Voice control method and device

Abstract

The present application relates to a voice control method and device. The method includes: obtaining voice instruction information; extracting target application clone program information and operation behavior information from the voice instruction information; generating a publish message according to the target application clone program information and the operation behavior information; searching for a subscription message matching the target application clone program information; using the application clone program corresponding to the subscription message matching the target application clone program information as the target application clone program; and sending the publish message to the target application clone program, so that the target application clone program obtains a corresponding execution instruction according to the operation behavior information and executes a corresponding action according to the execution instruction. Through the technical solution of the present application, it is realized to remotely control various different terminal applications or hardware connected to the terminal applications by voice, and there is no need for physical connection and pairing, which is flexible and efficient.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular, to a voice control method and device. Background Art

[0002] With the development of the Internet, voice control technology has been widely used. However, in the technology of voice control applications, the existing technology usually can only control the applications burned on the controlled devices that are pre-physically connected and paired to implement voice control applications. The entire system process is highly coupled and uniquely customized. Voice control instructions need to be transmitted to the controlled application program through each functional module on the controlled device in sequence, that is, only the local application program on the physically connected device can be voice-directed controlled, and the application program on other devices cannot be remotely controlled. Summary of the Invention

[0003] To solve the above technical problems or at least partially solve the above technical problems, embodiments of this application provide a voice control method and device.

[0004] In a first aspect, embodiments of this application provide a voice control method, which includes:

[0005] Obtain voice instruction information;

[0006] Extract target application clone program information and operation behavior information from the voice instruction information;

[0007] Generate a publish message according to the target application clone program information and the operation behavior information;

[0008] Search for a subscription message that matches the target application clone program information;

[0009] Use the application clone program corresponding to the subscription message that matches the target application clone program information as the target application clone program;

[0010] Send the publish message to the target application clone program, so that the target application clone program obtains a corresponding execution instruction according to the operation behavior information and executes a corresponding action according to the execution instruction.

[0011] Optionally, before searching for a subscription message that matches the target application clone program information, the method further includes:

[0012] Obtain a message subscription request sent by the application clone program, where the message subscription request includes source application clone program information;

[0013] Extract the source application clone program information from the message subscription request and generate a subscription message for the application clone program;

[0014] Searching for a subscription message that matches the target application clone program information includes:

[0015] Search for subscription messages where the source application dual instance program information matches the target application dual instance program information.

[0016] Optionally, the message subscription request is generated when the user logs in to the application dual instance program.

[0017] Optionally, extract the target application dual instance program information and operation behavior information from the voice command information, including:

[0018] Perform voice recognition and semantic parsing on the voice command information to obtain the target application dual instance program information and operation behavior information.

[0019] Optionally, perform voice recognition and semantic parsing on the voice command information to obtain the target application dual instance program information and operation behavior information, including:

[0020] Perform voice recognition and semantic parsing on the voice command information to obtain the target application dual instance program information and operation content information;

[0021] Search for the control instruction number corresponding to the operation content information, and use the control instruction number as the operation behavior information.

[0022] Optionally, the target application dual instance program information includes the target application program name and the target account identifier; the source application dual instance program information includes: the source application program name and the source account identifier.

[0023] Optionally, the target account identifier includes the target user account and the corresponding target user password; the source account identifier includes the source user account and the corresponding source user password.

[0024] Optionally, this method is based on the MQTT protocol. The target application dual instance program information is the topic of the published message, the operation behavior information is the content of the published message, and the source application dual instance program information is the topic of the subscribed message.

[0025] Optionally, obtain the voice command information, including:

[0026] Obtain the voice command information collected by the voice acquisition device.

[0027] In a second aspect, an embodiment of the present application provides a voice control device, which includes:

[0028] An acquisition module for obtaining voice command information;

[0029] An extraction module for extracting the target application dual instance program information and operation behavior information from the voice command information;

[0030] A first generation module for generating a published message according to the target application dual instance program information and operation behavior information;

[0031] A matching module, configured to find a subscription message that matches the target application cloning program information;

[0032] A target determination module, configured to use the application cloning program corresponding to the subscription message that matches the target application cloning program information as the target application cloning program;

[0033] A control module, configured to send a publish message to the target application cloning program, so that the target application cloning program obtains a corresponding execution instruction according to the operation behavior information, and executes a corresponding action according to the execution instruction.

[0034] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the processor is caused to execute the steps of the method according to any one of the previous items.

[0035] In a fourth aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it executes the steps of the method according to any one of the previous items.

[0036] The above technical solutions provided by the embodiments of the present application have the following advantages compared with the prior art:

[0037] Through the technical solution provided by the embodiment of the present application, based on voice acquisition technology, voice recognition technology, and semantic analysis technology, a publish message is generated according to voice instruction information, and the publish message is pushed to the target application cloning program that has subscribed to the publish message, realizing accurate and targeted remote voice control of the application cloning program, and being safe and reliable. In addition, the application cloning program can interact with the hardware for access, so that remote voice control of the application cloning program can be realized to control the hardware connected to the application cloning program. Description of the Drawings

[0038] The accompanying drawings here are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present invention, and are used together with the specification to explain the principles of the present invention.

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0040] Figure 1 It is an application environment diagram of the voice control method in an embodiment;

[0041] Figure 2Schematic flowchart of the voice control method in an embodiment;

[0042] Figure 3 Structural block diagram of the voice control device in an embodiment;

[0043] Figure 4 Internal structure diagram of a computer device in an embodiment. Specific implementation manners

[0044] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Apparently, the described embodiments are some but not all of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the scope of protection of the present application.

[0045] The embodiments of the present application perform voice control based on a subscription and publishing mode, which includes a subscription end, an agent server end, and a publishing end. The subscription end subscribes to messages from the agent server end according to their respective service logics. The publishing end publishes corresponding messages to the agent server end according to the occurring services. When the published message is subscribed to by one or more subscription ends, the agent server end will push the published message to the subscription ends that have subscribed to the published message.

[0046] Figure 1 Application environment diagram of the voice control method in an embodiment; Refer to Figure 1 , the voice control method is applied to a voice control system. The voice control system includes a terminal group 10, a server 20, and a voice collection device 30. Each terminal in the terminal group 10 (such as terminal 11, terminal 12, terminal 13, etc., not limited thereto) and the voice collection device 30 are respectively connected to the server 20 through a network. The server 20 receives the voice signal collected by the voice collection device 30 to obtain voice command information, extracts the target application clone program information and operation behavior information from the voice command information, generates a published message according to the target application clone program information and operation behavior information; searches for a subscribed message that matches the target application clone program information; uses the application clone program corresponding to the subscribed message that matches the target application clone program information as the target application clone program; sends the published message to the target application clone program, so that the target application clone program obtains a corresponding execution instruction according to the operation behavior information, and executes corresponding actions according to the execution instruction. The target application clone program logs in to a certain terminal in the terminal group 10.

[0047] In this embodiment, the voice collection device 30 belongs to the publishing end, the application clone programs in each terminal of the terminal group 10 belong to the subscription end, and the server 20 belongs to the agent server end.

[0048] The application cloning program can be an application program logged in through an account, or an application web page logged in through an account, etc., not limited to this.

[0049] The terminal can specifically be a desktop terminal or a mobile terminal. The mobile terminal can specifically be at least one of a mobile phone, a tablet computer, a laptop computer, etc. An application program is installed on each terminal, and each application program obtains different application cloning programs by logging in with different accounts. Multiple application programs can be installed on each terminal. The server 20 can be implemented by an independent server or a server cluster composed of multiple servers.

[0050] The voice collection device 30 can be a common smart speaker, which is used to receive the user's voice command and transmit it to the server for voice recognition. The smart speaker can be mounted on the terminal.

[0051] On the server 20, different types of terminal applications can be registered. Each terminal application can be logged in with multiple different accounts, that is, the same terminal application can simultaneously run multiple application cloning programs logged in with different accounts. Therefore, the server 20 can remotely control the same terminal application of different accounts, or control different types of terminal applications.

[0052] Figure 2 It is a schematic flowchart of the voice control method in an embodiment; refer to Figure 2 , the voice control method includes the following steps:

[0053] S100: Obtain voice command information.

[0054] Specifically, the server 20 obtains the user's voice command information. The voice command information includes the voice information of the target application cloning program, the voice information of the target account, the voice information of the operation behavior, etc.

[0055] S200: Extract the target application cloning program information and operation behavior information from the voice command information.

[0056] Specifically, the server 20 has a voice recognition function. The server 20 processes the received voice command information and can extract the non-voice form information of the target application cloning program information and operation behavior information from the voice information, for example, convert the voice form information into text form information.

[0057] S300: Generate a publish message according to the target application cloning program information and operation behavior information.

[0058] Specifically, after processing the received voice command information, the server 20 can generate a publishing message, which includes information about the target application clone program to be voice-controlled and information about the operation behavior that the target application clone program will execute.

[0059] S400: Search for a subscription message that matches the target application clone program information.

[0060] Specifically, the subscription messages are subscribed to the server 20 by multiple different application clone programs, or can be a list of subscription messages pre-stored in the server 20. Each subscription message corresponds to an application clone program.

[0061] S500: Use the application clone program corresponding to the subscription message that matches the target application clone program information as the target application clone program.

[0062] Specifically, there may be multiple publishing messages generated by the server 20, and there may also be multiple obtained subscription messages. Only when the publishing message matches the subscription message will the matching publishing message be sent to the application clone program that has subscribed to the matching subscription message.

[0063] S600: Send the publishing message to the target application clone program, so that the target application clone program can obtain the corresponding execution instruction according to the operation behavior information and execute the corresponding action according to the execution instruction.

[0064] Specifically, the subscription message corresponding to the target application clone program matches the publishing message. The publishing message carries instruction information. After receiving the publishing message, the target application clone program will parse the instruction information and execute the corresponding action. That is, the voice remote control of the terminal application clone program is completed.

[0065] In one embodiment, before step S400, the method further includes:

[0066] Obtain a message subscription request sent by the application clone program, where the message subscription request includes source application clone program information;

[0067] Extract the source application clone program information from the message subscription request to generate a subscription message for the application clone program.

[0068] Specifically, the application clone program can send a message subscription request to the server. The message subscription request includes the information of the application clone program, that is, the source application clone program information. After receiving the message subscription request, the server extracts the source application clone program information therein to generate a subscription message for the application clone program.

[0069] Step S400 specifically includes: Search for a subscription message whose source application clone program information matches the target application clone program information.

[0070] When the source application clone program information of the subscribed message matches the target application clone program information of the published message, the published message will be sent to the application clone program that has subscribed to the subscribed message.

[0071] In one embodiment, the message subscription request is generated when the user logs in to the application clone program.

[0072] Specifically, when the user logs in to a certain application clone program using an account on a certain terminal, a message subscription request will be sent to the server to receive in a timely manner the published messages generated according to the voice control instructions sent by the server, so as to respond to the remote voice control in a timely manner.

[0073] In one embodiment, step S200 specifically includes:

[0074] Perform speech recognition and semantic parsing on the voice instruction information to obtain the target application clone program information and the operation behavior information.

[0075] Since it is necessary to convert the voice information into text information for the subsequent matching actions, a speech recognition and semantic analysis cloud service platform can be used to recognize the voice instruction information and convert the voice instruction information into the corresponding text information. The recognition result is the recognized text information, that is, the target application clone program information and the operation behavior information in text form. The operation behavior information is the action that the user hopes the target application clone program to execute, such as opening the home page, forecasting the weather, controlling the hardware docked with the application clone program (such as turning the hardware on and off, switching the working mode of the hardware, etc.).

[0076] In one embodiment, performing speech recognition and semantic parsing on the voice instruction information to obtain the target application clone program information and the operation behavior information includes:

[0077] Perform speech recognition and semantic parsing on the voice instruction information to obtain the target application clone program information and the operation content information;

[0078] Search for the control instruction number corresponding to the operation content information, and use the control instruction number as the operation behavior information.

[0079] Specifically, the operation behavior information may be relatively more text information, which can be converted into a control instruction number to facilitate the transmission of messages.

[0080] In one embodiment, the target application clone program information includes the target application program name and the target account identifier; the source application clone program information includes: the source application program name and the source account identifier.

[0081] Since different application cloning programs can be generated by logging in to the same application through different accounts, using the application name and account identifier as the unique identifier of the application cloning program can effectively identify the application cloning program.

[0082] In one embodiment, the target account identifier includes the target user account and the corresponding target user password; the source account identifier includes the source user account and the corresponding source user password.

[0083] When the account identifier includes the user account and the user password, the security can be improved. Since the user password is relatively confidential, the security of the operation can be effectively guaranteed. At the same time, considering that the account identifier containing the user password needs to be sent between the subscription end and the proxy server, if the account identifier is not encrypted, there will be a risk of eavesdropping. Therefore, when the account identifier is generated, it is encrypted at the generation end to avoid eavesdropping during data transmission. Specifically, when the source account identifier is generated at the subscription end, the subscription end encrypts the source account identifier and then sends it to the proxy server; when the target account identifier is generated at the proxy server, it is encrypted by the same encryption method and then matched with the encrypted source account identifier.

[0084] In one embodiment, step S100 specifically includes: obtaining the voice command information collected by the voice collection device.

[0085] Specifically, the voice collection device 30 can be a smart speaker, which is used to receive the user's voice command information and send it to the server 20.

[0086] The voice collection device 30 can be set with a wake-up word, and the voice collection device 30 will collect the voice command only after receiving the wake-up word.

[0087] In one embodiment, the method is based on the MQTT protocol. The target application cloning program information is the topic of the published message, the operation behavior information is the content of the published message, and the source application cloning program information is the topic of the subscribed message. Optionally, the method can also use the long connection or polling method.

[0088] In one embodiment, the server 20 may include a speech recognition server, a message publishing server, and an MQTT server, where the MQTT server applies the MQTT communication protocol. Of course, in one embodiment, the speech recognition server, the message publishing server, and the MQTT server may be integrated into one server. The speech recognition server is used to obtain and recognize speech instruction information, and extract target application clone program information and operation behavior information from the speech instruction information; the message publishing server is used to generate a publishing message according to the target application clone program information and the operation behavior information; the MQTT server is used to receive a subscription request sent by the application clone program to obtain a subscription message, match the publishing message and the subscription message, and send the publishing message to the target application clone program that has subscribed to the subscription message.

[0089] Among them, MQTT is a message transmission protocol based on the publish / subscribe mode. It has the characteristics of being lightweight, open, simple, easy to implement, and having low communication bandwidth requirements. These characteristics make it a good choice for machine-to-machine communication and Internet of Things applications. Therefore, it is also applied to mobile phone APPs and Web applications.

[0090] In one embodiment, an application clone program can run multiple application clone programs simultaneously, and each application clone program logs in with a different account. In the single sign-on mode (that is, one account can only log in to one application clone program, and when logging in repeatedly to the same type of application clone program, the previously logged-in one will be forcibly logged out), the application clone program where the account is located can be uniquely determined according to the account logged in to the application clone program.

[0091] In one embodiment, the application clone program can be a local application clone program, a web application, or a non-login demonstration program or web page application. The hardware provides an interaction interface to dock with the terminal application, and executes instructions to finally trigger hardware operations, that is, the ultimate goal of the manipulation is also the hardware.

[0092] In one embodiment, the voice collection device 30 can also be used as a result feedback terminal to verbally express the manipulation result.

[0093] The technical solution of the present application can control different types of application programs by voice. Because the application clone programs are different in different types of application programs, there can be the same account names without conflict. When there is only one type of application program, the topic of the message can be only the account identifier, and the application program name is not required.

[0094] It should be understood that although Figure 2The steps in the flowchart are shown in sequence according to the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2 At least a part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0095] Figure 3 is a structural block diagram of a voice control device in an embodiment; refer to Figure 3 and the voice control device 100 includes:

[0096] The acquisition module 110 is used to obtain voice command information.

[0097] The extraction module 120 is used to extract target application clone program information and operation behavior information from the voice command information.

[0098] The first generation module 130 is used to generate a release message according to the target application clone program information and the operation behavior information.

[0099] The matching module 140 is used to find a subscription message that matches the target application clone program information.

[0100] The target determination module 150 is used to use the application clone program corresponding to the subscription message that matches the target application clone program information as the target application clone program.

[0101] The control module 160 is used to send the release message to the target application clone program, so that the target application clone program obtains a corresponding execution instruction according to the operation behavior information and executes a corresponding action according to the execution instruction.

[0102] In one embodiment, the device further includes:

[0103] The subscription module is used to obtain a message subscription request sent by the application clone program, where the message subscription request includes source application clone program information.

[0104] The second generation module is used to extract the source application clone program information from the message subscription request and generate a subscription message for the application clone program.

[0105] The matching module 140 is specifically used to find a subscription message whose source application clone program information matches the target application clone program information.

[0106] In one embodiment, the message subscription request is generated when the user logs in to the application cloning program.

[0107] In one embodiment, the extraction module 120 is specifically configured to perform speech recognition and semantic parsing on the voice command information to obtain the target application cloning program information and the operation behavior information.

[0108] In one embodiment, performing speech recognition and semantic parsing on the voice command information to obtain the target application cloning program information and the operation behavior information specifically includes: performing speech recognition and semantic parsing on the voice command information to obtain the target application cloning program information and the operation content information; searching for the control command number corresponding to the operation content information, and using the control command number as the operation behavior information.

[0109] In one embodiment, the target application cloning program information includes the target application name and the target account identifier; the source application cloning program information includes: the source application name and the source account identifier.

[0110] In one embodiment, the target account identifier includes the target user account and the corresponding target user password; the source account identifier includes the source user account and the corresponding source user password.

[0111] In one embodiment, the acquisition module 110 is specifically configured to obtain the voice command information collected by the voice acquisition device.

[0112] The device in this embodiment is used to execute the above-mentioned voice control method, and its working principle and beneficial effects correspond one by one, which will not be elaborated here.

[0113] Figure 4 It is the internal structure diagram of a computer device in one embodiment. Refer to Figure 4 , this computer device may specifically be Figure 1 the server 20 in. This computer device is connected to a processor, a memory, a network interface, an input device, a voice device, and a display screen through a system bus. Among them, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of this computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can implement the voice control method. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor can execute the voice control method. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device may be a touch layer covered on the display screen, or a button, a trackball, or a touchpad provided on the outer shell of the computer device, or an external keyboard, touchpad, or mouse, etc. The voice device may be a smart speaker, etc.

[0114] Those skilled in the art can understand,Figure 4 The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0115] In one embodiment, the voice control device 100 provided by this application can be implemented in the form of a computer program, and the computer program can run on a computer device as shown in Figure 4 The memory of the computer device may store each program module that makes up the voice control device 100. For example, Figure 3 the acquisition module 110, extraction module 120, first generation module, matching module 140, target determination module 150, and control module 160 shown in

[0116] For example, Figure 4 the computer device shown in Figure 3 can obtain voice instruction information through the acquisition module 110 in the voice control device 100 shown in

[0117] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: obtaining voice instruction information; extracting target application clone program information and operation behavior information from the voice instruction information; generating a publish message according to the target application clone program information and operation behavior information; searching for a subscription message that matches the target application clone program information; using the application clone program corresponding to the subscription message that matches the target application clone program information as the target application clone program; sending the publish message to the target application clone program, so that the target application clone program obtains a corresponding execution instruction according to the operation behavior information and executes corresponding actions according to the execution instruction.

[0118] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: obtaining voice instruction information; extracting target application clone program information and operation behavior information from the voice instruction information; generating a publishing message according to the target application clone program information and the operation behavior information; searching for a subscription message matching the target application clone program information; using the application clone program corresponding to the subscription message matching the target application clone program information as the target application clone program; and sending the publishing message to the target application clone program, so that the target application clone program obtains a corresponding execution instruction according to the operation behavior information and executes a corresponding action according to the execution instruction.

[0119] The technical solution of the present application will be described below with a specific application scenario. The user logs in to the user account "B" in the application "A", and the user password is: "pass". Then the application will automatically subscribe to a subscription message with the topic: "A / B / pass" from the MQTT server, and define this application clone program as application clone program Z.

[0120] The user issues a voice instruction to the smart speaker: "Xiaoyin, let B open the home page of application A, password pass" (where "Xiaoyin" is the wake-up word of the smart speaker). After receiving the voice instruction, the smart speaker will send the voice message to the voice recognition server in the server.

[0121] After receiving the voice message, the voice recognition server performs voice recognition and semantic analysis to obtain the recognition result: "B" is the target account identifier, "application A" is the target terminal application identifier, "application A" can also be used as the wake-up word of the server and the target terminal application, "pass" is the password of the target account; "open the... home page" is the operation content information, and according to the pre-stored comparison table of operation content information and operation behavior information, "Q1" is obtained as the operation behavior information. The voice recognition server sends the recognition result to the message publishing server to generate a publishing message according to the target application clone program identifier. The message publishing server sends the publishing message to the MQTT server. The MQTT server is also used to receive the subscription request of the application clone program and generate a corresponding subscription message according to the subscription request. When the MQTT server receives the publishing message, it matches the topic "A / B / Pass" of the publishing message with the topic of the subscription message, and sends the publishing message to the target application clone program Z corresponding to the subscription message that can match the topic "A / B / Pass". After receiving the publishing message, the target application clone program Z matches the corresponding execution instruction "showHome" according to the control instruction number "Q1" and executes it, so that the target application clone program finally completes the operation of opening the home page.

[0122] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0123] It should be noted that in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the element.

[0124] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A voice control method, characterized in that, The method includes: Obtaining voice command information; Extracting target application clone program information and operation behavior information from the voice command information; Generating a publish message according to the target application clone program information and the operation behavior information; Searching for a subscription message that matches the target application clone program information; Regarding the application clone program corresponding to the subscription message that matches the target application clone program information as the target application clone program; Sending the publish message to the target application clone program, so that the target application clone program obtains a corresponding execution instruction according to the operation behavior information, and executes a corresponding action according to the execution instruction; Before searching for a subscription message that matches the target application clone program information, the method further includes: Obtaining a message subscription request sent by an application clone program, where the message subscription request includes source application clone program information; Extracting the source application clone program information from the message subscription request to generate a subscription message for the application clone program; The searching for a subscription message that matches the target application clone program information includes: Searching for a subscription message whose source application clone program information matches the target application clone program information; When the source application clone program information of the subscription message matches the target application clone program information of the publish message, the publish message will be sent to the application clone program that has subscribed to the subscription message.

2. The method according to claim 1, characterized in that, The message subscription request is generated when the user logs in to the application clone program.

3. The method according to claim 1, wherein The extracting target application clone program information and operation behavior information from the voice command information includes: Performing voice recognition and semantic parsing on the voice command information to obtain target application clone program information and operation behavior information.

4. The method according to claim 3, wherein The performing voice recognition and semantic parsing on the voice command information to obtain target application clone program information and operation behavior information includes: Performing voice recognition and semantic parsing on the voice command information to obtain target application clone program information and operation content information; Searching for a control instruction number corresponding to the operation content information, and using the control instruction number as the operation behavior information.

5. The method according to claim 1, characterized in that, The target application clone program information includes a target application program name and a target account identifier; the source application clone program information includes: a source application program name and a source account identifier.

6. The method according to claim 5, characterized in that, The target account identifier includes a target user account and a corresponding target user password; the source account identifier includes a source user account and a corresponding source user password.

7. The method according to claim 1, characterized in that, The method is based on the MQTT protocol, the target application clone program information is the topic of the publish message, the operation behavior information is the content of the publish message, and the source application clone program information is the topic of the subscription message.

8. The method according to claim 1, characterized in that, The obtaining voice command information includes: Obtaining voice command information collected by a voice collection device.

9. A voice control device, characterized in that, The device includes: A collection module, configured to obtain voice command information; An extraction module, configured to extract target application clone program information and operation behavior information from the voice command information; A first generation module, configured to generate a release message according to the target application clone program information and the operation behavior information; A matching module, configured to search for a subscription message that matches the target application clone program information; A target determination module, configured to use the application clone program corresponding to the subscription message that matches the target application clone program information as the target application clone program; A control module, configured to send the release message to the target application clone program, so that the target application clone program obtains a corresponding execution instruction according to the operation behavior information, and executes a corresponding action according to the execution instruction; A subscription module, configured to obtain a message subscription request sent by an application clone program, where the message subscription request includes source application clone program information; A second generation module, configured to extract the source application clone program information from the message subscription request and generate a subscription message for the application clone program; The matching module is configured to search for a subscription message in which the source application clone program information matches the target application clone program information; When the source application clone program information of the subscription message matches the target application clone program information of the release message, the release message will be sent to the application clone program that has subscribed to the subscription message.

Images