WO2019141028A1

WO2019141028A1 - Control method, device and system for electrical device

Info

Publication number: WO2019141028A1
Application number: PCT/CN2018/120927
Authority: WO
Inventors: 徐夏伶; 卢俊杰; 宋德超
Original assignee: 珠海格力电器股份有限公司
Priority date: 2018-01-22
Filing date: 2018-12-13
Publication date: 2019-07-25
Also published as: CN108320753A

Abstract

Provided are a control method, device and system for an electrical device. The method comprises: acquiring first voice information sent by a target object (S102); using a voiceprint identification model to identify the first voice information, and determining voiceprint information corresponding to the target object, wherein the voiceprint identification model is trained through machine learning by using multiple sets of sample data, and the multiple sets of sample data comprise the voice information of the target object and the matched voiceprint information (S104); acquiring a control mode corresponding to the voiceprint information (S106); and controlling an electrical device according to the control mode (S108). By means of the method, the technical problem of the low degree of personalization caused by the fact that the existing electrical device cannot operate according to the control habits of different users is solved.

Description

Control method, device and system for electrical equipment

Technical field

The present application relates to the field of intelligent control of electrical equipment, and in particular to a method, device and system for controlling electrical equipment.

Background technique

The existing electrical equipment has added a voice control function, and the user can directly control the electrical equipment through voice, and needs to be manually operated, which is convenient for the user to use, and improves the intelligence of the electrical equipment. For example, air conditioners, users can control the air conditioner to turn on, off, lower the temperature, increase the wind speed, etc. by voice.

However, the existing electrical equipment does not fully utilize the advantages of voice. All users control the electrical equipment in the same way, and cannot distinguish the operating behaviors and control habits of different users, and cannot provide personalized intelligent services to the users. The device is less personalized.

In view of the fact that existing electrical equipment cannot work according to the control habits of different users, and the degree of personalization is low, an effective solution has not yet been proposed.

Summary of the invention

The embodiment of the present application provides a control method, device, and system for an electrical device, so as to at least solve the technical problem that the existing electrical device cannot work according to different user control habits, and the degree of personalization is low.

In an embodiment of the present application, a method for controlling an electrical device includes: acquiring first voice information sent by a target object; identifying the first voice information by using a voiceprint recognition model, and determining, corresponding to the target object, Voiceprint information, wherein the voiceprint recognition model is trained by machine learning using a plurality of sets of sample data, the plurality of sets of sample data includes: voice information of the target object and matching voiceprint information; and obtaining control corresponding to the voiceprint information Mode; according to the control method, the electrical equipment is controlled.

In an embodiment of the present application, a method for controlling an electrical device is provided, including: acquiring first voice information sent by a target object; identifying the first voice information, and determining voiceprint information corresponding to the target object; Obtain a control mode corresponding to the voiceprint information; control the electrical device according to the control mode.

In an embodiment of the present application, a control device for an electrical device is further provided, comprising: a first acquiring module, configured to acquire first voice information sent by a target object; and an identification module configured to use a voiceprint recognition model pair The first voice information is identified, and the voiceprint information corresponding to the target object is determined, wherein the voiceprint recognition model is trained by using machine learning using a plurality of sets of sample data, and the plurality of sets of sample data includes: voice information of the target object and matching The voiceprint information; the second acquisition module is configured to obtain a control mode corresponding to the voiceprint information; and the control module is configured to control the electrical device according to the control mode.

In an embodiment of the present application, a control device for an electrical device is further provided, including: a first acquiring module configured to acquire first voice information sent by a target object; and an identifying module configured to perform the first voice information Identifying, determining the voiceprint information corresponding to the target object; the second acquiring module is configured to acquire a control mode corresponding to the voiceprint information; and the control module is configured to control the electrical device according to the control mode.

In an embodiment of the present application, a control system for an electrical device is further provided, comprising: a collecting device configured to collect first voice information sent by a target object; and a processor connected to the collecting device and configured to use the voiceprint The recognition model identifies the first voice information, determines the voiceprint information corresponding to the target object, and acquires a control manner corresponding to the voiceprint information, wherein the voiceprint recognition model is trained by using a plurality of sets of sample data through machine learning, The plurality of sets of sample data includes: voice information of the target object and matched voiceprint information; and the controller is connected to the processor and configured to control the electrical device according to the control mode.

In an embodiment of the present application, a storage medium is further provided, where the storage medium includes a stored program, wherein the device in which the storage medium is located controls the control method of the above-mentioned electrical device when the program is running.

In an embodiment of the present application, there is further provided a processor, the processor being configured to execute a program, wherein the method for controlling the electrical device is executed when the program is running.

In the embodiment of the present application, the first voice information sent by the target object is acquired, the first voice information is identified by using the voiceprint recognition model, the voiceprint information corresponding to the target object is determined, and the control manner corresponding to the voiceprint information is obtained. According to the control method, the electrical equipment is controlled. It is easy to notice that the voiceprint information is used to distinguish the voiceprint information of different users, and the voiceprint information of different users is bound to the control commands one by one, so as to distinguish different users and control according to different users. It is customary to control the electrical equipment to achieve the technical effect of improving the personalization of the electrical equipment and improving the user experience, thereby solving the problem that the existing electrical equipment cannot work according to the control habits of different users, and the degree of personalization is low.

DRAWINGS

The drawings described herein are intended to provide a further understanding of the present application, and are intended to be a part of this application. In the drawing:

1 is a flow chart of a method of controlling an electrical device according to an embodiment of the present application;

2 is a schematic diagram of an optional voiceprint recognition model according to an embodiment of the present application;

3 is a schematic diagram of an optional local storage voiceprint information and a control mode according to an embodiment of the present application;

4 is a schematic diagram of an optional server storing voiceprint information and a control manner according to an embodiment of the present application;

FIG. 5 is a schematic diagram of an optional control method for acquiring local storage according to an embodiment of the present application; FIG.

FIG. 6 is a schematic diagram of an optional control method for acquiring server storage according to an embodiment of the present application; FIG.

7 is a flow chart of another method of controlling an electrical device according to an embodiment of the present application;

FIG. 8 is a schematic diagram of a control device for an electric appliance according to an embodiment of the present application; FIG.

9 is a schematic diagram of another control device of an electric appliance according to an embodiment of the present application;

FIG. 10 is a schematic diagram of a control system of an electrical appliance in accordance with one embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present application. It is an embodiment of the present application, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope shall fall within the scope of the application.

It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or order. It is to be understood that the data so used may be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "comprises" and "comprises" and "the" and "the" are intended to cover a non-exclusive inclusion, for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to Those steps or units may include other steps or units not explicitly listed or inherent to such processes, methods, products or devices.

First, the technical terms appearing in the embodiments of the present application are explained as follows:

Voiceprint recognition: It is a kind of biometric technology, also known as speaker recognition. There are two types, namely, speaker recognition and speaker confirmation. Voiceprint recognition is the conversion of sound signals into electrical signals, which are then identified by a computer. Voiceprint recognition contains two key issues, one is feature extraction and the other is pattern matching (pattern recognition). The task of feature extraction is to extract and select acoustic or linguistic features that are highly distinguishable and highly stable to the speaker's voiceprint. Good features should be able to effectively distinguish between different speakers, but they can remain relatively stable when the same speaker's voice changes; it is not easy to be imitated by others or can better solve the problem of being imitated by others; Anti-noise performance.

User's operating habits: It means that the user analyzes and understands all the operational behavior information of a certain home appliance, and summarizes a set of personalized usage habits or usage preferences of the user for a certain home appliance. Home appliance manufacturers can provide personalized intelligent services to users in accordance with user operating habits, thereby improving the user experience.

Example 1

According to one embodiment of the present application, an embodiment of a method of controlling an electrical device is provided. It is noted that the steps illustrated in the flowchart of the accompanying drawings may be executed in a computer system such as a set of computer executable instructions. And, although the logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in a different order than the ones described herein.

FIG. 1 is a flowchart of a method for controlling an electrical device according to an embodiment of the present application. As shown in FIG. 1 , the method includes the following steps:

Step S102: Acquire first voice information sent by the target object.

Optionally, in the foregoing embodiment of the present application, the first voice information includes: a start instruction or a wake-up instruction.

Optionally, the target object may be a user currently controlling the electrical device by voice, and a voice collection device such as a microphone is installed on the electrical device, and the voice information sent by the user may be collected; when the user needs to control the electrical device through voice, the user The start command for controlling the start of the electrical device may be issued, or the wake-up command of the electrical device may be woken up, and the command issued by the user is related to the state of the electrical device. If the electrical device is in the off state, the user issues a start command; if the electrical device is in the sleep state, then The user issues a wake-up command. For example, for an air conditioner, when the air conditioner is turned off, when the user needs to use the air conditioner, a voice of “turning on the air conditioner” may be issued, and the voice includes a start command.

Step S104: Identifying the first voice information by using a voiceprint recognition model, and determining voiceprint information corresponding to the target object, wherein the voiceprint recognition model is trained by using machine learning by using a plurality of sets of sample data, and the plurality of sets of sample data includes : Voice information of the target object and matching voiceprint information.

Optionally, the voiceprint recognition model described above may be previously modeled according to voice information sent by the user, and the voiceprint recognition model can distinguish different users and obtain unique voice patterns of different users.

Step S106, obtaining a control mode corresponding to the voiceprint information.

Optionally, in the foregoing embodiment of the present application, the control manner includes: a history control instruction and/or historical state information of the electrical device.

Optionally, the foregoing control manner may be a control instruction issued by the user last time controlling the electrical device, or may be a set of custom instructions corresponding to the user, that is, performing all control commands issued by the user before controlling the electrical device. The historical control instruction set obtained by the analysis and summary may also be the historical state information of the electrical device when the user last controlled the electrical device (ie, the historical state information of the electrical device mentioned above). For example, for the air conditioner, the historical state information may be The operating mode, set temperature, set wind speed, and sweep direction of the air conditioner when the user last controlled the air conditioner.

Step S108, controlling the electrical equipment according to the control mode.

Optionally, the electrical device described above may be a home appliance having a voice control function.

In an optional solution, when the user needs to control the electrical device, the user may send a voice message including a start command or a wake-up command, and the electronic device may input the voice information after collecting the voice message sent by the user. In the pre-established voiceprint recognition model, the voiceprint corresponding to the user is obtained, and the history control instruction corresponding to the voiceprint is further queried from the storage device, that is, the last control command or the custom instruction set of the user is queried. The electrical device executes the queried historical control instruction, thereby realizing the judgment of the user through the voiceprint information, and executing the history control instruction corresponding to the user.

In another optional solution, when the user needs to control the electrical device, the user may send a voice message including a start command or a wake-up command, and the electrical device may input the voice information after collecting the voice information sent by the user. Go to the pre-established voiceprint recognition model, obtain the voiceprint corresponding to the user, and further query the historical state information corresponding to the voiceprint from the storage device, that is, query the electrical device when the user last controls the electrical device The historical state information, the electrical device performs a query set corresponding to the historical state information, or adjusts the click state information to the queried historical state information, thereby realizing the user's judgment through the voiceprint information, and executing the user corresponding Historical control instructions.

Through the foregoing embodiment of the present application, the first voice information sent by the target object is obtained, the first voice information is identified by using the voiceprint recognition model, the voiceprint information corresponding to the target object is determined, and the control manner corresponding to the voiceprint information is obtained. According to the control method, the electrical equipment is controlled. It is easy to notice that the voiceprint information is used to distinguish the voiceprint information of different users, and the voiceprint information of different users is bound to the control commands one by one, so as to distinguish different users and control according to different users. It is customary to control the electrical equipment to achieve the technical effect of improving the personalization of the electrical equipment and improving the user experience, thereby solving the problem that the existing electrical equipment cannot work according to the control habits of different users, and the degree of personalization is low.

Optionally, in the foregoing embodiment of the present application, before the first voice information is identified by using the voiceprint recognition model to determine the voiceprint information corresponding to the target object, the method further includes:

Step S110: Acquire a plurality of second voice information sent by the target object, where each second voice information includes one of: a control instruction, a wake-up instruction, and a preset instruction.

Optionally, the preset instruction may be a preset instruction for establishing a voiceprint recognition model.

Step S112, extracting a voiceprint feature in the plurality of second voice information to obtain a plurality of sets of sample data.

Step S114, establishing a preset recognition model, and training the preset recognition model by using a plurality of sets of sample data to obtain a voiceprint recognition model.

In an optional solution, in order to distinguish different users by using voiceprint information, firstly, a voiceprint recognition model needs to be established, and the user can send voice information to the electrical device multiple times, and the electrical device sends the user multiple times after receiving the user. After the voice information, the voiceprint analysis can be performed on each received voice information, and the voiceprint sign is extracted, thereby obtaining a plurality of voiceprint signs corresponding to the user, that is, obtaining multiple sets of sample data, and further utilizing multiple sets of samples. The data is trained on the established preset recognition model to obtain a voiceprint recognition model. The voiceprint recognition model may be stored in the local storage device of the electrical device, or may be sent to the server for storage by the wireless module of the electrical device.

Optionally, in the foregoing embodiment of the present application, in a case that the control mode includes: a history control instruction, in step S114, the preset recognition model is trained by using a plurality of sets of sample data to obtain a voiceprint recognition model, and the method is Also includes:

Step S116: Acquire third voice information sent by the target object, where the third voice information includes: a history control instruction.

Step S118: Identify the third voice information by using the voiceprint recognition model, and determine voiceprint information corresponding to the target object.

Step S120, obtaining a correspondence between the history control command and the voiceprint information according to the history control instruction and the voiceprint information.

In an optional solution, after the voiceprint recognition model is successfully established, the user may send voice information including a control instruction to the electrical device, and the electrical device executes the control command, and simultaneously inputs the voice information into the voiceprint recognition model to obtain The voiceprint information of the user, that is, the voiceprint pairing of the voice information sent by the user, after the pairing is successful, the correspondence between the control command and the voiceprint information can be obtained, and the correspondence between the control command and the voiceprint information is stored in the In the local storage device of the electrical device, the correspondence between the control command and the voiceprint information may also be sent to the server for storage through the wireless module.

Optionally, in the foregoing embodiment of the present application, after the correspondence between the history control command and the voiceprint information is obtained according to the historical control instruction and the voiceprint information, the method further includes:

Step S122: Acquire at least one history control instruction corresponding to the voiceprint information.

Step S124, processing at least one history control instruction to obtain a history control instruction set corresponding to the voiceprint information.

In an optional solution, the electrical equipment or the server may analyze and summarize the control instructions corresponding to one user, that is, the control commands corresponding to the same voiceprint information, periodically, irregularly, or in real time, and summarize the control habits of the user. Thereby getting a set of custom instructions from the user.

Optionally, in the foregoing embodiment of the present application, in the case that the control mode includes: historical state information of the electrical device, in step S114, the preset recognition model is trained by using the plurality of sets of sample data to obtain the voiceprint recognition model. The method further includes:

Step S126: Acquire third voice information sent by the target object, where the third voice information includes: a history control instruction.

Step S128, the third voice information is input to the voiceprint recognition model, and the voiceprint information corresponding to the target object is obtained.

Step S130, according to the historical control instruction, control the electrical device, and acquire historical state information of the electrical device.

Step S132, obtaining a correspondence between the historical state information of the electrical device and the voiceprint information according to the historical state information and the voiceprint information of the electrical device.

In an optional solution, after the voiceprint recognition model is successfully established, the user may send voice information including a control instruction to the electrical device, the electrical device executes the control command, and acquires state information of the electrical device, and simultaneously performs voice information. Inputting to the voiceprint recognition model, obtaining the voiceprint information of the user, that is, performing voiceprint matching on the voice information sent by the user, and after the pairing is successful, the correspondence between the state information of the electrical device and the voiceprint information can be obtained, and The correspondence between the state information of the electrical device and the voiceprint information is stored in the local storage device of the electrical device, and the correspondence between the state information of the electrical device and the voiceprint information may be sent to the server for storage through the wireless module.

Optionally, in the foregoing embodiment of the present application, the control mode is stored in the storage device of the electrical device and/or the server, and in step S106, the control manner corresponding to the voiceprint information includes one or more of the following:

Step S1062, obtaining a control mode from the storage device of the electric device according to the voiceprint information.

In step S1064, the voiceprint information is sent to the server, and the control mode returned by the server is received.

In an optional solution, since the control mode is stored in the local storage device of the electrical device, or in the server, after the voiceprint information of the user is acquired, the local storage device of the electrical device can be read and The control method corresponding to the voiceprint information may also send the voiceprint information to the server through the wireless module, and the server queries the control mode corresponding to the voiceprint information, and then controls the electrical device according to the control mode.

It should be noted that, in order to reduce the storage amount of the stored data of the electrical device, the correspondence between the voiceprint information of different users and the control command may be stored in the server.

Optionally, in the foregoing embodiment of the present application, after acquiring the first voice information sent by the target object in step S102, the method further includes:

Step S134, identifying the first voice information, and determining whether the first voice information includes a start command or a wake-up command.

Step S136, if it is determined that the first voice information includes a start command or a wake-up command, the first voice information is re-identified by the voiceprint recognition model, and the voiceprint information corresponding to the target object is determined.

Step S138, if it is determined that the first voice information does not include a start command or a wake-up command, the first voice information is not recognized again by using the voiceprint recognition model.

In an optional solution, in order to prevent the erroneous operation of the electrical device, after receiving the voice information sent by the user, the electrical device first performs voice recognition on the voice information, and determines whether the voice information includes a start command or a wake-up command, if Determining that the voice information includes any one of the instructions, determining that the user needs to control the electrical device, and further inputting the voice information into the voiceprint recognition model, obtaining the voiceprint information of the user, and controlling according to the voiceprint information of the user Ways to control electrical equipment.

It should be noted that, after acquiring the plurality of second voice information sent by the target object, the plurality of second voice information may be identified, and determining whether the plurality of second voice information includes a control instruction, a wake-up instruction, or a preset instruction, If it is determined that any one of the second voice information includes a control instruction, a wake-up instruction, or a preset instruction, extracting a voiceprint feature of the second voice information; if determining that any one of the second voice information does not include a control instruction, a wake-up instruction, or a preset instruction , the voiceprint feature of the second voice information is not extracted.

It should be noted that, after acquiring the third voice information sent by the target object, the third voice information may be identified, determining whether the third voice information includes a history control instruction, and if it is determined that the third voice information includes a history control instruction, Then, the third voice information is identified by using the voiceprint recognition model, and the voiceprint information corresponding to the target object is determined; if it is determined that the third voice information does not include the history control instruction, the third voice information is not executed.

2 is a schematic diagram of an optional voiceprint recognition model according to an embodiment of the present application, and FIG. 3 is a schematic diagram of an optional local storage voiceprint information and a control manner according to an embodiment of the present application. FIG. 4 is a schematic diagram of an optional server storing voiceprint information and a control manner according to an embodiment of the present application. FIG. 5 is a schematic diagram of an optional control method for acquiring local storage according to an embodiment of the present application. FIG. 6 is a schematic diagram of an optional control method for acquiring server storage according to an embodiment of the present application. A preferred embodiment of the present application is described in detail below with reference to FIG. 2 to FIG. 6 .

As shown in FIG. 2, the user can voice the voice appliance (ie, the above-mentioned electrical appliance), and the voice appliance can receive three voices sent by the user, namely, vocal A, vocal B, and vocal C, and voice module of the voice appliance. The voiceprint analysis is performed on the received sound, and the characteristics of the voiceprint are extracted to obtain three voiceprints, namely voiceprint A, voiceprint B, and voiceprint C, and a voiceprint recognition model can be further established.

As shown in FIG. 3 and FIG. 4, after the voiceprint recognition model is successfully established, the user can issue a control command to the voice home appliance, and the voice module of the voice home appliance performs voiceprint matching on the control command through the voiceprint recognition model, and after the pairing is successful, the pair will be The control command of the voiceprint should be stored locally, or the control module corresponding to the voiceprint can be sent to the server for data storage through the wireless module of the voice appliance.

As shown in FIG. 5 and FIG. 6 , when the user needs to control the voice home appliance, the user may issue a power-on command or a wake-up command to the voice home appliance, and the voice module of the voice home appliance performs voiceprint matching on the power-on command or the wake-up command through the voiceprint recognition model. The corresponding control mode is queried from the local storage through the matched voiceprint information, and the queried control mode is transmitted to the control module of the voice home appliance, and the control module executes the control mode. The matched voiceprint information may also be sent to the server through the wireless module of the voice appliance, and the server queries the corresponding control mode, and the wireless module transmits the control mode queried from the server to the control module, and the control module executes the control mode.

Through the above scheme, the voice command is used to bind the operation command to the individual of the user one by one, and the voiceprint is used to distinguish different operation requirements of different people on the home appliance, thereby improving the personalization of the user operation and improving the user experience.

Example 2

FIG. 7 is a flowchart of another method for controlling an electrical device according to an embodiment of the present application. As shown in FIG. 7, the method includes the following steps:

Step S702, acquiring first voice information sent by the target object.

Step S704, identifying the first voice information, and determining voiceprint information corresponding to the target object.

Step S706, obtaining a control manner corresponding to the voiceprint information.

Step S708, controlling the electrical device according to the control mode.

In an optional solution, when the user needs to control the electrical device, the user may send a voice message including a start command or a wake-up command, and the electrical device may sound the voice information after collecting the voice information sent by the user. Pattern recognition, obtaining the voiceprint corresponding to the user, further querying the history control instruction corresponding to the voiceprint from the storage device, that is, querying the last control command or custom instruction set of the user, and the electrical device performs the query The history control instruction, thereby realizing the judgment of the user through the voiceprint information, and executing the history control instruction corresponding to the user.

In another optional solution, when the user needs to control the electrical device, the user may send a voice message including a start command or a wake-up command, and the electronic device may perform voice information after collecting the voice message sent by the user. The voiceprint is recognized, the voiceprint corresponding to the user is obtained, and the historical state information corresponding to the voiceprint is further queried from the storage device, that is, the historical state information of the electrical device when the user last controls the electrical device is queried, and the electrical appliance The device executes the command set corresponding to the historical state information that is queried, or adjusts the squeak state information to the queried historical state information, thereby realizing the judgment of the user through the voiceprint information, and executing the history control instruction corresponding to the user.

Through the foregoing embodiment of the present application, the first voice information sent by the target object is obtained, the first voice information is identified, the voiceprint information corresponding to the target object is determined, and the control manner corresponding to the voiceprint information is obtained, according to the control manner, Electrical equipment is controlled. It is easy to notice that the voiceprint information is used to distinguish the voiceprint information of different users, and the voiceprint information of different users is bound to the control commands one by one, so as to distinguish different users and control according to different users. It is customary to control the electrical equipment to achieve the technical effect of improving the personalization of the electrical equipment and improving the user experience, thereby solving the problem that the existing electrical equipment cannot work according to the control habits of different users, and the degree of personalization is low.

Optionally, in the foregoing embodiment of the present application, in step S704, the first voice information is identified, and the voiceprint information corresponding to the target object is determined to include:

Step S7042: Identifying the first voice information by using a voiceprint recognition model, and determining voiceprint information corresponding to the target object, wherein the voiceprint recognition model is trained by using machine learning using a plurality of sets of sample data, and the plurality of sets of sample data includes : Voice information of the target object and matching voiceprint information.

In an optional solution, after collecting the voice information sent by the user, the electrical device may input the voice information into a pre-established voiceprint recognition model to obtain a voiceprint corresponding to the user.

Example 3

According to one embodiment of the present application, an embodiment of a control device for an electrical device is provided.

FIG. 8 is a schematic diagram of a control device for an electrical device according to an embodiment of the present application. As shown in FIG. 8, the device includes:

The first obtaining module 82 is configured to acquire first voice information sent by the target object.

The identification module 84 is configured to identify the first voice information by using a voiceprint recognition model, and determine voiceprint information corresponding to the target object, wherein the voiceprint recognition model is trained by using a plurality of sets of sample data through machine learning, and multiple groups The sample data includes: voice information of the target object and matching voiceprint information.

The second obtaining module 86 is configured to acquire a control manner corresponding to the voiceprint information.

The control module 88 is configured to control the electrical device according to the control mode.

Example 4

9 is a schematic diagram of another control device for an electrical device according to an embodiment of the present application. As shown in FIG. 9, the device includes:

The first obtaining module 92 is configured to acquire first voice information sent by the target object.

The identification module 94 is configured to identify the first voice information and determine voiceprint information corresponding to the target object.

The second obtaining module 96 is configured to acquire a control manner corresponding to the voiceprint information.

The control module 98 is configured to control the electrical device according to the control mode.

Example 5

According to one embodiment of the present application, an embodiment of a control system for an electrical device is provided.

FIG. 10 is a schematic diagram of a control system of an electrical appliance according to an embodiment of the present application. As shown in FIG. 10, the system includes a collection device 102, a processor 104, and a controller 106.

The collecting device 102 is configured to collect the first voice information sent by the target object, and the processor 104 is connected to the collecting device, and is configured to identify the first voice information by using the voiceprint recognition model, and determine the voiceprint information corresponding to the target object. And obtaining a control method corresponding to the voiceprint information, wherein the voiceprint recognition model is trained by using a plurality of sets of sample data through machine learning, and the plurality of sets of sample data includes: voice information of the target object and matching voiceprint information; The device 106 is coupled to the processor and is configured to control the electrical device in accordance with a control mode.

Optionally, the foregoing collecting device may be a microphone installed on the electrical device, but is not limited thereto. The processor may be a voice module of the electrical device; the controller 106 may be an electrical device. The control module of the device; the target object may be a user currently controlling the electrical device by voice, and a voice collecting device such as a microphone is installed on the electrical device, and the voice information sent by the user may be collected; the voiceprint recognition model may be pre-defined according to the user. The sent voice information is modeled, and the voiceprint recognition model can distinguish different users and obtain unique voiceprints of different users; the above electrical device can be a home appliance with voice control function.

Optionally, in the foregoing embodiment of the present application, the first voice information includes: a start command or a wake-up command, and the control manner includes: a history control command and/or historical state information of the electrical device.

Optionally, when the user needs to control the electrical device by voice, the user may issue a start command for controlling the start of the electrical device, or wake up the wake-up command of the electrical device, and the command issued by the user is related to the state of the electrical device, if the electrical device is turned off. , the user issues a start command; if the electrical device is in a sleep state, the user issues a wake-up command. For example, for an air conditioner, when the air conditioner is turned off, when the user needs to use the air conditioner, a voice of “turning on the air conditioner” may be issued, and the voice includes a start command. The above control method may be a control command issued by the user last time controlling the electrical device, or may be a set of custom instructions corresponding to the user, that is, analyzing and summarizing all control commands issued by the user before controlling the electrical device. The historical control instruction set may also be historical state information of the electrical device when the user last controlled the electrical device (ie, the historical state information of the electrical device mentioned above). For example, for the air conditioner, the historical state information may be the user's last control. Air conditioner working mode, set temperature, set wind speed, sweep direction, etc. when air conditioning.

Example 6

According to an embodiment of the present application, an embodiment of a storage medium is provided. The storage medium includes a stored program, wherein the device in which the storage medium is located is controlled to execute the electrical device in Embodiment 1 or Embodiment 2 described above when the program is running. Control Method.

Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: acquiring first voice information sent by the target object; identifying the first voice information by using a voiceprint recognition model, determining and The voiceprint information corresponding to the target object, wherein the voiceprint recognition model is trained by machine learning using multiple sets of sample data, and the plurality of sets of sample data includes: voice information of the target object and matching voiceprint information; The control method corresponding to the information; according to the control mode, the electrical equipment is controlled.

Alternatively, in the present embodiment, the storage medium may also be provided as program code for storing various preferred or optional method steps provided by the control method of the electrical device.

Example 7

According to an embodiment of the present application, there is provided an embodiment of a processor, the processor being arranged to run a program, wherein the control method of the electrical device in Embodiment 1 or Embodiment 2 is executed when the program is running.

The various functional modules provided by the embodiments of the present application may be operated in an electrical device or a similar computing device, or may be stored as part of a storage medium.

Thus, embodiments of the present application can provide an electrical device.

In the embodiment, the electrical device is configured to execute the following steps in the control method of the electrical device: acquiring the first voice information sent by the target object; using the voiceprint recognition model to identify the first voice information, determining the target object Corresponding voiceprint information, wherein the voiceprint recognition model is trained by machine learning using a plurality of sets of sample data, and the plurality of sets of sample data includes: voice information of the target object and matching voiceprint information; and obtaining corresponding to the voiceprint information Control method; control the electrical equipment according to the control method.

Optionally, the electrical device can include: one or more processors, memory, and transmission devices.

The memory can be used to store software programs and modules, such as the control method of the electrical device and the program instruction/module corresponding to the device in the embodiment of the present application, and the processor executes various software programs and modules stored in the memory. Functional application and data processing, that is, the control method of the above electrical equipment is realized. The memory may include a high speed random access memory, and may also include non-volatile memory such as one or more magnetic storage devices, flash memory, or other non-volatile solid state memory. In some examples, the memory can further include memory remotely located relative to the processor, which can be connected to the terminal over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The above transmission device is for receiving or transmitting data via a network. Specific examples of the above network may include a wired network and a wireless network. In one example, the transmission device includes a Network Interface Controller (NIC) that can be connected to other network devices and routers via a network cable to communicate with the Internet or a local area network. In one example, the transmission device is a Radio Frequency (RF) module for communicating with the Internet wirelessly.

Specifically, the memory is used to store a voiceprint recognition model, history control instructions, and historical state information as well as an application.

The processor can call the memory stored information and the application by the transmitting device to execute the program code of the method steps of each of the alternative or preferred embodiments of the above method embodiments.

A person of ordinary skill in the art may understand that all or part of the steps of the foregoing embodiments may be completed by a program to instruct related hardware, and the program may be stored in a readable storage medium, and the storage medium may include: A disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

The control method and apparatus of the electric appliance according to the present application are described by way of example with reference to the accompanying drawings. However, it should be understood by those skilled in the art that various modifications may be made to the control method and apparatus of the electrical device proposed by the present application without departing from the scope of the present application. Therefore, the scope of protection of the present application should be determined by the content of the appended claims.

The serial numbers of the embodiments of the present application are merely for the description, and do not represent the advantages and disadvantages of the embodiments.

In the above-mentioned embodiments of the present application, the descriptions of the various embodiments are different, and the parts that are not detailed in a certain embodiment can be referred to the related descriptions of other embodiments.

In the several embodiments provided by the present application, it should be understood that the disclosed technical contents may be implemented in other manners. The device embodiments described above are only schematic. For example, the division of the unit may be a logical function division. In actual implementation, there may be another division manner, for example, multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, unit or module, and may be electrical or otherwise.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application, in essence or the contribution to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium. A number of instructions are included to cause a computer device (which may be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: a U disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, and the like. .

The above description is only a preferred embodiment of the present application, and it should be noted that those skilled in the art can also make several improvements and retouchings without departing from the principles of the present application. It should be considered as the scope of protection of this application.

Industrial applicability

The technical solution provided by the embodiment of the present application can be applied to the operation process of the electrical device, using the first voice information sent by the target object, using the voiceprint recognition model to identify the first voice information, and determining the voiceprint corresponding to the target object. The information, the control method corresponding to the voiceprint information, and the control scheme for the electrical equipment according to the control method can solve the problem that the existing electrical equipment cannot work according to the control habits of different users, and the degree of personalization is low, achieving high The personalization of electrical equipment enhances the user experience.

Claims

A method of controlling electrical equipment includes:

Obtaining the first voice information sent by the target object;

Identifying the first voice information by using a voiceprint recognition model, and determining voiceprint information corresponding to the target object, wherein the voiceprint recognition model is trained by machine learning using a plurality of sets of sample data, The plurality of sets of sample data includes: voice information of the target object and matching voiceprint information;

Obtaining a control manner corresponding to the voiceprint information;

According to the control method, the electrical equipment is controlled.
The method of claim 1, wherein the first voice information comprises a start command or a wake-up command, the control mode comprising: a history control command and/or historical state information of the electrical device.
The method according to claim 2, wherein before the first voice information is identified by using a voiceprint recognition model, and the voiceprint information corresponding to the target object is determined, the method further includes:

Obtaining a plurality of second voice information sent by the target object, where each second voice information includes one of: a control instruction, a wake-up instruction, and a preset instruction;

Extracting voiceprint features in the plurality of second voice information to obtain the plurality of sets of sample data;

Establishing a preset recognition model, and training the preset recognition model by using the plurality of sets of sample data to obtain the voiceprint recognition model.
The method according to claim 3, wherein, in the case that the control mode comprises: the history control instruction, the preset recognition model is trained by using the plurality of sets of sample data to obtain the voiceprint After identifying the model, the method further includes:

Acquiring the third voice information sent by the target object, where the third voice information includes: the history control instruction;

Identifying the third voice information by using the voiceprint recognition model, and determining voiceprint information corresponding to the target object;

Corresponding relationship between the history control instruction and the voiceprint information is obtained according to the history control instruction and the voiceprint information.
The method according to claim 4, wherein after the correspondence between the history control instruction and the voiceprint information is obtained according to the history control instruction and the voiceprint information, the method further includes:

Obtaining at least one history control instruction corresponding to the voiceprint information;

Processing the at least one history control instruction to obtain a history control instruction set corresponding to the voiceprint information.
The method according to claim 3, wherein, in the case that the control mode comprises: historical state information of the electrical device, the preset recognition model is trained using the plurality of sets of sample data to obtain a After the voiceprint recognition model, the method further includes:

Acquiring the third voice information sent by the target object, where the third voice information includes: the history control instruction;

Inputting the third voice information into the voiceprint recognition model to obtain voiceprint information corresponding to the target object;

Controlling the electrical device according to the historical control instruction, and acquiring historical state information of the electrical device;

Corresponding relationship between the historical state information of the electrical device and the voiceprint information is obtained according to the historical state information of the electrical device and the voiceprint information.
The method according to claim 2, wherein said control mode is stored in a storage device of said electric appliance and/or server, wherein obtaining a control mode corresponding to said voiceprint information comprises one or more of the following :

Obtaining the control mode from a storage device of the electrical device according to the voiceprint information;

Transmitting the voiceprint information to a server and receiving the control mode returned by the server.
The method of claim 2, wherein after acquiring the first voice information sent by the target object, the method further comprises:

Identifying the first voice information, and determining whether the first voice information includes the startup instruction or the wake-up instruction;

If it is determined that the first voice information includes the startup instruction or the wake-up instruction, the first voice information is re-identified by using a voiceprint recognition model, and voiceprint information corresponding to the target object is determined;

If it is determined that the first voice information does not include the start command or the wake-up command, the first voice information is not recognized again by using a voiceprint recognition model.
A method of controlling electrical equipment includes:

Obtaining the first voice information sent by the target object;

Identifying the first voice information, and determining voiceprint information corresponding to the target object;

Obtaining a control manner corresponding to the voiceprint information;

According to the control method, the electrical equipment is controlled.
The method according to claim 9, wherein the first voice information comprises: a start instruction or a wake-up instruction, wherein the identifying the first voice information, determining the voiceprint information corresponding to the target object comprises:

Identifying the first voice information by using a voiceprint recognition model, and determining voiceprint information corresponding to the target object, wherein the voiceprint recognition model is trained by machine learning using a plurality of sets of sample data, The plurality of sets of sample data includes: voice information of the target object and matching voiceprint information.
A control device for an electrical device, comprising:

a first acquiring module, configured to acquire first voice information sent by the target object;

An identification module configured to identify the first voice information by using a voiceprint recognition model to determine voiceprint information corresponding to the target object, wherein the voiceprint recognition model is to use machine learning training by using multiple sets of sample data And the plurality of sets of sample data includes: voice information of the target object and matched voiceprint information;

a second acquiring module, configured to acquire a control manner corresponding to the voiceprint information;

The control module is configured to control the electrical device according to the control mode.
A control device for an electrical device, comprising:

a first acquiring module, configured to acquire first voice information sent by the target object;

An identification module, configured to identify the first voice information, and determine voiceprint information corresponding to the target object;

a second acquiring module, configured to acquire a control manner corresponding to the voiceprint information;

The control module is configured to control the electrical device according to the control mode.
A control system for an electrical device, comprising:

The collecting device is configured to collect the first voice information sent by the target object;

The processor is connected to the collecting device, configured to identify the first voice information by using a voiceprint recognition model, determine voiceprint information corresponding to the target object, and acquire control corresponding to the voiceprint information The method, wherein the voiceprint recognition model is trained by machine learning using a plurality of sets of sample data, the plurality of sets of sample data comprising: voice information of the target object and matched voiceprint information;

The controller is coupled to the processor and configured to control the electrical device according to the control mode.
A storage medium, the storage medium comprising a stored program, wherein the device in which the storage medium is located controls the control method of the electric appliance according to any one of claims 1 to 10 while the program is running.
A processor, the processor being configured to execute a program, wherein the program is executed to execute the control method of the electrical device according to any one of claims 1 to 10.