115 results about "Text database" patented technology

The invention discloses a multilayer dynamic aggregation big language model driven letter text analysis method, which relates to the technical field of natural language processing, and comprises the following steps of: acquiring multi-format letter data and converting the multi-format letter data into a text sequence with a timestamp, performing semantic analysis and structure processing on the text sequence, generating a text block set, and storing the text block set into a text database; performing multi-task training and topic fusion on the text block set to generate a comprehensive semantic vector, constructing a dynamic bridging graph based on the comprehensive semantic vector, activating associated text blocks by the bridging graph through semantic and time sequence relevance, responding to user query, splicing the activated text block content into a context Prompt, and inputting the context Prompt into a large language model; obtaining a one-time generated answer; the method has the advantages that semantic information and time sequence information are associated through the dynamic bridging graph, accurate response of the large language model is achieved based on the context Prompt, and the method has the advantages that complex semantic association is efficiently captured, context understanding coherence is improved, and dynamic information aggregation is achieved.

The invention discloses a multi-modal agricultural question and answer method and system for generating RAG based on retrieval enhancement, and the method comprises the steps: collecting and constructing crop disease image data containing a farmland complex background and corresponding text description, and forming an agricultural image-text knowledge database; based on the agricultural image-text knowledge database, multi-modal features of an input image and a query text are extracted, image-text joint similarity retrieval is carried out, and knowledge image-text candidates are obtained; inputting the knowledge image-text candidates into an image-text rearrangement module for rearrangement; taking the reordered image-text knowledge as condition input, accessing a large language model, and generating diagnosis description and prevention and treatment suggestions for the current crop diseases; and outputting a multi-modal question and answer result according to the image and question input by the user. According to the method, the agricultural image-text database is constructed, and multi-modal retrieval, rearrangement and large language model generation technologies are combined, so that accurate and efficient crop disease multi-modal question answering is realized, and the reliability of diagnosis and prevention suggestions is improved.

The invention discloses a sewage treatment question and answer method and device based on a large model, a medium and a product, and relates to the field of language model construction.The method comprises the steps that existing data related to sewage treatment are obtained; preprocessing the existing data to obtain text data; segmenting the text data to obtain text blocks; storing the text blocks in a text database, encoding the text blocks to generate semantic vectors, and storing the generated semantic vectors in a vector database; a keyword search method and a vector similarity search method are adopted, based on the sewage treatment problem, retrieval results related to the sewage treatment problem are obtained from the text database and the vector database; the retrieval results are reordered, and answer document fragments are obtained; forming prompts based on the sewage treatment questions and the answer document fragments; and inputting the prompt into the large language model to generate a sewage treatment question and answer text. According to the invention, accurate answers corresponding to sewage treatment questions can be provided, so that the risk of sewage treatment is reduced.

The invention relates to the technical field of aggregation retrieval, in particular to a distributed aggregation retrieval method for a law and regulation text database, which comprises the following steps: collecting and integrating law and regulation text data, preprocessing the law and regulation text data, removing useless punctuations and blank characters, and generating a preprocessed text set. According to the method, data integration and preprocessing are carried out on the regulation text, useless punctuations and redundant blank characters are effectively removed, the purity of text data is guaranteed, and the accuracy of subsequent word segmentation and word frequency statistics is improved; the implementation of the word segmentation and word frequency statistical process is helpful for identifying key feature vocabularies in the regulatory text, so that the accuracy of the subsequent inverted index construction stage is enhanced; by preliminarily constructing the inverted index and implementing similar item merging and low-frequency vocabulary removing operation, the index scale and redundant interference are reduced, and the index query efficiency and accuracy are improved.

The invention relates to an automatic patent document generation method and system based on retrieval enhancement, and the method comprises the steps: carrying out the feature extraction of text content inputted by a user, and obtaining keywords and key sentences of the text content; based on the keywords, performing text retrieval in a pre-constructed text database, and sorting text retrieval results; based on the key sentences, vector retrieval is carried out in a pre-constructed vector database, and vector retrieval results are sorted; reordering the text retrieval result and the vector retrieval result through a reciprocal ordering algorithm; determining an auxiliary enhanced document in the reordering result; inputting the text content input by the user and the auxiliary enhanced document into the large language model, and outputting a patent document conforming to the standard template through the large language model; wherein patent documents in a text format are stored in the text database; vectorized patent documents are stored in the vector database; the large language model is trained based on a text database and a vector database.

The invention discloses a clothing attribute identification method and system, computer equipment and a readable storage medium, and relates to the technical field of image identification. The clothing attribute identification method comprises the following steps: acquiring a to-be-identified picture; and obtaining a picture text database of the clothes, and obtaining a clothes attribute recognition model according to the picture text database of the clothes and the deep learning model. And according to the clothing attribute identification model, identifying the attribute of the clothing in the to-be-identified picture, and obtaining the attribute data of the clothing in the to-be-identified picture. In the aspect of data, massive clothing data is crawled through a crawler technology, part of open source data sets are combined, pre-labeling is performed by means of the powerful content understanding ability of a visual language large model, and a professional clothing attribute data set is constructed. In the algorithm aspect, the advantages of a Transform architecture and a CNN are combined, a lightweight network structure with a self-attention mechanism based on a local sliding frame and key point regression as an auxiliary task is designed, and the method is used for solving the problem of clothing multi-attribute recognition and giving consideration to model precision and reasoning time delay.

The invention relates to the technical field of artificial intelligence, in particular to an intelligent paper marking content detection and identification method and system based on deep learning, and the method comprises the steps: determining a to-be-detected region through a locator; identifying a to-be-detected area based on the pixel value, and screening out an effective detection area; the uploaded characters are recognized and matched with a preset character database, and clear characters and fuzzy characters are distinguished; determining alternative preset characters corresponding to the fuzzy characters, performing screening through context semantics to obtain first preset characters, determining whether the same fuzzy characters exist or not, determining second preset characters for the same fuzzy characters, determining target characters according to the first preset characters or the second preset characters, or determining the target characters according to the target characters. Determining a writing model based on a deep learning algorithm and the plurality of clear characters, determining a third preset character based on the writing model and the fuzzy character, and determining a target character based on the first preset character and the third preset character. The accuracy of the intelligent paper marking result is improved.

This invention discloses a method, system, and storage medium for constructing a knowledge graph in the civil aviation service field. The method includes: S1, using a BERT-BiLSTM-CRF algorithm model to extract entities and obtain interrelated entity vector sequences, feature vector sequences, and annotation sequences; S2, using a convolutional neural network model to extract sentence vectors and their contained entity vectors, and employing n filters to identify and extract a database of entity-relationship-entity triples; S3, using a conditional random field entity node integration model to integrate the annotation information and store it in the corresponding entities as entity attribute values; S4, using the triple database and the integrated entity attribute values ​​to link and fuse them to construct a civil aviation knowledge graph. This invention can obtain a comprehensive and accurate civil aviation knowledge graph of entity relationships based on a civil aviation knowledge text database. It can not only satisfy passenger knowledge question answering and querying needs but also serve as a training and educational resource, improving the overall service level.

An embodiment includes analyzing text content of a user query to identify via natural language processing (NLP) a query topic. The embodiment maps the query topic to a topic cluster at a node of a hierarchical model of a text database. The embodiment generates query demand data indicative of demand for the topic cluster based on user queries. The embodiment identifies the topic cluster as a topic-cache candidate based on the query demand data. The embodiment compares an amount of memory required for storing text associated with the first topic cluster to available cache memory. The embodiment caches the text of the topic cluster candidate upon determining that there is sufficient available cache memory space.

The invention provides a blue-green algae image recognition method and system based on hierarchical self-adaption and domain driving, and the method comprises the steps: enhancing an image through employing an improved dark channel algorithm; constructing a blue-green algae biological attribute text database, and performing synonym replacement and sentence pattern recombination; multi-scale visual features are extracted through a hierarchical adaptive Swin Transform model, and key region characterization is enhanced in combination with dynamic spectrum attention; the text is input into a Bio-ALBERT model, and semantic embedding of field optimization is generated through term mask prediction and attribute relation pre-training; constructing a two-layer heterogeneous graph by using a graph attention interaction network GAIN, calculating a cross-modal association weight through a bidirectional graph attention mechanism, and outputting a cross-modal graph feature; multi-scale cross-modal association is modeled through a hierarchical graph attention fusion mechanism, and a comparison alignment loss optimization model is combined; and high-precision blue-green algae identification is realized. According to the method, through multi-scale perception, domain semantic adaptation and graph structure fusion, the accuracy of blue-green algae detection in a complex environment is improved.

The invention provides a knowledge question-answering method and device, a processor and a storage medium, and belongs to the field of information retrieval, and the method comprises the following steps: constructing a professional knowledge base for a specific field; wherein the professional knowledge base at least comprises a full-text database and a vector database; receiving a user query, and preprocessing the user query to obtain a standardized query; executing multi-path knowledge recall from the plurality of heterogeneous data sources in parallel based on the standardized query to generate a fusion recall result; wherein the plurality of heterogeneous data sources comprise but are not limited to a full-text database, a vector database, an internal retrieval API (Application Program Interface) plug-in and an internet retrieval interface; the historical interaction information, the fusion recall result and the standardized query are assembled into cue words through the instruction template; and inputting the cue word into the large language model to generate a reply text, and outputting the reply text in multiple modes. Through the method provided by the invention, the accuracy and coverage rate of knowledge recall can be improved, the answer is closer to real consultation, and the user experience is improved.

The embodiment of the invention discloses a text processing method and device based on a block chain, electronic equipment and a storage medium. The method can comprise the steps of obtaining a to-be-processed text; performing Hash calculation on the to-be-processed text to obtain a Hash value; generating a target block based on the hash value; consensus is carried out on the target block through a plurality of block chain nodes corresponding to the block chain to obtain a consensus result, and a text database is arranged in each block chain node in the plurality of block chain nodes; and when the consensus result is that the consensus is consistent, storing the to-be-processed text into the text database, and adding the target block into the block chain. According to the scheme, the text processing efficiency can be improved.

The invention provides a knowledge question answering method and system, a storage medium and a program product, and relates to the technical field of artificial intelligence. The method comprises the following steps: analyzing a first question, and extracting entities and entity relationships in the first question; retrieving entities and entity relationships in a knowledge graph database to obtain a plurality of key node entities and first content; based on the plurality of key node entities, performing retrieval in a text database to obtain second content; based on the plurality of key node entities, performing retrieval in a picture vector database to obtain third content; based on the plurality of key node entities, performing retrieval in a semantic vector database to obtain fourth content; the knowledge blocks in the first content, the second content, the third content and the fourth content are sorted so that content related to the first question can be output, and the knowledge graph database, the text database, the picture vector database and the semantic vector database are generated based on the knowledge files.

The invention relates to an entity extraction, storage and retrieval method based on LLM and multiple databases, entity information is extracted from a to-be-stored data set by constructing a prompt based on the LLM, an entity ID is generated based on the entity information, and entity attributes and relationships are written into a full-text library and a graph database respectively in the data storage process and are bound through the entity ID, so that the entity extraction efficiency is improved, and the data storage efficiency is improved. And the performance pressure of mass data storage of a single-class database is reduced. And after classification, synchronously writing into a full-text library and a graph database, writing entity attribute entries into the full-text library and binding the entity attribute entries with entity IDs previously written into the full-text library, and writing entity relationships into the graph database and binding the entity relationships with entity IDs previously written into the graph database. The data retrieval service is provided through the unified retrieval entry, the user does not need to increase the learning cost, the search scene is automatically judged to query the target database, the performance advantages of each database are fully played, and the mass data storage and retrieval efficiency is further improved.

The application discloses a generalizable voice generation SQL method. The technical scheme adopted by the application is as follows: step 1), acoustic information diversification processing and speaker information standardization processing are performed on original voice input by using voice reprogramming; step 2), semantic information rich audio representation is extracted by using a self-supervised audio representation model; step 3), the audio representation obtained in step 2) is classified by using a reverse gradient and a classifier on audio of different speakers, and gradient reversal is used during reasoning to learn speaker-independent audio representation; and step 4), the audio representation obtained in step 2) is input into a relation-aware transformer together with text database features, and the output is randomly input into an SQL decoder to obtain predicted SQL, and MLE loss is calculated with real SQL. The application adopts voice reprogramming and gradient reversal classifier technology, solves direct voice to SQL parsing, reduces acoustic method and style information in audio while retaining semantic information.

This application provides a method, apparatus, storage medium, and processor for querying similar text. The method includes: when the text type of the text to be queried is a first type of vocabulary, decomposing the text to be queried into multiple short words; determining a first target word vector for each short word; determining a second target word vector for the text to be queried based on the first target word vectors of all short words, thereby determining a first similarity between each word in the text database and the text to be queried; determining multiple first words in the text database that semantically match the text to be queried based on the first similarity, and a target similarity between each word in the text database and each first word; determining words in the text database whose target similarity is greater than a preset similarity threshold as target words matching the text to be queried. This greatly reduces the situation where text vectors cannot be recognized or have large errors, improving the success rate and accuracy of text recognition.

The embodiment of the invention provides a multi-modal answer generation method and device.The multi-modal answer generation method comprises the steps that question analysis and answer generation are conducted on a question through a large language model, and at least one sub-question, an associated question, a sub-question answer and an associated question answer are obtained, performing text retrieval in a text database according to the question, each sub-question, the associated question, the sub-question answer and the associated question answer, calculating the semantic similarity of the question and each candidate initial text obtained by the text retrieval through a similarity calculation model, and screening out the initial text of which the semantic similarity is greater than a similarity threshold; the method comprises the following steps of: acquiring multimedia data of a question, performing text merging of initial texts through a large language model to obtain answer texts, and finally splicing the multimedia data and the answer texts according to a position association relationship between the multimedia data associated with the initial texts and the answer texts to obtain multi-modal answer data of the question, so as to realize the generation of the multi-modal answer data of the question.

The invention discloses a laying hen epidemic disease detection method based on DistilBERT-GATv2 and BiLSTM-TCN, and the method comprises the following steps: extracting related data from unstructured text data, and constructing a high-quality structured text database; a DistilBERT model is adopted to carry out fine tuning training on the labeled corpus, accurate recognition of a target entity is achieved, and standardized entity categories and texts are output; realizing extraction of a semantic relationship between entities, and constructing disease triple data; a cross-sentence anaphora resolution mechanism and an entity normalization algorithm are introduced, semantic references are unified, and consistency and uniqueness of node semantics in the knowledge graph are ensured; storing the constructed triple data in a graph database to complete the construction of the domain exclusive knowledge graph; visual presentation of entity nodes, relation edges and query paths is achieved by configuring a visual component. According to the method, the epidemic disease type of the laying hen can be efficiently detected and diagnosed, the accuracy of an intelligent monitoring system is improved, manual intervention is reduced, and the automation level of laying hen disease prevention and control is improved.

The application relates to an audio evaluation method, a computer device and a storage medium. By obtaining a plurality of emission probabilities corresponding to the audio to be evaluated, obtaining first transition probabilities between each template character in a template audio text corresponding to the audio to be evaluated, and second transition probabilities between each preset character in a preset audio text database, determining a first decoding path and a second decoding path based on the decoding of the emission probabilities, the first transition probabilities and the second transition probabilities, comparing a template decoding path corresponding to the template audio with the first decoding path and the second decoding path, and determining an evaluation result of the audio to be evaluated based on the first evaluation value and the second evaluation value determined thereby. Compared with the traditional multi-dimensional evaluation of audio, the scheme decodes two evaluation values based on the emission probabilities, the first transition probabilities and the second transition probabilities, and then determines the evaluation result, solves the misjudgment problem in multi-dimensional evaluation, and improves the accuracy of audio evaluation.

The application discloses a kind of civil aviation safety report theme modeling methods based on large language model and semantic enhancement, its method includes: civil aviation safety theme semantic feature model extracts the text semantic vector and event structure vector of safety report text, and obtains the fusion feature vector of safety report text by fusion;Safety report text database is carried out cluster clustering processing and obtains initial cluster set and noise sample set;Select representative front p% as the representative sample set of cluster;Construct noise sample evaluation repair mechanism module, and select the candidate cluster to which noise sample belongs using noise sample evaluation repair mechanism module;Comprehensive gain function is constructed using representative sample set in cluster, and representative sample iteration screening processing of candidate sample is carried out in cluster.The application realizes the theme modeling goal of semantic accuracy, comprehensive coverage and stable result by multi-module collaborative innovation, and provides reliable technical support for management decision.

The application relates to a text clustering method based on an improved whale optimization algorithm, and belongs to the fields of big data mining and machine learning. The method comprises the following steps: S1: obtaining scientific research text data from a scientific research text database by using Spark, and performing data cleaning; S2: performing word segmentation, stop word removal, feature selection, vectorization and dimension reduction operations on the text data after data cleaning, so that unstructured text data is converted into structured numerical data; and S3: calculating initial clustering centers by using a K-means algorithm, optimizing the clustering centers by using an improved whale optimization algorithm, and outputting clustering results. The global optimization capability of the improved whale optimization algorithm is utilized, the problem that current text clustering algorithms are prone to falling into local optimization is solved, the accuracy of clustering of scientific research text data is improved, the data dimension is reduced, and the clustering effect is enhanced.

The application discloses a multi-view clustering method and system based on self-step learning and view weighting, and belongs to the technical field of multi-view data processing. The method comprises the following steps: normalizing a multi-view data set, splicing the multi-view data, initializing each view clustering kernel and distribution matrix by using a kmeans algorithm, and calculating each view weight; each view sample weight matrix, each view clustering kernel and distribution matrix are iteratively updated in sequence through a target function; and when an iteration end condition is met, a final clustering kernel and distribution matrix are output. The clustering system comprises an acquisition module, a preprocessing module, a construction module, an optimization module and a clustering output module. The self-step learning model is used to sequentially learn clustering data and finally obtain a clustering result. Through view weighting, the model can selectively learn information of different views, thereby effectively improving clustering accuracy. The application can be applied to retrieval of an image database, a text database and the like.

The invention provides an automatic international disease classification code coding method based on a multi-synonym matching network. The method comprises the following steps: S1, preparing a medical text database; s2, a main structure layer of a multi-synonym matching network algorithm model is constructed, a main calculation structure is designed, and the main structure layer of the multi-synonym matching network algorithm model comprises an encoder, a label encoder and a decoder; s3, training by using the prepared data set for training to obtain a model weight for reasoning, and evaluating a training result; s4, setting of various parameters of the multi-modal large language model is adjusted, the multi-modal large language model is designed to be combined with a multi-synonym matching network algorithm, the function of the multi-modal large language model is matched with a method target task, and a multi-modal ICD coding model based on a multi-synonym matching network is obtained; and S5, testing the multi-mode automatic international disease classification code coding model based on the multi-synonym matching network to enable the model to meet task requirements. According to the method disclosed by the invention, the ICD coding accuracy and convenience are effectively improved.

The invention discloses a data query method and a related device, and relates to the field of computers, and the method comprises the following steps: obtaining a query text, a database mode and a description text of the database mode; based on the query text, the database mode and the description text, calling a large language model, and generating an initial structured query language corresponding to the query text; calling a large language model, extracting a mode element from the initial structured query language to obtain a first mode element having an association relationship with the query text, and establishing a mapping relationship between a target mode element and the query text; based on the last structured query language and the mapping relation, calling a large language model, and generating a current structured query language corresponding to the query text; and under the condition that the current structured query language is the same as the last structured query language, performing data query based on the current structured query language to obtain query data indicated by the query text. The data query difficulty can be reduced.

The present invention provides a college admissions consultation question-and-answer system based on an offline universal large language model. The system comprises: an input module for inputting college admissions consultation question text; a classification and retrieval model for classifying and predicting the question text to obtain a predicted classification label; screening various text databases for corresponding classifications; performing feature extraction on the question text and each document in the corresponding classification text database, performing similarity matching, and selecting the document text with the highest similarity as the output result; a combination module for organizing the question text and the output document text using prompts to form an organized text; and an offline universal large language model for taking the organized text as input and outputting college admissions consultation response data. This system utilizes the offline universal large language model to replace the answer extraction module of traditional question-and-answer systems, reducing model training costs while making the question-and-answer system more intelligent.

The invention relates to an automatic driving edge scene understanding retrieval enhancement method and device and a medium. The method comprises the following steps: carrying out fine tuning training on a cross-modal vector embedding model by adopting a difficult-to-negative and semi-difficult-to-negative sample sampling comparison learning method; the trained cross-modal vector embedding model is adopted to generate embedding of an image-text pair, the text coding model is adopted to generate embedding of text description, and the image-text pair and the text description are respectively stored in a multi-modal database and a text database which share the same index; inputting a real image of an automatic driving edge scene, generating embedding of an image-text pair, retrieving a closest scene image from a multi-modal database according to embedding information, and splicing the closest scene image with the automatic driving edge scene and the real image to obtain an automatic driving edge scene image; and inputting the spliced image, the text description corresponding to the image closest to the scene and a set prompt word into a visual language model to obtain edge scene understanding without illusion. Compared with the prior art, the illusion problem existing in edge scene understanding can be effectively relieved.

This invention discloses an entity relationship recognition method and apparatus for decision knowledge graphs. The method includes: retrieving a set of decision text information from a decision knowledge text database; preprocessing the set of decision text information to obtain a preprocessed dataset; and performing entity relationship recognition processing on the preprocessed dataset to obtain an entity relationship information set.

Embodiments of the present disclosure relate to systems, methods, and computer product programs for identifying one or more seminal cases within a database containing legal case data. The disclosed systems and methods provide a way to identify one or more seminal cases for a particular legal issue by mining a text database containing electronic legal documents for citation reasons and mining the text therein to determine whether the legal issue addressed in the citation reasons involves a seminal case. Data is created by data mining and is obtained from a plurality of citation reasons that identify seminal cases for a particular legal issue, such that when one or more of the seminal cases are returned as search results, output data corresponding to the seminal cases enables an external device to distinguish the seminal cases.

The present application relates to a method, system, terminal and medium for converting text clarity based on OCR technology, which includes obtaining an ancient text image; generating character parameters based on the ancient text image; determining the recognition area of ​​each character based on the character parameters; identifying each recognition area and generating shape features corresponding to each character; comparing the shape features of the characters with a preset ancient text database to determine the ancient text font style; identifying the shape features of the characters based on the ancient text font style and the ancient text database, searching for the corresponding high-definition character model and generating high-definition characters based on the high-definition character model; arranging all high-definition characters according to the original character arrangement order; performing a proofreading operation and adjusting the high-definition characters based on the proofreading results; and outputting a high-definition image showing the high-definition characters. The present application has the effect of improving the recognition of ancient text and facilitating readers to read, copy and learn ancient text.

An embodiment includes analyzing text content of a user query to identify via natural language processing (NLP) a query topic. The embodiment maps the query topic to a topic cluster at a node of a hierarchical model of a text database. The embodiment generates query demand data indicative of demand for the topic cluster based on user queries. The embodiment identifies the topic cluster as a topic-cache candidate based on the query demand data. The embodiment compares an amount of memory required for storing text associated with the first topic cluster to available cache memory. The embodiment caches the text of the topic cluster candidate upon determining that there is sufficient available cache memory space.