Audio output method, output device, cooking equipment, server and storage medium

Abstract

The present invention proposes an audio output method, an output device, a cooking device, a server and a storage medium. The audio output method includes: in response to a voice control instruction, identifying the identity information corresponding to the voice control instruction and the semantic information in the voice control instruction; sending the identity information and the semantic information to the server so that the server can determine the first audio data according to the identity information and the semantic information; receiving and playing the first audio data from the server. The present invention sends the semantic information and the identity information corresponding to the voice control instruction issued by the user to the server, and the server can determine the corresponding first audio data according to the semantic information and the identity information. By outputting the first audio data from the server through the target device, it is possible to meet the user's personalized needs for the broadcast semantics while ensuring that the semantics corresponding to the voice broadcast by the target device meets the user's needs.

Description

Technical Field

[0001] The present invention belongs to the technical field of household appliances, and in particular, relates to an audio output method, an output device, a cooking device, a server and a storage medium. Background Art

[0002] With the development of artificial intelligence and the Internet of Things, more and more cooking devices have the ability to communicate with humans. In the prior art, fixed voice files are stored in the device in advance, and the voice files are played when the voice broadcast is needed, resulting in a single audio output of the voice broadcast, which cannot meet the personalized needs of users. Summary of the invention

[0003] The present invention aims to solve one of the technical problems existing in the prior art or related technology.

[0004] To this end, a first aspect of the present invention provides an audio output method.

[0005] A second aspect of the present invention provides an audio output method.

[0006] A third aspect of the present invention provides an audio output device.

[0007] A fourth aspect of the present invention provides an audio output device.

[0008] A fifth aspect of the present invention provides an audio output device.

[0009] A sixth aspect of the present invention provides a readable storage medium.

[0010] A seventh aspect of the present invention provides a cooking device.

[0011] An eighth aspect of the present invention provides a server.

[0012] In view of this, according to the first aspect of the present invention, an audio output method is proposed, including: responding to a voice control instruction, identifying identity identification information corresponding to the voice control instruction, and semantic information in the voice control instruction; sending the identity identification information and the semantic information to a server, so that the server determines the first audio data based on the identity identification information and the semantic information; receiving and playing the first audio data from the server.

[0013] The audio output method provided by the present invention can be applied to a user terminal or a cooking device, hereinafter referred to as a target device. A sound collection device is provided in the target device, and a voice control instruction sent by a user is received through the sound collection device. After receiving the voice control instruction of the user, the target device identifies the voice control instruction issued by the user. The target device includes a voiceprint recognition unit and a semantic recognition unit. The voiceprint recognition unit identifies the voiceprint features in the voice control instruction, and determines the identity information of the user who outputs the voice control instruction according to the voiceprint features. The target device identifies the semantic information in the voice control instruction through the semantic recognition unit. Among them, the identity information includes the user's registered account and other identification information that can determine the user's identity. The target device also includes a networked communication device, which establishes a communication connection with a server through the communication device, and sends the identified semantic information and identity information to the server. After receiving the semantic information and identity information, the server can determine the identity information of the user corresponding to the voice control instruction and the meaning corresponding to the voice control instruction. The server determines the first audio data in the server according to the user's identity information and the specific meaning of the voice control instruction, and transmits the first audio data back to the target device. The target device plays the received first audio data.

[0014] In some possible implementation schemes, multiple audio data are stored in the server, wherein the multiple audio data correspond to different user IDs. After receiving the semantic information and the user's identity information, the server can find the corresponding multiple audio data according to the user's identity information, and then filter the first audio data in the multiple audio data through the semantic information, so that the first audio data corresponds to the user's identity information and the semantic information. It can be understood that the multiple audio data corresponding to the user's identity information are data pre-stored in the server. Through the identity information, multiple audio data that meet the user's personalization can be found, and then the first audio data that the user needs to play is determined through the semantic information, so that the audio data played by the target device meets the user's needs while also meeting the user's personalized needs.

[0015] In some other possible implementation schemes, a plurality of script contents and a plurality of voiceprint features are stored in the server, wherein the plurality of voiceprint features correspond to the identity information of different users. After the server receives the semantic information and the identity information of the user, it can find the corresponding voiceprint feature according to the identity information of the user, and find the corresponding target script content in the plurality of script contents according to the semantic information. The server synthesizes the script content with the voiceprint feature to obtain the first audio data. Since the script content in the first audio data is consistent with the semantic information in the voice control instruction output by the user, and the voiceprint feature in the first audio data is consistent with the identity information of the user, the audio data played by the target device can meet the user's needs while also meeting the user's personalized needs. It can be understood that the voiceprint feature is the voiceprint feature pre-stored by the user in the server.

[0016] In the related art, cooking equipment or user terminals can output voice information during the cooking process to prompt the user of relevant operations during the cooking process, but the output voice information is the voice information pre-stored by the user in the device. The timbre (voiceprint features) of the voice information is relatively single and cannot meet the user's personalized needs.

[0017] The present invention sends semantic information and identity information corresponding to the voice control command issued by the user to the server, and the server can determine the corresponding first audio data according to the semantic information and identity information. The target device outputs the first audio data from the server, which can meet the user's personalized needs for the broadcast semantics while ensuring that the semantics corresponding to the voice broadcast by the target device meets the user's needs.

[0018] In addition, the audio output method in the above technical solution provided by the present invention may also have the following additional technical features:

[0019] In one possible design, the audio output method further includes: obtaining first audio data in response to an audio setting instruction; and sending the first audio data to a server so that the server binds the first audio data to the identity identification information.

[0020] In this design, before the user controls the target device through the voice control command, the user can execute the audio setting command on the target device, wherein the audio setting command includes the first audio data, and the first audio data includes the user's voice content. After the target device receives the first audio data including the user's voice content, it uploads the first audio data to the server. After the server receives the first audio data, it binds the first audio data with the user's identity information and stores it, so that after the server recognizes the user's identity information, it can find the corresponding first audio data according to the identity information.

[0021] Specifically, after receiving the audio setting instruction, the target device starts recording the user's voice content to obtain the first audio data, wherein the voice content is the voice broadcast in the subsequent use of the target device.

[0022] In some specific implementations, the target device is an oven, the user activates the voice broadcast recording function of the oven, the user searches for the method of roasting chicken wings, text content is displayed on the display screen of the oven, the user starts reading according to the text content, and the oven can record the user's reading content, and after the recording is completed, the first audio data is generated according to the recorded content, and the first audio data is uploaded to the server, and the server binds the first audio data with the text content and the user ID. After the user uses the oven to select the roast chicken wings function, the oven receives the first audio data returned from the server and plays the first audio data, so that the user can hear the previously recorded reading content during the cooking process.

[0023] The present invention records the user's voice through a target device to obtain first audio data, and uploads the first audio data to a server. When the user needs to broadcast the voice through the target device, the target device can interact with the server to play the first audio data recorded in advance by the user, thereby realizing the user's personalized setting of the target device's broadcast voice.

[0024] In one possible design, the audio output method also includes: obtaining second audio data in response to an audio setting instruction; extracting a first voiceprint feature of the second audio data; and sending the first voiceprint feature to a server so that the server can bind the identity recognition information to the first voiceprint feature.

[0025] In this design, before the user controls the target device through the voice control command, the user can execute the audio setting command on the target device, wherein the audio setting command includes the user's second audio data, and the second audio data includes the user's voice content. After the target device receives the second audio data including the user's voice content, the target device can extract the first voiceprint feature in the voice content, and upload the first voiceprint feature to the server. After the server receives the first voiceprint feature, it binds and stores the first voiceprint feature with the user's identity information, so that after the server recognizes the user's identity information, it can synthesize the first audio data according to the first voiceprint feature and the script content, so that the timbre of the first audio data when it is played is consistent with the first voiceprint feature pre-stored in the server by the user, so that the target device can perform personalized voice broadcasting.

[0026] Specifically, after receiving the audio setting instruction, the target device starts to receive the user's voice content, identifies the first voiceprint feature of the user's voice content during the receiving process, and after identifying the first voiceprint feature, uploads the first voiceprint feature and the user's identity information to the server at the same time, so that the server binds the two. In the process of the user subsequently controlling the target device to perform voice broadcast, the target device can request the server for the first audio data synthesized by the first voiceprint feature.

[0027] The received first audio data is synthesized according to the first voiceprint feature.

[0028] It is worth noting that the user can bind the identity recognition information to multiple first voiceprint features, that is, the identity recognition information of each user in the server is bound to multiple different first voiceprint features.

[0029] In some possible implementation modes, the server finds multiple first voiceprint features through identity recognition information, and randomly selects one of the multiple first voiceprint features to be synthesized with the script content.

[0030] The present invention extracts the first voiceprint feature in the user's voice content through the target device, and binds the first voiceprint feature with the user's identity recognition information in the server, so that the user can query the corresponding first voiceprint feature through the identity recognition information, and synthesize the first voiceprint feature with the script content, so that when the user needs to broadcast the voice through the target device, the target device can interact with the server and play the first audio data synthesized by the first voiceprint feature pre-stored by the user, thereby realizing the user's personalized setting of the target device broadcast voice.

[0031] In one possible design, identifying the identity recognition information corresponding to the voice control instruction includes: extracting a second voiceprint feature in the voice control instruction; and searching for the identity recognition information according to the second voiceprint feature.

[0032] In this design, after receiving the voice control command, the target device recognizes the second voiceprint feature in the voice control command through the voiceprint recognition unit, wherein the voiceprint recognition unit stores a recognition model trained in advance, and the second voiceprint feature can be recognized by inputting the voice control command into the recognition model. The target device also stores the correspondence between the user's identity information and the second voiceprint feature, and the user's identity information can be queried based on the recognized second voiceprint feature and the correspondence.

[0033] Specifically, when the user registers an account through the target device, the target device prompts the user to enter the second voiceprint feature. After the user enters the second voiceprint feature, the target device binds the second voiceprint feature with the registered account information, wherein the account information can be used as the user's identity identification information.

[0034] The present invention extracts the second voiceprint feature in the received voice control command through the target device, and searches for the identity recognition information corresponding to the second voiceprint feature according to the pre-stored correspondence relationship. In the case of no need for the user to manually input the identity recognition information, the accuracy of the extracted user identity recognition information is also guaranteed.

[0035] In one possible design, identifying the identity information corresponding to the voice control instruction includes: collecting image data, where the time of collecting the image data corresponds to the time of receiving the voice control instruction; and determining the identity information based on the image data.

[0036] In this design, the target device includes a user terminal and / or a cooking device, wherein the user terminal includes a mobile phone, a computer, a tablet computer, a smart speaker, etc. The cooking device includes an oven, a steamer, an electric rice cooker, a steam-bake combination machine, etc. An image acquisition device is provided on the user terminal and / or the cooking device.

[0037] When the target device receives the voice control command, the image acquisition device of the target device is called, image data with the user's facial features are acquired by the image acquisition device, and the user's identity information is determined by identifying the facial features in the image data.

[0038] Specifically, when a user registers an account through a target device, the target device prompts the user to enter facial features. After the user enters the facial features, the target device binds the facial features with the registered account information, wherein the account information can be used as the user's identity identification information.

[0039] The present invention collects image data during the voice control instruction process through the image acquisition device of the target device, and can find the identity recognition information corresponding to the image data by identifying the image features in the image data. Without the need for the user to manually input the identity recognition information, the accuracy of extracting the user's identity recognition information is also guaranteed.

[0040] In one possible design, the audio output method is applied to a cooking device, and before receiving and playing the first audio data from the server, it also includes: obtaining a first cooking parameter of the cooking device; sending the first cooking parameter to the server, so that the server determines the sending time of the first audio data according to the cooking parameter, and sends the first audio data to the cooking device according to the sending time; and playing the received first audio data.

[0041] In this design, when the target device is a cooking device, during the operation of the cooking device, a first cooking parameter of the cooking device is determined and uploaded to the server. The server can determine the playback time of the first audio data based on the first cooking parameter uploaded by the cooking device. The cooking device plays the first audio data immediately after receiving the first audio data. Therefore, the playback time is the sending time of the first audio data, and the first audio data is transmitted back to the cooking device according to the sending time so that the cooking device can play the first audio data.

[0042] Specifically, when the cooking device is cooking according to the recipe, the server sends the first audio data to the cooking device according to the cooking progress, so that the cooking device can play the first audio data to prompt the user to operate. For example: roasting chicken wings in an oven, before the oven receives the first audio data, the cavity temperature of the oven is obtained, and the cavity temperature is uploaded to the server in real time. After the server receives the cavity temperature, it determines whether the cavity temperature reaches the preheating temperature. If the preheating temperature is reached, "preheating is completed, put in the roasted wings" is sent back to the cooking device, that is, the first audio data is sent back to the cooking device, and the cooking device plays the first audio data after receiving the first audio data, thereby achieving the effect of real-time playback of recipes.

[0043] The present invention connects a cooking device to a server, and while the cooking device is cooking according to a recipe, a first cooking parameter of the cooking device is uploaded to the server. The server can transmit first audio data back to the cooking device in real time according to the first cooking parameter, so that the cooking device can play the first audio data according to the actual cooking status, improves the real-time performance of the first audio data playback process, and enables the user to cook according to the first audio data played by the target device.

[0044] In one possible design, the audio output method is applied to a cooking device to receive and play first audio data from a server, including: receiving the first audio data and temporarily storing the first audio data in a local storage area; obtaining a second cooking parameter of the cooking device; determining a playback time of the first audio data based on the second cooking parameter; and playing the first audio data according to the playback time.

[0045] In this design, when the target device is a cooking device, the cooking device receives the first audio data sent back by the server and temporarily stores the first audio data. A second cooking parameter is obtained during the operation of the cooking device, the cooking progress of the cooking device can be determined according to the second cooking parameter, the play time of the first audio data is determined according to the cooking progress, and the first audio data is cooked according to the play time.

[0046] Specifically, the cooking device temporarily stores the first audio data from the server, and plays the temporarily stored first audio data according to the cooking progress while the cooking device is cooking according to the recipe. For example, when roasting chicken wings in an oven, the temperature in the oven cavity is obtained, and the cavity temperature is uploaded to the server in real time to determine whether the cavity temperature has reached the preheating temperature. When the preheating temperature is reached, the cooking device plays "preheating is complete, add roasted wings". After the cooking device receives the first audio data, the first audio data is temporarily stored, and the first audio data is played according to the actual cooking progress, thereby achieving the effect of playing recipes in real time.

[0047] The present invention temporarily stores the received first audio data, detects the cooking process of the cooking device in real time, and controls the cooking device to play the first audio data according to the cooking process. This enables the cooking device to play the first audio data according to the actual cooking state, improves the real-time performance of the first audio data playing process, and enables the user to cook according to the first audio data played by the target device.

[0048] According to a second aspect of the present invention, an audio output method is proposed, comprising: receiving identity recognition information and semantic information of a target device; determining first audio data based on the identity recognition information and the semantic information; and sending the first audio data to the target device so that the target device plays the first audio data.

[0049] The audio output method provided by the present invention is applied to a server. After receiving semantic information and identity recognition information from a target device, the server can determine the identity information of the user corresponding to the voice control instruction and the meaning corresponding to the voice control instruction. The server determines the first audio data in the server according to the identity information of the user and the specific meaning of the voice control instruction, and transmits the first audio data back to the target device. The target device plays the received first audio data.

[0050] Among them, the target device is provided with a sound collection device, and the voice control command sent by the user is received through the sound collection device. After receiving the voice control command from the user, the target device identifies the voice control command issued by the user. The target device includes a voiceprint recognition unit and a semantic recognition unit. The voiceprint recognition unit identifies the voiceprint features in the voice control command, and determines the identity information of the user who outputs the voice control command according to the voiceprint features. The target device identifies the semantic information in the voice control command through the semantic recognition unit. Among them, the identity information includes the user's registered account and other identification information that can determine the user's identity. The target device also includes a networked communication device, which establishes a communication connection with the server through the communication device, and sends the identified semantic information and identity information to the server.

[0051] In some possible implementation schemes, multiple audio data are stored in the server, wherein the multiple audio data correspond to different user IDs. After receiving the semantic information and the user's identity information, the server can find the corresponding multiple audio data according to the user's identity information, and then filter the first audio data in the multiple audio data through the semantic information, so that the first audio data corresponds to the user's identity information and the semantic information. It can be understood that the multiple audio data corresponding to the user's identity information are data pre-stored in the server. Through the identity information, multiple audio data that meet the user's personalization can be found, and then the first audio data that the user needs to play is determined through the semantic information, so that the audio data played by the target device meets the user's needs while also meeting the user's personalized needs.

[0052] In some other possible implementation schemes, a plurality of script contents and a plurality of voiceprint features are stored in the server, wherein the plurality of voiceprint features correspond to the identity information of different users. After the server receives the semantic information and the identity information of the user, it can find the corresponding voiceprint feature according to the identity information of the user, and find the corresponding target script content in the plurality of script contents according to the semantic information. The server synthesizes the script content with the voiceprint feature to obtain the first audio data. Since the script content in the first audio data is consistent with the semantic information in the voice control instruction output by the user, and the voiceprint feature in the first audio data is consistent with the identity information of the user, the audio data played by the target device can meet the user's needs while also meeting the user's personalized needs. It can be understood that the voiceprint feature is the voiceprint feature pre-stored by the user in the server.

[0053] In the related art, cooking equipment or user terminals can output voice information during the cooking process to prompt the user of relevant operations during the cooking process, but the output voice information is the voice information pre-stored by the user in the device. The timbre (voiceprint features) of the voice information is relatively single and cannot meet the user's personalized needs.

[0054] The present invention sends semantic information and identity information corresponding to the voice control command issued by the user to the server, and the server can determine the corresponding first audio data according to the semantic information and identity information. The target device outputs the first audio data from the server, which can meet the user's personalized needs for the broadcast semantics while ensuring that the semantics corresponding to the voice broadcast by the target device meets the user's needs.

[0055] In addition, the audio output method in the above technical solution provided by the present invention may also have the following additional technical features:

[0056] In one possible design, the audio output method further includes: receiving first audio data from a target device; and binding the first audio data with identity recognition information.

[0057] In this design, before the user controls the target device through the voice control command, the user can execute the audio setting command on the target device, wherein the audio setting command includes the first audio data, and the first audio data includes the user's voice content. After the target device receives the first audio data including the user's voice content, it uploads the first audio data to the server. After the server receives the first audio data, it binds the first audio data with the user's identity information and stores it, so that after the server recognizes the user's identity information, it can find the corresponding first audio data according to the identity information.

[0058] Specifically, after receiving the audio setting instruction, the target device starts recording the user's voice content to obtain the first audio data, wherein the voice content is the voice broadcast in the subsequent use of the target device.

[0059] In some specific implementations, the target device is an oven, the user activates the voice broadcast recording function of the oven, the user searches for the method of roasting chicken wings, text content is displayed on the display screen of the oven, the user starts reading according to the text content, and the oven can record the user's reading content, and after the recording is completed, the first audio data is generated according to the recorded content, and the first audio data is uploaded to the server, and the server binds the first audio data with the text content and the user ID. After the user uses the oven to select the roast chicken wings function, the oven receives the first audio data returned from the server and plays the first audio data, so that the user can hear the previously recorded reading content during the cooking process.

[0060] The present invention records the user's voice through a target device to obtain first audio data, and uploads the first audio data to a server. When the user needs to broadcast the voice through the target device, the target device can interact with the server to play the first audio data recorded in advance by the user, thereby realizing the user's personalized setting of the target device's broadcast voice.

[0061] In one possible design, the audio output method further includes: receiving a first voiceprint feature from a target device; and binding the first voiceprint feature to identity recognition information.

[0062] In this design, before the user controls the target device through the voice control command, the user can execute the audio setting command on the target device, wherein the audio setting command includes the user's second audio data, and the second audio data includes the user's voice content. After the target device receives the second audio data including the user's voice content, the target device can extract the first voiceprint feature in the voice content, and upload the first voiceprint feature to the server. After the server receives the first voiceprint feature, it binds and stores the first voiceprint feature with the user's identity information, so that after the server recognizes the user's identity information, it can synthesize the first audio data according to the first voiceprint feature and the script content, so that the timbre of the first audio data when it is played is consistent with the first voiceprint feature pre-stored in the server by the user, so that the target device can perform personalized voice broadcasting.

[0063] Specifically, after receiving the audio setting instruction, the target device starts to receive the user's voice content, identifies the first voiceprint feature of the user's voice content during the receiving process, and after identifying the first voiceprint feature, uploads the first voiceprint feature and the user's identity information to the server at the same time, so that the server binds the two. In the process of the user subsequently controlling the target device to perform voice broadcast, the target device can request the server for the first audio data synthesized by the first voiceprint feature.

[0064] The received first audio data is synthesized according to the first voiceprint feature.

[0065] It is worth noting that the user can bind the identity recognition information to multiple first voiceprint features, that is, the identity recognition information of each user in the server is bound to multiple different first voiceprint features.

[0066] In some possible implementation modes, the server finds multiple first voiceprint features through identity recognition information, and randomly selects one of the multiple first voiceprint features to be synthesized with the script content.

[0067] The present invention extracts the first voiceprint feature in the user's voice content through the target device, and binds the first voiceprint feature with the user's identity recognition information in the server, so that the user can query the corresponding first voiceprint feature through the identity recognition information, and synthesize the first voiceprint feature with the script content, so that when the user needs to broadcast the voice through the target device, the target device can interact with the server and play the first audio data synthesized by the first voiceprint feature pre-stored by the user, thereby realizing the user's personalized setting of the target device broadcast voice.

[0068] In one possible design, determining the first audio data based on the identity recognition information and the semantic information includes: searching for the first voiceprint feature based on the identity recognition information; searching for script content based on the semantic information; and synthesizing the first audio data based on the script content and the first voiceprint feature.

[0069] In this design, after the server receives the semantic information and identity identification information sent by the target device, the server finds the corresponding first voiceprint feature based on the identity identification information. At the same time, the server also finds the corresponding script content based on the semantic information. After the server finds the first voiceprint feature and the script content, the server obtains the first audio data by synthesizing the first voiceprint feature and the script content.

[0070] The server in the present invention can search for the corresponding first voiceprint feature and script content according to the semantic information and identity recognition information sent by the target device, and obtain the corresponding first audio data by synthesizing the first voiceprint feature and the script content.

[0071] In one possible design, before sending the first audio data to the target device, it includes: receiving a first cooking parameter from the target device; determining a sending time of the first audio data according to the first cooking parameter; and sending the first audio data to the target device according to the sending time, so that the target device plays the received first audio data.

[0072] In this design, when the target device is a cooking device, during the operation of the cooking device, a first cooking parameter of the cooking device is determined and uploaded to the server. The server can determine the playback time of the first audio data based on the first cooking parameter uploaded by the cooking device. The cooking device plays the first audio data immediately after receiving the first audio data. Therefore, the playback time is the sending time of the first audio data, and the first audio data is transmitted back to the cooking device according to the sending time so that the cooking device can play the first audio data.

[0073] Specifically, when the cooking device is cooking according to the recipe, the server sends the first audio data to the cooking device according to the cooking progress, so that the cooking device can play the first audio data to prompt the user to operate. For example: roasting chicken wings in an oven, before the oven receives the first audio data, the cavity temperature of the oven is obtained, and the cavity temperature is uploaded to the server in real time. After the server receives the cavity temperature, it determines whether the cavity temperature reaches the preheating temperature. If the preheating temperature is reached, "preheating is completed, put in the roasted wings" is sent back to the cooking device, that is, the first audio data is sent back to the cooking device, and the cooking device plays the first audio data after receiving the first audio data, thereby achieving the effect of real-time playback of recipes.

[0074] The present invention connects a cooking device to a server, and while the cooking device is cooking according to a recipe, a first cooking parameter of the cooking device is uploaded to the server. The server can transmit first audio data back to the cooking device in real time according to the first cooking parameter, so that the cooking device can play the first audio data according to the actual cooking status, improves the real-time performance of the first audio data playback process, and enables the user to cook according to the first audio data played by the target device.

[0075] According to a third aspect of the present invention, an audio output device is proposed, including: a recognition module, used to respond to a voice control instruction, identify identity recognition information corresponding to the voice control instruction, and semantic information in the voice control instruction; a first sending module, used to send the identity recognition information and the semantic information to a server, so that the server determines the first audio data based on the identity recognition information and the semantic information; a first receiving module, used to receive the first audio data from the server; and a playing module, used to play the first audio data.

[0076] The audio output device provided by the present invention can be applied to a user terminal or a cooking device, hereinafter referred to as a target device. A sound collection device is provided in the target device, and a voice control instruction sent by a user is received through the sound collection device. After receiving the voice control instruction of the user, the target device identifies the voice control instruction issued by the user. The target device includes a voiceprint recognition unit and a semantic recognition unit. The voiceprint recognition unit identifies the voiceprint features in the voice control instruction, and determines the identity information of the user who outputs the voice control instruction according to the voiceprint features. The target device identifies the semantic information in the voice control instruction through the semantic recognition unit. Among them, the identity information includes the user's registered account and other identification information that can determine the user's identity. The target device also includes a networked communication device, which establishes a communication connection with a server through the communication device, and sends the identified semantic information and identity information to the server. After receiving the semantic information and identity information, the server can determine the identity information of the user corresponding to the voice control instruction and the meaning corresponding to the voice control instruction. The server determines the first audio data in the server according to the user's identity information and the specific meaning of the voice control instruction, and transmits the first audio data back to the target device. The target device plays the received first audio data.

[0077] In some possible implementation schemes, multiple audio data are stored in the server, wherein the multiple audio data correspond to different user IDs. After receiving the semantic information and the user's identity information, the server can find the corresponding multiple audio data according to the user's identity information, and then filter the first audio data in the multiple audio data through the semantic information, so that the first audio data corresponds to the user's identity information and the semantic information. It can be understood that the multiple audio data corresponding to the user's identity information are data pre-stored in the server. Through the identity information, multiple audio data that meet the user's personalization can be found, and then the first audio data that the user needs to play is determined through the semantic information, so that the audio data played by the target device meets the user's needs while also meeting the user's personalized needs.

[0078] In some other possible implementation schemes, a plurality of script contents and a plurality of voiceprint features are stored in the server, wherein the plurality of voiceprint features correspond to the identity information of different users. After the server receives the semantic information and the identity information of the user, it can find the corresponding voiceprint feature according to the identity information of the user, and find the corresponding target script content in the plurality of script contents according to the semantic information. The server synthesizes the script content with the voiceprint feature to obtain the first audio data. Since the script content in the first audio data is consistent with the semantic information in the voice control instruction output by the user, and the voiceprint feature in the first audio data is consistent with the identity information of the user, the audio data played by the target device can meet the user's needs while also meeting the user's personalized needs. It can be understood that the voiceprint feature is the voiceprint feature pre-stored by the user in the server.

[0079] In the related art, cooking equipment or user terminals can output voice information during the cooking process to prompt the user of relevant operations during the cooking process, but the output voice information is the voice information pre-stored by the user in the device. The timbre (voiceprint features) of the voice information is relatively single and cannot meet the user's personalized needs.

[0080] The present invention sends semantic information and identity information corresponding to the voice control command issued by the user to the server, and the server can determine the corresponding first audio data according to the semantic information and identity information. The target device outputs the first audio data from the server, which can meet the user's personalized needs for the broadcast semantics while ensuring that the semantics corresponding to the voice broadcast by the target device meets the user's needs.

[0081] According to a fourth aspect of the present invention, an audio output device is proposed, comprising: a second receiving module, used to receive identity recognition information and semantic information of a target device; a determination module, used to determine first audio data based on the identity recognition information and semantic information; a second sending module, used to send the first audio data to the target device, so that the target device plays the first audio data.

[0082] The audio output device provided by the present invention is applied to a server. After receiving the semantic information and identity recognition information from the target device, the server can determine the identity information of the user corresponding to the voice control instruction and the meaning corresponding to the voice control instruction. The server determines the first audio data in the server according to the identity information of the user and the specific meaning of the voice control instruction, and transmits the first audio data back to the target device. The target device plays the received first audio data.

[0083] Among them, the target device is provided with a sound collection device, and the voice control command sent by the user is received through the sound collection device. After receiving the voice control command from the user, the target device identifies the voice control command issued by the user. The target device includes a voiceprint recognition unit and a semantic recognition unit. The voiceprint recognition unit identifies the voiceprint features in the voice control command, and determines the identity information of the user who outputs the voice control command according to the voiceprint features. The target device identifies the semantic information in the voice control command through the semantic recognition unit. Among them, the identity information includes the user's registered account and other identification information that can determine the user's identity. The target device also includes a networked communication device, which establishes a communication connection with the server through the communication device, and sends the identified semantic information and identity information to the server.

[0084] In some possible implementation schemes, multiple audio data are stored in the server, wherein the multiple audio data correspond to different user IDs. After receiving the semantic information and the user's identity information, the server can find the corresponding multiple audio data according to the user's identity information, and then filter the first audio data in the multiple audio data through the semantic information, so that the first audio data corresponds to the user's identity information and the semantic information. It can be understood that the multiple audio data corresponding to the user's identity information are data pre-stored in the server. Through the identity information, multiple audio data that meet the user's personalization can be found, and then the first audio data that the user needs to play is determined through the semantic information, so that the audio data played by the target device meets the user's needs while also meeting the user's personalized needs.

[0085] In some other possible implementation schemes, a plurality of script contents and a plurality of voiceprint features are stored in the server, wherein the plurality of voiceprint features correspond to the identity information of different users. After the server receives the semantic information and the identity information of the user, it can find the corresponding voiceprint feature according to the identity information of the user, and find the corresponding target script content in the plurality of script contents according to the semantic information. The server synthesizes the script content with the voiceprint feature to obtain the first audio data. Since the script content in the first audio data is consistent with the semantic information in the voice control instruction output by the user, and the voiceprint feature in the first audio data is consistent with the identity information of the user, the audio data played by the target device can meet the user's needs while also meeting the user's personalized needs. It can be understood that the voiceprint feature is the voiceprint feature pre-stored by the user in the server.

[0086] In the related art, cooking equipment or user terminals can output voice information during the cooking process to prompt the user of relevant operations during the cooking process, but the output voice information is the voice information pre-stored by the user in the device. The timbre (voiceprint features) of the voice information is relatively single and cannot meet the user's personalized needs.

[0087] The present invention sends semantic information and identity information corresponding to the voice control command issued by the user to the server, and the server can determine the corresponding first audio data according to the semantic information and identity information. The target device outputs the first audio data from the server, which can meet the user's personalized needs for the broadcast semantics while ensuring that the semantics corresponding to the voice broadcast by the target device meets the user's needs.

[0088] According to the fifth aspect of the present invention, an audio output device is proposed, comprising: a memory for storing programs or instructions; a processor for implementing the audio output method in the first and second aspects when executing the programs or instructions, thereby having all the beneficial effects of the audio output method in the first and second aspects.

[0089] According to the sixth aspect of the present invention, a readable storage medium is proposed, on which a program or instruction is stored. When the program or instruction is executed by a processor, the audio output method as described in the first and second aspects above is implemented, thereby having all the beneficial effects of the audio output method as described in the first and second aspects above.

[0090] According to the seventh aspect of the present invention, a cooking device is proposed, comprising: an audio output device as described in the third and fifth aspects above; and / or a readable storage medium as described in the sixth aspect above, thereby having all the beneficial effects of the audio output device as described in the third and fifth aspects above and / or the readable storage medium as described in the sixth aspect above.

[0091] According to the eighth aspect of the present invention, a server is proposed, comprising: an audio output device as described in the fourth and fifth aspects above; and / or a readable storage medium as described in the sixth aspect above, thereby having all the beneficial effects of the audio output device as described in the fourth and fifth aspects above and / or the readable storage medium as described in the sixth aspect above.

[0092] Additional aspects and advantages of the present invention will become apparent from the following description or may be learned by practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0093] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0094] Figure 1 One of the flowchart diagrams of the audio output method in the first embodiment of the present invention is shown;

[0095] Figure 2 A second flow chart of the audio output method in the first embodiment of the present invention is shown;

[0096] Figure 3 The third flowchart of the audio output method in the first embodiment of the present invention is shown;

[0097] Figure 4 A fourth flowchart diagram of the audio output method in the first embodiment of the present invention is shown;

[0098] Figure 5 FIG5 shows a fifth flow chart of the audio output method in the first embodiment of the present invention;

[0099] Figure 6 FIG6 shows a sixth flow chart of the audio output method in the first embodiment of the present invention;

[0100] Figure 7 FIG7 shows a seventh flow chart of the audio output method in the first embodiment of the present invention;

[0101] Figure 8 FIG. 1 shows a flow chart of an audio output method in a second embodiment of the present invention;

[0102] Fig. 9 A second flowchart diagram of the audio output method in the second embodiment of the present invention is shown;

[0103] Fig.10 A third flowchart diagram of the audio output method in the second embodiment of the present invention is shown;

[0104] Fig.11A fourth flowchart diagram of the audio output method in the second embodiment of the present invention is shown;

[0105] Fig.12 FIG5 shows a fifth flow chart of the audio output method in the second embodiment of the present invention;

[0106] Fig.13 shows a structural block diagram of an audio output device in a third embodiment of the present invention;

[0107] Fig.14 shows a structural block diagram of an audio output device in a fourth embodiment of the present invention;

[0108] Fig.15 A structural block diagram of an audio output device in a fifth embodiment of the present invention is shown. DETAILED DESCRIPTION

[0109] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0110] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0111] Refer to the following Figures 1 to 15 An audio output method, an audio output device, a cooking device, a server, and a readable storage medium according to some embodiments of the present invention are described.

[0112] Embodiment 1:

[0113] like Figure 1 As shown, a first embodiment of the present invention provides an audio output method, comprising:

[0114] Step 102, receiving a voice control instruction;

[0115] Step 104, identifying the identity information and semantic information corresponding to the voice control instruction;

[0116] Step 106, sending semantic information and identity information to the server;

[0117] Step 108: Receive the first audio data sent by the server, and play the first audio data.

[0118] The audio output method provided in this embodiment can be applied to a user terminal or a cooking device, hereinafter referred to as a target device. A sound collection device is provided in the target device, and a voice control instruction sent by a user is received through the sound collection device. After receiving the voice control instruction of the user, the target device identifies the voice control instruction issued by the user. The target device includes a voiceprint recognition unit and a semantic recognition unit. The voiceprint recognition unit identifies the voiceprint features in the voice control instruction, and determines the identity information of the user who outputs the voice control instruction according to the voiceprint features. The target device identifies the semantic information in the voice control instruction through the semantic recognition unit. Among them, the identity information includes the user's registered account and other identification information that can determine the user's identity. The target device also includes a networked communication device, which establishes a communication connection with the server through the communication device, and sends the identified semantic information and identity information to the server. After receiving the semantic information and identity information, the server can determine the identity information of the user corresponding to the voice control instruction and the meaning corresponding to the voice control instruction. The server determines the first audio data in the server according to the user's identity information and the specific meaning of the voice control instruction, and transmits the first audio data back to the target device. The target device plays the received first audio data.

[0119] In some possible implementation schemes, multiple audio data are stored in the server, wherein the multiple audio data correspond to different user IDs. After receiving the semantic information and the user's identity information, the server can find the corresponding multiple audio data according to the user's identity information, and then filter the first audio data in the multiple audio data through the semantic information, so that the first audio data corresponds to the user's identity information and the semantic information. It can be understood that the multiple audio data corresponding to the user's identity information are data pre-stored in the server. Through the identity information, multiple audio data that meet the user's personalization can be found, and then the first audio data that the user needs to play is determined through the semantic information, so that the audio data played by the target device meets the user's needs while also meeting the user's personalized needs.

[0120] In some other possible implementation schemes, a plurality of script contents and a plurality of voiceprint features are stored in the server, wherein the plurality of voiceprint features correspond to the identity information of different users. After the server receives the semantic information and the identity information of the user, it can find the corresponding voiceprint feature according to the identity information of the user, and find the corresponding target script content in the plurality of script contents according to the semantic information. The server synthesizes the script content with the voiceprint feature to obtain the first audio data. Since the script content in the first audio data is consistent with the semantic information in the voice control instruction output by the user, and the voiceprint feature in the first audio data is consistent with the identity information of the user, the audio data played by the target device can meet the user's needs while also meeting the user's personalized needs. It can be understood that the voiceprint feature is the voiceprint feature pre-stored by the user in the server.

[0121] In the related art, cooking equipment or user terminals can output voice information during the cooking process to prompt the user of relevant operations during the cooking process, but the output voice information is the voice information pre-stored by the user in the device. The timbre (voiceprint features) of the voice information is relatively single and cannot meet the user's personalized needs.

[0122] The present invention sends semantic information and identity information corresponding to the voice control command issued by the user to the server, and the server can determine the corresponding first audio data according to the semantic information and identity information. The target device outputs the first audio data from the server, which can meet the user's personalized needs for the broadcast semantics while ensuring that the semantics corresponding to the voice broadcast by the target device meets the user's needs.

[0123] like Figure 2 As shown, in any of the above embodiments, the audio output method further includes:

[0124] Step 202, when receiving the audio setting instruction, collecting first audio data;

[0125] Step 204: Send the first audio data to the server.

[0126] In this embodiment, before the user controls the target device through the voice control instruction, the user can execute the audio setting instruction on the target device, wherein the audio setting instruction includes the first audio data, and the first audio data includes the user's voice content. After the target device receives the first audio data including the user's voice content, it uploads the first audio data to the server. After the server receives the first audio data, it binds the first audio data with the user's identity identification information and stores it, so that after the server recognizes the user's identity identification information, it can find the corresponding first audio data according to the identity identification information.

[0127] Specifically, after receiving the audio setting instruction, the target device starts recording the user's voice content to obtain the first audio data, wherein the voice content is the voice broadcast in the subsequent use of the target device.

[0128] In some specific implementations, the target device is an oven, the user activates the voice broadcast recording function of the oven, the user searches for the method of roasting chicken wings, text content is displayed on the display screen of the oven, the user starts reading according to the text content, and the oven can record the user's reading content, and after the recording is completed, the first audio data is generated according to the recorded content, and the first audio data is uploaded to the server, and the server binds the first audio data with the text content and the user ID. After the user uses the oven to select the roast chicken wings function, the oven receives the first audio data returned from the server and plays the first audio data, so that the user can hear the previously recorded reading content during the cooking process.

[0129] The present invention records the user's voice through a target device to obtain first audio data, and uploads the first audio data to a server. When the user needs to broadcast the voice through the target device, the target device can interact with the server to play the first audio data recorded in advance by the user, thereby realizing the user's personalized setting of the target device's broadcast voice.

[0130] like Figure 3 As shown, in any of the above embodiments, the audio output method further includes:

[0131] Step 302, when receiving the audio setting instruction, collecting second audio data;

[0132] Step 304, extracting the first voiceprint feature of the second audio data;

[0133] Step 306: Send the first voiceprint feature to the server.

[0134] In this embodiment, before the user controls the target device through the voice control instruction, the user can execute the audio setting instruction on the target device, wherein the audio setting instruction includes the user's second audio data, and the second audio data includes the user's voice content. After the target device receives the second audio data including the user's voice content, the target device can extract the first voiceprint feature in the voice content, upload the first voiceprint feature to the server, and after the server receives the first voiceprint feature, it binds and stores the first voiceprint feature with the user's identity information, so that after the server recognizes the user's identity information, it can synthesize the first audio data according to the first voiceprint feature and the script content, so that the timbre of the first audio data when it is played is consistent with the first voiceprint feature of the user pre-stored in the server, so that the target device can perform personalized voice broadcasting.

[0135] Specifically, after receiving the audio setting instruction, the target device starts to receive the user's voice content, identifies the first voiceprint feature of the user's voice content during the receiving process, and after identifying the first voiceprint feature, uploads the first voiceprint feature and the user's identity information to the server at the same time, so that the server binds the two. In the process of the user subsequently controlling the target device to perform voice broadcast, the target device can request the server for the first audio data synthesized by the first voiceprint feature.

[0136] The received first audio data is synthesized according to the first voiceprint feature.

[0137] It is worth noting that the user can bind the identity recognition information to multiple first voiceprint features, that is, the identity recognition information of each user in the server is bound to multiple different first voiceprint features.

[0138] In some possible implementation modes, the server finds multiple first voiceprint features through identity recognition information, and randomly selects one of the multiple first voiceprint features to be synthesized with the script content.

[0139] The present invention extracts the first voiceprint feature in the user's voice content through the target device, and binds the first voiceprint feature with the user's identity recognition information in the server, so that the user can query the corresponding first voiceprint feature through the identity recognition information, and synthesize the first voiceprint feature with the script content, so that when the user needs to broadcast the voice through the target device, the target device can interact with the server and play the first audio data synthesized by the first voiceprint feature pre-stored by the user, thereby realizing the user's personalized setting of the target device broadcast voice.

[0140] like Figure 4 As shown, in any of the above embodiments, the step of identifying the identity information corresponding to the voice control instruction includes:

[0141] Step 402, extracting the second voiceprint feature in the voice control instruction;

[0142] Step 404: Search for identity recognition information using the second voiceprint feature according to the corresponding relationship.

[0143] In this embodiment, after receiving the voice control instruction, the target device recognizes the second voiceprint feature in the voice control instruction through the voiceprint recognition unit, wherein the voiceprint recognition unit stores a recognition model trained in advance, and the second voiceprint feature can be recognized by inputting the voice control instruction into the recognition model. The target device also stores the correspondence between the user's identity information and the second voiceprint feature, and the user's identity information can be queried based on the recognized second voiceprint feature and the correspondence.

[0144] Specifically, when the user registers an account through the target device, the target device prompts the user to enter the second voiceprint feature. After the user enters the second voiceprint feature, the target device binds the second voiceprint feature with the registered account information, wherein the account information can be used as the user's identity identification information.

[0145] The present invention extracts the second voiceprint feature in the received voice control command through the target device, and searches for the identity recognition information corresponding to the second voiceprint feature according to the pre-stored correspondence relationship. In the case of no need for the user to manually input the identity recognition information, the accuracy of the extracted user identity recognition information is also guaranteed.

[0146] like Figure 5 As shown, in any of the above embodiments, the step of identifying the identity information corresponding to the voice control instruction includes:

[0147] Step 502, controlling the image acquisition device to acquire image data;

[0148] The receiving time of the voice control command corresponds to the collecting time of the image data;

[0149] Step 504, searching for identity information based on the corresponding image data.

[0150] In this embodiment, the target device includes a user terminal and / or a cooking device, wherein the user terminal includes a mobile phone, a computer, a tablet computer, a smart speaker, etc. The cooking device includes an oven, a steamer, an electric rice cooker, a steam-bake combination machine, etc. An image acquisition device is provided on the user terminal and / or the cooking device.

[0151] When the target device receives the voice control command, the image acquisition device of the target device is called, image data with the user's facial features are acquired by the image acquisition device, and the user's identity information is determined by identifying the facial features in the image data.

[0152] Specifically, when a user registers an account through a target device, the target device prompts the user to enter facial features. After the user enters the facial features, the target device binds the facial features with the registered account information, wherein the account information can be used as the user's identity identification information.

[0153] The present invention collects image data during the voice control instruction process through the image acquisition device of the target device, and can find the identity recognition information corresponding to the image data by identifying the image features in the image data. Without the need for the user to manually input the identity recognition information, the accuracy of extracting the user's identity recognition information is also guaranteed.

[0154] like Figure 6 As shown, in any of the above embodiments, the audio output method is applied to a cooking device, and before receiving the first audio data sent by the server, it also includes:

[0155] Step 602, obtaining a first cooking parameter in a cooking device;

[0156] Step 604, sending the first cooking parameter to the server;

[0157] The server determines a sending time corresponding to the first audio data according to the first cooking parameter, and sends the first audio data to the cooking device according to the sending time.

[0158] Step 606: play the received first audio data.

[0159] In this embodiment, when the target device is a cooking device, during the operation of the cooking device, a first cooking parameter of the cooking device is determined and uploaded to the server. The server can determine the playback time of the first audio data based on the first cooking parameter uploaded by the cooking device. The cooking device plays the first audio data immediately after receiving the first audio data. Therefore, the playback time is the sending time of the first audio data, and the first audio data is transmitted back to the cooking device according to the sending time so that the cooking device can play the first audio data.

[0160] Specifically, when the cooking device is cooking according to the recipe, the server sends the first audio data to the cooking device according to the cooking progress, so that the cooking device can play the first audio data to prompt the user to operate. For example: roasting chicken wings in an oven, before the oven receives the first audio data, the cavity temperature of the oven is obtained, and the cavity temperature is uploaded to the server in real time. After the server receives the cavity temperature, it determines whether the cavity temperature reaches the preheating temperature. If the preheating temperature is reached, "preheating is completed, put in the roasted wings" is sent back to the cooking device, that is, the first audio data is sent back to the cooking device, and the cooking device plays the first audio data after receiving the first audio data, thereby achieving the effect of real-time playback of recipes.

[0161] The present invention connects a cooking device to a server, and while the cooking device is cooking according to a recipe, a first cooking parameter of the cooking device is uploaded to the server. The server can transmit first audio data back to the cooking device in real time according to the first cooking parameter, so that the cooking device can play the first audio data according to the actual cooking status, improves the real-time performance of the first audio data playback process, and enables the user to cook according to the first audio data played by the target device.

[0162] like Figure 7 As shown, in any of the above embodiments, the audio output method is applied to a cooking device, receiving and playing first audio data from a server, including:

[0163] Step 702, temporarily storing the received first audio data in a local storage area;

[0164] Step 704, determining a second cooking parameter during operation of the cooking device;

[0165] Step 706, determining a play time corresponding to the first audio data according to the second cooking parameter;

[0166] Step 708: Play the first audio data according to the play time.

[0167] In this embodiment, when the target device is a cooking device, the cooking device receives the first audio data sent back by the server and temporarily stores the first audio data. A second cooking parameter during the operation of the cooking device is obtained, the cooking progress of the cooking device can be determined according to the second cooking parameter, the play time of the first audio data is determined according to the cooking progress, and the first audio data is cooked according to the play time.

[0168] Specifically, the cooking device temporarily stores the first audio data from the server, and plays the temporarily stored first audio data according to the cooking progress while the cooking device is cooking according to the recipe. For example, when roasting chicken wings in an oven, the temperature in the oven cavity is obtained, and the cavity temperature is uploaded to the server in real time to determine whether the cavity temperature has reached the preheating temperature. When the preheating temperature is reached, the cooking device plays "preheating is complete, add roasted wings". After the cooking device receives the first audio data, the first audio data is temporarily stored, and the first audio data is played according to the actual cooking progress, thereby achieving the effect of playing recipes in real time.

[0169] The present invention temporarily stores the received first audio data, detects the cooking process of the cooking device in real time, and controls the cooking device to play the first audio data according to the cooking process. This enables the cooking device to play the first audio data according to the actual cooking state, improves the real-time performance of the first audio data playing process, and enables the user to cook according to the first audio data played by the target device.

[0170] Embodiment 2:

[0171] like Figure 8 As shown, a second embodiment of the present invention provides an audio output method, comprising:

[0172] Step 802, receiving semantic information and identity information sent by the target device;

[0173] Step 804, determining first audio data according to the semantic information and the identity recognition information;

[0174] Step 806: Send the first audio data to the target device.

[0175] After receiving the first audio data, the target device plays the first audio data.

[0176] The audio output method provided in this embodiment is applied to a server. After receiving the semantic information and identity recognition information from the target device, the server can determine the identity information of the user corresponding to the voice control instruction and the meaning of the voice control instruction. The server determines the first audio data in the server according to the identity information of the user and the specific meaning of the voice control instruction, and transmits the first audio data back to the target device. The target device plays the received first audio data.

[0177] Among them, the target device is provided with a sound collection device, and the voice control command sent by the user is received through the sound collection device. After receiving the voice control command from the user, the target device identifies the voice control command issued by the user. The target device includes a voiceprint recognition unit and a semantic recognition unit. The voiceprint recognition unit identifies the voiceprint features in the voice control command, and determines the identity information of the user who outputs the voice control command according to the voiceprint features. The target device identifies the semantic information in the voice control command through the semantic recognition unit. Among them, the identity information includes the user's registered account and other identification information that can determine the user's identity. The target device also includes a networked communication device, which establishes a communication connection with the server through the communication device, and sends the identified semantic information and identity information to the server.

[0178] In some possible implementation schemes, multiple audio data are stored in the server, wherein the multiple audio data correspond to different user IDs. After receiving the semantic information and the user's identity information, the server can find the corresponding multiple audio data according to the user's identity information, and then filter the first audio data in the multiple audio data through the semantic information, so that the first audio data corresponds to the user's identity information and the semantic information. It can be understood that the multiple audio data corresponding to the user's identity information are data pre-stored in the server. Through the identity information, multiple audio data that meet the user's personalization can be found, and then the first audio data that the user needs to play is determined through the semantic information, so that the audio data played by the target device meets the user's needs while also meeting the user's personalized needs.

[0179] In some other possible implementation schemes, a plurality of script contents and a plurality of voiceprint features are stored in the server, wherein the plurality of voiceprint features correspond to the identity information of different users. After the server receives the semantic information and the identity information of the user, it can find the corresponding voiceprint feature according to the identity information of the user, and find the corresponding target script content in the plurality of script contents according to the semantic information. The server synthesizes the script content with the voiceprint feature to obtain the first audio data. Since the script content in the first audio data is consistent with the semantic information in the voice control instruction output by the user, and the voiceprint feature in the first audio data is consistent with the identity information of the user, the audio data played by the target device can meet the user's needs while also meeting the user's personalized needs. It can be understood that the voiceprint feature is the voiceprint feature pre-stored by the user in the server.

[0180] In the related art, cooking equipment or user terminals can output voice information during the cooking process to prompt the user of relevant operations during the cooking process, but the output voice information is the voice information pre-stored by the user in the device. The timbre (voiceprint features) of the voice information is relatively single and cannot meet the user's personalized needs.

[0181] The present invention sends semantic information and identity information corresponding to the voice control command issued by the user to the server, and the server can determine the corresponding first audio data according to the semantic information and identity information. The target device outputs the first audio data from the server, which can meet the user's personalized needs for the broadcast semantics while ensuring that the semantics corresponding to the voice broadcast by the target device meets the user's needs.

[0182] like Fig. 9 As shown, in any of the above embodiments, the audio output method further includes:

[0183] Step 902, receiving first audio data sent by a target device;

[0184] Step 904: Bind the identity identification information to the first audio data.

[0185] In this embodiment, before the user controls the target device through the voice control instruction, the user can execute the audio setting instruction on the target device, wherein the audio setting instruction includes the first audio data, and the first audio data includes the user's voice content. After the target device receives the first audio data including the user's voice content, it uploads the first audio data to the server. After the server receives the first audio data, it binds the first audio data with the user's identity identification information and stores it, so that after the server recognizes the user's identity identification information, it can find the corresponding first audio data according to the identity identification information.

[0186] Specifically, after receiving the audio setting instruction, the target device starts recording the user's voice content to obtain the first audio data, wherein the voice content is the voice broadcast in the subsequent use of the target device.

[0187] In some specific implementations, the target device is an oven, the user activates the voice broadcast recording function of the oven, the user searches for the method of roasting chicken wings, text content is displayed on the display screen of the oven, the user starts reading according to the text content, and the oven can record the user's reading content, and after the recording is completed, the first audio data is generated according to the recorded content, and the first audio data is uploaded to the server, and the server binds the first audio data with the text content and the user ID. After the user uses the oven to select the roast chicken wings function, the oven receives the first audio data returned from the server and plays the first audio data, so that the user can hear the previously recorded reading content during the cooking process.

[0188] The present invention records the user's voice through a target device to obtain first audio data, and uploads the first audio data to a server. When the user needs to broadcast the voice through the target device, the target device can interact with the server to play the first audio data recorded in advance by the user, thereby realizing the user's personalized setting of the target device's broadcast voice.

[0189] like Fig.10 As shown, in any of the above embodiments, the audio output method further includes:

[0190] Step 1002, receiving a first voiceprint feature sent by a target device;

[0191] Step 1004: Bind the identity recognition information with the first voiceprint feature.

[0192] In this embodiment, before the user controls the target device through the voice control instruction, the user can execute the audio setting instruction on the target device, wherein the audio setting instruction includes the user's second audio data, and the second audio data includes the user's voice content. After the target device receives the second audio data including the user's voice content, the target device can extract the first voiceprint feature in the voice content, upload the first voiceprint feature to the server, and after the server receives the first voiceprint feature, it binds and stores the first voiceprint feature with the user's identity information, so that after the server recognizes the user's identity information, it can synthesize the first audio data according to the first voiceprint feature and the script content, so that the timbre of the first audio data when it is played is consistent with the first voiceprint feature of the user pre-stored in the server, so that the target device can perform personalized voice broadcasting.

[0193] Specifically, after receiving the audio setting instruction, the target device starts to receive the user's voice content, identifies the first voiceprint feature of the user's voice content during the receiving process, and after identifying the first voiceprint feature, uploads the first voiceprint feature and the user's identity information to the server at the same time, so that the server binds the two. In the process of the user subsequently controlling the target device to perform voice broadcast, the target device can request the server for the first audio data synthesized by the first voiceprint feature.

[0194] The received first audio data is synthesized according to the first voiceprint feature.

[0195] It is worth noting that the user can bind the identity recognition information to multiple first voiceprint features, that is, the identity recognition information of each user in the server is bound to multiple different first voiceprint features.

[0196] In some possible implementation modes, the server finds multiple first voiceprint features through identity recognition information, and randomly selects one of the multiple first voiceprint features to be synthesized with the script content.

[0197] The present invention extracts the first voiceprint feature in the user's voice content through the target device, and binds the first voiceprint feature with the user's identity recognition information in the server, so that the user can query the corresponding first voiceprint feature through the identity recognition information, and synthesize the first voiceprint feature with the script content, so that when the user needs to broadcast the voice through the target device, the target device can interact with the server and play the first audio data synthesized by the first voiceprint feature pre-stored by the user, thereby realizing the user's personalized setting of the target device broadcast voice.

[0198] like Fig.11 As shown, in any of the above embodiments, determining the first audio data according to the semantic information and the identity recognition information includes:

[0199] Step 1102, query and obtain a first voiceprint feature according to the identity recognition information;

[0200] Step 1104, searching and obtaining script content according to the semantic information;

[0201] Step 1106, synthesize the script content and the first voiceprint feature to obtain first audio data.

[0202] In this embodiment, after the server receives the semantic information and identity identification information sent by the target device, the server searches for the corresponding first voiceprint feature based on the identity identification information. At the same time, the server also searches for the corresponding script content based on the semantic information. After the server finds the first voiceprint feature and the script content, the server obtains the first audio data by synthesizing the first voiceprint feature and the script content.

[0203] The server of the present invention can search for the corresponding first voiceprint feature and script content according to the semantic information and identity recognition information sent by the target device, and obtain the corresponding first audio data by synthesizing the first voiceprint feature and the script content.

[0204] like Fig.12 As shown, in any of the above embodiments, before sending the first audio data to the target device, the process includes:

[0205] Step 1202, receiving a first cooking parameter sent by a target device;

[0206] Step 1204, determining a sending time for sending the first audio output according to the first cooking parameter;

[0207] Step 1206: Send the first audio data to the target device according to the sending time.

[0208] The target device plays the received first audio data.

[0209] In this embodiment, when the target device is a cooking device, during the operation of the cooking device, a first cooking parameter of the cooking device is determined and uploaded to the server. The server can determine the playback time of the first audio data based on the first cooking parameter uploaded by the cooking device. The cooking device plays the first audio data immediately after receiving the first audio data. Therefore, the playback time is the sending time of the first audio data, and the first audio data is transmitted back to the cooking device according to the sending time so that the cooking device can play the first audio data.

[0210] Specifically, when the cooking device is cooking according to the recipe, the server sends the first audio data to the cooking device according to the cooking progress, so that the cooking device can play the first audio data to prompt the user to operate. For example: roasting chicken wings in an oven, before the oven receives the first audio data, the cavity temperature of the oven is obtained, and the cavity temperature is uploaded to the server in real time. After the server receives the cavity temperature, it determines whether the cavity temperature reaches the preheating temperature. If the preheating temperature is reached, "preheating is completed, put in the roasted wings" is sent back to the cooking device, that is, the first audio data is sent back to the cooking device, and the cooking device plays the first audio data after receiving the first audio data, thereby achieving the effect of real-time playback of recipes.

[0211] The present invention connects a cooking device to a server, and while the cooking device is cooking according to a recipe, a first cooking parameter of the cooking device is uploaded to the server. The server can transmit first audio data back to the cooking device in real time according to the first cooking parameter, so that the cooking device can play the first audio data according to the actual cooking status, improves the real-time performance of the first audio data playback process, and enables the user to cook according to the first audio data played by the target device.

[0212] Embodiment three:

[0213] like Fig.13 As shown, in the third embodiment of the present invention, an audio output device 1300 is provided, comprising:

[0214] A first receiving module 1302, configured to receive a voice control instruction;

[0215] The recognition module 1304 is used to recognize the identity information and semantic information corresponding to the voice control instruction;

[0216] A first sending module 1306, configured to send semantic information and identity information to a server;

[0217] The server determines the first audio data according to the received identity recognition information and semantic information;

[0218] The first receiving module 1302 is used to receive the first audio data sent from the server;

[0219] The playing module 1308 is used to play the first audio data.

[0220] The audio output method provided in this embodiment can be applied to a user terminal or a cooking device, hereinafter referred to as a target device. A sound collection device is provided in the target device, and a voice control instruction sent by a user is received through the sound collection device. After receiving the voice control instruction of the user, the target device identifies the voice control instruction issued by the user. The target device includes a voiceprint recognition unit and a semantic recognition unit. The voiceprint recognition unit identifies the voiceprint features in the voice control instruction, and determines the identity information of the user who outputs the voice control instruction according to the voiceprint features. The target device identifies the semantic information in the voice control instruction through the semantic recognition unit. Among them, the identity information includes the user's registered account and other identification information that can determine the user's identity. The target device also includes a networked communication device, which establishes a communication connection with the server through the communication device, and sends the identified semantic information and identity information to the server. After receiving the semantic information and identity information, the server can determine the identity information of the user corresponding to the voice control instruction and the meaning corresponding to the voice control instruction. The server determines the first audio data in the server according to the user's identity information and the specific meaning of the voice control instruction, and transmits the first audio data back to the target device. The target device plays the received first audio data.

[0221] In some possible implementation schemes, multiple audio data are stored in the server, wherein the multiple audio data correspond to different user IDs. After receiving the semantic information and the user's identity information, the server can find the corresponding multiple audio data according to the user's identity information, and then filter the first audio data in the multiple audio data through the semantic information, so that the first audio data corresponds to the user's identity information and the semantic information. It can be understood that the multiple audio data corresponding to the user's identity information are data pre-stored in the server. Through the identity information, multiple audio data that meet the user's personalization can be found, and then the first audio data that the user needs to play is determined through the semantic information, so that the audio data played by the target device meets the user's needs while also meeting the user's personalized needs.

[0222] In some other possible implementation schemes, a plurality of script contents and a plurality of voiceprint features are stored in the server, wherein the plurality of voiceprint features correspond to the identity information of different users. After the server receives the semantic information and the identity information of the user, it can find the corresponding voiceprint feature according to the identity information of the user, and find the corresponding target script content in the plurality of script contents according to the semantic information. The server synthesizes the script content with the voiceprint feature to obtain the first audio data. Since the script content in the first audio data is consistent with the semantic information in the voice control instruction output by the user, and the voiceprint feature in the first audio data is consistent with the identity information of the user, the audio data played by the target device can meet the user's needs while also meeting the user's personalized needs. It can be understood that the voiceprint feature is the voiceprint feature pre-stored by the user in the server.

[0223] In the related art, cooking equipment or user terminals can output voice information during the cooking process to prompt the user of relevant operations during the cooking process, but the output voice information is the voice information pre-stored by the user in the device. The timbre (voiceprint features) of the voice information is relatively single and cannot meet the user's personalized needs.

[0224] The present invention sends semantic information and identity information corresponding to the voice control command issued by the user to the server, and the server can determine the corresponding first audio data according to the semantic information and identity information. The target device outputs the first audio data from the server, which can meet the user's personalized needs for the broadcast semantics while ensuring that the semantics corresponding to the voice broadcast by the target device meets the user's needs.

[0225] In any of the above embodiments, the first receiving module 1302 is used to collect first audio data when receiving an audio setting instruction;

[0226] The first sending module 1306 is configured to send the first audio data to the server.

[0227] In this embodiment, the user's voice is recorded through the target device to obtain the first audio data, and the first audio data is uploaded to the server. When the user needs to broadcast the voice through the target device, the target device can interact with the server to play the first audio data recorded by the user in advance, thereby realizing the user's personalized setting of the target device's broadcast voice.

[0228] In any of the above embodiments, the audio output device further includes:

[0229] A collection module, configured to collect second audio data upon receiving an audio setting instruction;

[0230] An extraction module, used to extract the first voiceprint feature of the second audio data;

[0231] The first sending module 1306 is further configured to send the first voiceprint feature to the server.

[0232] This embodiment extracts the first voiceprint feature from the user's voice content through the target device, and binds the first voiceprint feature with the user's identity recognition information in the server, so that the user can query the corresponding first voiceprint feature through the identity recognition information, and synthesize the first voiceprint feature with the script content. Therefore, when the user needs to broadcast the voice through the target device, the target device can interact with the server and play the first audio data synthesized by the first voiceprint feature pre-stored by the user, thereby realizing the user's personalized setting of the target device broadcast voice.

[0233] In any of the above embodiments, the extraction module is further used to extract the second voiceprint feature in the voice control instruction;

[0234] The audio output device also includes:

[0235] The search module is used to search for identity recognition information through the second voiceprint feature according to the corresponding relationship.

[0236] This embodiment extracts the second voiceprint feature in the received voice control command through the target device, and searches for the identity recognition information corresponding to the second voiceprint feature according to the pre-stored correspondence relationship. In the case where the user does not need to manually input the identity recognition information, the accuracy of the extracted user identity recognition information is also guaranteed.

[0237] In any of the above embodiments, the audio output device further includes:

[0238] A control module, used for controlling the image acquisition device to acquire image data;

[0239] The receiving time of the voice control command corresponds to the collecting time of the image data;

[0240] The seizure module is used to search for identity recognition information based on the corresponding image data.

[0241] This embodiment collects image data during the voice control instruction process through the image acquisition device of the target device, and can find the identity recognition information corresponding to the image data by identifying the image features in the image data. In the case where the user does not need to manually input the identity recognition information, the accuracy of extracting the user's identity recognition information is also guaranteed.

[0242] In any of the above embodiments, the audio output device further includes:

[0243] An acquisition module, used for acquiring a first cooking parameter in a cooking device;

[0244] A first sending module 1306, configured to send a first cooking parameter to a server;

[0245] The server determines a sending time corresponding to the first audio data according to the first cooking parameter, and sends the first audio data to the cooking device according to the sending time.

[0246] The playing module 1308 is configured to play the received first audio data.

[0247] This embodiment connects the cooking device to the server via a network. When the cooking device is cooking according to a recipe, the first cooking parameter of the cooking device is uploaded to the server. The server can transmit the first audio data back to the cooking device in real time according to the first cooking parameter. This enables the cooking device to play the first audio data according to the actual cooking status, improves the real-time performance of the first audio data playback process, and enables the user to cook according to the first audio data played by the target device.

[0248] In any of the above embodiments, the audio output device further includes:

[0249] A storage module, used for temporarily storing the received first audio data in a local storage area;

[0250] A determination module, used to determine a second cooking parameter during the operation of the cooking device;

[0251] The determination module is further used to determine the playing time corresponding to the first audio data according to the second cooking parameter;

[0252] The playing module 1308 is used to play the first audio data according to the playing time.

[0253] This embodiment temporarily stores the received first audio data, detects the cooking process of the cooking device in real time, and controls the cooking device to play the first audio data according to the cooking process. This enables the cooking device to play the first audio data according to the actual cooking state, improves the real-time performance of the first audio data playing process, and enables the user to cook according to the first audio data played by the target device.

[0254] Embodiment 4:

[0255] like Fig.14 As shown, in a fourth embodiment of the present invention, an audio output device 1400 is provided, comprising:

[0256] The second receiving module 1402 is used to receive semantic information and identity information sent by the target device;

[0257] A determination module 1404, configured to determine first audio data according to semantic information and identity recognition information;

[0258] The second sending module 1406 is configured to send the first audio data to a target device.

[0259] After receiving the first audio data, the target device plays the first audio data.

[0260] In this embodiment, by sending the semantic information and identity information corresponding to the voice control command issued by the user to the server, the server can determine the corresponding first audio data according to the semantic information and identity information. By outputting the first audio data from the server through the target device, it is possible to meet the user's personalized needs for the broadcast semantics while ensuring that the semantics corresponding to the voice broadcast by the target device meets the user's needs.

[0261] In any of the above embodiments, the second receiving module is used to receive the first audio data sent by the target device;

[0262] The audio output device also includes:

[0263] The binding module is used to bind the identity recognition information with the first audio data.

[0264] In this embodiment, the user's voice is recorded through the target device to obtain the first audio data, and the first audio data is uploaded to the server. When the user needs to broadcast the voice through the target device, the target device can interact with the server to play the first audio data recorded by the user in advance, thereby realizing the user's personalized setting of the target device's broadcast voice.

[0265] In any of the above embodiments, the second receiving module is further used to receive the first voiceprint feature sent by the target device;

[0266] The binding module is also used to bind the identity recognition information with the first voiceprint feature.

[0267] This embodiment extracts the first voiceprint feature from the user's voice content through the target device, and binds the first voiceprint feature with the user's identity recognition information in the server, so that the user can query the corresponding first voiceprint feature through the identity recognition information, and synthesize the first voiceprint feature with the script content. Therefore, when the user needs to broadcast the voice through the target device, the target device can interact with the server and play the first audio data synthesized by the first voiceprint feature pre-stored by the user, thereby realizing the user's personalized setting of the target device broadcast voice.

[0268] In any of the above embodiments, the audio output device further includes:

[0269] A query module, used to query and obtain a first voiceprint feature according to the identity recognition information;

[0270] The query module is also used to find the script content based on the semantic information;

[0271] The synthesis module is used to synthesize the script content and the first voiceprint feature to obtain the first audio data.

[0272] The server in this embodiment can search for the corresponding first voiceprint feature and script content according to the semantic information and identity recognition information sent by the target device, and obtain the corresponding first audio data by synthesizing the first voiceprint feature and the script content.

[0273] In any of the above implementations, the second receiving module 1402 is used to receive a first cooking parameter sent by a target device;

[0274] The audio output device also includes:

[0275] A determination module, configured to determine a sending time for sending the first audio output according to the first cooking parameter;

[0276] The second sending module 1406 is used to send the first audio data to the target device according to the sending time.

[0277] The target device plays the received first audio data.

[0278] This embodiment connects the cooking device to the server via a network. When the cooking device is cooking according to a recipe, the first cooking parameter of the cooking device is uploaded to the server. The server can transmit the first audio data back to the cooking device in real time according to the first cooking parameter. This enables the cooking device to play the first audio data according to the actual cooking status, improves the real-time performance of the first audio data playback process, and enables the user to cook according to the first audio data played by the target device.

[0279] Embodiment five:

[0280] like Fig.15 As shown, in the fourth embodiment of the present invention, an audio output device 1500 is provided, including: a memory 1502 and a processor 1504 .

[0281] The memory 1502 is used to store programs or instructions;

[0282] The processor 1504 is used to implement the audio output method in the above-mentioned embodiment 1 and embodiment 2 when executing the program or instruction, and thus has all the beneficial effects of the audio output method in the above-mentioned embodiment 1 and embodiment 2.

[0283] Embodiment six:

[0284] In the sixth embodiment of the present invention, a readable storage medium is provided, on which a program is stored. When the program is executed by a processor, the audio output method in any of the above embodiments is implemented, thereby having all the beneficial technical effects of the audio output method in any of the above embodiments.

[0285] Embodiment seven:

[0286] A cooking device is provided in the seventh embodiment of the present invention, comprising: an audio output device as in Embodiment 3 and Embodiment 5; and / or a readable storage medium as in Embodiment 6, thereby having all the beneficial effects of the audio output device in Embodiment 3 and Embodiment 5 and / or the readable storage medium in Embodiment 6.

[0287] The cooking device comprises a shell, an image acquisition device and an audio acquisition device. A cooking cavity is arranged in the shell, and the image acquisition device and the audio acquisition device are arranged in the shell.

[0288] Embodiment eight:

[0289] In the eighth embodiment of the present invention, a cooking device is provided, comprising: an audio output device as in the fourth and fifth embodiments; and / or a readable storage medium as in the sixth embodiment, thereby having all the beneficial effects of the audio output device in the fourth and fifth embodiments and / or the readable storage medium in the sixth embodiment.

[0290] The readable storage medium includes a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0291] It should be clarified that in the claims, specification and drawings of the present invention, the term "multiple" refers to two or more than two. Unless otherwise clearly defined, the orientation or position relationship indicated by the terms "upper" and "lower" is based on the orientation or position relationship shown in the drawings, which is only for the purpose of more conveniently describing the present invention and making the description process simpler, rather than indicating or implying that the device or element referred to must have the specific orientation described, be constructed and operated in a specific orientation, so these descriptions cannot be understood as limiting the present invention; the terms "connect", "install", "fix" and the like should be understood in a broad sense. For example, "connection" can be a fixed connection between multiple objects, or a detachable connection between multiple objects, or an integral connection; it can be a direct connection between multiple objects, or an indirect connection between multiple objects through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances of the above data.

[0292] In the claims, specification and drawings of the present invention, the description of the terms "one embodiment", "some embodiments", "specific embodiments" and the like means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In the claims, specification and drawings of the present invention, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0293] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An audio output method, characterized in that: include: In response to a voice control instruction, identifying identity information corresponding to the voice control instruction and semantic information in the voice control instruction; Sending the identity recognition information and the semantic information to a server, so that the server determines the first audio data according to the identity recognition information and the semantic information; receiving and playing the first audio data from the server; After the server receives the semantic information and the identity information, the server can find the corresponding voiceprint feature according to the identity information, and find the corresponding target script content according to the semantic information, and the server synthesizes the target script content with the voiceprint feature to obtain the first audio data; Before responding to the voice control instruction and identifying the identity identification information corresponding to the voice control instruction and the semantic information in the voice control instruction, the audio output method further includes: In response to the audio setting instruction, acquiring second audio data; Extracting a first voiceprint feature of the second audio data; The first voiceprint feature is sent to the server so that the server can bind the identity recognition information with the first voiceprint feature.

2. The audio output method according to claim 1, characterized in that: Also includes: In response to the audio setting instruction, acquiring the first audio data; The first audio data is sent to the server so that the server can bind the first audio data to the identity identification information.

3. The audio output method according to claim 1 or 2, characterized in that: The identifying information corresponding to the voice control instruction includes: Extracting a second voiceprint feature from the voice control instruction; The identity identification information is searched according to the second voiceprint feature.

4. The audio output method according to claim 1 or 2, characterized in that: The identifying information corresponding to the voice control instruction includes: Collecting image data, wherein the image data is collected at a time corresponding to the time when the voice control instruction is received; The identity recognition information is determined based on the image data.

5. The audio output method according to claim 1 or 2, characterized in that: The audio output method is applied to a cooking device, and before receiving and playing the first audio data from the server, the method further includes: Acquiring a first cooking parameter of the cooking device; sending the first cooking parameter to the server, so that the server determines a sending time of the first audio data according to the cooking parameter, and sends the first audio data to the cooking device according to the sending time; The received first audio data is played.

6. The audio output method according to claim 1 or 2, characterized in that: The audio output method is applied to a cooking device, and the receiving and playing of the first audio data from the server includes: Receiving the first audio data, and temporarily storing the first audio data in a local storage area; Acquiring a second cooking parameter of the cooking device; determining a playing time of the first audio data according to the second cooking parameter; Play the first audio data according to the playing time.

7. An audio output method, characterized in that: include: Receiving identification information and semantic information of the target device; Determine first audio data according to the identity recognition information and the semantic information; Sending the first audio data to the target device so that the target device plays the first audio data; The determining the first audio data according to the identity recognition information and the semantic information includes: Searching for a first voiceprint feature according to the identity recognition information; searching script content according to the semantic information; synthesizing the first audio data according to the script content and the first voiceprint feature; Before receiving the identity information and semantic information of the target device, the audio output method further includes: Receiving a first voiceprint feature from the target device; Binding the first voiceprint feature with the identity recognition information.

8. The audio output method according to claim 7, characterized in that: Also includes: receiving the first audio data from the target device; The first audio data is bound to the identity identification information.

9. The audio output method according to claim 7 or 8, characterized in that: Before sending the first audio data to the target device, the method includes: receiving a first cooking parameter from the target device; determining a sending time of the first audio data according to the first cooking parameter; The first audio data is sent to the target device at the sending time, so that the target device plays the received first audio data.

10. An audio output device, characterized in that: include: A recognition module, configured to respond to a voice control instruction and recognize identity information corresponding to the voice control instruction and semantic information in the voice control instruction; A first sending module, used for sending the identity recognition information and the semantic information to a server, so that the server can determine the first audio data according to the identity recognition information and the semantic information; A first receiving module, used for receiving the first audio data from the server; A playing module, used for playing the first audio data; A collection module, configured to collect second audio data upon receiving an audio setting instruction; An extraction module, used to extract the first voiceprint feature of the second audio data; The first sending module is further used to send the first voiceprint feature to a server; Among them, after the server receives the semantic information and the identity recognition information, the server can find the corresponding voiceprint feature according to the identity recognition information, and find the corresponding target script content according to the semantic information. The server synthesizes the target script content with the voiceprint feature to obtain the first audio data.

11. An audio output device, characterized in that: include: A second receiving module, used to receive identity information and semantic information of a target device; A determination module, configured to determine first audio data according to the identity recognition information and the semantic information; A second sending module, used for sending the first audio data to the target device, so that the target device plays the first audio data; A binding module, used to bind the identity identification information with the first audio data; The second receiving module is further used to receive the first audio data sent by the target device; Among them, after receiving the semantic information and the identity recognition information, the corresponding voiceprint feature can be found according to the identity recognition information, and the corresponding target script content can be found according to the semantic information, and the target script content is synthesized with the voiceprint feature to obtain the first audio data.

12. An audio output device, characterized in that: include: Memory, used to store programs or instructions; A processor, configured to implement the audio output method according to any one of claims 1 to 9 when executing the program or instruction.

13. A readable storage medium having a program or instruction stored thereon, characterized in that: When the program or instruction is executed by a processor, the audio output method according to any one of claims 1 to 9 is implemented.

14. A cooking device, characterized in that: include: The audio output device as claimed in claim 10 or 12; and / or The readable storage medium as claimed in claim 13.

15. A server, characterized in that: include: The audio output device as claimed in claim 11 or 12; and / or The readable storage medium as claimed in claim 13.

Images