605 results about "Question generation" patented technology

A user provides a question to be answered from detailed, dense or otherwise complex documents to a processing system that converts the question to a structured query language query and generates an embedding from the question, augmented by temporal data, synopses, themes, or other relevant information or data. The embedding is compared to embeddings generated from documents of a knowledge base to identify documents that are relevant to the question, and to rank such documents for their relevance. Highly ranking documents are combined with the query and provided to a language model that returns an answer to the question. A source for the answer is identified in at least one of the documents. The answer and the identified documents are presented to the user.

The invention discloses a large language model illusion detection-based medical question and answer method, which comprises the following steps: S10, data acquisition: acquiring a question, and generating a plurality of answers for the input question by using a large language model; s20, data preprocessing is carried out on the collected multiple answers given by the large language model; s30, the problem is processed by means of evidence deep learning, and a loss function of the evidence deep learning is obtained; s40, processing the generated pair answers by using structure entropy and enhanced semantic clustering to obtain a structure entropy loss function; and S50, knowledge boundary illusion detection: integrating the loss function of evidence deep learning and the structural entropy loss function to obtain a total weighted loss function, and judging an output final answer by setting a threshold value. According to the method, the big language model is optimized by combining the evidence deep learning theory and the structure entropy, so that the problem caused by the illusion phenomenon in the medical question and answer scene is effectively solved.

The invention relates to a multi-agent cooperation strategy generation method, device and equipment and a medium, and the method comprises the steps: separating acoustic spectrum features and text semantic features of conference voice through environment perception processing, solving a cross-modal information conflict problem, and generating an accurate semantic understanding result; identifying the essence of the problem based on task analysis, associating the responsibility field, and constructing a classifiable problem point set; calling an agent capability library to dynamically match problem requirements, and generating a candidate agent list; quantifying a problem influence range and a decision time limit through weighted emergency scores, and generating a priority-sorted agent sequence; screening and confirming a core problem point and a primary agent; and finally, generating an executable cooperation scheme through multi-agent collaborative optimization. According to the method, the problems of incomplete feature extraction, task allocation delay and resource conflict in the prior art are solved, and the operability and decision-making efficiency of a cooperation strategy are remarkably improved.

The invention discloses a depression risk screening optimization method based on large and small model linkage. The method comprises the following steps: selecting depression related indexes, obtaining interviewee questionnaire data, and preprocessing the data to obtain a scale source database; a depression risk prediction model is constructed, and PHQ-9 measurement results are compared for model training and verification; training a dialogue strategy module of a semantic analysis enhanced fine-tuning training large language model, constructing answer mapping through dynamic question generation and dialogue flow control, and converting a natural language of a user into standardized data required by a small model; training a man-machine interaction reinforcement learning model, generating a depression risk screening result based on a small model, inviting a user to carry out recognition degree evaluation, and dividing feedback into two types of recognition and question; for different feedbacks, strengthening or correcting the current interaction strategy and prediction logic, and storing the audited data as high-quality data to a training database by the system for subsequent large model fine tuning; and outputting a result and performing result interpretation and suggestion by using the semantic analysis reinforced fine-tuning large language model. Hierarchical early screening of depression risks is carried out based on large and small model linkage.

The invention discloses a progressive topic generation method based on semantic analysis and a knowledge graph. Performing preprocessing and semantic analysis on the question setting demand text, and extracting a necessary keyword set corresponding to the core knowledge points and an optional determiner set corresponding to the additional conditions; carrying out concept mapping in a college professional knowledge graph and associating with a course outline, constructing a hierarchical semantic constraint framework containing hard constraint and soft constraint, and carrying out consistency detection; adopting reverse index hard matching recall and knowledge graph soft extension recall to obtain candidate materials, and inputting the candidate materials into a field fine-tuning large language model to generate candidate questions; reordering is performed through multi-target learning ordering, teaching logic verification and quality evaluation are executed, and final questions are output; user feedback is received to form an incremental sample, and the generation model and the sorting model are updated, so that the accuracy, diversity and controllability of question generation are improved, and closed-loop optimization is supported.

The invention relates to an automatic full-process intelligent recruitment system based on competency evaluation, and belongs to the technical field of intelligent interview. The system comprises a data acquisition module, a question generation module, an interactive execution module, a dynamic questioning module, a dimension switching module, an anomaly monitoring module, a dual-camera verification module, a score report module and a context maintenance module. Through cooperative work of the modules, the system can realize full-process automation from candidate data collection to final scoring report generation. The data acquisition module is responsible for collecting various information of candidates and providing basic data for subsequent interview links. Automation, intelligentization and standardization of the recruitment process are realized, and the recruitment efficiency and quality are effectively improved. By generating interview questions and dynamic questions in real time, the system can more accurately inspect ability performance of candidates in different competency dimensions.

Computer-based techniques for performing systematic literature reviews are provided. Some embodiments include an SLR system including various components that interoperate to generate regulation-compliant SLR reports regarding an issue based on user-defined parameters. In several embodiments, the SLR system may integrate various artificial intelligence techniques to facilitate generation of SLR reports. For example, various SLR systems disclosed hereby may utilize generative pre-trained transformers to assist in aspects of systematic literature reviews, such as literature database queries, literature screening, data question generation, level of evidence classification, qualitative assessments, data extraction, and report generation.

The invention discloses a cue word generation method and device of a large language model and electronic equipment, and relates to the technical field of information processing.The method comprises the steps that firstly, a malicious problem generation template data set is constructed based on a preset malicious problem data set, or constructing a cue word attack variant template data set based on a preset cue word attack template data set; then, the malicious problem generation template data set or the cue word attack variation template data set is input into the large language model, and a cue word data set is generated; through the method, the cue word can be automatically generated by using the large language model, diversified application scenes can be covered, the risk identification capability for different attack scenes is improved, and the problem of low efficiency caused by manual cue word writing is avoided.

The invention provides an agent illusion correction method and device. The method comprises the following steps: firstly, analyzing and globally planning a problem input by a user, generating an execution plan comprising at least one subtask, performing reasoning circulation and retrieval enhancement based on the execution plan, generating an enhanced context evidence set, then performing screening and context optimization processing on the enhanced context evidence set, generating an optimized context, and finally, performing context optimization processing on the optimized context. And then, generating an initial answer based on the optimized context and the question, carrying out factuality and logic consistency closed-loop verification on the initial answer to detect whether illusion exists or not, if the illusion is detected, correcting the initial answer, generating a corrected answer, and recording the illusion event and the correction process to the reflection knowledge base. According to the method, self-correction and continuous optimization are realized through a closed-loop mechanism of problem decomposition, global planning, reasoning circulation, retrieval enhancement and optimization and correction reflection, so that the reliability and interpretability of agent answering are improved.

The invention relates to the technical field of human resource management, and provides a one-stop talent screening method and system. The method comprises the steps of performing text analysis on a job seeker resume, identifying structured information in the job seeker resume, performing weight distribution on the analyzed information through a preset post competency model, and generating a resume analysis result containing a candidate and target post matching degree score; consultation information about enterprise information, position treatment and office environment of the job seeker is obtained, the consultation information is analyzed to obtain a question intention of the user, and response content corresponding to the question intention is generated; performing semantic analysis on the communication record corresponding to the job seeker, and identifying the job hunting willingness level of the job seeker; and dynamically generating personalized interview questions through an interview question generation model in combination with the matching degree score and the job hunting willingness level to complete talent screening. The method is suitable for full-process automatic processing of resume screening, intelligent communication and adaptive interview in the enterprise recruitment process.

The invention belongs to the technical field of artificial intelligence, and particularly relates to a multi-modal mixed interview question generation system and method based on artificial intelligence. According to the method, customized interview questions are provided for candidates with different backgrounds and different skill levels by dynamically selecting questions based on candidate resumes and knowledge maps, the question difficulty and knowledge emphasis are automatically adjusted through multiple rounds of answering effects and interviewer labeling data, the effectiveness and flexibility of interview evaluation are improved, and the interview evaluation efficiency is improved. Answering results and behavior anomaly detection are fused, knowledge mastering is evaluated, potential non-behavior factors can be found, manual question screening time is shortened through an automatic process, consistency of interview experiences of different candidates is guaranteed, subjective prejudice is reduced, new knowledge documents and post description can be accessed at any time, a multi-modal graph is continuously iterated, and the method is high in practicability and high in practicability. And changes of new technical fields and new post requirements are adapted.

The invention discloses a data construction and fine tuning method for a knowledge retrieval model in the field of energy and power, and the method comprises the steps: carrying out the preprocessing of document data in the field of energy and power, and segmenting the document data into document segments suitable for the input of a retrieval model; performing question generation based on a large language model, generating a question-document pair positive sample set according to document fragments, and sampling to generate a question-document pair negative sample set; and in combination with contrast learning of the positive sample set and the negative sample set and LoRA parameter fine tuning, training a retrieval model, and performing problem retrieval by using the trained retrieval model. According to the method, high-quality problem-document pairs and challenging negative samples are generated, a comparative learning technology is combined, the retrieval model is optimized, the retrieval accuracy of the vector model in the field is remarkably improved, specific retrieval requirements in the energy power field can be deeply understood, and retrieval suggestions which are highly reliable and conform to habits in the field are generated.

The invention provides a method, a device and equipment for generating a multi-round dialogue corpus and training and testing a large language model. The method for generating the multi-round dialogue corpus comprises the following steps: acquiring first question information; vectorizing the first question information to obtain a first question vector; querying a target preceding text vector of which the similarity with the first question vector meets a preset similarity condition from a vector database in which a plurality of groups of data pairs are stored; any group of data pair comprises a preceding text vector generated according to a preceding text of a question of the user in a historical interaction process with the language model, and a following text of the question in the historical interaction process; obtaining question generation constraint information based on the question following text corresponding to the target preceding text vector; calling the large language model to generate second question information after the first question information by taking the question generation constraint information as a constraint condition; and generating a multi-round dialogue corpus based on the first question information and the second question information.

The invention provides a vertical field data construction method based on a large model, which belongs to the technical field of data processing and artificial intelligence, and comprises the following steps: converting a vertical field source document into an intermediate format text, and segmenting the intermediate format text into a plurality of text blocks; inputting the text blocks into a pre-trained generative language model, guiding the pre-trained generative language model according to pre-designed cue words to generate a plurality of candidate questions according to the content of the text blocks, and performing preliminary screening and fine screening on each candidate question to obtain a question set; pre-defining a mode of a knowledge graph according to field characteristics of the vertical field, processing all text blocks based on an information extraction model, and constructing a field knowledge graph; and performing local context retrieval on each final question in the question set based on the text block of the question source, performing global knowledge retrieval based on the domain knowledge graph, and generating a final answer and a final thinking chain. The method is suitable for different vertical fields, the data quality can be effectively improved, and the problem generation accuracy is guaranteed.

The invention discloses a feedback type retrieval enhancement generation method for refining and enhancing retrieval, which can give the confidence degree of answers while answering questions, and further process the answers lacking confidence. According to the method, the reliability of answers generated based on retrieval content is measured by introducing a confidence coefficient evaluation mechanism based on a retrieval strategy of first prediction and then matching, when the confidence coefficient is lower than a preset threshold value, it is indicated that a current retrieval result is insufficient to support accurate answering, at the moment, refined and enhanced retrieval is activated, refined questions are generated for original questions, and the accuracy of the questions is improved. Therefore, the understanding and retrieval effects on questions are enhanced, and the answering accuracy is improved.

A computerized method has the steps of: generating one or more queries from an input question; generating one or more outputs; and outputting an answer based on the one or more outputs. Said generating the one or more outputs has the steps of: for each query, forming a reasoning tree with the query being a root node and a current node, generating one or more candidates as leaf nodes of the current node, by inputting a reasoning path from the root node to the current node into a foundation model, searching the reasoning tree using an artificial intelligence model to select a leaf node as the current node, and repeating said generating the one or more candidate nodes and said searching the reasoning tree until a termination condition is met, and using an updated reasoning path from the root node to the current node as the output for the query.

The invention provides a big language model knowledge graph question answering method and system combined with semantic correction, and the method comprises the steps: generating a logic form according to an input question through a fine-tuned open source big language model, and executing a query statement corresponding to the logic form to obtain an answer; if the answer cannot be obtained by the query statement corresponding to the execution logic form, extracting a main line entity and a relationship from the non-executable logic form, and performing semantic similarity comparison on the extracted relationship and a relationship in the knowledge graph through an unsupervised dense searcher to generate a candidate relationship set; based on the main line entity and the candidate relation set, iteratively retrieving triples in a knowledge graph to construct a reasoning path; and screening the constructed reasoning path by using a closed source large language model, or selecting a tail entity in the multi-answer path, and outputting a final answer. According to the method, the non-executable logic form is corrected, the semantic analysis effect based on the large language model is optimized, and efficient knowledge graph question answering is achieved.

The invention discloses an intelligent agent-based large model education risk problem generation method, which is characterized in that a dynamic student intelligent agent is constructed to simulate a real learning behavior, and a potential risk problem in an education scene is automatically identified and generated in combination with the generation capability of a large language model; the method specifically comprises the steps of constructing a multi-dimensional student agent, constructing a risk problem generation rule base, generating potential risk problems and risk grade classification, optimizing risk problem generation quality, establishing an educational risk problem database, continuously updating and iterating and the like. Compared with the prior art, the method has the advantages that the safety and reliability of an AI education product are remarkably improved, the risk identification accuracy is remarkably improved along with the use time, an original solution is provided for safe development of the education science and technology field, healthy development of artificial intelligence in education application is guaranteed from the technical source, and the method is worthy of popularization and application. The method is widely applied to the fields of education content security auditing, self-adaptive learning system risk prevention and control and the like, and has good application prospects.

The embodiment of the invention discloses a question answering method and device based on retrieval enhancement generation, equipment and a medium, and relates to the technical field of large language model question answering. The method comprises the steps of obtaining a target question input by a user; on the basis of keywords in the target question, keyword retrieval is carried out on each text in a pre-established knowledge base; each text in the knowledge base corresponds to a text vector; retrieving a text vector similar to the target vector in a pre-established knowledge base, and determining a text corresponding to the retrieved text vector; the target vector is a vector generated based on a target problem; and processing the target question and a retrieval result obtained in the knowledge base based on the large language model to obtain an answer corresponding to the target question. According to the technical scheme, text retrieval and vector retrieval are carried out in the knowledge base, the retrieval result with higher timeliness and higher accuracy is obtained, and then the answer output by the large language model can be obtained based on the retrieval result and the target question.

The invention discloses an intelligent agent system and a control method thereof, and relates to the technical field of natural language processing. The system comprises an execution layer, a planning layer and an auditing layer, the planning layer identifies and extracts innovation task meta-information, constructs a task tree to complete operations such as hierarchical clustering, and determines a task execution path; the execution layer calculates the semantic similarity between the content of the knowledge graph and the user innovation question, determines the optimal question and answer, extracts heuristic information, and decomposes the heuristic information into sub-questions to construct a dependency graph; generating an answer set based on the graph solving sub-problems, and integrating answers by using a genetic algorithm to obtain an overall solution; and the auditing layer performs multi-dimensional scoring on the scheme, and determines a structured scheme report and optimization suggestions for users to use according to a scoring result. The method has the capabilities of structured reasoning, problem recursive decomposition and scheme closed-loop optimization, can generate a multi-dimensional evaluation result, and efficiently realizes systematic modeling of a clear path for analogy heuristic information support problem solution.

Techniques for generating a natural language prompt to further a goal of a dialog, are described. During a dialog, the system receives one or more user inputs including a user question, a user response to the question, and a request to generate a further question following the response. The system determines ASR output data corresponding to the user inputs, and determines dialog history data of the dialog. Using the ASR output data and the dialog history data, the system determines a category and an explanation of relevance corresponding to the category. Using the ASR output data, the dialog history, the category, and the explanation, the system determines the further question to be output to the user.

The invention discloses a robot interactive target object grabbing system and method, and the system comprises a visual positioning module which is configured to obtain a current scene image and an initial grabbing instruction, and carries out the prediction to obtain a candidate region coordinate set of a to-be-grabbed target object; the question generation module is configured to sample a candidate region coordinate from the candidate region coordinate set as a candidate target region, and generate a corresponding natural language question based on the scene image; the answer understanding module is configured to score the matching degree of each candidate area in response to the answer of the user to the natural language question; and the collaborative reasoning module is configured to integrate the probability of the coordinate of each candidate region obtained by the visual positioning module and the matching degree score of each candidate region by the answer understanding module, and output a final target region position. According to the method, the limitation that a traditional method depends on a preset template and an explicit category is broken through, and the target object to be grabbed by a user can still be accurately recognized in a complex scene.

The invention discloses a local knowledge base RAG method based on Bayesian reasoning, and belongs to the technical field of information retrieval. The method comprises the steps of obtaining all knowledge data of a local knowledge base, performing paragraph classification and coding on the knowledge data to obtain a paragraph set, and calculating the semantic probability of each paragraph in the paragraph set; obtaining a target professional vocabulary set of the target question, and calculating the semantic probability of each vocabulary in the target professional vocabulary set in each paragraph and the semantic probability of all vocabulary in the target professional vocabulary set in each paragraph in the paragraph set Calculating the conditional probability of each vocabulary in the target professional vocabulary set in each paragraph based on the occurrence frequency; and calculating the conditional probability of the target professional vocabulary set in each paragraph by adopting a Bayesian formula, sorting to obtain a conditional probability sorting result, selecting the paragraphs of which the total word number does not exceed a preset threshold value as a target paragraph set, and generating target retrieval information based on the target paragraph set and the target question. According to the method, the accuracy and reliability of question retrieval are improved.

The invention discloses an automatic thinking chain prompt generation method based on black box optimization and vulnerability quantification. The method comprises the following steps: acquiring an unlabeled training data set; screening a high-difficulty problem subset through a difficulty judgment module, and generating an annotation data set; generating a plurality of reasoning chains for each question in the annotation data set by using a large language model, and reserving the reasoning chains consistent with correct answers to form an example library; a variance reduction strategy gradient estimator is adopted to optimize an inference chain selection strategy, and a common style prompt is generated; and performing style diversification processing on the common style prompt through a novel format prompt module to generate an anti-vulnerability automatic thinking chain prompt.

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 relates to the technical field of education, and discloses an AI-based learning weakness promotion training test question generation system, which comprises a data acquisition module used for acquiring emotional data and cognitive load data of students in real time, the emotional data comprises emotional fluctuation information of the students, and the cognitive load data comprises emotional fluctuation information of the students; the cognitive load data comprises question solving time and question answering error deviation information of the students; the emotion and cognition analysis module is used for analyzing the current emotion fluctuation and cognition load of the student based on the collected emotion data and cognition load data, and generating a corresponding emotion fluctuation value and a cognition load value; and the test question generation module is used for dynamically generating test questions suitable for the current learning state of the student according to the emotion fluctuation value and the cognitive load value of the student, and adjusting the difficulty and the type of the questions. According to the method, the difficulty and the type of the test questions are dynamically adjusted by combining emotion fluctuation and cognitive load analysis, so that cognitive overload and emotion pressure are effectively avoided, and the learning efficiency and the learning motivation are improved.

The invention belongs to the technical field of automatic generation of face test questions, and particularly relates to a high-precision AI face test question generation method based on self-distillation and an industry knowledge base. According to the method, by dynamically adjusting the question difficulty, the actual ability of an interviewer can be reflected more accurately, the efficiency and accuracy of the interview process are improved, meanwhile, based on self-distillation and industry knowledge base-based interview question generation, it is ensured that interview questions are highly matched with post requirements, subjective evaluation errors are reduced, reliable data support is provided for recruitment decision making, and the method is suitable for popularization and application. According to the method, the intellectualization and individuation of the interview process are realized, and in addition, the difficulty and content of questions can be flexibly customized for different post characteristics, so that the pertinence and distinction degree of interview questions are further improved, the interview process of an interviewer is more efficient, the ability of the interviewer is accurately evaluated, and the recruitment quality of an enterprise is guaranteed.

The invention discloses a vertical field objective test data set construction method, system and device and a medium, and relates to the technical field of natural language processing, the construction method comprises the following steps: obtaining text data, and carrying out knowledge extraction and arrangement on the text data to obtain formatted text information; taking the formatted text information as input, and performing question generation, correct answer generation, interference option generation and analysis generation through a pre-established large model to obtain test data; performing quality detection on the obtained test data, and screening out the test data meeting the quality detection requirements; and performing self-inspection on the test data meeting the quality detection requirements, and retaining the test data passing the self-inspection to obtain a vertical field objective test data set. According to the method, the vertical domain test questions can be automatically generated on a large scale, the dependency degree of testers on professional domain knowledge is reduced, meanwhile, the labor cost is saved, the problem difficulty is controllable, and the professionality and accuracy of test question generation are improved.

The invention provides a wrong question book intelligent learning system and method based on OCR and similarity analysis. The method comprises the following steps: S1, carrying out wrong question picture preprocessing and feature extraction; s2, multi-dimensional similarity calculation is associated with knowledge points; s3, knowledge point error rate statistics and error pattern analysis; and S4, generating and pushing personalized exercises. According to the method, intelligence and individuation of error question management are realized through multi-technology fusion, the bottleneck of current error question management is broken through, and the learning efficiency and the knowledge mastering depth are improved.

The invention discloses a reward model training method, a question evaluation method, an electronic device and a storage medium, and relates to the technical field of large models.The reward model training method comprises the steps that a sample data set and a target cue word are obtained, and the sample data set comprises one or more text samples; inputting the target prompt word and the sample data set into a first question generation model, and generating a first question corresponding to each text sample; inputting the target prompt word and the sample data set into a second question generation model, and generating a second question corresponding to each text sample; wherein the problem generation capability of the first problem generation model is superior to the problem generation capability of the second problem generation model; constructing comparison data based on the text sample, the target prompt word, the first question and the second question; performing comparative learning on a preset reward model based on the comparative data to obtain a target reward model; wherein the target reward model is used for evaluating the problem quality. According to the invention, the quality evaluation problem can be solved.