Method, system and equipment for automatically updating PowerPoint and storage medium

Abstract

The invention discloses a method, a system and equipment for automatically updating a PowerPoint, and a storage medium, and the key points of the technical scheme are as follows: responding to an updating request of the PowerPoint; extracting first text paragraphs of the PowerPoint, and obtaining first paragraph vectors after performing structuring and vectorization processing on each first text paragraph; extracting second text paragraphs of the captured update information, and obtaining second paragraph vectors after structuring and vectorizing each second text paragraph; calculating semantic similarity between the first paragraph vector and the second paragraph vector to obtain a similarity matrix; and constructing a diffusion matrix according to the similarity matrix, simulating propagation of the update information between the first paragraph vectors through the diffusion matrix to obtain updated first paragraph vectors, and updating the presentation file according to the updated first paragraph vectors. According to the method, the presentation file is automatically updated, the presentation file content is optimized according to the updated content, and the presentation file making efficiency and quality are improved.

Description

Technical Field

[0001] The present invention belongs to the field of automated office technology, and in particular relates to a presentation automatic updating method, system, device and storage medium. Background Art

[0002] Presentations (PowerPoint, PPT) are widely used in daily work as one of the reporting media for daily meetings and summaries.

[0003] In today's era of information explosion, information is constantly updated every day. Due to the continuous updating of information, presentations must also be constantly updated, especially in the field of teaching. Teachers' teaching presentations usually need to keep up with the latest information. However, manually updating presentations based on the latest information is very cumbersome and inefficient. Summary of the invention

[0004] The purpose of the present invention is to provide a method, system, device and storage medium for automatically updating presentations, which can realize automatic updating of presentations and improve the efficiency and quality of making presentations.

[0005] A first aspect of the present invention provides a method for automatically updating a presentation, comprising:

[0006] respond to presentation update requests;

[0007] Extracting all first text paragraphs of the presentation, and performing structure processing and vectorization processing on each first text paragraph to obtain a first paragraph vector;

[0008] Extract all second text paragraphs of the captured update information, perform structural processing and vectorization processing on each second text paragraph, and obtain a second paragraph vector;

[0009] Calculate the semantic similarity between all first paragraph vectors and all second paragraph vectors to obtain a similarity matrix;

[0010] A diffusion matrix is ​​constructed according to the similarity matrix, and the propagation of the update information between the first paragraph vectors is simulated by the diffusion matrix to obtain the updated first paragraph vectors, and the presentation is updated according to all the updated first paragraph vectors.

[0011] In some embodiments, calculating the semantic similarity between all first paragraph vectors and all second paragraph vectors includes:

[0012] The semantic similarity between all first paragraph vectors and all second paragraph vectors is calculated according to the similarity calculation formula, and the similarity calculation formula is:

[0013] E ij =(Vi *V j ) / (||V i ||*||V j ||)

[0014] Among them, the V i represents the first paragraph vector of the ith paragraph, V j represents the jth second paragraph vector, E ij Represents the semantic similarity between the i-th first paragraph vector and the j-th second paragraph vector.

[0015] In some embodiments, constructing a diffusion matrix according to the similarity matrix includes:

[0016] The propagation ratio of all second paragraph vectors to all first paragraph vectors is calculated according to the propagation ratio calculation formula, and the propagation ratio calculation formula is:

[0017]

[0018] Among them, the E ij represents the semantic similarity between the i-th first paragraph vector and the j-th second paragraph vector, D ij Indicates the propagation ratio of the i-th first paragraph vector to the j-th second paragraph vector;

[0019] The propagation ratios of all second paragraph vectors on all first paragraph vectors constitute a diffusion matrix.

[0020] In some embodiments, simulating the propagation of update information between first paragraph vectors through the diffusion matrix to obtain an updated first paragraph vector includes:

[0021] During the propagation process, the first paragraph vector is updated according to the diffusion matrix. After multiple rounds of propagation, the change amplitude between the first paragraph vector after each round of propagation and the first paragraph vector of the previous round is calculated. When the change amplitude of the first paragraph vector is lower than the preset threshold, the propagation is stopped and the first paragraph vector obtained after the last round of propagation is used as the updated first paragraph vector.

[0022] In some embodiments, updating the first paragraph vector according to the diffusion matrix during the propagation process includes:

[0023] During the propagation process, the first paragraph vector is updated according to the paragraph update formula, which is:

[0024]

[0025] Wherein, D represents the diffusion matrix, represents the set of first paragraph vectors of round k, Represents the set of first paragraph vectors of round k+1.

[0026] In some embodiments, calculating the change magnitude between the first paragraph vector after each round of propagation and the first paragraph vector of the previous round includes:

[0027] The change amplitude between the first paragraph vector after each round of propagation and the first paragraph vector of the previous round is calculated according to the change amplitude calculation formula, and the change amplitude calculation formula is:

[0028]

[0029] Wherein, A represents the change amplitude between the first paragraph vector after each round of propagation and the first paragraph vector of the previous round.

[0030] In some embodiments, extracting all first text paragraphs of the presentation, and performing structural processing and vectorization processing on each first text paragraph to obtain a first paragraph vector includes:

[0031] Extracting all first text paragraphs of each page in order according to the page number of the presentation document to obtain a first paragraph set of each page;

[0032] After the first paragraph set of each page is structured and vectorized, the first vector set of each page is obtained.

[0033] A second aspect of the present invention provides a presentation automatic updating system, comprising:

[0034] A data acquisition module for responding to presentation update requests;

[0035] A first processing module is used to extract all first text paragraphs of the presentation document, and obtain a first paragraph vector after performing structural processing and vectorization processing on each first text paragraph;

[0036] A second processing module is used to extract all second text paragraphs of the captured update information, and obtain a second paragraph vector after performing structural processing and vectorization processing on each second text paragraph;

[0037] A similarity calculation module is used to calculate the semantic similarity between all first paragraph vectors and all second paragraph vectors to obtain a similarity matrix;

[0038] A propagation update module is used to construct a diffusion matrix according to the similarity matrix, simulate the propagation of update information between first paragraph vectors through the diffusion matrix, obtain updated first paragraph vectors, and update the presentation according to all updated first paragraph vectors.

[0039] A third aspect of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0040] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0041] The technical solution provided by the present invention has the following advantages and effects: by calculating the semantic similarity between the presentation and the update information, a similarity matrix is ​​obtained, and an update report is obtained through the similarity matrix and multiple rounds of information propagation processing, thereby realizing automatic updating of the presentation, ensuring that the presentation content is optimized according to the updated content, and improving the efficiency and quality of presentation production. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flowchart of the automatic presentation updating method provided by the present invention;

[0043] Figure 2 It is a structural block diagram of the presentation automatic updating system provided by the present invention;

[0044] Figure 3 It is a diagram of the internal structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to facilitate the understanding of the present invention, specific embodiments of the present invention will be described in more detail below with reference to the accompanying drawings.

[0046] Unless otherwise specified or defined, the "first, second..." used in this article is merely used to distinguish names and does not represent a specific quantity or order.

[0047] Unless specifically stated or defined otherwise, the term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0048] It should be noted that, in this document, “fixed to” or “connected to” may mean directly fixing or connecting to an element, or indirectly fixing or connecting to an element.

[0049] like Figure 1 As shown, this embodiment provides a method for automatically updating a presentation, comprising the following steps S1 to S5:

[0050] Step S1, responding to a presentation update request.

[0051] In actual applications, the presentation can be a locally stored presentation or a remote server presentation. After the user uploads or specifies the presentation, an update request is issued. Update information can be captured from specified information materials or industry news. This can be captured in advance or during the presentation update process. The specified information materials can be academic databases, electronic journals, online libraries, data and announcements released by governments or institutions, etc. Crawler tools can be used to capture update information from specified information materials or industry news.

[0052] Step S2: extract all first text paragraphs of the presentation, perform structural processing and vectorization processing on each first text paragraph, and obtain a first paragraph vector.

[0053] In practical applications, the titles, paragraphs, charts and notes in the presentation are identified, and then the paragraph content is extracted, and each paragraph in the paragraph content is identified as a first text paragraph, and then the first text paragraph is structured, and the key information of the first text paragraph is extracted, the semantic roles are marked, and the data relationship is established to obtain structured text data, and then the structured text data corresponding to the first text paragraph is vectorized. In this application, the local pre-trained Sentence-BERT model is used for reasoning to obtain a vectorized representation of the structured text data, that is, the first paragraph vector. The Sentence-BERT model generates a fixed-length text paragraph embedding vector, which makes the semantic similarity calculation between subsequent text paragraphs more efficient.

[0054] Furthermore, all the first text paragraphs of the presentation are extracted, and each first text paragraph is subjected to structured processing and vectorization processing to obtain a first paragraph vector, including:

[0055] Extracting all first text paragraphs of each page in order according to the page number of the presentation document to obtain a first paragraph set of each page;

[0056] After the first paragraph set of each page is structured and vectorized, the first vector set of each page is obtained.

[0057] In practical applications, by extracting all the first text paragraphs of each page of the presentation in sequence, the first paragraph set of all pages of the presentation can be obtained, and then all the first paragraph sets are structured and vectorized in order according to the page number to obtain the first vector set of all pages, so as to facilitate the subsequent semantic similarity calculation of the first vector set of each page and the paragraph vector corresponding to the update information, and obtain the similarity matrix corresponding to each page, that is, the presentation is processed page by page, and the content of the presentation can be decomposed into more detailed units. Each page usually revolves around a core theme, which is convenient for accurate content analysis, semantic extraction and structured processing. Page-by-page processing can also avoid processing a large amount of content at one time, reducing memory usage and computing resource consumption. For large presentations, page-by-page processing can significantly improve processing efficiency.

[0058] Step S3: extract all second text paragraphs of the captured update information, perform structural processing and vectorization processing on each second text paragraph, and obtain a second paragraph vector.

[0059] In actual application, the second text paragraph is extracted from the update information in the same way as in the presentation, and the structural processing and vectorization processing of the second text paragraph are both the same as the first text paragraph. Specifically, the second text paragraph is firstly structurally processed to obtain the structural data corresponding to the second text paragraph, and then the structural data corresponding to the second text paragraph is vectorized to obtain the second paragraph vector.

[0060] Step S4: Calculate the semantic similarity between all first paragraph vectors and all second paragraph vectors to obtain a similarity matrix.

[0061] In practical applications, by calculating the semantic similarity between the first paragraph vector and the second paragraph vector, it is possible to provide a quantitative basis for the association between the presentation and the updated information, thereby supporting the construction of an intelligent recommendation system and a knowledge graph, and providing an update basis for updating the presentation in this application. All second paragraph vectors form a second vector set. When the presentation is processed page by page, the first vector set of each page is obtained, and the semantic similarity between all first paragraph vectors in the first vector set of each page and all second paragraph vectors in the second vector set is calculated, thereby obtaining a similarity matrix for each page, which is convenient for subsequent page-by-page processing of the presentation according to the similarity matrix of each page.

[0062] Further, the calculating the semantic similarity between all first paragraph vectors and all second paragraph vectors includes:

[0063] The semantic similarity between all first paragraph vectors and all second paragraph vectors is calculated according to the similarity calculation formula, and the similarity calculation formula is:

[0064] E ij =(V i *V j ) / (||V i ||*||V j ||)

[0065] Among them, the V i represents the first paragraph vector of the ith paragraph, V j represents the jth second paragraph vector, E ij Represents the semantic similarity between the i-th first paragraph vector and the j-th second paragraph vector.

[0066] In practical applications, i=1,2,...,n, j=1,2,...,m, n represents the number of first paragraph vectors in the first vector set, and m represents the number of second paragraph vectors in the second vector set. In this application, the semantic similarity between the first paragraph vector and the second paragraph vector is obtained by calculating the cosine similarity between the first paragraph vector and the second paragraph vector. The cosine similarity focuses on the directionality between the vectors and reduces the influence of the vector length on the similarity calculation. The vector generated by Sentence-BERT can retain the semantic information of the text, so that the cosine similarity can more accurately measure the semantic similarity between the first paragraph vector and the second paragraph vector.

[0067] Step S5, constructing a diffusion matrix according to the similarity matrix, simulating the propagation of the update information between the first paragraph vectors through the diffusion matrix to obtain updated first paragraph vectors, and updating the presentation according to all updated first paragraph vectors.

[0068] In practical applications, the similarity matrix reflects the similarity between paragraphs, and the diffusion matrix simulates the propagation process of information or features between paragraphs on this basis. By continuously updating the representation of paragraphs, it integrates the information of other similar paragraphs, thereby realizing the updating and optimization of paragraphs. It is not limited by the format and content of paragraphs and can be applied to text content of various types and fields. Based on the similarity matrix and the diffusion process, the reasons and process of paragraph updating can be clearly explained, which increases the credibility of the results. It can automatically update according to the similarity between paragraphs without manual intervention, which greatly improves the efficiency of updating.

[0069] Furthermore, constructing a diffusion matrix according to the similarity matrix includes:

[0070] The propagation ratio of all second paragraph vectors to all first paragraph vectors is calculated according to the propagation ratio calculation formula, and the propagation ratio calculation formula is:

[0071]

[0072] Among them, the E ij represents the semantic similarity between the i-th first paragraph vector and the j-th second paragraph vector, D ij Indicates the propagation ratio of the i-th first paragraph vector to the j-th second paragraph vector;

[0073] The propagation ratios of all second paragraph vectors on all first paragraph vectors constitute a diffusion matrix.

[0074] In practical applications, each row in the diffusion matrix represents the propagation ratio of information from one paragraph vector to other paragraph vectors, the first paragraph vector is updated according to the propagation ratio, the presentation is updated according to the updated first paragraph vector, the updated content of the updated presentation includes content modification, content completion and format optimization, and the updated content is directly embedded in the modification point of the presentation in the form of color annotation to generate an update report. Specifically, the updated first paragraph vector is compared with the first paragraph vector before the update, the modification point is screened out, and according to the similarity matrix, the second paragraph vector with the highest similarity to the modification point is screened out from the second vector set, and the second text paragraph corresponding to the second paragraph vector is embedded in the corresponding modification point in the form of color annotation.

[0075] For example, a page of the presentation contains:

[0076] Optimization algorithms for deep learning include gradient descent, Adam optimizer, etc. With the improvement of computing power, the training of deep neural networks has become more and more efficient.

[0077] The latest news is:

[0078] Recent studies have shown that the AdaBelief optimizer converges faster than the Adam optimizer, especially when dealing with sparse data.

[0079] Final output:

[0080] Optimization algorithms for deep learning include gradient descent, Adam optimizer, etc. Recent studies have shown that the AdaBelief optimizer has a faster convergence speed than the Adam optimizer, especially when dealing with sparse data. With the improvement of computing power, the training of deep neural networks has become more and more efficient.

[0081] Furthermore, the step of simulating the propagation of the update information between the first paragraph vectors through the diffusion matrix to obtain the updated first paragraph vector includes:

[0082] During the propagation process, the first paragraph vector is updated according to the diffusion matrix. After multiple rounds of propagation, the change amplitude between the first paragraph vector after each round of propagation and the first paragraph vector of the previous round is calculated. When the change amplitude of the first paragraph vector is lower than the preset threshold, the propagation is stopped and the first paragraph vector obtained after the last round of propagation is used as the updated first paragraph vector.

[0083] In practical applications, multi-round propagation allows information to interact multiple times between different paragraphs or nodes, thereby integrating knowledge more comprehensively. This step-by-step propagation method ensures that the information of each paragraph or node is fully considered and updated, avoiding information omissions that may result from a single propagation. Multi-round propagation can more accurately identify and transmit important information by gradually optimizing the propagation path and intensity of information, and can effectively improve the accuracy and reliability of information propagation. When the change amplitude of the first paragraph vector is lower than a preset threshold, the propagation is stopped. The preset threshold is usually set to a smaller value (such as 1e-4, which means 0.0001).

[0084] Furthermore, updating the first paragraph vector according to the diffusion matrix during the propagation process includes:

[0085] During the propagation process, the first paragraph vector is updated according to the paragraph update formula, which is:

[0086]

[0087] Wherein, D represents the diffusion matrix, represents the set of first paragraph vectors of round k, Represents the set of first paragraph vectors of round k+1.

[0088] In practical applications, simulating the propagation of information between paragraph vectors actually involves multiplying the current first paragraph vector with the diffusion matrix D in each round of propagation to update the first paragraph vector. The diffusion matrix D is fixed, built based on the initial similarity matrix, and remains unchanged throughout the propagation process. In this way, information propagates between paragraphs, ultimately making the paragraph vectors more accurate, comprehensive, and coherent after multiple rounds of propagation.

[0089] Furthermore, the calculation of the change amplitude between the first paragraph vector after each round of propagation and the first paragraph vector of the previous round includes:

[0090] The change amplitude between the first paragraph vector after each round of propagation and the first paragraph vector of the previous round is calculated according to the change amplitude calculation formula, and the change amplitude calculation formula is:

[0091]

[0092] Wherein, A represents the change amplitude between the first paragraph vector after each round of propagation and the first paragraph vector of the previous round.

[0093] In practical applications, the modulus between the first paragraph vector after propagation and the first paragraph vector in the previous round reflects the overall change amplitude, rather than just the local change, which is convenient for measuring the intensity and effect of information propagation. By providing a global change indicator, it can help determine whether the information propagation has reached a stable state. When the change amplitude is lower than the preset threshold, it can be considered that the propagation process has converged, thereby stopping further propagation.

[0094] The automatic presentation updating method of the present invention obtains a similarity matrix by calculating the semantic similarity between the presentation and the update information, and obtains an update report through the similarity matrix and multiple rounds of information propagation processing, thereby achieving real-time updating of the presentation, ensuring that the content keeps up with the latest research trends, optimizing the presentation content, and improving the presentation quality.

[0095] like Figure 2 As shown, the embodiment of the present invention further provides a presentation automatic updating system, comprising:

[0096] The data acquisition module 10 is used to respond to the update request of the presentation;

[0097] A first processing module 20 is used to extract all first text paragraphs of the presentation, and obtain a first paragraph vector after performing structural processing and vectorization processing on each first text paragraph;

[0098] A second processing module 30 is used to extract all second text paragraphs of the captured update information, and obtain a second paragraph vector after performing structural processing and vectorization processing on each second text paragraph;

[0099] A similarity calculation module 40 is used to calculate the semantic similarity between all first paragraph vectors and all second paragraph vectors to obtain a similarity matrix;

[0100] The propagation update module 50 is used to construct a diffusion matrix according to the similarity matrix, simulate the propagation of the update information between the first paragraph vectors through the diffusion matrix, obtain the updated first paragraph vectors, and update the presentation according to all the updated first paragraph vectors.

[0101] As an optional implementation, the similarity calculation module includes the following units not shown in the figure:

[0102] A similarity calculation unit is used to calculate the semantic similarity between all first paragraph vectors and all second paragraph vectors according to a similarity calculation formula, wherein the similarity calculation formula is:

[0103] Eij =(V i *V j ) / (||V i ||*||V j ||)

[0104] Among them, the V i represents the first paragraph vector of the ith paragraph, V j represents the jth second paragraph vector, E ij Represents the semantic similarity between the i-th first paragraph vector and the j-th second paragraph vector.

[0105] As an optional implementation, the propagation update module includes the following units not shown in the figure:

[0106] The matrix construction unit is used to calculate the propagation ratio of all second paragraph vectors on all first paragraph vectors according to the propagation ratio calculation formula, and the propagation ratio calculation formula is:

[0107]

[0108] Among them, the E ij represents the semantic similarity between the i-th first paragraph vector and the j-th second paragraph vector, D ij Indicates the propagation ratio of the i-th first paragraph vector to the j-th second paragraph vector;

[0109] The propagation ratios of all second paragraph vectors on all first paragraph vectors constitute a diffusion matrix.

[0110] As an optional implementation, the propagation update module includes the following units not shown in the figure:

[0111] The multi-round propagation unit is used to update the first paragraph vector according to the diffusion matrix during the propagation process. After multiple rounds of propagation, the change amplitude between the first paragraph vector after each round of propagation and the first paragraph vector of the previous round is calculated until the change amplitude of the first paragraph vector is lower than a preset threshold. The propagation is stopped and the first paragraph vector obtained after the last round of propagation is used as the updated first paragraph vector.

[0112] As an optional implementation, the multi-round propagation unit includes the following units not shown in the figure:

[0113] The paragraph updating unit is used to update the first paragraph vector according to the paragraph updating formula during the propagation process. The paragraph updating formula is:

[0114]

[0115] Wherein, D represents the diffusion matrix, represents the set of first paragraph vectors of round k, Represents the set of first paragraph vectors of round k+1.

[0116] As an optional implementation, the multi-round propagation unit includes the following units not shown in the figure:

[0117] The amplitude calculation unit is used to calculate the change amplitude between the first paragraph vector after each round of propagation and the first paragraph vector of the previous round according to the change amplitude calculation formula, and the change amplitude calculation formula is:

[0118]

[0119] Wherein, A represents the change amplitude between the first paragraph vector after each round of propagation and the first paragraph vector of the previous round.

[0120] As an optional implementation, all first text paragraphs of the presentation are extracted, and each first text paragraph is subjected to structured processing and vectorization processing to obtain a first paragraph vector, including the following units not shown in the figure:

[0121] Extracting all first text paragraphs of each page in order according to the page number of the presentation document to obtain a first paragraph set of each page;

[0122] After the first paragraph set of each page is structured and vectorized, the first vector set of each page is obtained.

[0123] Each module of the above-mentioned automatic presentation updating system can be implemented in whole or in part by software, hardware and their combination. Each module and unit can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module above.

[0124] like Figure 3 As shown, an embodiment of the present invention discloses a computer device, including a memory and a processor, wherein the memory stores a computer program;

[0125] The computer device may be a server, and its internal structure diagram may be as follows: Figure 3As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the automatic presentation update method described in the above embodiments is implemented.

[0126] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0127] An embodiment of the present invention further discloses a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the automatic presentation updating method described in the above embodiments.

[0128] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0129] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. A method for automatically updating a presentation, characterized in that: include: respond to presentation update requests; Extracting all first text paragraphs of the presentation, and performing structure processing and vectorization processing on each first text paragraph to obtain a first paragraph vector; Extract all second text paragraphs of the captured update information, perform structural processing and vectorization processing on each second text paragraph, and obtain a second paragraph vector; Calculate the semantic similarity between all first paragraph vectors and all second paragraph vectors to obtain a similarity matrix; A diffusion matrix is ​​constructed according to the similarity matrix, and the propagation of the update information between the first paragraph vectors is simulated by the diffusion matrix to obtain the updated first paragraph vectors, and the presentation is updated according to all the updated first paragraph vectors.

2. The method for automatically updating a presentation as claimed in claim 1, characterized in that: The calculating the semantic similarity between all first paragraph vectors and all second paragraph vectors includes: The semantic similarity between all first paragraph vectors and all second paragraph vectors is calculated according to the similarity calculation formula, and the similarity calculation formula is: E ij =(V i *V j ) / (||V i ||*||V j ||) Among them, the V i represents the first paragraph vector of the ith paragraph, V j represents the jth second paragraph vector, E ij Represents the semantic similarity between the i-th first paragraph vector and the j-th second paragraph vector.

3. The method for automatically updating a presentation as claimed in claim 1, characterized in that: The step of constructing a diffusion matrix according to the similarity matrix comprises: The propagation ratio of all second paragraph vectors to all first paragraph vectors is calculated according to the propagation ratio calculation formula, and the propagation ratio calculation formula is: Among them, the E ij represents the semantic similarity between the i-th first paragraph vector and the j-th second paragraph vector, D ij Indicates the propagation ratio of the i-th first paragraph vector to the j-th second paragraph vector; The propagation ratios of all second paragraph vectors on all first paragraph vectors constitute a diffusion matrix.

4. The method for automatically updating a presentation as claimed in claim 1, characterized in that: The step of simulating the propagation of the update information between the first paragraph vectors through the diffusion matrix to obtain the updated first paragraph vector includes: During the propagation process, the first paragraph vector is updated according to the diffusion matrix. After multiple rounds of propagation, the change amplitude between the first paragraph vector after each round of propagation and the first paragraph vector of the previous round is calculated. When the change amplitude of the first paragraph vector is lower than the preset threshold, the propagation is stopped and the first paragraph vector obtained after the last round of propagation is used as the updated first paragraph vector.

5. The method for automatically updating a presentation as claimed in claim 4, characterized in that: The updating of the first paragraph vector according to the diffusion matrix during the propagation process includes: During the propagation process, the first paragraph vector is updated according to the paragraph update formula, which is: Wherein, D represents the diffusion matrix, represents the set of first paragraph vectors of round k, Represents the set of first paragraph vectors of round k+1.

6. The method for automatically updating a presentation as claimed in claim 5, characterized in that: The calculation of the change amplitude between the first paragraph vector after each round of propagation and the first paragraph vector of the previous round includes: The change amplitude between the first paragraph vector after each round of propagation and the first paragraph vector of the previous round is calculated according to the change amplitude calculation formula, and the change amplitude calculation formula is: Wherein, A represents the change amplitude between the first paragraph vector after each round of propagation and the first paragraph vector of the previous round.

7. The method for automatically updating a presentation as claimed in any one of claims 1 to 6, characterized in that: The extracting of all first text paragraphs of the presentation, and performing structural processing and vectorization processing on each first text paragraph to obtain a first paragraph vector includes: Extracting all first text paragraphs of each page in order according to the page number of the presentation document to obtain a first paragraph set of each page; After the first paragraph set of each page is structured and vectorized, the first vector set of each page is obtained.

8. The presentation automatic updating system is characterized by: include: A data acquisition module for responding to presentation update requests; A first processing module is used to extract all first text paragraphs of the presentation document, and obtain a first paragraph vector after performing structural processing and vectorization processing on each first text paragraph; A second processing module is used to extract all second text paragraphs of the captured update information, and obtain a second paragraph vector after performing structural processing and vectorization processing on each second text paragraph; A similarity calculation module is used to calculate the semantic similarity between all first paragraph vectors and all second paragraph vectors to obtain a similarity matrix; A propagation update module is used to construct a diffusion matrix according to the similarity matrix, simulate the propagation of update information between first paragraph vectors through the diffusion matrix, obtain updated first paragraph vectors, and update the presentation according to all updated first paragraph vectors.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images