323 results about "Word generation" patented technology

The invention provides a knowledge graph construction system and method based on cue words, and the method comprises the steps: determining a mapping relation corresponding to an obtained unstructured document set through a data collection module, and transmitting the mapping relation to a vector data storage module; sending the obtained rule extraction file to an automatic cue word generation module to obtain a target template, and distributing the target template to a problem auditing module and a cue word judgment module; the vector data storage module obtains vectorized data based on the mapping relation and stores the vectorized data to a vector database; the problem auditing module audits a drawing instruction input by a user according to the template, and if the auditing is passed, the drawing instruction is sent to the cue word judgment module, so that the cue word judgment module inputs the corresponding template and the drawing instruction into the intelligent reasoning and executing module, the drawing instruction is embedded into the template and then is transmitted into a preset large language model, the drawing instruction is disassembled, and the drawing instruction is sent to the intelligent reasoning and executing module. And according to a disassembling result, querying a vector database and calling related tools, so that efficient and accurate knowledge graph construction is realized.

The invention provides a cue word generation method and device, equipment, a medium and a program product, and relates to the technical field of computers, in particular to the technical field of artificial intelligence, natural language processing and deep learning. According to the specific implementation scheme, user input content is obtained; based on constraints of a user knowledge base and / or a user intention rule base, adopting an intention recognition model to perform cue word intention recognition on user input content, and outputting cue words reflecting user intentions; and inputting the cue word into the cloud model to obtain an output result. According to the embodiment of the invention, the generation accuracy of the cue word can be improved.

The invention provides a cue word hierarchical optimization method for complex problem decomposition, which belongs to the field of artificial intelligence and natural language processing, and comprises task analysis, hierarchical cue word generation, feedback optimization mechanism, example reinforcement learning and multi-round interactive optimization. The execution effect and adaptability of complex tasks are improved, and the reasoning quality and the stability of generated results are improved.

The invention relates to the technical field of multi-round dialogue processing, in particular to a multi-round dialogue processing method based on RAG technology dynamic cue word retrieval. Comprising the following steps of question input by a user, initial retrieval and cue word generation, question splicing and answer generation, historical dialogue management and context coding, multi-round question analysis and retrieval enhancement, complex question decomposition and parallel retrieval, multi-source information fusion and generation model optimization, iterative feedback and model tuning, and exception handling and fault-tolerant mechanism. According to the method, related information is retrieved from an external knowledge base, the model can utilize wider and more specific knowledge to generate answers and better track dialogue history and context, so that answers consistent and coherent with the dialogue history are generated, the model can generate answers on a short input sequence by retrieving and splicing related cue words, and meanwhile, the model can be used for analyzing the dialogue history. Cue words are dynamically generated according to user input and retrieval results, so that the model can better adapt to different dialogue scenes and user requirements.

The invention relates to the technical field of artificial intelligence and natural language processing, in particular to a cue word compiling and generating method and system for a large language model.The method comprises the steps that in response to a compiling calling request, a PDL protocol is received to serve as a compiling input text; performing lexical and grammatical analysis on the compiled input text, and constructing a corresponding abstract syntax tree AST as an intermediate representation according to a context-independent method; semantic verification and structure correction are carried out on the AST, and when semantics are effective, structure optimization is carried out to generate an optimized AST; and traversing the optimized AST, matching a cue word template in a cue word generation rule base, mapping semantic nodes into structured text fragments, splicing the structured text fragments to form a final cue word text, and outputting a compilation result consistent with PDL protocol semantics. By introducing a PDL-oriented compiling mechanism, automatic analysis, structure optimization and high-quality cue word generation of an input protocol are realized before cue words of a large language model are generated, and the development efficiency and the output quality of the cue words are improved.

The invention discloses an infrared and visible light image fusion method, electronic equipment and a storage medium, and belongs to the technical field of image processing. The method comprises the following steps: acquiring a weak visible light image and an infrared image corresponding to the weak visible light image; an image fusion network is constructed, the image fusion network is supervised by using a supervised label generated by a pre-trained brightness adjustment network, and the quality of a fused image is constrained by using a pre-trained cue word generation network; and inputting the weak visible light image and the infrared image corresponding to the weak visible light image into the image fusion network for fusion to obtain a fused image. According to the technical scheme, the problem of daytime overexposure existing in a traditional night image fusion algorithm is effectively restrained, and meanwhile the problem of night point light source overexposure is effectively restrained.

The invention relates to the technical field of natural language processing, in particular to a context-based Prompt generative model optimization system, which comprises a context analysis module, a cue word generation module, a context optimization module, a semantic check module and a structure reconstruction module. According to the method, the context path and the semantic hierarchy information of the semantic unit are introduced, the fine degree of semantic matching degree recognition is improved, semantic guide deviation caused by statement template solidification is avoided, the cue words are recombined in combination with the semantic coherence weight and the logic dependency relationship, and the recognition accuracy is improved. The consistency and expression accuracy of the prompt content in the context are enhanced, the prompt word insertion sequence and connection mode are dynamically adjusted through a semantic conflict detection and structure rechecking mechanism, coherence and stability of a semantic structure and controllable generation of the prompt content are kept, semantic conflicts and expression chaos caused by static matching are effectively avoided in the generation process, and the generation efficiency is improved. And dynamic adaptation of prompt configuration and smooth optimization of language output are integrally realized.

The invention discloses a game cue word generation method fusing an expert strategy and multi-thinking-chain reasoning. The method comprises the following steps that multi-modal input composed of a text and an image is obtained; multi-mode information is injected into multi-thinking-chain reasoning and expert strategies, and efficient access and cue word splicing of the multi-mode information are achieved; inputting the micro-operation multi-mode cue word fusing the expert multi-stage strategy and the multi-thinking chain reasoning into a large language model; performing comprehensive analysis on the input information by the large language model, generating a plurality of thinking chains in parallel, selecting an optimal scheme through evaluation, and mapping a high-level decision into a specific game operation instruction; the large language model outputs an action instruction to an LLM-PySC2 interface, and the game environment is executed and influenced; and outputting game information, related knowledge, legal actions, action parameters and actions of the previous step back to the large model, and carrying out learning and evaluation again.

The invention discloses a multi-agent cooperative cue word engineering optimization method, system and device and a medium, and relates to the technical field of cue word engineering, the method comprises the following steps: after initially receiving a user input task, starting a cue word optimization process; an initial cue word template is created through a cue word generation agent, historical optimal templates are retrieved from a knowledge base for fusion, and candidate cue word templates are generated. And the analysis agent inputs the candidate template into the second large language model to generate a candidate answer. And the evaluation agent performs multi-dimensional evaluation on the answers and gives scores and defect analysis. And according to an analysis result, updating the cue word to generate a candidate template of the intelligent agent. And arranging the intelligent agent to cyclically execute the steps until the stop condition is met, and outputting the optimal cue word template. And finally, storing the optimal template into a knowledge base and establishing a semantic index to support subsequent retrieval reuse. According to the method, manual intervention is not needed, and a complete automatic process of generating, evaluating and optimizing the cue word is realized.

The invention relates to an inference decision-making method, device and equipment for a complex dynamic game scene. The method comprises the following steps: constructing a two-step Markov reasoning framework on the basis of an agent decision-making process in war game confrontation simulation, and dividing a decision into two steps of state reasoning and action decision-making. And designing a structured dynamic decision option library based on the framework, and constructing a dynamic reasoning decision chain. In the cue word generation stage, cue words are generated according to chains and combined with real-time observation information to be input into the large language model; in the state reasoning stage, the model selects options from a state option library to form structured situation description; and an action decision-making stage: selecting a strategy from the strategy option library according to a state reasoning result and converting the strategy into a simulation execution action. According to the method, through layered constraint and structured processing, the accuracy of key information extraction in wargame confrontation is improved.

The embodiment of the invention provides a method for constructing large model cue words in the financial credit field based on the ReAct theory. The method can solve the technical problem of cue word errors caused by semantic understanding deviation in related technologies. The method comprises the following steps: defining a role and a capability boundary of a dynamic cue word generation model, and binding a structured credit knowledge graph; inputting the received original business problem, the scene label and the real-time data into a dynamic prompt word generation model to obtain at least one first keyword; matching entity nodes related to the first keyword in the credit mapping knowledge domain, and generating a keyword entity association result; calling a preset process template according to the scene label, generating a reasoning chain comprising at least one reasoning layer node, and inserting a judgment condition: binding a tool calling instruction at the action layer node, obtaining external data, backfilling the external data to the reasoning chain, obtaining backfilled data, executing the reasoning chain, and outputting a service result; the cue word priority weight is improved according to the service result, and the cue word accuracy is improved.

The invention relates to the technical field of computer vision and natural language processing, and discloses an image-based cue word generation method, which comprises the following steps of: obtaining non-text vision elements, text elements and position information thereof from a cue image, screening and processing the elements, removing text contents in the image and generating a cue image without characters. And based on the target non-text visual elements, cutting out corresponding image areas from the prompt image without characters, inputting the image areas into the multi-modal model, and generating prompt words related to the visual elements. According to the method, the non-text visual elements and the text elements in the image are automatically recognized, the image without characters is generated, and character interference is avoided. The cue word highly related to the image content is generated, the cue word generation accuracy and automation are achieved, and the processing efficiency and the cue word quality are improved. The complexity of writing the cue word by the user is effectively reduced, so that the user can generate the cue word with high quality and accurate semantics through simple image interaction.

The invention relates to the field of image generation, and discloses a picture material batch generation method and device, equipment and a medium, and the method comprises the steps: receiving a prompt word generation request, confirming a target scene, and generating a plurality of prompt texts in batches according to the prompt word generation request and the target scene; calling a target generation model matched with the target scene from a plurality of pre-trained picture generation models, wherein the plurality of picture generation models have different generation styles; inputting the plurality of prompt texts into a target generation model, and generating a plurality of initial picture materials in batches; and performing multi-dimensional scoring on the plurality of initial picture materials according to a preset scoring strategy, and screening out a target picture material from the plurality of initial picture materials according to a scoring result. According to the method, the prompt texts are generated in batches, the multiple picture materials are generated in batches through the models with the corresponding generation styles, screening is carried out through multi-dimensional intelligent scores, batch generation and screening of the stylized picture materials are achieved, and the efficiency and quality of picture material generation are improved.

The invention provides a data classification and grading method and system, and belongs to the technical field of data processing, and the method comprises the steps: obtaining the class information of to-be-processed data, and determining the grading rule information according to the class information; inputting the to-be-processed data and the grading rule information into a target cue word template to generate a target cue word; the target prompt word template is determined according to the format of the to-be-processed data; inputting the target cue word into a target grading model to obtain grading information output by the target grading model; wherein the target grading model is obtained by matching from a pre-constructed model library based on the format of the processing data. According to the method, the accuracy of data classification and grading is effectively improved by combining dynamic category recognition, target cue word generation and grading model dynamic matching based on the model library.

The invention discloses a low-altitude flight intelligent decision-making method based on atlas retrieval enhanced generation and digital flight rules. The method comprises the following steps: firstly, preprocessing and translating a digital flight rule (DFR) text, extracting entities and relationships through a large language model, constructing a structured knowledge graph, and storing the structured knowledge graph in a vector database; and secondly, circularly calling the large model for three times: calling an optimization cue word to generate a template for the first time, calling a template-based analysis DFR text to complete atlas construction for the second time, and calling a combination atlas retrieval capability to execute compliance verification and route intelligent decision-making of a low-altitude flight task for the third time. In addition, when an airspace rule is changed or a temporary announcement exists, real-time updating of knowledge is achieved by inserting a new node into the knowledge graph or modifying edge attributes. According to the method, GraphRAG and DFR combination is generated through map retrieval enhancement, the interpretability, accuracy and dynamic adaptability of large model decision making are improved, and the problem of complex decision making in a low-altitude environment is solved.

The invention discloses a knowledge graph enhanced cue word generation method and device, equipment and a medium, and relates to the technical field of large language models.The method comprises the steps that knowledge retrieved from a knowledge graph is constructed into a mind map form; the method comprises the following steps of: performing one-round or two-round conversion on knowledge among different organization forms through a prompt large language model, finally generating a plurality of candidate knowledge cue words in a mind map form, scoring the candidate cue words, selecting optimal cue words corresponding to each piece of training data to form a false cue data set, and performing false cue processing on the false cue data set. A large language model is finely adjusted by using the pseudo prompt data set to serve as a knowledge prompt optimizer, the finely-adjusted knowledge prompt optimizer can generate knowledge prompt words adaptive to the large language model according to input and related knowledge, and the inference ability of the large language model is fully stimulated.

The invention relates to the technical field of financial science and technology and natural language processing, in particular to an intelligent financial cue word generation and optimization system based on a knowledge graph, which comprises a financial field knowledge base, a cue word element extraction module, a field specialization template library, a cue word generation engine, an evaluation and optimization module and a manual feedback and labeling system, the efficiency is improved, through template generation and parameterization configuration, the prompt word writing time is shortened, and the labor cost is remarkably reduced. And quality guarantee: the accuracy of professional terms is improved, the structural integrity and compliance coverage are remarkably improved, and the output deviation of a large model is reduced. And scene adaptation: the fields of security investment, financial analysis and the like are supported, and the cue word complexity and professional depth are automatically adjusted according to user roles (investors / analysts). And dynamic evolution: through real-time updating of the knowledge graph and artificial feedback learning, the system can adapt to financial environment changes (such as new supervision policies and emerging analysis methods), and continuously optimizes and generates strategies.

The invention discloses a large language model context capability excitation method and system based on an attention sink point. The method comprises the following steps: firstly, extracting a key context information vector from input data; then, in some specific Transform decoding layers of the model, anchor lexical elements in the input sequence are identified, and attention calculation paths of the anchor lexical elements are separated. In the anchor point path, contextual information is injected into representation of anchor point lexical elements through one-time cross attention calculation, and the result is stored in a key value cache for being reused in the subsequent generation step; and the non-anchor lexical elements keep the original calculation mode. And finally, the model carries out autoregression lexical element generation based on the updated sequence representation until a complete text is output. As a universal module, the method can be seamlessly integrated to any pre-training large language model based on a Transform decoder, and context information of the model is effectively excited and utilized on the premise that extra reasoning calculation overhead is hardly introduced.

The invention discloses a sensitive cue word generation method and system based on parameter sensitivity quantification, relates to the technical field of artificial intelligence security, and aims to solve the problem that sensitive test samples are difficult to generate in integrity verification of a black box large language model. The method comprises the steps of obtaining an original large language model; a comprehensive parameter sensitivity index is constructed, the microscopic sensitivity used for representing tiny parameter modification and the macroscopic sensitivity used for representing large modification such as parameter quantification and pruning are fused, and therefore the sensitivity of cue words is comprehensively quantified; in the continuous embedding space, a gradient optimization algorithm is adopted to maximize the comprehensive index as a target to carry out iterative optimization, and constraints such as semantic rationality are applied to ensure that the generated cue word is natural and smooth; and finally, mapping the optimized embedded vector back to the discrete lexical element sequence to obtain a final sensitive cue word. According to the method, the low-cost and automatic test sample generation is realized, and the accuracy, efficiency and concealment of cloud model integrity verification are remarkably improved.

The invention provides a cue word generation method, computer equipment and a computer program, and the method comprises the steps: obtaining first reply information which is generated by a target model, is used for output and corresponds to first question information, carrying out the blocking processing of the first reply information, and carrying out the caching of a plurality of pieces of first segment information; in response to second question information which is input by the user and belongs to the same dialogue scene with the first question information, retrieving target fragment information associated with the second question information in the multiple pieces of first fragment information, and based on the second question information and the target fragment information, according to a cue word template used for guiding a target model; and creating a cue word corresponding to the second question information to assist the target model in understanding target fragment information required by the context of the dialogue scene so as to generate second reply information. The processing process can be realized by a computer program based on artificial intelligence, namely an intelligent agent, and the intelligent agent can be embedded into an application degree or an operating system such as a browser or an application store to provide an intelligent function in a dialogue form.

The disclosure provides a method and apparatus for generating a word, an electronic device, and a storage medium. The method for generating a word includes: obtaining images corresponding to a word to be processed and a reference word; and inputting the image to be processed into a target font style fusion model to obtain a target word of the word to be processed in a target font style. The target font style is determined based on the target font style fusion model fusing a reference font style of the reference word and a font style to be processed of the word to be processed.

The embodiment of the invention provides a cue word generation method and device, a program product and a storage medium, and the method comprises the steps: obtaining task description information of a target task; performing prompt word generation operation on the task description information by using a pre-trained target network model to obtain a target prompt word; wherein the generation operation comprises the steps that multiple meta prompts are extracted from the task description information, a meta prompt set is obtained, and the multiple meta prompts all comprise the summary of the target task; target mapping operation is executed on the meta prompt set to obtain a candidate prompt word set comprising a plurality of candidate prompt words, and the target mapping operation comprises construction of a mapping relation among the plurality of candidate prompt words and a mapping relation between the plurality of candidate prompt words and preset candidate prompt words; and extracting a target cue word of which the quality feature is greater than a preset threshold value from the candidate cue word set. Through the method and the device, the problem that accurate cue words cannot be generated in related technologies is solved.

The invention discloses a training method of a machine generated text detection model based on prefix enhancement and a machine generated text detection method and device.The training method of the machine generated text detection model comprises the steps that an original text is input into a prefix enhancement mapping module, and a first prefix enhancement prompt feature vector after linear adaptation is obtained; inputting the original text into a word embedding module to obtain an original text feature vector; inputting the prefix enhancement prompt feature vector and the original text feature vector into a feature weighted average module to obtain a first fused feature vector; and finally, a prediction result of the original text is obtained through an output module. And training based on the feature vector after the first fusion, the prediction result, and the difference degree between the current prediction result of the model and the real label. According to the method, a prefix enhancement technology is introduced, and the understanding ability of the model to the input text is enhanced through a specific cue word generation algorithm, so that the accuracy of machine generated text detection is improved.

The invention discloses a model answer generation method and device, equipment and a storage medium, and relates to the technical field of large model application, and the model answer generation method comprises the steps: obtaining a user question of a target user; inputting the user question into a user question and answer model for intention recognition, cue word generation and answer generation to obtain a model answer output by the user question and answer model; and pushing the model answer to the target user to complete user question and answer. According to the method and the device, the requirements of the user can be quickly and accurately understood, so that an accurate direction is provided for subsequent prompt word generation and answer generation, answer deviation caused by misunderstanding of the intention of the user is avoided, personalized prompts can be generated according to the questions of different users, the answers better meet the specific requirements of the user, and the user experience is improved. The pertinence and practicability of the answers are improved, so that the user question-answering model can generate higher-quality and more accurate answers, and the trust and satisfaction of the user to the question-answering system are enhanced.

The invention provides a cue word generation method and device based on a large model, relates to the technical field of artificial intelligence, in particular to the technical field of deep learning, natural language processing and large language models, and can be used for application scenes such as generative search, intelligent document editing, intelligent assistants, virtual assistants and intelligent e-commerce. A specific embodiment of the method comprises the steps of generating question and answer pairs based on question and answer data in a chat page; matching the question and answer pair with a cue word template corresponding to a question in the question and answer pair to generate a first cue word; the question and answer pair is input into a pre-trained cue word generation model, a second cue word is obtained, and the cue word generation model is obtained by taking the sample question and answer pair as input, taking the sample cue word as output and training a large language model; and integrating the first cue word and the second cue word to generate a cue word.

The embodiment of the invention discloses a cue word generation method, a cue word-based dialogue method and a related device. The cue word generation method comprises the following steps: acquiring a plurality of sample question and answer pairs about a target field; according to the initial prompt word and the plurality of question sample texts, obtaining answer training texts corresponding to the question sample texts through a natural language dialogue model; and according to the plurality of answer training texts and the plurality of answer sample texts, adjusting the initial cue word until a preset condition is met to obtain a target cue word. The dialogue method based on the cue word comprises the steps of obtaining a question text and a target cue word, wherein the target cue word is obtained through the method; according to the question text and the target prompt word, an answer text corresponding to the question text is obtained through a natural language dialogue model, and the answer text is related to a target field corresponding to the target prompt word. By adopting the embodiment of the invention, the target cue word can be efficiently generated, and the accuracy of the target cue word indicating that the natural language dialogue model generates the answer text is relatively high.

The invention discloses an intelligent cue word generation evaluation method and system based on multi-component collaboration, and relates to the technical field of artificial intelligence and natural language processing. The method comprises the following steps: acquiring a multi-format text, converting the multi-format text into an input-output pair, and generating a plurality of candidate cue words; after determining a communication mode according to the text form, standardizing cue words according to the structured template of each large language model; calling each platform to generate answer analysis and unify formats, and extracting target contents by utilizing regularization; and carrying out multi-mode evaluation on the candidate cue words, selecting an optimal cue word, and outputting a structured evaluation result and an optimization suggestion based on multiple indexes. According to the method, full-process automatic processing of prompt word generation, optimization and evaluation is achieved, various model platforms, data sets, algorithms and evaluation indexes are supported, and good universality and expansibility are achieved.

The invention discloses an unmanned aerial vehicle image semantic transmission and question-answering system and method driven by a large language model, and an image semantic extraction and quantification module carries out the semantic feature extraction of an original image captured by an unmanned aerial vehicle through a semantic encoder, and discretizes a feature vector through a codebook mechanism, and is used for wireless channel transmission. And the image reconstruction module recovers the transmission image from the semantic level according to the received discrete vector corresponding to the codebook shared by the receiving end and the transmitting end. And the image subtitle generation module takes the image recovered by the image reconstruction module as input, and generates text description information by using a BLIP subtitle generation system. And the cue word generation module generates a section of cue word according to the user task description and the text description information output by the image subtitle generation module. And the large language model question-answering module outputs natural language response to guide the next action of the unmanned aerial vehicle according to the cue word. According to the method, the robustness and efficiency of wireless image transmission under the condition of low signal-to-noise ratio are improved, the interpretability of a question answering system is improved, and the method has a certain practical value.

The invention discloses an underground engineering on-demand ventilation knowledge graph retrieval enhancement generation method and system, and belongs to the technical field of artificial intelligence, and the method comprises the steps of data cleaning and ontology layer modeling, knowledge extraction based on prompt engineering, knowledge graph data filling and storage, storage of an extraction result in a Neo4j graph database, and retrieval enhancement generation of an inference engine. Developing an intelligent question and answer platform, and providing knowledge graph visualization and interactive question and answer functions; the system comprises a data acquisition and preprocessing layer, an ontology and knowledge extraction layer, a graph storage layer, a semantic index and entity link layer, a sub-graph arrangement and cue word generation layer, a generation and reasoning layer and an application and interaction layer. According to the invention, the acquisition and management efficiency of underground engineering ventilation knowledge is improved, the professionality and accuracy of the question-answering system are enhanced, the interface is friendly, knowledge tracing is supported, and convenient experience is provided for users.

The invention provides a dynamic interactive document generation method and device based on generative AI, computer equipment and a storage medium. The method comprises the following steps: receiving multi-modal input data; generating a composite cue word by adopting a cross-modal semantic alignment model of a QWen text encoder and a BriVL image encoder; dynamically adjusting the semantic weight of the prompt word based on a weight formula of a knowledge graph matching degree, a user historical acceptance degree and an AI confidence degree; calling the generative AI model to generate document content; a quality detection module identifies questions and actively inquires a user by adopting a layered interaction strategy; correcting the content through an incremental cue word according to the feedback; and optimizing a cue word generation strategy by adopting a PPO reinforcement learning algorithm. According to the method, the problems of static template limitation, low efficiency of cue words and lack of interactivity in traditional document generation are solved, dynamic and interactive personalized document generation is realized, and the document generation quality and efficiency are remarkably improved.