Voice interaction method, device, equipment and storage medium

Abstract

The present invention discloses a voice interaction method, device, equipment and storage medium, and relates to the field of voice interaction technology. The method includes: obtaining voice interaction information of a target user; performing signal enhancement processing on the voice interaction information to perform voice recognition on the target enhanced signal to obtain text information; performing semantic recognition on the text information to obtain a text recognition result, so as to perform corresponding functional operations in the target application according to the text recognition result. The present invention can improve the sensitivity of instructions by performing signal enhancement processing on the voice interaction information, and obtain text recognition results by extracting voice recognition and natural language processing algorithms, thereby performing functional operations corresponding to the text recognition results, and realizing rapid interaction between users and APP applications.

Description

Technical Field

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

[0002] With the advancement of science and technology, interactive technology has entered a diversified era. From the initial button interaction to today's touch screen interaction, somatosensory interaction, voice interaction and other methods, the interaction methods of terminal devices have become richer and more intelligent. Especially voice interaction technology, the biggest advantage of voice interaction is that it can free the user's hands. Take driving as an example. During driving, users cannot manually operate the device, so voice assistants are particularly important. Through voice commands, users can achieve basic functions such as making calls and adjusting the volume, making driving safer and more convenient.

[0003] Although voice interaction brings convenience in many scenarios, most current voice assistants are still limited to performing relatively simple and basic tasks. For example, they can help users make calls, send text messages, play music, open applications, etc. However, most of these functions are single and specific, lacking flexibility and depth, and cannot meet the needs of users in complex life scenarios. Summary of the invention

[0004] Based on this, it is necessary to provide a voice interaction method, device, equipment and storage medium for the above-mentioned technical problems to solve at least one of the above-mentioned technical problems.

[0005] The present invention provides a voice interaction method, comprising:

[0006] Obtain voice interaction information of target users;

[0007] Performing signal enhancement processing on the voice interaction information to perform voice recognition on the target enhanced signal to obtain text information;

[0008] Semantic recognition is performed on the text information to obtain a text recognition result, so as to execute a corresponding functional operation in the target application according to the text recognition result.

[0009] Optionally, according to a voice interaction method provided by the present invention, the step of performing voice recognition on the target enhanced signal to obtain text information includes:

[0010] Performing feature processing on the target enhanced signal to obtain feature information;

[0011] The acoustic feature information in the feature information is identified using a preset acoustic model.

[0012] The word sequence information in the feature information is identified using a preset language recognition model.

[0013] The text information is generated according to the acoustic feature information and the word sequence information.

[0014] Optionally, according to a voice interaction method provided by the present invention, the performing semantic recognition on the text information to obtain a text recognition result includes:

[0015] Extracting entity information from the text information;

[0016] Performing intent recognition on the text information to obtain user intent;

[0017] The text recognition result is generated based on the entity information and the user intention.

[0018] Optionally, according to a voice interaction method provided by the present invention, the performing a corresponding functional operation in a target application according to the text recognition result includes:

[0019] The decision execution instruction corresponding to the text recognition result is searched in a preset instruction library, so as to execute the functional operation corresponding to the decision execution instruction in the target application.

[0020] Optionally, according to a voice interaction method provided by the present invention, the executing a functional operation corresponding to the decision execution instruction in the target application includes:

[0021] When the type of the decision execution instruction is a page jump type, the page of the target application is controlled to jump to the page corresponding to the decision execution instruction;

[0022] If the type of the decision execution instruction is a navigation service type, generating a corresponding navigation path based on the decision execution instruction;

[0023] If the type of the decision execution instruction is a dialogue communication type, the text recognition result is sent to the corresponding dialogue user; when the dialogue text information sent by the dialogue user is received, the dialogue text information is converted into voice information, and the voice information is played.

[0024] Optionally, according to a voice interaction method provided by the present invention, after performing semantic recognition on the text information and obtaining a text recognition result, the method further includes:

[0025] If the decision execution instruction corresponding to the text recognition result is not found in the instruction library, determining the similarity between the text recognition result and the decision execution instruction in the instruction library;

[0026] Based on the similarity, query prompt information is generated, and the query prompt information is played.

[0027] Optionally, according to a voice interaction method provided by the present invention, after executing a corresponding functional operation in a target application according to the text recognition result, the method further includes:

[0028] According to the execution result, voice feedback information is generated and returned to the target user.

[0029] The present invention also provides a voice interaction device, comprising:

[0030] An acquisition module is used to acquire the user's voice interaction information;

[0031] A signal processing module, used to perform signal enhancement processing on the voice interaction information, so as to perform voice recognition on the target enhanced signal to obtain text information;

[0032] The execution module is used to perform semantic recognition on the text information to obtain a text recognition result, so as to execute a corresponding functional operation in a target application according to the text recognition result.

[0033] The present invention also provides a computer device, comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, wherein the processor implements the above-mentioned voice interaction method when executing the computer-readable instructions.

[0034] The present invention also provides one or more readable storage media storing computer-readable instructions, and the computer-readable instructions implement the above-mentioned voice interaction method when executed by a processor.

[0035] The above-mentioned voice interaction method, device, equipment and storage medium include: obtaining the voice interaction information of the target user; performing signal enhancement processing on the voice interaction information to perform voice recognition on the target enhanced signal to obtain text information; performing semantic recognition on the text information to obtain a text recognition result, so as to perform corresponding functional operations in the target application according to the text recognition result. The present invention can improve the sensitivity of the instruction by performing signal enhancement processing on the voice interaction information, and obtain the text recognition result by extracting the voice recognition and natural language processing algorithm, so as to perform the functional operation corresponding to the text recognition result, and realize the rapid interaction between the user and the APP application. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0037] Figure 1 is a flow chart of a voice interaction method according to an embodiment of the present invention;

[0038] Figure 2 It is a schematic diagram of a flow chart of controlling page jump provided by an embodiment of the present invention;

[0039] Figure 3 It is a schematic diagram of a flow chart of controlling page jump provided by an embodiment of the present invention;

[0040] Figure 4 is a structural schematic diagram of a voice interaction device in one embodiment of the present invention;

[0041] Figure 5 is a schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] The terms used in one or more embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of the present invention. The singular forms of "a", "said" and "the" used in one or more embodiments of the present invention are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of the present invention refers to and includes any or all possible combinations of one or more associated listed items.

[0044] The embodiments of the present invention can be applied to various scenarios, such as cargo transportation, smart home control, logistics management, etc. The present invention is specifically described in the cargo transportation scenario. Specifically, in one embodiment, Figure 1 As shown, Figure 1 : is a flow chart of a voice interaction method in an embodiment of the present invention. The embodiment of the present invention provides a voice interaction method, comprising the following steps:

[0045] Step S11, obtaining voice interaction information of the target user;

[0046] It should be noted that the voice interaction information may be voice information such as opening a page, querying a delivery route, sending a conversation message, etc. For example, the voice interaction information may be "check order status" or "open the delivery order page", etc.

[0047] Step S12, performing signal enhancement processing on the voice interaction information to perform voice recognition on the target enhanced signal to obtain text information;

[0048] Specifically, the voice interaction information is subjected to echo cancellation processing, for example, by using an adaptive filtering algorithm to eliminate the echo or reflected signal in the voice, and then the voice interaction information after the echo cancellation processing is subjected to voice enhancement processing. In addition, the voice interaction information can also be subjected to signal enhancement processing by using sound source localization and beamforming technology to obtain a target enhanced signal.

[0049] Furthermore, speech recognition is performed on the target enhanced signal to identify information such as phonemes and syllables in the target enhanced signal. In addition, word sequence information in the target enhanced signal is identified to help identify more accurate sentence structures and vocabulary. The target enhanced signal is then converted into text information based on sound information such as phonemes and syllables and word sequence information.

[0050] Step S13, performing semantic recognition on the text information to obtain a text recognition result, so as to execute a corresponding functional operation in the target application according to the text recognition result.

[0051] Specifically, text recognition is performed on the text information to identify entity information and user intention in the text information. For example, when opening the details page of order A, the entity information includes order A, and the user intention is to request to open the page, and then a text recognition result is generated according to the entity information and the user intention. Furthermore, the corresponding functional operation is performed in the target application according to the text recognition result. For example, the functional operation includes page jump, dialogue communication, navigation service, message notification and other functional operations. The specific execution process is specifically described in the following embodiments and will not be repeated here.

[0052] In addition, during the execution of the function operation, it is necessary to monitor the execution status of the function operation, so as to generate voice feedback information and return it to the target user according to the execution result. For example, the voice interaction information is to open the order details page. If the execution result is that no valid information is recognized, a voice feedback message of no valid information is generated and played to the target user. If the page has successfully jumped to the order details page, a prompt message that the order details page has been opened is generated.

[0053] The embodiment of the present invention, through the above scheme, includes: obtaining the voice interaction information of the target user; performing signal enhancement processing on the voice interaction information to perform voice recognition on the target enhanced signal to obtain text information; performing semantic recognition on the text information to obtain a text recognition result, so as to perform corresponding functional operations in the target application according to the text recognition result. The present invention can improve the sensitivity of the instruction by performing signal enhancement processing on the voice interaction information, and obtain the text recognition result through voice recognition and natural language processing algorithm extraction, so as to perform the functional operation corresponding to the text recognition result, and realize the rapid interaction between the user and the APP application.

[0054] In one embodiment of the present invention, performing speech recognition on the target enhanced signal to obtain text information includes:

[0055] The target enhanced signal is subjected to feature processing to obtain feature information; the acoustic feature information in the feature information is identified using a preset acoustic model; the word sequence information in the feature information is identified using a preset language recognition model; and the text information is generated according to the acoustic feature information and the word sequence information.

[0056] Specifically, feature information is extracted from the target enhanced signal, and then the audio feature information is identified using a preset acoustic model to obtain acoustic feature information, where the acoustic feature information includes information such as phonemes or phonetic symbols. The acoustic model uses a deep neural network (such as a convolutional neural network CNN model, a long short-term memory network LSTM model, or a Transformer model, etc.) to learn the phoneme pattern in the speech signal. For example, when "hello" appears in a certain speech, the model will recognize the phonemes [h], [e], [l], [o], etc.

[0057] In addition, a preset language recognition model (for example, an N-gram model, a statistical language recognition model, a neural network language recognition model, etc.) is used to recognize feature information according to contextual relationships to generate word sequence information that is more in line with natural language rules.

[0058] Furthermore, the final text information is generated based on the acoustic feature information identified by the acoustic model and the word sequence information identified by the language recognition model. In addition, the recognized text can be spelled corrected, formatted, etc. to ensure that the final output text meets the writing standards of the language.

[0059] The embodiment of the present invention, through the above scheme, includes: performing feature processing on the target enhanced signal to obtain feature information; using a preset acoustic model to identify the acoustic feature information in the feature information. Using a preset language recognition model to identify the word sequence information in the feature information. Generating the text information based on the acoustic feature information and the word sequence information. Combining the outputs of the acoustic model and the language recognition model to convert the target enhanced signal into text information can accurately decompose and process the audio information, thereby efficiently performing related tasks.

[0060] In one embodiment of the present invention, semantic recognition is performed on the text information to obtain a text recognition result, including:

[0061] Extracting entity information from the text information; performing intent recognition on the text information to obtain user intent; and generating the text recognition result based on the entity information and the user intent.

[0062] Specifically, entity information in the text information is extracted, and the text information is subjected to intent recognition to obtain the user's intent; then, the text recognition result is constructed based on the entity information and the user's intent. This achieves automatic understanding and processing of user needs, thereby quickly and accurately understanding the user's intent and providing more efficient services.

[0063] In one embodiment of the present invention, performing corresponding functional operations in the target application according to the text recognition result includes:

[0064] The decision execution instruction corresponding to the text recognition result is searched in a preset instruction library, so as to execute the functional operation corresponding to the decision execution instruction in the target application.

[0065] It should be noted that the instruction library stores the function types that the voice assistant can serve and the corresponding instruction information. If the decision execution instruction corresponding to the text recognition result is queried in the preset instruction library, the function operation corresponding to the decision execution instruction is directly executed in the target application, wherein the specific execution process of the function operation is as follows:

[0066] In one embodiment, when the type of the decision execution instruction is a page jump type, the page of the control target application jumps to the page corresponding to the decision execution instruction. For example, in the cargo transportation scenario, it can jump to the order grabbing page, order details page, etc. Figure 2 , Figure 2This is a flow chart of controlling page jumps provided by an embodiment of the present invention. First, the driver inputs the wake-up keyword by voice. The wake-up keyword refers to the keyword that wakes up the voice assistant in working state, and then determines whether the terminal has enabled the microphone permission. If the microphone permission exists, the voice assistant is awakened. At this time, the driver inputs the function page that needs to be opened by voice, and it is necessary to determine whether the application APP refers to opening the function page; if supported, the voice assistant responds with a prompt (for example, the page has been opened for you), and then controls the page to jump to the corresponding function page; if not supported, the voice assistant responds with a prompt (for example, prompts such as the function is not supported temporarily).

[0067] In one embodiment, if the type of decision execution instruction is a navigation service type, a corresponding navigation path is generated based on the decision execution instruction. Optionally, the voice interaction information is the destination location and current location input by the target user, then a corresponding navigation path is generated based on the destination location and current location and pushed to the target user.

[0068] In one embodiment, if the type of the decision execution instruction is a dialogue communication type, the text recognition result is sent to the corresponding dialogue user. That is, the dialogue content input by the target user's voice is processed by signal enhancement, voice recognition and semantic recognition, and then the text recognition result is sent to the corresponding dialogue user. In addition, when the dialogue text information sent by the dialogue user is received, the dialogue text information is converted into voice information, and the voice information is played, so as to realize the establishment of voice communication between the two ends of the service.

[0069] For example, refer to Figure 3 , Figure 3 This is a flow chart of controlling page jumps provided by an embodiment of the present invention. When the driver is on his way to the loading site, if he receives a text message sent by the current order user, the conversation text message is converted into a voice message, and then the voice message and the user information of the current order user are played, thereby guiding the driver to reply to the message. In other embodiments, when the driver is already loading or unloading, or the order is completed, there is no need to play the message sent by the order user by voice, thereby reducing interference to the driver.

[0070] After receiving the reply information input by the driver's voice, identify whether the driver's reply information matches the wake-up keyword of the voice assistant. If it does, send the reply information input by the driver's voice to the current order user. In addition, it is necessary to detect the status of the message sending. If the message is sent successfully, the voice assistant will respond with a voice message that the message has been sent; if the message fails to be sent, the voice assistant will respond with a voice message that the reply failed, and guide the driver to reply again. By establishing voice communication on both ends of the service, the reading and reply ratio of the message is increased, which not only ensures the driver's driving safety, but also improves the driver's service efficiency.

[0071] In other embodiments, the voice assistant can also perform service functions of the message notification type. When the voice assistant is in the awake state, it can play notification information of various functions by voice, for example, voice playback of weather, order information, user order change notifications, order warning response information, and money arrival notifications.

[0072] In other embodiments, the driver can be reminded of fatigue driving based on the driver's continuous working hours. For example, if it is detected that the driver's continuous working time is greater than a preset time, a voice reminder is given to the driver to pay attention to fatigue driving and to remind him to take a rest.

[0073] Through the above solution, the embodiment of the present invention realizes the introduction of voice wake-up, voice-to-text and other related capabilities when it is inconvenient for users to click and touch, so as to assist the interaction between the driver and the APP in the driving scene. While ensuring the driving safety of the driver, it also improves the driver's service efficiency.

[0074] In one embodiment of the present invention, after performing semantic recognition on the text information and obtaining a text recognition result, the method further includes:

[0075] If the decision execution instruction corresponding to the text recognition result is not found in the instruction library, the similarity between the text recognition result and the decision execution instruction in the instruction library is determined; based on the similarity, query prompt information is generated, and the query prompt information is played.

[0076] Specifically, if the decision execution instruction corresponding to the text recognition result is not found in the instruction library, the similarity between the text recognition result and each decision execution instruction in the instruction library is calculated, for example, cosine similarity, Jaccard similarity, edit distance, etc. Then, according to the similarity, a preset number of instructions are selected, and the preset number can be set according to the actual situation. It will not be repeated here. In one embodiment, the instruction with the highest similarity is selected, and then based on the selected instruction, an inquiry prompt message is generated for playback to ask the user whether he needs to execute the instruction or provide further help, thereby reducing the situation where the user cannot express or does not know how to consult and use the voice interaction function.

[0077] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0078] In one embodiment, a voice interaction device is provided, which corresponds one-to-one to the voice interaction method in the above embodiment. Figure 4 As shown, Figure 4 : is a structural diagram of a voice interaction device in one embodiment of the present invention, the voice interaction device comprising:

[0079] An acquisition module 21 is used to acquire the user's voice interaction information;

[0080] The signal processing module 22 is used to perform signal enhancement processing on the voice interaction information to perform voice recognition on the target enhanced signal to obtain text information;

[0081] The execution module 23 is used to perform semantic recognition on the text information to obtain a text recognition result, so as to execute a corresponding functional operation in the target application according to the text recognition result.

[0082] The signal processing module 22 is also used for:

[0083] Performing feature processing on the target enhanced signal to obtain feature information;

[0084] The acoustic feature information in the feature information is identified using a preset acoustic model.

[0085] The word sequence information in the feature information is identified using a preset language recognition model.

[0086] The text information is generated according to the acoustic feature information and the word sequence information.

[0087] The execution module 23 is also used for:

[0088] Extracting entity information from the text information;

[0089] Performing intent recognition on the text information to obtain user intent;

[0090] The text recognition result is generated based on the entity information and the user intention.

[0091] The execution module 23 is also used for:

[0092] The decision execution instruction corresponding to the text recognition result is searched in a preset instruction library, so as to execute the functional operation corresponding to the decision execution instruction in the target application.

[0093] The execution module 23 is also used for:

[0094] When the type of the decision execution instruction is a page jump type, the page of the target application is controlled to jump to the page corresponding to the decision execution instruction;

[0095] If the type of the decision execution instruction is a navigation service type, generating a corresponding navigation path based on the decision execution instruction;

[0096] If the type of the decision execution instruction is a dialogue communication type, the text recognition result is sent to the corresponding dialogue user; when the dialogue text information sent by the dialogue user is received, the dialogue text information is converted into voice information, and the voice information is played.

[0097] The voice interaction device also includes:

[0098] A determination module, configured to determine the similarity between the text recognition result and the decision execution instruction in the instruction library if the decision execution instruction corresponding to the text recognition result is not found in the instruction library;

[0099] A generating module is used to generate inquiry prompt information based on the similarity and play the inquiry prompt information.

[0100] The voice interaction device also includes:

[0101] The conversion module is used to generate voice feedback information according to the execution result and return it to the target user.

[0102] For the specific definition of the voice interaction device, please refer to the definition of the voice interaction method above, which will not be repeated here. Each module in the above-mentioned voice interaction device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the functional operations corresponding to the above modules.

[0103] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, Figure 5 : is a schematic diagram of a computer device in one embodiment of the present invention. The computer device includes a processor, a memory, a network interface and a database connected by a device bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a readable storage medium and an internal memory. The readable storage medium stores functional operating devices, computer-readable instructions and a database. The internal memory provides an environment for the operation of the functional operating devices and computer-readable instructions in the readable storage medium. The database of the computer device is used to store data involved in the voice interaction method. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer-readable instructions are executed by the processor, a voice interaction method is implemented. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.

[0104] In one embodiment, a computer device is provided. The computer device may be a terminal device, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, and a network interface connected through a device bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a readable storage medium. The readable storage medium stores computer-readable instructions. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer-readable instructions are executed by the processor, a voice interaction method is implemented. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.

[0105] In one embodiment, a computer device is provided, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, and when the processor executes the computer-readable instructions, the steps of the above-mentioned voice interaction method are implemented. The method includes: obtaining voice interaction information of a target user; performing signal enhancement processing on the voice interaction information to perform voice recognition on the target enhanced signal to obtain text information; performing semantic recognition on the text information to obtain a text recognition result, and performing corresponding functional operations in the target application according to the text recognition result.

[0106] In one embodiment, a readable storage medium is provided, the readable storage medium stores computer-readable instructions, and the computer-readable instructions are executed by the processor to implement the above-mentioned voice interaction method steps. A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a non-volatile readable storage medium or a volatile readable storage medium. When the computer-readable instructions are executed, they may include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0107] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0108] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A voice interaction method, characterized in that: include: Obtain voice interaction information of target users; Performing signal enhancement processing on the voice interaction information to perform voice recognition on the target enhanced signal to obtain text information; Semantic recognition is performed on the text information to obtain a text recognition result, so as to execute a corresponding functional operation in the target application according to the text recognition result.

2. The voice interaction method according to claim 1, characterized in that: The step of performing speech recognition on the target enhanced signal to obtain text information includes: Performing feature processing on the target enhanced signal to obtain feature information; The acoustic feature information in the feature information is identified using a preset acoustic model. The word sequence information in the feature information is identified using a preset language recognition model. The text information is generated according to the acoustic feature information and the word sequence information.

3. The voice interaction method according to claim 1, characterized in that: The performing semantic recognition on the text information to obtain a text recognition result includes: Extracting entity information from the text information; Performing intent recognition on the text information to obtain user intent; The text recognition result is generated based on the entity information and the user intention.

4. The voice interaction method according to claim 1, characterized in that: The performing corresponding functional operations in the target application according to the text recognition result includes: The decision execution instruction corresponding to the text recognition result is searched in a preset instruction library, so as to execute the functional operation corresponding to the decision execution instruction in the target application.

5. The voice interaction method according to claim 4, characterized in that: The executing of the functional operation corresponding to the decision execution instruction in the target application includes: When the type of the decision execution instruction is a page jump type, the page of the target application is controlled to jump to the page corresponding to the decision execution instruction; If the type of the decision execution instruction is a navigation service type, generating a corresponding navigation path based on the decision execution instruction; If the type of the decision execution instruction is a dialogue communication type, the text recognition result is sent to the corresponding dialogue user; when the dialogue text information sent by the dialogue user is received, the dialogue text information is converted into voice information, and the voice information is played.

6. The voice interaction method according to claim 1, characterized in that: After performing semantic recognition on the text information and obtaining a text recognition result, the method further includes: If the decision execution instruction corresponding to the text recognition result is not found in the instruction library, determining the similarity between the text recognition result and the decision execution instruction in the instruction library; Based on the similarity, query prompt information is generated, and the query prompt information is played.

7. The voice interaction method according to claim 1, characterized in that: After the target application performs a corresponding functional operation according to the text recognition result, the method further includes: According to the execution result, voice feedback information is generated and returned to the target user.

8. A voice interaction device, characterized in that: include: An acquisition module is used to acquire the user's voice interaction information; A signal processing module, used to perform signal enhancement processing on the voice interaction information, so as to perform voice recognition on the target enhanced signal to obtain text information; The execution module is used to perform semantic recognition on the text information to obtain a text recognition result, so as to execute a corresponding functional operation in a target application according to the text recognition result.

9. A computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executed on the processor, characterized in that: When the processor executes the computer-readable instructions, the voice interaction method according to any one of claims 1 to 7 is implemented.

10. A readable storage medium having computer readable instructions stored thereon, characterized in that: When the computer-readable instructions are executed by a processor, the voice interaction method according to any one of claims 1 to 7 is implemented.

Images