CN111881307A - Demonstration manuscript generation method and device, computer equipment and storage medium - Google Patents
Demonstration manuscript generation method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111881307A CN111881307A CN202010737234.XA CN202010737234A CN111881307A CN 111881307 A CN111881307 A CN 111881307A CN 202010737234 A CN202010737234 A CN 202010737234A CN 111881307 A CN111881307 A CN 111881307A
- Authority
- CN
- China
- Prior art keywords
- topic
- paragraph
- sub
- presentation
- keywords
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000003860 storage Methods 0.000 title claims description 12
- 239000000463 material Substances 0.000 claims abstract description 107
- 238000004458 analytical method Methods 0.000 claims abstract description 50
- 238000000605 extraction Methods 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 2
- 230000010354 integration Effects 0.000 abstract description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 10
- 238000011161 development Methods 0.000 description 8
- 230000018109 developmental process Effects 0.000 description 8
- 230000008451 emotion Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000003086 colorant Substances 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000007423 decrease Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/43—Querying
- G06F16/435—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/189—Automatic justification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The scheme relates to artificial intelligence and provides a presentation generation method, which comprises the following steps: receiving a main keyword of a presentation inputted by a user through a client; searching text materials in a text material library by using the main keywords; splicing and integrating the text materials; performing manuscript style analysis processing by using the keywords and the subtopics; determining the integral style information of the presentation; inputting the sub-topics and the topic paragraphs corresponding to the sub-topics into a keyword extraction model for relevant word extraction; and inputting the paragraph keywords into a picture library for searching to generate a presentation corresponding to the keywords. According to the method, the material search, the picture material search, the style recommendation and the format typesetting can be performed through the simple main keywords, so that a large amount of time for information search and integration work at the early stage is saved, the corresponding presentation is quickly and automatically generated after the main keywords input by the client side, and the problem of low generation efficiency of the presentation in the prior art is solved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a method and a device for generating a presentation, computer equipment and a storage medium.
Background
With the continuous development of internet technology, the production level of the presentation is gradually improved, the application field is wider and wider, the presentation becomes an important part of the work and life of people, and the presentation plays a significant role in the fields of work reporting, enterprise propaganda, product recommendation, wedding celebration, project bidding, management consultation, education training and the like. The application field of the presentation is increasingly wide, and people have more and more requirements on making slides. The presentation has become an indispensable expression form in modern social work, and the presentation forms of the reports are generally regular and uniform, and the contents are relatively fixed.
At present, when a user makes a presentation, the user needs to manually search relevant information by using a search engine, manually and manually screen required materials from thousands of documents, the required materials need to contain a large number of characters, pictures and the like, then a presentation frame is manually built, the materials are filled in the presentation frame, and finally the typesetting is beautified.
Disclosure of Invention
The invention provides a presentation generation method, a presentation generation device, computer equipment and a storage medium, and aims to solve the problem of low presentation generation efficiency.
A presentation generation method includes:
receiving a main keyword of a presentation inputted by a user through a client;
searching text materials in a text material library by using the main keywords to obtain a plurality of text materials;
splicing and integrating a plurality of text materials to obtain an integral text material;
performing topic identification and paragraph disassembly on the whole text material to obtain at least one sub-topic and a topic paragraph corresponding to the sub-topic;
performing manuscript style analysis processing by using the keywords and the sub-topics to obtain style analysis results corresponding to each sub-topic;
determining the overall style information of the presentation according to the style analysis result corresponding to each subtopic;
inputting the sub-topics and the topic paragraphs corresponding to the sub-topics into a keyword extraction model for related word extraction, and obtaining paragraph keywords related to the topic paragraphs;
inputting a plurality of paragraph keywords into a picture library for searching to obtain a target picture corresponding to the paragraph keywords;
and typesetting according to the target picture, the overall style information of the presentation, the subtopics and the topic paragraphs corresponding to the subtopics to generate the presentation corresponding to the main body keywords.
A presentation generation apparatus comprising:
the receiving module is used for receiving the main keywords of the presentation inputted by the user through the client;
the first search module is used for searching text materials in a text material library by using the main keywords to obtain a plurality of text materials;
the splicing and integrating module is used for splicing and integrating a plurality of text materials to obtain an integral text material;
the recognition and disassembly module is used for performing topic recognition and paragraph disassembly on the whole text material to obtain at least one sub-topic and a topic paragraph corresponding to the sub-topic;
the analysis module is used for carrying out manuscript style analysis processing by utilizing the keywords and the subtopics to obtain a style analysis result corresponding to each subtopic;
the determining module is used for determining the integral style information of the presentation according to the style analysis result corresponding to each subtopic;
the extraction module is used for inputting the subtopic and the topic paragraph corresponding to the subtopic into a keyword extraction model to extract related words, so as to obtain paragraph keywords related to the topic paragraph;
the second search module is used for inputting a plurality of paragraph keywords into a picture library for searching to obtain a target picture corresponding to the paragraph keywords;
and the generation module is used for typesetting according to the target picture, the overall style information of the presentation, the subtopics and the topic paragraphs corresponding to the subtopics to generate the presentation corresponding to the main body keywords.
A computer device comprising a memory, a processor and a computer program stored in said memory and executable on said processor, said processor implementing the steps of the presentation generation method described above when executing said computer program.
A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the presentation generation method described above.
In one scheme of the method, the device, the computer equipment and the storage medium for generating the presentation, a main keyword input by a user through a client is received; searching text materials in a text material library by using the main keywords; splicing and integrating the text materials; carrying out presentation style analysis processing by utilizing the keywords and the subtopics; determining the integral style information of the presentation; inputting the sub-topics and the topic paragraphs corresponding to the sub-topics into a keyword extraction model for relevant word extraction; and inputting a plurality of related words into the photo library for searching to generate a presentation corresponding to the keywords. According to the method, intelligent search of text materials and picture information can be completed through simple main keywords input by a user, presentation template recommendation with a proper style is given by combining types of the main keywords, a large amount of time for information search and integration work in the early stage is saved, material search, picture material search, style recommendation and format typesetting are carried out based on the keywords, so that a corresponding presentation can be quickly and automatically generated after the main keywords input by a client side, and the problem of low generation efficiency of the presentation in the prior art is solved.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the description of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a schematic diagram of an application environment of a presentation generation method according to an embodiment of the present invention;
FIG. 2 is a flowchart of a presentation generation method according to an embodiment of the present invention;
FIG. 3 is another flowchart of a presentation generation method according to an embodiment of the present invention;
FIG. 4 is another flowchart of a presentation generation method according to an embodiment of the present invention;
FIG. 5 is another flowchart of a presentation generation method according to an embodiment of the present invention;
FIG. 6 is another flowchart of a presentation generation method according to an embodiment of the present invention;
FIG. 7 is another flowchart of a presentation generation method according to an embodiment of the present invention;
FIG. 8 is another flowchart of a presentation generation method according to an embodiment of the present invention;
fig. 9 is a functional block diagram of a presentation generation apparatus according to an embodiment of the present invention;
FIG. 10 is a schematic diagram of a computer device according to an embodiment of the invention.
Detailed Description
The technical solutions in the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The presentation generation method provided by the invention can be applied to the application environment shown in fig. 1, wherein a server communicates with a client through a network.
In an embodiment, as shown in fig. 2, a presentation generation method is provided, which is described by taking the application of the method to the server in fig. 1 as an example, and includes the following steps:
s10: and receiving the main keywords of the presentation input by the user through the client.
Understandably, when the presentation needs to be generated, the client can provide the subject keywords input by the user, and the server can receive the subject keywords fed back by the client. The main keyword may be any word, for example, when aiming at a large-segment advanced technology newsletter, the main keyword may be "5G", "regional chain", or the like.
S20: and searching the text materials in a text material library by using the main keywords to obtain a plurality of text materials.
Understandably, the text material library may be a material library for storing text materials, for example, the text material library is searched by using the main keyword "5G" to obtain related text materials such as "5G concept", "5G development status", and the like.
S30: and splicing and integrating a plurality of text materials to obtain an integral text material.
Understandably, the entire text material refers to the text content associated with the text material. For example, the obtained text materials related to the "5G concept", "5G current development", and the like are spliced and integrated to obtain an overall text material, that is, the overall text material is integrated with a plurality of text materials to obtain the text content related to 5G.
S40: and performing topic identification and paragraph disassembly on the whole text material to obtain at least one sub-topic and a topic paragraph corresponding to the sub-topic.
In an embodiment, the whole text material includes a plurality of natural paragraphs, as shown in fig. 3, in step S40, that is, the topic identification and paragraph disassembly are performed on the whole text material to obtain at least one sub-topic and a topic paragraph corresponding to the sub-topic, which specifically includes the following steps:
s41: and performing topic identification on the whole text material by using the keywords in each natural paragraph as features and using an unsupervised clustering model to obtain N sub-topics.
In this step, the overall text material needs to be subject to segmentation topic identification, and for example, the keywords in each sentence in each natural paragraph are taken as features to be subjected to unsupervised clustering by using an unsupervised clustering model, which may be K-means clustering, for dividing the overall text material into N sub-topics, for example, the overall text material under the "5G" main keyword includes sub-topics of "historical development", "existing application", "future trend", and so on.
S42: and performing topic paragraph identification on the whole text material according to the N sub-topics, and identifying a topic paragraph corresponding to each sub-topic.
For example, the overall text material under the "5G" main body keyword includes sub-topics of "historical development", "existing application", "future trend", and the like, the sub-topics of "historical development", "existing application", "future trend", and the like are taken as sub-topic keywords, and the topic paragraphs of the overall text material are identified by using the sub-topic keywords, and the topic paragraphs corresponding to "historical development" are identified as the following paragraphs 1: "1G era, born in chicago in 1986, the first generation of mobile communication technology (1st generation, abbreviated as 1G) went on the stage, etc.," the subject section corresponding to the existing application "is as follows: the existing 5G is applied to the fields of folding car networking, automatic driving, folding surgical operations, folding smart power grids and the like.
Finally, each sub-topic and the corresponding topic paragraph are stored in a structural form in a related mode, understandably, each sub-topic and the corresponding topic paragraph in the whole text material are stored in a related mode, for example, the sub-topic 'historical development' corresponds to the paragraph 1 in the structural form in a related mode; each sub-topic and the corresponding paragraph are stored in an associated manner so as to be convenient for the subsequent generation of a typesetting template corresponding to the sub-topic, and then a slide corresponding to the sub-topic is generated according to the typesetting template, while the whole text material is divided into N sub-topics, each sub-topic can correspond to different typesetting templates, and then a presentation is generated according to the slides corresponding to the N sub-topics.
In the embodiment corresponding to fig. 3, the unsupervised clustering model is used for performing topic identification on the whole text material, so that N sub-topics can be divided, paragraph identification is performed according to the N sub-topics, so that different topic paragraphs corresponding to different topics are separated from the whole text material, and finally, each sub-topic in the whole text material and the corresponding topic paragraph are stored in an associated manner, so that a relatively clear text logic framework is formed.
In an embodiment, as shown in fig. 4, in step S42, that is, performing topic paragraph identification on the whole text material according to the N sub-topics, where the identification of the topic paragraph corresponding to each sub-topic specifically includes the following steps:
s421: and performing abstract extraction processing on each natural paragraph in the subject paragraphs by using a Textrank algorithm to obtain a plurality of abstracts.
S422: and selecting a summary which exceeds a preset important value from a plurality of abstracts extracted from the natural paragraph as a related sentence of the natural paragraph.
In the step, a Textrank algorithm containing semantic information is used for carrying out abstract extraction processing on each natural paragraph in the subject paragraphs to obtain a plurality of abstracts; understandably, the TextRank algorithm is an extraction type summarization method based on a graph model, and the TextRank algorithm can extract the summarization of a document by utilizing semantic information among words in the document. The principle of abstract extraction processing by the TextRank algorithm is as follows: dividing natural paragraphs into a plurality of sentences, using similarity between the sentences as the weight of edges, calculating the TextRank value of the sentences through loop iteration, and selecting a plurality of abstracts of each natural paragraph; and selecting the abstract with more than a preset important value from the plurality of abstracts extracted from the natural paragraph as the associated sentence of the natural paragraph.
S423: and screening the associated sentences by using an MMR model, removing redundant sentences with high semantic association, and obtaining target sentences corresponding to the natural paragraphs.
Understandably, MMR is an abbreviation of maximum local relevance, chinese is the maximum boundary correlation algorithm or the maximum edge correlation algorithm, and the MMR algorithm aims to reduce redundancy of the sorted results and ensure the correlation of the results.
The target sentence is a sentence with unrelated semantics, the related sentence is screened by using the MMR model, and the redundant sentence with high semantic relevance in the related sentence obtained in the step S422 is removed to obtain the target sentence.
S424: and integrating the target sentences corresponding to all the natural paragraphs of the sub-topics to obtain the topic paragraphs corresponding to the sub-topics.
It can be understood that all the natural paragraphs under each sub-topic are integrated with the corresponding target sentences to obtain the topic paragraphs corresponding to the sub-topics, and text materials corresponding to the topic paragraphs under each sub-topic are used.
In the embodiment corresponding to fig. 4, for each natural paragraph in the topic paragraphs, a Textrank algorithm containing semantic information is used to perform abstract extraction processing, to obtain a sentence with high importance in the natural paragraph as an abstract, a sentence with the abstract exceeding a preset importance value is selected as an associated sentence, and then an MMR model is used to remove a redundant sentence with high semantic association, to obtain a text material corresponding to each sub-topic, so as to prevent the problem that the text material has low relevance or the text material is redundant due to excessive text materials, thereby improving the readability of the presentation.
In an embodiment, as shown in fig. 5, after step S40, that is, after performing topic identification and paragraph parsing on the whole text material by using an unsupervised clustering model to obtain at least one sub-topic and a topic paragraph corresponding to the sub-topic, the method specifically includes the following steps:
s43: and detecting whether a topic paragraph corresponding to the sub-topic contains a hierarchical title or not.
S44: and if the topic paragraphs corresponding to the sub-topics contain hierarchical titles, performing hierarchical paragraph parsing on the topic paragraphs corresponding to the sub-topics to obtain hierarchical paragraphs corresponding to the hierarchical titles after the hierarchical paragraphs are parsed.
Exemplarily, performing topic level title identification on topic paragraphs corresponding to the sub-topics by using an unsupervised clustering model to detect whether the topic paragraphs corresponding to the sub-topics contain level titles or not; if the topic paragraphs corresponding to the sub-topics contain hierarchical titles, detecting the hierarchical title corresponding to each topic paragraph, and performing hierarchical paragraph disassembly on the topic paragraphs by using the sub-level titles to obtain the hierarchical paragraphs corresponding to the hierarchical titles after the hierarchical paragraph disassembly; finally, each hierarchy header in the subject paragraph is stored in association with the corresponding hierarchy.
Further, whether the hierarchical paragraphs include sub-hierarchical titles or not can be further judged, and if the hierarchical paragraphs include sub-hierarchical titles, the hierarchical paragraphs are disassembled to obtain sub-hierarchical paragraphs corresponding to the sub-hierarchical titles after the sub-hierarchical paragraphs are disassembled.
In the embodiment corresponding to fig. 5, if the topic section corresponding to the sub-topic includes a hierarchical title, performing hierarchical section parsing on the topic section corresponding to each sub-topic to obtain a hierarchical section corresponding to each hierarchical title after the hierarchical section is parsed, so as to implement parsing the topic section into different hierarchical sections corresponding to different hierarchical titles, and finally performing associated storage on each hierarchical title and corresponding hierarchy in the topic section to form a more complete overall logical frame; in addition, after the topic paragraphs are hierarchically disassembled, the obtained hierarchical titles and hierarchical paragraphs can generate a presentation with higher readability.
S50: and performing manuscript style analysis processing by using the keywords and the sub-topics to obtain style analysis results corresponding to each sub-topic and obtain style analysis results.
Understandably, the document style Analysis processing, namely, the text emotion Analysis (Sentiment Analysis), refers to a process of analyzing, processing and extracting subjective text with emotion colors by using natural language processing and text mining technologies. Understandably, analyzing, processing and extracting the main body keywords and the sub-topics by using text emotion analysis, and extracting the emotions of the main body keywords and the sub-topics, such as science, romance, seriousness and the like;
in this step, the keyword and the sub-topics are used to perform document style analysis processing, so as to obtain a style analysis result corresponding to each sub-topic, and obtain a style analysis result corresponding to each sub-topic, where the style analysis results include, but are not limited to: scientific style, romantic style, serious style, fresh style, brief style, and other styles. In this way, the style analysis result corresponding to each of the sub-topics can be determined. If the emotion of the main body keyword is science and technology and the emotion of the sub-topic is serious, the style analysis result is obtained as science and technology and a serious style, and if the emotion of the main body keyword is science and technology and the emotion of the sub-topic is science and technology, the style analysis result is obtained as science and technology style.
S60: and determining the integral style information of the presentation according to the style analysis result corresponding to each subtopic.
In an embodiment, as shown in fig. 6, in step S60, that is, the determining the style information of the entire presentation according to the style analysis result corresponding to each sub-topic specifically includes the following steps:
s61: and determining template color matching information corresponding to each sub-topic and text format information corresponding to the topic paragraph by using the style analysis result, wherein the text format information comprises text font information and text font size information.
S62: and determining the overall style information of the presentation according to the template color matching information, the text font information and the text font size information.
Understandably, the template color matching information refers to different color matching information corresponding to the style template, and the template color matching information corresponding to the subtopic is searched from a template sample database by using the style analysis result, for example, if the style analysis result is a romantic style, the template color matching information corresponding to the subtopic is determined to be a pink romantic template; finding the text format information corresponding to the sub-topic to the corresponding topic paragraph according to the sub-topic, which can be referred to as step S40 in detail, and will not be described here again; the style analysis result is utilized to determine text format information corresponding to the theme paragraph corresponding to the sub-theme, understandably, the text font information refers to the font type of the text, and the text font size information refers to the font size of the text, for example, the style analysis result is romantic style, the text format information under the romantic style is the text font size information of the five-size, the text font information of the song body, and further, the color matching of the text under the romantic style is light yellow; and finally, determining the overall style information of the presentation according to the template color matching information, the text font information and the text font size information.
In the embodiment corresponding to fig. 6, the template color matching information corresponding to the subtopic and the text format information corresponding to the disassembled material are obtained according to the style analysis result, and then the overall style information of the presentation is determined according to the template color matching information, the text font information and the text font size information, so that the subsequently generated presentation is high in degree of cut.
S70: and inputting the sub-topics and the topic paragraphs corresponding to the sub-topics into a keyword extraction model for related word extraction, so as to obtain paragraph keywords related to the topic paragraphs.
Understandably, common algorithms of the keyword extraction model include TF-IDF (term frequency-inverse document frequency), textrank (term frequency), and the like, and the TF-IDF algorithm is a common weighting technique for information retrieval in information exploration. Is a statistical method for evaluating the importance of a word to one of a set of documents or a corpus of documents. The importance of a word increases in proportion to the number of times it appears in a document, but also decreases in inverse proportion to the frequency with which it appears in the corpus. TextRank is an algorithm based on graph sorting, a text is divided into a plurality of units (words and sentences), graph models are established, important components in the text are sorted by using a voting mechanism, and keyword extraction and abstract making can be realized by using the information of a single-chapter document as far as possible. And inputting the sub-topics and the topic paragraphs corresponding to the sub-topics into a keyword extraction model for relevant word extraction, and extracting relevant word examples related to the topic paragraphs for the topic paragraphs corresponding to the sub-topics, for example, for the front-edge science and technology newsletter of a big paragraph, the relevant words may be "5G", "block chain", "big data", and the like.
S80: and inputting a plurality of paragraph keywords into a picture library for searching to obtain a target picture corresponding to the paragraph keywords.
In an embodiment, as shown in fig. 7, in step S80, that is, inputting a plurality of paragraph keywords into a picture library for searching, to obtain a target picture corresponding to the paragraph keywords, the method specifically includes the following steps:
s81: and inputting a plurality of paragraph keywords into a picture library for searching to obtain a target picture corresponding to the paragraph keywords.
S82: and processing the size of the target picture corresponding to the paragraph key words and adjusting the position of the target picture according to the presentation typesetting template to obtain the adjusted target picture.
Understandably, pictures stored in the picture library all have related subject labels, and a plurality of paragraph keywords are input into the picture library for searching to obtain target pictures corresponding to the paragraph keywords. The layout template of the presentation refers to the standard style template corresponding to the style information of the entire presentation determined in step S60, and different style templates may have certain limitations on the size of the picture. Since the shapes and definitions of the pictures in the picture library are different, when the presentation with the pictures is generated, the pixels of the target picture in the picture library may be different from the picture pixels required by the composition template, and therefore, the size of the target picture corresponding to the paragraph keywords needs to be processed, for example, the searched pixels of the target picture in the picture library are 400 × 500, and the pixels of the picture required by the composition template are 300 × 400, the target picture in the picture library is firstly compressed to 300 × 375, and the remaining 25 pixels of the vertical pixels are temporarily filled with transparent color. In addition, in the generated presentation, the user can also adjust the size of the target picture by himself/herself.
Further, since the shapes of the pictures in the picture library may be in various forms, such as a pentagram, a circle, a triangle, a polygon, etc., and the shape of the picture required by the layout template is a fixed square, the target picture corresponding to the paragraph key needs to be cut to obtain a cut target picture matching the shape of the picture required by the layout template.
Understandably, the typesetting template of the presentation document comprises a preset display position corresponding to the picture, the position of the target picture can be determined according to the typesetting template of the presentation document, and if the position of the target picture deviates from the preset display position, the position of the target picture is adjusted to obtain the adjusted target picture.
In addition, the user can edit or modify the display contents in each presentation. For example, adjusting text, pictures, fonts, colors, text boxes, and adding pictures to a presentation at specified locations.
In the embodiment corresponding to fig. 7, the size of the target picture corresponding to the paragraph keyword and the position of the target picture are adjusted according to the template of the presentation, so that the target picture of the subsequently generated presentation is not large or small, and the position of the target picture exceeds the presentation or is too biased, so that the subsequently generated presentation is highly readable and more attractive.
S90: and typesetting according to the target picture, the overall style information of the presentation, the subtopics and the topic paragraphs corresponding to the subtopics to generate the presentation corresponding to the main body keywords.
In an embodiment, as shown in fig. 8, in step S90, that is, the typesetting is performed according to the target picture, the overall style information of the presentation, the sub-topics, and the topic paragraphs corresponding to the sub-topics, so as to generate the presentation corresponding to the main body keywords, specifically including the following steps:
s91: and extracting the overall style information of the target picture, the demonstration manuscript and the characteristics of the subject paragraph to obtain the corresponding picture characteristics, the style characteristics of the demonstration manuscript and the characteristics of the subject paragraph.
Understandably, the material used for generating the presentation may include at least one of text, picture, audio and video, and the corresponding characteristics of the material are different according to different types of the material, and taking a subject paragraph as an example, the characteristics of the subject paragraph, i.e., the characteristics of the subject paragraph, refer to the number of lines of text, font, and format of each line of text in the paragraph; the characteristics of the target picture, namely picture characteristics, refer to the characteristics of the format, the type and the like of the picture; the style characteristics refer to the overall style corresponding to the presentation, and refer to step S60 in detail, which will not be described herein again.
S92: and matching the picture characteristics, the subject paragraph characteristics and the style characteristics with the pre-stored typesetting rules of the typesetting template to obtain the successfully matched typesetting template corresponding to each sub-subject.
Understandably, matching the picture characteristics, the subject paragraph characteristics and the style characteristics with the pre-stored typesetting rules of the typesetting template to obtain the typesetting template corresponding to the successfully matched typesetting rule; different typesetting templates of the presentation and corresponding typesetting rules are stored in a pre-storage database, for example, the typesetting rule of one typesetting template can be typesetting for one page of the presentation with three lines of characters; or typesetting a page of presentation containing a title and a text, or typesetting the presentation containing pictures and characters according to the sizes of the pictures and the characters and the proportion of the pictures and the characters occupying the page positions, and the like, wherein the corresponding typesetting rules of different typesetting templates can be the same, that is, the same typesetting rule can correspond to a plurality of different typesetting templates; or, the typesetting rules of the typesetting templates may be different according to the difference of the typesetting templates, and the typesetting templates stored in the database may be continuously updated according to the needs of the user.
Matching the picture characteristics and the subject paragraph characteristics with the typesetting rules of the pre-stored typesetting template to obtain the typesetting rules of the pre-stored typesetting template which accord with the picture characteristics and the subject paragraph characteristics; understandably, because the typesetting rules of the typesetting templates have corresponding relations with the picture characteristics and the subject paragraph characteristics, one typesetting rule may correspond to a plurality of different typesetting templates in the pre-stored typesetting templates and the database of the corresponding typesetting rules for the picture characteristics and the subject paragraph characteristics, therefore, when the picture characteristics and the subject paragraph characteristics are matched with the pre-stored typesetting rules of the typesetting templates, the typesetting rules corresponding to each typesetting template in the database need to be extracted first, then the typesetting rules matched with the picture characteristics and the characteristics of the subject paragraph characteristics are selected from all the extracted typesetting rules, and then each corresponding typesetting template is inquired from the database according to the successfully matched typesetting rules.
For example, 3 lines of characters are stored in the topic paragraph feature, a sub-topic corresponding to the topic paragraph represents that a topic needs to be highlighted at a main level, a first line of characters of the topic paragraph feature is "a company 2018 new-article release meeting in spring," a secondary highlight is performed, a second line of characters is "2018.04.0914: 30," represents time, and may be not highlighted, and a third line of characters represents a place for "Beijing university gym," or may be not highlighted. According to the theme topic paragraph, the corresponding theme paragraph characteristics can be acquired as 3 lines of characters in one page of presentation, wherein the main level of the sub-theme is highlighted, the secondary level of the first line is highlighted, the second line and the third line are not highlighted, the picture characteristics comprise a square picture, according to the typesetting rule, the typesetting rule extracted from the database can be utilized to be matched with the theme paragraph characteristics and the picture characteristics, and then the typesetting template which is successfully matched with the theme paragraph characteristics and the picture characteristic package and is suitable for the sub-theme, the 3 lines of characters and the square picture in one page of presentation can be inquired, and the number of the typesetting templates which accord with the typesetting rule can be multiple; therefore, the typesetting template of the typesetting rule is further determined according to the style characteristics, for example, if the style characteristics are romantic, the typesetting template with the style characteristics being romantic is further matched.
In addition, the typesetting template corresponding to the successfully matched typesetting rule is displayed to the user, and the user can perform preselection operation on the typesetting template.
S93: and typesetting the target picture, the sub-topics and the topic paragraphs corresponding to the sub-topics by utilizing the successfully matched typesetting template corresponding to each sub-topic to generate the presentation corresponding to the main body keywords.
Understandably, the target pictures, the sub-topics and the topic paragraphs corresponding to the sub-topics are typeset by utilizing the typesetting templates corresponding to the successfully matched typesetting rules, so that each sub-topic, the topic paragraphs corresponding to the sub-subjects and the target pictures corresponding to the topic paragraphs are typeset by utilizing the successfully matched typesetting templates to generate slides corresponding to the sub-topics, and then the presentation corresponding to the main-subject keywords is automatically generated according to the slides corresponding to the N sub-topics.
In the embodiment corresponding to fig. 8, the picture features, the document style features and the topic paragraph features are matched with the typesetting rules of the pre-stored typesetting templates, and typesetting is performed by using the typesetting templates corresponding to the successfully matched typesetting rules, so that the presentation corresponding to the main body keywords can be automatically generated, thereby realizing a generation mode of a presentation with higher intelligence and automation level, saving time and labor, improving user experience, and improving the generation efficiency of the presentation.
In the embodiment corresponding to fig. 2, the method and the system can complete intelligent search of text materials and picture information through simple main keywords input by a user, and provide style-appropriate presentation template recommendation by combining the types of the main keywords, so that a large amount of time for information search and integration work in the early stage is saved, and material search, picture material search, style recommendation and format typesetting are performed based on the main keywords, so that the corresponding presentation can be quickly and automatically generated after the main keywords input by a client, and the problem of low generation efficiency of the presentation in the prior art is solved.
It should be understood that, the sequence numbers of the steps in the above embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the present invention.
In an embodiment, a presentation generation apparatus is provided, which corresponds to the presentation generation method in the above-described embodiment one to one. As shown in fig. 9, the presentation generating apparatus includes a receiving module 10, a first searching module 20, a splicing and integrating module 30, a recognition and parsing module 40, an analyzing module 50, a determining module 60, an extracting module 70, a second searching module 80, and a generating module 90. The functional modules are explained in detail as follows:
a receiving module 10, which receives a main keyword of a presentation inputted by a user through a client;
the first search module 20 is used for searching text materials in a text material library by using the main keywords to obtain a plurality of text materials;
the splicing and integrating module 30 is used for splicing and integrating a plurality of text materials to obtain an integral text material;
the identification disassembling module 40 is used for performing topic identification and paragraph disassembly on the whole text material to obtain at least one sub-topic and a topic paragraph corresponding to the sub-topic;
the analysis module 50 is used for performing document style analysis processing by using the keywords and the sub-topics to obtain style analysis results corresponding to each sub-topic;
the determining module 60 determines the overall style information of the presentation according to the style analysis result corresponding to each sub-topic;
the extracting module 70 inputs the sub-topics and the topic paragraphs corresponding to the sub-topics into a keyword extraction model for related word extraction, so as to obtain paragraph keywords related to the topic paragraphs;
the second search module 80 inputs a plurality of paragraph keywords into the picture library for searching to obtain a target picture corresponding to the paragraph keywords;
and the generating module 90 performs typesetting according to the target picture, the overall style information of the presentation, the sub-topics and the topic paragraphs corresponding to the sub-topics, and generates the presentation corresponding to the main body keywords.
For specific limitations of the presentation generation apparatus, reference may be made to the above limitations of the presentation generation method, which are not described herein again. The respective modules in the presentation generation apparatus may be wholly or partially implemented by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, as shown in fig. 10, there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
receiving a main keyword of a presentation inputted by a user through a client;
searching text materials in a text material library by using the main keywords to obtain a plurality of text materials;
splicing and integrating a plurality of text materials to obtain an integral text material;
performing topic identification and paragraph disassembly on the whole text material to obtain at least one sub-topic and a topic paragraph corresponding to the sub-topic;
performing manuscript style analysis processing by using the keywords and the sub-topics to obtain style analysis results corresponding to each sub-topic;
determining the overall style information of the presentation according to the style analysis result corresponding to each subtopic;
inputting the sub-topics and the topic paragraphs corresponding to the sub-topics into a keyword extraction model for related word extraction, and obtaining paragraph keywords related to the topic paragraphs;
inputting a plurality of paragraph keywords into a picture library for searching to obtain a target picture corresponding to the paragraph keywords;
and typesetting according to the target picture, the overall style information of the presentation, the subtopics and the topic paragraphs corresponding to the subtopics to generate the presentation corresponding to the main body keywords.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
receiving a main keyword of a presentation inputted by a user through a client;
searching text materials in a text material library by using the main keywords to obtain a plurality of text materials;
splicing and integrating a plurality of text materials to obtain an integral text material;
performing topic identification and paragraph disassembly on the whole text material to obtain at least one sub-topic,
and a topic paragraph corresponding to the sub-topic;
performing manuscript style analysis processing by using the keywords and the sub-topics to obtain style analysis results corresponding to each sub-topic;
determining the overall style information of the presentation according to the style analysis result corresponding to each subtopic;
inputting the sub-topics and the topic paragraphs corresponding to the sub-topics into a keyword extraction model for related word extraction, and obtaining paragraph keywords related to the topic paragraphs;
inputting a plurality of paragraph keywords into a picture library for searching to obtain a target picture corresponding to the paragraph keywords;
and typesetting according to the target picture, the overall style information of the presentation, the subtopics and the topic paragraphs corresponding to the subtopics to generate the presentation corresponding to the main body keywords.
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 used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. 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 Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present 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 solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. A presentation generation method, comprising:
receiving a main keyword of a presentation inputted by a user through a client;
searching text materials in a text material library by using the main keywords to obtain a plurality of text materials;
splicing and integrating a plurality of text materials to obtain an integral text material;
performing topic identification and paragraph disassembly on the whole text material to obtain at least one sub-topic and a topic paragraph corresponding to the sub-topic;
performing manuscript style analysis processing by using the keywords and the sub-topics to obtain style analysis results corresponding to each sub-topic;
determining the overall style information of the presentation according to the style analysis result corresponding to each subtopic;
inputting the sub-topics and the topic paragraphs corresponding to the sub-topics into a keyword extraction model for related word extraction, and obtaining paragraph keywords related to the topic paragraphs;
inputting a plurality of paragraph keywords into a picture library for searching to obtain a target picture corresponding to the paragraph keywords;
and typesetting according to the target picture, the overall style information of the presentation, the subtopics and the topic paragraphs corresponding to the subtopics to generate the presentation corresponding to the main body keywords.
2. The method of generating a presentation as claimed in claim 1, wherein the overall text material includes a plurality of natural paragraphs, and performing topic identification and paragraph parsing on the overall text material to obtain at least one sub-topic and a topic paragraph corresponding to the sub-topic comprises:
performing topic identification on the whole text material by using the keywords in each natural paragraph as features and using an unsupervised clustering model to obtain N sub-topics;
and performing topic paragraph identification on the whole text material according to the N sub-topics, and identifying a topic paragraph corresponding to each sub-topic.
3. The method of generating a presentation as claimed in claim 1, wherein said performing topic paragraph recognition on said overall text material according to N of said sub-topics, and identifying a topic paragraph corresponding to each of said sub-topics comprises:
performing abstract extraction processing on each natural paragraph in the subject paragraphs by using a Textrank algorithm to obtain a plurality of abstracts;
selecting a summary exceeding a preset important value from a plurality of abstracts extracted from the natural paragraph as a related sentence of the natural paragraph;
screening the associated sentences by using an MMR model, removing redundant sentences with high semantic association, and obtaining target sentences corresponding to the natural paragraphs;
and integrating the target sentences corresponding to all the natural paragraphs of the sub-topics to obtain the topic paragraphs corresponding to the sub-topics.
4. The method for generating a presentation according to claim 1, wherein after performing topic identification and paragraph parsing on the whole text material to obtain at least one sub-topic and a topic paragraph corresponding to the sub-topic, the method further comprises:
detecting whether a topic paragraph corresponding to the sub-topic contains a hierarchical title or not;
and if the topic paragraphs corresponding to the sub-topics contain hierarchical titles, performing hierarchical paragraph parsing on the topic paragraphs corresponding to the sub-topics to obtain hierarchical paragraphs corresponding to the hierarchical titles after the hierarchical paragraphs are parsed.
5. The method for generating a presentation according to claim 1, wherein the determining the style information of the entire presentation according to the style analysis result corresponding to each sub-topic comprises:
determining template color matching information corresponding to each sub-topic and text format information corresponding to a topic paragraph by using the style analysis result, wherein the text format information comprises text font information and text font size information;
and determining the overall style information of the presentation according to the template color matching information, the text font information and the text font size information.
6. The method for generating a presentation as claimed in claim 1, wherein said inputting a plurality of paragraph keywords into a picture library for searching to obtain a target picture corresponding to the paragraph keywords comprises:
inputting a plurality of paragraph keywords into a picture library for searching to obtain a target picture corresponding to the paragraph keywords;
and processing the size of the target picture corresponding to the paragraph key words and adjusting the position of the target picture according to the presentation typesetting template to obtain the adjusted target picture.
7. The method for generating a presentation according to claim 1, wherein generating the presentation corresponding to the main keyword by composing the target picture, the overall style information of the presentation, the sub-topics, and the topic paragraphs corresponding to the sub-topics comprises:
extracting the target picture, the overall style information of the presentation and the characteristics of the subject paragraph to obtain corresponding picture characteristics, document style characteristics and subject paragraph characteristics;
matching the picture characteristics, the subject paragraph characteristics and the style characteristics with the pre-stored typesetting rules of the typesetting template to obtain successfully matched typesetting templates corresponding to each sub-subject;
and typesetting the target picture, the sub-topics and the topic paragraphs corresponding to the sub-topics by utilizing the successfully matched typesetting template corresponding to each sub-topic to generate the presentation corresponding to the main body keywords.
8. A presentation generation apparatus, comprising:
the receiving module is used for receiving the main keywords of the presentation inputted by the user through the client;
the first search module is used for searching text materials in a text material library by using the main keywords to obtain a plurality of text materials;
the splicing and integrating module is used for splicing and integrating a plurality of text materials to obtain an integral text material;
the recognition and disassembly module is used for performing topic recognition and paragraph disassembly on the whole text material to obtain at least one sub-topic and a topic paragraph corresponding to the sub-topic;
the analysis module is used for carrying out manuscript style analysis processing by utilizing the keywords and the subtopics to obtain a style analysis result corresponding to each subtopic;
the determining module is used for determining the integral style information of the presentation according to the style analysis result corresponding to each subtopic;
the extraction module is used for inputting the subtopic and the topic paragraph corresponding to the subtopic into a keyword extraction model to extract related words, so as to obtain paragraph keywords related to the topic paragraph;
the second search module is used for inputting a plurality of paragraph keywords into a picture library for searching to obtain a target picture corresponding to the paragraph keywords;
and the generation module is used for typesetting according to the target picture, the overall style information of the presentation, the subtopics and the topic paragraphs corresponding to the subtopics to generate the presentation corresponding to the main body keywords.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the presentation generation method as claimed in any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the presentation generation method according to any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010737234.XA CN111881307B (en) | 2020-07-28 | 2020-07-28 | Presentation generation method and device, computer equipment and storage medium |
| PCT/CN2020/118004 WO2021164255A1 (en) | 2020-07-28 | 2020-09-27 | Presentation generation method and apparatus, computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010737234.XA CN111881307B (en) | 2020-07-28 | 2020-07-28 | Presentation generation method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111881307A true CN111881307A (en) | 2020-11-03 |
| CN111881307B CN111881307B (en) | 2024-04-05 |
Family
ID=73201395
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010737234.XA Active CN111881307B (en) | 2020-07-28 | 2020-07-28 | Presentation generation method and device, computer equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111881307B (en) |
| WO (1) | WO2021164255A1 (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112328149A (en) * | 2020-11-11 | 2021-02-05 | 维沃移动通信有限公司 | Image format setting method, device and electronic device |
| CN113221509A (en) * | 2021-06-11 | 2021-08-06 | 中国平安人寿保险股份有限公司 | Automatic generation method, device and equipment of slide and storage medium |
| CN113220200A (en) * | 2021-05-25 | 2021-08-06 | 深圳市爱思软件技术有限公司 | Demonstration file display method and device, storage medium and electronic device |
| CN113268971A (en) * | 2021-06-23 | 2021-08-17 | 中国平安人寿保险股份有限公司 | Intelligent generation method and device of demonstration report, computer equipment and storage medium |
| CN113553450A (en) * | 2021-08-03 | 2021-10-26 | 广东新学未科技有限公司 | Automatic PPT presentation generation method and device, computing equipment and storage medium |
| CN113743087A (en) * | 2021-09-07 | 2021-12-03 | 珍岛信息技术（上海）股份有限公司 | Text generation method and system based on neural network vocabulary extension paragraphs |
| CN114398883A (en) * | 2022-01-19 | 2022-04-26 | 平安科技（深圳）有限公司 | Presentation generation method and device, computer readable storage medium and server |
| CN114818731A (en) * | 2022-05-18 | 2022-07-29 | 浙江工业大学 | Keyword extraction method fusing language model and semantic features |
| CN115145452A (en) * | 2022-07-01 | 2022-10-04 | 杭州网易云音乐科技有限公司 | Post generation method, medium, terminal device and computing device |
| CN115203614A (en) * | 2022-07-28 | 2022-10-18 | 武汉小帆船电子商务有限公司 | Page automatic generation, analysis and processing method based on webpage development |
| CN115690116A (en) * | 2022-11-08 | 2023-02-03 | 武汉金山办公软件有限公司 | Image display method and device in presentation |
| CN116561324A (en) * | 2023-07-04 | 2023-08-08 | 江苏曙光云计算有限公司 | Network information intelligent analysis regulation and control system and method based on artificial intelligence |
| CN116579308A (en) * | 2023-07-06 | 2023-08-11 | 之江实验室 | Method and device for generating a presentation |
| CN116579317A (en) * | 2023-07-13 | 2023-08-11 | 中信联合云科技有限责任公司 | Method and system for automatically generating publications based on AI content |
| CN117036203A (en) * | 2023-10-08 | 2023-11-10 | 杭州黑岩网络科技有限公司 | Intelligent drawing method and system |
| WO2024218839A1 (en) * | 2023-04-17 | 2024-10-24 | ヤマハ発動機株式会社 | Content generation system |
| CN119202283A (en) * | 2024-11-22 | 2024-12-27 | 北京饼干科技有限公司 | A method and system for intelligently generating presentations based on AI |
Families Citing this family (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113849462B (en) * | 2021-09-16 | 2025-02-11 | 广东创意热店互联网科技有限公司 | A method, system, computer device and medium for intelligent recommendation of network materials |
| CN113822025A (en) * | 2021-11-25 | 2021-12-21 | 深圳市明源云链互联网科技有限公司 | Office file automatic generation method, device, equipment and storage medium |
| CN114238671A (en) * | 2021-12-17 | 2022-03-25 | 广州金山移动科技有限公司 | Presentation processing method and device, electronic equipment and storage medium |
| CN114254610A (en) * | 2021-12-17 | 2022-03-29 | 广州金山移动科技有限公司 | Slide processing method, device and electronic device |
| CN114501076A (en) * | 2022-02-07 | 2022-05-13 | 浙江核新同花顺网络信息股份有限公司 | Video generation method, apparatus, and medium |
| CN114707009A (en) * | 2022-04-13 | 2022-07-05 | 中国银行股份有限公司 | Written report demonstration manuscript manufacturing method and device |
| CN114912425A (en) * | 2022-05-17 | 2022-08-16 | 中国银行股份有限公司 | Presentation generation method and device |
| CN114996527A (en) * | 2022-06-27 | 2022-09-02 | 招商银行股份有限公司 | Link icon adding method and device, terminal device and storage medium |
| CN115618852B (en) * | 2022-11-22 | 2023-04-07 | 山东天成书业有限公司 | Text digital automatic proofreading system |
| CN116527994A (en) * | 2023-04-19 | 2023-08-01 | 五八畅生活(北京)信息技术有限公司 | Video generation method and device and electronic equipment |
| CN116842138B (en) * | 2023-07-24 | 2024-07-19 | 上海金麦穗信息技术集团有限公司 | Document-based retrieval method, device, equipment and storage medium |
| CN117113961B (en) * | 2023-10-20 | 2024-02-09 | 中电数创(北京)科技有限公司 | Agent-based document writing method and system |
| CN117992622A (en) * | 2024-01-29 | 2024-05-07 | 浪潮智能终端有限公司 | Question-answer type PPT document retrieval system and method based on large model |
| CN117951290A (en) * | 2024-02-04 | 2024-04-30 | 百度在线网络技术（北京）有限公司 | Method, device, electronic device and storage medium for generating presentation content |
| CN118537446A (en) * | 2024-05-08 | 2024-08-23 | 百度在线网络技术（北京）有限公司 | Automatic picture allocation method, device and equipment for presentation file and storage medium |
| CN119150834B (en) * | 2024-11-13 | 2025-03-14 | 北京奇虎科技有限公司 | Content template generation method and device, storage medium and electronic equipment |
| CN119513290B (en) * | 2025-01-13 | 2025-04-11 | 湖南正宇软件技术开发有限公司 | Book content retrieval method, device and computer equipment based on intelligent word segmentation |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001344230A (en) * | 1999-04-30 | 2001-12-14 | Nec Corp | Device and method for generating multimedia document, and recording medium with program for allowing computer to execute the method recorded thereon |
| CN102256030A (en) * | 2010-05-20 | 2011-11-23 | Tcl集团股份有限公司 | Photo album showing system capable of matching background music and background matching method thereof |
| WO2013163636A1 (en) * | 2012-04-28 | 2013-10-31 | Hewlett-Packard Development Company, L.P. | Generating a page, assigning sections to a document and generating a slide |
| CN105763925A (en) * | 2014-12-17 | 2016-07-13 | 珠海金山办公软件有限公司 | Video recording method and device for presentation files |
| CN107077460A (en) * | 2014-09-30 | 2017-08-18 | 微软技术许可有限责任公司 | Structuring sample author content |
| CN110390086A (en) * | 2018-04-19 | 2019-10-29 | 北京搜狗科技发展有限公司 | A kind of method, apparatus and storage medium generating text |
| CN111259180A (en) * | 2020-01-14 | 2020-06-09 | 广州视源电子科技股份有限公司 | Image pushing method and device, electronic equipment and storage medium |
| CN111291210A (en) * | 2020-01-14 | 2020-06-16 | 广州视源电子科技股份有限公司 | Image material library generation method, image material recommendation method and related device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9081765B2 (en) * | 2008-08-12 | 2015-07-14 | Abbyy Infopoisk Llc | Displaying examples from texts in dictionaries |
| CN106021226A (en) * | 2016-05-16 | 2016-10-12 | 中国建设银行股份有限公司 | Text abstract generation method and apparatus |
-
2020
- 2020-07-28 CN CN202010737234.XA patent/CN111881307B/en active Active
- 2020-09-27 WO PCT/CN2020/118004 patent/WO2021164255A1/en active Application Filing
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001344230A (en) * | 1999-04-30 | 2001-12-14 | Nec Corp | Device and method for generating multimedia document, and recording medium with program for allowing computer to execute the method recorded thereon |
| CN102256030A (en) * | 2010-05-20 | 2011-11-23 | Tcl集团股份有限公司 | Photo album showing system capable of matching background music and background matching method thereof |
| WO2013163636A1 (en) * | 2012-04-28 | 2013-10-31 | Hewlett-Packard Development Company, L.P. | Generating a page, assigning sections to a document and generating a slide |
| CN107077460A (en) * | 2014-09-30 | 2017-08-18 | 微软技术许可有限责任公司 | Structuring sample author content |
| CN105763925A (en) * | 2014-12-17 | 2016-07-13 | 珠海金山办公软件有限公司 | Video recording method and device for presentation files |
| CN110390086A (en) * | 2018-04-19 | 2019-10-29 | 北京搜狗科技发展有限公司 | A kind of method, apparatus and storage medium generating text |
| CN111259180A (en) * | 2020-01-14 | 2020-06-09 | 广州视源电子科技股份有限公司 | Image pushing method and device, electronic equipment and storage medium |
| CN111291210A (en) * | 2020-01-14 | 2020-06-16 | 广州视源电子科技股份有限公司 | Image material library generation method, image material recommendation method and related device |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112328149A (en) * | 2020-11-11 | 2021-02-05 | 维沃移动通信有限公司 | Image format setting method, device and electronic device |
| CN113220200A (en) * | 2021-05-25 | 2021-08-06 | 深圳市爱思软件技术有限公司 | Demonstration file display method and device, storage medium and electronic device |
| CN113220200B (en) * | 2021-05-25 | 2023-11-28 | 深圳市爱思软件技术有限公司 | Presentation file presentation method and device, storage medium and electronic device |
| CN113221509A (en) * | 2021-06-11 | 2021-08-06 | 中国平安人寿保险股份有限公司 | Automatic generation method, device and equipment of slide and storage medium |
| CN113221509B (en) * | 2021-06-11 | 2022-06-17 | 中国平安人寿保险股份有限公司 | Automatic generation method, device and equipment of slide and storage medium |
| CN113268971A (en) * | 2021-06-23 | 2021-08-17 | 中国平安人寿保险股份有限公司 | Intelligent generation method and device of demonstration report, computer equipment and storage medium |
| CN113553450A (en) * | 2021-08-03 | 2021-10-26 | 广东新学未科技有限公司 | Automatic PPT presentation generation method and device, computing equipment and storage medium |
| CN113553450B (en) * | 2021-08-03 | 2024-01-30 | 广东新学未科技有限公司 | Automatic generation method and device of PPT presentation, computing equipment and storage medium |
| CN113743087A (en) * | 2021-09-07 | 2021-12-03 | 珍岛信息技术（上海）股份有限公司 | Text generation method and system based on neural network vocabulary extension paragraphs |
| CN113743087B (en) * | 2021-09-07 | 2024-04-26 | 珍岛信息技术（上海）股份有限公司 | Text generation method and system based on neural network vocabulary extension paragraph |
| CN114398883B (en) * | 2022-01-19 | 2023-07-07 | 平安科技（深圳）有限公司 | Presentation generation method and device, computer readable storage medium and server |
| CN114398883A (en) * | 2022-01-19 | 2022-04-26 | 平安科技（深圳）有限公司 | Presentation generation method and device, computer readable storage medium and server |
| CN114818731A (en) * | 2022-05-18 | 2022-07-29 | 浙江工业大学 | Keyword extraction method fusing language model and semantic features |
| CN114818731B (en) * | 2022-05-18 | 2025-02-18 | 浙江工业大学 | A keyword extraction method integrating language model and semantic features |
| CN115145452A (en) * | 2022-07-01 | 2022-10-04 | 杭州网易云音乐科技有限公司 | Post generation method, medium, terminal device and computing device |
| CN115203614A (en) * | 2022-07-28 | 2022-10-18 | 武汉小帆船电子商务有限公司 | Page automatic generation, analysis and processing method based on webpage development |
| CN115690116A (en) * | 2022-11-08 | 2023-02-03 | 武汉金山办公软件有限公司 | Image display method and device in presentation |
| WO2024218839A1 (en) * | 2023-04-17 | 2024-10-24 | ヤマハ発動機株式会社 | Content generation system |
| CN116561324A (en) * | 2023-07-04 | 2023-08-08 | 江苏曙光云计算有限公司 | Network information intelligent analysis regulation and control system and method based on artificial intelligence |
| CN116561324B (en) * | 2023-07-04 | 2023-09-01 | 江苏曙光云计算有限公司 | Network information intelligent analysis regulation and control system and method based on artificial intelligence |
| CN116579308A (en) * | 2023-07-06 | 2023-08-11 | 之江实验室 | Method and device for generating a presentation |
| CN116579308B (en) * | 2023-07-06 | 2023-10-10 | 之江实验室 | Presentation generation method and device |
| CN116579317A (en) * | 2023-07-13 | 2023-08-11 | 中信联合云科技有限责任公司 | Method and system for automatically generating publications based on AI content |
| CN116579317B (en) * | 2023-07-13 | 2023-10-13 | 中信联合云科技有限责任公司 | Method and system for automatically generating publications based on AI content |
| CN117036203B (en) * | 2023-10-08 | 2024-01-26 | 杭州黑岩网络科技有限公司 | Intelligent drawing method and system |
| CN117036203A (en) * | 2023-10-08 | 2023-11-10 | 杭州黑岩网络科技有限公司 | Intelligent drawing method and system |
| CN119202283A (en) * | 2024-11-22 | 2024-12-27 | 北京饼干科技有限公司 | A method and system for intelligently generating presentations based on AI |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021164255A1 (en) | 2021-08-26 |
| CN111881307B (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111881307B (en) | Presentation generation method and device, computer equipment and storage medium | |
| TWI536181B (en) | Language identification in multilingual text | |
| CN112215008B (en) | Entity identification method, device, computer equipment and medium based on semantic understanding | |
| CN113961685A (en) | Information extraction method and device | |
| US20170235841A1 (en) | Enterprise search method and system | |
| US20190392035A1 (en) | Information object extraction using combination of classifiers analyzing local and non-local features | |
| CN112395410B (en) | Entity extraction-based industry public opinion recommendation method and device and electronic equipment | |
| CN111178079B (en) | Triplet extraction method and device | |
| CA3177671A1 (en) | Enquiring method and device based on vertical search, computer equipment and storage medium | |
| US20180081861A1 (en) | Smart document building using natural language processing | |
| CN112818093A (en) | Evidence document retrieval method, system and storage medium based on semantic matching | |
| CN112231494B (en) | Information extraction method and device, electronic equipment and storage medium | |
| US9262400B2 (en) | Non-transitory computer readable medium and information processing apparatus and method for classifying multilingual documents | |
| CN114090776A (en) | Document analysis method, system and device | |
| CN118312583B (en) | LLM-based equipment demand matching method, device and storage medium | |
| CN107357777A (en) | The method and apparatus for extracting label information | |
| CN112529743A (en) | Contract element extraction method, contract element extraction device, electronic equipment and medium | |
| Leonandya et al. | A semi-supervised algorithm for Indonesian named entity recognition | |
| CN117194607A (en) | Searching method and system based on natural language | |
| CN115203445B (en) | Multimedia resource search method, device, equipment and medium | |
| CN111222309A (en) | Question generation method and device | |
| CN113505889B (en) | Processing method and device of mapping knowledge base, computer equipment and storage medium | |
| CN117576262A (en) | Method and device for generating activity poster, storage medium and electronic device | |
| CN111681731A (en) | Method for automatically marking colors of inspection report | |
| CN112800771A (en) | Article identification method and device, computer readable storage medium and computer equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |