicated by the target voice instruction when any of the second node devices among the other node devices receives the target voice instruction and detects that the instruction information of the target voice instruction meets the response condition of the second node device.

[0030] Optionally, the device may further include:

[0031] The second execution module is used for, when the instruction information satisfies the response condition of the first node device, the first node device responds to the target voice instruction and executes the target control operation indicated by the target voice instruction.

[0032] Optionally, the device may further include:

[0033] A first acquisition module, configured to acquire trigger information corresponding to the target trigger factor when the first node device detects the target trigger factor;

[0034] The first starting module is used to start the first node device when the trigger information meets a preset trigger condition.

[0035] Optionally, the first parsing module includes:

[0036] A first recognition module, configured to perform voice recognition on the target voice instruction to obtain text information corresponding to the target voice instruction;

[0037] The first determination module is used to determine the instruction information based on the text information; the instruction information includes control information, device information and space information.

[0038] Optionally, the first determining module includes:

[0039] A first extraction module is used to extract keywords from the text information to obtain target keywords; the target keywords at least include control keywords;

[0040] A first determination submodule, configured to determine the control information based on the control keyword;

[0041] A second determination submodule is configured to determine the device information and the space information based on the device keyword and the space keyword when the target keyword includes the device keyword and the space keyword;

[0042] A third determination submodule, configured to determine the device information based on a first device identifier corresponding to the first node device when the target keyword does not include a device keyword;

[0043] The fourth determination submodule is used to determine the spatial information based on the first spatial identifier corresponding to the first node device when the target keyword does not include the spatial keyword.

[0044] Optionally, the response condition of the first node device includes that the device information in the instruction information matches the first device identifier corresponding to the first node device and the space information matches the first space identifier corresponding to the first node device;

[0045] The response condition of the second node device includes that the device information in the instruction information matches the second device identifier of the second node device and the space information matches the second space identifier of the second node device.

[0046] Optionally, the target control operation is determined based on the control information.

[0047] In a third aspect, the present invention provides an electronic device comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the device control method described in any one of the first aspects is implemented.

[0048] In a fourth aspect, the present invention provides a readable storage medium, which, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute the steps in the device control method in any one of the embodiments of the first aspect above.

[0049] In an embodiment of the present invention, when the first node device in the device cluster receives the target voice command, the target voice command is parsed to obtain the command information indicated by the target voice command; when the command information does not meet the response condition of the first node device, the first node device forwards the target voice command to other node devices in the device cluster based on the MESH network; when any of the second node devices in other node devices receives the target voice command and detects that the target voice command meets the response condition of the second node device, the second node device responds to the target voice command and executes the target control operation indicated by the target voice command. In this way, the node devices in the device cluster can receive and identify the target voice command, and forward the target voice command through the MESH network, so that each node device in the device cluster forms a local wireless local area network without access to an external network or a remote server, thereby reducing the cost of device control. In addition, by using offline voice recognition, there is no need to upload the voice signal to the cloud for recognition, thereby reducing the risk of leakage and improving the security of device control. At the same time, when any first node device in the device cluster receives the target voice command, it can first identify whether it is a command that it needs to respond to. If not, it can forward the message to other node devices in the device cluster through the MESH network, so that the second node device that the target voice command actually needs to control can receive the target voice command and perform the target control operation. Correspondingly, for users, they can input the target control command to any node device in the device cluster without the need for targeted command output, and realize the linkage control of the node devices that actually need to be controlled, which improves the convenience of device control and further improves the intelligence of device control. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 is a flowchart of a device control method provided by an embodiment of the present invention;

[0052] Figure 2 is a flowchart of a specific example provided by an embodiment of the present invention;

[0053] Figure 3 is a structural diagram of a device control device provided by an embodiment of the present invention;

[0054] Figure 4 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] Figure 1 is a flow chart of the steps of a device control method provided by an embodiment of the present invention, such as Figure 1 As shown, the method may include:

[0057] Step 101: When a first node device in a device cluster receives a target voice instruction, the target voice instruction is parsed to obtain instruction information indicated by the target voice instruction.

[0058] In an embodiment of the present invention, a device cluster may be a collection of devices deployed in an area, for example, it may be a collection of multiple smart home devices in an indoor area. Multiple devices in a device cluster may form a MESH self-organizing network through their respective MESH self-organizing network modules, and each device may communicate based on the MESH network. Each device may self-organize and network based on different network topologies, such as chain topology, star topology, and mesh topology. After networking, the devices in the device cluster may serve as node devices in the MESH self-organizing network. Among them, the chain topology refers to the chain distribution between each node device, and only two adjacent node devices can communicate directly; the star topology refers to the node devices being connected in a star shape to form a network, and there is a central node device in the network, and other node devices are directly connected to the central node device. The mesh topology refers to multiple types of networks being connected by multiple node devices, allowing the network to select the fastest path to transmit data.

[0059] The microphone array in the node device can capture the voice signal emitted by the user and pre-process the collected voice signal, which may include noise removal, echo cancellation, automatic gain control, etc., to improve the quality of the voice signal. The key parameters reflecting the voice characteristics, such as pitch, timbre, speaking speed, etc., are extracted from the pre-processed voice signal. The extracted features are compared with the pre-trained speech recognition model to find the best matching model, thereby recognizing the user's voice command.

[0060] When the first node device in the device cluster receives the target voice command, it will parse the target voice command to obtain the command information indicated by the target voice command. The first node device can be any node device in the device cluster that captures the voice signal sent by the user. The command information can include device information, space information and control information. The device information is used to characterize the node device that the target voice command needs to control, the space information is used to characterize the space type that the target voice command needs to control, and the control information is used to characterize the type of control operation that the target voice command needs to perform on the node device. The process of parsing the target voice command can include text conversion and semantic analysis, etc., and the command information indicated by the target voice command is obtained by understanding the user's intentions and needs.

[0061] Step 102: When the instruction information does not meet the response condition of the first node device, the first node device forwards the target voice instruction to other node devices in the device cluster based on the MESH network.

[0062] In the embodiment of the present invention, after the first node device obtains the instruction information, it is determined whether the instruction information satisfies the response condition of the first node device. Specifically, when the instruction information matches the response condition of the first node device, it is determined that the instruction information satisfies the response condition of the first node device; when the instruction information does not match the response condition of the first node device, it is determined that the instruction information does not satisfy the response condition of the first node device. The response condition of the first node device may include that the device information in the instruction information matches the first device identifier corresponding to the first node device and the space information matches the first space identifier corresponding to the first node device.

[0063] For any node device in the device cluster, a device identifier is pre-set for the node device as a device identifier, and a space identifier is pre-set as a space identifier. Exemplarily, the device type of the node device can be set as the device identifier, for example, the device identifier can be an air conditioner, a television, or a washing machine. Based on the space where the node device is located, the space identifier corresponding to the node device is determined. For example, the space identifier can be a bedroom or a living room. Furthermore, in order to distinguish between multiple node devices of the same type and multiple spaces of the same type in the same space, a serial number can be added to the device identifier and the space identifier for distinction. For example, the device identifier can be air conditioner 2, television 1, washing machine 1, and the space identifier can be bedroom 2, living room 1, and bathroom 2.

[0064] When the device information in the instruction information does not match the first device identifier corresponding to the first node device and the space information does not match the first space identifier corresponding to the first node device, that is, the instruction information does not meet the response condition of the first node device, it indicates that the current first node device is not the node device indicated by the target voice instruction, and the current first node device does not need to respond to the target voice instruction. Therefore, the first node device will forward the target voice instruction to other node devices in the device cluster based on the MESH network. When the first node device forwards the target voice instruction based on the MESH network, it will adaptively forward the instruction. Since the propagation of Mesh signals is radial, node devices at a certain distance around the first node device can receive the target voice instruction. Specifically, according to the distribution between the node devices, communication will be carried out in different network topology forms. For example, if node devices A, B, and C are all within the transmission range of the first node device E at the same time, and A, B, and C are not within their respective transmission ranges, then E forwards the target voice instruction in a star topology. If node devices A, B, and C are all within the transmission range of the first node device E at the same time, and A, B, and C are within their respective transmission ranges, then E forwards the target voice command in a mesh topology. If node devices A and B are within their respective transmission ranges, B and E are within their respective transmission ranges, and E and A are not within their respective transmission ranges, then E forwards the target voice command in a chain topology.

[0065] Step 103: When any of the second node devices among the other node devices receives the target voice instruction and detects that the instruction information of the target voice instruction meets the response condition of the second node device, the second node device responds to the target voice instruction and executes the target control operation indicated by the target voice instruction.

[0066] In the embodiment of the present invention, any node device within the signal transmission range of the first node device can receive the target voice command forwarded by the first node device. When each node device receives the target voice command, it will parse the target voice command to obtain the command information, and determine whether the command information meets the response condition of the node device. If not, the node device will continue to forward the target voice command.

[0067] For any second node device, if it is detected that the target voice instruction satisfies the response condition of the second node device, it is characterized that the second node device is the node device indicated by the target voice instruction, and the second node device needs to respond to the target voice instruction. Therefore, the second node device will respond to the target voice instruction and perform the target control operation indicated by the target voice instruction. Among them, the second node device is the node device that needs to be controlled as indicated by the target voice instruction. The response condition of the second node device includes that the device information in the instruction information matches the second device identifier of the second node device and the space information matches the second space identifier of the second node device. The target control operation is determined based on the control information in the instruction information. The control information may include opening, closing, adjusting parameters, etc. Correspondingly, the target control operation performed by the node device may include opening, closing, adjusting parameters, etc.

[0068] In summary, in an embodiment of the present invention, when the first node device in the device cluster receives the target voice command, the target voice command is parsed to obtain the command information indicated by the target voice command; when the command information does not meet the response condition of the first node device, the first node device forwards the target voice command to other node devices in the device cluster based on the MESH network; when any of the second node devices in other node devices receives the target voice command and detects that the target voice command meets the response condition of the second node device, the second node device responds to the target voice command and executes the target control operation indicated by the target voice command. In this way, the node devices in the device cluster can receive and identify the target voice command, and forward the target voice command through the MESH network, so that each node device in the device cluster forms a local wireless local area network without access to an external network or a remote server, thereby reducing the cost of device control, and using offline voice recognition, there is no need to upload the voice signal to the cloud for recognition, which reduces the risk of leakage and improves the security of device control. At the same time, when any first node device in the device cluster receives the target voice command, it can first identify whether it is a command that it needs to respond to. If not, it can forward the message to other node devices in the device cluster through the MESH network, so that the second node device that the target voice command actually needs to control can receive the target voice command and perform the target control operation. Correspondingly, for users, they can input the target control command to any node device in the device cluster without the need for targeted command output, and realize the linkage control of the node devices that actually need to be controlled, which improves the convenience of device control and further improves the intelligence of device control.

[0069] Optionally, the embodiment of the present invention may further include the following steps:

[0070] Step 201: When the instruction information satisfies a response condition of the first node device, the first node device responds to the target voice instruction and executes a target control operation indicated by the target voice instruction.

[0071] In an embodiment of the present invention, if the target voice instruction satisfies the response condition of the first node device, it characterizes that the first node device is a node device that the target voice instruction indicates needs to be controlled, and the first node device needs to respond to the target voice instruction. Therefore, the first node device will respond to the target voice instruction and perform the target control operation indicated by the target voice instruction.

[0072] In an embodiment of the present invention, after receiving the target voice command, the first node device can determine whether it needs to respond to the target voice command. If so, it can directly respond to the target voice command. If not, it can forward the target voice command to other node devices based on the MESH network, thereby achieving that any node device can not only recognize the control commands corresponding to its own device, but also recognize the control commands corresponding to other devices.

[0073] Optionally, the embodiment of the present invention may further include the following steps:

[0074] Step 301: When the first node device detects a target trigger factor, obtain trigger information corresponding to the target trigger factor.

[0075] In an embodiment of the present invention, when the first node device detects a target trigger factor, it indicates that the user has an attempt to wake up the first node device, so the target trigger factor can be captured and the trigger information corresponding to the target trigger factor can be obtained. Among them, the target trigger factor can be pre-set, and the target trigger factor can be a sound, an action, etc. Correspondingly, depending on the target trigger factor, the trigger information corresponding to the target trigger factor is also different. Exemplarily, the trigger information corresponding to the target trigger factor may include the text content, sound energy, pitch, timbre, speech speed, etc. corresponding to the sound, or the action type, action amplitude, action duration, etc. corresponding to the action.

[0076] Step 302: When the trigger information meets a preset trigger condition, start the first node device.

[0077] In an embodiment of the present invention, when the trigger information meets the preset trigger condition, the first node device is awakened and the first node device is started. After the first node device is started, it can capture and detect in real time whether there is a target voice instruction, and perform the operation of step 101 when the target voice instruction is received. Among them, the preset trigger condition is pre-set by the user, and can be set according to the target trigger factor and the trigger information. The embodiment of the present invention does not limit this. Exemplarily, the preset trigger condition may include that the text content corresponding to the sound matches the preset text; the sound energy of the sound is greater than the preset threshold; the action type meets the preset action type; the action duration is greater than the preset duration, etc. It can be understood that the preset trigger condition may include one condition or multiple conditions, that is, it may be necessary for multiple different trigger information to meet multiple conditions contained in the preset trigger condition before the trigger information is considered to meet the preset trigger condition.

[0078] Exemplarily, the preset trigger condition may be a wake-up word, such as "hello". When the first node device detects a sound, it is necessary to obtain the text content corresponding to the sound. When the text content meets the preset trigger condition, that is, "hello", the first node device is started. Or, the preset trigger condition may be a fist gesture. When the first node device detects an action, it obtains the action type corresponding to the action. When the action type meets the preset trigger condition, that is, the fist gesture, the first node device is started. Or, the preset trigger condition may be the wake-up word "hello" and the sound energy is greater than a preset threshold. When the first node device detects a sound, it is necessary to obtain the text content and sound energy corresponding to the sound. When the text content meets the preset trigger condition, that is, "hello" and the sound energy is greater than the preset threshold, the first node device is started.

[0079] In the embodiment of the present invention, the first node device is awakened and started through the target trigger factor, thereby improving the flexibility of device control.

[0080] Optionally, step 101 may include the following steps:

[0081] Step 401: Perform voice recognition on the target voice instruction to obtain text information corresponding to the target voice instruction.

[0082] In the embodiment of the present invention, speech recognition is performed on the target voice command, including in-depth analysis of text information to understand the user's intention and specific needs. This usually involves natural language processing technology, such as part-of-speech tagging, syntactic analysis, semantic role tagging, etc. After speech recognition is performed on the target voice command, text information corresponding to the target voice command is obtained.

[0083] Step 402: Determine the instruction information based on the text information; the instruction information includes control information, device information and space information.

[0084] In an embodiment of the present invention, based on the text information of the target voice command, the command information corresponding to the target voice command is determined. Among them, the command information includes control information, device information, and space information.

[0085] Optionally, step 402 may include the following steps:

[0086] Step 4021: Extract keywords from the text information to obtain target keywords; the target keywords at least include control keywords.

[0087] In an embodiment of the present invention, the text information may be preprocessed first, and then keywords may be further extracted from the text information to obtain target keywords of at least one keyword type. The preprocessing steps may include decomposing the text into words or tokens (tokens) and removing common but meaningless words in the text, such as "de", "shi", etc. Then, keywords are extracted from the preprocessed text information to obtain target keywords. Among them, the target keywords at least include control keywords. Correspondingly, the target voice command at least includes command content for characterizing the control type. In addition to control keywords, the target keywords may also include device keywords and / or space keywords. Of course, the target keywords may also only include control keywords.

[0088] Step 4022: Determine the control information based on the control keywords.

[0089] In an embodiment of the present invention, the control information is determined based on the control keywords. Exemplarily, the control keywords themselves may be directly determined as the control information, or the control information may be determined based on the control keywords according to the first correspondence relationship. For example: the identified control keywords may be "open", "turn on", etc., and according to the first correspondence relationship, the control information will be determined as "open".

[0090] Step 4023: When the target keywords include device keywords and space keywords, determine the device information and the space information based on the device keywords and the space keywords.

[0091] In an embodiment of the present invention, when the target keywords include device keywords and space keywords, the device information and space information can be determined based on the device keywords and space keywords. Similar to the control keywords, the device keywords and space keywords can be directly determined as device information and space information, or the device keywords can be used to determine the device information according to the second correspondence, and the space keywords can be used to determine the space information according to the third correspondence. For example: the identified device keywords can be television, television, etc., and according to the second correspondence, the device information will be determined as "television"; the identified space keywords can be bathroom, toilet, etc., and according to the third correspondence, the space information will be determined as "bathroom".

[0092] It is understandable that when the method of determining the instruction information is to directly determine the control keyword, device keyword and space keyword itself as the control information, device information and space information, the user needs to accurately input the instruction content of the control keyword, device keyword and space keyword when inputting the instruction, such as "open", "TV", "bathroom" and so on. When the input keyword is "turn on", "TV", "bathroom", the instruction information cannot be recognized, so as to avoid the erroneous response of each device in the device cluster to the instruction. The specific setting can be made according to the actual needs, and the embodiment of the present invention does not limit this.

[0093] Step 4024: When the target keyword does not include a device keyword, determine the device information based on the first device identifier corresponding to the first node device.

[0094] In an embodiment of the present invention, when the target keyword does not include a device keyword, the device information is determined based on the first device identifier corresponding to the first node device. That is, when the target keyword does not include a device keyword, that is, when the target voice command does not include content indicating the device, the device identifier of the current device receiving the target voice command can be determined as the device information by default. Exemplarily, assuming that the first node device is an air conditioner, when the target keyword does not include the device keyword, the air conditioner can be determined as the device information.

[0095] Step 4025: When the target keyword does not include a spatial keyword, determine the spatial information based on a first spatial identifier corresponding to the first node device.

[0096] In an embodiment of the present invention, when the target keyword does not include a spatial keyword, the spatial information is determined based on the first spatial identifier corresponding to the first node device. That is, when the target keyword does not include a spatial keyword, that is, when the target voice instruction does not contain content indicating a space, the spatial identifier of the current device receiving the target voice instruction can be determined as the spatial information by default. Exemplarily, assuming that the first node device is in a bedroom, when the target keyword does not contain a spatial keyword, the bedroom can be determined as the spatial information.

[0097] In an embodiment of the present invention, keywords are extracted from text information to obtain target keywords that at least include control keywords. When the target keywords do not include device keywords and space keywords, the first device identifier and the first space identifier of the first node device can be determined as device information and space information by default, thereby improving the flexibility and convenience of device control.

[0098] In a possible implementation, when the first node device detects the sound of the target trigger factor, it obtains trigger information, including text content and sound energy, and starts the first node device when the text content is "Hello" and the sound energy is greater than a preset threshold. After the first node device is awakened, it starts to detect instructions, and obtains instruction information when receiving the target voice instruction. For example, when the target voice instruction is "turn on the air conditioner in the master bedroom", the recognized instruction information includes control information "turn on", device information "air conditioner" and space information "master bedroom"; when the target voice instruction is "turn on the device", the recognized instruction information includes control information "turn on", device information "air conditioner" determined based on the first device identifier corresponding to the first node device, and space information "master bedroom" determined based on the first space identifier corresponding to the first node device. When the target voice instruction is "turn on the air conditioner", the recognized instruction information includes control information "turn on", device information "air conditioner" and space information "master bedroom" determined based on the first space identifier corresponding to the first node device. Detect whether it is a local command. If the command information meets the response condition corresponding to the first node device, that is, the device information (air conditioner) in the command information matches the first device identifier (air conditioner) corresponding to the first node device and the space information (master bedroom) matches the first space identifier (master bedroom) corresponding to the first node device, then respond to the target voice command and execute the target control operation indicated by the target voice command. If the command information does not meet the response condition corresponding to the first node device, the target voice command is forwarded to other node devices in the device cluster based on the MESH network. Upon receiving the target voice command, other node devices execute "get command information" and subsequent steps.

[0099] It can be understood that, when the target voice instruction received by the first node device is "turn on the device", the identified device information is the first device identifier corresponding to the first node device, and the spatial information is the first spatial identifier corresponding to the first node device. Accordingly, the first node device receiving the target voice instruction will respond to the target voice instruction based on the instruction information and execute the target control operation indicated by the target voice instruction. In other words, when the instruction content of the target voice instruction does not specify the device information and spatial information, that is, when the target voice instruction only contains control information, any node device that receives the target voice instruction can directly respond to the target voice instruction by default and automatically execute the target control operation indicated by the target voice instruction. In this way, the instruction response speed of the node device can be further improved.

[0100] For example, Figure 2 A flow chart showing the specific steps of a device control method is shown in FIG. Figure 2 As shown, when the first node device detects the target trigger factor, it is determined whether the trigger information of the target trigger factor meets the preset trigger condition. If not, the process is terminated; if so, the first node device is started. The target voice instruction is received and the instruction information of the target voice instruction is obtained. It is determined whether the instruction information meets the response condition of the first node device. If so, the first node device responds to the target voice instruction and executes the target control operation indicated by the target voice instruction. If not, the target voice instruction is forwarded to other node devices in the device cluster based on the MESH network based on the first node device. After receiving the target voice instruction, each node device will determine whether the instruction information meets the response condition of the second node device. If so, the target control operation indicated by the target voice instruction is executed; if not, the target voice instruction will be forwarded to other node devices in the device cluster based on the MESH network. When receiving the target voice instruction, each other node device will obtain the instruction information and perform a new round of judgment until the instruction information meets the response condition of any node device in the other node devices.

[0101] Figure 3 is a schematic diagram of the structure of a device control device provided by an embodiment of the present invention, such as Figure 3 As shown, the device may specifically include:

[0102] The first parsing module 501 is used to parse the target voice instruction when the first node device in the device cluster receives the target voice instruction, so as to obtain the instruction information indicated by the target voice instruction;

[0103] A first forwarding module 502 is configured to forward the target voice command to other node devices in the device cluster based on the MESH network by the first node device if the command information does not meet the response condition of the first node device;

[0104] The first execution module 503 is used for the second node device to respond to the target voice instruction and execute the target control operation indicated by the target voice instruction when any of the second node devices in the other node devices receives the target voice instruction and detects that the instruction information of the target voice instruction meets the response condition of the second node device.

[0105] The embodiment of the present invention provides a device control device. When the first node device in the device cluster receives the target voice command, the target voice command is parsed to obtain the command information indicated by the target voice command; when the command information does not meet the response condition of the first node device, the first node device forwards the target voice command to other node devices in the device cluster based on the MESH network; when any of the second node devices in other node devices receives the target voice command and detects that the target voice command meets the response condition of the second node device, the second node device responds to the target voice command and executes the target control operation indicated by the target voice command. In this way, the node devices in the device cluster can receive and identify the target voice command, and forward the target voice command through the MESH network, so that each node device in the device cluster forms a local wireless local area network without access to an external network or a remote server, thereby reducing the cost of device control. In addition, by using offline voice recognition, there is no need to upload the voice signal to the cloud for recognition, thereby reducing the risk of leakage and improving the security of device control. At the same time, when any first node device in the device cluster receives the target voice command, it can first identify whether it is a command that it needs to respond to. If not, it can forward the message to other node devices in the device cluster through the MESH network, so that the second node device that the target voice command actually needs to control can receive the target voice command and perform the target control operation. Correspondingly, for users, they can input the target control command to any node device in the device cluster without the need for targeted command output, and realize the linkage control of the node devices that actually need to be controlled, which improves the convenience of device control and further improves the intelligence of device control.

[0106] Optionally, the device may further include:

[0107] The second execution module is used for, when the instruction information satisfies the response condition of the first node device, the first node device responds to the target voice instruction and executes the target control operation indicated by the target voice instruction.

[0108] Optionally, the device may further include:

[0109] A first acquisition module, configured to acquire trigger information corresponding to the target trigger factor when the first node device detects the target trigger factor;

[0110] The first starting module is used to start the first node device when the trigger information meets a preset trigger condition.

[0111] Optionally, the first parsing module 501 includes:

[0112] A first recognition module, configured to perform voice recognition on the target voice instruction to obtain text information corresponding to the target voice instruction;

[0113] The first determination module is used to determine the instruction information based on the text information; the instruction information includes control information, device information and space information.

[0114] Optionally, the first determining module includes:

[0115] A first extraction module is used to extract keywords from the text information to obtain target keywords; the target keywords at least include control keywords;

[0116] A first determination submodule, configured to determine the control information based on the control keyword;

[0117] A second determination submodule is configured to determine the device information and the space information based on the device keyword and the space keyword when the target keyword includes the device keyword and the space keyword;

[0118] A third determination submodule, configured to determine the device information based on a first device identifier corresponding to the first node device when the target keyword does not include a device keyword;

[0119] The fourth determination submodule is used to determine the spatial information based on the first spatial identifier corresponding to the first node device when the target keyword does not include the spatial keyword.

[0120] Optionally, the response condition of the first node device includes that the device information in the instruction information matches the first device identifier corresponding to the first node device and the space information matches the first space identifier corresponding to the first node device;

[0121] The response condition of the second node device includes that the device information in the instruction information matches the second device identifier of the second node device and the space information matches the second space identifier of the second node device.

[0122] Optionally, the target control operation is determined based on the control information.

[0123] The present invention also provides an electronic device, see Figure 4 , including: a processor 601, a memory 602, and a computer program 6021 stored in the memory and executable on the processor, wherein the processor implements the device control method of the aforementioned embodiment when executing the program.

[0124] The present invention also provides a readable storage medium, when the instructions in the storage medium are executed by the processor of the electronic device, the electronic device can execute the device control method of the aforementioned embodiment.

[0125] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0126] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific languages ​​is for disclosing the best mode of the present invention.

[0127] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0128] Similarly, it should be understood that in order to streamline the present invention and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the following intention: that the claimed invention requires more features than the features explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0129] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0130] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the sorting device according to the present invention. The present invention may also be implemented as a device or apparatus program for executing part or all of the methods described herein. Such a program for implementing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0131] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

[0132] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0133] It should be noted that all actions of acquiring signals, information or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.

[0134] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0135] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A device control method, characterized in that: The method comprises: When the first node device in the device cluster receives the target voice instruction, the target voice instruction is parsed to obtain instruction information indicated by the target voice instruction; If the instruction information does not meet the response condition of the first node device, the first node device forwards the target voice instruction to other node devices in the device cluster based on the MESH network; When any of the second node devices among the other node devices receives the target voice instruction and detects that the instruction information of the target voice instruction meets the response condition of the second node device, the second node device responds to the target voice instruction and performs the target control operation indicated by the target voice instruction.

2. The method according to claim 1, characterized in that The method further comprises: In a case where the instruction information satisfies a response condition of the first node device, the first node device responds to the target voice instruction and performs a target control operation indicated by the target voice instruction.

3. The method according to claim 1, characterized in that The method further comprises: When the first node device detects a target trigger factor, acquiring trigger information corresponding to the target trigger factor; When the trigger information meets a preset trigger condition, the first node device is started.

4. The method according to claim 1, characterized in that The step of parsing the target voice command to obtain the command information indicated by the target voice command includes: Performing voice recognition on the target voice command to obtain text information corresponding to the target voice command; Based on the text information, the instruction information is determined; the instruction information includes control information, device information and space information.

5. The method according to claim 4, characterized in that The determining the instruction information based on the text information includes: Extracting keywords from the text information to obtain target keywords; the target keywords at least include control keywords; determining the control information based on the control keyword; In a case where the target keyword includes a device keyword and a space keyword, determining the device information and the space information based on the device keyword and the space keyword; In a case where the target keyword does not include a device keyword, determining the device information based on a first device identifier corresponding to the first node device; In a case where the target keyword does not include a spatial keyword, the spatial information is determined based on a first spatial identifier corresponding to the first node device.

6. The method according to claim 1, characterized in that The response condition of the first node device includes that the device information in the instruction information matches the first device identifier corresponding to the first node device and the space information matches the first space identifier corresponding to the first node device; The response condition of the second node device includes that the device information in the instruction information matches the second device identifier of the second node device and the space information matches the second space identifier of the second node device.

7. The method according to claim 4, characterized in that The target control operation is determined based on the control information.

8. A device control device, characterized in that: The device comprises: A first parsing module, configured to parse the target voice instruction when the first node device in the device cluster receives the target voice instruction, and obtain instruction information indicated by the target voice instruction; A first forwarding module, configured to forward the target voice command to other node devices in the device cluster based on the MESH network by the first node device if the command information does not meet the response condition of the first node device; The first execution module is used for the second node device to respond to the target voice instruction and execute the target control operation indicated by the target voice instruction when any of the second node devices among the other node devices receives the target voice instruction and detects that the instruction information of the target voice instruction meets the response condition of the second node device.

9. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the device control method according to any one of claims 1 to 7 is implemented.

10. A readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the device control method described in any one of claims 1 to 7.

Images