Household appliance control method and device, computer equipment and storage medium

Abstract

The embodiment of the invention discloses a household appliance control method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring household appliance control voice input by a user; extracting at least one target intention keyword corresponding to the household appliance control voice through a preset intention classification model; determining a first target node corresponding to each target intention keyword in a preset knowledge graph; generating a target household appliance control instruction corresponding to each target intention keyword according to a mapping relation of each first target node in the knowledge graph, wherein the target household appliance control instruction carries a target household appliance identifier; and issuing the target household appliance control instruction to the corresponding target household appliance equipment according to each target household appliance identifier. By implementing the method provided by the embodiment of the invention, the intention of the user can be accurately identified and realized.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a control method, device, computer equipment, and storage medium for household appliances. Background Art

[0002] With the popularity of smart home devices and the development of the Internet of Things, various smart home appliances (such as air conditioners, lighting, audio, and smart curtains) have become part of people's daily lives. These home appliances are equipped with networking and automated control capabilities, which can improve the convenience and comfort of life.

[0003] However, when controlling home appliances through voice, traditional control systems can only recognize specified voice commands (for example, "turn down the air conditioner by two degrees"), but cannot accurately recognize the user's intentions for more complex commands (for example, "I'm so hot"). Summary of the Invention

[0004] The embodiments of the present invention provide a control method, device, computer device, and storage medium for household appliances, which can accurately identify and implement the user's intention when performing voice control on household appliances.

[0005] In a first aspect, an embodiment of the present invention provides a method for controlling a household appliance, comprising:

[0006] Get the home appliance control voice input by the user;

[0007] Extracting at least one target intent keyword corresponding to the home appliance control voice through a preset intent classification model;

[0008] Determine the first target node corresponding to each of the target intent keywords in a preset knowledge graph;

[0009] Generate target home appliance control instructions corresponding to each target intent keyword according to the mapping relationship of each first target node in the knowledge graph, wherein the target home appliance control instructions carry a target home appliance identifier;

[0010] The target home appliance control instructions are respectively issued to the corresponding target home appliance devices according to each target home appliance identifier.

[0011] In a second aspect, an embodiment of the present invention further provides a control device for a household appliance, comprising:

[0012] a first acquiring unit, configured to acquire a home appliance control voice input by a user;

[0013] an extraction unit, configured to extract at least one target intent keyword corresponding to the home appliance control voice using a preset intent classification model;

[0014] A first determining unit is used to determine the first target node corresponding to each of the target intent keywords in a preset knowledge graph;

[0015] A first generating unit is configured to generate a target home appliance control instruction corresponding to each of the target intent keywords according to a mapping relationship between each of the first target nodes in the knowledge graph, wherein the target home appliance control instruction carries a target home appliance identifier;

[0016] The sending unit is used to send the target home appliance control instructions to the corresponding target home appliance devices according to each target home appliance identifier.

[0017] In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above method when executing the computer program.

[0018] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the above method can be implemented.

[0019] The embodiments of the present invention provide a method, device, computer device and storage medium for controlling home appliances. The method includes: obtaining home appliance control voice input by a user; extracting at least one target intent keyword corresponding to the home appliance control voice through a preset intent classification model; determining the first target node corresponding to each target intent keyword in a preset knowledge graph; generating target home appliance control instructions corresponding to each target intent keyword according to the mapping relationship of each first target node in the knowledge graph, the target home appliance control instructions carrying a target home appliance identifier; and issuing the target home appliance control instructions to the corresponding target home appliance device according to each target home appliance identifier. The embodiment of the present invention combines the intent classification model with the knowledge graph to perform intent recognition on the home appliance control voice input by the user, generate corresponding home appliance control instructions, and accurately identify and realize the user's intention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 any creative work.

[0021] Figure 1 A schematic flow chart of a method for controlling a household appliance provided by an embodiment of the present invention;

[0022] Figure 2 A schematic diagram of a sub-flow chart of a method for controlling a household appliance provided by an embodiment of the present invention;

[0023] Figure 3 A schematic diagram of a sub-flow chart of a method for controlling a household appliance provided by an embodiment of the present invention;

[0024] Figure 4 A schematic diagram of a sub-flow chart of a method for controlling a household appliance provided by an embodiment of the present invention;

[0025] Figure 5 A schematic block diagram of a control device for a household appliance provided by an embodiment of the present invention;

[0026] Figure 6 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0028] It will be understood that when used in this specification and the appended claims, the terms “comprises” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0029] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the present invention. As used in the specification and appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0030] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0031] Embodiments of the present invention provide a control method and device for household appliances, a computer device, and a storage medium.

[0032] The executor of the control method of the household appliance may be the control device of the household appliance provided in an embodiment of the present invention, or a computer device integrating the control device of the household appliance, wherein the control device of the household appliance may be implemented in hardware or software, and the computer device may be a control device in the household appliance or an independent control device.

[0033] The control method of the home appliance device is applied to a computer device, which obtains a home appliance control voice input by a user; extracts at least one target intent keyword corresponding to the home appliance control voice through a preset intention classification model; determines the first target node corresponding to each of the target intent keywords in a preset knowledge graph; generates target home appliance control instructions corresponding to each of the target intent keywords according to the mapping relationship of each of the first target nodes in the knowledge graph, the target home appliance control instructions carrying a target home appliance identifier; and issues the target home appliance control instructions to the corresponding target home appliance device according to each of the target home appliance identifiers.

[0034] Among them, the knowledge graph provided by the embodiment of the present invention is constructed using the Resource Description Framework (RDF) and / or the Ontology Wed Language (OWL). The knowledge graph is constructed based on the family as a unit. Through the knowledge graph, the relationship between devices can be semantically associated and decoupled at the same time, and no longer relies on logical control for binding execution.

[0035] Specifically, the knowledge graph provided in this embodiment constructs semantic associations between user intentions and device functions through the relationship between nodes and edges, and provides a flexible semantic control mechanism; wherein, the nodes in the knowledge graph represent entities (such as devices, intentions, users, and rooms, etc.), and the edges represent relationships (such as control, location, and inclusion, etc.).

[0036] Specifically, different device nodes (e.g., air conditioner, lighting, dehumidifier) ​​contain attributes such as: name, model, function, status, location, etc.

[0037] User nodes (can be multi-roles, such as administrators and ordinary users), including attributes such as ID, name, preferences, habits, etc.

[0038] Intent nodes (such as cooling, dehumidification, and brightening lights) contain attributes such as intent name and parameters (such as temperature value).

[0039] Room nodes (such as living room, bedroom, kitchen), including attributes such as name, area, location, etc.

[0040] Among them, the relationship description words of each edge in the knowledge graph include control, location, function, user preference, etc., which are used for intent classification and description.

[0041] When constructing a knowledge graph, after determining the information of each node and each edge pair in the knowledge graph, you can use RDF for standardized entry and use (subject, predicate, object) to describe, such as (user 1, control, air conditioner) (air conditioner 3, located in, living room) (dehumidifier, increase, two gears). If some complex relationships are involved, OWL can be used to supplement the description, that is, by defining subclasses, attributes, and restrictions to describe them. For example, the intention of cooling and dehumidifying can be associated with air conditioners, dehumidifiers, etc.

[0042] Figure 1 FIG. 1 is a flow chart of a method for controlling household appliances provided by an embodiment of the present invention. Figure 1 As shown, the method includes the following steps S110-S150.

[0043] S110: Acquire home appliance control voice input by the user.

[0044] In this embodiment, when the user needs to control a home appliance, he or she can wake up (by voice or manual wake-up) the control device that receives the voice, and then input the home appliance control voice into the control device, for example, saying: "I'm so hot" or "It's so hot, the air is too humid". At this time, the control device receives the user's voice through the microphone: "I'm so hot" or "It's so hot, the air is too humid".

[0045] In some embodiments, the control permission of the control device is set by setting a tone whitelist. In this case, after step S110 and before step S120, the following steps are further performed:

[0046] Performing timbre recognition processing on the home appliance control voice to obtain a target timbre; determining whether the target timbre exists in a preset timbre whitelist; and generating a control rejection warning if the target timbre does not exist;

[0047] At this time, if the target timbre exists in the white list, step S120 is executed; otherwise, step S120 is not entered.

[0048] In other embodiments, control permissions can also be set for the control device by setting a tone blacklist. At this time, the home appliance control voice is subjected to tone recognition processing to obtain the target tone; it is determined whether the target tone exists in the preset tone blacklist; if the target tone exists, a control rejection warning is generated.

[0049] At this time, if the target timbre does not exist in the blacklist, step S120 is executed; otherwise, step S120 is not entered.

[0050] S120. Extract at least one target intent keyword corresponding to the home appliance control voice through a preset intent classification model.

[0051] In some embodiments, see Figure 2 , step S120 includes:

[0052] S1201: Perform text conversion on the home appliance control voice to obtain a home appliance control text.

[0053] Specifically, ASR technology is used to convert the home appliance control voice into text.

[0054] S1202: Extract at least one initial intent keyword from the home appliance control text according to a preset slot extraction technology.

[0055] Specifically, slot extraction technology is used to find the key parameters of each intent.

[0056] S1203: Perform vectorization processing on each of the initial intent keywords to obtain an initial intent vector corresponding to each of the initial intents.

[0057] Specifically, models such as Bidirectional Encoder Representation from Transformer (BERT) and Natural Language Processing Model (Generative Pre-trained Transformer, GPT) can be used to vectorize text.

[0058] S1204: Determine target intent vectors corresponding to the respective initial intent vectors from a plurality of preset standard intent vectors, and determine the intent keyword corresponding to the target intent vector as the target intent keyword.

[0059] Specifically, in this embodiment, standard intention vectors of multiple standard intentions are preset. For each initial intention vector, the similarity between the initial intention vector and each standard intention vector is calculated, and then the standard intention vector with the highest similarity is determined as the target intention vector corresponding to the initial intention vector.

[0060] For example, the target intent keyword corresponding to the initial intent keyword "heat" is "cool down".

[0061] S130. Determine the first target node corresponding to each of the target intent keywords in the preset knowledge graph.

[0062] For example, the identified target keyword is "cooling down". At this time, the intention node corresponding to "cooling down" in the knowledge graph is determined as the first node.

[0063] In addition, if there are multiple target intent keywords identified, such as "cooling" and "dehumidification", the first node obtained at this time includes the intent node corresponding to "cooling" in the knowledge graph, and the intent node corresponding to "dehumidification".

[0064] S140. Generate target home appliance control instructions corresponding to each target intent keyword according to the mapping relationship of each first target node in the knowledge graph, and the target home appliance control instructions carry a target home appliance identifier.

[0065] For example, devices and control instructions with "cooling" and "dehumidification" functions are found in the knowledge graph.

[0066] Furthermore, since different users have different preferences for temperature, etc., this embodiment also provides different control strategies (control instructions) for different users. For example, when associating the keyword "cooling down", user A needs to lower the temperature by 2 degrees, and user B needs to lower the temperature by 3 degrees.

[0067] At this time, if Figure 3 As shown, step S140 includes:

[0068] S1401. Perform timbre recognition processing on the home appliance control voice to obtain a target timbre, and determine a target user corresponding to the target timbre.

[0069] S1402. Determine the second target node of the target user in the knowledge graph.

[0070] S1403. Generate the target home appliance control instruction according to the mapping relationship between each of the first target nodes and the second target nodes in the knowledge graph.

[0071] Furthermore, since there are multiple rooms in a home, it is necessary to find the corresponding room and then control the home appliances in the corresponding room. At this time, before generating the target home appliance control instruction according to the mapping relationship between each first target node and the second target node in the knowledge graph, the method further includes:

[0072] Obtaining a target room corresponding to the home appliance control voice; determining a third target node of the target room in the knowledge graph;

[0073] The generating of the plurality of target home appliance control instructions according to the mapping relationship between each of the first target node and the second target node in the knowledge graph includes:

[0074] The target home appliance control instruction is generated according to the mapping relationship between the first target node, the second target node and the third target node in the knowledge graph.

[0075] In some embodiments, when there are multiple target home appliance control instructions, before issuing the target home appliance control instructions to the corresponding target home appliance devices according to each target home appliance identifier, the method further includes:

[0076] Conflict detection is performed on the multiple target home appliance control instructions; if there is a command conflict among the multiple target home appliance control instructions, the command priority corresponding to each target home appliance control instruction is obtained; and the multiple target home appliance control instructions are filtered according to each command priority.

[0077] The instruction priority includes device importance priority, device status priority, and system context multi-round conversation priority.

[0078] Among them, for the device importance priority, if there are two or more devices that meet the conditions for a certain target intent keyword, there will be a command conflict in the target home appliance control instructions generated at this time. It is necessary to retain the target home appliance control instructions corresponding to the device with the highest priority according to the device importance priority, and filter out other conflicting instructions; for the device status priority, for example, for the same device, "open instruction" and "close instruction" are generated at the same time, and there is a conflict between these two instructions. At this time, if the current device status is "closed", the "open instruction" will be used as the final instruction, and the "close instruction" will be filtered out. Similarly, if the current device status is "open", the "close instruction" will be used as the final instruction, and the "open instruction" will be filtered out; if there is still a conflict after judging the device importance priority and the device status priority, it will be judged by the system context multi-round conversation priority. For example, which device was mentioned last time, then continue to execute instructions on that device.

[0079] S150: issuing the target home appliance control instructions to the corresponding target home appliance devices according to the target home appliance identifiers.

[0080] In this embodiment, in order to avoid blocking the control of other devices due to waiting for a single device to respond, when multiple target home appliance control instructions need to be issued, this embodiment executes each target home appliance control instruction in parallel.

[0081] Specifically, each device starts an independent thread to asynchronously send target home appliance control instructions. "goroutines" in Go can be used to ensure that control commands are executed in parallel.

[0082] See also Figure 4 In some embodiments, step S150 includes:

[0083] S1501. Obtain a target device list, wherein the target device list maintains a correspondence between multiple home appliance identifiers and physical addresses.

[0084] S1502: Determine the target physical address corresponding to each target home appliance identifier from the target device list.

[0085] S1503: Send the target home appliance control instruction to the corresponding target home appliance according to each target physical address.

[0086] Specifically, after generating the target home appliance control instruction, it is also necessary to obtain the sending address (physical address) according to the target device list; and then send the control instruction according to the corresponding sending address.

[0087] Furthermore, in some embodiments, a user feedback mechanism is provided to confirm the execution results and user satisfaction through the synchronization of the user feedback mechanism, and to continuously optimize the knowledge graph and control strategy based on this result.

[0088] In summary, this embodiment obtains the home appliance control voice input by the user; extracts at least one target intent keyword corresponding to the home appliance control voice through a preset intent classification model; determines the first target node corresponding to each of the target intent keywords in a preset knowledge graph; generates target home appliance control instructions corresponding to each of the target intent keywords according to the mapping relationship of each of the first target nodes in the knowledge graph, and the target home appliance control instructions carry a target home appliance identifier; and sends the target home appliance control instructions to the corresponding target home appliance devices according to each of the target home appliance identifiers. The embodiment of the present invention combines the intent classification model with the knowledge graph to perform intent recognition on the home appliance control voice input by the user, and generates corresponding home appliance control instructions, accurately identifying and realizing the user's intent.

[0089] Figure 5 FIG is a schematic block diagram of a control device 500 for a household appliance provided by an embodiment of the present invention. Figure 5 As shown, corresponding to the above-mentioned control method for household appliances, the present invention further provides a control device 500 for household appliances. The control device 500 for household appliances includes a unit for executing the above-mentioned control method for household appliances. The control device 500 for household appliances can be configured in a control device in a household appliance or in an independent control device. The control device 500 for household appliances includes a first acquisition unit 501, an extraction unit 502, a first determination unit 503, a first generation unit 504, and a sending unit 505:

[0090] The first acquiring unit 501 is configured to acquire the home appliance control voice input by the user;

[0091] In this embodiment, when the user needs to control a home appliance, he or she can wake up (by voice or manual wake-up) the control device that receives the voice, and then input the home appliance control voice into the control device, for example, saying: "I'm so hot" or "It's so hot, the air is too humid". At this time, the control device receives the user's voice through the microphone: "I'm so hot" or "It's so hot, the air is too humid".

[0092] An extraction unit 502 is configured to extract at least one target intent keyword corresponding to the home appliance control voice using a preset intent classification model;

[0093] For example, the target intent keyword corresponding to the initial intent keyword "heat" is "cool down".

[0094] A first determining unit 503 is configured to determine a first target node corresponding to each target intent keyword in a preset knowledge graph;

[0095] For example, the identified target keyword is "cooling down". At this time, the intention node corresponding to "cooling down" in the knowledge graph is determined as the first node.

[0096] In addition, if there are multiple target intent keywords identified, such as "cooling" and "dehumidification", the first node obtained at this time includes the intent node corresponding to "cooling" in the knowledge graph, and the intent node corresponding to "dehumidification".

[0097] A first generating unit 504 is configured to generate target home appliance control instructions corresponding to each target intent keyword according to a mapping relationship between each first target node in the knowledge graph, wherein the target home appliance control instructions carry a target home appliance identifier;

[0098] For example, devices and control instructions with "cooling" and "dehumidification" functions are found in the knowledge graph.

[0099] The issuing unit 505 is configured to issue the target home appliance control instruction to the corresponding target home appliance device according to each target home appliance identifier.

[0100] In some embodiments, the extraction unit 502 is specifically configured to:

[0101] Performing text conversion on the home appliance control voice to obtain a home appliance control text;

[0102] extracting at least one initial intent keyword from the home appliance control text according to a preset slot extraction technology;

[0103] Performing vectorization processing on each of the initial intent keywords to obtain an initial intent vector corresponding to each of the initial intents;

[0104] The target intention vectors corresponding to the respective initial intention vectors are determined from a plurality of preset standard intention vectors, and the intention keywords corresponding to the target intention vectors are determined as the target intention keywords.

[0105] Specifically, in this embodiment, standard intention vectors of multiple standard intentions are preset. For each initial intention vector, the similarity between the initial intention vector and each standard intention vector is calculated, and then the standard intention vector with the highest similarity is determined as the target intention vector corresponding to the initial intention vector.

[0106] In some embodiments, the control device 500 of the household appliance further includes:

[0107] A recognition unit, configured to perform timbre recognition processing on the home appliance control voice to obtain a target timbre;

[0108] A second determining unit, configured to determine whether the target timbre exists in a preset timbre whitelist;

[0109] a second generating unit, configured to generate a rejection control warning if the target timbre does not exist;

[0110] At this time, the extraction unit 502 is specifically used to:

[0111] If the target timbre exists, at least one target intent keyword corresponding to the home appliance control voice is extracted through the intent classification model.

[0112] In some embodiments, the first generating unit 504 is specifically configured to:

[0113] Performing timbre recognition processing on the home appliance control voice to obtain a target timbre, and determining a target user corresponding to the target timbre;

[0114] Determine a second target node of the target user in the knowledge graph;

[0115] The target home appliance control instruction is generated according to the mapping relationship between each of the first target nodes and the second target nodes in the knowledge graph.

[0116] In some embodiments, the control device 500 of the household appliance further includes:

[0117] A second acquiring unit is configured to acquire a target room corresponding to the home appliance control voice;

[0118] A third determining unit, configured to determine a third target node of the target room in the knowledge graph;

[0119] At this time, the first generating unit 504 is specifically configured to:

[0120] The target home appliance control instruction is generated according to the mapping relationship between the first target node, the second target node and the third target node in the knowledge graph.

[0121] In some embodiments, when there are multiple target home appliance control instructions, the control device 500 of the home appliance further includes:

[0122] a detection unit, configured to perform conflict detection on a plurality of target home appliance control instructions;

[0123] a third acquiring unit, configured to acquire the instruction priority corresponding to each of the target home appliance control instructions when there is an instruction conflict between the plurality of target home appliance control instructions;

[0124] The filtering unit is used to filter the plurality of target home appliance control instructions according to the priority of each instruction.

[0125] The instruction priority includes device importance priority, device status priority, and system context multi-round conversation priority.

[0126] Among them, for the device importance priority, if there are two or more devices that meet the conditions for a certain target intent keyword, there will be a command conflict in the target home appliance control instructions generated at this time. It is necessary to retain the target home appliance control instructions corresponding to the device with the highest priority according to the device importance priority, and filter out other conflicting instructions; for the device status priority, for example, for the same device, "open instruction" and "close instruction" are generated at the same time, and there is a conflict between these two instructions. At this time, if the current device status is "closed", the "open instruction" will be used as the final instruction, and the "close instruction" will be filtered out. Similarly, if the current device status is "open", the "close instruction" will be used as the final instruction, and the "open instruction" will be filtered out; if there is still a conflict after judging the device importance priority and the device status priority, it will be judged by the system context multi-round conversation priority. For example, which device was mentioned last time, then continue to execute instructions on that device.

[0127] In some embodiments, the sending unit 505 is specifically configured to:

[0128] Obtain a target device list, wherein the target device list maintains a correspondence between multiple home appliance identifiers and physical addresses; determine the target physical address corresponding to each target home appliance identifier from the target device list; and issue the target home appliance control instruction to the corresponding target home appliance device according to each target physical address.

[0129] To sum up, the control device 500 for the home appliance in the embodiment of the present invention can recognize the intent of the home appliance control voice input by the user by combining the intention classification model with the knowledge graph, and generate corresponding home appliance control instructions to accurately identify and realize the user's intention.

[0130] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the control device and each unit of the above-mentioned household appliance can refer to the corresponding description in the aforementioned method embodiment. For the convenience and brevity of description, it will not be repeated here.

[0131] The control device of the household appliance can be implemented in the form of a computer program. The computer program can be used in Figure 6 Runs on the computer device shown.

[0132] See also Figure 6 , Figure 6 6 is a schematic block diagram of a computer device provided by an embodiment of the present invention. The computer device 600 is a control device in a home appliance, or can be an independent control device, which can be a terminal or a server.

[0133] See Figure 6 The computer device 600 includes a processor 602 , a memory, and a network interface 605 connected via a system bus 601 , wherein the memory may include a non-volatile storage medium 603 and an internal memory 604 .

[0134] The non-volatile storage medium 603 can store an operating system 6031 and a computer program 6032. The computer program 6032 includes program instructions, which, when executed, can enable the processor 602 to execute a method for controlling a household appliance.

[0135] The processor 602 is used to provide computing and control capabilities to support the operation of the entire computer device 600.

[0136] The internal memory 604 provides an environment for the operation of the computer program 6032 in the non-volatile storage medium 603. When the computer program 6032 is executed by the processor 602, the processor 602 can execute a method for controlling a household appliance.

[0137] The network interface 605 is used to communicate with other devices over the network. Figure 6 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device 600 to which the solution of the present invention is applied. The specific computer device 600 may include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0138] The processor 602 is configured to execute a computer program 6032 stored in the memory to implement the following steps:

[0139] Get the home appliance control voice input by the user;

[0140] Extracting at least one target intent keyword corresponding to the home appliance control voice through a preset intent classification model;

[0141] Determine the first target node corresponding to each of the target intent keywords in a preset knowledge graph;

[0142] Generate target home appliance control instructions corresponding to each target intent keyword according to the mapping relationship of each first target node in the knowledge graph, wherein the target home appliance control instructions carry a target home appliance identifier;

[0143] The target home appliance control instructions are respectively issued to the corresponding target home appliance devices according to each target home appliance identifier.

[0144] It should be understood that in the embodiment of the present invention, the processor 602 may be a central processing unit (CPU), and the processor 602 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0145] Those skilled in the art will appreciate that all or part of the steps in the method of the above-described embodiment can be implemented by instructing the relevant hardware through a computer program. The computer program includes program instructions, which can be stored in a storage medium that is computer-readable. The program instructions are executed by at least one processor in the computer system to implement the steps in the method of the above-described embodiment.

[0146] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor, the processor performs the following steps:

[0147] Get the home appliance control voice input by the user;

[0148] Extracting at least one target intent keyword corresponding to the home appliance control voice through a preset intent classification model;

[0149] Determine the first target node corresponding to each of the target intent keywords in a preset knowledge graph;

[0150] Generate target home appliance control instructions corresponding to each target intent keyword according to the mapping relationship of each first target node in the knowledge graph, wherein the target home appliance control instructions carry a target home appliance identifier;

[0151] The target home appliance control instructions are respectively issued to the corresponding target home appliance devices according to each target home appliance identifier.

[0152] The storage medium may be any computer-readable storage medium that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk.

[0153] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0154] In the several embodiments provided herein, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the various units is merely a logical functional division, and actual implementation may employ other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be omitted or not implemented.

[0155] The steps in the methods of the embodiments of the present invention may be adjusted in order, combined, or deleted as needed. The units in the devices of the embodiments of the present invention may be combined, divided, or deleted as needed. Furthermore, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit.

[0156] If this integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the existing technology, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, terminal, or network device, etc.) to execute all or part of the steps of the method described in various embodiments of the present invention.

[0157] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A method for controlling a household appliance, characterized in that: include: Get the home appliance control voice input by the user; Extracting at least one target intent keyword corresponding to the home appliance control voice through a preset intent classification model; Determine the first target node corresponding to each of the target intent keywords in the preset knowledge graph; Generate target home appliance control instructions corresponding to each of the target intent keywords according to the mapping relationship of each of the first target nodes in the knowledge graph, wherein the target home appliance control instructions carry a target home appliance identifier; The target home appliance control instructions are respectively issued to the corresponding target home appliance devices according to each of the target home appliance identifiers.

2. The method according to claim 1, characterized in that The extracting at least one target intent keyword corresponding to the home appliance control voice by using a preset intent classification model includes: Performing text conversion processing on the home appliance control voice to obtain a home appliance control text; extracting at least one initial intent keyword from the home appliance control text according to a preset slot extraction technology; Performing vectorization processing on each of the initial intent keywords to obtain initial intent vectors corresponding to each of the initial intents; The target intention vectors corresponding to the initial intention vectors are determined from a plurality of preset standard intention vectors, and the intention keywords corresponding to the target intention vectors are determined as the target intention keywords.

3. The method according to claim 1, characterized in that: Before extracting at least one target intent keyword corresponding to the home appliance control voice through a preset intent classification model, the method further includes: Performing timbre recognition processing on the home appliance control voice to obtain a target timbre; Determine whether the target timbre exists in a preset timbre whitelist; If the target timbre does not exist, a rejection control warning is generated; The extracting at least one target intent keyword corresponding to the home appliance control voice by using a preset intent classification model includes: If the target timbre exists, at least one target intent keyword corresponding to the home appliance control voice is extracted through the intent classification model.

4. The method according to claim 1, characterized in that: The generating target home appliance control instructions corresponding to each of the target intent keywords respectively according to the mapping relationship of each of the first target nodes in the knowledge graph includes: Performing timbre recognition processing on the home appliance control voice to obtain a target timbre, and determining a target user corresponding to the target timbre; Determine a second target node of the target user in the knowledge graph; The target home appliance control instruction is generated according to the mapping relationship between the first target nodes and the second target nodes in the knowledge graph.

5. The method according to claim 4, characterized in that Before generating the target home appliance control instruction according to the mapping relationship between each of the first target node and the second target node in the knowledge graph, the method further includes: Obtain the target room corresponding to the home appliance control voice; Determine a third target node of the target room in the knowledge graph; The generating a plurality of target home appliance control instructions according to the mapping relationship between each of the first target node and the second target node in the knowledge graph includes: The target home appliance control instruction is generated according to the mapping relationship between the first target node, the second target node and the third target node in the knowledge graph.

6. The method according to claim 1, characterized in that When there are multiple target home appliance control instructions, before issuing the target home appliance control instructions to the corresponding target home appliance devices according to the target home appliance identifiers, the method further includes: Performing conflict detection on a plurality of target home appliance control instructions; If there is a command conflict among the plurality of target home appliance control commands, obtaining the command priority corresponding to each of the target home appliance control commands; The plurality of target home appliance control instructions are filtered according to the instruction priorities.

7. The method according to any one of claims 1 to 6, characterized in that The step of sending the target home appliance control instruction to the corresponding target home appliance device according to each target home appliance identifier includes: Obtain a target device list, wherein the target device list maintains a correspondence between multiple home appliance identifiers and physical addresses; Determine the target physical addresses corresponding to the target home appliance identifiers from the target device list; The target home appliance control instruction is sent to the corresponding target home appliance device according to each target physical address.

8. A control device for household electrical appliances, characterized in that: include: A first acquisition unit, used to acquire the home appliance control voice input by the user; An extraction unit, configured to extract at least one target intent keyword corresponding to the home appliance control voice through a preset intent classification model; A first determination unit, used to determine the first target nodes corresponding to each of the target intent keywords in a preset knowledge graph; A first generating unit, configured to generate a target home appliance control instruction corresponding to each of the target intent keywords according to a mapping relationship between each of the first target nodes in the knowledge graph, wherein the target home appliance control instruction carries a target home appliance identifier; The sending unit is used to send the target home appliance control instructions to the corresponding target home appliance devices according to each target home appliance identifier.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for controlling the household appliance according to any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the control method for a household appliance according to any one of claims 1 to 7.

Images