CN112035612A

CN112035612A - PPT automatic declaring method and device based on natural language recognition and processing technology

Info

Publication number: CN112035612A
Application number: CN202010888380.2A
Authority: CN
Inventors: 邹芳; 曹磊
Original assignee: Ping An Life Insurance Company of China Ltd
Current assignee: Ping An Life Insurance Company of China Ltd
Priority date: 2020-08-28
Filing date: 2020-08-28
Publication date: 2020-12-04

Abstract

The application relates to an artificial intelligence technology, is applied to intelligent education, and discloses a PPT automatic announcement method, a device, equipment and a storage medium based on a natural language recognition and processing technology, wherein the method comprises the following steps: loading an imported PPT file; analyzing and extracting the characteristics of the PPT file by using a natural language identification and processing technology; matching a proper interpretation model in an interpretation model library according to the feature extraction result; performing script training based on the matching result to generate a propaganda script; and calling a preset voice robot to announce the explaining script. The PPT automatic propaganda method, the device, the equipment and the storage medium based on the natural language recognition and processing technology can generate a propaganda script based on a preset propaganda model and PPT content, call the voice robot to automatically declare the PPT content, reduce the labor cost and ensure the propaganda effect. The application also relates to blockchain techniques, the declarative models being stored in blockchain nodes.

Description

PPT automatic declaring method and device based on natural language recognition and processing technology

Technical Field

The application relates to the field of artificial intelligence, in particular to a PPT (power point protocol) automatic announcement method, a PPT automatic announcement device, PPT automatic announcement equipment and a storage medium based on natural language recognition and processing technology.

Background

PPT (PowerPoint) is one of the most common office software, has very wide application in various scenes such as content reports, topic speeches, training courseware and the like, and needs to rely on a speaker to perform demonstration and explanation. A good PPT has high correlation between the announcement effect and the talent of the speaker and logic, higher labor cost is needed, and the demonstration effect is poor in certain environments lacking of manpower. Meanwhile, through market demand analysis, a large number of repetitive meetings often exist in daily office, particularly, a phenomenon that the same display content is often explained for a plurality of times in office activities such as enterprise training, road demonstration recommendation, field recruitment, business meetings and the like, and a robot technology is urgently needed to be developed, so that the robot replaces the repeated labor of human beings in the office work, the office efficiency is improved, the conference participation quality is improved, and the innovation influence is enhanced, so that an artificial intelligent robot capable of automatically carrying out PPT content speech is needed to complete the automatic speech work of PPT.

Disclosure of Invention

The main purpose of the present application is to provide a method, an apparatus, a device and a storage medium for PPT automatic declaration based on natural language identification and processing technology, and to solve the technical problems of high labor cost and poor declaration effect of the current PPT content declaration.

In order to achieve the above object, the present application provides a PPT automatic declaration method based on natural language identification and processing technology, including:

loading an imported PPT file;

analyzing and extracting the characteristics of the PPT file by using a natural language identification and processing technology;

matching a proper interpretation model in an interpretation model library according to the feature extraction result;

performing script training based on the matching result to generate a propaganda script;

and calling a preset voice robot to announce the explaining script.

Further, before the step of loading the imported PPT file, the method further includes:

carrying out content specification check on the PPT file;

if the PPT content does not pass the content specification check, prompting the user that the PPT content is not specified, and realizing automatic announcement.

Further, the step of parsing and feature extracting the PPT file by using natural language identification and processing technology includes:

analyzing a directory of the PPT file, and extracting chapter characteristics of the PPT file;

analyzing the content of the PPT file, and extracting the content characteristics of the PPT file;

and analyzing the layout of the PPT file content, and extracting the layout characteristics of the PPT file.

Further, the script training based on the matching result, and the step of generating the announcement script includes:

providing artificial audition for the propaganda script, and acquiring artificial auxiliary correction or supplement contents;

and updating the explaining script according to the artificial auxiliary correction or supplement content.

Further, the step of calling a preset voice robot to announce the announced script comprises:

generating a first interactive window for interacting with a user, wherein the first interactive window is used for starting, pausing and stopping calling the voice robot to carry out PPT content announcement according to the announcement script;

and generating a second interactive window for interacting with the user, wherein the second interactive window is used for adjusting the tone color, the speech speed and the volume of the voice robot.

Further, the step of calling a preset voice robot to announce the announced script further includes:

and recording the speaking process of the speaking robot into a video and storing the video in a storage device.

The embodiment of the present application further provides a PPT automatic announcement device based on natural language identification and processing technology, including:

the loading unit is used for loading the imported PPT file;

the characteristic extraction unit is used for analyzing and extracting the characteristics of the PPT file by utilizing a natural language identification and processing technology;

the matching unit is used for matching a proper interpretation model in the interpretation model base according to the feature extraction result;

the propaganda script generating unit is used for carrying out script training based on the matching result to generate a propaganda script;

and the speaking unit is used for calling a preset voice robot to speak the speaking script.

Further, the feature extraction unit includes:

the chapter feature extraction unit is used for analyzing the directory of the PPT file and extracting chapter features of the PPT file;

the content feature extraction unit analyzes the content of the PPT file and is used for extracting the content features of the PPT file;

and the layout feature extraction unit analyzes the layout of the PPT file content and is used for extracting the layout features of the PPT file.

The present application further provides a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the steps of any of the above methods when executing the computer program.

The present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the method of any of the above.

The PPT automatic propaganda method, the device, the equipment and the storage medium based on the natural language recognition and processing technology can generate a propaganda script based on a preset propaganda model and PPT content, call the voice robot to automatically declare the PPT content, reduce the labor cost and ensure the propaganda effect.

Drawings

Fig. 1 is a schematic flowchart of a PPT auto-declaration method based on natural language identification and processing technology according to an embodiment of the present application;

fig. 2 is a schematic block diagram of a structure of a PPT auto-enunciation device based on natural language identification and processing technology according to an embodiment of the present application;

fig. 3 is a block diagram illustrating a structure of a computer device according to an embodiment of the present application.

The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

The application relates to an artificial intelligence technology, which is applied to intelligent education and realizes a PPT automatic announcement method, a device, equipment and a readable storage medium by utilizing a voice robot and a natural language recognition and processing technology.

Referring to fig. 1, an embodiment of the present application provides a PPT auto-declaration method based on natural language identification and processing technology, including the steps of:

s1, loading the imported PPT file;

s2, analyzing and extracting the characteristics of the PPT file by using a natural language identification and processing technology;

s3, matching a proper declaration model in a declaration model library according to the feature extraction result;

s4, performing script training based on the matching result to generate a propaganda script;

and S5, calling a preset voice robot to announce the announced script.

As described in step S1, for the purpose of automatic declaration of PPT based on natural language recognition and processing technology, the PPT file imported by the user is loaded first. The PPT can be imported by a user through a removable storage medium such as a U disk, a mobile hard disk and the like, or can be shared or downloaded through a network, such as a file transfer tool, a mailbox, a network disk and the like. The process of loading the PPT file imported by the user by the system can be realized by opening the PPT file by utilizing an application program capable of opening the PPT format. After the imported PPT file is loaded, whether the content of the PPT meets the requirements or not can be checked, the check rule is preset, further operation is performed after the PPT is checked, if the PPT does not pass the check, the user can be prompted that the content of the PPT is not standard, automatic announcement cannot be realized, and the user is advised to modify the content format of the PPT.

As described in step S2, the content feature elements are mined by analyzing the contents of the PPT file using the natural language recognition and processing technique. A large number of pictures, tables and the like may exist in the PPT file, and different types of languages, such as chinese and english, chinese and japanese, may also exist in the PPT file, and the contents of the PPT file need to be processed by using a natural language identification and processing technique, so that the contents of the PPT file can be continuously analyzed. Specifically, chapter characteristics of the PPT can be analyzed, for example, contents of a front cover, a catalogue, a text and a back cover of the PPT can be analyzed; the contents of the PPT can be analyzed, such as the title, the subtitle, the text, the graph, the dubbing picture, the dubbing sound, the video, the animation, the attachment and the like of the PPT; the layout characteristics of the PPT can be analyzed, which layout is adopted by the PPT is analyzed, and the analysis result can be one or more combinations of an upper layout, a lower layout, a left layout, a right layout, a center layout and a dispersed layout. The content and the structure of the PPT can be known by analyzing the PPT, and a proper declaration model is selected for content declaration.

As described in the above step S3, an appropriate utterance model is matched in the utterance model library according to the feature extraction result. The declaration model is a rule engine structured and constructed based on characteristics of a PPT (power point) lecture scene, and comprises two parts, wherein the first part is a flow paradigm, if the PPT overall situation (how many pages are total, what the theme is, introduction in several parts and the like) is summarized before the overall declaration, then the declaration is performed page by page, and when each page of content is declared, a corresponding flow paradigm is provided, if the title is broadcasted first, then the content is displayed one by one and is announced in a matched manner according to the principle of firstly displaying left and then right, and firstly displaying up and down. The second part is a content paradigm, which is a rule arrangement based on the common way of declaring material content, such as: the table materials can firstly declare the head of the column and then introduce the data of each row, and the multiple sections of texts can select to broadcast all or only the title according to the number of the texts. The rule engine can be set by a program and continuously expanded manually, and necessary declaration contents of the PPT, such as page summary, content key points, content detailed explanation, animation declaration and the like, can be realized through the PPT declaration model. Specifically, the declaration model comprises a plurality of concrete declaration templates so as to realize professional declaration of different contents. For example, a form declaration template may declare a form, and a chart declaration template may declare a chart, such as a histogram, a pie chart, etc. It is readily understood that declaring a template also relies on recognition techniques for words in the picture. The template can be manually corrected and debugged by a manufacturer, and the specific declaration rule of the template is continuously perfected so that the template has higher accuracy and applicability.

As described in step S4, the scenario training is performed based on the matching result, and the announcement scenario is generated. And the script training refers to a process that the system automatically generates the announced content according to the content analysis result and the model matching result. Specifically, the system determines chapters, contents and layout of PPT contents according to the content analysis result, and then announces corresponding contents according to a corresponding announcement template in an announcement model matched with the analysis result. For example, a declaration outline is determined according to chapters of the PPT, a content declaration sequence is determined according to the layout of the PPT, a corresponding table declaration model is used according to tables in the PPT content, a picture declaration model is used for corresponding pictures, and the like, so that a declaration script is finally generated. The process of script training is according to explaining the template and generating in the model of explaining, and its effect relies on and explains the rule of model, the template and formulates, can provide artifical preview or audition for the script after script training is accomplished to correct or supplement the content of explaining, also can improve the rule in the template of explaining.

As described in step S5, after the lecture script is generated, the system may select the corresponding voice robot timbre, speech rate and volume according to the PPT content and the template to generate the lecture robot, may provide an external window for the user to start or call, and may also provide an external window for the user to actively select the timbre, speech rate and volume of the voice robot.

In one embodiment, before the step of loading the imported PPT file, the method further comprises:

carrying out content specification check on the PPT file;

As described above, the method for PPT auto-declaration based on natural language identification and processing technology in the present application requires that the PPT satisfy a certain format or content specification, and therefore, after loading and importing the PPT file, the method further includes a step of checking the content specification of the PPT file, where the checking rule may be preset, for example, checking whether the PPT has a specific frame, that is, checking whether the PPT has an explicit directory, and whether each directory in the content has a corresponding PPT page, and if the PPT page corresponding to the directory is absent, the content of the PPT may be incomplete, and in order to ensure a complete demonstration effect, a popup window may be used to remind that the PPT content is not normal, and auto-declaration cannot be achieved. Preferably, the user can be prompted about the reason why the PPT content is not normal, so that the user can modify the PPT content in a targeted manner, and robot automatic speech is realized.

In a specific embodiment, the step S2 of parsing and feature extracting the PPT file by using natural language identification and processing technology includes:

As described above, in the present solution, it is necessary to perform content analysis on the PPT file and mine content feature elements. Specifically, chapter characteristics of the PPT can be analyzed, for example, contents of a front cover, a catalogue, a text and a back cover of the PPT can be analyzed; the contents of the PPT can be analyzed, such as the title, the subtitle, the text, the graph, the dubbing picture, the dubbing sound, the video, the animation, the attachment and the like of the PPT; the layout characteristics of the PPT can be analyzed, which layout is adopted by the PPT is analyzed, and the analysis result can be one or more combinations of an upper layout, a lower layout, a left layout, a right layout, a center layout and a dispersed layout. The contents and the structure of the PPT can be known through analyzing the PPT, and a proper declaration model is selected for content declaration.

In one embodiment, the step of matching an appropriate declarative model in a declarative model library based on the feature extraction results is followed by the steps of:

semantic analysis is carried out on the content of the PPT file to obtain a content theme, content theme matching is carried out in a preset announcement database, and the matched data is used as the expanded announcement content of the content theme.

As described above, the contents of the general high-quality declaration PPT file are enriched, and the contents of the PPPT file only need to be declared according to the declaration template, but some PPT files have less contents, and in order to ensure the declaration effect, the declaration contents can be enriched by adopting a method of expanding the declaration contents, so as to ensure the declaration effect. Specifically, semantic analysis can be performed on the contents of the PPT file to obtain a content theme, content theme matching is performed in a preset declaration database, and the matched data is used as the extension declaration contents of the content theme. The preset data of the declaration database can be crawled on the network by utilizing a web crawler technology, for example, the declaration PPT of a product class can be crawled on a company website, and also can be crawled on an encyclopedia website. The expanded declaration content is optional, interaction can be carried out with manual work after the declaration script is generated, and whether the expanded declaration content is added or not is determined manually, so that the relevance of the matched content is ensured, and the declaration effect is improved.

In a specific embodiment, the step of performing script training based on the matching result and generating the announcement script includes:

As described above, the scenario training is performed based on the matching result, and the introduction scenario is generated. And the script training refers to a process that the system automatically generates the announced content according to the content analysis result and the model matching result. After the script training is finished, manual preview or audition can be provided for the script, so that the content of the propaganda is corrected or supplemented.

In one embodiment, the step of calling the preset voice robot to announce the announcement script includes:

As described above, as a speaking robot, the most basic speaking capability is Speech synthesis, and Speech synthesis (Text To Speech) meets the requirement of generating Speech from a known Text, and a man-machine interaction closed loop is opened. The existing voice robot can realize multiple tone color selection, supports self-defined volume and speech speed, and can convert a propaganda script into corresponding propaganda voice by utilizing the voice robot, namely, the robot is generated. In order to make the speech more effective, a first external window interacting with the user may be generated so that the user may actively select the timbre and the speech rate of the voice robot. It is understood that if the user does not actively select the timbre and the speech rate of the voice robot, the system may select the default timbre and the speech rate of the voice robot according to a preset rule. The preset rule can be that the tone and the speech speed of the voice robot are determined according to the content and the length of the PPT, for example, the PPT of the infant product promotion class can use female voice and slower speech speed, and the PPT of the business class content with longer content can use male voice and faster speech speed. And the user can start or call the voice robot at any time through the second external window to finish the declaration of the PPT content according to the declaration script.

In one embodiment, the step of invoking the preset voice robot to announce the announced script further includes:

As described above, in order to facilitate repeated speech of the same PPT content, the process of announcing the PPT by the announcing robot can be recorded as an announcing video, and only the corresponding video needs to be played in the subsequent multiple speeches, the format of the video output is diversified, such as people WMV, AVI, MP4, MOV, MKV, FLV, MPEG, VOB, WEBM, and the like, and the storage device can be a storage tool such as a hard disk, a U disk, and the like.

In one embodiment, the declaration model, the voice robot, the recorded video and the like can be stored in a blockchain, and the PPT automatic declaration method based on the natural language recognition and processing technology is implemented in a blockchain network.

As described above, the blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product services layer, and an application services layer.

The block chain underlying platform can comprise processing modules such as user management, basic service, intelligent contract and operation monitoring. The user management module is responsible for identity information management of all blockchain participants, and comprises public and private key generation maintenance (account management), key management, user real identity and blockchain address corresponding relation maintenance (authority management) and the like, and under the authorization condition, the user management module supervises and audits the transaction condition of certain real identities and provides rule configuration (wind control audit) of risk control; the basic service module is deployed on all block chain node equipment and used for verifying the validity of the service request, recording the service request to storage after consensus on the valid request is completed, for a new service request, the basic service firstly performs interface adaptation analysis and authentication processing (interface adaptation), then encrypts service information (consensus management) through a consensus algorithm, transmits the service information to a shared account (network communication) completely and consistently after encryption, and performs recording and storage; the intelligent contract module is responsible for registering and issuing contracts, triggering the contracts and executing the contracts, developers can define contract logics through a certain programming language, issue the contract logics to a block chain (contract registration), call keys or other event triggering and executing according to the logics of contract clauses, complete the contract logics and simultaneously provide the function of upgrading and canceling the contracts; the operation monitoring module is mainly responsible for deployment, configuration modification, contract setting, cloud adaptation in the product release process and visual output of real-time states in product operation, such as: alarm, monitoring network conditions, monitoring node equipment health status, and the like.

The PPT automatic declaring method based on the natural language identification and processing technology can generate the declaration script based on the preset declaration model and the PPT content, call the voice robot to declare the PPT content automatically, reduce the labor cost and ensure the declaration effect.

Referring to fig. 2, an embodiment of the present application further provides a PPT auto-declaration apparatus based on natural language recognition and processing technology, including:

the loading unit 1 is used for loading the imported PPT file;

the feature extraction unit 2 is used for analyzing and extracting features of the PPT file by using a natural language identification and processing technology;

the matching unit 3 is used for matching a proper interpretation model in the interpretation model base according to the feature extraction result;

a lecture script generating unit 4 for performing script training based on the matching result to generate a lecture script;

and the speaking unit 5 is used for calling a preset voice robot to speak the speaking script.

In one embodiment, the PPT auto-enunciation device based on natural language recognition and processing technology further comprises:

the content specification checking unit is used for checking the content specification of the PPT file;

and the prompting unit is used for prompting the user that the PPT content is not standard and automatic announcement cannot be realized if the PPT content does not pass the content specification check.

In a specific embodiment, the feature extraction unit 2 includes:

In a specific embodiment, the announcement scenario generating unit 4 further includes:

the audition unit is used for providing artificial audition for the propaganda script and acquiring artificial auxiliary correction or supplement contents;

and the updating unit is used for updating the explaining script according to the artificial auxiliary correction or the supplementary content.

In a specific embodiment, the announcement unit 5 includes:

the first interactive window generating unit is used for generating a first interactive window interacted with a user, and the first interactive window is used for starting, pausing and stopping calling the voice robot to carry out PPT content announcement according to the announcement script;

and the second interactive window generating unit is used for generating a second interactive window interacted with the user, and the second interactive window is used for adjusting the tone, the speech speed and the volume of the voice robot.

and the recording unit is used for recording the announcing process of the announcing robot into a video and storing the video in the storage device.

Referring to fig. 3, an embodiment of the present invention further provides a computer device, where the computer device may be a server, and an internal structure of the computer device may be as shown in fig. 3. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer designed processor is used to provide computational and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used for announcing data such as templates and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to realize a PPT automatic declaration method based on natural language recognition and processing technology.

The processor executes the PPT automatic declaring method based on the natural language identification and processing technology, and the PPT automatic declaring method comprises the following steps: loading an imported PPT file; analyzing and extracting the characteristics of the PPT file by using a natural language identification and processing technology; matching a proper interpretation model in an interpretation model library according to the feature extraction result; performing script training based on the matching result to generate a propaganda script; and calling a preset voice robot to announce the explaining script.

In one embodiment, before the step of loading the imported PPT file, the method further comprises: carrying out content specification check on the PPT file; if the PPT content does not pass the content specification check, prompting the user that the PPT content is not specified, and realizing automatic announcement.

In a specific embodiment, the step S2 of parsing and feature extracting the PPT file by using natural language identification and processing technology includes: extracting chapter features of the PPT file; extracting content features of the PPT file; and extracting the layout characteristics of the PPT file.

In a specific embodiment, the step of performing script training based on the matching result and generating the announcement script includes: providing artificial audition for the propaganda script, and acquiring artificial auxiliary correction or supplement contents; and updating the explaining script according to the artificial auxiliary correction or supplement content.

In one embodiment, the step of calling the preset voice robot to announce the announcement script includes: generating a first interactive window for interacting with a user, wherein the first interactive window is used for starting, pausing and stopping calling the voice robot to carry out PPT content announcement according to the announcement script; and generating a second interactive window for interacting with the user, wherein the second interactive window is used for adjusting the tone color, the speech speed and the volume of the voice robot.

In one embodiment, the step of invoking the preset voice robot to announce the announced script further includes: and recording the speaking process of the speaking robot into a video and storing the video in a storage device.

An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a PPT auto-declaration method based on natural language identification and processing technology, and includes the steps of: loading an imported PPT file; analyzing and extracting the characteristics of the PPT file by using a natural language identification and processing technology; matching a proper interpretation model in an interpretation model library according to the feature extraction result; performing script training based on the matching result to generate a propaganda script; and calling a preset voice robot to announce the explaining script.

The PPT automatic propaganda method based on the natural language identification and processing technology can generate a propaganda script based on a preset propaganda model and PPT content, call the voice robot to automatically declare the PPT content, reduce the labor cost and ensure the propaganda effect.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.

The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.

Claims

1. A PPT automatic declaring method based on natural language recognition and processing technology is characterized by comprising the following steps:

loading an imported PPT file;

and calling a preset voice robot to announce the explaining script.

2. The method for PPT auto-declaration based on natural language identification and processing technology as claimed in claim 1, wherein said step of loading imported PPT file is preceded by the steps of:

carrying out content specification check on the PPT file;

3. The PPT auto-enunciation method based on natural language identification and processing technology as claimed in claim 1, wherein the step of parsing and feature extracting the PPT file by using natural language identification and processing technology comprises:

4. The PPT automatic declaration method based on natural language identification and processing technology as claimed in claim 1, wherein the script training is performed based on the matching result, and the step of generating the declaration script is followed by:

5. The PPT automatic declaring method based on natural language identification and processing technology according to claim 1, wherein the step of invoking a preset voice robot to declare the declaration script comprises:

6. The PPT automatic declaring method based on natural language identification and processing technology according to claim 1, wherein the step of invoking a preset voice robot to declare the declaration script further comprises:

recording the speaking process of the speaking robot into a video and storing the video in a storage device;

and generating a third interactive window for interacting with the user, wherein the third interactive window is used for playing the video.

7. A PPT automatic declaring device based on natural language recognition and processing technology is characterized by comprising:

the loading unit is used for loading the imported PPT file;

8. The PPT auto-enunciation device based on natural language recognition and processing technology as claimed in claim 7, wherein said feature extraction unit comprises:

9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 6 when executing the computer program.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.