WO2021159904A1

WO2021159904A1 - Voice data processing method and device for intelligent voice conversation system

Info

Publication number: WO2021159904A1
Application number: PCT/CN2021/071367
Authority: WO
Inventors: 彭殷路; 孔冬兵
Original assignee: 升智信息科技(南京)有限公司
Priority date: 2020-02-11
Filing date: 2021-01-13
Publication date: 2021-08-19
Also published as: CN111402872B; CN111402872A

Abstract

A voice data processing method and device for an intelligent voice conversation system, a computer apparatus, and a storage medium. The method comprises: defining each service component of an intelligent voice conversation system as an initial expansion function, and enabling the initial expansion function to complete independent logic calling or service calling, and to support modular reuse (S10); implementing and releasing the initial expansion function, such that the initial expansion function is present in a function library of the intelligent voice conversation system and is available to a user (S20); configuring the initial expansion function in the function library so as to acquire a target expansion function (S30); and using the target expansion function to process voice data of the user during a call so as to acquire content represented by the voice data (S40). The method improves efficiency of corresponding voice data processing in an intelligent voice conversation system, and improves flexibility of related session management.

Description

Voice data processing method and device for intelligent voice dialogue system

Technical field

The present invention relates to the technical field of voice signal processing, in particular to a voice data processing method, device, computer equipment and storage medium used in an intelligent voice dialogue system.

Background technique

Intelligent voice dialogue system, also known as intelligent conversation agent or intelligent chat system. It refers to a system that realizes language interaction with humans through artificial intelligence technology, based on speech recognition, natural language processing and speech synthesis technology. Intelligent voice dialogue systems are mainly divided into task-oriented dialogue systems and non-task-oriented dialogue systems from the application scenarios. Typical task-oriented dialogue systems such as intelligent voice assistants and smart phone outbound systems, and typical non-task-oriented systems such as Smart speakers, chat robots, etc.

The human-computer interaction link of the traditional intelligent voice dialogue system mainly includes three stages: speech recognition, semantic understanding and speech synthesis. Speech recognition is to convert the speech spoken by the user into the corresponding text; semantic understanding is to extract the user's intention from the text-level dialogue context and other information expressed by the user and generate the response text; speech synthesis refers to the conversion of the response text into speech and Play to the user. Speech recognition and speech synthesis technology have strong versatility, that is, the type and application of intelligent speech dialogue systems are different, and even the configuration of interactive speech templates will not have a greater impact on their effects.

The semantic understanding in the traditional intelligent speech dialogue system has a strong correlation between the dialogue field and the dialogue scene. Although the general natural language understanding model solves the technical problems of text intention determination and named entity recognition to a certain extent, there are still some problems. The needs of many user scenarios in different fields cannot be met based on traditional semantic understanding solutions, which directly lead to the problems of unintelligent dialogue and a very poor sense of actual dialogue experience. Experienced speech configuration engineers can to a certain extent alleviate the problem of dialogue experience through the configuration of speech skills, but this also leads to the complexity of a single speech to a certain extent, and it is more likely to appear in the process of dialogue with users. The problem of technical logic. In particular, task-oriented intelligent voice dialogue systems often need to interface with external systems to obtain data to obtain user-related data, or send instructions to external systems to help users complete actual task operations. The traditional solution is to complete related functions through customized development. , The main problems are the long development and integration cycle, the realization of functions cannot meet the requirements of complex speech configuration, and the ability to handle complex business events in the dialogue process. At the same time, the scalability and maintainability of the system are very poor. , The function of the system is mixed with the configuration of speech skills, and it is necessary to update the system to realize the update of speech skills.

Generally speaking, the traditional intelligent voice dialogue system realizes the on-line and delivery of dialogue services through speech and speech processes. For example, the outbound sales system of smart phones will have operators who count, sort and summarize some sales based on sales scenarios. The champion's words and the flow of words. In the process of outbound conversation, the system will perform intent recognition and conversation management according to the design of speech and speech flow.

Common speech skills and structured methods of speech flow and conversation management methods include:

A simple interactive structure based on keywords, that is, to determine the user's intention through the matching of keywords and key phrases, and respond according to the user's intention. A typical implementation method is AIML (Artificial Intelligence Markup Language). This method can support simple context understanding and multi-lens dialogue capabilities based on limited keywords, and is generally common in early non-task-oriented intelligent voice dialogue systems.

A structured template based on a tree or a finite state machine, that is, modeling speech and speech flow as a tree structure or a graph structure of a finite state machine, compared to a simple interactive structure based on keywords, a tree and a finite state machine speech The flow structure method can integrate more conversation context during the conversation, and can combine the resources obtained in the conversation with the user information obtained through other means to provide more flexible and personalized conversation services. This method needs to artificially define the dialogue process according to the dialogue scene. It is suitable for task-oriented scenarios where the dialogue is completely guided by the system. It is suitable for simple tasks. The disadvantage is that it is difficult to expand. It is easy to make the speech flow process complicated and difficult to maintain. Input comparison Limited, the operational flexibility of the speech flow is poor.

A framework template based on named entity recognition, that is, a framework speech flow template based on slot value extraction, this technical solution usually models the speech flow process as a slot value extraction process. The so-called slot value extraction is to extract the information that needs to be completed to understand the user's intention according to the type of information from the expression, and transform it into a clear instruction or response according to the completion status of all the slot value information required by the task. In terms of specific implementation, the framework based on named entity recognition is usually used as an extension of the finite state machine phone process template to obtain relatively complex information and support the types and sequence of information input, and enhance the system to support task-oriented and non-task-oriented The ability to mix scenes of different types.

As human language expression has the three characteristics of complexity, randomness and irrationality, traditional speech and speech flow structured methods and conversation management often have problems of complex processes and low flexibility.

Summary of the invention

In view of the above problems, the present invention proposes a voice data processing method, device, computer equipment and storage medium for an intelligent voice dialogue system.

In order to achieve the purpose of the present invention, a voice data processing method for an intelligent voice dialogue system is provided, which includes the following steps:

S10: Define each service component of the intelligent voice dialogue system as an initial expansion function, so that the initial expansion function has the function of completing independent logic calls or business calls, and supporting modular multiplexing;

S20. Implement and publish the initial expansion function, so that the initial expansion function is in the function library of the intelligent voice dialogue system for users to use;

S30, configure the initial expansion function in the function library to obtain the target expansion function;

S40: Use the target extension function to process the voice data of the user during the call, so as to obtain the content represented by the voice data.

In one embodiment, implementing and publishing the initial extension function includes:

Realize and develop the initial expansion function according to the specific definition of the initial expansion function and the functional requirements of the initial expansion function.

In one embodiment, configuring the initial expansion function in the function library to obtain the target expansion function includes:

Use an initial expansion function in the function library as the input of another initial expansion function to obtain a customized target expansion function.

In one embodiment, using the target expansion function to process the voice data input by the user to obtain the content represented by the voice data includes:

According to the initial expansion function and the target expansion function provided in the function library, the function configuration is performed on the nodes of the speech art, and the configured function is used to define the intention and information of the user's voice data characterization during the call.

A voice data processing device for an intelligent voice dialogue system, including:

The definition module is used to define each business component of the intelligent voice dialogue system as an initial expansion function, so that the initial expansion function can complete independent logic calls or business calls, and support modular multiplexing;

The realization module is used to realize and publish the initial expansion function, so that the initial expansion function is in the function library of the intelligent voice dialogue system for users to use;

The configuration module is used to configure the initial expansion function in the function library to obtain the target expansion function;

The processing module is used to process the voice data of the user during the call by using the target extension function to obtain the content represented by the voice data.

In an embodiment, the implementation module is further used for:

In an embodiment, the configuration module is further used for:

In an embodiment, the processing module is further used for:

According to the initial expansion function and the target expansion function provided in the function library, the function configuration is performed on the node of the speech art, and the configured function is used to define the intention and information of the user's voice data characterization during the call.

A computer device includes a memory, a processor, and a computer program stored on the memory and running on the processor. When the processor executes the computer program, it implements the intelligent voice dialogue system in any one of the above embodiments. The steps of the voice data processing method.

A computer-readable storage medium has a computer program stored thereon, and when the computer program is executed by a processor, the steps of the voice data processing method for an intelligent voice dialogue system of any one of the above embodiments are realized.

In the above-mentioned voice data processing method, device, computer equipment and storage medium for the intelligent voice dialogue system, each service component of the intelligent voice dialogue system is defined as an initial expansion function, so that the initial expansion function can complete independent logical calls or Service call and support modular multiplexing functions, implement and publish the initial expansion function, make the initial expansion function in the function library of the intelligent voice dialogue system for users to use, configure the initial expansion function in the function library, Obtain the target extension function, and then use the target extension function to process the user's voice data during the call to obtain the content represented by the voice data, improve the efficiency of corresponding voice data processing in the intelligent voice dialogue system, and improve the flexibility of related session management. Specifically, the common logic components, rule components and business domain components in the intelligent voice dialogue system are realized in the way of modular componentization and service combination, and the speech and speech flow are assembled through the dynamic configuration method, and the speech template is enhanced. At the same time of business description ability, it reduces the complexity of the speech template and improves the scalability and reusability.

Description of the drawings

Fig. 1 is a flowchart of a high-precision warning method according to an embodiment;

FIG. 2 is a schematic diagram of a call flow of an execution example of an extended function-based speech technique flow template according to an embodiment;

Figure 3 is a schematic structural diagram of a high-precision warning device according to an embodiment;

Fig. 4 is a schematic diagram of a computer device according to an embodiment.

Detailed ways

In order to make the purpose, technical solutions, and advantages of this application clearer and clearer, the following further describes the application in detail with reference to the accompanying drawings and embodiments. 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.

The reference to "embodiments" herein means that a specific feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art clearly and implicitly understand that the embodiments described herein can be combined with other embodiments.

The voice data processing method for the intelligent voice dialogue system provided in this application can be applied to related intelligent voice dialogue systems. The above-mentioned voice data processing terminal defines each service component of the intelligent voice dialogue system as an initial expansion function, so that the initial expansion function can complete independent logic calls or business calls, and support modular multiplexing functions, and realize and publish all The initial expansion function is described so that the initial expansion function is in the function library of the intelligent voice dialogue system for users to use, the initial expansion function in the function library is configured to obtain the target expansion function, and the target expansion function is used to process the user’s voice during the call Data to obtain the content represented by the voice data, so as to reduce the complexity of processing the corresponding voice data and improve the flexibility of the related session management solution. Among them, the voice data processing terminal can be, but is not limited to, various personal computers and notebook computers and other intelligent processing equipment.

In an embodiment, as shown in FIG. 1, a voice data processing method for an intelligent voice dialogue system is provided. Taking the method applied to a voice data processing terminal as an example for description, the method includes the following steps:

S10: Define each service component of the intelligent voice dialogue system as an initial expansion function, so that the initial expansion function has the function of completing independent logic calls or business calls, and supporting modular multiplexing.

The above steps can define the business protagonist of the intelligent voice dialogue system and the interface component of the external system that the dialogue system needs to connect as an extension function (initial extension function). In essence, it is a process of abstracting the business scenarios of the intelligent voice dialogue system and its application. Some commonly used business components in the intelligent voice dialogue system are defined as extension functions. These extension functions can complete independent and simple logic calls or business calls, and Support modular reuse.

Further, extension functions (initial extension functions) can be classified according to functions, such as logic functions, system functions, named entity recognition functions, business domain functions, and external service call functions. The extension function needs to define the function input, including the acceptable input parameters and its types; the extension function needs to define the function output, including the output of the function and its type, the output types include: numeric, Boolean, string, enumeration, etc. .

The classification of extension functions is used to manage the functions and improve the interactive experience of building words. The input and output definition of the extension function determines the input needs and final output behavior of the function execution.

S20. Implement and publish the initial expansion function, so that the initial expansion function is in the function library of the intelligent voice dialogue system for users to use.

The above-mentioned users may include operators of intelligent voice dialogue systems, etc.

The specific definition of the initial expansion function refers to the function that the corresponding function (initial expansion function) needs to realize, that is, what problem the function is used to solve. The realization of the initial expansion function refers to the process by which the developer realizes the corresponding function according to the functional requirement.

Specifically, in this embodiment, the specific definition of the initial expansion function and the functional requirements of the business function (initial expansion function) can be developed to implement a business function process. After the extension function is implemented and released, it will be registered in the available function library of the intelligent voice dialogue system for users such as operators who use the intelligent voice dialogue system.

S30: Configure the initial expansion function in the function library to obtain the target expansion function.

In this embodiment, the extended functions provided by the intelligent voice dialogue system can be combined and configured to implement custom extended components of complex functions, thereby obtaining target extended functions; these custom extended components (target extended functions) are still extended through custom The function method is registered in the available function library of the system, and users such as operators can call these customized extension functions in different business scenarios and speech templates.

This embodiment is a process of defining the intelligent voice dialogue system and its custom extended function combination call mode in the speech technique template of the intelligent speech dialogue system, and finally configuring it into a usable speech technique template. The service execution engine of the intelligent voice dialogue system finally calls the extension function according to the defined speech template to realize the functions of intent recognition and session management in the dialogue process.

Furthermore, when constructing huashu, the speech builder of the intelligent voice dialogue system can perform functions at the node of huashu based on the extension functions provided in the function library of the intelligent voice dialogue system and the custom extension functions defined by their own configuration. Configuration, the content of the configuration includes the function to be executed, the order in which the function is executed, the input data source of the function and the output data assignment. By using these functions, it is possible to clearly define the intention recognition and information extraction of the user's speech during the call. These expansion functions can be reused in different speech nodes or even in different speeches, which can effectively reduce the speech The complexity of the configuration.

In the voice data processing method used in the intelligent voice dialogue system, each service component of the intelligent voice dialogue system is respectively defined as an initial expansion function, so that the initial expansion function can complete independent logic calls or business calls, and supports modular replication. Use functions, realize and publish the initial expansion function, make the initial expansion function in the function library of the intelligent voice dialogue system for users to use, configure the initial expansion function in the function library, obtain the target expansion function, and then adopt the target The extension function processes the user's voice data during the call to obtain the content represented by the voice data, improves the efficiency of corresponding voice data processing in the intelligent voice dialogue system, and enhances the flexibility of related session management. Specifically, the common logic components, rule components and business domain components in the intelligent voice dialogue system are realized in the way of modular componentization and service combination, and the speech and speech flow are assembled through the dynamic configuration method, and the speech template is enhanced. At the same time of business description ability, it reduces the complexity of the speech template and improves the scalability and reusability.

In one embodiment, following the principle of separating the construction and use of the extension function, the producers of the intelligent voice dialogue system can be divided into two types of users: extension function developers and business speech builders. Among them, the extension function developer has professional function combination service and business domain knowledge, and its main responsibilities are specifically expressed as: providing the specific implementation of the extension function for the intelligent voice dialogue system and maintaining the function library of the system, including adding, updating and extending Functions, provide detailed service descriptions corresponding to extension functions, etc.

A business speech builder, with knowledge of the business domain of speech application and the ability to build intelligent speech, can use the extended function library and the speech flow structure template to build speech and speech flow according to the characteristics of the domain.

In this embodiment, the extension function developer performs the encapsulation of the function, and provides the interface definition and implementation description of the function. Take the implementation of the extension function extracted from the city name named entity as an example. The input of the function is a string type, which is often expressed by the user Text, the output of the function is the extracted city name and predicted score, which are defined as string type and numeric type respectively.

In an example, the function definition can be described in the following ways:

In this embodiment, the speech art builder uses the extension function library to configure the custom expansion function and the intelligent speech art construction configuration. According to the requirements of the business field and the definition and description of the extension function, the speech builder builds the key processing steps of the speech node through the legal combination of the expansion function, such as the behavioral ability of intention recognition and session management. For example, for the user's expression of "what's the weather tomorrow", the speech builder needs and is not limited to use the following extension functions to complete an intelligent answer.

Several examples of related voice data processing are listed below:

The keyword-based verbal domain filtering expansion function is used to extract the user's intention from the user's expression sentence. For example, in this example, the "weather" keyword is used to output the verbal domain as the domain node of "inquiring weather".

The domain screening expansion function based on semantic similarity is used to extract user intentions from user expression sentences. For example, in this example, the output speech field is the domain node of "inquiring weather" and the similarity score is 0.99.

The domain word art node matching expansion function, the input is a list of candidate domain nodes, and the output is the domain word art node with the highest score.

The date named entity extraction extension function is used to extract the date from the user statement. For example, the date entity extracted in this example is "tomorrow"

The city location named entity extraction extension function is used to extract locations from user expressions.

The date natural language expression formatting function, the input is the date entity extracted from the user's expression, and the output is the formatted date, such as "2019-10-28".

The conversation context information extraction extension function retrieves the same type of information available from the conversation context when the required named entity extraction is empty.

Weather query expansion function, when the required parameters (date, location and city) slot values are all extracted, call this function to output weather information.

The reply text generates an extended function, and outputs the reply text based on the output of the weather query extended function and the definition of the speech template, such as "It will rain tomorrow in Nanjing, remember to bring an umbrella".

In the implementation process of the present invention, the expansion function used in the speech flow template and its calling logic will eventually be generated according to the speech construction configuration of the speech construction builder to generate a speech execution example. In an example, FIG. 2 shows a schematic diagram of a call flow of an execution example of a speech flow template based on an extension function of the present invention.

Referring to FIG. 3, FIG. 3 is a schematic structural diagram of a voice data processing device for an intelligent voice dialogue system according to an embodiment, including:

The definition module 10 is used to define each service component of the intelligent voice dialogue system as an initial expansion function, so that the initial expansion function has the function of completing independent logic calls or business calls, and supporting modular multiplexing;

The implementation module 20 is used to implement and publish the initial expansion function, so that the initial expansion function is in the function library of the intelligent voice dialogue system for users to use;

The configuration module 30 is used to configure the initial expansion function in the function library to obtain the target expansion function;

The processing module 40 is used to process the voice data of the user during the call by using the target expansion function to obtain the content represented by the voice data.

In an embodiment, the implementation module is further used for:

In an embodiment, the configuration module is further used for:

In an embodiment, the processing module is further used for:

For the specific limitation of the voice data processing device used in the intelligent voice dialogue system, please refer to the above limitation on the voice data processing method used in the intelligent voice dialogue system, which will not be repeated here. The various modules in the voice data processing device used in the intelligent voice dialogue system can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules may be embedded in the form of hardware or independent of the processor in the computer equipment, or may be stored in the memory of the computer equipment in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. 4. The computer equipment includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide calculation and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program is executed by the processor to realize a voice data processing method for the intelligent voice dialogue system. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, or it can be a button, a trackball or a touchpad set on the housing of the computer equipment , It can also be an external keyboard, touchpad, or mouse.

Those skilled in the art can understand that the structure shown in FIG. 4 is only a block diagram of part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may Including more or fewer parts than shown in the figure, or combining some parts, or having a different arrangement of parts.

Based on the above example, in one embodiment, a computer device is further provided. The computer device includes a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the The program implements the voice data processing method used in the intelligent voice dialogue system as any of the above embodiments.

A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer readable storage. In the medium, as in the embodiment of the present invention, the program can be stored in the storage medium of the computer system and executed by at least one processor in the computer system to realize the voice data processing for the intelligent voice dialogue system as described above. The flow of an embodiment of the method. Wherein, the storage medium may be a magnetic disk, an optical disc, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM), etc.

Accordingly, in one embodiment, there is also provided a computer storage medium, a computer readable storage medium, on which a computer program is stored, where the program is executed by the processor to implement any one of the above-mentioned embodiments for Voice data processing method of intelligent voice dialogue system.

The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be It is considered as the range described in this specification.

It should be noted that the term "first\second\third" involved in the embodiments of this application only distinguishes similar objects, and does not represent a specific order for the objects. Understandably, "first\second\third" "Three" can be interchanged in specific order or precedence when permitted. It should be understood that the objects distinguished by "first\second\third" can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.

The terms "include" and "have" and any variations thereof in the embodiments of the present application are intended to cover non-exclusive inclusions. For example, a process, method, device, product, or device that includes a series of steps or modules is not limited to the listed steps or modules, but optionally includes unlisted steps or modules, or optionally also includes Other steps or modules inherent to these processes, methods, products or equipment.

The above-mentioned embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation on the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can be made, and these all fall within the protection scope of this application. Therefore, the scope of protection of the patent of this application shall be subject to the appended claims.

Claims

A voice data processing method for an intelligent voice dialogue system is characterized in that it comprises the following steps:

S10: Define each service component of the intelligent voice dialogue system as an initial expansion function, so that the initial expansion function has the function of completing independent logic calls or business calls, and supporting modular multiplexing;

S20. Implement and publish the initial expansion function, so that the initial expansion function is in the function library of the intelligent voice dialogue system for users to use;

S30, configure the initial expansion function in the function library to obtain the target expansion function;

S40: Use the target extension function to process the voice data of the user during the call, so as to obtain the content represented by the voice data.
The voice data processing method for an intelligent voice dialogue system according to claim 1, wherein implementing and publishing the initial expansion function comprises:

Realize and develop the initial expansion function according to the specific definition of the initial expansion function and the functional requirements of the initial expansion function.
The voice data processing method for an intelligent voice dialogue system according to claim 1, wherein configuring the initial expansion function in the function library to obtain the target expansion function comprises:

Use an initial expansion function in the function library as the input of another initial expansion function to obtain a customized target expansion function.
The voice data processing method for an intelligent voice dialogue system according to claim 1, wherein using a target expansion function to process voice data input by a user to obtain the content represented by the voice data comprises:

According to the initial expansion function and the target expansion function provided in the function library, the function configuration is performed on the nodes of the speech art, and the configured function is used to define the intention and information of the user's voice data characterization during the call.
A voice data processing device used in an intelligent voice dialogue system, which is characterized in that it comprises:

The definition module is used to define each business component of the intelligent voice dialogue system as an initial expansion function, so that the initial expansion function can complete independent logic calls or business calls, and support modular multiplexing;

The realization module is used to realize and publish the initial expansion function, so that the initial expansion function is in the function library of the intelligent voice dialogue system for users to use;

The configuration module is used to configure the initial expansion function in the function library to obtain the target expansion function;

The processing module is used to process the voice data of the user during the call by using the target extension function to obtain the content represented by the voice data.
The voice data processing device for an intelligent voice dialogue system according to claim 5, wherein the realization module is further used for:

Realize and develop the initial expansion function according to the specific definition of the initial expansion function and the functional requirements of the initial expansion function.
The voice data processing device for an intelligent voice dialogue system according to claim 5, wherein the configuration module is further used for:

Use an initial expansion function in the function library as the input of another initial expansion function to obtain a customized target expansion function.
The voice data processing device for an intelligent voice dialogue system according to claim 5, wherein the processing module is further used for:

According to the initial expansion function and target expansion function provided in the function library, the function configuration is performed on the node of the speech art, and the configured function is used to define the intention and information of the user's voice data during the call.
A computer device, comprising a memory, a processor, and a computer program stored on the memory and running on the processor, wherein the processor implements any one of claims 1 to 4 when the computer program is executed The steps of the method.
A computer-readable storage medium with a computer program stored thereon, wherein the computer program implements the steps of any one of claims 1 to 4 when the computer program is executed by a processor.