Voice information processing methods, devices, equipment and storage media

Abstract

This invention discloses a voice information processing method, apparatus, device, and storage medium. The method includes: upon detecting that a user has opened a target user interface, acquiring controls corresponding to a control registration request of the target user interface, the controls including text input box controls and / or non-text input box controls; acquiring and recognizing user voice information to obtain text recognition results and intent recognition results; determining, based on a preset correspondence between intent recognition results and controls, whether a target non-text input box control corresponding to the intent recognition result exists; if so, generating corresponding response information and sending it to the target user interface to cause the target user interface to perform a corresponding operation. This invention implements voice information control, optimizes existing user interface voice interaction functions, can recognize complex voice information, and provide consistent system feedback responses, with an extremely simple implementation method.

Description

Technical Field

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

[0002] With the improvement of computer hardware processing power and network speed, various smart devices have begun to integrate voice recognition-related artificial intelligence technologies to enhance the human-computer interaction experience.

[0003] In existing technologies, the implementation methods for speech recognition functions typically include the following two types: The first type is an independent intelligent speech module that provides automatic speech recognition (ASR) and natural language understanding (NLU) technologies, converts the collected user's speech information into text and intent, and then sends it to an application with speech recognition capabilities for independent processing by the application; The second type is to integrate the intelligent speech module into a dialogue management module, which collects the user's speech information and outputs the dialogue intent.

[0004] Of the two existing methods, the first method is simple to implement, but the dialogue content is monotonous, and the response rules of different speech recognition applications are inconsistent. Different applications will respond differently to the same user voice information in similar scenarios, resulting in inconsistent feedback to the user. The second method can achieve rich dialogue content with good logic, and the response rules can be designed to be consistent. However, the development process is complex, requiring the import of a dedicated dialogue development module, and the development cost is also high. Summary of the Invention

[0005] This invention provides a voice information processing method, apparatus, device, and storage medium. By acquiring controls on the user interface and associating the recognized voice information with the controls, voice information is made into controls, optimizing the existing user interface voice interaction function. It can recognize complex voice information and provide consistent feedback response to the system. At the same time, the implementation method is extremely simple.

[0006] In a first aspect, embodiments of the present invention provide a voice information processing method, including:

[0007] When a user opens a target user interface, the control corresponding to the control registration request of the target user interface is obtained, the control including a text input box control and / or a non-text input box control;

[0008] The user's voice information is acquired, the voice information is recognized, and the text recognition result and intent recognition result of the voice information are obtained.

[0009] Based on the preset correspondence between intent recognition results and controls, determine whether there is a target non-text input box control corresponding to the intent recognition result;

[0010] If a target non-text input box control exists that corresponds to the intent recognition result, a response message corresponding to the target non-text input box control is generated and sent to the target user interface so that the target user interface performs the operation corresponding to the response message.

[0011] Secondly, embodiments of the present invention also provide a voice information processing device, comprising:

[0012] The control acquisition module is used to acquire the control corresponding to the control registration request of the target user interface when it is detected that the user has opened the target user interface. The control includes a text input box control and / or a non-text input box control.

[0013] The speech recognition module is used to acquire the user's speech information, recognize the speech information, and obtain the text recognition result and intent recognition result of the speech information;

[0014] The first control judgment module is used to determine whether there is a target non-text input box control corresponding to the intent recognition result based on the preset correspondence between the intent recognition result and the control.

[0015] The response sending module is used to generate response information corresponding to the target non-text input box control and send it to the target user interface if there is a target non-text input box control corresponding to the intent recognition result, so that the target user interface performs the operation corresponding to the response information.

[0016] Thirdly, embodiments of the present invention also provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the voice information processing method as described in the embodiments of the present invention.

[0017] Fourthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, characterized in that the computer program, when executed by a processor, implements the voice information processing method as described in the embodiments of the present invention.

[0018] The technical solution of this invention acquires controls on the user interface and associates the recognized voice information with the controls, thereby realizing the control-based representation of voice information, optimizing the existing user interface voice interaction function, recognizing complex voice information and providing consistent feedback response to the system, and the implementation method is extremely simple. Attached Figure Description

[0019] Figure 1 This is a flowchart of a voice information processing method provided in Embodiment 1 of the present invention.

[0020] Figure 2 This is a flowchart of a voice information processing method provided in Embodiment 2 of the present invention.

[0021] Figure 3 This is a schematic diagram of the structure of a voice information processing device provided in Embodiment 3 of the present invention.

[0022] Figure 4 This is a schematic diagram of the structure of a computer device provided in Embodiment 4 of the present invention. Detailed Implementation

[0023] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it.

[0024] It should also be noted that, for ease of description, the accompanying drawings show only the parts relevant to the invention and not all of them. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of the operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but it may also have additional steps not included in the drawings. The process may correspond to a method, function, procedure, subroutine, subprogram, etc.

[0025] Example 1

[0026] Figure 1 This is a flowchart illustrating a voice information processing method provided in Embodiment 1 of the present invention. This embodiment of the invention is applicable to situations where users need to control electronic devices using voice. The method can be executed by the voice information processing device provided in this embodiment, which can be implemented in software and / or hardware and is generally integrated into a computer device. For example, an intelligent voice assistant. Figure 1 As shown, the method of this embodiment of the invention specifically includes:

[0027] Step 101: When the user opens the target user interface, obtain the control corresponding to the control registration request of the target user interface, the control including text input box control and / or non-text input box control.

[0028] The target user interface is the interface currently displayed to the user and that allows interaction with the user. It can be a webpage or an application interface, etc., and is not limited here. The target user interface includes at least one user-touchable control, which the user can interact with by clicking, swiping up or down, or turning pages using their fingers or hardware devices.

[0029] The control registration request for the target user interface is sent from the target user interface to the intelligent voice assistant. Upon receiving the control registration request, the intelligent voice assistant can identify the touchable controls present on the target user interface. The target user interface can send the control registration request via message or method, etc., without limitation here. The message type of the control registration request can be JSON or XML, etc., without limitation here.

[0030] A text input box control is used to receive text entered by the user and display the entered text at the corresponding position in the text input box control of the target user interface. For example, the target user interface can be a search engine webpage, and the text input box control can be a search content input box, which receives the text "travel guide" entered by the user and displays "travel guide" in the search content input box of the webpage.

[0031] Non-text input box controls are used to sense user actions and execute their own preset functions based on the sensed user actions. These can be buttons or lists, such as a search confirmation button that executes the search function when the user clicks or touches it. Alternatively, they can be a list of search records that displays the search records below the last currently displayed search record when the user swipes up.

[0032] Step 102: Obtain the user's voice information, recognize the voice information, and obtain the text recognition result and intent recognition result of the voice information.

[0033] Voice information can be collected by a voice input device and sent to a smart voice assistant.

[0034] The method for recognizing speech information can employ Automatic Speech Recognition (ASR) technology to perform text recognition on the acquired speech information, obtaining the text recognition result of the speech information, which is the text corresponding to the sentences in the speech information; Natural Language Understanding (NLU) technology is then used to perform intent recognition on the text recognition result, obtaining the intent recognition result of the speech information, which is the target operation that the user wants to perform contained in the speech information.

[0035] For example, if the user's voice information is "previous page", the text recognition result can be the text "previous page", and the intent recognition result can be that the user wants to turn the page, and the direction of turning the page is to turn up one page.

[0036] Step 103: Based on the preset correspondence between intent recognition results and controls, determine whether there is a target non-text input box control that corresponds to the intent recognition result.

[0037] In the preset mapping between intent recognition results and controls, each intent recognition result corresponds to a control. This control is designed to perform its preset function based on the user's desired action contained in the intent recognition result. This mapping associates the user's voice information with controls, thus realizing the control-based representation of voice information.

[0038] The target non-text input box control is the non-text input box control on the target user interface that the user wants to control via voice information.

[0039] Step 104: If a target non-text input box control exists that corresponds to the intent recognition result, then generate response information corresponding to the target non-text input box control and send it to the target user interface so that the target user interface performs the operation corresponding to the response information.

[0040] The response information corresponding to the target non-text input box control includes user target operation information and target non-text input box control information from the intent recognition result. After receiving the response information, the target user interface determines the user's target non-text input box control based on the target non-text input box control information in the response information, and performs the target operation on the target non-text input box control according to the user target operation information in the response information.

[0041] This invention provides a voice information processing method that acquires controls on the user interface and associates the recognized voice information with the controls, thereby realizing the control-based processing of voice information, optimizing the existing user interface voice interaction function, recognizing complex voice information and providing consistent feedback response to the system, and the method is extremely simple to implement.

[0042] Optionally, the voice information processing method provided in this embodiment further includes, after step 103:

[0043] If there is no target non-text input box control corresponding to the intent recognition result, then determine whether the control includes a text input box control;

[0044] If the control includes a text input box control, the text recognition result is sent to the text input box control so that the text recognition result is displayed in the text input box control on the target user interface.

[0045] If there is no target non-text input box control corresponding to the intent recognition result, it indicates that the user's voice information is not an operation command and the user's purpose is not to perform an operation on the non-text input box control. Therefore, it is necessary to determine whether the user's voice information is the text that the user wants to input. Thus, it is necessary to determine whether the control includes a text input box control that can input and display text.

[0046] If the control includes a text input box control, indicating that the user's voice information is the text the user wants to input, then the text recognition result of the voice information is sent to the text input box control, and the text input box control displays the text content of the text recognition result at the corresponding position of the target user interface to complete the user's input operation.

[0047] Optionally, based on the above implementation method, after determining whether the control includes a text input box control, the voice information processing method further includes: if the control does not include a text input box control, then sending an error prompt instruction to the target user interface so that the target user interface sends an error prompt to the user.

[0048] If the controls do not include a text input box control, it indicates that none of the controls on the target user interface correspond to the current user voice information, meaning no operation can be performed based on the user voice information. This is judged as a recognition error or that the user has issued an incorrect command, and the target user interface sends an error message to the user. The error message can be a voice prompt played using a voice output device or a text prompt displayed on the target user interface; there are no limitations on this.

[0049] For example, this embodiment provides a specific implementation in a practical situation. When a user opens a search engine webpage, the webpage identifies a text input box control as the search content input box, a non-text input box control as a button with a preset generalized "OK" function, and a non-text input box control as a search record list. When the user's voice message is "previous page," the text recognition result based on speech recognition technology is "previous page," and the intent recognition result is that the user wants to perform a page-turning operation, with the page-turning direction being one page up. Therefore, based on the preset correspondence between the intent recognition result and the controls, the target non-text input box control is determined to be the search record list. A corresponding response is then generated and sent to the search engine webpage. The search engine webpage executes the operation of turning the search record list one page up, and the search record list performs the page-turning and display function. When the user's voice message is "travel guide", the text recognition result obtained based on speech recognition technology is "travel guide". The intent recognition result is that the user wants to obtain travel guide, but there is no non-text input box control that can perform this function. Therefore, it is determined that the webpage includes a text input box control as a search content input box. Then, the text "travel guide" is entered into the search content input box and displayed in the search content input box of the webpage.

[0050] The above implementation method realizes voice information control by acquiring the controls on the user interface and mapping the recognized voice information to the controls; by mapping the voice information to the text input box controls, the voice recognition function is extended from recognizing the user's operation intention to recognizing the user's intention to input text, and automatic text input can be realized, realizing full voice control; timely feedback is given to voice information that cannot be recognized, improving the efficiency of user voice control and user experience, further optimizing the existing user interface voice interaction function, recognizing complex voice information and providing consistent feedback response of the system, and at the same time, the implementation method is extremely simple.

[0051] Example 2

[0052] Figure 2 This is a flowchart of a voice information processing method provided in Embodiment 2 of the present invention. This embodiment of the present invention can be combined with various optional solutions in one or more of the above embodiments. In this embodiment, before obtaining the control corresponding to the control registration request of the target user interface, the method may further include: receiving interface description information sent by the target user interface, wherein the interface description information includes the control registration request of the target user interface and page space information.

[0053] like Figure 2 As shown, the method of this embodiment of the invention specifically includes:

[0054] Step 201: When it is detected that the user has opened the target user interface, receive the interface description information sent by the target user interface. The interface description information includes the control registration request and page space information of the target user interface.

[0055] The page space information may include the type of control, the number of each type of control, and the sequence number of the first row currently displayed in the list control.

[0056] Step 202: Obtain the control corresponding to the control registration request of the target user interface, the control including text input box control and / or non-text input box control.

[0057] Step 203: Obtain the user's voice information, recognize the voice information, and obtain the text recognition result and intent recognition result of the voice information.

[0058] Step 204: Based on the preset correspondence between intent recognition results and controls, determine whether there is a target non-text input box control that corresponds to the intent recognition result.

[0059] Step 205: If a target non-text input box control exists that corresponds to the intent recognition result, then generate response information corresponding to the target non-text input box control and send it to the target user interface so that the target user interface performs the operation corresponding to the response information.

[0060] The specific implementation methods of the above steps can be found in the implementation methods of the corresponding steps provided in Example 1, and will not be repeated here.

[0061] Optionally, in step 205, generating response information corresponding to the target non-text input box control and sending it to the target user interface to cause the target user interface to perform an operation corresponding to the response information includes:

[0062] Based on the page space of the target user interface, determine whether the target user interface meets the operation execution conditions corresponding to the target non-text input box control;

[0063] If the target user interface meets the operation execution conditions corresponding to the target non-text input box control, then the operation execution instruction corresponding to the target non-text input box control is sent to the target user interface so that the target user interface performs the operation corresponding to the operation execution instruction;

[0064] If the target user interface does not meet the operation execution conditions corresponding to the target non-text input box control, then the operation prompt instruction corresponding to the target non-text input box control is sent to the target user interface, so that the target user interface sends a prompt corresponding to the operation prompt instruction to the user.

[0065] The operation execution condition refers to the conditions required for the target non-text input box control to execute its preset function based on the user's target operation contained in the voice information. The operation execution instruction is the instruction that controls the target non-text input box control to execute the target operation when the target user interface meets the operation execution condition. The operation prompt instruction is the instruction that controls the target user interface to send a corresponding prompt to the user when the target user interface does not meet the operation execution condition. This can be a voice prompt played using a voice output device or a text prompt displayed on the target user interface, and is not limited here.

[0066] For example, this embodiment provides a specific implementation in a real-world scenario. When a user opens a search engine webpage, it is determined that a non-text input box control exists on the webpage as a search record list. The page space includes a search record list that can display 5 rows, with a total of 10 search records. The current first row of the list is numbered 0. When the user's voice message is "previous page," the text recognition result based on speech recognition technology is "previous page," and the intent recognition result is that the user wants to perform a page-turning operation, with the page-turning direction being one page up. Therefore, through the preset correspondence between the intent recognition result and the control, the target non-text input box control is determined to be the search record list. However, based on the aforementioned page space conditions, it is determined that the search record list is already on the first page, and the condition for performing the operation of turning one page up is not met. Therefore, a corresponding operation prompt instruction is generated and sent to the search engine webpage. The search engine webpage controls the voice output device to play a voice prompt to the user: "The current list is already on the first page."

[0067] This invention provides a voice information processing method that acquires controls on the user interface and associates the recognized voice information with the controls to realize voice information controllability; it also acquires the spatial situation on the user interface to determine the execution conditions of the user's target operation and provides timely prompts, thereby optimizing the existing user interface voice interaction function. This method can recognize complex voice information and provide consistent feedback responses to the system, and is extremely simple to implement.

[0068] Optionally, the voice information processing method further includes: receiving a control cancellation request sent by the target user interface, and canceling the control corresponding to the control cancellation request.

[0069] In this process, the control cancellation request is sent from the target user interface to the smart voice assistant. After receiving the control cancellation request, the smart voice assistant ignores the corresponding control in the subsequent voice information processing. As a result, the user cannot use voice control to execute the preset function of the control corresponding to the control cancellation request.

[0070] The above implementation makes the voice control function on the user interface more flexible, allowing users to choose whether to control the controls via voice as needed.

[0071] Example 3

[0072] Figure 3 This is a schematic diagram of the structure of a voice information processing device provided in Embodiment 3 of the present invention, as shown below. Figure 3 As shown, the device includes: a control acquisition module 301, a voice recognition module 302, a first control judgment module 303, and a response sending module 304.

[0073] The system includes a control acquisition module 301, which acquires controls corresponding to the control registration request of the target user interface when a user opens the target user interface. These controls include text input box controls and / or non-text input box controls. A speech recognition module 302 acquires the user's speech information, recognizes the speech information, and obtains text recognition results and intent recognition results. A first control judgment module 303 determines whether a target non-text input box control corresponding to the intent recognition result exists based on a preset correspondence between intent recognition results and controls. A response sending module 304, if a target non-text input box control corresponding to the intent recognition result exists, generates response information corresponding to the target non-text input box control and sends it to the target user interface, causing the target user interface to perform an operation corresponding to the response information.

[0074] This invention provides a voice information processing device that acquires controls on the user interface and associates the recognized voice information with the controls, thereby realizing the control-based representation of voice information, optimizing the existing user interface voice interaction function, recognizing complex voice information and providing consistent feedback response to the system, and the implementation method is extremely simple.

[0075] In one optional embodiment of the present invention, the voice information processing device may further include: a second control judgment module and a text sending module.

[0076] The second control determination module is used to determine whether the control includes a text input box control if there is no target non-text input box control corresponding to the intent recognition result.

[0077] A text sending module is used to send the text recognition result to the text input box control if the control includes a text input box control, so that the text recognition result is displayed in the text input box control on the target user interface.

[0078] In an optional embodiment of the present invention, the voice information processing device may further include an error instruction sending module, configured to send an error prompt instruction to the target user interface if the control does not include a text input box control, so that the target user interface sends an error prompt to the user.

[0079] In an optional embodiment of the present invention, the voice information processing device may further include an interface description information receiving module, configured to receive interface description information sent by a target user interface, wherein the interface description information includes the control registration request and page space information of the target user interface.

[0080] In an optional embodiment of the present invention, the response sending module 304 may include: an operation execution condition judgment submodule, configured to determine whether the target user interface meets the operation execution conditions corresponding to the target non-text input box control based on the page space of the target user interface; an operation execution instruction sending submodule, configured to send an operation execution instruction corresponding to the target non-text input box control to the target user interface if the target user interface meets the operation execution conditions corresponding to the target non-text input box control, so that the target user interface performs the operation corresponding to the operation execution instruction; and an operation prompt instruction sending submodule, configured to send an operation prompt instruction corresponding to the target non-text input box control to the target user interface if the target user interface does not meet the operation execution conditions corresponding to the target non-text input box control, so that the target user interface sends a prompt corresponding to the operation prompt instruction to the user.

[0081] In an optional embodiment of the present invention, the voice information processing device may further include a control cancellation module, which is used to receive a control cancellation request sent by the target user interface and cancel the control corresponding to the control cancellation request.

[0082] The above-described voice information processing device can execute the voice information processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the voice information processing method.

[0083] Example 4

[0084] Figure 4 This is a schematic diagram of the structure of a computer device provided in Embodiment 4 of the present invention. Figure 4A block diagram of an exemplary computer device 12 suitable for implementing embodiments of the present invention is shown. Figure 4 The computer device 12 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0085] like Figure 4 As shown, the computer device 12 is represented in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors 16, memory 28, and bus 18 connecting different system components (including memory 28 and processor 16).

[0086] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0087] Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0088] Memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 4 Not shown; usually referred to as a "hard drive"). Although Figure 4 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0089] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of the present invention.

[0090] Computer device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with the computer device 12, and / or with any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, computer device 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18. It should be understood that, although... Figure 4 As not shown, it can be used in conjunction with computer device 12 with other hardware and / or software modules, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0091] The processor 16 executes various functional applications and data processing by running programs stored in the memory 28, thereby implementing the voice information processing method provided in this embodiment of the invention: when a user opens a target user interface, the processor acquires a control corresponding to the control registration request of the target user interface, the control including a text input box control and / or a non-text input box control; the processor acquires the user's voice information, recognizes the voice information, and obtains the text recognition result and intent recognition result of the voice information; based on a preset correspondence between the intent recognition result and the control, the processor determines whether there is a target non-text input box control corresponding to the intent recognition result; if there is a target non-text input box control corresponding to the intent recognition result, the processor generates response information corresponding to the target non-text input box control and sends it to the target user interface, so that the target user interface performs an operation corresponding to the response information.

[0092] Example 5

[0093] Embodiment 5 of the present invention provides a computer-readable storage medium storing a computer program thereon. When the program is executed by a processor, it implements the voice information processing method provided in this embodiment of the present invention: when a user opens a target user interface, the method acquires a control corresponding to a control registration request of the target user interface, the control including a text input box control and / or a non-text input box control; the method acquires the user's voice information, recognizes the voice information, and obtains a text recognition result and an intent recognition result of the voice information; based on a preset correspondence between the intent recognition result and the control, the method determines whether there is a target non-text input box control corresponding to the intent recognition result; if there is a target non-text input box control corresponding to the intent recognition result, the method generates response information corresponding to the target non-text input box control and sends it to the target user interface, so that the target user interface performs an operation corresponding to the response information.

[0094] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0095] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0096] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0097] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or computer device. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0098] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A voice information processing method characterized by comprising: Comprise: When detecting that a user opens a target user interface, obtain a control corresponding to a control registration request of the target user interface, the control comprising a text input box control and / or a non-text input box control; Obtain voice information of the user, identify the voice information to obtain a character recognition result and an intent recognition result of the voice information; According to a preset corresponding relationship between an intent recognition result and a control, determine whether there is a target non-text input box control corresponding to the intent recognition result; If there is a target non-text input box control corresponding to the intent recognition result, generate response information corresponding to the target non-text input box control and send it to the target user interface, so that the target user interface performs an operation corresponding to the response information; Generating response information corresponding to the target non-text input box control and sending it to the target user interface to make the target user interface perform an operation corresponding to the response information, comprising: According to the page space condition of the target user interface, determine whether the target user interface satisfies the operation execution condition corresponding to the target non-text input box control, the page space condition being sent by the target user interface; If the target user interface does not satisfy the operation execution condition corresponding to the target non-text input box control, send an operation prompt instruction corresponding to the target non-text input box control to the target user interface, so that the target user interface sends a prompt corresponding to the operation prompt instruction to the user.

2. The method of claim 1, wherein, After determining whether there is a target non-text input box control corresponding to the intent recognition result, further comprising: If there is no target non-text input box control corresponding to the intent recognition result, determine whether the control comprises a text input box control; If the control comprises a text input box control, send the character recognition result to the target user interface, so that the target user interface displays the character recognition result at a position corresponding to the text input box control.

3. The method of claim 2, wherein, After determining whether the control comprises a text input box control, further comprising: If the control does not comprise a text input box control, send an error prompt instruction to the target user interface, so that the target user interface sends an error prompt to the user.

4. The method of claim 1, wherein, Before obtaining the control corresponding to the control registration request of the target user interface, further comprising: Receive interface description information sent by the target user interface, the interface description information comprising the control registration request and the page space condition of the target user interface.

5. The method of claim 4, wherein, Generating response information corresponding to the target non-text input box control and sending it to the target user interface to make the target user interface perform an operation corresponding to the response information, comprising: If the target user interface satisfies the operation execution condition corresponding to the target non-text input box control, send an operation execution instruction corresponding to the target non-text input box control to the target user interface, so that the target user interface performs an operation corresponding to the operation execution instruction.

6. The method of claim 1, wherein, Further comprising: A control unregistration request sent by a target user interface is received, and a control corresponding to the control unregistration request is unregistered.

7. A voice information processing apparatus characterized by comprising: Comprise: A control obtaining module, configured to obtain a control corresponding to a control registration request of a target user interface when it is detected that a user opens the target user interface, the control comprising a text input box control and / or a non-text input box control; A speech recognition module, configured to obtain speech information of the user, and recognize the speech information to obtain a text recognition result and an intent recognition result of the speech information; A first control judging module, configured to determine whether there is a target non-text input box control corresponding to the intent recognition result according to a preset corresponding relationship between an intent recognition result and a control; A response sending module, configured to generate response information corresponding to the target non-text input box control and send the response information to the target user interface if there is a target non-text input box control corresponding to the intent recognition result, so that the target user interface performs an operation corresponding to the response information; The response sending module is further configured to determine whether the target user interface satisfies an operation execution condition corresponding to the target non-text input box control according to a page space condition of the target user interface, the page space condition being sent by the target user interface; If the target user interface does not satisfy the operation execution condition corresponding to the target non-text input box control, an operation prompt instruction corresponding to the target non-text input box control is sent to the target user interface, so that the target user interface sends a prompt corresponding to the operation prompt instruction to the user.

8. The apparatus of claim 7, wherein, Further comprise: A second control judging module, configured to determine whether the control comprises a text input box control if there is no target non-text input box control corresponding to the intent recognition result; A text sending module, configured to send the text recognition result to the text input box control if the control comprises a text input box control, so that the text recognition result is displayed in the text input box control on the target user interface.

9. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the speech information processing method in any one of claims 1-6.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the speech information processing method in any one of claims 1-6.

Images