Off-line voice broadcast method, device, equipment and computer storage medium

Abstract

The invention belongs to the technical field of intelligent household appliances, and particularly relates to an offline voice broadcast method, device and equipment and a computer storage medium. After a natural language instruction sent by a user is obtained, the natural language instruction is immediately sent to a WiFi module of the intelligent household electrical appliance, then the WiFi module of the intelligent household electrical appliance generates request information corresponding to the natural language instruction, and a feedback result corresponding to the request information is obtained through a cloud server of the intelligent household electrical appliance. And the voice module of the intelligent household electrical appliance is controlled to broadcast the broadcast corpus in the feedback result. According to the method, when the intelligent household electrical appliance with the voice technology is in an offline environment, the intelligent household electrical appliance can still use the voice function application depending on the online service, so that the intelligent household electrical appliance becomes more convenient and faster in the daily life of the user, and the use experience of the intelligent household electrical appliance is improved.

Description

Technical Field

[0001] The present application belongs to the technical field of smart home appliances, and specifically relates to an offline voice broadcast method, device, equipment and computer storage medium. Background Art

[0002] In today's intelligent life, voice technology is a convenient and fast way of interaction, which is relied on by more and more users. Through voice technology, people can easily interact with smart home appliances and perform various operations through voice commands.

[0003] However, existing voice technology can usually only use online functions when connected to the Internet. When smart home appliances with voice technology are in an offline environment, they cannot use voice function applications that rely on online services. This situation brings certain inconveniences to users' daily use.

[0004] Therefore, how to ensure that smart home appliances with voice technology can still use voice function applications that rely on online services when they are in an offline environment, thereby ensuring normal use by users and improving the user experience, is the problem that needs to be solved at present. Summary of the invention

[0005] The present application provides an offline voice broadcast method, device, equipment and computer storage medium, which are used to solve the problem that when smart home appliances using voice technology are in an offline environment, the smart home appliances cannot use voice function applications that rely on online services.

[0006] In a first aspect, the present application provides an offline voice broadcast method, comprising:

[0007] Obtain natural language instructions sent by users;

[0008] Sending the natural language command to the WiFi module of the smart home appliance, so that the WiFi module generates corresponding request information according to the natural language command, and sends the request information to the cloud server;

[0009] The feedback result sent by the WiFi module is obtained, and according to the feedback result, a broadcast corpus corresponding to the feedback result is determined, and the voice module of the smart home appliance is controlled to broadcast the broadcast corpus.

[0010] Optionally, sending the natural language command to a WiFi module of the smart home appliance includes:

[0011] Determining, according to the natural language instruction, a target function corresponding to the natural language instruction;

[0012] Determine whether the target function is a function in online mode;

[0013] When the target function is a function in an online mode, the natural language instruction is sent to a WiFi module of the smart home appliance.

[0014] Optionally, determining corresponding broadcast corpus according to the feedback result includes:

[0015] Using the audio file contained in the feedback result as the broadcast corpus;

[0016] or,

[0017] Acquire a first association relationship between the feedback result and a plurality of candidate broadcast corpora;

[0018] According to the feedback result and the first association relationship, a broadcast corpus corresponding to the feedback result is determined, wherein the broadcast corpus is any one of the candidate broadcast corpuses.

[0019] Optionally, determining corresponding broadcast corpus according to the feedback result includes:

[0020] Acquire a second association relationship between the identification information and the candidate broadcast corpus;

[0021] Determine, according to the feedback result, a plurality of target identification information and a broadcasting timing between the plurality of target identification information;

[0022] According to the multiple target identification information, the broadcasting sequence and the second association relationship, a broadcasting corpus corresponding to the feedback result is determined, wherein the broadcasting corpus includes multiple candidate broadcasting corpuses.

[0023] In a second aspect, the present application provides an offline voice broadcast method, comprising:

[0024] Obtaining a natural language instruction sent by a control module of the smart home appliance;

[0025] Generate corresponding request information according to the natural language instruction, and send the request information to the cloud server;

[0026] The feedback result sent by the cloud server is obtained, and the feedback result is sent to the control module, so that the control module determines the corresponding broadcast corpus according to the feedback result, and controls the voice module to broadcast the broadcast corpus.

[0027] Optionally, generating corresponding request information according to the natural language instruction includes:

[0028] Performing word segmentation processing on the natural language instruction to obtain multiple word segmentation vectors;

[0029] According to the multiple word segmentation vectors, request information corresponding to the natural language instruction is determined.

[0030] In a third aspect, the present application provides an offline voice broadcasting device, comprising:

[0031] An acquisition module, used to acquire natural language instructions sent by a user;

[0032] A sending module, used to send the natural language instruction to the WiFi module of the smart home appliance, so that the WiFi module generates corresponding request information according to the natural language instruction, and sends the request information to the cloud server;

[0033] The acquisition module is further used to obtain the feedback result sent by the WiFi module;

[0034] A determination module, configured to determine, according to the feedback result, a broadcast corpus corresponding to the feedback result;

[0035] The control module is used to control the voice module of the smart home appliance to broadcast the broadcast corpus.

[0036] Optionally, the determination module is further used to determine a target function corresponding to the natural language instruction according to the natural language instruction;

[0037] The device further comprises: a judgment module;

[0038] The judging module is used to judge whether the target function is a function in the online mode;

[0039] The sending module is specifically used to send the natural language instruction to the WiFi module of the smart home appliance when the target function is a function in the online mode.

[0040] Optionally, the determination module is specifically configured to use the audio file included in the feedback result as the announcement corpus;

[0041] or,

[0042] The acquisition module is further used to acquire a first association relationship between the feedback result and a plurality of candidate broadcast corpora;

[0043] The determination module is specifically configured to determine a broadcast corpus corresponding to the feedback result according to the feedback result and the first association relationship, wherein the broadcast corpus is any one of the candidate broadcast corpuses.

[0044] Optionally, the acquisition module is further used to acquire a second association relationship between the identification information and the candidate broadcast corpus;

[0045] The determination module is further used to determine a plurality of target identification information and a broadcasting timing between the plurality of target identification information according to the feedback result;

[0046] The determination module is specifically configured to determine the broadcast corpus corresponding to the feedback result according to the multiple target identification information, the broadcast timing and the second association relationship, wherein the broadcast corpus includes multiple candidate broadcast corpuses.

[0047] In a fourth aspect, the present application provides an offline voice broadcasting device, comprising:

[0048] An acquisition module, used to acquire a natural language instruction sent by the control module of the smart home appliance;

[0049] A processing module, used to generate corresponding request information according to the natural language instruction;

[0050] A sending module, used for sending the request information to a cloud server;

[0051] The acquisition module is also used to obtain the feedback result sent by the cloud server, and send the feedback result to the control module, so that the control module determines the corresponding broadcast corpus according to the feedback result, and controls the voice module to broadcast the broadcast corpus.

[0052] Optionally, the processing module is further used to perform word segmentation processing on the natural language instruction to obtain multiple word segmentation vectors;

[0053] The device further comprises: a determination module;

[0054] The determination module is used to determine the request information corresponding to the natural language instruction based on the multiple word segmentation vectors.

[0055] In a fifth aspect, the present application provides an offline voice broadcast device, including:

[0056] Memory;

[0057] processor;

[0058] Wherein, the memory stores computer-executable instructions;

[0059] The processor executes the computer-executable instructions stored in the memory to implement the offline voice broadcast method as described in the first aspect and various possible implementations of the first aspect.

[0060] In a sixth aspect, the present application provides a computer storage medium having computer execution instructions stored thereon, wherein the computer execution instructions are executed by a processor to implement the offline voice broadcast method as described in the first aspect and various possible implementation methods of the first aspect.

[0061] The present application provides an offline voice broadcast method, which immediately sends the natural language command to the WiFi module of the smart home appliance after obtaining the natural language command sent by the user, and then the WiFi module of the smart home appliance will generate request information corresponding to the natural language command, and obtain the feedback result corresponding to the request information through the cloud server of the smart home appliance, so as to control the voice module of the smart home appliance to broadcast the broadcast corpus in the feedback result. This method not only ensures that when the smart home appliance with voice technology is in an offline environment, the smart home appliance can still use those voice function applications that rely on online services, thereby making the smart home appliance more convenient and quick in the daily life of the user, thereby improving the user experience of the smart home. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0063] Figure 1 This is the process interaction of the offline voice broadcast method provided by this application Figure 1 ;

[0064] Figure 2 This is the process interaction of the offline voice broadcast method provided by this application Figure 2 ;

[0065] Figure 3 The structure diagram of the offline voice broadcast device provided in this application Figure 1 ;

[0066] Figure 4 The structure diagram of the offline voice broadcast device provided in this application Figure 2 ;

[0067] Figure 5 A schematic diagram of the structure of the offline voice broadcast device provided for this application.

[0068] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0069] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0070] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in sequences other than those illustrated or described herein, for example.

[0071] In the embodiments of the present application, the words "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0072] In today's intelligent life, voice technology is a convenient and fast way of interaction, which is relied on by more and more users. Users only need to tell the voice device their needs through the voice interaction function, and the voice device will perform tasks according to the instructions issued by the user, which not only improves the quality of life of users, but also adds fun to their lives. In addition, the voice interaction function can also be used as part of the smart home to realize voice control of home appliances, making the user's home life more intelligent.

[0073] However, existing voice technology can usually only be used online when connected to the Internet. When smart home appliances with voice technology are in an offline environment, they cannot use voice function applications that rely on online services. For example, when users use voice interaction technology to send messages, make calls, or play music, these functions will not be available if the current voice interaction technology is in an offline environment. In addition, some applications that rely on cloud voice services, such as smart translation tools and voice assistants, cannot be used offline.

[0074] Therefore, the current urgent problem to be solved is how to ensure that when smart home appliances with voice technology are in an offline environment, they can still use voice function applications that rely on online services, thereby ensuring normal use by users and improving the user experience.

[0075] In view of the above problems, the present application provides an offline voice broadcast method. Since the offline voice module model in the prior art usually cannot directly interact with the functions of the cloud server, and when the user interacts with the smart home appliance with offline voice, it is usually necessary to realize the remote operation of the smart home appliance through APP or other remote control methods, so this method not only reduces the flexibility of the smart home appliance, but also reduces the convenience of the smart home appliance. Therefore, the present application first proposes an offline voice recognition model, which includes both offline function voice instructions and online function voice instructions. The model can realize the function of offline voice directly using the cloud server, and then realize the interaction between the user and the smart home appliance with offline voice, thereby improving the user experience.

[0076] When training the existing offline speech module model, the present application may adopt the following training algorithms, for example: module matching, hidden Markov model, and deep learning-based methods, so as to obtain an offline speech recognition model that includes both offline functional voice instructions and online functional instructions.

[0077] The offline voice broadcast method provided by the present application, after obtaining the natural language command sent by the user, immediately sends the natural language command to the WiFi module of the smart home appliance, and then the WiFi module of the smart home appliance will generate request information corresponding to the natural language command, and obtain the feedback result corresponding to the request information through the cloud server of the smart home appliance, so as to control the voice module of the smart home appliance to broadcast the broadcast corpus in the feedback result. This method not only ensures that when the smart home appliances with voice technology are in an offline environment, the smart home appliances can still use those voice function applications that rely on online services, thereby making the smart home appliances more convenient and quick in the daily life of the user, thereby improving the user experience of the smart home.

[0078] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0079] Figure 1 The process of the offline voice broadcast method provided in the embodiment of the present application Figure 1 .like Figure 1 The offline voice broadcast method provided in this embodiment includes:

[0080] S101: The control module of the smart home appliance obtains a natural language command sent by a user.

[0081] Among them, natural language instructions refer to the instruction information issued by users to smart home appliances through spoken or written language.

[0082] By obtaining the natural language commands sent by the user, the command information that the smart home appliances can execute can be obtained.

[0083] Since natural language commands are one of the ways for users to interact with smart appliances, through natural language commands, users can directly express the operations or requirements to be performed to smart appliances without having to perform cumbersome button or touch screen operations, which can make smart appliances more convenient and more humane, thereby improving user experience and convenience of operation. Therefore, in order to achieve a more natural and intuitive user interaction experience, smart appliances need to obtain natural language commands sent by users.

[0084] Different smart home appliances correspond to different natural language instructions. It is understandable that since different smart home appliances have different functions and operation modes, and when a user needs to operate a smart home appliance function, it is necessary to send instruction information corresponding to the need to the smart home appliance, that is, it is necessary to send a natural language instruction to the smart home appliance so that the smart home appliance completes the corresponding operation according to the natural language instruction.

[0085] For example, when the smart home appliance is a smart speaker, and the smart speaker has functions such as music playback, weather query, and alarm setting, if the user says to the smart speaker, "Play a pop song," the smart speaker will receive the instruction information corresponding to the user's instruction "Play a pop song," and execute the instruction information; and when the smart home appliance is a smart TV, and the smart home appliance has functions such as volume control, TV channel switching, and playback control, if the user says to the smart TV, "Turn up the volume," the smart home appliance will receive the instruction information corresponding to the user's instruction "Turn up the volume," and execute the instruction information.

[0086] S102: The control module of the smart home appliance sends the natural language instruction.

[0087] The control module of the smart home appliance sends the natural language command to the WiFi module of the smart home appliance, usually according to a specific communication protocol and communication link.

[0088] It can be understood that after the control module of the smart home appliance obtains the natural language command information sent by the user, the smart home appliance control module is responsible for parsing the natural language commands sent by the user, converting them into a command format recognizable by the WiFi module of the smart home appliance, and sending these commands to the WiFi module of the smart home appliance through a specific communication protocol and communication link.

[0089] S103: The WiFi module of the smart home appliance obtains the natural language instruction sent by the control module of the smart home appliance.

[0090] By acquiring the natural language instructions sent by the control module of the smart home appliance, the instruction information corresponding to the natural language instructions can be obtained.

[0091] The WiFi module of the smart home appliance obtains the natural language instructions sent by the control module of the smart home appliance, usually according to a specific communication protocol and communication link.

[0092] It can be understood that sending and receiving can only be carried out after the WiFi module of the smart home appliance and the control module of the smart home appliance establish a connection relationship. Therefore, the WiFi module of the smart home appliance needs to establish a connection relationship with the control module of the smart home appliance according to a specific communication protocol and communication link. After the connection relationship is established, the WiFi module of the smart home appliance will receive the data packet sent by the control module of the smart home appliance, thereby obtaining the command information sent by the control module of the smart home appliance.

[0093] S104: The WiFi module of the smart home appliance generates corresponding request information according to the natural language instruction.

[0094] The request information refers to the relevant data or information obtained according to the instruction sent by the user.

[0095] Since different smart home appliances have different functions and operating methods, and when the control module of the smart home appliance obtains the natural language command sent by the user, it is necessary to send request information corresponding to the natural voice command to the WiFi module of the smart home appliance, so that the control module of the smart home appliance can obtain the feedback result corresponding to the request, that is, the WiFi module of the smart home appliance can obtain the feedback result corresponding to the request information.

[0096] Different request information corresponds to different natural language instructions. It is understandable that the functions of smart home appliances are complex and diverse. When a user needs to use function A in a smart home appliance, the user needs to send instruction information corresponding to function A, and when a user needs to use function B in a smart home appliance, the user needs to send instruction information corresponding to function B.

[0097] For example, the smart speaker has functions such as music playback, weather query, and alarm setting. If the voice command sent by the user to the smart speaker is "play a pop music", the smart speaker will generate a request information corresponding to "play a pop music"; if the voice command sent by the user to the smart speaker is "wake me up at 7 o'clock tomorrow", the smart speaker will generate a request information corresponding to "wake me up at 7 o'clock tomorrow".

[0098] S105: The WiFi module of the smart home appliance sends the request information.

[0099] When the WiFi module of the smart home appliance generates request information according to the acquired natural language instruction, in order to obtain the processing result of the request information, the request information needs to be sent to the cloud server of the smart home appliance.

[0100] Since the WiFi module of the smart home appliance sends request information to the cloud server of the smart home appliance, it is usually necessary to establish a connection relationship before the request information can be sent to the cloud server of the smart home appliance. Therefore, in order for the WiFi module of the smart home appliance to obtain the processing result corresponding to the request information, the WiFi module of the smart home appliance needs to be connected to the cloud server of the smart home appliance according to a specific communication protocol and communication link. Then, when the connection is established, the WiFi module of the smart home appliance can send the request information directly to the cloud server of the smart home appliance.

[0101] S106: The cloud server of the smart home appliance sends a feedback result.

[0102] The feedback result refers to the result obtained by the cloud server of the smart home appliance after immediately analyzing and processing the request information sent by the WiFi module of the smart home appliance when the cloud server of the smart home appliance receives the request information.

[0103] When the WiFi module of the smart home appliance has established a connection with the cloud server of the smart home appliance, and the cloud server of the smart home appliance receives the request information sent by the WiFi module of the smart home appliance, the cloud server of the smart home appliance will call the interface in the cloud server according to the content of the request information, so as to determine the feedback result corresponding to the request information.

[0104] S107: The WiFi module of the smart home appliance obtains the feedback result sent by the cloud server.

[0105] Among them, the feedback result refers to the feedback result obtained after the cloud server of the smart home appliance processes and analyzes the request information.

[0106] By acquiring the feedback result sent by the WiFi module of the smart home appliance, the broadcast corpus corresponding to the feedback information can be obtained, so as to control the voice module of the smart home appliance to broadcast according to the broadcast corpus.

[0107] S108: The WiFi module of the smart home appliance sends the feedback result.

[0108] When the WiFi module of the smart home appliance obtains the feedback result corresponding to the request information, in order to ensure that the voice module of the smart home appliance can accurately execute the content of the feedback result, it is necessary to send the feedback result to the control module of the smart home appliance.

[0109] Since the WiFi module of the smart home appliance has established a connection with the control module of the smart home appliance when it receives the natural language command sent by the control module of the smart home appliance, when the WiFi module of the smart home appliance obtains the feedback result sent by the cloud server of the smart home appliance, the feedback result can be sent to the control module of the smart home appliance, so that the control module of the smart home appliance controls the voice module of the smart home appliance according to the feedback result.

[0110] S109: The control module of the smart home appliance obtains the feedback result sent by the WiFi module.

[0111] The control module of the smart home appliance obtains the feedback result sent by the WiFi module of the smart home appliance, usually according to a specific communication protocol and communication link.

[0112] It is understandable that in order to obtain the feedback results sent by the WiFi module of the smart home appliance, the control module of the smart home appliance usually needs to establish a communication connection with the WiFi module of the smart home appliance, and when the communication connection is established, it can promptly obtain the feedback information sent by the WiFi module of the smart home appliance.

[0113] When the control module of the smart home appliance obtains the feedback result sent by the WiFi module, it needs to process and analyze the feedback result to obtain the broadcast corpus corresponding to the feedback result, and then control the voice module of the smart home appliance to broadcast the broadcast corpus.

[0114] S110: The control module of the smart home appliance determines corresponding broadcast corpus according to the feedback result.

[0115] Among them, the broadcast corpus refers to the audio or text content broadcast by the voice module of smart home appliances.

[0116] By obtaining the feedback results, the broadcast corpus corresponding to the feedback results can be obtained.

[0117] It is understandable that in order to ensure that the voice module of the smart home appliance can correctly execute the operations or functions corresponding to the natural language instructions, the control module of the smart home appliance needs to process the obtained feedback results to obtain the broadcast corpus corresponding to the feedback results.

[0118] The way in which the control module of the smart home appliance obtains the feedback result sent by the cloud server of the smart home appliance may include: directly sending the feedback result from the cloud server of the smart home appliance to the control module of the smart home appliance, or obtaining the feedback result through the WiFi module of the smart home appliance. This application does not limit this.

[0119] In this step, for example, after obtaining the feedback result sent by the WiFi module of the smart home appliance, the broadcast corpus corresponding to the feedback result can be determined according to the feedback result, thereby controlling the voice module of the smart home appliance to broadcast.

[0120] S111: The control module of the smart home appliance controls the voice module of the smart home appliance to broadcast the broadcast corpus.

[0121] When the control module of the smart home appliance determines the corpus that the voice module of the smart home appliance needs to broadcast, it can control the voice module of the smart home appliance to broadcast the corpus content corresponding to the corpus, so that the corpus broadcast by the voice module of the smart home appliance is the same as the natural language command sent by the user to the smart home appliance.

[0122] By broadcasting the natural language commands sent by users, not only can the normal use of smart home appliances be ensured, but also the user experience can be improved, thereby improving the efficiency of the use of smart home appliances.

[0123] The offline voice broadcast method provided in this embodiment obtains the natural language instruction sent by the user, and sends the natural language instruction to the WiFi module of the smart home appliance, and then obtains the request information corresponding to the natural language instruction and the feedback result corresponding to the request information through the WiFi module of the smart home appliance, and then continues to control the voice module of the smart home appliance to broadcast the broadcast corpus in the feedback result. This method not only ensures that when the smart home appliance with voice technology is in an offline environment, the smart home appliance can still use those voice function applications that rely on online services, but also ensures the normal use of the smart home appliance, thereby improving the user experience and thus improving the use efficiency of the smart home appliance.

[0124] Figure 2 The process of the offline voice broadcast method provided in the embodiment of the present application Figure 2 .like Figure 2 As shown, this embodiment is Figure 1 Based on the embodiment, the offline voice broadcast method is described in detail. The offline voice broadcast method provided by this embodiment includes:

[0125] S201: The control module of the smart home appliance obtains a natural language command sent by the user.

[0126] Step S201 is similar to the above-mentioned step S101 and will not be described in detail here.

[0127] S202: The control module of the smart home appliance determines a target function corresponding to the natural language instruction according to the natural language instruction.

[0128] By acquiring the natural language instructions sent by the user, the functional information corresponding to the natural language instructions can be obtained.

[0129] It can be understood that since smart home appliances have different functions and operating methods, and when smart home appliances obtain natural language instructions sent by users, they need to identify the natural language instructions, convert them into specific text or specific instruction codes, and then obtain the functional information corresponding to the natural language instructions. Therefore, through different natural language instructions, the functions corresponding to the natural language instructions can be obtained, that is, different natural language instructions correspond to different functions.

[0130] For example, the smart speaker has functions such as music playback, weather query, and alarm setting. If the voice command sent by the user to the smart speaker is "play a pop song", then the target function corresponding to the voice command "play a pop song" is "music playback"; if the voice command sent by the user to the smart speaker is "wake me up at 7 o'clock tomorrow", then the target function corresponding to the voice command "wake me up at 7 o'clock tomorrow" is "alarm setting".

[0131] S203: The control module of the smart home appliance determines whether the target function is a function in an online mode.

[0132] Among them, the functions in the online mode refer to the functions or operations that can be used by the smart home appliance when the smart home appliance is connected to the Internet.

[0133] Natural language instructions may include, for example, online instructions and offline instructions. Online instructions refer to the online functions of smart home appliances that users can operate online through an Internet connection, while offline instructions refer to the functions of smart home appliances that users can still operate without an Internet connection.

[0134] The purpose of judging whether the target function is a function in the online mode is to determine whether the current natural language instruction is an online instruction.

[0135] Since the offline speech recognition model provided by the present application includes both offline voice commands and online voice commands, when the control module of the smart home appliance obtains the natural language command sent by the user and determines the target function corresponding to the natural language command, it is necessary to use the offline speech recognition model to determine whether the smart home appliance is in an online state. Then, when it is determined that the smart home appliance is not in an online state, it is necessary to determine whether the target function is a function in the online mode, so as to better process the function in the online mode.

[0136] If the target function is a function in online mode, it indicates that the current natural language command is an online command, and therefore, the natural language command can be sent to the WiFi module of the smart home appliance.

[0137] If the target function is not a function in online mode, it indicates that the current natural language instruction is not an online instruction, that is, the current natural language instruction can be determined as an offline instruction. Therefore, the smart home appliance can be controlled to execute the natural language instruction.

[0138] For example, smart speakers have functions such as music playback, weather query, and alarm setting. If a user sends a message to the smart speaker saying "query today's weather conditions", the control module of the smart speaker will determine that the command is an online command and will send the command to the WiFi module of the smart home appliance to wait for the query result.

[0139] S204: When the target function is a function in the online mode, the control module of the smart home appliance sends the natural language instruction.

[0140] When it is determined that the target function is a function in the online mode, the natural language instruction corresponding to the target function can be sent to the WiFi module of the smart home appliance, so that the WiFi module of the smart home appliance processes and analyzes the natural language instruction.

[0141] It is understandable that since the functions in the online mode usually need to access the cloud server to obtain the feedback results corresponding to the target functions, the natural language instructions corresponding to the target functions need to be sent to the WiFi module of the smart home appliance.

[0142] S205: The WiFi module of the smart home appliance obtains the natural language instruction sent by the control module of the smart home appliance.

[0143] Step S205 is similar to the above-mentioned step S103 and will not be described in detail here.

[0144] S206: The WiFi module of the smart home appliance performs word segmentation processing on the natural language instruction to obtain multiple word segmentation vectors.

[0145] The word segmentation process is used to indicate that the natural language instruction is segmented into independent words or phrases. The word segmentation vector is used to indicate the expression method of converting the word segmentation result into a vector representation.

[0146] Through word segmentation processing, natural language instructions can be converted into a form that is easier for the cloud server of smart home appliances to understand and process.

[0147] The word segmentation processing method may use, for example, a rule-based word segmentation method, such as a maximum matching method, a minimum matching method, and a forward maximum matching method, or a statistical-based word segmentation method, such as a hidden Markov model-based word segmentation method, or a deep learning-based word segmentation method, such as using a recurrent neural network model for word segmentation. This application does not limit this.

[0148] The word segmentation vector may be determined by, for example, using a bag-of-words model or a word embedding technique, which is not limited in the present application.

[0149] After the WiFi module of the smart home appliance receives the natural language instruction sent by the user, it needs to perform word segmentation processing on the natural language instruction in order to obtain the word segmentation vector corresponding to the natural language instruction.

[0150] It is understandable that after the WiFi module of the smart home appliance receives the natural language command sent by the user, it needs to perform word segmentation processing on the command so as to decompose the entire command into single words or phrases, thereby obtaining multiple word segmentation vectors corresponding to the natural language command.

[0151] For example, the current natural language instruction is "query today's weather conditions", then after word segmentation processing of the natural language instruction, multiple word segmentation vectors corresponding to the natural language instruction and the sequence relationship of multiple analysis vectors can be obtained, namely "query: sequence A1"; "today: sequence A2"; "of: sequence A3", "weather: sequence A4" and "condition: sequence A5".

[0152] S207: The WiFi module of the smart home appliance determines request information corresponding to the natural language instruction based on the multiple word segmentation vectors.

[0153] By constructing multiple word segmentation vectors, request information corresponding to natural language instructions can be obtained.

[0154] It can be understood that since multiple word segmentation vectors are determined based on natural language instructions and there is a sequence relationship between the multiple word segmentation vectors, when the WiFi module of the smart home appliance constructs multiple analysis vectors, the word segmentation vectors can be constructed according to the sequence relationship so that the obtained request information corresponds to the natural language instructions.

[0155] S208: The WiFi module of the smart home appliance sends the request information.

[0156] Step S208 is similar to the above step S105 and will not be described again here.

[0157] S209: The cloud server of the smart home appliance obtains the request information.

[0158] By acquiring the request information sent by the WiFi module of the smart home appliance, the content of the request information can be obtained, and the content generally includes the object of operation, the mode of operation and the instruction of operation.

[0159] It can be understood that when the WiFi module of the smart home appliance sends a request message to the cloud server of the smart home appliance, the WiFi module of the smart home appliance has already established a connection relationship with the cloud server of the smart home appliance, so the cloud server of the smart home appliance can immediately obtain the request message sent by the WiFi module of the smart home appliance.

[0160] S210: The cloud server of the smart home appliance determines the feedback result according to the request information.

[0161] Different feedback results correspond to different request information. Since smart home appliances have multiple operation modes and operation functions, when the WiFi module of the smart home appliance determines the request information corresponding to the natural language instruction, it can determine the feedback result corresponding to the request information according to the request information.

[0162] It is understandable that when the request information is sent to the cloud server of the smart home appliance, the cloud server of the smart home appliance will process the information carried in the request information to generate a corresponding feedback result and return it to the WiFi module of the smart home appliance.

[0163] S211: The cloud server of the smart home appliance sends the feedback result.

[0164] Step S211 is similar to the above-mentioned step S106 and will not be described in detail here.

[0165] S212: The WiFi module of the smart home appliance obtains the feedback result sent by the cloud server.

[0166] Step S212 is similar to the above step S107 and will not be described again.

[0167] S213: The WiFi module of the smart home appliance sends the feedback result.

[0168] Step S213 is similar to the above step S108 and will not be described again.

[0169] S214: The control module of the smart home appliance obtains the feedback result sent by the WiFi module.

[0170] Step S214 is similar to the above step S109 and will not be described again.

[0171] S215: The control module of the smart home appliance determines a corresponding broadcast forecast according to the feedback result.

[0172] Specifically, according to the feedback result, the specific implementation method of determining the corresponding broadcast prediction may include:

[0173] 1) Using the audio file contained in the feedback result as the broadcast corpus.

[0174] Among them, when the control module of the smart home appliance obtains the feedback result sent by the smart home appliance, the control module of the smart home appliance can obtain the audio file corresponding to the natural language instruction, and then the audio file can be used as the broadcast corpus of the voice module, so that the voice module can accurately broadcast the audio file.

[0175] 2) Obtaining a first association relationship between the feedback result and a plurality of candidate broadcast corpora; determining a broadcast corpus corresponding to the feedback result according to the feedback result and the first association relationship, wherein the broadcast corpus is any one of the candidate broadcast corpora.

[0176] The candidate announcement corpus refers to the announcement corpus pre-stored in the voice module of the smart home appliance.

[0177] The first association relationship is used to indicate that there is an association relationship between multiple candidate broadcast corpora of the smart home appliance and the feedback results.

[0178] Different feedback results correspond to different candidate broadcast corpora. When the voice module of the smart home appliance obtains a feedback result corresponding to a natural language instruction, it is necessary to determine the broadcast corpus corresponding to the feedback result based on the first association relationship between the feedback result and multiple candidate broadcast corpora.

[0179] It is understandable that when the voice module of the smart home appliance obtains the feedback result sent by the cloud server of the smart home appliance, the feedback result can be matched with multiple candidate broadcast corpora in the voice module to determine the candidate broadcast corpora with the highest matching degree with the feedback result.

[0180] For example, the natural language command sent by the user is "check today's weather", and the broadcast corpus currently stored in the voice module of the smart home appliance includes: today's weather is sunny, today's weather is cloudy, and today's weather is cold, etc. Then, when the voice module of the smart home appliance obtains the feedback result corresponding to the natural language command, it can obtain the broadcast corpus corresponding to the feedback result, that is, it can determine that "today's weather is sunny" matches the natural language command.

[0181] 3) obtaining a second association relationship between the identification information and the candidate broadcast corpus; determining multiple target identification information and a broadcast timing between the multiple target identification information according to the feedback result; determining a broadcast corpus corresponding to the feedback result according to the multiple target identification information, the broadcast timing and the second association relationship, wherein the broadcast corpus includes multiple candidate broadcast corpuses.

[0182] The identification information refers to the information corresponding to the feedback result.

[0183] The candidate announcement corpus refers to the announcement corpus pre-stored in the voice module of the smart home appliance.

[0184] Different feedback results correspond to different identification information. When the control module of the smart home appliance obtains a feedback result corresponding to a natural language instruction, that is, obtains the identification information corresponding to the feedback result, it is necessary to obtain a second association relationship between the identification information and the candidate broadcast corpus so that the obtained broadcast corpus is more accurate.

[0185] By processing and analyzing the feedback results, multiple target identification information corresponding to the feedback results and the broadcast timing between the multiple target identification information can be obtained, and then the broadcast corpus corresponding to the feedback results can be determined based on the target identification information, the broadcast timing and the second association relationship.

[0186] For example, the user sends a natural language command such as "check today's weather", and the voice module of the smart home appliance currently stores the following broadcast forecasts: today's weather, sunny, cloudy, temperature, twenty, one, two, degrees, wind direction, southeast, wind force, weak, wind, strong and other broadcast corpora. Therefore, when the voice module of the smart home appliance obtains the feedback result corresponding to the natural language command, it can check the broadcast corpus in the voice module, and then obtain the corpus to be broadcast by the voice module "Today's weather is sunny, 37 degrees, wind direction is southeast and wind force is weak".

[0187] S216: The control module of the smart home appliance controls the voice module of the smart home appliance to broadcast the forecast.

[0188] Step S216 is similar to the above step S111 and will not be described again.

[0189] The offline voice broadcast method provided in this embodiment analyzes and processes the acquired natural language instructions to obtain the target function corresponding to the natural language instructions, and after determining that the target function is a function in the online mode, sends the natural language instructions to the WiFi module of the smart home appliance, and after obtaining the feedback information corresponding to the natural language instructions through the WiFi module of the smart home appliance again, controls the voice module of the smart home appliance to broadcast according to the broadcast corpus corresponding to the feedback information. This method not only ensures that when the smart home appliances with voice technology are in an offline environment, the smart home appliances can still use those voice function applications that rely on online services, thereby making the smart home appliances more convenient and quick in the daily life of users, thereby improving the user experience of smart homes.

[0190] Figure 3 The structure diagram of the offline voice broadcast device provided in this application Figure 1 .like Figure 3As shown, the present application provides an offline voice broadcasting device, and the offline voice broadcasting device 300 includes:

[0191] The acquisition module 301 is used to acquire the natural language instruction sent by the user;

[0192] A sending module 302 is used to send the natural language instruction to the WiFi module of the smart home appliance, so that the WiFi module generates corresponding request information according to the natural language instruction, and sends the request information to the cloud server;

[0193] The acquisition module 301 is also used to obtain the feedback result sent by the WiFi module;

[0194] A determination module 303 is used to determine the broadcast corpus corresponding to the feedback result according to the feedback result;

[0195] The control module 304 is used to control the voice module of the smart home appliance to broadcast the broadcast language material.

[0196] Optionally, the determination module 303 is further configured to determine a target function corresponding to the natural language instruction according to the natural language instruction;

[0197] The device further includes: a judgment module 305;

[0198] The judging module 305 is used to judge whether the target function is a function in the online mode;

[0199] The sending module 302 is specifically configured to send the natural language instruction to the WiFi module of the smart home appliance when the target function is a function in an online mode.

[0200] Optionally, the determination module 303 is specifically configured to use the audio file included in the feedback result as the announcement corpus;

[0201] or,

[0202] The acquisition module 301 is further used to acquire a first association relationship between the feedback result and a plurality of candidate broadcast corpora;

[0203] The determining module 303 is specifically configured to determine the broadcast corpus corresponding to the feedback result according to the feedback result and the first association relationship, wherein the broadcast corpus is any one of the candidate broadcast corpuses.

[0204] Optionally, the acquisition module 301 is further used to acquire a second association relationship between the identification information and the candidate broadcast corpus;

[0205] The determination module 303 is further used to determine a plurality of target identification information and a broadcasting timing between the plurality of target identification information according to the feedback result;

[0206] The determination module 303 is specifically configured to determine the broadcast corpus corresponding to the feedback result according to the multiple target identification information, the broadcast timing and the second association relationship, wherein the broadcast corpus includes multiple candidate broadcast corpuses.

[0207] Figure 4 The structure diagram of the offline voice broadcast device provided in this application Figure 2 .like Figure 4 As shown, the present application provides an offline voice broadcast device, and the offline voice broadcast device 400 includes:

[0208] An acquisition module 401 is used to acquire a natural language instruction sent by a control module of the smart home appliance;

[0209] The processing module 402 is used to generate corresponding request information according to the natural language instruction;

[0210] The sending module 403 is used to send the request information to the cloud server;

[0211] The acquisition module 401 is further used to acquire the feedback result sent by the cloud server, and send the feedback result to the control module, so that the control module determines the corresponding broadcast corpus according to the feedback result, and controls the voice module to broadcast the broadcast corpus.

[0212] Optionally, the processing module 402 is further configured to perform word segmentation processing on the natural language instruction to obtain a plurality of word segmentation vectors;

[0213] The apparatus further includes: a determination module 404;

[0214] The determination module 404 is used to determine the request information corresponding to the natural language instruction according to the multiple word segmentation vectors.

[0215] Figure 5 This is a schematic diagram of the structure of the offline voice broadcast device provided by this application. Figure 5 As shown, the present application provides an offline voice broadcast device, and the offline voice broadcast device 500 includes: a receiver 501, a transmitter 502, a processor 503 and a memory 504.

[0216] Receiver 501, used for receiving instructions and data;

[0217] A transmitter 502, used for sending instructions and data;

[0218] Memory 504, used to store computer-executable instructions;

[0219] The processor 503 is used to execute the computer-executable instructions stored in the memory 504 to implement the various steps performed by the offline voice broadcast method in the above embodiment. For details, please refer to the relevant description in the above offline voice broadcast method embodiment.

[0220] Optionally, the memory 504 may be independent or integrated with the processor 503 .

[0221] When the memory 504 is independently provided, the electronic device further includes a bus for connecting the memory 504 and the processor 503 .

[0222] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, an offline voice broadcast method as performed by the above-mentioned offline voice broadcast device is implemented.

[0223] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In hardware implementations, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include (or non-transitory media) and a communication medium (or temporary media). As known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those of ordinary skill in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0224] So far, the technical solution of the present application has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments, and the above embodiments are only used to illustrate the technical solution of the present application rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. An offline voice broadcast method, characterized in that: A control module applied to a smart home appliance, the method comprising: Obtain natural language instructions sent by users; Sending the natural language command to the WiFi module of the smart home appliance, so that the WiFi module generates corresponding request information according to the natural language command, and sends the request information to the cloud server; The feedback result sent by the WiFi module is obtained, and corresponding broadcast corpus is determined according to the feedback result, and the voice module of the smart home appliance is controlled to broadcast the broadcast corpus.

2. The method according to claim 1, characterized in that The step of sending the natural language command to the WiFi module of the smart home appliance includes: Determining, according to the natural language instruction, a target function corresponding to the natural language instruction; Determine whether the target function is a function in online mode; When the target function is a function in an online mode, the natural language instruction is sent to a WiFi module of the smart home appliance.

3. The method according to claim 1, characterized in that: Determining corresponding broadcast corpus according to the feedback result includes: Using the audio file contained in the feedback result as the broadcast corpus; or, Acquire a first association relationship between the feedback result and a plurality of candidate broadcast corpora; According to the feedback result and the first association relationship, a broadcast corpus corresponding to the feedback result is determined, wherein the broadcast corpus is any one of the candidate broadcast corpuses.

4. The method according to claim 1, characterized in that: Determining corresponding broadcast corpus according to the feedback result includes: Acquire a second association relationship between the identification information and the candidate broadcast corpus; Determine, according to the feedback result, a plurality of target identification information and a broadcasting timing between the plurality of target identification information; According to the multiple target identification information, the broadcasting sequence and the second association relationship, a broadcasting corpus corresponding to the feedback result is determined, wherein the broadcasting corpus includes multiple candidate broadcasting corpuses.

5. An offline voice broadcast method, characterized in that: A WiFi module applied to smart home appliances, the method comprising: Obtaining a natural language instruction sent by a control module of the smart home appliance; Generate corresponding request information according to the natural language instruction, and send the request information to the cloud server; The feedback result sent by the cloud server is obtained, and the feedback result is sent to the control module, so that the control module determines the corresponding broadcast corpus according to the feedback result, and controls the voice module to broadcast the broadcast corpus.

6. The method according to claim 5, characterized in that The generating corresponding request information according to the natural language instruction includes: Performing word segmentation processing on the natural language instruction to obtain multiple word segmentation vectors; According to the multiple word segmentation vectors, request information corresponding to the natural language instruction is determined.

7. An offline voice broadcasting device, characterized in that: The device comprises: An acquisition module, used to acquire natural language instructions sent by a user; A sending module, used to send the natural language instruction to the WiFi module of the smart home appliance, so that the WiFi module generates corresponding request information according to the natural language instruction, and sends the request information to the cloud server; The acquisition module is further used to obtain the feedback result sent by the WiFi module; A determination module, configured to determine, according to the feedback result, a broadcast corpus corresponding to the feedback result; The control module is used to control the voice module of the smart home appliance to broadcast the broadcast corpus.

8. An offline voice broadcasting device, characterized in that: The device comprises: An acquisition module, used to acquire a natural language instruction sent by the control module of the smart home appliance; A processing module, used to generate corresponding request information according to the natural language instruction; A sending module, used for sending the request information to a cloud server; The acquisition module is also used to obtain the feedback result sent by the cloud server, and send the feedback result to the control module, so that the control module determines the corresponding broadcast corpus according to the feedback result, and controls the voice module to broadcast the broadcast corpus.

9. An offline voice broadcasting device, characterized in that: include: Memory; processor; Wherein, the memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the offline voice broadcast method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that: The computer storage medium stores computer execution instructions, which, when executed by a processor, are used to implement the offline voice broadcasting method according to any one of claims 1 to 7.

Images