A voice processing method, device and computer storage medium

Abstract

The present application discloses a voice processing method, device and computer storage medium, the voice processing method comprising the following steps: obtaining a first voice, the first voice carrying recipient information; determining the recipient account based on the recipient information; and playing the first voice via a target speaker device when a preset condition is met; wherein the target speaker device is a speaker device logged in by the recipient account. The voice processing method, device and computer storage medium provided by the present application can simply and quickly realize voice interaction between different users through a speaker device, thereby improving the user experience.

Description

Technical Field

[0001] The present invention relates to the field of speech processing technology, and in particular to a speech processing method, device and computer storage medium. Background Art

[0002] Smart speakers are based on traditional speakers, combined with communication technology, sensor technology or other Internet technologies, so that they have more new functions that are in line with modern life scenarios on top of the basic function of amplification. Smart speakers are not only regarded as the core interactive components of future smart homes and smart Internet of Things, but also as a collection of various content and skills of artificial intelligence. However, existing smart speakers can only be used for simple conversations with users, and cannot achieve voice interaction between different users. How to achieve voice interaction between different users through speaker devices has been under research.

[0003] The preceding description is intended to provide general background information and does not necessarily constitute prior art. Summary of the invention

[0004] An object of the present invention is to provide a voice processing method, device and computer storage medium, which have the advantage of realizing voice interaction between different users through a speaker device.

[0005] Another object of the present invention is to provide a voice processing method, device and computer storage medium, which have the advantage of being able to determine the speaker device used to output voice based on the user's real-time position, thereby ensuring the timeliness of voice interaction between different users.

[0006] Another object of the present invention is to provide a voice processing method, device and computer storage medium, which have the advantage of being able to quickly determine the recipient account corresponding to the user voice based on the acquired user voice.

[0007] Another object of the present invention is to provide a voice processing method, device and computer storage medium, which have the advantage of being able to automatically detect whether reminder conditions are met according to user input requirements and output reminder voice accurately and timely.

[0008] Another object of the present invention is to provide a voice processing method, device and computer storage medium, which have the advantage of playing voice only when the user's privacy conditions are met, avoiding information leakage and better protecting user privacy.

[0009] Other advantages and features of the present invention will become more apparent from the following detailed description and may be realized by means of the instrumentalities and combinations particularly pointed out in the appended claims.

[0010] According to an invention of the present invention, a speech processing method of the present invention that can achieve the aforementioned objects and other objects and advantages comprises the following steps:

[0011] Acquire a first voice, where the first voice carries recipient information;

[0012] Based on the recipient information, determining a recipient account; and

[0013] When a preset condition is met, the first voice is played via a target speaker device; wherein the target speaker device is the speaker device logged in by the recipient account.

[0014] According to an embodiment of the present invention, determining the recipient account based on the recipient information includes the following steps:

[0015] Based on the device identifier of the speaker device that collects the first voice, query the stored login correspondence between the device identifiers of different speaker devices and accounts to obtain a target account corresponding to the device identifier;

[0016] Obtaining the address book information of the target account; and

[0017] The recipient account is determined based on the address book information of the target account and the recipient information. In this way, the user does not need to input the recipient account additionally, and the recipient account can be determined quickly, further improving the user experience.

[0018] According to an embodiment of the present invention, determining the recipient account according to the address book information of the target account and the recipient information includes the following steps:

[0019] When it is determined based on the address book information of the target account that there are multiple users matching the recipient information or no user matching the recipient information, based on the preset information, the account corresponding to the user that meets the preset rule is selected as the recipient account, and / or based on the input selection instruction, the account corresponding to the user indicated by the selection instruction is selected as the recipient account. In this way, when the recipient account cannot be directly determined based on the address book information and the recipient information, the recipient account is determined by combining the preset information and / or the input selection operation, which is flexible and accurate.

[0020] According to an embodiment of the present invention, the preset condition includes at least one of the following conditions:

[0021] It is detected that the recipient account logs into the speaker device;

[0022] It is detected that a recipient user corresponding to the recipient account is near the target speaker device; and

[0023] It is detected that only the recipient user corresponding to the recipient account and the designated user are near the target speaker device, and the designated user is pre-set by the recipient user. In this way, it can ensure that the voice is known to the real recipient in time and reduce the risk of information leakage, thereby improving the security and privacy of voice interaction.

[0024] Accordingly, the present invention provides a speech processing device for executing the above method, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: obtaining a first voice, wherein the first voice carries recipient information; determining a recipient account based on the recipient information; and when a preset condition is met, playing the first voice via a target speaker device; wherein the target speaker device is a speaker device logged in by the recipient account.

[0025] Accordingly, the present invention provides a computer storage medium, wherein the computer storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned speech processing method are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 A schematic diagram of an application environment of the speech processing method provided by an embodiment of the present invention;

[0027] Figure 2 A flow chart of a speech processing method provided by an embodiment of the present invention;

[0028] Figure 3 An interactive schematic diagram of a speech processing method provided by an embodiment of the present invention;

[0029] Figure 4 A schematic diagram of the structure of a speech processing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0030] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0031] It should be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0032] It should be understood that, although the terms first, second, third, etc. may be used to describe various information in this article, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this article, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein can be interpreted as "at the time of..." or "when..." or "in response to determination". Furthermore, as used in this article, the singular forms "one", "one" and "the" are intended to also include plural forms, unless there is an opposite indication in the context. It should be further understood that the terms "comprising", "including" indicate that there are described features, steps, operations, elements, components, projects, kinds, and / or groups, but do not exclude the existence, occurrence or addition of one or more other features, steps, operations, elements, components, projects, kinds, and / or groups. The terms "or" and "and / or" used herein are interpreted as inclusive, or mean any one or any combination. Thus, “A, B, or C” or “A, B and / or C” means “any of the following: A; B; C; A and B; A and C; B and C; A, B, and C.” An exception to this definition will occur only when a combination of elements, functions, steps, or operations are inherently mutually exclusive in some manner.

[0033] It should be understood that, although the various steps in the flowchart in the embodiment of the present application are displayed in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and it can be performed in other orders. Moreover, at least a portion of the steps in the figure may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and their execution order is not necessarily performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0034] It should be noted that, in this article, step codes such as S101, S102, etc. are used for the purpose of expressing the corresponding content more clearly and concisely, and do not constitute a substantial limitation on the sequence. When implementing the step, those skilled in the art may execute S102 first and then S101, etc., but these should all be within the scope of protection of this application.

[0035] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0036] In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present application, and have no specific meanings. Therefore, "module", "component" or "unit" can be used in a mixed manner.

[0037] Figure 1 The schematic diagram of the application environment of the voice processing method provided in the embodiment of the present invention is that the speaker device 1 and the server 2 perform data interaction via the network 3. After the user logs in to the server 2, the speaker device 1 receives the input first voice carrying the recipient information, and sends the first voice to the server 2; after the server 2 obtains the first voice, it determines the recipient account based on the recipient information, and when the preset conditions are met, the speaker device 1 logged in via the recipient account plays the first voice, thereby realizing voice interaction between different users simply and quickly through the speaker device. Among them, the speaker device 1 that receives the first voice and the speaker device 1 logged in via the recipient account can be the same speaker device or different speaker devices. It should be noted that the speaker device 1 can be a car computer, a car speaker, a smart speaker or other devices. In addition, Figure 1Only two speaker devices are shown as an example, and one or more speaker devices may be used in actual applications. Optionally, the speaker device 1 or the server 2 may also perform the following steps: after obtaining the first voice carrying the recipient information, determine the recipient account based on the recipient information, and play the first voice via the target speaker device when the preset conditions are met, wherein the target speaker device is the speaker device logged in by the recipient account.

[0038] See also Figure 2 , is a flow chart of a speech processing method provided by an embodiment of the present invention. The speech processing method can be executed by a speech processing device provided by an embodiment of the present invention. The speech processing device can be implemented in software and / or hardware. The speech processing device can be specifically Figure 1 The speaker device 1 or the server 2 in the embodiment of the present invention, the voice processing method comprises the following steps:

[0039] Step S101: Acquire a first voice, where the first voice carries receiver information;

[0040] In one embodiment, the execution subject of the voice processing method is a speaker device, and the speaker device may obtain the first voice in response to detecting that a preset wake-up button is triggered, obtain the first voice, and / or, in response to receiving a preset wake-up voice or a preset wake-up word, obtain the first voice. In this way, the voice is quickly obtained through a fast wake-up operation, thereby improving the efficiency of voice processing. Here, the speaker device may collect the first voice carrying the recipient information input by the user through a voice collection device such as a microphone. In addition, after waking up the speaker device, the user may control the speaker device to log in. The speaker device may support one or more login methods, for example, the speaker device may support voiceprint login, fingerprint login, face login, voice command login, etc. Specifically, for different users, different voice commands may be set as login verification information, such as the first user may use the voice command "Xiaoyin, open sesame" as login verification information, and the second user may use the voice command "Xiaoyin, do-re-mi" as login verification information. Of course, the speaker device may also log in through a connected mobile terminal with a management application. In order to guide the user to log in to the account, the speaker device may play a login prompt audio or display a login prompt message.

[0041] In one embodiment, before the speaker device obtains the first voice, the method may further include the following steps: obtaining login verification information, and sending the device identification of the speaker device and the login verification information to the server to log in to the target account. Wherein, the device identification of the speaker device may be the unique identification information of the speaker device, such as a barcode, a QR code or an electronic product code preset on the speaker device. Taking the login verification information as the login verification voice as an example, after the speaker device obtains the login verification voice input by the user, the login verification voice and the device identification of the speaker device are sent to the server to request the server to verify the login verification voice and log in to the corresponding target account. It can be understood that the purpose of the speaker device sending the device identification of the speaker device to the server is to enable the server to associate the device identification of the speaker device with the target account after the login verification information is verified, so as to complete the login and facilitate subsequent voice interaction operations. In addition, after the server verifies the login verification information and allows the target account to log in to the speaker device, it can send a verification response message and information related to the target account such as the user name to the speaker device.

[0042] In another embodiment, the execution subject of the voice processing method is a server, and the server obtains the first voice by receiving the first voice sent by a speaker device. Here, the speaker device that sends the first voice to the server can be called a speaker device logged in by a sender account or a sender user.

[0043] It should be noted that the recipient information may include at least one of the following information: the recipient's name, nickname, account, etc. For example, the first voice may contain nicknames such as "Mom" and "Dad". Of course, the recipient information may be one recipient information or multiple recipient information. In addition, the first voice may also carry the sender account or the device identifier of the speaker device logged in by the sender user.

[0044] Step S102: Determine the recipient's account based on the recipient's information;

[0045] Specifically, based on the device identification of the speaker device that collects the first voice, the stored login correspondence between the device identifications of different speaker devices and accounts is queried to obtain the target account corresponding to the device identification; the address book information of the target account is obtained; and the recipient account is determined based on the address book information of the target account and the recipient information. In this way, the user does not need to enter the recipient account additionally, and the recipient account can be quickly determined, further improving the user experience.

[0046] In one embodiment, the executor of the voice processing method is a speaker device, and the speaker device determines the recipient account based on the recipient information, which may specifically include the following steps: the speaker device queries the local address book information, and takes the account corresponding to the user matching the recipient information as the recipient account; or, the speaker device sends a query request carrying the recipient information and the device identification of the speaker device to the server, so as to query the login correspondence between the device identifications of different speaker devices and the accounts stored in the server, and receives the address book information of the target account corresponding to the device identification returned by the server based on the query request, and determines the recipient account based on the address book information of the target account and the recipient information.

[0047] In another embodiment, the execution subject of the voice processing method is a server, and the server determines the recipient account based on the recipient information, which may specifically include the following steps: the server queries the stored login correspondence between the device identification and the account of different speaker devices based on the device identification of the speaker device, and obtains the target account corresponding to the device identification; obtains the address book information of the target account; and determines the recipient account based on the address book information of the target account and the recipient information. It can be understood that after receiving the first voice carrying the recipient information sent by the speaker device, the server correspondingly learns that the speaker device wants to send the first voice to the recipient user corresponding to the recipient information. At this time, it is necessary to first determine the target account logged in to the speaker device, which can also be called the sender account. When different users or the same user use different accounts to log in to the same or different speaker devices, the server can record the login correspondence between the device identification and the account of the speaker device logged in by each account to facilitate the management of speaker devices and accounts. In one embodiment, the method may further include: the server receives the device identification and login verification information of the speaker device sent by the speaker device, verifies the login verification information according to the corresponding relationship between different login verification information and accounts stored, logs in the target account corresponding to the login verification information after the verification is passed, and stores the corresponding relationship between the device identification of the speaker device and the target account. Here, in the process of the speaker device performing account login, after receiving the device identification and login verification information of the speaker device sent by the speaker device, the server verifies the login verification information according to the corresponding relationship between different login verification information and accounts stored, that is, compares whether the stored login verification information contains the login verification information sent by the speaker device. If it contains, it means that the verification of the login verification information is passed. At this time, the target account corresponding to the login verification information can be obtained accordingly, and the corresponding relationship between the device identification of the speaker device and the target account is stored. It should be noted that the login verification information can be voice information, fingerprint information or face image, etc. In addition, after the server verifies the login verification information sent by the speaker device, it can also send a verification success response message to the speaker device to indicate that the speaker device has logged in to the target account. At the same time, the verification success response message can also carry the target account information. In addition, the correspondence between different login verification information and accounts stored by the server is obtained when the user registers an account.

[0048] Among them, similar to the address book on the mobile phone, the address book of WeChat, the contact list of QQ, etc., the address book information of the target account includes the names or nicknames of different users and corresponding accounts and other data, such as the names and corresponding accounts of friends, the nicknames and corresponding accounts of family members, etc. Here, the corresponding account includes but is not limited to mobile phone numbers, SIM card information, social accounts or payment accounts, etc. Taking the use of mobile phone numbers to register an account as an example, the first user uses mobile phone number A as an account to register in the server, and the first user's father uses mobile phone number B as an account to register in the server. The first user can add the account registered by his father in the server, that is, mobile phone number B, to the address book of his own account through the add friend operation and other methods, and set the corresponding contact name to the nickname "Dad"; of course, the server can also extract the address book data on the first user's mobile phone, determine the contacts registered in the server among all the contacts of the first user according to the address book data, and recommend to the first user whether to add one or more registered contacts to the address book of his own account.

[0049] In one embodiment, the determining of the recipient account based on the address book information of the target account and the recipient information may include the following steps: querying the address book information of the target account, and determining that the account corresponding to the user matching the name or nickname of the recipient is the recipient account. For example, if the recipient information includes the recipient's name "Zhang San", querying the address book information of the target account to determine the account corresponding to the user "Zhang San" in the address book as the recipient account.

[0050] In another embodiment, the determination of the recipient account based on the address book information of the target account and the recipient information may include the following steps: when it is determined based on the address book information of the target account that there are multiple users matching the recipient information or no user matching the recipient information, based on the preset information, select the account corresponding to the user that meets the preset rule as the recipient account, and / or based on the input selection instruction, select the account corresponding to the user indicated by the selection instruction as the recipient account. Here, the preset information and preset rules can be set according to actual needs. For example, if the preset information includes chat records, the preset rules may include at least one of the following rules: there is a chat record between the sender account within a preset time period before the current time; and the name of the chat object corresponding to the chat record matches the recipient information. In this way, the recipient user can be quickly and accurately determined through a simple screening operation. An example is as follows: Assuming that the receiver information includes the nickname "Mr. Chen", and the address book information of the target account records multiple users with the name or nickname "Mr. Chen", then the account corresponding to Mr. Chen with chat records within a preset time range (e.g., 10 minutes or 24 hours) before the current time can be used as the receiver account. Alternatively, assuming that the receiver information includes the nickname "Xiao Liuzi", and the address book information of the target account does not record the user with the name or nickname "Xiao Liuzi", then the chat information between different chat objects in the chat record can be queried. If a chat message contains "Xiao Liuzi, are you there?" or "Xiao Liuzi, let's go play basketball together tomorrow", etc., which calls the chat object "Xiao Liuzi", then the account corresponding to the chat object can be used as the receiver account. It should be noted that when it is determined that there are multiple users matching the receiver information based on the address book information of the target account, the information of multiple users matching the receiver information can be output for the user to select, and the selection instruction input by the user can be a voice selection instruction, or a touch selection instruction, etc. For example, if there are multiple users matching the recipient information "Li Si", the information of multiple users matching the recipient information "Li Si" can be output by voice, so that the user can select the desired recipient user by voice. In this way, when the recipient account cannot be directly determined based on the address book information and the recipient information, the recipient account can be determined by combining the preset information and / or the input selection operation, which is flexible and accurate.

[0051] Step S103: When a preset condition is met, the first voice is played via a target speaker device; wherein the target speaker device is a speaker device logged in by the recipient account.

[0052] In one embodiment, when the first voice is a reminder voice, that is, the purpose of the first voice is to remind the user, the preset condition may include at least one of the following conditions: the current time meets the time reminder condition indicated by the first voice; the current location meets the location reminder condition indicated by the first voice; and the event indicated by the first voice is detected. Among them, the current time meets the time reminder condition indicated by the first voice can be that the current time reaches or exceeds the reminder time indicated by the first voice. For example, assuming that the first voice is "remind me at 2:30 pm to attend the meeting at 3 pm on time", if the current time is 2:30 pm, it means that the current time meets the time reminder condition indicated by the first voice, and the first voice is played via the target speaker device. The current location meets the location reminder condition indicated by the first voice can be that the current location is located at the reminder location indicated by the first voice or the current location is less than the preset distance from the reminder location indicated by the first voice. For example, assuming that the first voice is "remind me when I am about to arrive at Hotel A", if the distance between the current location and Hotel A is less than the preset distance, it means that the current location meets the location reminder condition indicated by the first voice, and the first voice is played via the target speaker device. The detection of the occurrence of the event indicated by the first voice may be the detection that the event indicated by the first voice has occurred or is occurring. For example, assuming that the first voice is "Remind me when the weather forecast is playing", if the weather is currently being broadcast, the first voice is played via the target speaker device. In this embodiment, the first voice is determined to be a reminder voice when the first voice meets at least one of the following requirements, including: no recipient information is carried; the recipient information carried corresponds to the sender himself; keywords such as time, place or reminder are detected. Here, after obtaining the first voice, it is possible to directly identify whether the first voice is a reminder voice or other type of voice, or it is possible to first detect whether an indication message indicating that a reminder voice will be input has been obtained before the first voice is obtained. In this way, it can ensure that the voice is known to the recipient in a timely manner, thereby improving the effectiveness and convenience of voice interaction.

[0053] In another embodiment, when the first voice is a chat voice, that is, the purpose of the first voice is to talk or chat with the user, the preset condition may include at least one of the following conditions: detecting that the recipient account is logged into the speaker device; detecting that the recipient user corresponding to the recipient account is near the target speaker device; and detecting that only the recipient user and the designated user corresponding to the recipient account are near the target speaker device, and the designated user is pre-set by the recipient user or the system default. In this way, it can ensure that the voice is known to the real recipient in time and reduce the risk of information leakage, thereby improving the security and privacy of voice interaction. Here, in one embodiment, when the executor of the voice processing method is a speaker device, the speaker device may detect whether the recipient user and / or the designated user corresponding to the recipient account are near the speaker device in one or more ways, and optionally, detect whether the recipient user and / or the designated user corresponding to the recipient account are near the speaker device by at least one way or parameter of voiceprint recognition, image recognition, infrared detection, and Bluetooth signal strength. It can be understood that the speaker device can collect sounds in the surrounding environment through a sound collection device such as a microphone, and perform voiceprint recognition on the collected sounds to detect whether the recipient user and / or designated user corresponding to the recipient account is near the speaker device. For example, assuming that the recipient user corresponding to the recipient account uses voice to log in to the speaker device, after the speaker device obtains the first voice, the speaker device collects sounds in the surrounding environment, and performs voiceprint recognition on the collected sounds in the surrounding environment based on the voice input by the recipient user corresponding to the recipient account when logging in. If the recognition is successful, it means that the recipient user corresponding to the recipient account is near the speaker device. Of course, the speaker device can also detect whether the recipient user corresponding to the recipient account is near the speaker device through a human body sensing device such as an infrared detector. In addition, the recipient user corresponding to the recipient account may use a mobile terminal or wearable device to establish a Bluetooth connection with the speaker device. At this time, the Bluetooth signal strength detected by the speaker device between the mobile terminal or wearable device can represent the distance between the recipient user corresponding to the recipient account and the speaker device. If the Bluetooth signal strength is greater than the preset strength threshold, it means that the recipient user corresponding to the recipient account is detected near the speaker device, otherwise it means that the recipient user corresponding to the recipient account is not near the speaker device.An example is as follows: Suppose a user inputs the voice message "Mom, the bank card password is 123456" through the car speaker. After the user's mother uses her corresponding account to log in to the smart speaker at home and the smart speaker obtains the voice message, the smart speaker decides whether to output the voice message according to different occasions. For example, the smart speaker may output the voice message when it detects that only the user's mother is at home, or only the user's mother and other designated family members are at home. However, the smart speaker may not output the voice message when it detects that there are guests at home in addition to the user's mother and / or other designated family members. This ensures that the voice message can be promptly known to the recipient and reduces the risk of information leakage.

[0054] In another embodiment, when the execution subject of the voice processing method is a server, the server can detect whether the recipient account is logged into the speaker device by detecting whether the login verification information related to the recipient account is received. In addition, the server can also determine whether the recipient user corresponding to the recipient account is near the target speaker device by receiving the detection result sent by the speaker device, and whether only the recipient user corresponding to the recipient account and the designated user are near the target speaker device. For example, after the server receives the voice sent by the first speaker device, if it detects that the recipient account corresponding to the voice is logged into the second speaker device, the voice can be sent to the second speaker device so that the second speaker device plays the voice.

[0055] In summary, in the voice processing method provided by the above embodiment, after the first voice is acquired, the recipient account is determined based on the recipient information carried in the first voice, and when the preset conditions are met, the first voice is played via the speaker device logged in by the recipient account, so as to realize voice interaction between different users through the speaker device; at the same time, the speaker device used to output the voice can be determined based on the real-time location of the user, thereby ensuring the timeliness of voice interaction between different users; and, based on the acquired user voice, the recipient account corresponding to the user voice can be quickly determined, and the satisfaction of the reminder conditions can be automatically detected according to the needs input by the user, and the reminder voice can be output accurately and timely to improve the user experience; and, the voice is played only when the user privacy conditions are met, thereby avoiding information leakage and better protecting user privacy.

[0056] In another embodiment, the first voice also carries the sender account, and the method further comprises the following steps: when it is determined that the second voice is obtained within a preset time, the second voice is played through the speaker device logged in by the sender account. Here, the execution subject of the voice processing method is the speaker device, and when the speaker device logged in by the receiver account determines that the second voice is obtained within a preset time, the second voice is played through the speaker device logged in by the sender account to achieve fast voice interaction. Taking the speaker device including the first speaker device and the second speaker device as an example, assuming that the sender user inputs the first voice to the first speaker device logged in by the sender account, and the first speaker device enables the second speaker device logged in by the receiver account to play the first voice through the server, at this time, the second speaker device can remain awake, listening or activated within the preset time after playing the first voice, if the receiver user inputs the second voice to the second speaker device within the preset time, then the second speaker device determines to use the sender account corresponding to the first voice as the receiver account corresponding to the second voice, and then sends the second voice and the sender account corresponding to the first voice to the server, so that the first speaker device logged in by the sender account can play the second voice through the server. The first speaker device and the second speaker device can be the same speaker device or different speaker devices. In this way, when the second voice is obtained within the preset time after the first voice is played, the second voice is played directly through the speaker device logged in by the sender's account, without the need to wake up the speaker device again or repeat the recipient's information, which is convenient to operate and improves the efficiency of voice interaction.

[0057] Based on the same inventive concept as the above embodiments, the technical solutions of the above embodiments are described in detail below through specific application scenarios. In this embodiment, the execution subject of the voice processing method includes a speaker device and a server, the speaker device includes a first speaker device and a second speaker device, and the first speaker device is a car machine and the second speaker device is a smart speaker. Figure 3 , which is an interactive schematic diagram of a speech processing method provided by an embodiment of the present invention, comprising the following steps:

[0058] Step S201. The vehicle computer obtains the user input login verification voice;

[0059] In this embodiment, the login verification voice is taken as "123" as an example for description.

[0060] Step S202. The vehicle sends a login verification voice to the server;

[0061] Step S203. The server performs voiceprint recognition on the login verification voice;

[0062] Specifically, the server performs voiceprint recognition on the login verification voice "123" to query whether there is a user whose voiceprint matches the voice of the login verification voice "123".

[0063] Step S204. The server recognizes successfully and controls the vehicle computer to log in to the target account;

[0064] Here, after the server successfully recognizes the voiceprint of the login verification voice "123", it obtains the target account corresponding to the user to control the vehicle computer to log in to the target account, and returns a response message of logging in to the target account to the vehicle computer.

[0065] Step S205. The vehicle computer obtains the first voice input by the user;

[0066] In this embodiment, the first voice is taken as an example of "Mom, come home later".

[0067] Step S206. The vehicle computer sends the first voice to the server;

[0068] Here, the car computer sends the first voice "Mom, come home late" to the server.

[0069] Step S207: The server searches the address book of the target account for a recipient account corresponding to the first voice;

[0070] Here, the server searches for the user's mother's account in the address book of the target account and uses it as the recipient account.

[0071] Step S208. The server controls the smart speaker to log in to the recipient's account;

[0072] Here, the user of the smart speaker can input a login verification voice into the smart speaker, and the smart speaker will send the login verification voice to the server to request to log in to the recipient account. After the server verifies the login verification voice, it sends a response message to the smart speaker to log in to the recipient account, so that the smart speaker successfully logs in to the recipient account.

[0073] Step S209. The server sends the first voice to the smart speaker;

[0074] Here, when the server detects that the login account of the smart speaker is the recipient account, it sends the first voice to the smart speaker.

[0075] Step S210: When the smart speaker detects that a preset condition is met, the smart speaker plays the first voice;

[0076] Here, when the smart speaker detects that the user's mother is nearby, it plays the first voice.

[0077] Step S211. The smart speaker obtains the second voice within a preset time period;

[0078] In this embodiment, the second voice is a reply voice input by the user's mother "OK, I'm going for a walk in the park" as an example for explanation. For example, assuming that the preset duration is 10 seconds, after the user's mother plays the first voice "Mom, come home later" on the smart speaker, she replies with the second voice "OK, I'm going for a walk in the park" within 5 seconds, and the smart speaker obtains the second voice.

[0079] Step S212: The smart speaker sends the second voice to the server;

[0080] Step S213. The server sends the second voice to the vehicle computer;

[0081] Step S214: The vehicle computer plays the second voice.

[0082] In this way, voice interaction between users can be achieved simply and quickly through the car computer and smart speakers, improving the user experience.

[0083] Based on the same inventive concept as the above embodiments, the present invention provides a speech processing device, such as Figure 4 As shown, the voice processing device can be set on a server, a car machine, a smart speaker and other devices. Those skilled in the art may not limit the specific location of its setting and / or installation. The voice processing device includes: a processor 110 and a memory 111 for storing a computer program that can be run on the processor 110; wherein, Figure 4 The processor 110 shown in the figure is not used to indicate that the number of the processor 110 is one, but is only used to indicate the positional relationship of the processor 110 relative to other devices. In actual applications, the number of the processor 110 may be one or more; similarly, Figure 4 The memory 111 shown in the figure has the same meaning, that is, it is only used to refer to the position relationship of the memory 111 relative to other devices. In actual applications, the number of memories 111 can be one or more.

[0084] The processor 110 is used to execute the following steps when running the computer program:

[0085] Acquire a first voice, where the first voice carries recipient information;

[0086] Based on the recipient information, determining a recipient account; and

[0087] When a preset condition is met, the first voice is played via a target speaker device; wherein the target speaker device is the speaker device logged in by the recipient account.

[0088] In this way, voice interaction between different users can be achieved through the speaker device; at the same time, the speaker device used to output voice can be determined based on the user's real-time location, thereby ensuring the timeliness of voice interaction between different users; and, based on the acquired user voice, the recipient account corresponding to the user voice can be quickly determined, and the satisfaction of the reminder conditions can be automatically detected according to the needs of the user input, and the reminder voice can be output accurately and timely to improve the user experience; and, the voice is played only when the user privacy conditions are met, thereby avoiding information leakage and better protecting user privacy.

[0089] In one embodiment, the first voice also carries a sender account, and the processor 110 is configured to execute the following steps when running the computer program:

[0090] When it is determined that the second voice is acquired within the preset time, the second voice is played via the speaker device logged in by the sender account.

[0091] In another embodiment, when the processor 110 is used to run the computer program, the processor 110 performs the following steps:

[0092] Based on the device identifier of the speaker device that collects the first voice, query the stored login correspondence between the device identifiers of different speaker devices and accounts to obtain a target account corresponding to the device identifier;

[0093] Obtaining the address book information of the target account; and

[0094] A recipient account is determined based on the address book information of the target account and the recipient information.

[0095] In this way, the user does not need to enter the recipient's account additionally, and the recipient's account can be quickly determined, further improving the user experience.

[0096] In another embodiment, when the processor 110 is used to run the computer program, the processor 110 performs the following steps:

[0097] When it is determined based on the address book information of the target account that there are multiple users matching the recipient information or there is no user matching the recipient information, based on preset information, the account corresponding to the user that meets the preset rules is selected as the recipient account, and / or based on the input selection instruction, the account corresponding to the user indicated by the selection instruction is selected as the recipient account.

[0098] In this way, when the recipient's account cannot be directly determined based on the address book information and the recipient's information, the recipient's account is determined by combining preset information and / or input selection operations, which is flexible and highly accurate.

[0099] In another embodiment, the preset information includes chat records; and the preset rules include at least one of the following rules:

[0100] There is a chat record between the sender account and the sender account within a preset time period before the current time; and

[0101] The name of the chat object corresponding to the chat record matches the recipient information.

[0102] In this way, through a simple screening operation, the recipient user can be quickly and accurately determined.

[0103] In another embodiment, the preset condition includes at least one of the following conditions:

[0104] The current time meets the time reminder condition indicated by the first voice;

[0105] The current location meets the location reminder condition indicated by the first voice; and

[0106] The occurrence of the event indicated by the first voice is detected.

[0107] In this way, it can be ensured that the voice is known to the recipient in a timely manner, thereby improving the effectiveness and convenience of voice interaction.

[0108] In another embodiment, the preset condition includes at least one of the following conditions:

[0109] It is detected that the recipient account logs into the speaker device;

[0110] It is detected that a recipient user corresponding to the recipient account is near the target speaker device; and

[0111] It is detected that only the recipient user corresponding to the recipient account and a designated user are near the target speaker device, and the designated user is pre-set by the recipient user.

[0112] In this way, it can ensure that the voice is known to the real recipient in a timely manner and reduce the risk of information leakage, thereby improving the security and privacy of voice interaction.

[0113] In another embodiment, when the processor 110 is used to run the computer program, the processor 110 performs the following steps:

[0114] In response to detecting that a preset wake-up button is triggered, acquiring a first voice; and / or,

[0115] In response to receiving a preset wake-up voice or a preset wake-up word, a first voice is acquired.

[0116] In this way, the voice can be quickly acquired through a quick wake-up operation, thereby improving the efficiency of voice processing.

[0117] The speech processing device may further include: at least one network interface 112. The various components in the speech processing device are coupled together via a bus system 113. It is understood that the bus system 113 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 113 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, the bus system 113 is not described in detail. Figure 4 Various buses are labeled as bus system 113 .

[0118] The memory 111 may be a volatile memory or a nonvolatile memory, or may include both volatile and nonvolatile memories. The nonvolatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a ferromagnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disk, or a compact disc read-only memory (CD-ROM); the magnetic surface memory may be a disk memory or a tape memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), and direct RAM bus random access memory (DRRAM, Direct Rambus Random Access Memory).The memory 111 described in the embodiments of the present invention is intended to include but is not limited to these and any other suitable types of memories.

[0119] The memory 111 in the embodiment of the present invention is used to store various types of data to support the operation of the voice processing device. Examples of these data include: any computer program used to operate on the voice processing device, such as an operating system and an application; contact data; phone book data; messages; pictures; videos, etc. Among them, the operating system includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application program may include various applications, such as a media player (Media Player), a browser (Browser), etc., which are used to implement various application services. Here, the program that implements the method of the embodiment of the present invention may be included in the application program.

[0120] Based on the same inventive concept as the aforementioned embodiment, the present embodiment further provides a computer storage medium, in which a computer program is stored. The computer storage medium may be a ferromagnetic random access memory (FRAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); it may also be various devices including one or any combination of the above memories, such as a mobile phone, a computer, a tablet device, a personal digital assistant, etc.

[0121] When the computer program is executed by the processor, the following steps are performed:

[0122] Acquire a first voice, where the first voice carries recipient information;

[0123] Based on the recipient information, determining a recipient account; and

[0124] When a preset condition is met, the first voice is played via a target speaker device; wherein the target speaker device is the speaker device logged in by the recipient account.

[0125] In this way, voice interaction between different users can be achieved through the speaker device; at the same time, the speaker device used to output voice can be determined based on the user's real-time location, thereby ensuring the timeliness of voice interaction between different users; and, based on the acquired user voice, the recipient account corresponding to the user voice can be quickly determined, and the satisfaction of the reminder conditions can be automatically detected according to the needs of the user input, and the reminder voice can be output accurately and timely to improve the user experience; and, the voice is played only when the user privacy conditions are met, thereby avoiding information leakage and better protecting user privacy.

[0126] In one embodiment, the first voice also carries the sender's account, and the computer program is executed by a processor to perform the following steps:

[0127] When it is determined that the second voice is acquired within the preset time, the second voice is played via the speaker device logged in by the sender account.

[0128] In another embodiment, when the computer program is executed by a processor, the following steps are performed:

[0129] Based on the device identifier of the speaker device that collects the first voice, query the stored login correspondence between the device identifiers of different speaker devices and accounts to obtain a target account corresponding to the device identifier;

[0130] Obtaining the address book information of the target account; and

[0131] A recipient account is determined based on the address book information of the target account and the recipient information.

[0132] In this way, the user does not need to enter the recipient's account additionally, and the recipient's account can be quickly determined, further improving the user experience.

[0133] In another embodiment, when the computer program is executed by a processor, the following steps are performed:

[0134] When it is determined based on the address book information of the target account that there are multiple users matching the recipient information or there is no user matching the recipient information, based on preset information, the account corresponding to the user that meets the preset rules is selected as the recipient account, and / or based on the input selection instruction, the account corresponding to the user indicated by the selection instruction is selected as the recipient account.

[0135] In this way, when the recipient's account cannot be directly determined based on the address book information and the recipient's information, the recipient's account is determined by combining preset information and / or input selection operations, which is flexible and highly accurate.

[0136] In another embodiment, the preset information includes chat records; and the preset rules include at least one of the following rules:

[0137] There is a chat record between the sender account and the sender account within a preset time period before the current time; and

[0138] The name of the chat object corresponding to the chat record matches the recipient information.

[0139] In this way, through a simple screening operation, the recipient user can be quickly and accurately determined.

[0140] In another embodiment, the preset condition includes at least one of the following conditions:

[0141] The current time meets the time reminder condition indicated by the first voice;

[0142] The current location meets the location reminder condition indicated by the first voice; and

[0143] The occurrence of the event indicated by the first voice is detected.

[0144] In this way, it can be ensured that the voice is known to the recipient in a timely manner, thereby improving the effectiveness and convenience of voice interaction.

[0145] In another embodiment, the preset condition includes at least one of the following conditions:

[0146] It is detected that the recipient account logs into the speaker device;

[0147] It is detected that a recipient user corresponding to the recipient account is near the target speaker device; and

[0148] It is detected that only the recipient user corresponding to the recipient account and a designated user are near the target speaker device, and the designated user is pre-set by the recipient user.

[0149] In this way, it can ensure that the voice is known to the real recipient in a timely manner and reduce the risk of information leakage, thereby improving the security and privacy of voice interaction.

[0150] In another embodiment, when the computer program is executed by a processor, the following steps are performed:

[0151] In response to detecting that a preset wake-up button is triggered, acquiring a first voice; and / or,

[0152] In response to receiving a preset wake-up voice or a preset wake-up word, a first voice is acquired.

[0153] In this way, the voice can be quickly acquired through a quick wake-up operation, thereby improving the voice processing efficiency. The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above-mentioned embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0154] In this document, the terms "comprises," "comprising," or any other variations thereof, are intended to cover a non-exclusive inclusion of elements other than those listed and may also include additional elements not expressly listed.

[0155] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A speech processing method, characterized in that: The method comprises the following steps: Acquire a first voice, where the first voice carries recipient information; Based on the recipient information, determining a recipient account; and When a preset condition is met, the first voice is played via a target speaker device; wherein the target speaker device is a speaker device logged in by the recipient account; Wherein, determining the recipient account based on the recipient information includes the following steps: Based on the device identifier of the speaker device that collects the first voice, query the stored login correspondence between the device identifiers of different speaker devices and accounts to obtain a target account corresponding to the device identifier; Obtaining the address book information of the target account; and When it is determined that there are multiple users matching the recipient information based on the address book information of the target account, the account corresponding to the user that meets the preset rules is selected as the recipient account based on preset information, the preset information includes chat records, and the preset rules include chat records with the sender account within a preset time period before the current time.

2. The method of claim 1, wherein: The first voice also carries a sender account, and the method further includes the following steps: When it is determined that the second voice is acquired within the preset time, the second voice is played via the speaker device logged in by the sender account.

3. The method of claim 1, wherein: Also includes: When it is determined based on the contact information of the target account that there is no user matching the recipient information, based on preset information, an account corresponding to a user that meets preset rules is selected as the recipient account.

4. The method of claim 3, wherein: The preset rules include: The name of the chat object corresponding to the chat record matches the recipient information.

5. The method of claim 1, wherein: The preset condition includes at least one of the following conditions: The current time meets the time reminder condition indicated by the first voice; The current location meets the location reminder condition indicated by the first voice; as well as The occurrence of the event indicated by the first voice is detected.

6. The method of claim 1, wherein: The preset condition includes at least one of the following conditions: It is detected that the recipient account logs into the speaker device; It is detected that a recipient user corresponding to the recipient account is near the target speaker device; as well as It is detected that only the recipient user corresponding to the recipient account and a designated user are near the target speaker device, and the designated user is pre-set by the recipient user.

7. The method of claim 1, wherein: The obtaining of the first voice comprises the following steps: In response to detecting that a preset wake-up button is triggered, acquiring a first voice; and / or, In response to receiving a preset wake-up voice or a preset wake-up word, a first voice is acquired.

8. A speech processing device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the speech processing method according to any one of claims 1 to 7 are implemented.

9. A computer storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the speech processing method according to any one of claims 1 to 7 are implemented.

Images