CN117436416A - Presentation generation method and device, electronic equipment and storage medium - Google Patents

Presentation generation method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN117436416A
CN117436416A CN202311385888.0A CN202311385888A CN117436416A CN 117436416 A CN117436416 A CN 117436416A CN 202311385888 A CN202311385888 A CN 202311385888A CN 117436416 A CN117436416 A CN 117436416A
Authority
CN
China
Prior art keywords
target
outline
presentation
text
content
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311385888.0A
Other languages
Chinese (zh)
Inventor
王肃晨
丁健
胡谦
胡慧阳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
iFlytek Co Ltd
Original Assignee
iFlytek Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by iFlytek Co Ltd filed Critical iFlytek Co Ltd
Priority to CN202311385888.0A priority Critical patent/CN117436416A/en
Publication of CN117436416A publication Critical patent/CN117436416A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/10—Text processing
    • G06F40/166—Editing, e.g. inserting or deleting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/10—Text processing
    • G06F40/166—Editing, e.g. inserting or deleting
    • G06F40/186—Templates

Abstract

The invention provides a presentation generating method, a presentation generating device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a content text, wherein the content text represents the content of a presentation to be generated; extracting the outline of the content text to obtain a target outline; extracting the demonstration text of each node in the target outline from the content text; generating a target presentation file containing a content text based on the target outline and the presentation text of each node in the target outline, wherein the presentation text of each node in the target outline is derived from the content text, and ensuring the accuracy and reliability of the extracted presentation text of each node in the target outline; the method can also ensure the demonstration text of each node in the target outline to be embodied without omission, and improves the integrity of the demonstration text of each node in the target outline, thereby improving the accuracy and the integrity of the target demonstration manuscript, reducing the time cost of the demonstration manuscript manufacturing compared with the manual demonstration manuscript manufacturing, and improving the demonstration manuscript manufacturing efficiency.

Description

Presentation generation method and device, electronic equipment and storage medium
Technical Field
The present invention relates to the field of presentation generation technologies, and in particular, to a presentation generation method, device, electronic apparatus, and storage medium.
Background
In recent years, the application level of the presentation file of people is gradually improved, the application field is wider and wider, the presentation file becomes an important component part of the work and life of people, and the application has a significant role in the fields of work report, enterprise propaganda, product recommendation, project bidding, management consultation, education training and the like, so that the efficiency problem of making the presentation file is gradually focused on by people.
At present, the presentation is usually manufactured manually, so that the time cost for manufacturing the presentation is too high, and the efficiency of manufacturing the presentation is reduced.
Disclosure of Invention
The invention provides a method, a device, electronic equipment and a storage medium for generating a presentation, which are used for solving the defects that the presentation is usually manufactured manually, the time cost for manufacturing the presentation is too high, and the efficiency of manufacturing the presentation is reduced in the prior art.
The invention provides a presentation generating method, which comprises the following steps:
acquiring a content text, wherein the content text represents the content of a presentation to be generated;
Extracting the outline of the content text to obtain a target outline;
extracting the demonstration text of each node in the target outline from the content text;
and generating a target presentation file containing the content text based on the target outline and the presentation text of each node in the target outline.
According to the method for generating the presentation file provided by the invention, the method for extracting the presentation text of each node in the target outline from the content text comprises the following steps:
extracting node outline information respectively associated with each node from the target outline;
and matching the node outline information of each node with each language segment in the content text, and determining the demonstration text of the node based on the successfully matched language segments.
According to the presentation generating method provided by the invention, the outline extraction is performed on the content text to obtain the target outline, and the method comprises the following steps:
extracting a primary outline title from the content text;
matching each level of outline title with each language segment in the content text, and generating a second level outline title under each level of outline title based on the language segments matched with each level of outline title;
And constructing the target outline based on the primary outline title and a secondary outline title under the primary outline title.
According to the presentation generating method provided by the invention, the first-level outline title is extracted from the content text, and the method comprises the following steps:
extracting a first-level outline title from the content text based on the title of the target presentation;
the title is determined based on the content text and/or user input.
The presentation generating method provided by the invention further comprises the following steps:
displaying the target presentation and receiving modification operation;
determining the content to be modified and the modification type in the target presentation based on the modification operation;
performing content modification under the modification type on the content to be modified to obtain target content;
and adjusting the target presentation based on the target content, and displaying the adjusted target presentation.
The presentation generating method provided by the invention further comprises the following steps:
and adjusting the demonstration remark text of the target demonstration manuscript based on the target content, wherein the demonstration remark text is determined based on the content text and the text displayed on each page in the target demonstration manuscript.
According to the method for generating the presentation file provided by the invention, the generation of the target presentation file containing the content text based on the target outline and the presentation text of each node in the target outline comprises the following steps:
determining a theme template of the target presentation, the theme template being determined based on the content text and/or the user input;
and generating a target presentation file containing the content text based on the target outline, the presentation text of each node in the target outline and the theme template of the target presentation file.
According to the method for generating the presentation, the theme template for determining the target presentation comprises the following steps:
determining a candidate topic template and displaying based on the semantics of the content text and/or the expression style of the content text;
user input based on the candidate topic templates is received, and in response to the user input, a topic template of the target presentation is determined from the candidate topic templates.
The invention also provides a presentation generating device, comprising:
the acquisition unit is used for acquiring content texts, wherein the content texts represent contents of the presentation to be generated;
The outline extraction unit is used for extracting the outline of the content text to obtain a target outline;
the demonstration text extraction unit is used for extracting demonstration text of each node in the target outline from the content text;
and the target presentation unit is used for generating a target presentation containing the content text based on the target outline and the presentation text of each node in the target outline.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the presentation generating method according to any one of the above when executing the program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a presentation generation method as described in any of the above.
The invention also provides a computer program product comprising a computer program which when executed by a processor implements a presentation generating method as described in any one of the above.
According to the method, the device, the electronic equipment and the storage medium for generating the presentation file, the content text is obtained, the outline extraction is carried out on the content text to obtain the target outline, the presentation text of each node in the target outline is extracted from the content text, and finally, the target presentation file containing the content text is generated based on the target outline and the presentation text of each node in the target outline. The demonstration text of each node in the target outline is derived from the content text, so that on one hand, the accuracy and the reliability of the demonstration text of each node in the extracted target outline are ensured; on the other hand, the method can also ensure the demonstration text of each node in the target outline to be embodied without omission, and improves the integrity of the demonstration text of each node in the extracted target outline, thereby improving the accuracy and the integrity of the target demonstration manuscript generated on the basis of the demonstration text of each node in the target outline, reducing the time cost of the demonstration manuscript manufacturing compared with the manual demonstration manuscript manufacturing, and improving the efficiency of the demonstration manuscript manufacturing.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for generating a presentation file according to the present invention;
fig. 2 is a schematic flow chart of step 130 in the method for generating a presentation file according to the present invention;
fig. 3 is a schematic flow chart of step 120 in the presentation generating method provided by the present invention;
fig. 4 is a schematic flow chart of the adjustment target presentation provided in the present invention;
fig. 5 is a flowchart illustrating step 140 in the method for generating a presentation file according to the present invention;
fig. 6 is a schematic flow chart of step 141 in the method for generating a presentation file according to the present invention;
fig. 7 is a schematic structural diagram of a presentation generating device provided by the present invention;
fig. 8 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention provides a presentation generating method, fig. 1 is a flow diagram of the presentation generating method provided by the invention, as shown in fig. 1, the method comprises the following steps:
step 110, obtaining content text, wherein the content text represents the content of the presentation to be generated.
Specifically, a content text can be obtained, the content text represents the content of a presentation to be generated, the presentation to be generated is the presentation to be generated later, the presentation to be generated can be a presentation of a PPT or similar PPT, and the PPT format can be any one of. PPT or. Pptx.
The content text may be directly input by the user, or may be obtained by performing voice transcription on the acquired audio, or may be obtained by acquiring an image through an image acquisition device such as a scanner, a mobile phone, a camera, a tablet, and performing OCR (Optical Character Recognition ) on the image, which is not particularly limited in the embodiment of the present invention.
The maximum word number of the content text may be 5000 words or 4000 words, or may be adaptively adjusted according to different application scenarios, etc., which is not particularly limited in the embodiment of the present invention.
And 120, extracting the outline of the content text to obtain a target outline.
Specifically, after the content text is obtained, outline extraction may be performed on the content text to obtain a target outline.
Here, the outline extraction is performed on the content text to obtain the target outline, and a large language model (Large Language Model, LLM) may be used, and the large language model may be a large-sized star fire model (IFlytek Spark), an XLnet model (extremum Multi-label Learning Network), a ROBERTa model (Robustly Optimized BERT approach), and the embodiment of the present invention is not limited thereto.
In addition, the user may also perform outline extraction on the content text through a circle selection or a line selection mode to obtain a target outline, or may further perform outline extraction on the content text through a large language model and a circle selection or a line selection mode to obtain a target outline, which is not particularly limited in the embodiment of the present invention.
In consideration of the obtained target outline, the user may have some places that are not satisfied or confused, so that the user is supported to manually modify the page for displaying the target outline, for example, when the user stops the mouse on any outline title in the target outline, an editing and deleting icon is displayed, if the user clicks the editing icon, the specific content of the outline title of the target outline can be modified, and if the user clicks the deleting icon, the outline title corresponding to the icon can be deleted.
In addition, when the user edits the target outline, the large language model can also detect the content edited by the user and the content text, so that a place where the content edited by the user does not match with the content text is detected, and a popup window prompts the user to 'please confirm whether you edit errors'.
For example, a section of the content text is 'dinosaur body type characteristics are different, some Gao Dawei are strong, some are small and flexible, the characteristics not only influence survival strategies of the dinosaur body type characteristics, but also reflect diversity and complexity of biological evolution', one outline in target outline edited by a user is 'animal body type characteristics', and then the large language model can detect that the content edited by the user is not matched with the content text, and the popup window prompts the user to 'please confirm whether you edit errors'.
And 130, extracting the demonstration text of each node in the target outline from the content text.
Specifically, the presentation text of each node in the target outline may be extracted from the content text, where each node in the target outline refers to a basic unit constituting the target outline.
Here, the demonstration text of each node in the target outline is extracted from the content text, and a large language model may be used, and the large language model may be a large-sized language model such as a star fire model, an XLNet model, a ROBERTa model, or the like, which is not particularly limited in the embodiment of the present invention.
It should be noted that, the presentation text of each node in the target outline is extracted from the content text, where the presentation text of each node may be a direct text in the content text, may be a synonymous text in the content text, may be an optimized text obtained after the content text is colored, and the embodiment of the present invention is not limited in particular.
It can be understood that the demonstration text of each node in the target outline is derived from the content text, on one hand, the accuracy and the reliability of the demonstration text of each node in the extracted target outline are ensured; on the other hand, the demonstration text of each node in the target outline can be embodied without omission, and the integrity of the demonstration text of each node in the extracted target outline is improved.
And 140, generating a target presentation file containing the content text based on the target outline and the presentation text of each node in the target outline.
Specifically, after the target outline and the demonstration text of each node in the target outline are obtained, a target demonstration document containing content text can be generated based on the target outline and the demonstration text of each node in the target outline, and the process can generate a cover page, a catalog page, a subject page, a text page and the like of each page of the target demonstration document page by page.
Here, the target presentation, i.e., the presentation finally generated, may be a PPT or PPT-like presentation, and the PPT format may be any of. PPT or. Pptx.
It may be appreciated that the target presentation may include one PPT page or multiple PPT pages, and after the target presentation is generated, a font format of the presentation text in the target presentation may be set, where the font format may include a font size, a font color, a font label, a font thickening, a font inclination, and so on, and the embodiment of the present invention is not limited in this particular manner.
In addition, when the target presentation is generated, the theme template of the target presentation is combined to generate the target presentation which is more suitable for the user. Here, the theme template of the target presentation may include business wind, very simple wind, gradual technology wind, etc., which is not particularly limited in the embodiment of the present invention.
Before generating the target presentation containing the content text, the user may also manually select the content richness of the generated target presentation, for example, may select the content richness of the target presentation as "standard", may select the content richness of the target presentation as "concise", may also select the content richness of the target presentation as "single page", and the embodiment of the present invention is not limited thereto specifically.
Further, when the target presentation is generated, the large language model can recommend a more suitable typesetting template for the target presentation according to the relation between texts in the text content of the target presentation. For example, when the relation between texts in the text content in the target presentation is a total score relation, the large language model may recommend a typesetting template more suitable for the total score relation; for another example, when the relationship between the texts in the text content in the target presentation is a parallel relationship, the large language model may recommend a typesetting template that is more suitable for the parallel relationship, which is not particularly limited in the embodiment of the present invention.
In addition, in consideration of possible dissatisfaction of the user with the generated target presentation, a "regeneration" button is provided at the lowermost end of the target presentation page for generating the content text, and clicking the "regeneration" button regenerates the target presentation.
According to the method provided by the embodiment of the invention, the content text is obtained, the outline extraction is carried out on the content text to obtain the target outline, the demonstration text of each node in the target outline is extracted from the content text, and finally, the target demonstration text containing the content text is generated based on the target outline and the demonstration text of each node in the target outline. The demonstration text of each node in the target outline is derived from the content text, so that on one hand, the accuracy and the reliability of the demonstration text of each node in the extracted target outline are ensured; on the other hand, the method can also ensure the demonstration text of each node in the target outline to be embodied without omission, and improves the integrity of the demonstration text of each node in the extracted target outline, thereby improving the accuracy and the integrity of the target demonstration manuscript generated on the basis of the demonstration text of each node in the target outline, reducing the time cost of the demonstration manuscript manufacturing compared with the manual demonstration manuscript manufacturing, and improving the efficiency of the demonstration manuscript manufacturing.
Based on the above embodiment, fig. 2 is a schematic flow chart of step 130 in the method for generating a presentation file according to the present invention, as shown in fig. 2, step 130 includes:
step 131, extracting node outline information respectively associated with each node from the target outline;
and 132, matching the node outline information of each node with each language segment in the content text, and determining the demonstration text of the node based on the successfully matched language segments.
Specifically, node outline information respectively associated with each node can be extracted from the target outline, wherein the node outline information reflects node information in a directory structure of the target outline, and the node outline information displays main contents and hierarchical relations of the target outline and helps readers to better understand and master key points and structures of the target outline.
After node outline information respectively associated with each node is extracted, the node outline information of each node can be matched with each language segment in the content text, and the demonstration text of the node is determined based on the successfully matched language segments.
It can be understood that the node outline information of each node is matched with each language segment in the content text, and the demonstration text of the node is determined based on the successfully matched language segments, and the source information of each language segment in the content text is covered in the node outline information, so that the speed of determining the demonstration text of the node based on the successfully matched language segments is improved, and the accuracy and reliability of the demonstration text of the node are further improved.
Here, the node outline information of each node is matched with each language segment in the content text, and a large language model may be used, and the large language model may be a large model of a star fire, an XLNet model, a ROBERTa model, or the like, which is not particularly limited in the embodiment of the present invention.
In addition, considering that the time logic or the time sequence of the text content acquisition sequence contained in each language segment in the content text is not necessarily completely matched with the node outline information of each node, namely, some narratives of each language segment in the content text may be disordered, therefore, when determining the demonstration text of the node, the time logic or the time sequence of the text content acquisition sequence contained in each language segment in the content text can also be considered, for example, when the content text is news and the current event type, the demonstration text of the node corresponds to the positive sequence of each language segment in the content text; for another example, when the content text is not a news or a current event type, the presentation text of the node is determined based on the semantic matching of the node outline information of each node and each language segment in the content text, which is not particularly limited in the embodiment of the present invention.
It can be understood that under the condition that the successfully matched speech segments are shorter, the successfully matched speech segments can be directly used as the demonstration text of the node; under the condition that the successfully matched speech segments are longer, abstract text obtained after abstracting the successfully matched speech segments can be used as a demonstration text of the node, and the embodiment of the invention is not particularly limited.
The abstract model (text compression model) may be used for abstracting the successfully matched speech segments, and the abstract model may be a removable abstract model or a generated abstract model.
It can be understood that the demonstration text of each node in the target outline is obtained by matching the node outline information of each node with each language segment in the content text, so that the accuracy and the reliability of the demonstration text of each node in the extracted target outline are ensured from the text level, the matching degree of the node outline information of each node and each language segment in the content text can be ensured from the semantic level, and the accuracy and the integrity of the demonstration text of each node in the extracted target outline are improved.
Based on the above embodiment, fig. 3 is a schematic flow chart of step 120 in the method for generating a presentation file according to the present invention, as shown in fig. 3, step 120 includes:
step 121, extracting a primary outline title from the content text;
step 122, matching each level of outline title with each language segment in the content text, and generating a second level of outline title under each level of outline title based on the language segments matched with each level of outline title;
And step 123, constructing the target outline based on the primary outline title and the secondary outline title under the primary outline title.
Specifically, after the content text is obtained, a primary outline title may be extracted from the content text, where the primary outline title refers to a title hierarchy in the presentation to be generated that is used to specify a paragraph format of the hierarchy (1 st to 9 th) for paragraphs in the content text. Primary outline titles typically use a title 1 style, while outline title levels for title 1 styles generally default to level 1.
Here, the user may also extract the first-level outline title from the content text by a circle selection or a stroke selection manner, or may extract the first-level outline title from the content text by a large language model and a circle selection or a stroke selection manner, which is not limited in particular in the embodiment of the present invention.
In addition, when the primary outline title is extracted from the content text, the title of the target presentation can be referred to, and the relevance between the primary outline title and the title of the target presentation is ensured, so that the accuracy and the reliability of the extracted primary outline title are further improved.
Then, each level one outline title may be matched with each paragraph in the content text, and a level two outline title under each level one outline title may be generated based on the paragraphs matched with each level one outline title.
In addition, considering that the time logic or the time sequence of the text content acquisition sequence contained in each language segment in the content text is not necessarily completely matched with the semantic meaning of each level of outline title, namely, some narratives of each language segment in the content text may be disordered, therefore, when being matched with each level of outline title, the time logic or the time sequence of the text content acquisition sequence contained in each language segment in the content text can also be considered, for example, when the content text is news and the current event type, the secondary outline title under each level of outline title corresponds to the positive sequence of each language segment in the content text; for another example, when the content text is not of news, current types, the secondary outline titles under each primary outline title are determined based on semantic matching of each primary outline title with each paragraph in the content text, which is not particularly limited by the embodiments of the present invention.
Here, the user may also extract the secondary outline titles under each primary outline title from the content text by a circle selection or a line selection manner, or may extract the secondary outline titles under each primary outline title from the content text by a large language model and a circle selection or a line selection manner, which is not limited in particular in the embodiment of the present invention.
Here, the secondary outline title refers to one level in a title hierarchy in the presentation to be generated, the secondary outline title generally uses a title 2 style, and the outline title level of the title 2 style generally defaults to 2 levels.
Here, the matching of each level of outline title with each language segment in the content text may use a large language model, which may be a large model of the starfire, XLNet, ROBERTa, etc., which is not particularly limited in the embodiment of the present invention.
It can be understood that, in the case that the speech segments matched with each primary outline title are shorter, the speech segments matched with each primary outline title can be directly used as the secondary outline title; under the condition that the speech segments matched with the primary outline titles are longer, abstract text obtained after abstracting the speech segments matched with the primary outline titles can be used as a secondary outline title, and the embodiment of the invention is not particularly limited.
The abstract model (text compression model) may be used for abstracting the speech segments matched with the primary outline headlines, and the abstract model may be a removable abstract model or a generative abstract model, which is not limited in particular in the embodiment of the present invention.
After the primary and secondary outline titles are obtained, a target outline may be constructed based on the primary outline title and the secondary outline title under the primary outline title.
It can be understood that the primary outline titles are all derived from the content text, so that the accuracy and the reliability of the extracted primary outline titles are improved; on the other hand, the secondary outline titles are not only derived from the content text, but also matched with the primary outline titles, so that the accuracy and the reliability of the secondary outline titles are further ensured.
According to the method provided by the embodiment of the invention, the primary outline titles are extracted from the content text, each primary outline title is matched with each language segment in the content text, the secondary outline titles under each primary outline title are generated based on the language segments matched with each primary outline title, and the target outline is constructed based on the primary outline titles and the secondary outline titles under the primary outline titles, so that on one hand, the primary outline titles are ensured to be all derived from the content text, and the accuracy and the reliability of the extracted primary outline titles are improved; on the other hand, the secondary outline titles are not only derived from the content text, but also matched with the primary outline titles, so that the accuracy and the reliability of the secondary outline titles are further ensured.
Based on the above embodiment, step 121 includes:
step 1211, extracting a first-level outline title from the content text based on the title of the target presentation;
the title is determined based on the content text and/or user input.
In particular, considering that the primary schema title also needs to be related to the title of the target presentation, the primary schema title may be extracted from the content text based on the title of the target presentation.
Here, the title of the target presentation may be determined based on the content text and/or the user input, that is, the title of the target presentation may be determined based on the content text, may be determined based on the user input, may be determined based on the content text and the user input, and embodiments of the present invention are not limited in detail.
In the case where the title of the target presentation is determined based on the content text and the user input, the title of the target presentation may be generated based on the content text first, and in consideration of the fact that the user may be dissatisfied with or confused with the title of the target presentation, the user may modify the generated title of the target presentation based on the generated title of the target presentation, thereby finally determining the title of the target presentation.
It can be understood that, referring to the title of the target presentation, the primary outline title is extracted from the content text, so as to ensure the relevance between the primary outline title and the title of the target presentation, thereby further improving the accuracy and reliability of the extracted primary outline title.
Based on the above embodiment, fig. 4 is a schematic flow chart of the adjustment target presentation provided by the present invention, as shown in fig. 4, further including:
step 410, displaying the target presentation and receiving a modification operation;
step 420, determining the content to be modified and the modification type in the target presentation based on the modification operation;
step 430, performing content modification under the modification type on the content to be modified to obtain target content;
and step 440, adjusting the target presentation based on the target content, and displaying the adjusted target presentation.
Specifically, in view of the fact that the user may be dissatisfied or questioned with the target presentation after the target presentation is generated, the target presentation may be presented and a modification operation may be received after the target presentation is generated, where the modification operation may include a beautifying operation, a expanding operation, a compacting operation, a translating operation, and the like, and embodiments of the present invention are not limited thereto in particular.
It should be noted that the modification operation may be an operation that needs to be modified, which is detected by the large language model according to information such as a user history habit, or may be a modification operation made by a user selecting and dividing a part of text, or may be a modification operation generated according to a voice command input by the user, which is not limited in particular in the embodiment of the present invention.
After receiving the modification operation, the content to be modified and the modification type in the target presentation may be determined based on the modification operation.
Here, the content to be modified may be obtained by modifying the target presentation file on the terminal screen by the user, where the modifying operation may be any one of a sliding gesture, a dragging gesture, a pressure recognition gesture, a long-press gesture, an area change gesture, a double-press gesture, and a double-click gesture, which is not specifically limited in the embodiment of the present invention.
The modification types herein may include beautification, expansion, compaction, translation, etc., and embodiments of the present invention are not limited in this regard.
After the content to be modified and the modification type in the target presentation are determined, content modification under the modification type can be performed on the content to be modified, so as to obtain target content.
For example, the content to be modified is "the requirements of people on the production of the presentation are higher and higher", the modification type is "expansion writing", and then the content modification under the modification type is "expansion writing" is executed on the content to be modified, and the obtained target content is "the requirements of people on the production of the presentation are higher and higher along with the continuous development and progress of technology". In the past, people may simply use text and pictures to make presentations, but now the demands of people on presentations have far exceeded these basic elements. First, they want the presentation not only to communicate information clearly, but also to attract the attention of the viewer. Thus, designers need to use more innovative and unique design elements, such as animations, videos, etc., to enhance the visual effect of a presentation. Second, they want the presentation to be able to contain more information than just simple text and pictures. Therefore, the producers need to spend more time and effort collecting and organizing the relevant information to ensure that the presentation is both rich and accurate. In addition, they wish to be able to make more interactions with the viewer, such as questions, votes, etc., through the presentation. Therefore, producers need to use more advanced techniques, such as virtual reality, augmented reality, etc., to enhance the interactivity of presentations. "
For another example, the content to be modified is "the requirements of People on the production of the presentation file are higher and higher", the modification type is "translation", and then the content modification under the modification type is "translation" is executed on the content to be modified, and the obtained target content is "peole's demand for presentation production is increasing".
After the target content is obtained, the target presentation may be adjusted based on the target content and the adjusted target presentation may be presented. For example, the corresponding location of the target presentation may be directly replaced with the target content.
According to the method provided by the embodiment of the invention, the target presentation is displayed, the modification operation is received, the content to be modified and the modification type in the target presentation are determined based on the modification operation, then the content modification under the modification type is executed on the content to be modified, the target content is obtained, finally, the target presentation is adjusted based on the target content, and the adjusted target presentation is displayed, so that the content modification under the modification type can be executed on the target presentation, the target presentation is further perfected, and the satisfaction degree of a user on the target presentation is improved.
Based on the above embodiment, further comprising:
And adjusting the demonstration remark text of the target demonstration manuscript based on the target content, wherein the demonstration remark text is determined based on the content text and the text displayed on each page in the target demonstration manuscript.
Specifically, after the target content is obtained, the presentation remark text of the target presentation may be adjusted based on the target content, where the presentation remark text is determined based on the content text and the text presented on each page in the target presentation.
That is, when generating the target presentation, the large language model can synchronously generate the presentation remark text of the target presentation according to the content text and the text displayed on each page in the target presentation, and the target content adjusts the target presentation, so that the presentation remark text of the corresponding target presentation should also be correspondingly adjusted, thereby keeping the consistency of the presentation remark text and the text displayed on each page in the target presentation.
Here, the presentation remark text is a supplementary note added to the target presentation, and mainly plays a role of auxiliary lecture. The presentation notes text may be used for the presenter to view during the presentation, but the audience cannot see the information.
According to the method provided by the embodiment of the invention, the demonstration remark text of the target demonstration manuscript is adjusted based on the target content, and the demonstration remark text is determined based on the content text and the text displayed on each page in the target demonstration manuscript, so that the consistency of the demonstration remark text and the text displayed on each page in the target demonstration manuscript is maintained.
Based on the above embodiment, fig. 5 is a schematic flow chart of step 140 in the method for generating a presentation file according to the present invention, and as shown in fig. 5, step 140 includes:
step 141, determining a theme template of the target presentation, wherein the theme template is determined based on the content text and/or the user input;
and step 142, generating a target presentation file containing the content text based on the target outline, the presentation text of each node in the target outline and the theme template of the target presentation file.
In particular, a topic template for the target presentation may be determined, where the topic template is determined based on the content text and/or user input.
Here, the topic template may be determined based on the content text, may be determined based on the user input, and may be determined based on the content text and the user input, which is not particularly limited in the embodiment of the present invention.
Here, the theme template of the target presentation may include business wind, very simple wind, gradual technology wind, etc., which is not particularly limited in the embodiment of the present invention.
For example, the large language model may recommend a topic template that matches the presentation to be generated based on the semantics and expression style of the content text, and the user may select a final topic template for the target presentation from the topic templates recommended by the large language model.
After determining the topic template of the target presentation, the target presentation including the content text may be generated based on the target outline, the presentation text of each node in the target outline, and the topic template of the target presentation.
After the user determines the topic template, clicking the next generation, and after the large language model receives the user instruction, generating a cover page, a catalog page, a topic page, a text page and the like of each page of the presentation according to the target outline and the presentation text of each node in the target outline page by page. And then rendering and displaying the images to a user for viewing at the web end.
In addition, a catalog icon is displayed on a display page of the target presentation at the web end, the whole catalog structure of the target presentation can be checked by clicking, and the corresponding target presentation page can be jumped by clicking a catalog structure of a certain level.
And when the user modifies and adjusts the primary outline title or the secondary outline title of the target presentation, the displayed directory structure is synchronously updated.
In addition, each page in the target presentation may display a respective subtitle and corresponding description content and picture, where the picture supports user modification and replacement, and may be selected for local or network picture upload.
In addition, the user can click to export the target presentation, and the content of the complete target presentation can be transferred from the format of the webpage end to the format of the target presentation for downloading and saving. After receiving the export instruction of the user, the large language model can describe the structure and the content of the whole target presentation by using a data structure (such as JSON), and then the back end generates a file in the format of the target presentation according to the data structure. Here, the contents described by the data structure include what the title of each page of the target presentation is, several subtitles, how the layout is specific, what the contents are, and so on.
Based on the above embodiment, fig. 6 is a schematic flow chart of step 141 in the method for generating a presentation file according to the present invention, and as shown in fig. 6, step 141 includes:
Step 1411, determining a candidate topic template and displaying based on the semantics of the content text and/or the expression style of the content text;
step 1412, receiving user input based on the candidate topic templates, and determining a topic template for the target presentation from the candidate topic templates in response to the user input.
Specifically, candidate topic templates are determined and presented based on the semantics of the content text and/or the expression style of the content text.
The candidate topic templates may be used as topic templates of the target presentation later, and the candidate topic templates may include business wind, extremely simple wind, gradual technology wind, and the like, which is not particularly limited in the embodiment of the present invention.
Here, the candidate topic templates may be determined and displayed based on the semantics of the content text, may be determined and displayed based on the expression style of the content text, and may be determined and displayed based on the semantics of the content text and the expression style of the content text, which is not particularly limited in the embodiment of the present invention.
For example, when the expression style of the content text is formally compared, the determined candidate topic template may be a business wind; for another example, when the expression style of the content text belongs to the popular science style, the determined candidate topic template may be a gradual change science and technology wind, which is not particularly limited in the embodiment of the present invention.
At this point, the user may make user input to the candidate topic templates, receive user input based on the candidate topic templates, and determine a topic template for the target presentation from the candidate topic templates in response to the user input.
For example, the candidate topic templates include business wind, extremely simple wind, gradual technology wind, etc., and if the user input is extremely simple wind, the topic template of the target presentation is determined to be extremely simple wind from the candidate topic templates.
Based on any one of the above embodiments, a presentation generating method includes the following steps:
first, a content text is acquired, where the content text represents the content of the presentation to be generated.
Second, a first level outline title is extracted from the content text based on the title of the target presentation, where the title is determined based on the content text and/or user input.
And thirdly, matching each primary outline title with each language segment in the content text, and generating a secondary outline title under each primary outline title based on the language segments matched with each primary outline title.
Fourth, a target outline is constructed based on the primary outline title and the secondary outline title under the primary outline title.
And fifthly, extracting node outline information respectively associated with each node from the target outline.
And sixthly, matching the node outline information of each node with each language segment in the content text, and determining the demonstration text of the node based on the successfully matched language segments.
Seventh, determining a candidate theme template and displaying the candidate theme template based on the semantics of the content text and/or the expression style of the content text; user input based on the candidate topic templates is received, and in response to the user input, a topic template for the target presentation is determined from the candidate topic templates.
Eighth, based on the target outline, the demonstration text of each node in the target outline and the theme template of the target demonstration manuscript, generating the target demonstration manuscript containing the content text.
And ninth, displaying the target presentation, receiving a modification operation, and determining the content to be modified and the modification type in the target presentation based on the modification operation.
And tenth, performing content modification under the modification type on the content to be modified to obtain target content, adjusting the target presentation based on the target content, and displaying the adjusted target presentation.
Eleventh, the presentation remark text of the target presentation is adjusted based on the target content, where the presentation remark text is determined based on the content text and the text presented on each page in the target presentation.
The presentation generating device provided by the invention is described below, and the presentation generating device described below and the presentation generating method described above can be referred to correspondingly.
Based on any one of the above embodiments, the present invention provides a presentation generating device, and fig. 7 is a schematic structural diagram of the presentation generating device provided by the present invention, as shown in fig. 7, where the device includes:
an obtaining unit 710, configured to obtain a content text, where the content text represents a content of a presentation to be generated;
a outline extraction unit 720, configured to extract an outline of the content text to obtain a target outline;
an extract presentation text unit 730, configured to extract a presentation text of each node in the target outline from the content text;
and a target presentation unit 740 for generating a target presentation containing the content text based on the target outline and the presentation text of each node in the target outline.
The device provided by the embodiment of the invention acquires the content text, performs outline extraction on the content text to obtain the target outline, extracts the demonstration text of each node in the target outline from the content text, and finally generates the target demonstration manuscript containing the content text based on the target outline and the demonstration text of each node in the target outline. The demonstration text of each node in the target outline is derived from the content text, so that on one hand, the accuracy and the reliability of the demonstration text of each node in the extracted target outline are ensured; on the other hand, the method can also ensure the demonstration text of each node in the target outline to be embodied without omission, and improves the integrity of the demonstration text of each node in the extracted target outline, thereby improving the accuracy and the integrity of the target demonstration manuscript generated on the basis of the demonstration text of each node in the target outline, reducing the time cost of the demonstration manuscript manufacturing compared with the manual demonstration manuscript manufacturing, and improving the efficiency of the demonstration manuscript manufacturing.
Based on any of the above embodiments, the extracting presentation text unit 730 is specifically configured to:
extracting node outline information respectively associated with each node from the target outline;
and matching the node outline information of each node with each language segment in the content text, and determining the demonstration text of the node based on the successfully matched language segments.
Based on any of the above embodiments, the outline extraction unit 720 specifically includes:
a primary outline title extracting unit, configured to extract a primary outline title from the content text;
the matching unit is used for matching each primary outline title with each language segment in the content text and generating a secondary outline title under each primary outline title based on the language segments matched with each primary outline title;
and a target outline constructing unit, configured to construct the target outline based on the primary outline title and a secondary outline title under the primary outline title.
Based on any of the above embodiments, extracting the primary schema title unit is specifically for:
extracting a first-level outline title from the content text based on the title of the target presentation;
the title is determined based on the content text and/or user input.
Based on any one of the above embodiments, the method further includes an adjustment target presentation unit, where the adjustment target presentation unit specifically includes:
the display target presentation unit is used for displaying the target presentation and receiving modification operation;
a modified content unit is used for determining the content to be modified and the modification type in the target presentation file based on the modification operation;
an execution content modification unit, configured to execute content modification under the modification type on the content to be modified, to obtain target content;
and the adjusting unit is used for adjusting the target presentation based on the target content and displaying the adjusted target presentation.
Based on any of the foregoing embodiments, the method further includes adjusting a presentation remark text unit, where the adjusting the presentation remark text unit is specifically configured to:
and adjusting the demonstration remark text of the target demonstration manuscript based on the target content, wherein the demonstration remark text is determined based on the content text and the text displayed on each page in the target demonstration manuscript.
Based on any of the foregoing embodiments, the generating the target presentation unit 740 specifically includes:
a theme template determining unit, configured to determine a theme template of the target presentation, where the theme template is determined based on the content text and/or the user input;
And the target presentation subunit is used for generating a target presentation containing the content text based on the target outline, the presentation text of each node in the target outline and the theme template of the target presentation.
Based on any of the above embodiments, determining the topic template unit is specifically for:
determining a candidate topic template and displaying based on the semantics of the content text and/or the expression style of the content text;
user input based on the candidate topic templates is received, and in response to the user input, a topic template of the target presentation is determined from the candidate topic templates.
Fig. 8 illustrates a physical structure diagram of an electronic device, as shown in fig. 8, which may include: processor 810, communication interface (Communications Interface) 820, memory 830, and communication bus 840, wherein processor 810, communication interface 820, memory 830 accomplish communication with each other through communication bus 840. The processor 810 may invoke logic instructions in the memory 830 to perform a presentation generation method comprising: acquiring a content text, wherein the content text represents the content of a presentation to be generated; extracting the outline of the content text to obtain a target outline; extracting the demonstration text of each node in the target outline from the content text; and generating a target presentation file containing the content text based on the target outline and the presentation text of each node in the target outline.
Further, the logic instructions in the memory 830 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, where the computer program product includes a computer program, where the computer program can be stored on a non-transitory computer readable storage medium, and when the computer program is executed by a processor, the computer can execute a presentation generating method provided by the above methods, and the method includes: acquiring a content text, wherein the content text represents the content of a presentation to be generated; extracting the outline of the content text to obtain a target outline; extracting the demonstration text of each node in the target outline from the content text; and generating a target presentation file containing the content text based on the target outline and the presentation text of each node in the target outline.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the presentation generating method provided by the above methods, the method comprising: acquiring a content text, wherein the content text represents the content of a presentation to be generated; extracting the outline of the content text to obtain a target outline; extracting the demonstration text of each node in the target outline from the content text; and generating a target presentation file containing the content text based on the target outline and the presentation text of each node in the target outline.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (11)

1. A presentation generating method, comprising:
acquiring a content text, wherein the content text represents the content of a presentation to be generated;
extracting the outline of the content text to obtain a target outline;
extracting the demonstration text of each node in the target outline from the content text;
and generating a target presentation file containing the content text based on the target outline and the presentation text of each node in the target outline.
2. The presentation generating method according to claim 1, wherein the extracting the presentation text of each node in the target outline from the content text includes:
extracting node outline information respectively associated with each node from the target outline;
and matching the node outline information of each node with each language segment in the content text, and determining the demonstration text of the node based on the successfully matched language segments.
3. The presentation generating method according to claim 1, wherein the extracting the outline of the content text to obtain the target outline includes:
extracting a primary outline title from the content text;
Matching each level of outline title with each language segment in the content text, and generating a second level outline title under each level of outline title based on the language segments matched with each level of outline title;
and constructing the target outline based on the primary outline title and a secondary outline title under the primary outline title.
4. The presentation generating method as claimed in claim 3, wherein said extracting a primary outline title from said content text comprises:
extracting a first-level outline title from the content text based on the title of the target presentation;
the title is determined based on the content text and/or user input.
5. The presentation generating method according to any one of claims 1 to 4, further comprising:
displaying the target presentation and receiving modification operation;
determining the content to be modified and the modification type in the target presentation based on the modification operation;
performing content modification under the modification type on the content to be modified to obtain target content;
and adjusting the target presentation based on the target content, and displaying the adjusted target presentation.
6. The presentation generating method as claimed in claim 5, further comprising:
and adjusting the demonstration remark text of the target demonstration manuscript based on the target content, wherein the demonstration remark text is determined based on the content text and the text displayed on each page in the target demonstration manuscript.
7. The presentation generating method according to any one of claims 1 to 4, wherein the generating a target presentation containing the content text based on the target outline and presentation text of each node in the target outline includes:
determining a theme template of the target presentation, the theme template being determined based on the content text and/or the user input;
and generating a target presentation file containing the content text based on the target outline, the presentation text of each node in the target outline and the theme template of the target presentation file.
8. The presentation generating method as claimed in claim 7, wherein said determining a theme template of the target presentation comprises:
determining a candidate topic template and displaying based on the semantics of the content text and/or the expression style of the content text;
User input based on the candidate topic templates is received, and in response to the user input, a topic template of the target presentation is determined from the candidate topic templates.
9. A presentation generating apparatus, comprising:
the acquisition unit is used for acquiring content texts, wherein the content texts represent contents of the presentation to be generated;
the outline extraction unit is used for extracting the outline of the content text to obtain a target outline;
the demonstration text extraction unit is used for extracting demonstration text of each node in the target outline from the content text;
and the target presentation unit is used for generating a target presentation containing the content text based on the target outline and the presentation text of each node in the target outline.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the presentation generation method of any of claims 1 to 8 when the program is executed.
11. A non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor implements the presentation generation method of any of claims 1 to 8.
CN202311385888.0A 2023-10-23 2023-10-23 Presentation generation method and device, electronic equipment and storage medium Pending CN117436416A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311385888.0A CN117436416A (en) 2023-10-23 2023-10-23 Presentation generation method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311385888.0A CN117436416A (en) 2023-10-23 2023-10-23 Presentation generation method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN117436416A true CN117436416A (en) 2024-01-23

Family

ID=89552768

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311385888.0A Pending CN117436416A (en) 2023-10-23 2023-10-23 Presentation generation method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117436416A (en)

Similar Documents

Publication Publication Date Title
US20180130496A1 (en) Method and system for auto-generation of sketch notes-based visual summary of multimedia content
US9036950B2 (en) Autogenerating video from text
CN104735468B (en) A kind of method and system that image is synthesized to new video based on semantic analysis
US9613268B2 (en) Processing of images during assessment of suitability of books for conversion to audio format
US20130191728A1 (en) Systems, methods, and media for generating electronic books
WO2012086356A1 (en) File format, server, view device for digital comic, digital comic generation device
US20160117301A1 (en) Annotation sharing system and method
JP2020005309A (en) Moving image editing server and program
CN111930289B (en) Method and system for processing pictures and texts
CN111553138B (en) Auxiliary writing method and device for standardizing content structure document
CN117436417A (en) Presentation generation method and device, electronic equipment and storage medium
CN117436414A (en) Presentation generation method and device, electronic equipment and storage medium
JP2019220098A (en) Moving image editing server and program
CN110297965B (en) Courseware page display and page set construction method, device, equipment and medium
CN113438532B (en) Video processing method, video playing method, video processing device, video playing device, electronic equipment and storage medium
CN117436416A (en) Presentation generation method and device, electronic equipment and storage medium
US11532111B1 (en) Systems and methods for generating comic books from video and images
JP6900334B2 (en) Video output device, video output method and video output program
CN117436415A (en) Presentation generation method and device, electronic equipment and storage medium
CN113918114B (en) Document control method, device, computer equipment and storage medium
TWI828490B (en) Online text translation system for page-turning comics
Fraser Contextually Recommending Expert Help and Demonstrations to Improve Creativity
US20240086452A1 (en) Tracking concepts within content in content management systems and adaptive learning systems
CN117171369A (en) Content generation method, device, computer equipment and storage medium
Warner Enhancing Visual Media Through Reflection and Recomposition

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination