301 results about "Question generation" patented technology

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 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 embodiment of the invention discloses a strategy model training method and device, a strategy generation method and device, a storage medium and a terminal. Firstly, a set of sample answers are generated for a target question through a preset large language model to serve as references. And during training, inputting an answer generated by the current strategy model and a sample answer into the evaluation model for comparison, and outputting a good and bad sorting result. The ranking is quantized as a reward value whose size is positively correlated with the degree to which the current answer is superior to the sample answer. And finally, the system adjusts strategy model parameters according to the reward value and guides the strategy model parameters to be continuously optimized. According to the method, scoring according to standard answers is replaced with relative sorting, and the problem that open questions lack clear judgment standards is solved. The method has the beneficial effects that the training data cost and labeling dependence are remarkably reduced, so that the model can realize stable and autonomous efficiency improvement in the vertical field, and a self-driven benign evolution cycle is formed.

The invention belongs to the technical field of education artificial intelligence and deep learning model optimization, and discloses a thinking tree enhancement-based test question knowledge system intelligent labeling method and system.The thinking tree enhancement-based test question knowledge system intelligent labeling method comprises the steps of collecting question data by introducing a thinking chain enhanced data generation mechanism, and generating a high-quality training sample; and a control mechanism is set, a question generation process is optimized, and the generated question is ensured to accord with teaching specifications in the aspects of knowledge point coverage, grade adaptability, difficulty matching and the like. Through a text encoder based on comparative learning optimization, the model can accurately carry out semantic alignment on questions and knowledge point labels, and label path information is fused through a double-coding mechanism, so that the hierarchical relationship between the labels and the capture capability of semantic dependence are improved. Finally, the constructed multi-label prediction model significantly improves the accuracy and generalization ability of knowledge point labeling, and can provide accurate support for personalized learning recommendation and teaching resource allocation.

The invention discloses a multi-round dialogue system and method based on conversion from a natural language to an SQL, and relates to the technical field of artificial intelligence, and the system comprises a user interaction module which is used for supporting a user to input a query problem and displaying a corresponding SQL query result; the context processing module is used for screening the effective dialogue history of the current question and re-integrating the effective dialogue history into a complete dialogue; the ambiguity processing module is used for identifying an entity from a dialogue history to define a user intention, processing a fuzzy keyword in a current question and guiding the user to complement a query condition; the re-splicing module is used for reconstructing a complete dialogue according to a time sequence, eliminating ambiguity, generating a summary through a large model, and combining the summary with a current problem to construct a complete problem; the SQL generation module is used for performing semantic analysis on the complete problem and outputting an SQL query instruction with the highest matching degree; and the execution and rendering module is used for executing the instruction on the target database and returning a query result. The conversation processing capability can be improved.

The invention discloses a classroom content evaluation system based on student questions and answers, and the system comprises a classroom information collection module, a data processing module, a classroom question generation module, a student answer interaction module, a semantic analysis module, a classroom evaluation generation module, a classified storage module, and a teaching strategy optimization module. The classroom information acquisition module monitors and acquires videos, audios, blackboard-writing texts and courseware images in real time, the data processing module converts multi-modal data into structured texts through voice recognition and OCR technologies, and the classroom question generation module generates a question set based on teaching content. The student answering interaction module receives answering data in a text, voice or image form, and the semantic analysis module analyzes teaching texts and answering contents and marks knowledge blind areas; the system has the advantages that multi-modal teaching content is integrated in real time, adaptability problems are dynamically generated, knowledge blind areas are accurately recognized, and the classroom effect is quantitatively evaluated in a multi-dimensional mode.

A method of using a computing device to improve an answer generated by a natural language question and answer system includes receiving, by a computing device, multiple questions in a natural language question and answer system. The computing device further generates multiple answers to the multiple questions. The computing device still further constructs a new training set with the generated multiple answers, where each answer is compared with a corresponding question of the multiple questions. The computing device additionally augments the new training set with one or more tokens delimiting a span of one or more of the generated multiple answers. The computing device further trains a new natural language question and answer system with the augmented new training set.

The invention provides a dynamic interview test question generation method, system and device based on real-time dialogue analysis and adaptive RAG and a medium, and the method comprises the steps: firstly creating a competency knowledge graph according to recruitment post information, and initializing a state machine; then monitoring interview dialogue streams, analyzing answers of candidates by using an AI large model, and performing evidence intensity and logic consistency verification based on dialogues and resumes of the candidates; updating the state of the corresponding node by using a state machine based on the result of the AI large model analysis, determining the investigation intention of the next step, and generating a plurality of alternative interview questions according to the investigation intention; continuously monitoring the interview conversation stream until the interview is finished; and finally, generating a structured evaluation report based on the competency node information of the interview state machine. According to the method, the conversation content is monitored in real time, the state machine and the AI large model are utilized, the answers of candidates are dynamically analyzed in the conversation process, the questions are generated, interview is converted into accurate strike, and the coverage rate of core ability points is greatly increased.

A computer-implemented method is provided to preforming bagging adversarial training for question-answer ranking models using neural networks. The method includes generating first question and answer (QA) pairs for a given question as a first training dataset to train a QA ranking model to build a pre-trained QA ranking model. A generative adversarial network (GAN) includes a generator and a discriminator configured to produce adversarial inputs to provide an updated training dataset. The pre-trained QA ranking model is retrained with the updated training dataset with the bagging adversarial training process. A plurality of trained models is sampled to generate a bagged model ensemble as a final trained QA ranking model for QA ranking tasks.

According to various aspects, systems and methods are provided for automatically matching candidates to job openings. The system may obtain a job request and determine recommended candidates. The recommended candidates may be determined by identifying candidate profiles based on the job request; providing, as inputs to a trained machine learning model, the job request and a first set of questions related to the job request; generating, using the trained machine learning model, a first set of answers based on the job request and the first set of questions; providing, as inputs to the trained machine learning model, the candidate profiles and a second set of questions related to the candidate profiles; generating, using the trained machine learning model, second sets of answers based on the candidate profiles and the second set of questions; and determining the recommended candidates based on the first and second sets of answers.

Technology is disclosed for programmatically generating procedures based on historical conversation records and providing the procedures to users to resolve similar issues. In one implementation, an input instruction is generated to cause a language model to determine resolved historical conversation records from historical conversation records. A second input instruction is generated to cause a language model to generate procedure documents from the resolved historical conversation records. The second input instruction includes the resolved historical conversation records and a procedure generation prompt instructing the second language model to (1) extract one or more issues from each resolved historical conversation record, (2) generate a corresponding issue description of each issue, (3) generate a corresponding step-by-step procedure resolving each issue, and (4) generate a corresponding issue resolution description for each issue. The procedure documents are stored in a knowledge base to provide the step-by-step procedures to users to resolve similar issues.

The invention provides a dialogue method, device and equipment based on a large model and a storage medium, and the method comprises the steps: generating question and answer data for a target domain through a self-game large model, and the question and answer data comprises the input and output of a forward reasoning stage, and the input and output of a backward reasoning stage; training and generating a target model based on the question and answer data, the target model being used for performing forward reasoning and backward reasoning for input data in the target field and generating corresponding forward output data and backward output data; in response to a target question which is input by a user and corresponds to the target field, calling the target model to process the target question, and generating a target forward reasoning answer and a target backward reasoning answer; and determining a target reply in combination with the target forward reasoning answer and the target backward reasoning answer, and outputting the target reply in a streaming manner.

A question generation model training method, includes: obtaining a historical complex question, an answer corresponding to the historical complex question, and a historical document-based knowledge base corresponding to the historical complex question, wherein the historical document-based knowledge base includes at least one historical document related to the historical complex question; extracting an entity term related to the historical complex question from the historical document, constructing a simple question based on the entity term, and determining a plurality of historical knowledge points based on the simple question and the historical complex question; and training a question generation model based on the historical document and the plurality of historical knowledge points by using a preset loss function, to obtain a trained question generation model, wherein the question generation model is used to generate a historical complex question corresponding to the historical document.

The invention discloses a question recommendation method and a related device. The method comprises the steps of performing modal classification on historical question and answer content to obtain a modal classification result of the historical question and answer content; when the modal classification result is a multi-modal category based on the text and the image, obtaining a historical question and answer text and a historical question and answer image in the historical question and answer content; and inputting the historical question and answer text and the historical question and answer image into a multi-modal question and answer model to generate recommended questions, and outputting a plurality of candidate recommended questions, related to the historical question and answer text and the historical question and answer image, of the historical question and answer content. According to the method, when it is judged that historical question and answer content belongs to a text and image-based multi-modal category, historical question and answer texts and historical question and answer images in the historical question and answer content are obtained, and multiple candidate recommendation questions related to the historical question and answer texts and the historical question and answer images are generated by using a multi-modal question and answer model; the correlation between multiple candidate recommendation questions and historical question and answer contents can be improved, so that the question recommendation accuracy and diversity are improved.

The invention relates to the technical field of artificial intelligence education, in particular to a heuristic teacher observation and evaluation AI support system based on Prompt engineering and RAG collaborative enhancement. According to the system, infant observation records are subjected to standardization processing through a data processing module, then large language models are called in sequence through four professional Prompt templates, and heuristic thinking question generation, deep inquiry analysis, behavior disassembly and target matching based on the RAG technology and synchronous generation of educational strategies and parent suggestions are achieved respectively. And a complete observation-reflection-evaluation-strategy closed-loop processing flow is formed. Through cooperative enhancement of Prompt engineering and RAG technology, automatic analysis and deep professional reflection guidance of observation records are realized, system processing efficiency and analysis depth are improved, error propagation is avoided by adopting an independent parallel architecture, and continuous improvement of system performance is ensured through a continuous optimization mechanism.

The system according to this embodiment aims to provide quick and accurate answers to questions about the news. [Solution] The system according to the embodiment comprises a reception unit, a generation unit, and a provision unit. The reception unit receives questions from the user. The generation unit generates answers based on the questions received by the reception unit. The provision unit provides the answers generated by the generation unit to the user.

The invention discloses a prompting method and system for enhancing the implicit reasoning ability of a large language model, and the method comprises the steps: receiving an original context, and generating a forward reasoning problem and a backward reasoning problem based on the sentence of the original context; the forward reasoning problem and the backward reasoning problem are screened, problems which are related to original context semantics and have logic values are reserved, and an intermediate reasoning problem set used for auxiliary reasoning is generated; combining the intermediate reasoning problem set with the original task input, and constructing an enhancement prompt; and inputting the enhancement prompt into the large language model and obtaining an answer. According to the method, a potential causal logic chain is complemented for the model, so that explicit and implicit information can be fused more sufficiently, the reasoning accuracy and robustness are improved, and the implicit information identification capability is enhanced; and the reasoning ability can be enhanced only by prompting the project without retraining or fine tuning of the model.

An object of a system according to an embodiment is to provide high-quality learning support in response to individual learning needs of students.SOLUTION: A system according to an embodiment includes a question reception unit, an advice generation unit, an instruction generation unit, an effect measurement unit, a model answer generation unit, and a visual information generation unit. The question reception unit receives a question from a student. The advice generation unit generates advice based on the question received by the question reception unit. The guidance generation unit generates learning guidance based on the advice generated by the advice generation unit. The effect measurement unit measures the effect based on the instruction generated by the instruction generation unit. The model answer generation unit generates a model answer based on the effect measured by the effect measurement unit. The visual information generation unit generates visual information based on the model answer generated by the model answer generation unit.SELECTED DRAWING: Figure 1

The invention discloses a multi-modal large model reasoning method, device and equipment based on generation understanding collaboration. Comprising the steps of receiving a to-be-understood target image and a corresponding text question; generating an editing prompt based on the target image and the text question, wherein the editing prompt is used for indicating an operation strategy for processing the target image; calling a generation branch of a unified multi-modal model, and generating an auxiliary image based on the editing prompt; and constructing input information based on the auxiliary image, calling the understanding branch of the unified multi-modal model to execute reasoning, and obtaining an answer corresponding to the text question. According to the visual understanding method, retraining and external tools are not needed, the model can construct visual thinking through controllable generation, the self-generation capacity serves as an internal reasoning step to complement visual evidence, and reasoning accuracy and robustness are improved through the evidence.

The invention discloses a multi-modal and dynamic retrieval enhancement-based welding process knowledge base construction method, which comprises the following steps of: slicing a process card, namely dynamically slicing process card data and generating a multi-granularity Embedding vector; constructing a hybrid index, wherein the hybrid index comprises a text field, a vector field and a process metadata field; performing mixed retrieval, generating Query Embedding for questions input by a user, filtering in combination with process metadata, and retrieving the first K associated slices; and enhancement generation: generating an answer on a display interface based on the retrieval result, and outputting the answer containing the process card number and an entry corresponding to the answer. According to the method, the retrieval accuracy can be remarkably improved, the probability that the generated result is inconsistent with the knowledge base is effectively reduced, the traceability of the generated result is ensured, and the problem that traditional document cutting is not matched with a process card is solved.

The invention provides a question reply method and device and electronic equipment, and relates to the technical field of artificial intelligence such as human-computer interaction, natural language understanding, large models and light weight. The method comprises the steps of obtaining a to-be-processed question input by a user in a current session; a plurality of alternative models associated with the to-be-processed problem are utilized to process the to-be-processed problem in parallel to obtain a plurality of candidate replies, the alternative models comprise at least one first-class model and at least one second-class model, and the parameter scale and / or single call cost of the first-class model are / is lower than that of the second-class model; determining a target model in the plurality of alternative models according to behavior information of the user for the plurality of candidate replies; and during the duration of the current session, generating corresponding reply contents for the input subsequent questions by using the target model. According to the method, the target model conforming to user preferences can be rapidly and clearly determined by simultaneously presenting the behavior information of the multiple candidate replies to the multiple alternative models by the user, and the interaction turns and the clarification cost are reduced.

The invention discloses a recommendation question generation method and system, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence and intelligent question answering. Comprising the following steps: collecting a session record set containing retrieval knowledge fragments of a user; based on session records in a specified time window, aggregating according to knowledge files and calculating a hot index to form a candidate knowledge file list; traversing the candidate knowledge file list, and generating candidate recommendation questions by using a large language model; extracting a professional label sequence concerned by the user, and constructing professional trend description in combination with the organization description; in response to a new session initiated by the target user, screening a personalized first recommendation question from the candidate recommendation questions; establishing a session in response to the user selecting the first recommended question or the autonomously input question; and providing an answer in the session by adopting a retrieval enhancement generation technology, and generating a new second recommendation question in real time based on the context. The question recommendation relevance and the user experience of the intelligent question-answering system in the professional field are effectively improved.

To provide a system for supporting an examinee to study an examination by using generative artificial intelligence.SOLUTION: The system includes a user interface means for inputting a school of choice and basic information of an examinee, an examination question generation means for automatically generating examination questions based on the school of choice information of the examinee, an analysis means for analyzing a trial result answered by the examinee and visualizing an unskillful field and a weak point, an answer explanation means for generating and displaying an explanation based on an analysis result, a teaching material recommendation means for recommending an online teaching material suitable for a learning situation of the examinee, and a similar question generation means for automatically generating similar questions based on the unskillful field of the examinee.SELECTED DRAWING: Figure 1

The invention discloses a subjective question automatic generation method based on a T5 neural network model, solves the problem of subjective question automatic generation in an end-to-end mode, and relates to the crossing field of artificial intelligence and intelligent education. Firstly, a Google T5 neural network model is used for decomposing a subjective generation process into three sub-tasks of context abstract, question generation and answer generation based on a T5 model by adopting a step-by-step refinement method based on a prefix task generalization ability, so that the reliability of automatic generation of subjective questions is improved. And secondly, in order to obtain a derivable soft abstract and a soft question in the training process of the model, approximately fitting a non-derivable One-hot vector by using the probability distribution of the generated abstract and the subjective question, so that joint training of three sub-tasks becomes possible. And finally, the model completes fine tuning of T5 model parameters through joint training of three sub-tasks, the generalization ability of the model is improved, and the problem of automatic generation of subjective questions is solved in a more effective manner.

This application discloses a question generation method, apparatus, storage medium, and electronic device, relating to the field of artificial intelligence technology. The method includes: acquiring English materials and English question types; generating corresponding question stems and options using a large-scale question generation model based on the English materials and question types; wherein, during the generation of question stems and options, a chain-like self-checking long-chain guidance strategy guides the large-scale question generation model; if a failure signal is detected during the generation of question stems or options, a retry node is triggered, and dynamic adjustments are made at the task template layer, large-scale model variable layer, and process layer according to the type of failure signal, and the question stems and options are regenerated using the large-scale question generation model; if no failure signal is detected during the regeneration of question stems or options, the English question is output based on the regenerated options and question stem. This application can improve the accuracy and generation efficiency of English exam questions.

The application discloses a progressive question generation method based on semantic analysis and a knowledge graph. The question generation demand text is preprocessed and semantically analyzed, the core knowledge point corresponding essential keyword set and the additional condition corresponding optional limiting word set are extracted, the concept mapping is carried out in the college professional knowledge graph, the curriculum outline is associated, the hierarchical semantic constraint framework containing hard constraint and soft constraint is constructed and consistency detection is carried out, the candidate materials are obtained by using the inverted index hard matching recall and the knowledge graph soft expansion recall, the candidate questions are generated by inputting the field fine-tuning large language model, the final questions are output by carrying out multi-objective learning sorting and reordering, teaching logic checking and quality evaluation, the incremental samples are formed by receiving user feedback, the generation model and the sorting model are updated, the accuracy, diversity and controllability of the question generation are improved, and closed-loop optimization is supported.

This invention belongs to the field of artificial intelligence technology. The embodiments of this invention provide a fully automated interview assistance method, system, and device based on a large language model. First, it acquires recruitment requirements, initial interview questions, and multimodal data of job seekers from the recruitment end to construct a multimodal dynamic knowledge base. This multimodal dynamic knowledge base includes content dynamic mechanisms, structure dynamic mechanisms, and iterative dynamic mechanisms, used to update the knowledge base content and sub-question sequences, update the structure of the knowledge graph in the multimodal dynamic knowledge base, and optimize sub-question generation and retrieval strategies, respectively. Then, based on the multimodal dynamic knowledge base, it determines the job seeker's structured question set, and subsequently determines the job seeker's interview assistance strategy. This invention, through three update mechanisms, makes knowledge application more closely aligned with actual interview scenarios, overcoming the shortcomings of traditional static and rigid knowledge bases.

The application relates to the technical field of natural languages, and discloses a question generation method, which comprises the following steps: acquiring a question data set, wherein the question data set comprises initial questions; generating questions by using a question generator to obtain candidate questions; generating answers by using an answer generator to obtain candidate answers and question answers; determining first similarity values and second similarity values according to all question answers corresponding to the same initial question and candidate answers corresponding to the same candidate question; and screening all candidate questions according to all first similarity values and all second similarity values to obtain target questions. Through discriminative learning on the adversarial questions, the learning result is fed back to the question generator for optimization, so that the question generation model has a higher accuracy in generating questions, and the accuracy of artificial customer service in replying to customer questions in the insurance field or the financial field is improved.

Provide a system. 【Solution means】 The information processing device has means for extracting age-based information based on the history information of the user, The information processing device has means for transmitting the age-based information to the display means, The display means has means for presenting the received age-based information to the user, The response processing device has means for analyzing the response from the user and generating the next question based on the response content, In the question generation, there is means for considering the user's interests and understanding and adjusting the conversation, There is means for performing a dialogue based on the presented information using speech synthesis technology, There is means for analyzing the voice input from the user using speech recognition technology, A system including the above.

The application discloses a method and device for generating answering content, a storage medium and an electronic device. It relates to the field of artificial intelligence. The method comprises the following steps: obtaining a target question of a target object; processing the target question by a target question and answer model to obtain answering content for the target question, wherein the target question and answer model is trained by a training sample set, a training sample in the training sample set is a sample question, a true label is a sample answer corresponding to the sample question, and the training sample set is generated by a question generation model based on a reference. Through the application, the question and answer model used in the related art relies on manual construction of the training sample set during training, the training effect of the question and answer model is poor, and the answering accuracy of the question and answer model during application is low.