Method and System for Analyzing and Predicting the Theme Trends of Scientific and Technical Literature

Abstract

The present application provides a method and system for analyzing and predicting the theme trends of scientific and technological literature. The method first collects and preprocesses the text data of scientific and technological literature; then uses a pre-trained semantic analysis model to obtain document semantic vectors; then performs topic clustering based on the document semantic vectors, extracts multiple topics and their representations; subsequently performs hierarchical clustering on the topics to form a hierarchical structure; then divides the text data according to time windows, analyzes the theme change characteristics to construct an evolutionary time series; finally predicts the change trend of the theme intensity. The present invention can accurately understand the deep semantics of the literature, effectively identify the key areas of concern in the literature, and predict the future evolution trend of the literature, providing forward-looking guidance for scientific and technological decision-making.

Description

Technical Field

[0001] The present application relates to the technical field of text mining and document analysis, and in particular to a method and system for analyzing and predicting the subject trend of scientific and technological documents. Background Art

[0002] In recent years, scientific and technological literature research has ushered in new development opportunities, but at the same time it faces the challenges of explosive growth in scientific and technological literature information and the iteration of research methods.

[0003] Traditional scientific and technological literature analysis mainly relies on manual reading, summarization and qualitative analysis methods, such as content analysis and comparative research. Although these methods can provide a deep understanding of literature texts, they are inefficient when faced with large-scale literature documents, and it is difficult to objectively quantify the evolution of literature. In recent years, text mining methods based on topic models such as LDA (latent Dirichlet allocation) have been introduced into the field of literature analysis, which can automatically identify topics and cluster them from a large number of literature texts.

[0004] The most relevant technology currently is the literature topic analysis method based on text mining. This method uses a specific algorithm to preprocess, extract features and model topics of literature texts, thereby revealing the distribution and evolution of literature topics. Its technical principle is to use computer linguistics and statistical methods to transform unstructured literature texts into structured data that can be quantified and analyzed, and then mine the semantic information and topic patterns contained in the text.

[0005] However, existing technologies have obvious limitations. First, the content of documents is heterogeneous and fragmented, and traditional topic models are difficult to accurately understand the deep semantics of document texts; second, existing methods do not clearly define the priority of cutting-edge scientific and technological development, making it difficult to accurately identify the key areas of focus of documents; in addition, there is a lack of effective prediction models for the future evolution trend of documents, and it is impossible to provide forward-looking guidance for scientific and technological decision-making. These problems seriously restrict the ability of scientific and technological literature research to support government scientific and technological decision-making. Summary of the invention

[0006] In view of this, the present application provides a method and system for analyzing and predicting document topic trends, which solves the problems in the prior art that traditional topic models are difficult to accurately understand the deep semantics of document texts, difficult to accurately identify key areas of document focus, and lack an effective model for predicting future document evolution trends.

[0007] The present application embodiment provides a method for analyzing and predicting the trend of scientific and technological literature topics, including:

[0008] Collecting scientific and technological literature text data, and preprocessing the scientific and technological literature text data to obtain target text data;

[0009] Encode the target text data using a pre-trained semantic analysis model to obtain a document semantic vector;

[0010] Perform topic clustering on the target text data based on the document semantic vector, extract multiple topics and the topic representation of each topic;

[0011] Perform hierarchical clustering on the topics based on the topic representation to form a topic hierarchical structure;

[0012] Divide the target text data into multiple time windows, analyze the change characteristics of the topics in each time window, and construct a topic evolution time series based on the change characteristics, where the change characteristics include occurrence frequency and intensity change;

[0013] Predict the intensity change trend of the topic according to the topic evolution time series.

[0014] The encoding of the target text data using a pre-trained semantic analysis model to obtain a document semantic vector includes:

[0015] Perform segmentation processing on the target text data to obtain text segments of a specified length;

[0016] Use the semantic analysis model to obtain the semantic representation of the text segment;

[0017] Integrate the semantic representations of the text segments into a document semantic vector, and the document semantic vector is used to indicate the semantic information and context relationship of the target text data.

[0018] The performing of topic clustering on the target text data based on the document semantic vector, extracting multiple topics and the topic representation of each topic includes:

[0019] Perform dimensionality reduction processing on the document semantic vector using a preset dimensionality reduction model to obtain a low-dimensional semantic vector;

[0020] Based on the low-dimensional semantic vector, use a preset clustering model to perform density clustering on the target text data to form multiple topics;

[0021] Calculate the word feature values of the words in each topic, and extract keywords based on the word feature values, where the word feature values include word frequency and inverse document frequency;

[0022] Optimize the keywords using a preset maximum similarity matching algorithm to obtain the topic representation of the topic.

[0023] The performing of hierarchical clustering on the topics based on the topic representation to form a topic hierarchical structure includes:

[0024] Calculate the semantic similarity based on the topic representation, and construct a similarity matrix between the topics according to the topic representation and the semantic similarity;

[0025] Use a preset hierarchical clustering model to perform hierarchical clustering on the topics to obtain a hierarchical system represented as a tree structure, where the hierarchical system includes multiple first-level topics and multiple second-level topics corresponding to the first-level topics;

[0026] Optimize and adjust the hierarchical system to form a hierarchical structure of topics.

[0027] The dividing the target text data into multiple time windows, analyzing the change characteristics of the topics in each time window, and constructing a topic evolution time series according to the change characteristics includes:

[0028] Divide the target text data in terms of time dimension according to the publication time of the target text data to obtain multiple consecutive time windows;

[0029] Use a preset topic mining model to perform topic mining on the target text data within the time window;

[0030] According to the topic mining results, calculate the topic characteristics of each topic in different time windows, where the topic characteristics include the occurrence frequency and intensity;

[0031] Use a preset dynamic topic model to analyze the topic characteristics to obtain the change characteristics of the topics, where the change characteristics are used to indicate the semantic change of the topics over time;

[0032] Generate the topic evolution time series according to the change characteristics.

[0033] The preprocessing the scientific and technological literature text data to obtain the target text data includes:

[0034] Use a preset large language model to evaluate the scientific and technological literature text data to obtain a complexity score, where the complexity score is used to indicate the professionalism, intersection and structural complexity of the scientific and technological literature text data;

[0035] Classify the scientific and technological literature text data according to the complexity score to obtain a first type of text and a second type of text, where the first type of text is used to indicate that the complexity score is lower than a preset score threshold, and the second type of text is used to indicate that the complexity score is higher than the score threshold;

[0036] Perform lightweight analysis on the first type of text and perform in-depth analysis on the second type of text to obtain a preliminary processing result;

[0037] Based on the preliminary processing results, obtain the target text data.

[0038] Evaluating the scientific and technological literature text data using a preset large language model to obtain a complexity score, including:

[0039] Collect training texts with complexity annotations, and fine-tune and train a preset initial large language model to obtain a large language model;

[0040] Use the large language model to calculate the analysis features of the scientific and technological literature text data, where the analysis features include professional vocabulary density, domain coverage, and logical hierarchy depth;

[0041] Calculate the text complexity score based on the analysis features, and generate an evaluation basis description based on the text complexity score;

[0042] Based on the evaluation basis description, obtain the complexity score of the scientific and technological literature text data.

[0043] The subject clustering of the target text data based on the document semantic vector and the extraction of multiple subjects and the subject representation of each subject further include:

[0044] Based on the document semantic vector, establish a scoring index system including literature level classification, publication time, and citation frequency;

[0045] Based on the document semantic vector and the scoring index system, construct a cost-sensitive decision tree, which is used to indicate increasing the weight assigned to samples whose importance reaches a preset importance threshold;

[0046] Extract classification rules from the cost-sensitive decision tree, where the classification rules include feature thresholds and classification paths;

[0047] Optimize the initial center point distribution of the subject clustering according to the classification rules, and perform subject clustering on the target text data according to the optimization results.

[0048] After predicting the intensity change trend of the subject according to the subject evolution time series, it further includes:

[0049] Based on the subject intensity change trend, construct a knowledge graph including literature entities, influence paths, and effect quantification indicators;

[0050] Use the knowledge graph to establish a multi-level analysis framework;

[0051] Establish a retrieval and inference system according to the multi-level analysis framework, and the retrieval and inference system includes an inference chain from literature to influence;

[0052] Adjust the effect quantification index, and perform multi-scenario prediction by combining the adjusted effect quantification index and the retrieval inference system to obtain the development trend under different conditions;

[0053] Among them, the inference chain is established through the following steps, including:

[0054] Based on the multi-level analysis framework, decompose the impact analysis task into multiple subtasks with logical dependencies;

[0055] Use the large language model to process the subtasks to obtain a progressive inference chain;

[0056] Retrieve the associated data related to each node of the progressive inference chain in the knowledge graph;

[0057] Combine the associated data and the inference process indicated by the large language model to verify and correct the inference results and generate an inference chain.

[0058] An embodiment of the present application also provides a device for analyzing and predicting the theme trend of scientific and technological literature, including:

[0059] A data preprocessing module for collecting scientific and technological literature text data and preprocessing the scientific and technological literature text data to obtain target text data;

[0060] A semantic encoding module for encoding the target text data using a pre-trained semantic analysis model to obtain a document semantic vector;

[0061] A theme clustering module for performing theme clustering on the target text data according to the document semantic vector, and extracting multiple themes and the theme representation of each theme;

[0062] A hierarchical analysis module for hierarchically clustering the themes according to the theme representation to form a theme hierarchical structure;

[0063] A time evolution analysis module for dividing the target text data into multiple time windows, analyzing the change characteristics of the themes in each time window, and constructing a theme evolution time series according to the change characteristics, where the change characteristics include the occurrence frequency and intensity change;

[0064] A trend prediction module for predicting the intensity change trend of the theme according to the theme evolution time series.

[0065] An embodiment of the present application also provides a computer device, the computer device includes:

[0066] At least one processor; and,

[0067] A memory communicatively connected to the at least one processor; wherein,

[0068] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method for analyzing and predicting the topic trend of the above-mentioned scientific and technological literature.

[0069] An embodiment of the present application also provides a computer-readable storage medium, which stores computer instructions for causing a computer to execute the method for analyzing and predicting the topic trend of the above-mentioned scientific and technological literature.

[0070] An embodiment of the present application also provides a computer program product, including computer instructions, which implement the steps of the method for analyzing and predicting the topic trend of the above-mentioned scientific and technological literature when executed by a processor.

[0071] The present application has the following technical effects:

[0072] Innovatively combines the BERT semantic model with the topic model to construct a BERTopic scientific and technological literature analysis framework, which can capture the deep semantic relationships of literature texts more accurately than traditional topic models such as LDA; designs a multi-level topic classification system, organizes topics through hierarchical clustering algorithms, and realizes an all-round analysis from macroscopic literature orientation to microscopic literature measures; proposes a method for analyzing the dynamic evolution of literature topics, and realizes a quantitative analysis of the evolution law of literature topics through time window division and dynamic topic modeling; develops a literature trend prediction model based on the topic evolution pattern, combines time series analysis and deep learning methods, and provides a forward-looking reference for future literature orientation. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the accompanying drawings required for use in the embodiments will be briefly introduced below. The accompanying drawings herein are incorporated into the specification and form a part of this specification. These drawings show embodiments consistent with the present disclosure and are used together with the specification to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only show some embodiments of the present disclosure and should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0074] Figure 1 It is a schematic flowchart of the method for analyzing and predicting the topic trend of scientific and technological literature provided by the embodiment of the present application;

[0075] Figure 2 It is a schematic flowchart of the implementation of the text representation module based on BERT semantic embedding provided by the embodiment of the present application;

[0076] Figure 3 Schematic diagram of the implementation process of the technology literature theme mining module based on BERTopic provided by the embodiment of the present application;

[0077] Figure 4 Schematic diagram of the implementation process of the literature theme hierarchical analysis module provided by the embodiment of the present application;

[0078] Figure 5 Schematic diagram of the implementation process of the literature theme time evolution analysis module provided by the embodiment of the present application. Detailed implementation manners

[0079] To make the objectives, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Apparently, the described embodiments are only some of the embodiments of the present disclosure, rather than all the embodiments. The components of the embodiments of the present disclosure described and illustrated herein generally may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the accompanying drawings is not intended to limit the scope of the claimed present disclosure, but is merely representative of selected embodiments of the present disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of the present disclosure without creative efforts shall fall within the protection scope of the present disclosure.

[0080] It should be noted that: like reference numerals and letters denote like items in the following drawings, and thus, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0081] The term "and / or" in this document merely describes an association relationship and indicates that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" in this document means any one of a plurality or any combination of at least two of a plurality. For example, including at least one of A, B, and C may represent including any one or more elements selected from the set composed of A, B, and C.

[0082] As Figure 1 shown, the embodiment of the present application provides a method for analyzing and predicting the theme trend of technology literature, including:

[0083] S1: Collect technology literature text data, preprocess the technology literature text data to obtain target text data;

[0084] The system first collects scientific and technological literature text data from various channels such as national and local government websites and the official websites of science and technology departments through web crawler technology. The collected data includes core information such as literature titles, publishing institutions, release times, and full text of the literature, ensuring the authority and comprehensiveness of the data sources. After the collection is completed, the system constructs a structured literature text database to provide basic data support for subsequent analysis. Next, the system conducts a comprehensive cleaning process on the collected literature text, including removing special characters, punctuation marks, and stop words in the text, unifying the text format, and performing Chinese word segmentation using professional word segmentation tools. At the same time, the system also extracts metadata information of the literature text, such as key attributes like release time, department, and region, which will play an important role in subsequent time series analysis and regional comparison. Finally, the preprocessed text data is standardized to ensure data quality and consistency, laying a solid foundation for subsequent semantic analysis. The quality of the preprocessing link directly affects the accuracy of subsequent analysis. Therefore, the system adopts strict data quality control measures in this link to ensure the high quality of the input data.

[0085] S1 specifically includes:

[0086] S1.1: Use a preset large language model to evaluate the scientific and technological literature text data to obtain a complexity score, which is used to indicate the professionalism, cross-disciplinarity, and structural complexity of the scientific and technological literature text data;

[0087] As the basis of the intelligent data filtering mechanism, it aims to comprehensively quantify the complexity of the literature text. The system designs a multi-dimensional complexity evaluation system, focusing on three core dimensions: professionalism, cross-disciplinarity, and structural complexity. Professionalism evaluates the depth of the use of professional terms and scientific concepts in the literature. Literature with high professionalism usually contains a large number of domain-specific terms and esoteric theoretical content; cross-disciplinarity evaluates the breadth of the literature involving multiple disciplines or technical fields. Literature with high cross-disciplinarity often integrates the knowledge and methods of multiple disciplines; structural complexity evaluates the complexity of the organizational structure, logical relationship, and expression method of the literature. Literature with high structural complexity may contain multi-level nested clauses, complex logical dependencies, or non-linear content organization. The large language model can accurately capture these complexity features through in-depth semantic understanding of the full text of the literature and generate a comprehensive complexity score. This evaluation method based on deep learning can understand the inherent complexity of the text more accurately than traditional keyword- or rule-based methods, providing a more reliable decision-making basis for subsequent processing.

[0088] S1.1.1: Collect training texts with complexity annotations and fine-tune the preset initial large language model to obtain a large language model;

[0089] The construction of the training dataset is a crucial step in this process. The system collects a large number of scientific and technological literature samples and invites domain experts to annotate the complexity of these samples. The annotation process considers multiple dimensions, such as the density of technical terms, the depth of concepts, the complexity of logical structures, and the degree of interdisciplinary in the literature. These annotated literature samples are used to fine-tune pre-trained large language models, such as BERT, GPT, etc. The fine-tuning process uses supervised learning methods to optimize the model parameters by minimizing the difference between the predicted complexity scores and the expert annotation scores. At the same time, to enhance the generalization ability of the model, the training data covers scientific and technological literature from different periods, different fields, and different types, ensuring that the model can adapt to the complexity assessment requirements of various literature texts. After sufficient training and validation, the system obtains a high-performance large language model dedicated to the complexity assessment of scientific and technological literature, providing a powerful tool for subsequent complexity scoring.

[0090] In the fine-tuning training process of the large language model, the following technical solutions are specifically adopted:

[0091] Training data construction: Select 10,000 literature with different complexities from the public scientific and technological literature database, and have 5 domain experts annotate the complexity according to a 1-10 scale to form a training set with a Kappa coefficient of 0.85 for annotation consistency.

[0092] Model architecture: Based on a pre-trained language model with a 12-layer Transformer structure, including 12 attention heads, a hidden layer dimension of 768, and a total number of parameters of about 110 million. To adapt to the characteristics of scientific and technological literature, 3,000 technical terms are added to the vocabulary.

[0093] Training parameter settings: Use the Adam optimizer, set the learning rate to 3e-5, use a linear learning rate warm-up and decay strategy, the batch size is 16, and train for 4 epochs. The loss function uses a combination of mean squared error (MSE) and cross-entropy to optimize both classification accuracy and scoring precision simultaneously.

[0094] Validation method: Adopt 5-fold cross-validation, use mean absolute error (MAE) and accuracy as evaluation metrics, and achieve a MAE of 0.72 and a complexity classification accuracy of 85% on the validation set.

[0095] S1.1.2: Use the large language model to calculate the analysis features of the scientific and technological literature text data, and the analysis features include the density of professional vocabulary, the scope of field coverage, and the depth of logical hierarchy;

[0096] These features are the basis for complexity scoring, including key metrics such as the density of specialized vocabulary, the scope of domain coverage, and the depth of logical hierarchy. The density of specialized vocabulary is calculated by identifying the proportion of specialized terms, scientific and technological concepts, and academic words in the text, reflecting the professional depth of the literature. The system utilizes the powerful semantic understanding ability of large language models to accurately identify specialized terms in various fields and can effectively grasp emerging scientific and technological concepts. The domain coverage measures the breadth of disciplines or technical fields covered by the literature. The system determines the interdisciplinary characteristics of the literature by analyzing the frequency and distribution of concepts in different fields in the text. For highly interdisciplinary literature, the system will give a higher complexity assessment. The depth of logical hierarchy is an important indicator for evaluating the structural complexity of the literature. The system analyzes features such as the hierarchical structure, clause relationships, and logical dependencies in the literature to quantify the organizational complexity of the literature. In addition, the system also analyzes auxiliary features such as syntactic complexity, semantic density, and reasoning depth of the literature to comprehensively capture the complex characteristics of the literature. These analyzed features together constitute a multi-dimensional feature space, providing a rich information basis for accurately evaluating the complexity of the literature.

[0097] S1.1.3: Calculate the text complexity score based on the analyzed features, and generate an evaluation basis description based on the text complexity score;

[0098] The calculation process uses a weighted comprehensive scoring method, assigns weights according to the importance of different features, and obtains the final complexity score. The setting of weights is based on the experience of domain experts and the statistical results of a large number of literature analyses, which can reflect the contribution degree of different features to complexity. To improve the interpretability of the scoring, the system also generates a detailed evaluation basis description, including the scoring situation of each dimension, key influencing factors, and typical feature examples. For example, for a literature rated as highly complex, the system may give the following description: "This literature contains a high density of artificial intelligence specialized terms (35% of the vocabulary are specialized terms), and at the same time involves cross-disciplinary content in three fields: computer science, statistics, and cognitive science. The literature structure shows a multi-layer nested relationship, and there are complex logical dependencies between clauses." Such a detailed evaluation basis helps users understand the source and meaning of the complexity score, enhancing the credibility and practicality of the evaluation results.

[0099] S1.1.4: Obtain the complexity score of the scientific and technological literature text data based on the evaluation basis description.

[0100] Taking into account the above analysis results, according to the preset scoring criteria, the complexity of the literature is quantified into specific scores, usually using a score range of 1 - 10 or a classification method of "low - medium - high". The complexity score not only reflects the overall complexity of the literature but also includes the refined evaluation results of each dimension, providing precise guidance for subsequent classification processing. The system will classify the literature into two categories: simple literature and complex literature according to the scoring results. Simple literature usually has a lower complexity score, with straightforward content and clear structure, suitable for lightweight processing; while complex literature has a higher complexity score and may contain profound professional content, complex logical structures or cross - field integrated knowledge, requiring more in - depth analysis. This complexity - based classification provides a scientific basis for the optimal allocation of system resources, enabling the system to concentrate more computing resources and analysis capabilities on those complex literatures that truly require in - depth processing, while quickly processing relatively simple literatures, improving the overall processing efficiency and analysis quality.

[0101] Through the above implementation, the system has completed the complexity assessment of the text data of scientific and technological literature, laying a foundation for subsequent strategic classification processing. This complexity assessment method based on large - language models has higher accuracy and adaptability compared with traditional rule - based or simple - feature - based methods, and can effectively process various types and fields of scientific and technological literature. At the same time, by generating detailed explanations of the evaluation basis, the system enhances the interpretability and credibility of the complexity assessment, enabling users to understand and verify the evaluation results. This high - quality complexity assessment provides a reliable guarantee for subsequent optimal resource allocation and selection of processing strategies, effectively improving the efficiency and quality of the entire literature analysis system.

[0102] S1.2: Classify the text data of the scientific and technological literature according to the complexity score to obtain a first - type text and a second - type text, where the first - type text is used to indicate that the complexity score is lower than a preset scoring threshold, and the second - type text is used to indicate that the complexity score is higher than the scoring threshold;

[0103] The system sets a preset scoring threshold (which can be dynamically adjusted according to the system's processing capacity and actual application requirements). Documents with a complexity score lower than the threshold are classified as the first type of text. This type of document usually has clear semantics, a clear structure, and moderate professionalism, and is suitable for lightweight processing. Documents with a complexity score higher than the threshold are classified as the second type of text. This type of document may contain esoteric professional content, complex structural organizations, or cross-disciplinary knowledge integration, and requires more in-depth analysis. In actual implementation, considering the multi-dimensional characteristics of the complexity score, the system may adopt a multi-threshold classification method, that is, set thresholds according to the complexity of different dimensions. Only when the document is lower than the corresponding threshold in all key dimensions will it be classified as the first type of text. This detailed classification strategy ensures the effective identification of complex documents and avoids misjudgments that may be caused by simple classification. At the same time, the system records the complexity details and classification basis of each document, providing a reference for subsequent processing and facilitating the continuous optimization of the classification strategy.

[0104] S1.3: Perform lightweight analysis on the first type of text and in-depth analysis on the second type of text to obtain preliminary processing results;

[0105] It is the core implementation link of the intelligent data filtering mechanism. Through a differential processing strategy, it realizes the optimal allocation of computing resources and the improvement of processing efficiency. For the first type of text (low complexity), the system adopts lightweight processing methods, such as basic text cleaning, simple semantic analysis, and conventional feature extraction. These methods have a small computational burden and fast processing speed, and are suitable for batch processing of relatively simple document texts. Specifically, the system may adopt a simplified language model, a shallow neural network, or an efficient statistical analysis method to quickly extract the core content and topic features of the text. For the second type of text (high complexity), the system starts the in-depth analysis mode and applies more powerful analysis tools and algorithms, such as a large language model with full parameters, in-depth semantic parsing, and complex logical structure analysis. The in-depth analysis mode invests more computing resources and processing time, and can more accurately understand the connotation and structure of complex documents, and capture subtle semantic features and logical relationships. The system may also apply specialized analysis strategies for different types of complex documents (such as interdisciplinary documents, highly professional documents, complex structure documents) to further improve the pertinence and efficiency of processing. Through this differential processing, the system significantly improves the overall processing efficiency while ensuring the analysis quality, and realizes the reasonable allocation of computing resources.

[0106] S1.4: Obtain the target text data based on the preliminary processing results.

[0107] Complete the preprocessing process of scientific and technological literature text data. Integrate and standardize the results of lightweight analysis and in-depth analysis to ensure that subsequent analysis can receive input data with a unified format and consistent quality. First, the system conducts a quality check on the processing results of the two types of texts, evaluating the integrity of key information extraction, the accuracy of semantic understanding, and the rationality of structural analysis to ensure that the processing results meet the predetermined quality standards. If it is found that the processing results of some documents do not meet the requirements, the system will mark them as needing to be reprocessed, possibly adjusting the processing strategy or parameters, or converting the texts originally classified as the first type into the second type for more in-depth analysis. Second, the system standardizes the processing results that meet the quality standards, including operations such as unified format, feature regularization, and metadata supplementation, to ensure the consistency of the data form. Finally, the system organizes the standardized data into a target text dataset, which contains multi-faceted information such as text content, structural information, semantic features, and complexity attributes, providing high-quality input for subsequent semantic encoding and topic clustering. Through this series of processes, the system not only completes the basic preprocessing of literature text data but also improves the overall processing efficiency through strategic diversion and differential processing, while ensuring the quality consistency of the processing results.

[0108] The intelligent data filtering mechanism based on LLM of the present invention has successfully achieved the efficient preprocessing of scientific and technological literature text data. The core advantages of this mechanism are as follows: First, through the accurate assessment of the literature complexity by the large language model, it provides a scientific decision-making basis for subsequent processing; Second, by classifying the literature into different complexity categories, it realizes the strategic allocation of processing resources; Third, through the differential processing strategies for different categories of literature, it significantly improves the processing efficiency while ensuring the analysis quality; Fourth, through strict quality control and standardization processing, it ensures the consistency and reliability of the preprocessing results. This innovative preprocessing method enables the system to more effectively handle large-scale and heterogeneous scientific and technological literature text data, laying a solid foundation for subsequent in-depth analysis.

[0109] S2: Use the pre-trained semantic analysis model to encode the target text data to obtain the document semantic vector;

[0110] The system uses a pre-trained Chinese BERT model as the semantic encoder. Through pre-training on a vast amount of Chinese corpora, this model already has strong semantic understanding capabilities. Considering the professional characteristics of scientific and technological literature, the system performs additional fine-tuning on the BERT model to enable it to better understand the professional terms and expressions in scientific and technological literature. For long literature texts, the system adopts a segmented processing strategy, dividing the text into segments of appropriate lengths, obtaining semantic representations separately and then integrating them, thus cleverly solving the input length limitation problem of the BERT model when processing long texts. In this way, the system can generate vector representations that express rich semantic information for each literature document. These vectors can capture the deep semantics and context relationships of the literature text, providing high-quality feature representations for subsequent topic clustering. Compared with traditional methods such as the bag-of-words model or Word2Vec, the BERT semantic vectors can more accurately capture the meanings of words in specific contexts, understand the semantic essence of the literature content, and thus effectively solve the semantic understanding challenges brought about by the heterogeneity and specialization of the literature content.

[0111] S3: Perform topic clustering on the target text data according to the document semantic vectors, and extract multiple topics and the topic representations of each topic;

[0112] The system performs topic clustering on the target text data based on the document semantic vectors, and extracts multiple topics and their representations. This step is the core part of the present invention and adopts a topic mining method based on BERTopic. First, the system uses the UMAP (Uniform Manifold Approximation and Projection) algorithm to perform dimensionality reduction on the high-dimensional semantic vectors, mapping the BERT vectors of hundreds or even thousands of dimensions to a low-dimensional space (usually 2-10 dimensions), while preserving the semantic relationships between documents. The UMAP algorithm is based on Riemannian geometry and algebraic topology theories, and can maximize the preservation of the local and global structures of the data while reducing the dimensions. Compared with traditional dimensionality reduction algorithms such as t-SNE, it has higher computational efficiency and better preserves the semantic distance relationship between data points. In the vector space after dimensionality reduction, the system applies the HDBSCAN (Hierarchical Density-Based Spatial Clustering of Applications with Noise) clustering algorithm to perform density clustering on the documents. HDBSCAN is a hierarchical extended version of the DBSCAN algorithm, which can identify clusters of any shape and effectively handle noisy data, and is particularly suitable for the irregular characteristics of the topic distribution in literature texts. Through clustering, the system groups the semantically similar documents to form a preliminary topic structure. Subsequently, the system calculates the eigenvalue of the words in each cluster, mainly using the innovative c-TF-IDF (class-based Term Frequency-Inverse Document Frequency) method, regarding each cluster as a "virtual document" and calculating the importance of the words in this cluster relative to other clusters. Finally, the system uses the Maximal Marginal Relevance (MMR) algorithm to optimize the keyword set, reducing the redundancy between keywords while ensuring a high correlation between the keywords and the topics, so as to form a topic representation that can accurately represent the topic content and cover different aspects of the topic.

[0113] The core parameter settings and optimization strategies of the BERTopic model are as follows:

[0114] UMAP dimensionality reduction parameters: n_neighbors is set to 15 to control the local neighborhood size; min_dist is set to 0.1 to balance the local and global structures; n_components is set to 5 to determine the vector dimension after dimensionality reduction. The parameters are optimized through grid search on different literature sets to maximize the balance between clustering quality and computational efficiency.

[0115] HDBSCAN clustering parameters: min_cluster_size is set to 10 to ensure that each topic contains sufficient samples; min_samples is set to 5 to control the clustering stability; cluster_selection_epsilon is set to 0.5 to optimize the recognition of small clusters. The system evaluates the clustering quality by combining the silhouette coefficient and the DB index to achieve dynamic adjustment of the parameters.

[0116] c-TF-IDF optimization: The word frequency calculation adopts smoothing processing to reduce the bias of long texts; the IDF calculation uses logarithmic scaling to balance the weights of common words and rare words; the top 20 highest-weighted words are used for keyword extraction, and the λ parameter of the MMR algorithm is set to 0.6 to balance relevance and diversity.

[0117] S4: Hierarchically cluster the topics based on the topic representation to form a hierarchical topic structure;

[0118] The system constructs a similarity matrix between topics based on the semantic similarity of topic keywords and the distribution of documents among different topics. The system calculates the cosine similarity or Jaccard similarity coefficient between sets of topic keywords, and at the same time considers the proportion of documents shared between different topics, and forms a comprehensive topic similarity matrix through weighted combination. Subsequently, the system applies a hierarchical clustering algorithm (such as Ward's method) to hierarchically cluster the topics. Ward's method selects the two clusters with the smallest increase in the within-group sum of squares after merging at each step of the clustering process, tending to generate clusters of similar sizes, which is particularly suitable for organizing the topics of scientific and technological literature. The clustering result can be represented as a tree structure (i.e., a dendrogram), and by setting an appropriate threshold, the system cuts out a multi-level topic structure from the dendrogram. Based on the hierarchical clustering result, the system defines a multi-level classification system for the topics of scientific and technological literature, usually including first-level topics (such as macro directions like "scientific and technological work", "scientific and technological enterprises", "scientific and technological finance", etc.), second-level topics (such as specific fields like "project management", "enterprise incubator", etc.) and third-level topics (such as specific literature measures). Finally, the system optimizes and adjusts the hierarchical topic system in combination with the knowledge of domain experts to ensure the scientificity and practicality of topic classification, which may include merging topics with similar semantics, splitting topics with overly broad content, or readjusting the hierarchical attribution of certain topics. In this way, the system finally constructs a multi-level topic structure that can grasp both the macro direction and the in-depth specific measures.

[0119] S5: Divide the target text data into multiple time windows, analyze the change characteristics of the topics in each time window, and construct a topic evolution time series based on the change characteristics, where the change characteristics include the occurrence frequency and intensity change;

[0120] The system divides the target text data into multiple time windows according to the publication time, analyzes the changing characteristics of the themes in each time window, and constructs a time series of theme evolution. First, the system divides the text data into a series of consecutive time windows according to the literature publication date. The division of the time windows can be flexibly set according to research needs, such as annually, quarterly, or in units of five-year plan cycles. Within each time window, the system independently applies the BERTopic model for theme mining, performing a series of processing steps such as document embedding, dimensionality reduction, clustering, and theme representation. This independent modeling method based on time windows can capture the unique literature theme structure of each period without being interfered by data from other periods. Subsequently, the system calculates the occurrence frequency and intensity of each theme in different time windows. The theme frequency is measured by calculating the proportion of the number of documents belonging to the theme in the total number of documents in the window, while the theme intensity is quantified by a weighted combination of factors such as the number of documents of the theme, the document length, and the level of the publishing institution. These frequency and intensity data constitute the time series of theme evolution, reflecting the ebb and flow of the attention of different literature themes. In addition, the system also introduces the Dynamic Topic Model (DTM) technology to analyze the semantic changes of theme content over time. DTM assumes that there is a certain continuity of the same theme in adjacent periods, but allows the word distribution of the theme to gradually change. In this way, the system can track the evolution trend of keywords within the theme, identify new words and decaying words, and reveal the subtle changes in the literature language and concerns. Finally, the system constructs a complete theme evolution map by calculating the similarity matrix of themes between adjacent time windows and tracking the processes of theme continuation, differentiation, and integration.

[0121] S6: Predict the trend of the change in the intensity of the theme according to the time series of theme evolution.

[0122] The system first uses the topic intensity time series data obtained from the time evolution analysis and applies traditional time series analysis methods for preliminary trend prediction. Commonly used methods include the autoregressive integrated moving average model (ARIMA) and the exponential smoothing method. The ARIMA model constructs a mathematical model to predict future values by analyzing the autocorrelation, difference stationarity, and moving average characteristics of the time series; while the exponential smoothing method performs weighted averaging on historical data, with the largest weight for the most recent data and the weights exponentially decaying over time. These methods are particularly suitable for capturing the linear trends and seasonal fluctuations of topic intensity. However, considering the non-linear characteristics of the evolution of scientific and technological literature, the system also combines deep learning methods to establish a more complex prediction model. As a special type of recurrent neural network, the long short-term memory network (LSTM) can learn long-term dependencies and is particularly suitable for processing time series data; while the Transformer model uses the attention mechanism to process sequence data in parallel and capture the correlations between different time points. These deep learning models learn the complex patterns of topic evolution through the training of a large amount of historical data and provide more accurate non-linear predictions. In addition to predicting the intensity changes of existing topics, the system also identifies emerging topics and fading topics through the analysis of the topic evolution map and predicts the future focus of attention in the literature. Finally, the system integrates external factors (such as the dynamics of scientific and technological development, changes in the international literature environment, major social events, etc.) to correct and adjust the prediction results, improving the accuracy and reliability of the prediction. Through multi-dimensional analysis and correction, the system can ultimately provide a comprehensive and accurate prediction of the trends in scientific and technological literature, providing forward-looking reference information for decision-makers.

[0123] In topic trend prediction, the system adopts the following deep learning model architectures and training strategies:

[0124] LSTM network structure: It contains 2 layers of bidirectional LSTM, with 128 hidden units in each layer, a dropout rate of 0.3, and Batch Normalization is connected after the input layer to accelerate training. The time window length is set to 8, and the intensity changes of the topic in the next 4 time windows are predicted.

[0125] Transformer structure: It uses 4 layers of Transformer encoders, 8 attention heads, the dimension of the feed-forward network is 512, and the positional encoding uses sine and cosine functions, with a global receptive field to capture long-term dependencies.

[0126] Model training and evaluation: The training data is divided into a training set and a test set at a ratio of 80%:20%. An early stopping strategy is adopted to avoid overfitting. The evaluation metrics include the root mean square error (RMSE) and the mean absolute percentage error (MAPE). The system implements model integration, combines the prediction results of the ARIMA and deep learning models, and generates the final prediction through weighted averaging, significantly improving the prediction accuracy.

[0127] S7: Based on the changing trend of the theme intensity, construct a knowledge graph including literature entities, influence paths, and effect quantification indicators;

[0128] The system constructs a domain knowledge graph for the impact analysis of scientific and technological literature as the knowledge basis for subsequent reasoning and analysis. This knowledge graph consists of three main components: the literature entity network, the scientific and technological innovation ecological network, and the literature-influence causal chain network. The literature entity network includes entities such as literature documents, publishing institutions, implementation objects, key stakeholders, etc., and relationships such as "publication", "supervision", "implementation", etc. between them, reflecting the basic information and management structure of the literature. The scientific and technological innovation ecological network includes entities such as scientific research institutions, enterprise entities, innovation projects, scientific and technological fields, etc., and relationships such as collaboration, competition, and resource flow between them, reflecting the scientific and technological innovation environment in which the literature plays a role. The literature-influence causal chain network records the causal relationships between historical literature and the observed impacts, including information such as the paths of direct and indirect impacts, time delays, and impact intensities, providing an empirical basis for literature influence reasoning. The system constructs this knowledge graph by integrating multi-source data, and the data sources include literature texts, scientific and technological project databases, scientific research output statistics, enterprise innovation survey data, etc. To ensure the accuracy and integrity of the knowledge graph, the system adopts a semi-automated knowledge extraction method and combines expert review for verification. During the construction of the knowledge graph, special attention is paid to capturing the association patterns between literature themes and specific impacts, and these association patterns will become an important basis for subsequent reasoning and analysis.

[0129] S8: Use the knowledge graph to establish a multi-level analysis framework;

[0130] The framework includes four main levels: the direct impact level, the system response level, the innovation achievement level, and the social and economic level. The direct impact level analyzes the direct effects of the literature on specific objects, such as financial support, tax incentives, regulatory requirements, etc., and the direct changes in the behavior of the objects caused by these effects. This level focuses on the immediate effects after the implementation of the literature and can usually be directly observed through government fund allocation data, tax exemption statistics, etc. The system response level analyzes the responses of various elements within the innovation system to the literature and their interactions, including resource reallocation, organizational structure adjustment, behavior pattern changes, etc. This level focuses on the internal dynamic adjustment process of the innovation system and reflects the conduction mechanism guided by the literature. The innovation achievement level analyzes the ultimate impact of the literature on scientific and technological innovation achievements, including quantitative indicators such as R & D investment, patent output, technological breakthroughs, product innovation, etc., and reflects the actual promotion effect of the literature on innovation activities. The social and economic level analyzes the impact of the literature on a broader social and economic level, including aspects such as industrial structure, employment changes, economic growth, sustainable development, etc., and reflects the long-term comprehensive benefits of the literature. In this multi-level framework, the system defines clear evaluation indicators and measurement criteria for each level, forming a structured literature impact evaluation system. Through this hierarchical analysis framework, the system can evaluate the impact path and effect of the literature from different dimensions and depths, effectively addressing the challenges of the complexity and multi-dimensionality of literature impact evaluation.

[0131] S9: Establish a retrieval and reasoning system according to the multi-level analysis framework, and the retrieval and reasoning system includes an inference chain from the literature to the impact;

[0132] The system implements an innovative Reason-while-Retrieve (RwR) framework, which organically combines the retrieval and reasoning processes, making the reasoning results based on both logical deduction and factual evidence. First, the system decomposes the complex literature impact analysis problem into a series of sub-problems, forming a problem tree, where there are logical dependencies among the sub-problems. For example, analyzing the impact of a certain innovation incentive literature can be decomposed into sub-problems such as R & D investment, talent attraction, and technological cooperation. Subsequently, the system constructs a progressive reasoning chain based on a large language model, with each reasoning step corresponding to a sub-problem. The large language model generates reasoning hypotheses or intermediate conclusions based on the current sub-problem and the existing information. This progressive reasoning supports the analysis of complex causal relationships and is suitable for the multi-path conduction of literature impact. In each reasoning step, the system retrieves the most relevant knowledge from the knowledge graph according to the current sub-problem and the reasoning state. The retrieval uses a hybrid strategy, combining semantic similarity search, relationship path query, and reasoning relevance scoring to ensure that the retrieved knowledge is both relevant and useful. The system integrates the retrieved knowledge with the reasoning process of the large language model to verify or adjust the reasoning hypothesis. If the retrieved evidence supports the reasoning hypothesis, the credibility of the hypothesis is enhanced; if there is a conflict, re-reasoning or hypothesis adjustment is triggered. Throughout the reasoning process, the system clearly traces and quantifies the sources of uncertainty in the reasoning chain, including knowledge gaps, evidence conflicts, reasoning jumps, etc., to provide a confidence assessment for the final conclusion. Through this interactive reasoning chain construction, the system can conduct evidence-based and traceable in-depth analysis of complex literature impacts, greatly improving the reliability and interpretability of the reasoning results.

[0133] The technical implementation details of the RwR framework are as follows:

[0134] Knowledge graph construction: Use the Neo4j graph database to store the literature impact knowledge network, which contains approximately 50,000 entity nodes and 200,000 relationship edges. Entity extraction adopts a method combining named entity recognition (NER) and distant supervision, and relationship extraction uses a BERT-based relationship classification model with an F1 score of 0.83.

[0135] Implementation of the progressive reasoning chain: Build a reasoning framework based on a large language model with 16 billion parameters, and design reasoning templates through few-shot prompting engineering to implement 9 basic reasoning modes, including conditional reasoning, comparative reasoning, and counterfactual reasoning, etc. The temperature parameter 0.3 is used in the reasoning process to maintain the certainty and coherence of the reasoning.

[0136] Retrieval-reasoning fusion mechanism: Design a bidirectional attention mechanism to enhance each other between the retrieval results and the reasoning process. The retrieval uses a hybrid retrieval strategy, combining BM25 and vector similarity, and emphasizes exact matching and semantic relevance. The reasoning fusion adopts a confidence-weighted method to automatically adjust the reasoning weights according to the evidence support degree.

[0137] Uncertainty quantification: Based on the Bayesian framework, calculate the confidence interval for each inference step, use Monte Carlo sampling to analyze the robustness of the prediction, and quantify the knowledge gap through information entropy to provide users with a transparent reliability assessment.

[0138] Among them, the inference chain is established through the following steps, including:

[0139] S9.1: Based on the multi-level analysis framework, decompose the impact analysis task into multiple subtasks with logical dependencies;

[0140] Task decomposition is the key first step in dealing with complex inference problems. The system adopts a structured task decomposition method to split the overall impact analysis problem into a series of subtasks with clear boundaries and dependencies. First, based on the previously constructed four-level impact analysis framework (direct impact layer, system response layer, innovation achievement layer, and socio-economic layer), the system determines the main dimensions of the impact analysis. Within each dimension, the system is further refined into specific subtasks. For example, analyzing the impact of innovation literature on a company's R & D investment can be decomposed into the following subtasks: what R & D resource support does the literature provide for the company, what is the company's response mechanism to this support, how do R & D resources translate into R & D investment growth, and what is the relationship between the investment growth and innovation output, etc. These subtasks form a directed acyclic graph (DAG), where each node in the graph represents a subtask, and the edges represent the dependencies between subtasks. Through this task decomposition, the system transforms the complex impact analysis problem into a series of manageable sub-problems, each with clear inputs, outputs, and evaluation criteria. Task decomposition not only reduces the complexity of a single inference step but also clarifies the logical path of the inference, providing a clear guiding framework for the subsequent inference process.

[0141] S9.2: Use the large language model to process the subtasks to obtain a progressive inference chain;

[0142] The system sequentially inputs the decomposed subtasks into a pre-trained large language model and uses its powerful reasoning ability to generate answers for each subtask. The processing process adopts a "context accumulation" strategy, that is, the processing of subsequent subtasks takes the results of previous subtasks as context input to ensure the coherence and consistency of the reasoning process. To improve the reasoning quality, the system adopts "reasoning prompt engineering" technology and designs a special prompt template for each type of subtask to guide the model to generate standardized and structured reasoning results. In addition, the system also implements a "multi-step thinking" mechanism, which requires the model to first analyze the problem, clarify the thinking, then gradually deduce, and finally summarize the conclusion. This explicit thinking process helps to reduce logical jumps and errors in reasoning. To handle the uncertainty in reasoning, the system adopts a "confidence annotation" method, which requires the model to annotate the confidence level for each reasoning step and clearly indicate the assumptions and limitations in the reasoning. Through these technologies, the system generates a progressive reasoning chain composed of multiple reasoning nodes, and each node contains the analysis process, reasoning result and confidence evaluation of the subtask. This reasoning chain represents the preliminary reasoning path from the literature to the impact, but it is only based on the general knowledge of the language model and still needs to be verified and enhanced through fact retrieval.

[0143] S9.3: Retrieve the associated data related to each node of the progressive reasoning chain in the knowledge graph;

[0144] To provide factual basis for the reasoning results of the language model, through the retrieval function of the knowledge graph, the reasoning is connected with the actual data. The system constructs multi-level retrieval queries for each node in the reasoning chain. First, the system extracts key entities and relationships from the reasoning node, such as literature name, implementation object, impact type, etc., as the basic retrieval conditions. Then, the system expands the retrieval scope according to the reasoning content and context, including similar literatures, related fields, similar impact cases, etc. In the retrieval process, the system adopts a hybrid retrieval strategy, combining exact matching and semantic similarity search to ensure the comprehensiveness and relevance of the retrieval results. For the retrieved results, the system conducts relevance scoring and deduplication processing, and preferentially retains the data that is most relevant to the current reasoning node and has the highest evidence value. The system's retrieval is not limited to the direct relationships in the knowledge graph, but also supports multi-hop queries, which can discover indirect but meaningful associated evidence. For example, if the reasoning involves the impact of a certain literature on an enterprise's R & D, the system will not only retrieve the direct literature-enterprise relationship, but also search for multi-hop paths such as literature-fund-enterprise or literature-talent-enterprise to capture complex impact mechanisms. Through this in-depth retrieval, the system collects relevant factual data for each reasoning node and provides an objective basis for reasoning verification.

[0145] S9.4: Combine the associated data and the reasoning process indicated by the large language model to verify and correct the reasoning results and generate a reasoning chain.

[0146] This is the core part of the RwR framework, which realizes the deep integration of reasoning and retrieval. First, the system matches the retrieved associated data with the corresponding reasoning nodes and analyzes the consistency between the data and the reasoning. For each reasoning node, the system calculates the "evidence support degree" to quantify the degree of support of the factual data for the reasoning conclusion. Based on the evaluation of the evidence support degree, the system classifies the reasoning results: for the reasoning fully supported by evidence, the system retains the original conclusion and adds specific factual basis to improve the credibility of the conclusion; for the reasoning partially supported by evidence, the system modifies or limits the conclusion to make it more compliant with the constraints of the factual data; for the reasoning with insufficient or contradictory evidence, the system marks it as "to be verified" and tries to resolve the contradiction by additional retrieval or adjusting the reasoning path. When dealing with evidence conflicts, the system adopts the "evidence weight" strategy, considering the authority, timeliness, and direct relevance of the data sources to resolve the conflicts between different pieces of evidence. After this verification and correction process, the system generates a complete reasoning chain that is both based on logical reasoning and supported by facts, with clear source annotations for each reasoning step: whether it is reasoning based on the language model, direct evidence from factual data, or a comprehensive judgment of both. This transparent source annotation makes the reasoning process traceable and verifiable, greatly enhancing the reliability and interpretability of the reasoning results.

[0147] The above constructs an innovative knowledge reasoning system that tightly combines reasoning and retrieval. Compared with traditional pure language model reasoning or simple information retrieval, this system has significant advantages: First, through task decomposition and progressive reasoning, the system effectively handles complex impact analysis problems, making the reasoning process clearer and more controllable; Second, the system combines the reasoning ability of large language models with the factual basis of knowledge graphs, retaining both the flexibility and generalization ability of the language model and avoiding its "hallucination" problem, improving the accuracy and reliability of reasoning; Third, the reasoning process of the system is transparent and interpretable, with clear reasoning paths and factual basis for each conclusion, facilitating user understanding and verification; Finally, the system supports interactive reasoning, capable of dynamically adjusting the reasoning path according to new information or questions, with strong adaptability and scalability. This retrieval reasoning system based on the RwR framework provides powerful intelligent support for the impact analysis of scientific and technological literature, can extract key information from a large amount of literature and data, construct a reliable causal reasoning chain, effectively answer complex questions of "why" and "how", and provide in-depth insights and basis for scientific and technological decision-making.

[0148] S10: Adjust the effect quantification index, and perform multi-scenario prediction by combining the adjusted effect quantification index and the retrieval reasoning system to obtain the development trends under different conditions;

[0149] Based on the inference results of the RwR framework, the system further conducts scenario simulations and sensitivity analyses of the literature impact. First, by adjusting the key parameters of the literature (such as the scale of funds, the proportion of tax incentives, the access threshold, etc.), the system simulates the differences in potential impacts of different literature design schemes. This parameter adjustment simulation helps decision-makers understand how subtle changes in literature design affect the final effect and provides quantitative references for literature optimization. Second, under different external environment assumptions (such as economic growth rate, international competition situation, technological development stage, etc.), the system evaluates the robustness and adaptability of the literature impact. By changing the external condition parameters, the system can identify the sensitivity of the literature effect to the environment and help design more flexible and adaptable literature schemes. In addition, the system also simulates the changing trends of the literature impact over time, including short-term effects, medium-term adjustments, and long-term impacts, revealing the time characteristics of the literature impact. This time dynamic simulation particularly focuses on the persistence and decay characteristics of the literature effect and helps design a reasonable literature implementation cycle and update mechanism. Finally, the system conducts factor sensitivity analysis to identify the key factors and conditions that are most sensitive to the literature impact and provides targeted suggestions for literature optimization. The system presents the simulation and analysis results in a visual manner, including impact path diagrams, sensitivity heatmaps, scenario comparison diagrams, etc., enabling decision-makers to intuitively understand the impact characteristics and optimization space of the literature scheme. Through this multi-scenario prediction analysis, the system provides rich decision support information for literature formulators and helps design more effective and targeted scientific and technological literature.

[0150] Among them, as Figure 2 shown, S2 specifically includes:

[0151] S2.1: Segment the target text data to obtain text segments of a specified length;

[0152] This addresses the limitation of pre-trained language models in processing long texts. Pre-trained models such as BERT usually have input length limitations (generally 512 tokens), while scientific and technological literature is often quite long and cannot be directly input into the model. To solve this problem, the system adopts an intelligent segmentation strategy to divide the long text into segments of appropriate length. The segmentation process takes into account the semantic integrity and preferentially cuts at natural paragraph boundaries or sentence boundaries to avoid splitting complete semantic units. For particularly long paragraphs, the system uses a sliding window technique and sets an appropriate overlapping area (usually 15 - 20% of the text length) to ensure the coherence of context information. For text parts containing special structures (such as tables, chart descriptions, formulas, etc.), the system adopts special processing rules to preserve their structural characteristics or convert them into a form understandable by the model. Through this intelligent segmentation processing, the system converts the original long text into a series of text segments with appropriate lengths and complete semantics, providing suitable input units for subsequent semantic encoding.

[0153] S2.2: Obtain the semantic representation of the text segment using the semantic analysis model;

[0154] Use pre-trained large language models (such as BERT, RoBERTa, etc.) as semantic encoders. These models have already possessed powerful semantic understanding capabilities through pre-training on a vast amount of text. To better adapt to the field of scientific and technological literature, the system also performs domain adaptation fine-tuning on the basic model, using a large amount of scientific and technological literature data to perform additional training on the model to enhance its understanding ability of professional terms and scientific and technological expressions. During the encoding process, the system inputs the text segment into the model to obtain a deep semantic representation. Specifically, the system extracts the hidden state vectors of the last few layers of the model, and these vectors contain rich semantic information and context relationships. For BERT-like models, the system usually uses the [CLS] token vector of the last layer as the semantic representation of the entire segment, or averages the vector representations of all tokens. These high-dimensional vectors (usually 768-dimensional or 1024-dimensional) capture the deep semantic features of the text, including multiple levels such as word meaning, syntactic relationship, and topic information, providing a high-quality semantic basis for subsequent document representation.

[0155] S2.3: Integrate the semantic representation of the text segment into a document semantic vector, and the document semantic vector is used to indicate the semantic information and context relationship of the target text data.

[0156] This step solves the problem of how to synthesize the local representations of multiple segments into the global representation of the entire document. For this purpose, the system designs a hierarchical semantic integration method. First, for each text segment, the system obtains its semantic vector representation, and these vectors capture the segment-level semantic information. Then, the system adopts a weighted integration mechanism to combine these segment vectors into a document-level overall representation. The integration process considers multiple factors: segment position (segments at the beginning and end of the document may contain more important overview information), segment content importance (evaluated by indicators such as keyword density), and semantic relevance between segments. The system implements an integration algorithm based on the attention mechanism to automatically learn the importance weights of different segments and give key segments higher influence. In addition, the system also retains the mapping relationship between the segment-level vector and the document-level vector, facilitating tracing the specific source of key information during subsequent analysis. The finally generated document semantic vector is a high-dimensional dense vector, comprehensively representing the semantic content and internal structural relationship of the document, providing an ideal input form for subsequent topic mining.

[0157] After completing the semantic representation, the system enters the topic clustering stage to identify the topic distribution in scientific and technological literature based on the semantic vectors of the documents. First, since the semantic vectors generated by BERT encoding usually have a high dimension (such as 768 dimensions), directly clustering in the high-dimensional space may face the problem of "curse of dimensionality", which affects the clustering effect.

[0158] Among them, as Figure 3 shown, S3 specifically includes:

[0159] S3.1: Use a preset dimensionality reduction model to perform dimensionality reduction processing on the document semantic vectors to obtain low-dimensional semantic vectors;

[0160] Use the UMAP (Uniform Manifold Approximation and Projection) algorithm as the main dimensionality reduction tool. The UMAP algorithm is based on Riemannian geometry and algebraic topology theory, and can retain the local and global structures of the data to the greatest extent while reducing the dimension. Compared with traditional dimensionality reduction methods (such as PCA, t-SNE), UMAP has the advantages of high computational efficiency and strong scalability, and is particularly suitable for processing large-scale literature data. In practical applications, the system usually reduces the high-dimensional vectors to a low-dimensional space of 5-15 dimensions, and this dimension range can balance information retention and computational efficiency. The selection of dimensionality reduction parameters takes into account the data scale and distribution characteristics, and the system adopts a dynamic parameter adjustment strategy to automatically optimize the parameter settings according to the actual data distribution to ensure that the dimensionality reduction results retain key information and are convenient for subsequent processing.

[0161] S3.2: Based on the low-dimensional semantic vectors, use a preset clustering model to perform density clustering on the target text data to form multiple topics;

[0162] Select HDBSCAN (Hierarchical Density-Based Spatial Clustering of Applications with Noise) as the main clustering algorithm. HDBSCAN is a hierarchical extension of the DBSCAN algorithm and has several key advantages: it can identify clusters of arbitrary shapes, has good robustness to noisy data, automatically determines the optimal number of clusters, and has strong ability to handle clusters with different densities. These characteristics make HDBSCAN particularly suitable for the needs of scientific literature topic clustering because the topic distribution of scientific literature is usually not uniform, with core topics and marginal topics and significant density differences. During the clustering process, the system optimizes the key parameters of HDBSCAN: the minimum cluster size parameter is dynamically adjusted according to the total amount of literature to ensure that the identified topics are sufficiently representative; the core distance parameter is adaptively set based on the local density distribution of the data to balance the clustering granularity and coverage. Through this optimized density clustering process, the system can naturally identify topic groups with semantic consistency from the literature data, and each group represents a relatively independent literature topic.

[0163] S3.3: Calculate the word feature values of the words in each topic, and extract keywords based on the word feature values, where the word feature values include word frequency and inverse document frequency;

[0164] To accurately represent the core content of each topic, the system innovatively applies the c-TF-IDF (class-based Term Frequency-Inverse Document Frequency) method. Different from traditional TF-IDF, c-TF-IDF regards each topic as a "virtual document" and calculates the importance of a word in this topic relative to other topics. Specifically, the TF (term frequency) part calculates the frequency of a word appearing in a specific topic, reflecting the contribution of the word to the topic; the IDF (inverse document frequency) part calculates the distribution breadth of the word in all topics, giving higher weights to words with strong topic specificity (appearing in only a few topics). Through c-TF-IDF calculation, the system generates a sorted list of all words in each topic, and words with high weights can usually accurately reflect the core content and unique features of the topic. The system also further combines the semantic representation information of the words, and by calculating the similarity between the word vector and the topic center vector, captures keywords with strong semantic relevance but low frequency, enhancing the semantic accuracy of the topic representation.

[0165] S3.4: Optimize the keywords using a preset maximum similarity matching algorithm to obtain the topic representation of the topic.

[0166] Optimize keywords using a preset Maximal Marginal Relevance (MMR) algorithm to obtain the topic representation of the topic. The MMR algorithm is a selection method that balances relevance and diversity. When selecting keywords, it considers both the relevance of the words to the topic and the diversity of the selected word set. Specifically, the system defines an objective function that combines relevance and diversity: MMR(w) = λ·sim(w,t) - (1-λ)·maxsim(w,S), where w is the candidate word, t is the topic center, S is the selected keyword set, sim represents the similarity function, and λ is the balance parameter (usually set to 0.5 - 0.7). The system iteratively selects keywords in descending order of MMR values until the predetermined number of keywords is reached (usually 10 - 20). This method ensures that the selected keyword set is not only highly relevant to the topic but also covers different aspects of the topic, avoiding the problems of content duplication or one-sided representation of the topic. Finally, each topic is represented by a set of optimized keywords, which together constitute the semantic feature representation of the topic and provide a basis for subsequent topic hierarchy analysis and evolution analysis.

[0167] Among them, S3 also includes:

[0168] S3.5: Based on the document semantic vector, establish a scoring index system including literature level classification, publication time, and citation frequency;

[0169] This index system comprehensively considers multiple importance dimensions of the literature: the level classification reflects the official attributes and authority of the literature, such as national level, provincial and ministerial level, local level, etc.; the publication time reflects the timeliness of the literature, and recently published literature may have higher reference value; the citation frequency reflects the influence and recognition of the literature, and highly cited literature usually represents important literature directions or research focuses. The system integrates these indicators into a unified importance score, assigns a weight value to each literature, and these weights will play an important role in the subsequent clustering process.

[0170] S3.6: Based on the document semantic vector and the scoring index system, construct a cost-sensitive decision tree, which is used to indicate increasing the assigned weight for samples whose importance reaches a preset importance threshold;

[0171] The system regards the mis-clustering of literature as a kind of "cost", and the mis-clustering cost of important literature is higher. Through the cost-sensitive decision tree, the system increases the assigned weight for samples whose importance reaches the preset importance threshold to ensure that these important literatures are processed more accurately in the clustering process. The construction process of the decision tree considers the semantic features and importance indicators of the literature, and learns decision rules that can effectively distinguish different types of literature by minimizing the weighted error rate.

[0172] S3.7: Extract classification rules from the cost-sensitive decision tree, where the classification rules include feature thresholds and classification paths;

[0173] Each path from the root node to the leaf node of the decision tree represents a classification rule, which contains a series of feature judgment conditions (feature thresholds) and the final classification result. The system extracts these rules to form a rule set, and each rule describes the feature pattern and the category of a certain type of literature. These rules are not only used for subsequent clustering optimization but also provide an interpretable basis for literature classification, enabling the system to clearly explain why a certain literature is classified into a specific theme. The rule extraction process also includes rule refinement and optimization, such as merging similar rules, removing redundant conditions, and adjusting the threshold range, to make the rule set more refined and comprehensive.

[0174] S3.8: Optimize the initial center point distribution of the topic clustering according to the classification rules, and perform topic clustering on the target text data based on the optimization result.

[0175] Traditional density clustering algorithms (such as HDBSCAN) may not fully consider the influence of important literature when dealing with literature of different importance. To solve this problem, the system innovatively applies the classification rules of the cost-sensitive decision tree to the clustering initialization process. Specifically, the system uses the classification rules to identify the set of important literature, and takes these literatures as the core to optimize the initial density estimation and core point selection of the clustering algorithm. This method ensures that important literature can become the "seed points" of clustering, guiding the formation of clustering boundaries and improving the recognition accuracy of the themes represented by important literature. After the initial optimization, the system executes an improved version of the HDBSCAN algorithm to organize all literatures into semantically consistent topic clusters while maintaining the clustering accuracy of important literature. Finally, the system obtains an optimized clustering result that considers both semantic similarity and literature importance.

[0176] The conversion process from text data to topic representation is realized. The innovation of this process lies in: combining the deep semantic understanding ability of BERT and the flexible grouping ability of density clustering to achieve accurate topic recognition of scientific and technological literature; introducing the c-TF-IDF and MMR algorithms to obtain relevant and diverse topic representations; innovatively applying the cost-sensitive learning idea to improve the clustering accuracy of important literature. These innovation points together constitute an efficient and accurate scientific and technological literature topic mining framework, laying a solid foundation for subsequent hierarchical analysis and evolutionary prediction.

[0177] Among them, as Figure 4 shown, S4 specifically includes:

[0178] S4.1: Calculate the semantic similarity based on the topic representation, and construct a similarity matrix between the topics according to the topic representation and the semantic similarity;

[0179] The system constructs a topic vector representation for each topic, which is based on two key pieces of information: one is the keyword set of the topic, and the other is the center point of the document semantic vectors belonging to the topic. For the keyword set, the system performs a weighted average of the word vectors of each keyword (the weight is the c-TF-IDF value of the word) to generate a keyword vector representation; for the document set, the system calculates the weighted average of all document semantic vectors under the topic (the weight is the importance score of the document) to generate a document vector representation. Then, the system fuses these two vector representations into a unified topic vector for subsequent similarity calculation. In the similarity calculation step, the system adopts a multi-angle similarity measurement method. In addition to the commonly used cosine similarity, the system also calculates the Jaccard similarity coefficient of the topic keyword set and the overlap degree of the topic document distribution. These three similarities are integrated into a comprehensive similarity score to more comprehensively reflect the association strength between topics. Finally, the system organizes the similarity values between all topic pairs into a similarity matrix, which is a symmetric matrix, and each element represents the semantic proximity degree between the topics corresponding to the row and column. This matrix provides a key input for subsequent hierarchical clustering and determines which topics should be grouped into higher-level categories.

[0180] S4.2: Use a preset hierarchical clustering model to perform hierarchical clustering on the topics to obtain a hierarchical system represented as a tree structure, where the hierarchical system includes multiple first-level topics and multiple second-level topics corresponding to the first-level topics;

[0181] The present invention selects the Ward hierarchical clustering method. This method considers minimizing the increase in within-group variance when merging clusters, tends to generate clusters of similar sizes, and is suitable for the organizational requirements of the themes in scientific and technological literature. The hierarchical clustering process is a bottom-up iterative merging process: initially, each theme is regarded as an independent cluster; then, in each iteration step, the system finds the two clusters with the highest similarity and merges them; this process continues until all themes are merged into one cluster or a preset stopping condition is reached. The clustering process can be visualized as a dendrogram (i.e., a hierarchical clustering tree), where the leaf nodes of the tree are the original themes, the internal nodes represent higher-level theme categories, and the root node contains all themes. The system obtains a multi-level theme classification system by "cutting" at appropriate positions in the dendrogram. The selection of the cutting position comprehensively considers factors such as the number of clusters, the internal consistency of the clusters, and the distinguishability between different clusters. In the present invention, the system usually constructs a two-level or three-level theme classification system, which includes multiple first-level themes (such as macro categories like "Technological Innovation", "Industrial Development", "Science and Technology Finance", etc.) and multiple second-level themes corresponding to the first-level themes (such as specific fields like "Basic Research", "Transformation of Scientific and Technological Achievements" under "Technological Innovation"). This hierarchical system provides a clear organizational structure for the themes in scientific and technological literature, helping to understand the subordinate relationships and correlation degrees between themes.

[0182] S4.3: Optimize and adjust the hierarchical system to form a theme hierarchical structure.

[0183] There may be some unreasonable aspects in the automatically generated hierarchical system, which need to be further optimized to improve its scientificity and practicality. The optimization process of the system includes multiple aspects: First, split or merge overly large or small clusters to maintain the balance of themes at each level; Second, based on the semantic relationships between themes, adjust the attribution relationships of some themes to ensure semantic consistency in classification; Third, utilize external domain knowledge bases (such as subject classification systems, technical field classification standards, etc.) to standardize the naming and organizational structure of themes, improving the professionalism and comprehensibility of classification. In practical applications, the system also supports an expert intervention mode, allowing domain experts to review and modify the automatically generated hierarchical structure based on their own knowledge, further enhancing the practical value of theme classification. Finally, the system forms a multi-level classification system for the themes in scientific and technological literature. This system not only retains the objectivity driven by data but also takes into account the guiding role of professional knowledge, providing an effective semantic framework for the organization and retrieval of scientific and technological literature.

[0184] After completing the construction of the theme hierarchical structure, the system enters the theme evolution analysis stage, focusing on the change trends of themes over time. This analysis is of great significance for grasping the dynamics of scientific and technological development.

[0185] Among them, such as Figure 5As shown in the figure, S5 specifically includes:

[0186] S5.1: Divide the target text data in terms of time dimension according to the release time of the target text data to obtain a plurality of consecutive time windows;

[0187] The division of time windows is the basis of time series analysis. The system designs a flexible time division strategy according to research requirements and data characteristics. Usually, the system uses natural time units (such as monthly, quarterly, annual) or literature cycles (such as five-year plan cycles) as the basis for dividing time windows. For cases with a large amount of data, smaller time units (such as monthly or quarterly) can be selected to capture more detailed changes; for cases with a small amount of data or when focusing on long-term trends, larger time units (such as annual or multi-year) can be selected. The system supports dynamic time window settings, allowing users to adjust the window size or sliding step according to specific needs. The setting of time windows should ensure both the statistical significance of the data volume within the window and the requirements of time resolution. In actual processing, the system first organizes all data in chronological order based on the release time attribute of the literature, and then divides the data into a series of consecutive time periods according to the preset window parameters. The literature within each time period constitutes a data set for a time window. This division of time windows provides a basic time framework for subsequent topic evolution analysis.

[0188] S5.2: Use a preset topic mining model to mine topics from the target text data within the time window;

[0189] To track the change of topics over time, the system needs to independently identify the topic structure in each time window. The present invention adopts two topic mining strategies: one is the independent modeling strategy, and the other is the incremental update strategy. In the independent modeling strategy, the system independently applies the BERTopic model to the data of each time window and executes a full set of topic mining processes (including document semantic encoding, dimensionality reduction, clustering, and topic representation extraction). This method can capture the topic patterns unique to each period without being affected by other periods, but may lead to the problem of inconsistent topic identification. In the incremental update strategy, the system processes the data of the new window in an incremental manner based on the topic model of the previous time window, only updating the topic distribution and representation while maintaining the continuity of topic identification. This method helps to maintain the consistency of topics and is convenient for cross-time comparison, but may miss emerging topics or ignore significant changes in topic content. To take into account the advantages of these two strategies, the system adopts a hybrid method: regularly execute independent modeling (such as annually or for each literature cycle), and at the same time adopt incremental update during the intermediate period, and set up a new topic discovery mechanism to timely identify emerging topics during incremental update. Through this hybrid strategy, the system can effectively capture the dynamic changes of the topic structure while maintaining the continuity of topics.

[0190] S5.3: According to the theme mining results, calculate the theme features of each theme in different time windows, where the theme features include occurrence frequency and intensity;

[0191] The theme features are the basic indicators for quantifying the temporal changes of themes. The theme frequency reflects the popularity of the theme and is usually measured by calculating the proportion of the number of documents belonging to the theme in the total number of documents in the window; the theme intensity reflects the importance or attention of the theme. The system calculates the theme intensity by synthesizing multiple factors, including: the number of theme documents, the average length of the documents, the average importance score of the documents (based on the previously constructed scoring index system), the concentration of theme keywords in the documents, etc. The calculation of the theme intensity takes into account the balance between the number of documents and the importance of the documents and can more accurately reflect the actual influence of the theme. The system calculates these feature values for each theme in each time window and organizes the results into time series data to form the time profile of the theme features. These time profiles are the data basis for subsequent evolution analysis and reflect the change patterns of themes over time.

[0192] S5.4: Analyze the theme features using a preset dynamic topic model to obtain the change features of the theme, where the change features are used to indicate the semantic changes of the theme over time;

[0193] In addition to the changes in theme frequency and intensity, the content structure of the theme also evolves over time. This semantic change reflects the subtle shift of the theme's focus. To capture this change, the system applies the Dynamic Topic Models (DTM) technology to analyze the temporal changes in the internal word distribution of the theme. The DTM model assumes that there is a certain continuity of the same theme in adjacent periods, but allows the word distribution of the theme to gradually change. The system compares the keyword distributions of each theme in each time window to identify newly added words, disappeared words, and significantly changed words. These lexical changes reflect the evolution trend of the theme content, such as the emergence of new technology concepts, the fading out of old concepts, and the change of focus, etc. The system also calculates the degree of semantic drift within the theme, that is, the distance between the semantic representations of the same theme at different time points, to quantify the speed and amplitude of the theme change. In addition, the system analyzes the mutual influence between themes, such as semantic penetration, theme differentiation and integration between themes, etc., to reveal the dynamic evolution law of the theme network. These change features together constitute a multi-dimensional description of theme evolution, reflecting not only the change of "how much" but also the change of "what".

[0194] S5.5: Generate the theme evolution time series based on the change features.

[0195] Integrate the various change features analyzed above into structured time - series data to provide input for trend prediction. The system organizes multiple types of topic evolution time - series: the topic popularity time - series, which records the frequency and intensity of each topic at each time point; the topic content change time - series, which records the changes in the distribution of topic keywords; and the topic relationship change time - series, which records the dynamics of the mutual influence and structural reorganization between topics. These time - series are stored in various forms, including numerical time - series (such as the numerical changes in topic intensity), vector - type time - series (such as the semantic representation of topics changing over time), and structural time - series (such as the evolution of topic network topology). The system also adds rich meta - information to the time - series data, such as time granularity, data source, processing method, etc., for subsequent interpretation and use. All time - series data are organized into a unified database, supporting multi - dimensional queries and analysis, providing high - quality training data for the final trend prediction.

[0196] The present invention realizes a comprehensive analysis of the topic structure and evolution law of scientific and technological literature. This analysis not only reveals the organizational structure of topics but also captures the change patterns of topics over time, providing an important basis for understanding the development trends of science and technology. Especially through the hierarchical organization of topics and the analysis of temporal changes, the system establishes a panoramic view from micro - topics to macro - domains, from static structures to dynamic evolution, which helps to grasp the overall trend and internal law of the development of science and technology from multiple perspectives and levels. This structured and dynamic analysis method breaks through the limitations of traditional literature analysis and provides more systematic and in - depth knowledge support for scientific and technological decision - making.

[0197] The embodiment of the present application also provides a device for analyzing and predicting the trends of scientific and technological literature topics, including:

[0198] A data pre - processing module, configured to collect scientific and technological literature text data, pre - process the scientific and technological literature text data to obtain target text data;

[0199] A semantic encoding module, configured to encode the target text data by using a pre - trained semantic analysis model to obtain a document semantic vector;

[0200] A topic clustering module, configured to perform topic clustering on the target text data according to the document semantic vector, and extract multiple topics and the topic representation of each topic;

[0201] A hierarchical analysis module, configured to perform hierarchical clustering on the topics according to the topic representation to form a hierarchical topic structure;

[0202] A time evolution analysis module for dividing the target text data into multiple time windows, analyzing the change characteristics of the theme in each time window, and constructing a theme evolution time series based on the change characteristics, where the change characteristics include occurrence frequency and intensity change;

[0203] A trend prediction module for predicting the intensity change trend of the theme according to the theme evolution time series.

[0204] An embodiment of the present application further provides a computer device, which includes:

[0205] At least one processor; and,

[0206] A memory communicatively connected to the at least one processor; wherein,

[0207] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method for analyzing and predicting the theme trend of scientific and technological literature as described above.

[0208] An embodiment of the present application further provides a computer-readable storage medium, which stores computer instructions for causing a computer to execute the method for analyzing and predicting the theme trend of scientific and technological literature as described above.

[0209] An embodiment of the present application further provides a computer program product, including computer instructions, which implement the steps of the method for analyzing and predicting the theme trend of scientific and technological literature as described above when executed by a processor.

[0210] The present application has the following technical effects:

[0211] Innovatively combines the BERT semantic model with the topic model to construct a BERTopic scientific and technological literature analysis framework, which can capture the deep semantic relationships of literature texts more accurately than traditional topic models such as LDA; designs a multi-level topic classification system, organizes topics through hierarchical clustering algorithms, and realizes an all-round analysis from macroscopic literature orientation to microscopic literature measures; proposes a method for dynamic evolution analysis of literature topics, and realizes a quantitative analysis of the evolution law of literature topics through time window division and dynamic topic modeling; develops a literature trend prediction model based on the theme evolution pattern, combines time series analysis and deep learning methods, and provides a forward-looking reference for future literature orientation.

[0212] An embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it executes the steps of the method for analyzing and predicting the topic trend of scientific and technological literature described in the above method embodiment. Among them, the storage medium may be a volatile or non-volatile computer-readable storage medium.

[0213] In addition, an embodiment of the present disclosure further provides a computer program product, on which a computer program is stored. When the computer program is run by a processor, it executes the steps of the method for analyzing and predicting the topic trend of scientific and technological literature provided in any one of the above embodiments of the present disclosure. For details, reference may be made to the above method embodiments, which will not be elaborated here.

[0214] Among them, the above computer program product may be specifically implemented in a manner of hardware, software, or a combination thereof. In an optional embodiment, the computer program product is specifically embodied as a computer storage medium, which may be a volatile or non-volatile computer-readable storage medium. In another optional embodiment, the computer program product is specifically embodied as a software product, such as a Software Development Kit (SDK), etc.

[0215] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described devices and apparatuses can refer to the corresponding processes in the foregoing method embodiments, which will not be elaborated here. In the several embodiments provided by the present disclosure, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For another example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces, and the indirect coupling or communication connection of the devices or units may be in an electrical, mechanical, or other form.

[0216] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0217] In addition, in each embodiment of the present disclosure, the functional units may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.

[0218] When the above-mentioned functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such an understanding, the technical solution of the present disclosure, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present disclosure. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs that can store program codes.

[0219] Finally, it should be noted that: the above-mentioned embodiments are only specific implementation manners of the present disclosure, used to illustrate the technical solutions of the present disclosure, rather than limiting them. The protection scope of the present disclosure is not limited thereto. Although the present disclosure has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: any person skilled in the art within the technical scope disclosed by the present disclosure can still modify the technical solutions recorded in the foregoing embodiments, or can easily think of changes, or perform equivalent replacements on some of the technical features; and these modifications, changes, or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should all be covered by the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A method for analyzing and predicting the theme trend of scientific and technological literature, characterized in that, Including: Collecting scientific and technological literature text data, preprocessing the scientific and technological literature text data to obtain target text data; Encoding the target text data by using a pre-trained semantic analysis model to obtain a document semantic vector; Performing topic clustering on the target text data according to the document semantic vector, and extracting multiple topics and topic representations of each topic; Performing hierarchical clustering on the topics according to the topic representations to form a topic hierarchical structure; Dividing the target text data into multiple time windows, analyzing the change characteristics of the topics in each time window, and constructing a topic evolution time series according to the change characteristics, wherein the change characteristics include occurrence frequency and intensity change; Predicting the intensity change trend of the topic according to the topic evolution time series; Wherein, the dividing the target text data into multiple time windows, analyzing the change characteristics of the topics in each time window, and constructing a topic evolution time series according to the change characteristics includes: Performing time dimension division on the target text data according to the publication time of the target text data to obtain a plurality of consecutive time windows; Using a preset topic mining model to perform topic mining on the target text data within the time window; Calculating topic characteristics of each topic in different time windows according to the topic mining result, wherein the topic characteristics include occurrence frequency and intensity; Analyzing the topic characteristics by using a preset dynamic topic model to obtain the change characteristics of the topic, and the change characteristics are used to indicate the semantic change of the topic over time; Generating the topic evolution time series according to the change characteristics.

2. The method according to claim 1, wherein The encoding the target text data by using a pre-trained semantic analysis model to obtain a document semantic vector includes: Performing segmentation processing on the target text data to obtain text segments of a specified length; Using the semantic analysis model to obtain semantic representations of the text segments; Integrating the semantic representations of the text segments into a document semantic vector, and the document semantic vector is used to indicate the semantic information and context relationship of the target text data.

3. The method according to claim 2, characterized in that The performing topic clustering on the target text data according to the document semantic vector, and extracting multiple topics and topic representations of each topic includes: Performing dimensionality reduction processing on the document semantic vector by using a preset dimensionality reduction model to obtain a low-dimensional semantic vector; Based on the low-dimensional semantic vector, performing density clustering on the target text data by using a preset clustering model to form multiple topics; Calculating word feature values of words in each topic, and extracting keywords according to the word feature values, wherein the word feature values include word frequency and inverse document frequency; Optimizing the keywords by using a preset maximum similarity matching algorithm to obtain the topic representation of the topic.

4. The method according to claim 3, wherein The performing hierarchical clustering on the topics according to the topic representations to form a topic hierarchical structure includes: Calculating semantic similarity based on the topic representations, and constructing a similarity matrix between the topics according to the topic representations and the semantic similarity; Hierarchical clustering is performed on the said subject using a preset hierarchical clustering model to obtain a hierarchical system represented as a tree structure, which includes multiple first-level subjects and multiple second-level subjects corresponding to the first-level subjects; The hierarchical system is optimized and adjusted to form a subject hierarchical structure.

5. The method according to claim 1, wherein The preprocessing of the scientific and technological literature text data to obtain the target text data includes: Using a preset large language model to evaluate the scientific and technological literature text data to obtain a complexity score, which is used to indicate the professionalism, cross-disciplinarity, and structural complexity of the scientific and technological literature text data; Classifying the scientific and technological literature text data according to the complexity score to obtain a first type of text and a second type of text, where the first type of text is used to indicate that the complexity score is lower than a preset score threshold, and the second type of text is used to indicate that the complexity score is higher than the score threshold; Performing lightweight analysis on the first type of text and in-depth analysis on the second type of text to obtain a preliminary processing result; According to the preliminary processing result, the target text data is obtained.

6. The method according to claim 5, wherein The use of a preset large language model to evaluate the scientific and technological literature text data to obtain a complexity score includes: Collecting training texts with complexity annotations and fine-tuning a preset initial large language model to obtain a large language model; Using the large language model to calculate the analysis features of the scientific and technological literature text data, where the analysis features include the density of professional vocabulary, the scope of field coverage, and the depth of logical hierarchy; Calculating a text complexity score according to the analysis features and generating an evaluation basis description according to the text complexity score; According to the evaluation basis description, the complexity score of the scientific and technological literature text data is obtained.

7. The method according to claim 6, wherein The subject clustering of the target text data according to the document semantic vector to extract multiple subjects and the subject representation of each subject further includes: Based on the document semantic vector, a scoring index system including literature level classification, publication time, and citation frequency is established; According to the document semantic vector and the scoring index system, a cost-sensitive decision tree is constructed, which is used to indicate increasing the weight assigned to samples whose importance reaches a preset importance threshold; Extracting classification rules from the cost-sensitive decision tree, where the classification rules include feature thresholds and classification paths; Optimizing the initial center point distribution of subject clustering according to the classification rules and performing subject clustering on the target text data according to the optimization result.

8. The method according to claim 7, wherein After predicting the intensity change trend of the subject according to the subject evolution time series, it further includes: Based on the subject intensity change trend, constructing a knowledge graph including literature entities, influence paths, and effect quantification indicators; Using the knowledge graph to establish a multi-level analysis framework; Establishing a retrieval and reasoning system according to the multi-level analysis framework, where the retrieval and reasoning system includes an inference chain from literature to influence; Adjusting the effect quantification indicators, and combining the adjusted effect quantification indicators and the retrieval and reasoning system to perform multi-scenario prediction to obtain development trends under different conditions; Among them, the inference chain is established through the following steps, including: Based on the multi-level analysis framework, the impact analysis task is decomposed into multiple subtasks with logical dependencies; The large language model is used to process the subtasks to obtain a progressive inference chain; Associated data related to each node of the progressive inference chain is retrieved in the knowledge graph; Combining the associated data and the inference process indicated by the large language model, the inference result is verified and corrected to generate an inference chain.

9. An apparatus for analyzing and predicting the theme trend of scientific and technological literature, characterized in that, Including: A data preprocessing module for collecting scientific and technological literature text data and preprocessing the scientific and technological literature text data to obtain target text data; A semantic encoding module for encoding the target text data using a pre-trained semantic analysis model to obtain a document semantic vector; A topic clustering module for performing topic clustering on the target text data according to the document semantic vector, and extracting multiple topics and the topic representation of each topic; A hierarchical analysis module for hierarchically clustering the topics according to the topic representation to form a topic hierarchical structure; A time evolution analysis module for dividing the target text data into multiple time windows, analyzing the change characteristics of the topics in each time window, and constructing a topic evolution time series according to the change characteristics, where the change characteristics include the occurrence frequency and intensity change, including: Dividing the target text data in the time dimension according to the publication time of the target text data to obtain a plurality of consecutive time windows; Using a preset topic mining model to mine the target text data within the time window; According to the topic mining result, calculating the topic characteristics of each topic in different time windows, where the topic characteristics include the occurrence frequency and intensity; Analyzing the topic characteristics using a preset dynamic topic model to obtain the change characteristics of the topic, and the change characteristics are used to indicate the semantic change of the topic over time; Generating the topic evolution time series according to the change characteristics; A trend prediction module for predicting the intensity change trend of the topic according to the topic evolution time series.

Images