Processing method, terminal device and storage medium

Abstract

The embodiment of the present application discloses a processing method, a terminal device and a storage medium, the method comprising: obtaining voice data in a human-computer interaction process; determining a language style and / or a user intention and / or a keyword according to the voice data; and determining a target reply strategy of a human-computer interaction application for the voice data according to at least one of the language style, the user intention and / or the keyword. The embodiment of the present application can improve the efficiency and accuracy of the reply strategy provided by the terminal device.

Description

Technical Field

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

[0002] With the rapid development of artificial intelligence and the Internet of Things, people have more and more requirements for smart devices, especially in terms of human-computer dialogue, and the requirements for voice recognition, analysis, and response of smart devices are getting higher and higher. In the process of conceiving and implementing this application, the inventor found that there are at least the following problems: smart devices can recognize, analyze, and respond to most voices, but when different users ask the same question to the smart device, there may be problems such as failure to recognize or a relatively single response, resulting in poor user experience.

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

[0004] The present application provides a processing method, a terminal device and a storage medium, which improve the efficiency and accuracy of the terminal device in providing a reply strategy.

[0005] In a first aspect, the present application provides a processing method, comprising:

[0006] Acquire voice data during human-computer interaction;

[0007] Determining language style and / or user intent and / or keywords based on the voice data;

[0008] Determine a target reply strategy of the human-computer interaction application for the voice data according to at least one of the language style, user intention and / or keywords.

[0009] Optionally, determining a target reply strategy of the human-computer interaction application for the voice data according to the language style, user intention and / or keywords includes:

[0010] Determining an initial reply strategy for the voice data according to the user intention and the keyword;

[0011] The initial response strategy is adjusted according to the voice style to obtain a target response strategy of the human-computer interaction application for the voice data.

[0012] Optionally, determining the user intention and / or keywords according to the voice data includes:

[0013] Converting the voice data into text to obtain voice text. Optionally, when the terminal device is in an offline state, converting the voice data into text to obtain voice text.

[0014] The voice text is processed according to a preset expression to determine the user intention and / or keywords corresponding to the preset expression.

[0015] Optionally, the method also includes: when the voice text is processed according to a preset expression and the user intention and / or keywords corresponding to the preset expression are not determined, processing the voice data using a voice processing model to determine the user intention and / or keywords corresponding to the voice processing model.

[0016] Optionally, the method also includes: when the voice data is processed using the voice processing model and the user intention and / or keywords corresponding to the voice processing model are not determined, and / or the terminal device does not switch from an offline state to an online state within a preset time, determining a target reply strategy of the human-computer interaction application for the voice data according to a first reply strategy.

[0017] Optionally, the method further comprises: when the user intention and / or keyword are determined, and / or the terminal device is switched from an offline state to an online state within a preset time, obtaining the user intention and / or keyword corresponding to the voice data determined by the cloud device;

[0018] The user intent and / or keywords determined by the cloud device are fused with the user intent and / or keywords corresponding to the preset expression, or the user intent and / or keywords determined by the cloud device are fused with the user intent and / or keywords corresponding to the speech processing model to obtain the target user intent and / or target keywords.

[0019] Optionally, determining a target reply strategy of the human-computer interaction application for the voice data according to at least one of the language style, user intention and / or keywords includes:

[0020] The target reply strategy is determined according to at least one of the language style, the target user intention and the target keyword.

[0021] Optionally, determining a target reply strategy of the human-computer interaction application for the voice data according to at least one of the language style, user intention and / or keywords includes:

[0022] When the terminal device is in an offline state, determining a second reply strategy of the human-computer interaction application for the voice data according to at least one of the language style, user intention and / or keyword;

[0023] When the second reply strategy is determined, and / or the terminal device switches from an offline state to an online state within a preset time, obtaining a third reply strategy corresponding to the voice data determined by the cloud device;

[0024] A fusion process is performed according to the second reply strategy and the third reply strategy to determine the target reply strategy of the human-computer interaction application for the voice data.

[0025] Optionally, the obtaining a third reply strategy corresponding to the voice data determined by the cloud device includes:

[0026] Sending the voice data to the cloud device so that the cloud device parses and processes the voice data, determines the user intent and / or keywords corresponding to the voice data, and determines a third reply strategy corresponding to the voice data according to the user intent and / or keywords corresponding to the voice data;

[0027] Receive the third reply strategy returned by the cloud device.

[0028] Optionally, before determining the target reply strategy of the human-computer interaction application for the voice data according to at least one of the language style, user intention and / or keywords, the method further includes:

[0029] Performing a fusion process on the user intention and the keyword according to the historical data information to determine the processed user intention and the processed keyword;

[0030] Optionally, determining a target reply strategy of the human-computer interaction application for the voice data according to at least one of the language style, user intention and / or keywords includes:

[0031] Determine a target reply strategy of a human-computer interaction application for the voice data according to at least one of the language style, the processed user intention, and the processed keywords.

[0032] Optionally, the method further includes: determining whether there is an application program in the terminal device that can execute the operation corresponding to the user intention;

[0033] If so, the step of determining a target response strategy of the human-computer interaction application for the voice data based on at least one of the language style, user intention and / or keywords is performed.

[0034] Optionally, the method further comprises: if it does not exist, outputting a prompt message, and optionally, the prompt message indicates an operation error of the user.

[0035] Optionally, determining the language style according to the speech data includes: determining the language style according to the speech data and a trained language style determination model.

[0036] Optionally, the method further comprises: acquiring sample data of sample speech data, the sample data comprising at least one sample speech segment and at least one style identifier of the sample speech segment;

[0037] The initial language style determination model is trained using the at least one sample speech segment and the style identifier of at least one sample speech segment to obtain the trained language style determination model.

[0038] In a second aspect, the present application further provides a data processing device, comprising:

[0039] An acquisition unit, used to acquire voice data during the human-computer interaction process;

[0040] a determination unit, configured to determine a language style and / or a user intention and / or a keyword according to the voice data;

[0041] The determination unit is further configured to determine a target response strategy of the human-computer interaction application for the voice data according to at least one of the language style, user intention and / or keywords.

[0042] In a third aspect, the present application further provides a terminal device, comprising: a memory and a processor, wherein a processing program is stored in the memory, and when the processing program is executed by the processor, the steps of any of the above methods are implemented.

[0043] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein the computer storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0044] As described above, the processing method of the present application obtains voice data in the human-computer interaction process, determines the language style based on the voice data, determines the user's intention and / or keywords based on the voice data, and finally determines the target reply strategy of the human-computer interaction application for the voice data based on at least one of the language style, user intention and / or keywords. It can be seen that through the processing method of the present application, the terminal device can accurately and quickly give the corresponding reply strategy based on the voice data, and can also personalize the reply strategy according to the user's language style. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application. In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor.

[0046] Figure 1 A schematic diagram of the hardware structure of a terminal device for implementing each embodiment of the present application;

[0047] Figure 2 A communication network system architecture diagram provided for an embodiment of the present application;

[0048] Figure 3 It is a flow chart of the first processing method provided in the embodiment of the present application;

[0049] Figure 4 is a schematic diagram of a human-computer interaction provided in an embodiment of the present application;

[0050] Figure 5 It is a flow chart of the second processing method provided in the embodiment of the present application;

[0051] Figure 6 is a schematic diagram of another human-computer interaction provided in an embodiment of the present application;

[0052] Figure 7 It is a flow chart of the third processing method provided in the embodiment of the present application;

[0053] Figure 8 It is a flowchart of the fourth processing method provided in the embodiment of the present application;

[0054] Fig. 9 is a structural schematic diagram of a processing device provided in an embodiment of the present application;

[0055] Fig.10 It is a structural diagram of another terminal device provided in an embodiment of the present application.

[0056] The realization of the purpose, functional features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. The above-mentioned drawings have shown clear embodiments of this application, which will be described in more detail later. These drawings and textual descriptions are not intended to limit the scope of the concept of this application in any way, but to illustrate the concept of this application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0057] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0058] It should be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0059] It should be understood that, although the terms first, second, third, etc. may be used to describe various information in this article, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this article, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination". Furthermore, as used in this article, the singular forms "one", "one" and "the" are intended to also include plural forms, unless there is an opposite indication in the context. It should be further understood that the terms "comprising" and "including" indicate that there are the described features, steps, operations, elements, components, projects, kinds, and / or groups, but do not exclude the existence, occurrence or addition of one or more other features, steps, operations, elements, components, projects, kinds, and / or groups. The terms "or", "and / or", "including at least one of the following" etc. used in this application can be interpreted as inclusive, or mean any one or any combination. For example, “comprising at least one of the following: A, B, C” means “any of the following: A; B; C; A and B; A and C; B and C; A and B and C”, and for another example, “A, B or C” or “A, B and / or C” means “any of the following: A; B; C; A and B; A and C; B and C; A and B and C”. An exception to this definition will only occur when a combination of elements, functions, steps or operations are inherently mutually exclusive in some manner.

[0060] It should be understood that, although the various steps in the flowchart in the embodiment of the present application are displayed in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and it can be performed in other orders. Moreover, at least a portion of the steps in the figure may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and their execution order is not necessarily performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0061] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0062] It should be noted that in this article, step codes such as S301, S302, etc. are used for the purpose of expressing the corresponding content more clearly and concisely, and do not constitute a substantial limitation on the sequence. When implementing the step, those skilled in the art may execute S302 first and then S301, etc., but these should all be within the scope of protection of this application.

[0063] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0064] In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present application, and have no specific meanings. Therefore, "module", "component" or "unit" can be used in a mixed manner.

[0065] The mobile terminal may be implemented in various forms. For example, the mobile terminal described in the present application may include mobile terminals such as mobile phones, tablet computers, laptop computers, PDAs, portable media players (PMPs), navigation devices, wearable devices, smart bracelets, pedometers, etc., as well as fixed terminals such as digital TVs and desktop computers.

[0066] The following description will be made by taking a mobile terminal as an example, and those skilled in the art will understand that, in addition to components specifically used for mobile purposes, the construction according to the embodiments of the present application can also be applied to fixed-type terminals.

[0067] See also Figure 1 , which is a schematic diagram of the hardware structure of a terminal device for implementing various embodiments of the present application, the terminal device 100 may include: RF (Radio Frequency) unit 101, WiFi module 102, audio output unit 103, A / V (audio / video) input unit 104, sensor 105, display unit 106, user input unit 107, interface unit 108, memory 109, processor 110, and power supply 111 and other components. Those skilled in the art can understand that Figure 1 The terminal device structure shown in the figure does not constitute a limitation on the terminal device. The terminal device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0068] Combine the following Figure 1 The following is a detailed introduction to each component of the terminal device:

[0069] The radio frequency unit 101 can be used for receiving and sending signals during information transmission or calls. Specifically, after receiving the downlink information of the base station, it is sent to the processor 110 for processing; optionally, the uplink data is sent to the base station. Generally, the radio frequency unit 101 includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc. In addition, the radio frequency unit 101 can also communicate with the network and other devices through wireless communication. The above-mentioned wireless communication can use any communication standard or protocol, including but not limited to GSM (Global System of Mobile communication), GPRS (General Packet Radio Service), CDMA2000 (Code Division Multiple Access 2000), WCDMA (Wideband Code Division Multiple Access), TD-SCDMA (Time Division-Synchronous Code Division Multiple Access), FDD-LTE (Frequency Division Duplexing-Long Term Evolution) and TDD-LTE (Time Division Duplexing-Long Term Evolution), etc.

[0070] WiFi is a short-range wireless transmission technology. The terminal device can help users send and receive emails, browse web pages and access streaming media through the WiFi module 102. It provides users with wireless broadband Internet access. Figure 1 The WiFi module 102 is shown, but it is understandable that it is not a necessary component of the terminal device and can be omitted as needed without changing the essence of the invention.

[0071] The audio output unit 103 can convert the audio data received by the RF unit 101 or the WiFi module 102 or stored in the memory 109 into an audio signal and output it as sound when the terminal device 100 is in a call signal receiving mode, a call mode, a recording mode, a voice recognition mode, a broadcast receiving mode, etc. Moreover, the audio output unit 103 can also provide audio output related to a specific function performed by the terminal device 100 (for example, a call signal receiving sound, a message receiving sound, etc.). The audio output unit 103 may include a speaker, a buzzer, etc.

[0072] The A / V input unit 104 is used to receive audio or video signals. The A / V input unit 104 may include a graphics processor (GPU) 1041 and a microphone 1042, and the graphics processor 1041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The processed image frame can be displayed on the display unit 106. The image frame processed by the graphics processor 1041 can be stored in the memory 109 (or other storage medium) or sent via the radio frequency unit 101 or the WiFi module 102. The microphone 1042 can receive sound (audio data) via the microphone 1042 in a telephone call mode, a recording mode, a voice recognition mode, and other operating modes, and can process such sound into audio data. The processed audio (voice) data can be converted into a format output that can be sent to a mobile communication base station via the radio frequency unit 101 in the case of a telephone call mode. The microphone 1042 can implement various types of noise elimination (or suppression) algorithms to eliminate (or suppress) noise or interference generated in the process of receiving and sending audio signals.

[0073] The terminal device 100 also includes at least one sensor 105, such as a light sensor, a motion sensor, and other sensors. Optionally, the light sensor includes an ambient light sensor and a proximity sensor. Optionally, the ambient light sensor can adjust the brightness of the display panel 1061 according to the brightness of the ambient light, and the proximity sensor can turn off the display panel 1061 and / or the backlight when the terminal device 100 is moved to the ear. As a type of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in all directions (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that identify the posture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for other sensors that can also be configured on the mobile phone, such as fingerprint sensors, pressure sensors, iris sensors, molecular sensors, gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc., they will not be repeated here.

[0074] The display unit 106 is used to display information input by the user or information provided to the user. The display unit 106 may include a display panel 1061, which may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

[0075] The user input unit 107 can be used to receive input digital or character information, and to generate key signal input related to the user settings and function control of the terminal device. Optionally, the user input unit 107 may include a touch panel 1071 and other input devices 1072. The touch panel 1071, also known as a touch screen, can collect the user's touch operation on or near it (such as the user's operation on the touch panel 1071 or near the touch panel 1071 using any suitable object or accessory such as a finger, stylus, etc.), and drive the corresponding connection device according to a pre-set program. The touch panel 1071 may include two parts: a touch detection device and a touch controller. Optionally, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into the touch point coordinates, and then sends it to the processor 110, and can receive and execute the command sent by the processor 110. In addition, the touch panel 1071 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel 1071, the user input unit 107 may further include other input devices 1072. Optionally, the other input devices 1072 may include but are not limited to at least one of a physical keyboard, a function key (such as a volume control key, a switch key, etc.), a trackball, a mouse, a joystick, etc., which are not specifically limited here.

[0076] Optionally, the touch panel 1071 may cover the display panel 1061. When the touch panel 1071 detects a touch operation on or near it, it transmits the information to the processor 110 to determine the type of touch event. Then, the processor 110 provides corresponding visual output on the display panel 1061 according to the type of touch event. Figure 1 In the embodiment, the touch panel 1071 and the display panel 1061 are used as two independent components to realize the input and output functions of the terminal device. However, in some embodiments, the touch panel 1071 and the display panel 1061 can be integrated to realize the input and output functions of the terminal device, which is not limited here.

[0077] The interface unit 108 is used as an interface through which at least one external device can be connected to the terminal device 100. For example, the external device may include a wired or wireless headset port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device with an identification module, an audio input / output (I / O) port, a video I / O port, a headphone port, etc. The interface unit 108 may be used to receive input (e.g., data information, power, etc.) from an external device and transmit the received input to one or more elements in the terminal device 100 or may be used to transmit data between the terminal device 100 and an external device.

[0078] The memory 109 can be used to store software programs and various data. The memory 109 can mainly include a program storage area and a data storage area. Optionally, the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 109 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0079] The processor 110 is the control center of the terminal device. It uses various interfaces and lines to connect various parts of the entire terminal device. It executes various functions of the terminal device and processes data by running or executing software programs and / or modules stored in the memory 109, and calling data stored in the memory 109, so as to monitor the terminal device as a whole. The processor 110 may include one or more processing units; preferably, the processor 110 may integrate an application processor and a modem processor. Optionally, the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 110.

[0080] The terminal device 100 may also include a power supply 111 (such as a battery) for supplying power to various components. Preferably, the power supply 111 may be logically connected to the processor 110 through a power management system, thereby implementing functions such as charging, discharging, and power consumption management through the power management system.

[0081] although Figure 1 Not shown, the terminal device 100 may also include a Bluetooth module, etc., which will not be described in detail here.

[0082] In order to facilitate understanding of the embodiments of the present application, the communication network system on which the terminal device of the present application is based is described below.

[0083] See also Figure 2 , Figure 2 A communication network system architecture diagram is provided for an embodiment of the present application, wherein the communication network system is an LTE system of universal mobile communication technology, and the LTE system includes a UE (User Equipment) 201, an E-UTRAN (Evolved UMTS Terrestrial Radio Access Network) 202, an EPC (Evolved Packet Core) 203 and an operator's IP service 204, which are connected in sequence for communication.

[0084] Optionally, UE201 may be the above-mentioned terminal 100, which will not be described in detail here.

[0085] E-UTRAN 202 includes eNodeB 2021 and other eNodeBs 2022 , etc. Optionally, eNodeB 2021 may be connected to other eNodeBs 2022 via a backhaul (eg, an X2 interface), and eNodeB 2021 is connected to EPC 203 , and eNodeB 2021 may provide UE 201 with access to EPC 203 .

[0086] EPC203 may include MME (Mobility Management Entity) 2031, HSS (Home Subscriber Server) 2032, other MMEs 2033, SGW (Serving Gate Way) 2034, PGW (PDN Gate Way) 2035 and PCRF (Policy and Charging Rules Function) 2036, etc. Optionally, MME 2031 is a control node that processes signaling between UE 201 and EPC 203, and provides bearer and connection management. HSS 2032 is used to provide some registers to manage functions such as home location register (not shown in the figure), and store some user-specific information such as service features and data rates. All user data can be sent through SGW2034, PGW2035 can provide IP address allocation and other functions for UE 201, PCRF2036 is the policy and charging control policy decision point for service data flow and IP bearer resources, which selects and provides available policy and charging control decisions for the policy and charging execution function unit (not shown in the figure).

[0087] The IP service 204 may include the Internet, an intranet, an IMS (IP Multimedia Subsystem) or other IP services.

[0088] Although the above introduction takes the LTE system as an example, those skilled in the art should know that the present application is not only applicable to the LTE system, but also to other wireless communication systems, such as GSM, CDMA2000, WCDMA, TD-SCDMA and future new network systems, etc., which are not limited here.

[0089] Based on the above-mentioned mobile terminal hardware structure and communication network system, various embodiments of the present application are proposed.

[0090] See also Figure 3 , Figure 3 1 is a flowchart of the first processing method provided in the embodiment of the present application. The method in the embodiment of the present application can be executed by a terminal device or by a server. The method can specifically include the following steps:

[0091] S301: Acquire voice data during human-computer interaction.

[0092] In an embodiment of the present application, when a user is conversing with a terminal device, the terminal device receives the user's voice data and parses the voice data during the human-computer interaction process, thereby providing accurate and fast responses and improving the user's experience.

[0093] S302: Determine language style and / or user intention and / or keywords according to the voice data.

[0094] In an embodiment of the present application, the determining of the language style according to the speech data includes: determining the language style according to the speech data and a trained language style determination model. Optionally, the trained language style determination model is obtained after training with a large amount of sample speech data. Optionally, sample data of the sample speech data is obtained, and the sample data includes at least one sample speech segment and at least one style identifier of the sample speech segment; the initial language style determination model is trained using the at least one sample speech segment and the style identifier of the at least one sample speech segment to obtain the trained language style determination model. It can be understood that when training the initial language style determination model, at least one sample speech segment is subjected to language style identification, that is, language style classification is performed, and then the initial language style determination model is trained using at least one identified sample speech segment to obtain the trained language style determination model.

[0095] It is understandable that the user's language style may include lively, deep, angry, happy, etc. Of course, the classification of language style can be determined according to actual conditions, and the present application embodiment is not limited thereto. Optionally, the terminal device can parse the corresponding language style, user intention and / or keywords according to the voice data, and determine the target reply strategy according to one or more of them. For example: Figure 4As shown, the user triggers human-computer interaction with the terminal device by pressing the operation. If the user inputs the voice data "play a song of Andy Lau", the terminal device interprets the user's intention as "listen to the song", the keywords can be "play the song", "Andy Lau", and the language style is lively, and then the terminal device searches for Andy Lau's songs in the song playing application and / or the browser for playing, and correspondingly determines the reply strategy as "OK, play it right away". Optionally, after searching for Andy Lau in the song playing application, the songs played the most times by the user in the terminal device, and / or the songs ranked at the top in the application, and / or the songs played most recently from the current time, etc. are played first; after searching for Andy Lau in the browser, the songs played the most times by the user in the browser, and / or the songs ranked at the top in the browser, and / or the songs played most recently from the current time, etc. are played first.

[0096] Optionally, the method also includes: determining whether there is an application in the terminal device that can perform the operation corresponding to the user intention; if so, executing the step of determining the target response strategy of the human-computer interaction application for the voice data based on at least one of the language style, user intention and / or keywords; and / or, if not, outputting a prompt message indicating that the user's operation is wrong.

[0097] In an embodiment of the present application, the voice data is parsed to obtain the user's intention and / or keywords, and optionally, it is determined whether there is an application in the terminal device that can perform the operation corresponding to the user's intention. If so, the subsequent steps are continued, and / or, if not, the user is prompted that the operation is wrong. For example, if the voice data is "open Baidu Maps for navigation", the user's intention is "open the Baidu Maps navigation application", and then the terminal device is automatically detected to see whether the Baidu Maps application exists. If so, the subsequent steps of determining the target reply strategy are continued, and / or, if not, the user is prompted that the operation is wrong or prompted whether the user needs to download the application.

[0098] S303: Determine a target reply strategy of the human-computer interaction application for the voice data according to at least one of the language style, the user intention and / or the keywords.

[0099] In an embodiment of the present application, the reply strategy may be a reply strategy database, which includes a one-to-one correspondence between user intent and reply strategy, or a one-to-many correspondence between user intent and reply strategy, or a one-to-one or one-to-many correspondence between keywords and reply strategies. Optionally, each user intent and / or keyword includes a reply strategy of at least one language style. After determining the user's language style, the target reply strategy of the language style may be determined accordingly based on the user intent and / or keywords. Optionally, the target reply strategy of the human-computer interaction application for voice data is determined based on at least one of the language style, user intent and / or keywords.

[0100] Optionally, the determining of the target reply strategy of the human-computer interaction application for the voice data according to the language style, user intention and / or keywords includes: determining an initial reply strategy for the voice data according to the user intention and / or the keywords; adjusting the initial reply strategy according to the language style to obtain the target reply strategy of the human-computer interaction application for the voice data. In the embodiment of the present application, after parsing the user intention and / or keywords according to the voice data, the initial reply strategy corresponding to the user intention and / or keywords can be determined. It can be understood that the initial reply strategy corresponding to the user intention and / or keywords contains at least one reply strategy of language style. Then, after the language style of the user's voice data is determined, the reply strategy of the same style in the initial reply strategy is determined based on the user's language style as the target reply strategy, so that the human-computer dialogue is more harmonious, the problem of single reply is avoided, and the personalized needs of the user are met.

[0101] Optionally, before determining the target response strategy of the human-computer interaction application for the voice data based on at least one of the language style, user intent and / or keywords, the method further includes: fusing the user intent and the keywords based on historical data information to determine the processed user intent and the processed keywords; Optionally, determining the target response strategy of the human-computer interaction application for the voice data based on at least one of the language style, user intent and / or keywords includes: determining the target response strategy of the human-computer interaction application for the voice data based on at least one of the language style, the processed user intent and the processed keywords.

[0102] In the embodiment of the present application, the user intention and / or keywords are obtained by parsing the voice data. To prevent parsing errors, the parsed user intention and / or keywords can be fused through historical data information to achieve accurate parsing of the voice data and improve the efficiency and accuracy of the reply. For example, if the current voice data is "the way home", the user intention obtained by parsing is "listening to music", and the keyword is "the way home". By detecting the historical data information, it can be known that there is voice data "going to school" in the historical dialogue information, and the user intention obtained by parsing is "route navigation", and the keyword is "navigation to school". The user did go to school based on navigation. At this time, the user intention and / or keywords obtained by parsing the voice data "the way home" are corrected based on the historical data information, and the processed user intention "route navigation" and the processed keyword "go home" are obtained. Finally, according to at least one of the language style of the voice data, the processed user intention and the processed keyword, the target reply strategy of the human-computer interaction application for the voice data is determined, so that the target reply strategy can not only meet the personalized requirements of the user, but also accurately reply to the voice data. It is understandable that the historical data information can be divided into time periods, such as data information within 10, 2, or 28 hours from the current time. Optionally, the parsed user intent and / or keywords can be fused according to the priority of the application to obtain processed user intent and processed keywords, such as the priority of song playback applications is higher than the priority of navigation applications, the priority of applications used closer to the current time is higher than the priority of applications used farther from the current time, and / or the priority of applications used more times in the historical data information is higher than the priority of applications used less times.

[0103] It can be seen that in the embodiments of the present application, by acquiring voice data in the human-computer interaction process, determining the language style based on the voice data, determining the user intention and / or keywords based on the voice data, and finally determining the target reply strategy of the human-computer interaction application for the voice data based on at least one of the language style, user intention and / or keywords, the terminal device can accurately and quickly give a corresponding reply strategy based on the voice data, and can also personalize the reply strategy based on the user's language style.

[0104] See also Figure 5 , Figure 5 : is a flow chart of the second processing method provided in the embodiment of the present application. The method in the embodiment of the present application can be executed by a terminal device or by a server. The method can specifically include the following steps:

[0105] S501: Acquire voice data during the human-computer interaction process.

[0106] S502: Convert the voice data into text to obtain voice text.

[0107] Optionally, when the terminal device is in an offline state, the voice data is converted into text to obtain the voice text. In another implementation, the terminal device can also convert the voice data into text online to obtain the voice text.

[0108] In an embodiment of the present application, when voice data is acquired, the network status of the terminal device is detected. If the current terminal device is offline and cannot perform voice analysis online, the voice data is first converted into text to obtain a text-type voice text, so that the terminal device can analyze the voice data in the human-computer interaction process when it is offline and make corresponding replies, thereby avoiding the situation where any voice data of the user cannot be processed and a corresponding reply strategy cannot be given when the terminal device is offline, thereby greatly improving the user experience.

[0109] S503: Process the voice text according to a preset expression to determine the user intention and / or keywords corresponding to the preset expression.

[0110] In an embodiment of the present application, the voice text is matched with a preset expression to determine the user intent and / or keywords corresponding to the preset expression. Optionally, when the user intent and / or keywords are determined, and / or the terminal device is switched from an offline state to an online state within a preset time, the user intent and / or keywords corresponding to the voice data determined by the cloud device are obtained; the user intent and / or keywords determined by the cloud device are fused with the user intent and / or keywords corresponding to the preset expression to obtain the target user intent and / or target keywords. In an embodiment of the present application, when the user intent and / or keywords are determined by a preset expression, and / or it is detected that the terminal device is switched to an online state within a preset time, the user intent and / or keywords determined by the cloud device are fused with the user intent and / or keywords corresponding to the preset expression, that is, the user intent and / or keywords determined in the preset expression are corrected to obtain the target user intent and / or target keywords, such as Figure 6As shown, if the user intent and keywords determined in the preset expression do not match the user intent and keywords determined by the cloud device, the target user intent and keywords are obtained by fusion processing, and then the target reply strategy is obtained; optionally, if the target user intent and / or target keyword are different from the user intent and / or keyword corresponding to the preset expression, the preset expression is adjusted and updated so that the updated preset expression can more accurately parse the voice data, thereby improving the accuracy of the voice parsing and reply strategy in the offline state. Optionally, when the language style of the voice data is determined according to the language style determination model in the offline state, and / or when the terminal device switches from the offline state to the online state within a preset time, the language style corresponding to the voice data determined by the cloud device is obtained, and the language style determined by the cloud device is fused with the language style corresponding to the language style model to obtain the target language style. In the embodiment of the present application, when the language style determined by the cloud device does not match the language style corresponding to the language style determination model, the language style determined by the cloud device is used as the target language style, and the language style determination model is adjusted and updated so that the updated language style determination model can more accurately determine the language style of the voice data, thereby further improving the accuracy of determining the target reply strategy.

[0111] S504: Determine a target reply strategy of the human-computer interaction application for the voice data based on at least one of the language style determined from the voice data, the user intent corresponding to the preset expression, and / or the keywords corresponding to the preset expression.

[0112] In an embodiment of the present application, an initial response strategy is determined based on the user intent and / or keywords corresponding to a preset expression, and then the initial response strategy is adjusted based on the language style to obtain a target response strategy. Of course, the target response strategy of the human-computer interaction application for voice data can be determined based on any one or both of the language style determined based on the voice data, the user intent and / or keywords corresponding to the preset expression.

[0113] It can be seen that in the embodiment of the present application, voice data is obtained during the human-computer interaction process, and when the terminal device is in an offline state, the voice data is converted into text to obtain voice text; the voice text is processed according to a preset expression, and the user intention and / or keywords corresponding to the preset expression are determined; then, based on at least one of the language style determined by the voice data, the user intention and / or keywords corresponding to the preset expression, the target reply strategy of the human-computer interaction application for the voice data is determined, so that when the terminal device is in an offline state, the voice data can be accurately analyzed and the target reply strategy can be quickly given.

[0114] See also Figure 7 , Figure 7: is a flowchart of a third processing method provided in an embodiment of the present application. The method in the embodiment of the present application can be executed by a terminal device or by a server. The method can specifically include the following steps:

[0115] S701: Acquire voice data during the human-computer interaction process.

[0116] S702: Convert the voice data into text to obtain voice text.

[0117] S703: Process the speech text according to a preset expression. If the user intent and / or keywords corresponding to the preset expression are not determined, process the speech data using a speech processing model to determine the user intent and / or keywords corresponding to the speech processing model.

[0118] In an embodiment of the present application, before using a speech processing model to process speech data, the speech processing model is trained with a large amount of data, that is, the speech data is processed with the trained speech processing model. The specific training may include: obtaining sample data of sample speech data, the sample data including at least one sample speech data and sample user intent and sample keywords of each sample speech data; using the at least one sample speech data, the sample user intent and the sample keywords to train the initial speech processing model to obtain a trained speech processing model. Optionally, the training of the speech processing model may be specifically implemented according to deep learning (recurrent neural network, convolutional neural network) and / or multi-task learning. When the speech text is processed according to a preset expression and the user intent and / or keywords corresponding to the preset expression are not determined, the speech data is processed using the trained speech processing model to determine the user intent and / or keywords corresponding to the speech processing model.

[0119] Optionally, when the user intention and / or keywords are determined according to the speech processing model, and / or the terminal device switches from an offline state to an online state within a preset time, the user intention and / or keywords corresponding to the speech data determined by the cloud device are obtained; the user intention and / or keywords determined by the cloud device are fused with the user intention and / or keywords corresponding to the speech processing model to obtain the target user intention and / or target keywords. In an embodiment of the present application, when the user intention and / or keywords are determined by the speech processing model, and it is detected that the terminal device switches to an online state within a preset time, the user intention and / or keywords determined by the cloud device are fused with the user intention and / or keywords corresponding to the speech processing model, that is, the user intention and / or keywords obtained by the speech processing model are corrected to obtain the target user intention and / or target keywords; optionally, if the target user intention and / or target keywords are different from the user intention and / or keywords corresponding to the speech processing model, the speech processing model is trained and updated, so that the updated speech processing model can more accurately parse the speech data, and improve the accuracy of speech parsing and reply strategies in offline states.

[0120] Optionally, when the voice data is processed using the voice processing model and the user intention and / or keywords corresponding to the voice processing model are not determined, and / or the terminal device does not switch from an offline state to an online state within a preset time, the target reply strategy of the human-computer interaction application for the voice data is determined according to the first reply strategy.

[0121] In an embodiment of the present application, when the user intent and / or keywords are not determined according to the preset expression processing, and / or the user intent and / or keywords corresponding to the voice processing model are not determined according to the voice processing model, and / or the terminal device is not switched from an offline state to an online state within a preset time, the target reply strategy is determined according to the first reply strategy, i.e., the default reply strategy. It can be understood that the first reply strategy includes reply strategies of multiple language styles, and when determining the target reply strategy for voice data in a human-computer interaction application, it can be determined in the first reply strategy according to the language style corresponding to the user voice data.

[0122] S704: Determine a target reply strategy of the human-computer interaction application for the voice data based on at least one of the language style determined by the voice data, the user intent corresponding to the voice processing model, and / or the keywords corresponding to the voice processing model.

[0123] In an embodiment of the present application, an initial response strategy is determined based on the user intent and / or keywords corresponding to the speech processing model, and then the initial response strategy is adjusted based on the language style to obtain a target response strategy. Of course, the target response strategy for the speech data of the human-computer interaction application can be determined based on any one or both of the language style determined by the speech data, the user intent corresponding to the speech processing model, and / or the keywords corresponding to the speech processing model.

[0124] It can be seen that in the embodiment of the present application, voice data is obtained during the human-computer interaction process, and when the terminal device is in an offline state, the voice data is converted into text to obtain voice text, and the voice text is processed according to a preset expression. If the user intent and / or keywords corresponding to the preset expression are not determined, the voice data is processed using a voice processing model to determine the user intent and / or keywords corresponding to the voice processing model. Finally, based on at least one of the language style determined by the voice data, the user intent corresponding to the voice processing model, and / or the keywords corresponding to the voice processing model, the target reply strategy of the human-computer interaction application for the voice data is determined, so that when the terminal device is in an offline state and the preset expression does not parse the user intent and / or keywords, the voice data is processed by the voice processing model to accurately parse the user intent and / or keywords corresponding to the voice data, and quickly give the target reply strategy of the corresponding language style, thereby avoiding the singleness of the reply strategy and improving the user experience.

[0125] See also Figure 8 , Figure 8 : is a flowchart of the fourth processing method provided in the embodiment of the present application. The method in the embodiment of the present application can be executed by a terminal device or by a server. The method can specifically include the following steps:

[0126] S801. Acquire voice data during the human-computer interaction process.

[0127] S802: Determine language style and / or user intention and / or keywords according to voice data.

[0128] In the embodiment of the present application, if the network status of the terminal device is detected to be offline, the language style and / or user intent and / or keywords are determined based on the voice data. It is understandable that the language style of the voice data can be determined by a trained language style determination model, and the user intent and / or keywords corresponding to the voice data can be determined by a preset expression and / or a trained voice processing model.

[0129] S803: Determine a second reply strategy of the human-computer interaction application for the voice data according to at least one of the language style, the user intention and / or the keywords.

[0130] In the embodiment of the present application, an initial reply strategy is determined according to user intent and / or keywords, and then the initial reply strategy is adjusted according to the language style to obtain a second reply strategy. It is understandable that the second reply strategy of the human-computer interaction application for voice data can be determined according to one, two or three of the language style, user intent and / or keywords.

[0131] S804: When the second reply strategy is determined and the terminal device switches from an offline state to an online state within a preset time, a third reply strategy corresponding to the voice data determined by the cloud device is obtained.

[0132] Optionally, the obtaining of the third reply strategy corresponding to the voice data determined by the cloud device includes: sending the voice data to the cloud device so that the cloud device parses and processes the voice data, determines the user intent and / or keywords corresponding to the voice data, and determines the third reply strategy corresponding to the voice data according to the user intent and / or keywords corresponding to the voice data; and receiving the third reply strategy returned by the cloud device. In the embodiment of the present application, when the second reply strategy is determined and it is detected that the terminal device switches from an offline state to an online state within a preset time, the voice data is sent to the cloud device so that the cloud device parses the voice data to obtain the user intent and / or keywords corresponding to the cloud device, and generates a third reply strategy according to the user intent and / or keywords, and then receives the third reply strategy returned by the cloud device. It can be understood that the cloud device also determines the corresponding language style according to the voice data, and then determines the target reply strategy of the human-computer interaction application for the voice data according to any one or more of the language style, the user intent corresponding to the cloud device, and / or the keywords corresponding to the cloud device.

[0133] S805: Perform fusion processing according to the second reply strategy and the third reply strategy to determine a target reply strategy for the human-computer interaction application with respect to the voice data.

[0134] In the embodiment of the present application, the second reply strategy determined in the offline state and the third reply strategy determined in the online state are integrated to determine the target reply strategy for the voice data of the human-computer interaction application. It can be understood that when the second reply strategy and the third reply strategy are not optional, the third reply strategy is preferred as the target reply strategy; of course, the reply strategy database in the offline state is updated and improved accordingly.

[0135] It can be seen that in an embodiment of the present application, voice data is obtained during the human-computer interaction process, and when the terminal device is in an offline state, the language style is determined according to the voice data, and the user intention and / or keywords are determined according to the voice data. When the second reply strategy is determined and the terminal device switches from an offline state to an online state within a preset time, a third reply strategy corresponding to the voice data determined by the cloud device is obtained, and the second reply strategy and the third reply strategy are fused and processed to determine the target reply strategy of the human-computer interaction application for the voice data, so that the reply strategies in the offline state and the online state are fused and processed to obtain a more accurate target reply strategy, thereby improving the reliability and accuracy of the terminal device's reply.

[0136] See also Fig. 9 , Fig. 9 1 is a schematic diagram of the structure of a data processing device provided in an embodiment of the present application, which can be mounted on a terminal device in the above method embodiment, and the device can specifically be a server. Optionally, in some embodiments, it can also be mounted on a terminal device. Fig. 9 The processing device shown can be used to perform the above Figure 3 , Figure 5 , Figure 7-Figure 8 Part or all of the functions of the method embodiment described. The detailed description of each module is as follows:

[0137] The acquisition unit 901 is used to acquire the voice data during the human-computer interaction process;

[0138] A determination unit 902, configured to determine a language style and / or a user intention and / or a keyword according to the voice data;

[0139] The determining unit 902 is further configured to determine a target reply strategy of the human-computer interaction application for the voice data according to at least one of the language style, user intention and / or keywords.

[0140] Optionally, in terms of determining a target response strategy for the voice data by the human-computer interaction application based on at least one of the language style, user intent and / or keywords, the determination unit 902 is specifically used to: determine an initial response strategy for the voice data based on the user intent and the keywords; adjust the initial response strategy based on the voice style to obtain a target response strategy for the voice data by the human-computer interaction application.

[0141] Optionally, in terms of determining user intent and / or keywords based on the voice data, the determination unit 902 is specifically used to: when the terminal device is in an offline state, convert the voice data into text to obtain voice text; process the voice text according to a preset expression to determine the user intent and / or keywords corresponding to the preset expression.

[0142] Optionally, the determination unit 902 is also used to process the voice data using a voice processing model to determine the user intention and / or keywords corresponding to the voice processing model when the voice text is processed according to a preset expression and the user intention and / or keywords corresponding to the preset expression are not determined.

[0143] Optionally, the determination unit 902 is also used to determine the target reply strategy of the human-computer interaction application for the voice data according to the first reply strategy when the voice data is processed using the voice processing model and the user intention and / or keywords corresponding to the voice processing model are not determined, and the terminal device is not switched from an offline state to an online state within a preset time.

[0144] Optionally, the acquisition unit 901 is also used to obtain the user intention and / or keywords corresponding to the voice data determined by the cloud device when the user intention and / or keywords are determined and the terminal device switches from an offline state to an online state within a preset time.

[0145] The processing unit 903 is used to fuse the user intention and / or keywords determined by the cloud device with the user intention and / or keywords corresponding to the preset expression, or to fuse the user intention and / or keywords determined by the cloud device with the user intention and / or keywords corresponding to the speech processing model to obtain the target user intention and / or target keyword.

[0146] Optionally, in terms of determining a target response strategy of a human-computer interaction application for the voice data based on at least one of the language style, user intent and / or keywords, the determination unit 902 is specifically used to determine the target response strategy based on at least one of the language style, the target user intent and the target keywords.

[0147] Optionally, in terms of determining the target reply strategy of the human-computer interaction application for the voice data according to at least one of the language style, user intention and / or keywords, the determining unit 902 is further configured to determine, when the terminal device is in an offline state, a second reply strategy of the human-computer interaction application for the voice data according to at least one of the language style, user intention and / or keywords;

[0148] The acquisition unit 901 is further configured to, when the second reply strategy is determined and the terminal device switches from an offline state to an online state within a preset time, acquire a third reply strategy corresponding to the voice data determined by the cloud device;

[0149] The processing unit 903 is further configured to perform fusion processing according to the second reply strategy and the third reply strategy to determine the target reply strategy of the human-computer interaction application for the voice data.

[0150] Optionally, the acquiring unit 901 is used to acquire a third reply strategy corresponding to the voice data determined by the cloud device, specifically including:

[0151] Send the voice data to the cloud device so that the cloud device parses and processes the voice data, determines the user intent and / or keywords corresponding to the voice data, and determines a third reply strategy corresponding to the voice data based on the user intent and / or keywords corresponding to the voice data; and receives the third reply strategy returned by the cloud device.

[0152] Optionally, the processing unit 903 is further configured to perform fusion processing on the user intention and the keyword according to the historical data information to determine a processed user intention and a processed keyword;

[0153] Optionally, the determining unit 902 determines a target reply strategy of the human-computer interaction application for the voice data according to at least one of the language style, user intention and / or keywords, specifically including:

[0154] Determine a target reply strategy of a human-computer interaction application for the voice data according to at least one of the language style, the processed user intention, and the processed keywords.

[0155] Optionally, the determination unit 902 is also used to determine whether there is an application in the terminal device that can perform the operation corresponding to the user intention; if so, execute the step of determining the target response strategy of the human-computer interaction application for the voice data based on at least one of the language style, user intention and / or keywords.

[0156] Optionally, the output unit 904 is configured to output a prompt message if it does not exist, wherein the prompt message indicates an operation error of the user.

[0157] Optionally, the determining unit 902 determines the language style according to the speech data, specifically including: determining the language style according to the speech data and a trained language style determination model.

[0158] Optionally, the acquisition unit 901 is further configured to acquire sample data of sample speech data, wherein the sample data includes at least one sample speech segment and at least one style identifier of the sample speech segment;

[0159] The processing unit 903 is further configured to train the initial language style determination model using the at least one sample speech segment and the style identifier of the at least one sample speech segment to obtain the trained language style determination model.

[0160] According to one embodiment of the present application, Figure 3 , Figure 5 , Figure 7-Figure 8 Some of the steps involved in the processing method shown can be represented by Fig. 9 The processing device shown is executed by each module. Fig. 9 The various units in the processing device shown can be respectively or completely combined into one or several other modules to constitute, or some of the modules can also be split into multiple smaller units in function to constitute, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present application. The above-mentioned units are divided based on logical functions. In practical applications, the functions of a module can also be implemented by multiple modules, or the functions of multiple modules can be implemented by one module. In other embodiments of the present application, the data processing device can also include other modules. In practical applications, these functions can also be implemented with the assistance of other modules, and can be implemented by the collaboration of multiple modules.

[0161] See also Fig.10 , Fig.10 1001, a processor 1002, and a processing program stored in the memory 1001 and executable on the processor 1002. When the processing program is executed by the processor, the steps of the processing method in any of the above embodiments are implemented.

[0162] The present application also provides a computer-readable storage medium, on which a processing program is stored. When the processing program is executed by a processor, the steps of the processing method in any of the above embodiments are implemented.

[0163] In the embodiments of the mobile terminal and computer-readable storage medium provided in the present application, all technical features of the embodiments of the above-mentioned processing methods are included, and the expansion and explanation content of the specification are basically the same as those of the embodiments of the above-mentioned methods, and will not be repeated here.

[0164] The embodiment of the present application further provides a computer program product, which includes a computer program code. When the computer program code runs on a computer, the computer executes the methods in the above various possible implementation modes.

[0165] An embodiment of the present application also provides a chip, including a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that a device equipped with the chip executes the methods in various possible implementation modes as described above.

[0166] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0167] The steps in the method of the embodiment of the present application can be adjusted in order, combined and deleted according to actual needs.

[0168] The units in the device of the embodiment of the present application can be merged, divided and deleted according to actual needs.

[0169] In the present application, the same or similar terminology concepts, technical solutions and / or application scenario descriptions are generally described in detail only the first time they appear. When they appear again later, they are generally not repeated for the sake of brevity. When understanding the technical solutions and other contents of the present application, for the same or similar terminology concepts, technical solutions and / or application scenario descriptions that are not described in detail later, reference can be made to the previous related detailed descriptions.

[0170] In the present application, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0171] The various technical features of the technical solution of the present application can be arbitrarily combined. In order to make the description concise, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of the present application.

[0172] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, a controlled terminal, or a network device, etc.) to execute the method of each embodiment of the present application.

[0173] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loading and executing computer program instructions on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server, a data center, etc. that contains one or more available media integrated. The available medium can be a magnetic medium, (e.g., a floppy disk, a storage disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state storage disk Solid State Disk (SSD)), etc.

[0174] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A processing method, characterized in that: The following steps are involved: S301: Acquiring voice data during the human-computer interaction process; S302: Determine language style and / or user intention and / or keywords according to the voice data; When the user intention and / or keyword are determined, and / or the terminal device switches from an offline state to an online state within a preset time, obtaining the user intention and / or keyword corresponding to the voice data determined by the cloud device; The user intent and / or keywords determined by the cloud device are integrated with the user intent and / or keywords corresponding to the preset expression, or the user intent and / or keywords determined by the cloud device are integrated with the user intent and / or keywords corresponding to the speech processing model to obtain the target user intent and / or target keyword; If the target user intention and / or target keyword are different from the user intention and / or keyword corresponding to the preset expression, the preset expression is adjusted and updated, or if the target user intention and / or target keyword are different from the user intention and / or keyword corresponding to the speech processing model, the speech processing model is trained and updated, wherein the preset expression and the speech processing model are used for speech data analysis; Performing a fusion process on the target user intention and the target keyword according to the historical data information to determine the processed user intention and the processed keyword, wherein the historical data information includes at least one of the following: historical conversation information, historical data information within a preset time period, and priority of an application program; Determine whether there is an application program in the terminal device that can perform the operation corresponding to the processed user intention, if so, execute step S303, if not, output a prompt message indicating that the user's operation is wrong or prompting the user whether to download the application program; S303: Determining a target reply strategy of the human-computer interaction application for the voice data according to at least one of the language style, the processed user intent, and / or the processed keywords, including: Determining an initial reply strategy for the voice data according to the processed user intent and / or the processed keywords; The initial response strategy is adjusted according to the language style to obtain a target response strategy for the voice data by a human-computer interaction application.

2. The method according to claim 1, characterized in that The step S302 includes: Converting the speech data into text to obtain speech text; The voice text is processed according to a preset expression to determine the user intention and / or keywords corresponding to the preset expression.

3. The method according to claim 2, characterized in that The method further comprises: When the voice text is processed according to the preset expression and the user intention and / or keywords corresponding to the preset expression cannot be determined, the voice data is processed using a voice processing model to determine the user intention and / or keywords corresponding to the voice processing model.

4. The method according to claim 3, characterized in that The method further comprises: When the voice data is processed using the voice processing model and the user intention and / or keywords corresponding to the voice processing model are not determined, and / or the terminal device does not switch from an offline state to an online state within a preset time, a target reply strategy for the human-computer interaction application for the voice data is determined according to the first reply strategy.

5. The method according to any one of claims 1 to 4, characterized in that The step S303 includes: When the terminal device is in an offline state, determining a second reply strategy of the human-computer interaction application for the voice data according to at least one of the language style, user intention and / or keyword; When the second reply strategy is determined, and / or the terminal device switches from an offline state to an online state within a preset time, obtaining a third reply strategy corresponding to the voice data determined by the cloud device; A fusion process is performed according to the second reply strategy and the third reply strategy to determine the target reply strategy of the human-computer interaction application for the voice data.

6. The method according to claim 5, characterized in that The obtaining of a third reply strategy corresponding to the voice data determined by the cloud device includes: Sending the voice data to the cloud device so that the cloud device parses and processes the voice data, determines the user intent and / or keywords corresponding to the voice data, and determines a third reply strategy corresponding to the voice data according to the user intent and / or keywords corresponding to the voice data; Receive the third reply strategy returned by the cloud device.

7. The method according to any one of claims 1 to 4, characterized in that Determining a language style according to the voice data includes: The language style is determined according to the speech data and the trained language style determination model.

8. The method according to claim 7, characterized in that The method further comprises: Acquire sample data of sample speech data, wherein the sample data includes at least one sample speech segment and at least one style identifier of the sample speech segment; The initial language style determination model is trained using the at least one sample speech segment and the style identifier of at least one sample speech segment to obtain the trained language style determination model.

9. A terminal device, characterized in that: The mobile terminal comprises: a memory and a processor, wherein a processing program is stored in the memory, and when the processing program is executed by the processor, the steps of the processing method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the processing method according to any one of claims 1 to 8 are implemented.

Images