WO2022142012A1

WO2022142012A1 - Script configuration adjustment method and apparatus, electronic device, and storage medium

Info

Publication number: WO2022142012A1
Application number: PCT/CN2021/090457
Authority: WO
Inventors: 方勇
Original assignee: 平安科技（深圳）有限公司
Priority date: 2020-12-29
Filing date: 2021-04-28
Publication date: 2022-07-07
Also published as: CN112612462A

Abstract

The present application relates to the technical field of artificial intelligence, and provides a script configuration adjustment method and apparatus, an electronic device, and a storage medium. The method comprises: analyzing a script configuration request to obtain a service attribute of a target script, and obtaining a corresponding intention set from an intention database on the basis of the service attribute of the target script; extracting a plurality of target intentions from the intention set according to an intention selection instruction, and associating tagged scripts of the plurality of target intentions with the service attribute of the target script to form script configuration information of the target script; creating a force-directed graph for the target script on the basis of the script configuration information of the target script; converting the force-directed graph for the target script into a tree layout, and displaying the script configuration information on an interface of a client; and adjusting the script configuration information of the target script according to a script adjustment instruction. In the present application, displaying the script configuration information by means of the force-directed graph and the tree layout improves script adjustment efficiency and configuration accuracy.

Description

Speech configuration adjustment method, device, electronic device and storage medium

This application claims the priority of the Chinese patent application filed on December 29, 2020 with the application number 202011595194.6 of the Chinese patent application entitled "Speech Configuration Adjustment Method, Device, Electronic Device and Storage Medium", the entire contents of which are by reference Incorporated in this application.

technical field

The present application relates to the technical field of artificial intelligence, and in particular, to a method, device, electronic device and storage medium for adjusting speech configuration.

Background technique

Human-computer dialogue is an important field in the field of artificial intelligence. When conducting human-computer dialogue, the inventor realized that the existing technology uses pre-set speech templates, and developers manually write the speech templates into corresponding speech templates by hardcoding. Under the robot, the client interface cannot be displayed. When there is an error in the configuration of the speech, the customer cannot know it, resulting in a low accuracy of the speech configuration. Especially when the speech needs to be adjusted after the speech configuration, professional developers are required. Adjusting the speech configuration information and structure according to the speech document provided by the customer results in slow response and low efficiency of speech adjustment.

SUMMARY OF THE INVENTION

In view of the above, it is necessary to propose a method, device, electronic device and storage medium for adjusting the configuration of speech, which can improve the adjustment efficiency and configuration of speech by displaying speech configuration information in the form of force-oriented graph and tree layout. Accuracy.

A first aspect of the present application provides a speech configuration adjustment method, the method comprising:

Receive the session configuration request sent by the client;

Analyzing the speech configuration request to obtain the business attribute of the target speech, and obtaining the corresponding intent set from the intent database based on the business attribute of the target speech;

Extracting multiple target intents from the intent set according to the intent selection instruction, and associating the tagged discourses of the multiple target intents with the service attributes of the target discourse to form discourse configuration information of the target discourse;

creating a force-directed graph of the target speech based on the speech configuration information of the target speech;

Convert the force-directed graph of the target language into a tree-like layout, and display it on the interface of the client;

Adjust the speech configuration information of the target speech according to the speech adjustment instruction.

A second aspect of the present application provides an electronic device, the electronic device comprising a memory and a processor, the memory for storing at least one computer-readable instruction, the processor for executing the at least one computer-readable instruction to Implement the following steps:

Receive the session configuration request sent by the client;

A third aspect of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores at least one computer-readable instruction, and when the at least one computer-readable instruction is executed by a processor, implements the following steps:

Receive the session configuration request sent by the client;

A fourth aspect of the present application provides a speech configuration adjustment device, the device comprising:

The receiving module is used to receive the technical configuration request sent by the client;

A parsing module, configured to parse the speech configuration request to obtain the business attribute of the target speech, and obtain the corresponding intent set from the intent database based on the business attribute of the target speech;

The extraction module is configured to extract multiple target intents from the intent set according to the intent selection instruction, and associate the tagged discourses of the multiple target intents with the business attributes of the target discourses to form a target discourse Talk configuration information;

A creation module, configured to create a force-directed graph of the target speech based on the speech configuration information of the target speech;

a conversion module, configured to convert the force-directed graph of the target speech into a tree-like layout, and display it on the interface of the client;

An adjustment module, configured to adjust the speech configuration information of the target speech according to the speech adjustment instruction.

The speech configuration adjustment method, device, electronic device, and storage medium described in the present application, on the one hand, obtain node data and reference relationships between nodes from the speech configuration information of the target speech, according to the node data and The reference relationship between the nodes creates a force-directed graph of the target speech, and the speech configuration is displayed by means of a force-directed graph, and the configuration information of the speech configuration of the target speech can be seen intuitively. When there is an error in the configuration process, the customer can make adjustments in time, which improves the efficiency of speech adjustment, and thus improves the accuracy of speech configuration; on the other hand, in order to avoid the phenomenon of confusion in the force-directed graph when there are too many nodes , converts the force-oriented graph of the target language into a tree-like layout, and displays the tree-like layout on the interface of the client, so that the client can intuitively see the configuration information of the target language and how to configure it When an error occurs, it can respond in time, which improves the efficiency and accuracy of speech adjustment; finally, when monitoring the adjustment instruction sent by the client, parsing the adjustment instruction to obtain the service attributes to be adjusted, The speech configuration information is quickly adjusted according to the location coordinates of the service attributes to be adjusted, which improves the accuracy and efficiency of the adjustment of the speech configuration information.

Description of drawings

FIG. 1 is a flowchart of a method for adjusting a speech configuration provided by Embodiment 1 of the present application.

FIG. 2 is a structural diagram of an apparatus for adjusting a voice configuration provided in Embodiment 2 of the present application.

FIG. 3 is a schematic structural diagram of an electronic device provided in Embodiment 3 of the present application.

Detailed ways

In order to more clearly understand the above objects, features and advantages of the present application, the present application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments may be combined with each other in the case of no conflict.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs. The terms used herein in the specification of the application are for the purpose of describing specific embodiments only, and are not intended to limit the application.

Example 1

In this embodiment, the voice configuration adjustment method can be applied to an electronic device. For an electronic device that needs to perform voice configuration adjustment, the voice configuration adjustment function provided by the method of the present application can be directly integrated on the electronic device. , or run in electronic equipment in the form of a software development kit (SKD).

As shown in FIG. 1 , the speech configuration adjustment method specifically includes the following steps. According to different requirements, the order of the steps in the flowchart can be changed, and some can be omitted.

S11: Receive a session configuration request sent by the client.

In this embodiment, the client initiates a voice configuration request through the client when performing voice configuration. Specifically, the client may be a smart phone, an IPAD, or other devices, and the server may be a voice configuration system. During the session configuration process, for example, the client may send a session configuration request to the session configuration system, and the session configuration system is configured to receive the session configuration request sent by the client.

S12, parse the speech configuration request to obtain the service attribute of the target speech, and obtain the corresponding intent set from the intention database based on the service attribute of the target speech.

In this embodiment, since each speech configuration request contains the service attribute of the target speech, the information such as the target speech type of the target speech, the service attribute of the target speech, etc., are obtained by parsing the speech configuration request, And based on the business attribute of the target language, the corresponding intent set is acquired from the intent database.

Optionally, the acquiring the corresponding intent set from the intent database based on the business attribute of the target language includes;

Determine the target speech type of the target speech according to the service attribute;

matching the type of the target utterance with the utterance type in the intent database;

When a target speech type matching the target speech type is matched in the speech types in the intent database, obtain the intent set corresponding to the target speech type; or

When no target speech type matching the target speech type is found in the speech types in the intent database, a default intent set is acquired.

In this embodiment, the association relationship of the target discourse is determined according to the intent, and after the target discourse type of the target discourse is acquired, the corresponding intent set is extracted from the intent database according to the target discourse class , specifically, each intent in the intent database is configured with a business attribute, the intent is configured from tagged discourses with the same intent in all historical discourse data, and each tagged discourse corresponds to a service attribute, which improves the management efficiency of the business attribute of the target speech.

S13, extracting multiple target intents from the intent set according to the intent selection instruction, and associating the tagged discourses of the multiple target intents with the business attributes of the target discourse to form a discourse configuration of the target discourse information.

In this embodiment, since there is one intent set corresponding to the discourse type of each target discourse, and each intent set stores multiple business attributes, the intent selection instruction in the discourse configuration request is selected from the intent set according to the intent set. The target intent corresponding to each service attribute is extracted from the .

Optionally, the associating the multiple target-intent tagged phrases with the service attributes of the target phrases includes:

extracting multiple first tags of multiple tagging words corresponding to each target intent;

extracting multiple key fields in the business attributes of the target language, and converting the multiple key fields into multiple second tags;

matching the plurality of second tags with the plurality of first tags;

When any second tag matches any of the first tags, associate the tagged speech corresponding to the any first label with the service attribute of the target speech; or

When any second label does not match any of the first labels, the tagged speech corresponding to any first label is not associated with the service attribute of the target speech.

In this embodiment, each target intent includes a plurality of tagged phrases, and each tagged phrase corresponds to a first tag. For example, the robot asks: Hello, are you interested in learning how to use the phrases? configure it? Corresponding to multiple first tags: interested, not interested, pending; extract the second tag from the business attribute of the target language: interested, when the "interested" in the first tag is the same as the "interested" in the second tag. "When matching, associate the business attribute of the target language with the tagged language corresponding to the first tag, and get "Hello, are you interested in learning how to configure the language?" as the target node, The next node corresponding to the target node is the topic configuration information corresponding to "interested".

Exemplarily, in this embodiment, by acquiring the target intent, and associating the tagged discourses of the multiple target intents with the business attributes of the target discourse according to the target intent, each of the target discourses is determined. The node configuration information of each node and the reference relationship between multiple nodes.

S14. Create a force-directed graph of the target speech based on the speech configuration information of the target speech.

In this embodiment, the force-directed graph is used to display the association relationship between the nodes of the speech, and the force-directed graph of the target speech is created according to the speech configuration information of the target speech.

Optionally, the creating a force-directed graph of the target speech based on speech configuration information of the target speech includes:

converting the node of the target speech in the speech configuration information into a node of the corresponding force-directed graph, wherein the node of the force-directed graph includes the speech label of the node of the target speech;

Convert the reference relationship between the nodes of the target speech in the speech configuration information into the edges between the nodes in the corresponding force-directed graph, where the edges between the nodes in the force-directed graph are used as the force The reference relationship between the nodes of the directed graph;

A force-directed graph of the target speech is created from nodes of the force-directed graph and edges between the force-directed graph nodes.

In some other optional embodiments, the creating a force-directed graph of the target speech based on the speech configuration information of the target speech includes:

performing data conversion on the discourse configuration information of the target discourse to obtain first structural data;

sending the first structure data to a relational database for processing to obtain the second structure data of the target speech and the third structure data of the reference relationship between the target speech;

Converting the node of the target language of the second structural data into a node of the corresponding force-directed graph, wherein the node of the force-directed graph contains the language label of the node of the target language;

Convert the reference relationship between the nodes of the target language in the third structural data into the edges between the nodes in the corresponding force-directed graph, where the edges between the nodes in the force-directed graph are used as the force The reference relationship between the nodes of the directed graph;

A force-directed graph of the target discourse is created from nodes of the force-directed graph and edges between nodes in the force-directed graph.

In this embodiment, the first structural data refers to converting the discourse configuration information of the target discourse into first structural data according to a preset conversion rule, and the relational database can determine the difference between the first data structures. The third structure data of the reference relationship and the second structure data corresponding to each node, and convert the node of the target language into the corresponding force-directed graph node, and convert the reference relationship between the nodes of the target language into The corresponding edge between the nodes in the force-directed graph, the force-directed graph of the target language is created according to the nodes of the force-directed graph and the edges between the nodes in the force-directed graph, which further improves the created force. Integrity of the orientation graph.

In this embodiment, node data and the reference relationship between nodes are obtained from the language configuration information of the target language, and the force orientation of the target language is created according to the node data and the reference relationship between the nodes Figure, showing the voice configuration through a force-directed graph, you can intuitively see the configuration information of the target voice configuration, when there is an error in the configuration process, the customer can make adjustments in time to improve the voice It can improve the efficiency of skill adjustment, thereby improving the accuracy of speech configuration.

S15: Convert the force-directed graph of the target language into a tree-like layout, and display it on the interface of the client.

In this embodiment, in order to avoid confusion in the force-directed graph when there are too many nodes, the force-directed graph of the target speech is converted into a tree-like layout, and the tree-like layout is displayed on the interface of the client , so that the client can intuitively see the configuration information of the target speech and how to configure it. When an error occurs, it can respond in time, which improves the efficiency and accuracy of speech adjustment.

Optionally, the converting the force-directed graph of the target speech into a tree-like layout includes:

Copying the speech configuration information in the force-oriented graph of the target speech to obtain the target speech configuration information, and converting the target speech configuration information into a preset tree structure;

calculating the first position coordinates of each node in the force-directed graph of the target speech;

Calculate the second position coordinate of each node according to the preset tree structure;

updating the second position coordinate of each node to the corresponding first position coordinate in the preset tree structure;

Restarting the preset tree structure converts the force-directed graph of the target speech into a tree-like layout.

In this embodiment, the tree-like layout can display the target speech more intuitively. In the process of converting the force-directed graph of the target speech into a tree structure, the force of the target speech is first The discourse configuration information in the orientation graph is copied to obtain the target discourse configuration information, which ensures the consistency between the discourse configuration information in the force-directed graph and the discourse configuration information in the tree layout, and improves the discourse configuration in the tree layout. Integrity of configuration information.

Specifically, after obtaining the target speech configuration information, convert the target speech configuration information into a preset tree structure, and use the preset tree layout to calculate and obtain the second position coordinates of each node , re-layout and change the second position coordinates in the preset tree structure, and update the second position coordinates to the first position coordinates of the corresponding nodes in the force-directed graph, without destroying the force-directed graph structure. Based on the tree-like layout of the force-directed graph conversion, it is convenient to more intuitively confirm the speech information of each node of the target speech and the relationship between the nodes, and improve the accuracy of speech configuration information adjustment.

S16: Adjust the speech configuration information of the target speech according to the speech adjustment instruction.

In this embodiment, the adjustment instruction is used to request to adjust the speech configuration information of the target speech, and when the adjustment instruction sent by the client is monitored, the adjustment instruction is triggered to perform speech configuration information of the target speech.

Optionally, the adjusting the speech configuration information of the target speech according to the speech adjustment instruction includes:

Analyzing the speech adjustment instruction to obtain the service attribute to be adjusted;

converting the service attribute to be adjusted into a target tag;

The location coordinates corresponding to the tree layout are determined according to the target label, and the node speech configuration information corresponding to the location coordinates is adjusted.

In this embodiment, since the user can intuitively see the speech configuration information and the reference relationship between the nodes in the tree layout of the target speech, when the speech configuration information needs to be adjusted, the corresponding communication is directly determined according to the business requirements. The position coordinates in the tree-like layout are quickly adjusted according to the speech configuration information according to the position coordinates, which improves the accuracy and efficiency of the adjustment of the speech configuration information.

To sum up, the method for adjusting a speech in this embodiment receives a speech configuration request sent by a client; parses the speech configuration request to obtain the service attributes of the target speech, The business attribute obtains the corresponding intent set from the intent database; extracts multiple target intents from the intent set according to the intent selection instruction, and compares the tagged discourses of the multiple target intents with the business attributes of the target discourse perform association to form the discourse configuration information of the target discourse; create a force-directed graph of the target discourse based on the discourse configuration information of the target discourse; convert the force-directed graph of the target discourse into a tree-like layout, and Displaying on the interface of the client; adjusting the discourse configuration information of the target discourse according to the discourse adjustment instruction.

In this embodiment, on the one hand, by acquiring node data and the reference relationship between nodes from the language configuration information of the target language, the target language is created according to the node data and the reference relationship between the nodes The force-directed graph of the target dialect is used to display the configuration of the dialect, and the configuration information of the dialect configuration of the target dialect can be seen intuitively. When an error occurs during the configuration process, the customer can adjust it in time. It improves the efficiency of language adjustment, thereby improving the accuracy of language configuration; on the other hand, in order to avoid the phenomenon of confusion in the force-directed graph when there are too many nodes, the force-directed graph of the target language is converted into a tree. and display the tree-like layout on the interface of the client, so that the client can intuitively see the configuration information of the target language and how to configure it. When an error occurs, it can respond in time, which improves the The efficiency and accuracy of the speech adjustment; finally, when monitoring the adjustment instruction sent by the client, parse the adjustment instruction to obtain the service attribute to be adjusted, and quickly adjust the speech according to the position coordinates of the service attribute to be adjusted. The configuration information improves the accuracy and efficiency of the adjustment of the speech configuration information.

Embodiment 2

In some embodiments, the speech configuration adjustment device 20 may include a plurality of functional modules composed of program code segments. The program codes of each program segment in the voice configuration adjustment device 20 may be stored in the memory of the electronic device and executed by the at least one processor to execute (see description in FIG. 1 for details) the voice configuration adjustment. Function.

In this embodiment, the speech configuration adjustment device 20 can be divided into a plurality of functional modules according to the functions performed by the device 20 . The functional modules may include: a receiving module 201 , a parsing module 202 , an extracting module 203 , a creating module 204 , a converting module 205 and an adjusting module 206 . A module referred to in this application refers to a series of computer program segments that can be executed by at least one processor and can perform fixed functions, and are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

The receiving module 201 is configured to receive a session configuration request sent by the client.

The parsing module 202 is configured to parse the speech configuration request to obtain the service attribute of the target speech, and obtain the corresponding intent set from the intention database based on the service attribute of the target speech.

Optionally, the parsing module 202 obtains the corresponding intent set from the intent database based on the business attribute of the target speech, including;

In this embodiment, the association relationship of the target speech is determined according to the intent, and after the target speech type of the target speech is acquired, the corresponding intent set is extracted from the intent database according to the target speech category. , specifically, each intent in the intent database is configured with a business attribute, the intent is configured from tagged discourses with the same intent in all historical discourse data, and each tagged discourse corresponds to a service attribute, which improves the management efficiency of the business attribute of the target speech.

The extraction module 203 is used for extracting multiple target intents from the intent set according to the intent selection instruction, and associating the tagged phrases of the multiple target intents with the business attributes of the target phrases to form a target phrase. Talk configuration information for the term.

Optionally, the extracting module 203 associating the multiple target-intent tagged phrases with the service attributes of the target phrases includes:

matching the plurality of second tags with the plurality of first tags;

The creating module 204 is configured to create a force-directed graph of the target speech based on the speech configuration information of the target speech.

Optionally, the creating module 204 creates a force-directed graph of the target speech based on the speech configuration information of the target speech, including:

In some other optional embodiments, the creating module 204 creates a force-directed graph of the target speech based on the speech configuration information of the target speech, including:

The conversion module 205 is configured to convert the force-directed graph of the target speech into a tree-like layout and display it on the interface of the client.

Optionally, the conversion module 205 converts the force-directed graph of the target speech into a tree-like layout including:

The adjustment module 206 is configured to adjust the speech configuration information of the target speech according to the speech adjustment instruction.

Optionally, the adjustment module 206 adjusting the speech configuration information of the target speech according to the speech adjustment instruction includes:

converting the service attribute to be adjusted into a target tag;

To sum up, the device for adjusting a speech voice in this embodiment receives a speech configuration request sent by a client; parses the speech configuration request to obtain the service attributes of a target speech, and based on the service attribute of the target speech The business attribute obtains the corresponding intent set from the intent database; extracts multiple target intents from the intent set according to the intent selection instruction, and compares the tagged discourses of the multiple target intents with the business attributes of the target discourse perform association to form the discourse configuration information of the target discourse; create a force-directed graph of the target discourse based on the discourse configuration information of the target discourse; convert the force-directed graph of the target discourse into a tree-like layout, and Displaying on the interface of the client; adjusting the discourse configuration information of the target discourse according to the discourse adjustment instruction.

Embodiment 3

Referring to FIG. 3 , it is a schematic structural diagram of an electronic device according to Embodiment 3 of the present application. In a preferred embodiment of the present application, the electronic device 3 includes a memory 31 , at least one processor 32 , at least one communication bus 33 and a transceiver 34 .

Those skilled in the art should understand that the structure of the electronic device shown in FIG. 3 does not constitute a limitation of the embodiments of the present application, and may be a bus-type structure or a star-shaped structure, and the electronic device 3 may also include a schematic more or less other hardware or software, or a different arrangement of components is shown.

In some embodiments, the electronic device 3 is an electronic device that can automatically perform numerical calculation and/or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits , programmable gate arrays, digital processors and embedded devices. The electronic device 3 may also include a client device, which includes but is not limited to any electronic product that can perform human-computer interaction with a client through a keyboard, a mouse, a remote control, a touchpad, or a voice-activated device, for example, Personal computers, tablets, smartphones, digital cameras, etc.

It should be noted that the electronic device 3 is only an example, and other existing or future electronic products, if applicable to the present application, should also be included within the protection scope of the present application, and incorporated herein by reference .

In some embodiments, the memory 31 is used to store program codes and various data, such as the voice configuration adjustment device 20 installed in the electronic device 3 , and to realize high-speed and automatic operation during the operation of the electronic device 3 . Complete program or data access. Described memory 31 comprises read-only memory (Read-Only Memory, ROM), programmable read-only memory (Programmable Read-Only Memory, PROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, EPROM) , One-time Programmable Read-Only Memory (OTPROM), Electronically-Erasable Programmable Read-Only Memory (EEPROM), Compact Disc Read- Only Memory, CD-ROM) or other optical disk storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

In some embodiments, the computer-readable storage medium described in this application may be non-volatile or volatile.

In some embodiments, the at least one processor 32 may be composed of integrated circuits, for example, may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits packaged with the same function or different functions, including one Or a combination of multiple central processing units (Central Processing units, CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The at least one processor 32 is the control core (Control Unit) of the electronic device 3, and uses various interfaces and lines to connect various components of the entire electronic device 3, by running or executing the program stored in the memory 31 or modules, and call data stored in the memory 31 to perform various functions of the electronic device 3 and process data.

In some embodiments, the at least one communication bus 33 is configured to enable connection communication between the memory 31 and the at least one processor 32 and the like.

Although not shown, the electronic device 3 may also include a power source (such as a battery) for supplying power to various components. Optionally, the power source may be logically connected to the at least one processor 32 through a power management device, so that the power management device Implement functions such as managing charging, discharging, and power consumption. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and any other components. The electronic device 3 may further include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

It should be understood that the embodiments are only used for illustration, and are not limited by this structure in the scope of the patent application.

The above-mentioned integrated units implemented in the form of software functional modules may be stored in a computer-readable storage medium. The above-mentioned software function modules are stored in a storage medium, and include several computer-readable instructions to enable a computer device (which may be a personal computer, an electronic device, or a network device, etc.) or a processor (processor) to execute various embodiments of the present application part of the method.

In a further embodiment, with reference to FIG. 2 , the at least one processor 32 can execute the operating device of the electronic device 3 and various installed application programs (such as the speech configuration adjusting device 20 ), program codes, etc. , for example, the various modules above.

Program codes are stored in the memory 31, and the at least one processor 32 can call the program codes stored in the memory 31 to perform related functions. Exemplarily, the program code may be divided into one or more modules/units, and the one or more modules/units may be a series of computer-readable instruction segments capable of performing specific functions, and the instruction segments are used to describe the The execution process of the program code in the electronic device. For example, each module described in FIG. 2 is a program code stored in the memory 31 and executed by the at least one processor 32, so as to realize the functions of the various modules to achieve the purpose of adjusting the speech configuration .

In an embodiment of the present application, the memory 31 stores a plurality of computer-readable instructions, and the plurality of computer-readable instructions are executed by the at least one processor 32 to implement the function of speech configuration adjustment.

Specifically, for the specific implementation method of the above instruction by the at least one processor 32, reference may be made to the description of the relevant steps in the embodiment corresponding to FIG. 1 , and details are not described herein.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are only illustrative. For example, the division of the modules is only a logical function division, and there may be other division manners in actual implementation.

The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, and may be located in one place or distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional module in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware, or can be implemented in the form of hardware plus software function modules.

It will be apparent to those skilled in the art that the present application is not limited to the details of the above-described exemplary embodiments, but that the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application. Accordingly, the embodiments are to be regarded in all respects as illustrative and not restrictive, and the scope of the application is to be defined by the appended claims rather than the foregoing description, which is therefore intended to fall within the scope of the claims. All changes within the meaning and scope of the equivalents of , are included in this application. Any reference signs in the claims shall not be construed as limiting the involved claim. Furthermore, it is clear that the word "comprising" does not exclude other units or, and the singular does not exclude the plural. A plurality of units or devices stated in this application may also be implemented by one unit or device through software or hardware. The terms first, second, etc. are used to denote names and do not denote any particular order.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application rather than limitations. Although the present application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present application can be Modifications or equivalent substitutions can be made without departing from the spirit and scope of the technical solutions of the present application.

Claims

A speech configuration adjustment method, wherein the speech configuration adjustment method comprises:

Receive the session configuration request sent by the client;

Analyzing the speech configuration request to obtain the business attribute of the target speech, and obtaining the corresponding intent set from the intent database based on the business attribute of the target speech;

Extracting multiple target intents from the intent set according to the intent selection instruction, and associating the tagged discourses of the multiple target intents with the service attributes of the target discourse to form discourse configuration information of the target discourse;

creating a force-directed graph of the target speech based on the speech configuration information of the target speech;

Convert the force-directed graph of the target language into a tree-like layout, and display it on the interface of the client;

Adjust the speech configuration information of the target speech according to the speech adjustment instruction.
The discourse configuration adjustment method of claim 1, wherein the creating a force-directed graph of the target discourse based on discourse configuration information of the target discourse comprises:

converting the node of the target speech in the speech configuration information into a node of the corresponding force-directed graph, wherein the node of the force-directed graph includes the speech label of the node of the target speech;

Convert the reference relationship between the nodes of the target speech in the speech configuration information into the edges between the nodes in the corresponding force-directed graph, where the edges between the nodes in the force-directed graph are used as the force The reference relationship between the nodes of the directed graph;

A force-directed graph of the target speech is created from nodes of the force-directed graph and edges between the force-directed graph nodes.
The discourse configuration adjustment method of claim 1, wherein the creating a force-directed graph of the target discourse based on discourse configuration information of the target discourse comprises:

performing data conversion on the discourse configuration information of the target discourse to obtain first structural data;

sending the first structure data to a relational database for processing to obtain the second structure data of the target speech and the third structure data of the reference relationship between the target speech;

Converting the node of the target language of the second structural data into a node of the corresponding force-directed graph, wherein the node of the force-directed graph contains the language label of the node of the target language;

Convert the reference relationship between the nodes of the target language in the third structural data into the edges between the nodes in the corresponding force-directed graph, where the edges between the nodes in the force-directed graph are used as the force The reference relationship between the nodes of the directed graph;

A force-directed graph of the target discourse is created from nodes of the force-directed graph and edges between nodes in the force-directed graph.
The speech configuration adjustment method according to claim 2 or 3, wherein the converting the force-directed graph of the target speech into a tree-like layout comprises:

Copying the speech configuration information in the force-oriented graph of the target speech to obtain the target speech configuration information, and converting the target speech configuration information into a preset tree structure;

calculating the first position coordinates of each node in the force-directed graph of the target speech;

Calculate the second position coordinate of each node according to the preset tree structure;

updating the second position coordinate of each node to the corresponding first position coordinate in the preset tree structure;

Restarting the preset tree structure converts the force-directed graph of the target speech into a tree-like layout.
The speech configuration adjustment method according to claim 1, wherein the adjusting the speech configuration information of the target speech according to the speech adjustment instruction comprises:

Analyzing the speech adjustment instruction to obtain the service attribute to be adjusted;

converting the service attribute to be adjusted into a target tag;

The location coordinates corresponding to the tree layout are determined according to the target label, and the node speech configuration information corresponding to the location coordinates is adjusted.
The discourse configuration adjustment method according to claim 1, wherein the associating the tagged discourses of the multiple target intents with the service attributes of the target discourses comprises:

extracting multiple first tags of multiple tagging words corresponding to each target intent;

extracting multiple key fields in the business attributes of the target language, and converting the multiple key fields into multiple second tags;

matching the plurality of second tags with the plurality of first tags;

When any second tag matches any of the first tags, associate the tagged speech corresponding to the any first label with the service attribute of the target speech.
The discourse configuration adjustment method according to claim 1, wherein the acquiring a corresponding intent set from an intent database based on a business attribute of the target discourse comprises;

Determine the target speech type of the target speech according to the service attribute;

matching the type of the target utterance with the utterance type in the intent database;

When a target speech type matching the target speech type is matched in the speech types in the intent database, obtain the intent set corresponding to the target speech type; or

When no target speech type matching the target speech type is found in the speech types in the intent database, a default intent set is acquired.
An electronic device, wherein the electronic device comprises a memory and a processor, the memory is used to store at least one computer-readable instruction, and the processor is used to execute the at least one computer-readable instruction to implement the following steps:

Receive the session configuration request sent by the client;

Analyzing the speech configuration request to obtain the business attribute of the target speech, and obtaining the corresponding intent set from the intent database based on the business attribute of the target speech;

Extracting multiple target intents from the intent set according to the intent selection instruction, and associating the tagged discourses of the multiple target intents with the service attributes of the target discourse to form discourse configuration information of the target discourse;

creating a force-directed graph of the target speech based on the speech configuration information of the target speech;

Convert the force-directed graph of the target language into a tree-like layout, and display it on the interface of the client;

Adjust the speech configuration information of the target speech according to the speech adjustment instruction.
The electronic device of claim 8, wherein the processor executes the at least one computer-readable instruction to implement the creation of the force directed graph of the target speech based on speech configuration information of the target speech , including:

converting the node of the target speech in the speech configuration information into a node of the corresponding force-directed graph, wherein the node of the force-directed graph includes the speech label of the node of the target speech;

Convert the reference relationship between the nodes of the target speech in the speech configuration information into the edges between the nodes in the corresponding force-directed graph, where the edges between the nodes in the force-directed graph are used as the force The reference relationship between the nodes of the directed graph;

A force-directed graph of the target speech is created from nodes of the force-directed graph and edges between the force-directed graph nodes.
The electronic device of claim 8, wherein the processor executes the at least one computer-readable instruction to implement the creation of the force directed graph of the target speech based on speech configuration information of the target speech , including:

performing data conversion on the discourse configuration information of the target discourse to obtain first structural data;

sending the first structure data to a relational database for processing to obtain the second structure data of the target speech and the third structure data of the reference relationship between the target speech;

Converting the node of the target language of the second structural data into a node of the corresponding force-directed graph, wherein the node of the force-directed graph contains the language label of the node of the target language;

Convert the reference relationship between the nodes of the target language in the third structural data into the edges between the nodes in the corresponding force-directed graph, where the edges between the nodes in the force-directed graph are used as the force The reference relationship between the nodes of the directed graph;

A force-directed graph of the target discourse is created from nodes of the force-directed graph and edges between nodes in the force-directed graph.
The electronic device according to claim 9 or 10, wherein, when the processor executes the at least one computer-readable instruction to realize the conversion of the force-directed graph of the target speech into a tree-like layout, it specifically includes :

Copying the speech configuration information in the force-oriented graph of the target speech to obtain the target speech configuration information, and converting the target speech configuration information into a preset tree structure;

calculating the first position coordinates of each node in the force-directed graph of the target speech;

Calculate the second position coordinate of each node according to the preset tree structure;

updating the second position coordinate of each node to the corresponding first position coordinate in the preset tree structure;

Restarting the preset tree structure converts the force-directed graph of the target speech into a tree-like layout.
The electronic device according to claim 8, wherein, when the processor executes the at least one computer-readable instruction to realize the adjustment of the speech configuration information of the target speech according to the speech adjustment instruction, it specifically includes:

Analyzing the speech adjustment instruction to obtain the service attribute to be adjusted;

converting the service attribute to be adjusted into a target tag;

The location coordinates corresponding to the tree layout are determined according to the target label, and the node speech configuration information corresponding to the location coordinates is adjusted.
9. The electronic device of claim 8, wherein the processor executes the at least one computer-readable instruction to implement the tagging utterances of the plurality of target intents with business attributes of the target utterances When making an association, it specifically includes:

extracting multiple first tags of multiple tagging words corresponding to each target intent;

extracting multiple key fields in the business attributes of the target language, and converting the multiple key fields into multiple second tags;

matching the plurality of second tags with the plurality of first tags;

When any second tag matches any of the first tags, associate the tagged speech corresponding to the any first label with the service attribute of the target speech.
A computer-readable storage medium, wherein the computer-readable storage medium stores at least one computer-readable instruction, and the at least one computer-readable instruction implements the following steps when executed by a processor:

Receive the session configuration request sent by the client;

Analyzing the speech configuration request to obtain the business attribute of the target speech, and obtaining the corresponding intent set from the intent database based on the business attribute of the target speech;

Extracting multiple target intents from the intent set according to the intent selection instruction, and associating the tagged discourses of the multiple target intents with the service attributes of the target discourse to form discourse configuration information of the target discourse;

creating a force-directed graph of the target speech based on the speech configuration information of the target speech;

Convert the force-directed graph of the target language into a tree-like layout, and display it on the interface of the client;

Adjust the speech configuration information of the target speech according to the speech adjustment instruction.
15. The storage medium of claim 14, wherein the at least one computer-readable instruction is executed by the processor to implement the creation of a force directed graph of the target utterance based on utterance configuration information of the target utterance , including:

converting the node of the target speech in the speech configuration information into a node of the corresponding force-directed graph, wherein the node of the force-directed graph contains the speech label of the node of the target speech;

Convert the reference relationship between the nodes of the target speech in the speech configuration information into the edges between the nodes in the corresponding force-directed graph, where the edges between the nodes in the force-directed graph serve as the force The reference relationship between the nodes of the directed graph;

A force-directed graph of the target speech is created from nodes of the force-directed graph and edges between the force-directed graph nodes.
15. The storage medium of claim 14, wherein the at least one computer-readable instruction is executed by the processor to implement the creation of a force directed graph of the target utterance based on utterance configuration information of the target utterance , including:

performing data conversion on the discourse configuration information of the target discourse to obtain first structural data;

sending the first structure data to a relational database for processing to obtain the second structure data of the target speech and the third structure data of the reference relationship between the target speech;

Converting the node of the target language of the second structural data into a node of the corresponding force-directed graph, wherein the node of the force-directed graph contains the language label of the node of the target language;

Convert the reference relationship between the nodes of the target language in the third structural data into the edges between the nodes in the corresponding force-directed graph, where the edges between the nodes in the force-directed graph are used as the force The reference relationship between the nodes of the directed graph;

A force-directed graph of the target discourse is created from nodes of the force-directed graph and edges between nodes in the force-directed graph.
The storage medium of claim 15 or 16, wherein, when the at least one computer-readable instruction is executed by the processor to implement the converting the force-directed graph of the target speech into a tree-like layout, specifically include:

Copying the speech configuration information in the force-oriented graph of the target speech to obtain the target speech configuration information, and converting the target speech configuration information into a preset tree structure;

calculating the first position coordinates of each node in the force-directed graph of the target speech;

Calculate the second position coordinate of each node according to the preset tree structure;

updating the second position coordinate of each node to the corresponding first position coordinate in the preset tree structure;

Restarting the preset tree structure converts the force-directed graph of the target speech into a tree-like layout.
The storage medium according to claim 14, wherein, when the at least one computer-readable instruction is executed by the processor to realize the adjustment of the speech configuration information of the target speech according to the speech adjustment instruction, it specifically comprises:

Parsing the speech adjustment instruction to obtain the service attribute to be adjusted;

converting the service attribute to be adjusted into a target tag;

The position coordinates corresponding to the tree layout are determined according to the target tags, and the node speech configuration information corresponding to the position coordinates is adjusted.
15. The storage medium of claim 14, wherein the at least one computer-readable instruction is executable by the processor to implement the service of linking the plurality of target-intent tagged utterances to the target utterance When attributes are associated, they include:

extracting multiple first tags of multiple tagging words corresponding to each target intent;

extracting multiple key fields in the business attribute of the target language, and converting the multiple key fields into multiple second tags;

matching the plurality of second tags with the plurality of first tags;

When any one of the second tags matches the any one of the first tags, the tagged speech corresponding to the any one of the first labels is associated with the service attribute of the target speech.
A speech configuration adjustment device, wherein the speech configuration adjustment device comprises:

The receiving module is used to receive the technical configuration request sent by the client;

a parsing module, configured to parse the speech configuration request to obtain the business attribute of the target speech, and obtain the corresponding intent set from the intent database based on the business attribute of the target speech;

The extraction module is configured to extract multiple target intents from the intent set according to the intent selection instruction, and associate the tagged discourses of the multiple target intents with the business attributes of the target discourses to form a target discourse speech configuration information;

A creation module, configured to create a force-directed graph of the target speech based on the speech configuration information of the target speech;

a conversion module, for converting the force-directed graph of the target language into a tree-like layout, and displaying it on the interface of the client;

An adjustment module, configured to adjust the speech configuration information of the target speech according to the speech adjustment instruction.