1670 results about "Text generation" patented technology

The invention provides a knowledge and data fused medical content image-text generation system and method. Relates to the technical field of digital medical treatment and artificial intelligence. The multi-modal feature extraction module is used for extracting multi-modal features from the multi-modal data; the multi-modal feature fusion module is used for carrying out cross-modal dynamic fusion on the multi-modal features to generate cross-modal high-consistency fusion features; the model training optimization module is used for configuring a soft and hard target loss function and a parameter optimizer; the information analysis and reasoning module is used for carrying out semantic matching on the fusion features, the disease classification and the clinical path based on a dynamic medical knowledge network, and generating disease prediction probability distribution and a semantic reasoning path; and the image-text report generation module is used for generating an image-text report containing a diagnosis conclusion and an interpretation basis according to the prediction probability and the semantic reasoning path. According to the invention, intelligent and precise generation of medical contents can be realized.

The invention provides an audit report automatic generation method based on natural language processing, and relates to the technical field of natural languages, and the method comprises the steps: obtaining audit document data passing the examination and approval, the audit document data comprising an audit manuscript, an audit problem, an audit evidence obtaining sheet and an audit verification sheet; performing semantic analysis on the audit document data through a natural language processing model, and extracting key information of an audit subject, a risk point and a compliance conclusion; inputting the key information into a structured processing algorithm to generate structured data matched with a preset auditing template; and inputting the structured data into a pre-training text generation model for language reconstruction, generating an audit report text, automatically filling the audit report text into a corresponding field of an audit template, and outputting a complete audit report.

The embodiment of the invention provides an intelligent project text generation method and device, and the method achieves the precise screening of positive and negative training corpora through the construction of a multi-dimensional scoring mechanism, and the comprehensive evaluation of the text coverage degree, the technical correlation degree, the fluency and the professional term specification degree. And constructing a complete knowledge graph based on the relation extraction model and the external knowledge base, and fusing the enterprise technical feature matrix and the basic information to generate an enterprise portrait vector. By transforming a decoding layer structure of a pre-training large model, enterprise portrait vectors are used as condition vectors to be embedded, and personalized text generation is achieved. According to the method, the defects of the traditional technology in the aspects of training sample quality evaluation, knowledge graph integrity and enterprise feature fusion are effectively overcome, and the professionality and pertinence of project text generation are remarkably improved.

Disclosed in the present disclosure is a rich-media document auxiliary generation apparatus. The apparatus comprises a material extraction module, a theme sorting module, a semantic retrieval module, a structured data text generation module, an illustration recommendation module and a video composition module. The present disclosure uses intelligent means to assist a user to efficiently generate a high-quality rich-media composite document, thereby quickly and accurately describing a theme event in an all-round way.

Aiming at the problems of insufficient language understanding depth, weak personalized dialogue generation ability, lack of continuous learning and long-term user state modeling and the like in the current emotion recognition and psychological intervention technology, the invention provides a user emotion recognition and psychological intervention method combined with a large language model (LLM). According to the method, the potential emotional state is identified by analyzing free text information input by a user by utilizing the powerful capabilities of a large language model in the aspects of natural language understanding, emotional modeling and text generation; constructing a multi-round dialogue context, and reasoning a psychological change trend of the user; in combination with a psychological knowledge base, personalized and mild psychological intervention dialogue content with a dredging effect is generated. The system supports recognition and classification of various emotional states such as depression, anxiety and alonity, is suitable for various interaction scenes (such as APPs, webpages and social robots), and can greatly improve the precision of emotion recognition and the timeliness and effectiveness of psychological intervention. The emotion recognition and psychological intervention method based on the large language model provides solid technical support for constructing an intelligent, continuous and personalized psychological health management system, and has wide application prospects and profound social significance.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as financial science and technology and medical health, and discloses a protocol text generation and verification method and device, equipment and a medium. The method comprises the following steps: acquiring multi-modal data related to a target object, constructing a dynamic abnormal portrait, matching the dynamic abnormal portrait with a clause knowledge graph, screening candidate clauses to form a candidate clause pool, generating a protocol text according to the candidate clause pool, carrying out logic conflict detection on the protocol text, and carrying out compliance verification when a logic conflict is not detected. And after the compliance verification is passed, generating a record from the protocol text, storing and outputting. According to the method, multi-source clause knowledge and dynamic abnormal portraits are fused, automatic clause screening and protocol generation based on risk features are achieved, logic conflict detection and compliance verification are carried out, the generation efficiency and personalized suitability are improved, and the protocol compliance is enhanced.

The present application is applicable to the technical field of artificial intelligence, and provides a text generation method, a method for training a text generation model, and a related device. The method comprises: acquiring an input text; determining an input token vector on the basis of the input text, wherein the input token vector comprises an input token array, an output token array, an output mask array, N candidate tokens, and N candidate mask arrays; inputting the input token vector into a text generation model to obtain an output result, wherein the output result comprises candidate output tokens and a probability distribution thereof; sampling the output result to obtain a sampling result; performing rejection sampling on the basis of the sampling result to obtain an output token; and adding the output token into the output token array, and using the output token array as an output text. The method in an embodiment of the present application can ensure generation performance while improving decoding speed and does not rely on any additional models.

The invention relates to the technical field of artificial intelligence and natural language processing, and particularly discloses a text content generation method based on artificial intelligence, and the method comprises the steps: obtaining natural language text input, and extracting a semantic recognition feature vector; acquiring context state data and encoding the context state data into a state recognition feature vector; generating a fusion feature vector containing a semantic and state association relationship through fusion analysis; constructing a causal discrimination model based on the fusion features, and outputting the matching confidence of semantics and states; dynamically adjusting a generation strategy according to the confidence coefficient, if the matching degree is high, generating a standard text, otherwise, triggering an error correction mechanism to output a corrected text; and finally, performing logic consistency verification on the generated text to ensure that physical constraints, technological procedures and safety standards in the industrial field are met. According to the method, by introducing multi-level feature fusion, causal reasoning, intelligent error correction and rule verification mechanisms, context perception and safety controllability in the text generation process are achieved.

A method and related system for generating document embeddings within an embedding space based on a set of structured documents by determining (i) a first vector based on a first segment of a first document and (ii) a second vector based on a second segment of the first document and updating association vectors indicating the second segment based on a distance between the first and second vectors. The method also includes generating a document embedding based on the association vectors, generating a candidate vector based on a candidate document, and determining a result indicating that a second distance between the candidate vector and a first document embedding satisfies a document embedding distance threshold. The method may also include generating a new document by providing, to a text generation model, a portion of the candidate document and a portion of the second segment of the first document.

The invention discloses a data analysis problem generation method based on image input and large model combination, and the method comprises the following steps: S1, obtaining original image data, and carrying out the preprocessing of the original image data; s2, constructing a visual language model based on a Qwen-VL architecture, and performing bidirectional alignment to generate a visual feature vector; s3, constructing a cue word template, and fusing the cue word template through a cross attention mechanism to generate structured text description; s4, constructing a large language model based on a Transform architecture, and performing supervision and fine tuning by adopting a LoRA method to generate a data analysis problem candidate sequence; s5, semantic consistency detection and structural rule matching are carried out, and sequences which do not meet semantic specifications or structural constraints are removed; and S6, constructing an image-text alignment triple, and writing the image-text alignment triple into the data structure in the JSON format for coding and storage. According to the method, the image can be converted into a data analysis problem, and the text generation quality and efficiency are remarkably improved.

The invention relates to the technical field of data processing, in particular to a strategy generation and evaluation method based on a large language model, a medium and equipment, and the method comprises the steps: dynamically determining a first model unit and a second model unit through the character number of codes and cue words and the memory attribute of a preset large language model; resource and efficiency balance is optimized while independence of reference strategy codes is guaranteed, and integrity and stability of initial strategy text generation are guaranteed; an initial strategy text is generated according to the first model unit, and reference strategy codes corresponding to the roles are generated in combination with the preset role cues and the second model unit, so that the same initial strategy text can adapt to understanding perspectives of different roles, and a multi-dimensional evaluation basis is obtained; in combination with the first similarity between the strategy codes and the weight of the preset role prompt word, effectiveness evaluation is performed on the initial strategy text, the semantic transfer accuracy and interpretation suitability of the initial strategy text in a multi-role scene are reflected, and meanwhile, the accuracy of an evaluation result is improved.

The invention discloses a multi-agent-based programmable logic controller structured text generation method. The method comprises the following steps: constructing a programmable logic controller programming task solution knowledge base; five large model agents are constructed, including a knowledge retrieval agent, a task planning agent, a structured text generation agent, a verification agent and an error correction agent. According to the method, through mutual cooperation of multiple agents and flexible calling of various tools and models, the knowledge deficiency of a large language model in the programming aspect of the programmable logic controller is made up by utilizing a retrieval enhancement generation technology, the illusion problem of the large language model in the process of generating the structured text of the programmable logic controller is effectively reduced, and the reliability of the structured text of the programmable logic controller is improved. And the success rate and the expansibility of automatically generating the structured text of the programmable logic controller are improved.

The invention relates to a zero sample text classification method and device based on cross-modal information completion. According to the method, cross-modal information complemented image construction is realized by designing a new image label mapping mechanism and based on context text generation, finally, a multi-modal collaborative reasoning framework is designed in a reasoning stage, text semantic perception capability is enhanced by prompting project optimization text input, and zero sample reasoning capability of a CLIP model is effectively improved. Aiming at the semantic deviation problem of automatic label generation, a cross-modal information complemented image is constructed based on context text generation so as to optimize the text semantic representation integrity, and meanwhile, a prompt design is introduced in a reasoning stage to enhance the text semantic perception capability; according to the two-stage keyword automatic selection mechanism, firstly, a keyword candidate set is generated through a large model, secondly, through multi-modal matching and selection, the optimal keyword phrases are selected to serve as text information complemented by cross-modal information, and semantic accuracy and field adaptability are effectively improved.

The invention provides a big language model pruning method and device, a storage medium and a program product. The method comprises the steps of obtaining a pre-trained big language model and a corresponding text data set; dependent neurons are activated through iteration, interdependent coupling groups in the large language model are recognized, and the coupling groups serve as basic units of pruning; based on the coupling group, performing coarse-grained evaluation and fine-grained evaluation on the parameters in the group, and fusing and calculating the importance of the parameters to generate a pruning mask; redundant parameters in the model are removed through pruning operation according to the pruning mask; performing parameter optimization on the pruned model, and performing fine tuning through a text data set to generate a target large language model; and deploying the target large language model to a computing device, executing a text generation or semantic analysis task, and counting the task accuracy rate and the model compression rate. According to the method, the parameter quantity of the model is effectively reduced, so that deployment is simple, and the downstream task processing accuracy of the pruned model is improved.

The invention provides an AI auxiliary reading method and system based on dynamic partitioning knowledge classification self-verification, and relates to the technical field of artificial intelligence, the method comprises the following steps: carrying out dynamic semantic partitioning on a super-long text to obtain a plurality of initial text units with consistent internal semantics; performing topic model construction according to the initial text unit and a layered Dirichlet process to obtain a topic distribution tag; receiving a user query request, and extracting a retrieval text set according to the hierarchical retrieval strategy and a retrieval text corresponding to the user query request; inputting the constraint cue word extracted by the topic distribution tag corresponding to the retrieval text set, the retrieval text set and the retrieval text into a text generation model to output a to-be-calibrated text; if the error scoring function of the to-be-calibrated text and any initial text unit in the retrieval text set is smaller than a preset error threshold value, the to-be-calibrated text serves as a credible text to be output to a user. According to the invention, the credibility and accuracy of the answer can be enhanced.

The invention discloses an image counterfeiting multi-type detection method and system based on a visual large language model, and belongs to the technical field of image processing and computer vision. The method comprises the following steps of: preprocessing a data set containing normal, copy and paste forged and spliced forged images, extracting visual and language features by utilizing a pre-training model, and realizing feature fusion by adopting a multi-modal alignment technology. Whether an image is forged or not is judged through a classification task, a forged area is positioned through a segmentation task, and meanwhile a forged text description is output through a text generation module. The loss function is optimized in combination with classification, segmentation, comparison and text cross entropy loss. And adopting an end-to-end training and course learning strategy training model, and outputting a forgery probability, a regional mask and text description during reasoning. According to the method, multiple counterfeit types can be processed at the same time, high-precision positioning is achieved, multi-modal information is effectively fused, and detailed counterfeit text description can be provided.

The invention proposes a flood disaster dynamic prediction method based on multi-source remote sensing data and a knowledge graph, and relates to the field of data prediction, and the method comprises the specific steps: firstly, building a space-time disaster dynamic model through a physical drive text generation module, and describing the evolution process of a flood disaster; generating personalized flood disaster description in combination with the static characteristics and the dynamic remote sensing data; then, a multi-scale residual diffusion enhancement module improves sensitivity to dynamic change of disasters through multi-scale trend extraction and residual calculation, noise is removed, and useful information is reserved; then, the multi-modal fusion module enhances interdependence and information sharing among different modals by using adaptive modal mapping, a cross attention mechanism and a weighted fusion strategy; and finally, training through a regression model, dynamically adjusting the feature weight by using an adaptive feature weighting mechanism and an incremental learning mechanism, and finally obtaining a flood disaster prediction value through the prediction set.

The invention discloses an intelligent oral English training system and method based on Prompt engineering, and relates to the technical field of oral English training. According to the method, a user is allowed to freely describe training requirements by using a natural language, the system automatically constructs a training Prompt, and personalized customization is realized; content deviating from a training target is accurately recognized through a deviation question detection module, a user is guided to return to a theme through real-time voice or text, and effectiveness and pertinence of training are guaranteed; a clear template definition ensures systematicness and reproducibility of a training task, and clear control and evaluation of a teaching target are facilitated; in combination with voice recognition, voice synthesis and text generation, natural interaction in a real context is realized, and the training experience is improved; on the basis of multi-dimensional automatic evaluation of a keyword hit rate, pronunciation quality and the like, personalized learning suggestions are supported; teachers are supported to generate training tasks in batches, students are supported to customize scenes, and different education environment requirements are met.

The invention provides an intelligent number asking method for large model index query, and belongs to the field of natural language processing and database query. An auxiliary information base is constructed to store a database structure and historical question and answer examples, and key entities and fields are extracted by conducting structured format processing on natural language questions; a large language model guided by a small number of examples is utilized to generate an intermediate expression close to an SQL grammar and a plurality of SQL query candidates, and a consistency alignment mechanism is designed to verify candidate SQL in the aspects of field matching, aggregation functions, data tables and the like so as to screen out an optimal SQL query. Finally, the generated correct SQL and the corresponding question and answer pairs are fed back to the auxiliary information base, and self-learning enhancement is achieved. According to the method, under the condition that only a small number of training examples are needed, the accuracy and expandability of large language model text generation SQL query are improved.

The invention discloses a knowledge cross validation question-answering method and system for reducing hallusion of a large language model, and belongs to the technical field of artificial intelligence, and the method is implemented by the following steps: generating results through multiple times of sampling: when a user puts forward a question, controlling the large model to perform multiple times of sampling, and generating a specified number of results; calculating hidden state related indexes: extracting the hidden state of the last token of the middle layer of the large model corresponding to the result, and calculating covariance matrixes and answer discrete feature values of the hidden states; mLP model prediction: inputting the discrete feature value of the answer and the length of the answer into a multilayer perceptron MLP, and outputting a hallucination-free probability; querying and summarizing a knowledge graph; and calculating a final illusion-free score and outputting a result. According to the method, the answer quality and credibility of a large language model can be remarkably improved, and the method is particularly suitable for application scenes with extremely high requirements on the accuracy of single-mode text generation contents.

The invention relates to a retrieval method and device based on static word embedding, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps of performing word segmentation on an original text to obtain a first word segmentation result, training a static word embedding model by utilizing the first word segmentation result to obtain word vectors, and generating a synonym word library; the method comprises the following steps: establishing a full-text inverted index by utilizing an original text, and expanding query words by utilizing a synonym library in a retrieval stage; encoding the original text into a semantic vector by using a semantic generation model, and constructing a vector index based on the semantic vector; based on a to-be-queried text in a user query request, performing retrieval by using the full-text inverted index to obtain a first candidate document, and performing retrieval by using the vector index to obtain a second candidate document; performing fusion processing on the first candidate document and the second candidate document to obtain a target candidate document; and inputting the target candidate document into the text generation model to obtain a retrieval result. By adopting the method, the accuracy of text retrieval can be improved.

The invention discloses a cervical cell image intelligent diagnosis system based on a multi-modal visual language large model, belongs to the field of cervical cell image recognition, and particularly relates to the cervical cell image intelligent diagnosis system based on the multi-modal visual language large model. In order to solve the problems of low diagnosis accuracy, strong subjectivity, insufficient efficiency and lack of interpretation in the prior art, the invention provides a cervical cell image intelligent diagnosis system based on a multi-modal visual language large model. The system comprises an image block acquisition module, an image preprocessing and color normalization module, an effective tissue region screening module, a cell region extraction and post-processing module, an image end and text end processing module, a visual language large model acquisition and training module, a cell description text generation module in an inference stage, and a risk judgment and classification module. An interpretability verification and credibility evaluation module; and a structured diagnosis report output module.

The invention discloses a structured remote sensing report generation system, method and device based on a syntax tree and a medium, the system comprises a user input layer, a core processing layer and an output and verification layer, the system receives user demand parameters and input data, automatically analyzes the demand parameters and standardizes the input data; generating a syntax tree structure conforming to industry specifications, and driving the large model to obtain a first draft of a report under the constraint of the syntax tree; and performing automatic verification and manual intervention correction on the first draft of the report to form a professional remote sensing report. According to the method, the multi-dimensional syntax tree architecture is constructed, and the hierarchical syntax analysis algorithm and the domain knowledge graph are combined, so that semantic association of the multi-modal remote sensing data and accurate mapping of terminologies are realized, automatic generation of a long document report meeting remote sensing geographic industry specifications is supported, the structured degree and logic continuity of text generation are improved, and the text generation efficiency is improved. The method can be widely applied to the fields of geological monitoring analysis, environment evaluation report generation and the like.

The invention provides a large model intelligent reasoning method combining reinforcement learning and retrieval enhancement generation, and belongs to the technical field of artificial intelligence. Comprising the following steps: data input: data preprocessing; constructing a reinforcement learning environment; an RAG mechanism is integrated; training the model; and evaluating and iteratively optimizing. A reinforcement learning framework based on rules is introduced to guide a model to develop advanced reasoning skills such as reflection, verification and summarization. And in combination with a retrieval enhancement generation mechanism, the model can access and utilize a wide background knowledge base before answering questions. The synergistic effect between information retrieval and text generation is optimized. According to the method, the deficiency of knowledge of the model can be made up by introducing the external knowledge base, and the synergistic effect between information retrieval and text generation can be optimized in the reinforcement learning process, so that the capability of the model for processing complex reasoning tasks is remarkably improved, and formation of a more generalization reasoning strategy is promoted.

A method can be implemented via execution of computing instructions configured to run at a processor. The method can include: receiving, from a user, an image of a product; receiving, from the user, user-submitted logo alt text describing a brand of the product in the image; receiving, from the user, user-submitted image alt text describing the image; extracting brand information from the user-submitted logo alt text; extracting product information from the user-submitted image alt text; generating an instruction prompt that includes the brand information, as extracted, and the product information, as extracted; and generating a recommended image alt text describing the image and including the brand information, as extracted, and the product information, as extracted, by querying a multimodal generative artificial intelligence (multimodal GenAI) model with the instruction prompt. Other embodiments are disclosed.

A method for training a text generation machine learning model for prompt generation includes receiving a plurality of training text strings; executing a text generation machine learning model using each of the plurality of training text strings to generate a plurality of training generated text strings, each of the plurality of generated text strings corresponding to generating a content item; executing a content scoring machine learning model using each of the plurality of generated text strings to generate a text performance score for each of the plurality of training generated text strings; for each of the plurality of generated text strings, adjusting one or more weights or parameters of the text generation machine learning model proportional to the text performance score for the generated text string.

The invention relates to the technical field of financial management, and discloses a causal interpretability and illusion suppression method, system and device for text generation, and the key point of the technical scheme is that the method comprises the following steps: S1, obtaining related data according to a generation target, extracting the causal relationship between entities, and constructing a causal map; s2, extracting a causal chain related to the generated target from the causal atlas, and inputting the causal chain and the input variables into the large language model to obtain a target text; s3, performing anti-fact intervention processing on the input variable, inputting the input variable into the large language model, and recording a logic test result; s4, identifying an entity from the target text, comparing the entity with the fact data related to the generated target, and calculating an entity alignment score; and S5, according to the causal chain, the target text, the logic test result and the entity alignment score, generating an interpretation report and performing structured output, so that the output text has higher logicality and higher credibility.

The embodiment of the invention relates to a reply text generation method and device, computer equipment and a storage medium. After an input text is preprocessed, a target text is obtained; acquiring context information corresponding to the target text, a first prompt word template and a first keyword; retrieving related information corresponding to the input text from a first database according to the input text, the context information, the first cue word template and the first keyword to obtain a retrieval result; generating cue words of a large language model according to the input text, the context information, the first cue word template, the first keyword and the retrieval result; and inputting the cue word into the large language model to output the reply text through the large language model. Therefore, after the input text is combined with the context information, the cue word template of the industry and the keyword to retrieve the related information, the cue word of the large language model is generated according to the retrieval information, the reply text is accurately generated through the large language model, and the question and answer accuracy and the user satisfaction degree are improved.

The invention provides a controllable text generation method, device and equipment, and the method comprises the steps: obtaining an input text, segmenting the input text, and obtaining a plurality of input words; inputting an input word into the trained vertical classifier, and outputting a category probability corresponding to the input word; constructing a word-level attribute graph according to all the input words and the category probability corresponding to each input word; processing the word-level attribute graph by utilizing a webpage ranking algorithm to obtain a target keyword; generating a semantic-level attribute graph according to the attribute graph generation prompt; determining a target combination prompt according to the input text, the original prompt, the target keyword, the context information and the semantic-level attribute graph; and inputting the target combination prompt into the large language model, processing the target combination prompt by the large language model, and outputting a controllable text. The word-level attribute graph and the semantic-level attribute graph are combined to guide the large model to better understand the input text, so that the high-quality response is generated, and the controllable generation of the vertical drive is realized.

The invention belongs to the field of natural language processing and artificial intelligence, and particularly relates to a long text writing generation method and system based on multi-agent cooperation. The method comprises the following steps: receiving a text theme input by a user, completing complex theme decoupling, and outputting an outline directory; the method comprises the following steps: collecting keywords according to a text topic and an outline catalog, obtaining a retrieval result by retrieving the Internet, a domain database and network resources, and preprocessing to obtain a reference with a uniform format; performing systematic evaluation on the reference literature from the field integrating degree and the logic relevance, and performing grading processing on the reference literature to obtain a high-quality reference literature; based on the text theme and the high-quality reference, long text content is generated according to a set logic structure and writing specifications. According to the method, the fragmented expression problem is effectively avoided, the academic value and reading experience of the text are remarkably improved, the inherent defects of a traditional long text generation technology are practically overcome, and a high-efficiency solution is provided for text creation in the professional field.