68 results about "Question asking" patented technology

The invention belongs to the technical field of intelligent question-answering systems, and particularly relates to an intelligent question-answering inference system based on a knowledge graph, which is characterized in that firstly, a knowledge graph construction module fuses multi-source data to generate a structured graph, and after a user inputs a natural language question, a question-answering analysis module completes intention classification and entity disambiguation and converts the question into structured query; an inference engine module fuses symbol rules and graph neural network inference through a hybrid inference sub-module, and a dynamic weight adjustment sub-module optimizes weights according to errors and attenuation factors to generate an inference result; the knowledge updating module incrementally updates the atlas in real time and detects conflicts, the interactive interface module visually presents a result, and the evaluation optimization module iteratively optimizes parameters in combination with offline evaluation and online feedback. The whole process is from user question asking to result output, accurate reasoning and continuous performance improvement are achieved, and multi-field question and answer requirements are met.

The invention provides a knowledge enhancement type sports video understanding method based on large-model dual-mode reasoning, and belongs to the field of video understanding. Firstly, a sports video needing questioning and a question text are obtained, and the sports video, the question text and cue words are input into a reactive reasoning agent; the reactive reasoning agent classifies the questions according to the question texts and the cue words, and if the questions belong to simple questions, the reactive reasoning agent answers the questions according to the input sports videos; if the questions belong to complex questions, the questions are answered through a deep reasoning agent, and the deep reasoning agent is composed of a dynamic motion divider, a key segment selector and a fine-grained matcher based on the sports knowledge graph. According to the method, a dual-mode reasoning system is innovatively introduced, the dynamics and domain specificity of the sports video and the diversity and complexity of questions asked by the user are fully considered, and the performance of a (multi-mode) large language model in a sports video understanding task is remarkably improved.

The invention provides a student course learning evaluation method and device and electronic equipment, and relates to the technical field of education informatization. The method comprises the following steps: acquiring reply data of questions asked by a student in a learning process of a target course; performing feature extraction on the answer content to obtain answer content features and semantic category labels; standard answers corresponding to the questions are extracted according to the knowledge graph, and candidate answer features are generated; selecting a corresponding target answer feature according to the semantic category label; calculating the semantic similarity of the answer content features and the target answer features, and determining whether the answer content is correct or not according to the semantic similarity and a similarity threshold value; counting the number of correct answer contents, and calculating the answer accuracy; and according to the answer correct rate and the answer state, determining a knowledge mastering score of the student for the target course, and according to the knowledge mastering score and a score threshold, determining a mastering degree of the student for the target course. According to the invention, the accuracy of student course mastering degree evaluation can be improved.

The invention discloses a content-based news duplicate removal method and device and a nonvolatile storage medium. The method comprises the steps of obtaining a to-be-processed news set, deleting to-be-processed news with text structure similarity greater than or equal to preset similarity, and obtaining residual to-be-processed news; determining a content element and a category system of each piece of residual to-be-processed news, and classifying the plurality of pieces of residual to-be-processed news with the same content element and category system into a to-be-deduplicated set; for each piece of target residual to-be-processed news in the to-be-deduplicated set, triggering a text analysis model by adopting a first cue word to output a plurality of questions related to the target residual to-be-processed news to obtain a question list, and triggering the text analysis model by adopting a second cue word to output summary information of the target residual to-be-processed news; and according to the first semantic similarity of the question list and the second semantic similarity of the summary information, determining to-be-deleted news in the to-be-deduplicated set.

The invention discloses an intelligent question and answer processing method and device, equipment and a storage medium. When the method provided by the embodiment of the invention is executed, the intelligent question and answer model can firstly obtain the questioning question to be processed and identify the real-time performance of the question. Wherein if the answer to the question changes with time, the question is a real-time question, or if the answer to the question needs to be replied based on the update information, the question is also a real-time question. And if the problem is a real-time problem, generating a preliminary reply to the problem. And then evaluating the confidence coefficient of the preliminary reply based on question and answer data in a knowledge base associated with the intelligent question and answer model. If the confidence coefficient is greater than or equal to a confidence threshold value, directly outputting the preliminary reply; on the contrary, if the confidence coefficient is smaller than a confidence threshold value, outputting a rejection answer or an uncertainty, and obtaining a question reply of the questioning question obtained based on the RAG query. The response accuracy and the resource utilization efficiency of the intelligent question and answer are improved.

The invention provides an assessment interview method and device for enterprise employees and a storage medium, and the method comprises the steps: determining an initial problem in a preset assessment interview problem library based on the post type and historical performance data of the enterprise employees; questioning by using the initial question so as to receive answer information of the enterprise employees; determining the semantic integrity of the answer information; if the semantic integrity is smaller than a preset integrity threshold value, generating a question-chasing question of the initial question according to a semantic element type missing in the answer information; asking questions by utilizing the question-asking questions to receive supplementary answer information of the enterprise employees; and according to the answer information, supplementing the answer information, and determining an assessment interview evaluation result of the enterprise employees. According to the method and the device, the questioning content can be adjusted according to the post types and the historical performance data of the enterprise employees, and the questioning can be selectively performed according to the answer information of the enterprise employees, so that the questioning of the assessment interviews is more accurate and deep, and the accuracy of the result obtained by the assessment interviews is improved.

The invention relates to an intelligent deep questioning method and system, and belongs to the technical field of natural language processing and intelligent evaluation. The method comprises the following steps: acquiring a candidate response, converting the candidate response into a standardized text, analyzing the text in combination with multi-dimensional monitoring data, positioning competency missing elements, generating a missing identification set, and marking a sorting question-chasing point; constructing a dynamic self-adaptive score matrix in which competency is linked with a questioning point, fusing monitoring data to calibrate scores and confidence, and generating a questioning technology intervention scheme; a virtual interviewer role library is preset, roles are dynamically matched, and the intervention logic and the missing identification set are combined to generate specialized questioning content; and when the core element capability element characterization is insufficient or the confidence coefficient does not reach the standard, generating a target element cognition questioning problem, and after element extraction and fusion, outputting a multi-dimensional competency score and a confidence coefficient report. According to the invention, the upgrading of the questioning from mechanical questioning to intelligent technical intervention is realized, the questioning targeting and the evaluation accuracy are improved, and reliable support is provided for accurate talent selection.

There is provided a computer implemented method of dynamic generation of audio content of a panel including questions asked by a moderator and responses by responders, comprising: accessing user interest(s) of a target user, accessing a social network graph that includes the target user, selecting questions correlated with the user interest(s) of the target user, selecting responses to questions by responders, wherein the responders are linked to the target user in the social network graph, wherein the responders are associated with user interests correlated with the user interest(s) of the target user, dynamically assembling audio content(s) from voice records and / or from audio recordings generating by converting text to voice, each audio content including a sub-set of the selected questions and a sub-set of the responses, and providing dynamically assembled audio content(s) for selection thereof for playing on a speaker.

The invention discloses a problem dynamic recommendation method, device and equipment based on an HITS algorithm. The method comprises the steps of obtaining a questioned question set and a to-be-recommended question set; initializing the hub degree of each asked question; initializing the authority of each question to be recommended; for each to-be-recommended question, iteratively updating the authority of the to-be-recommended question based on the initial value of the authority of the to-be-recommended question and the latest value of the hub degree of each questioned question; for each questioned question, iteratively updating the hub degree of the questioned question based on the initial value of the hub degree of the questioned question and the latest value of the authority degree of each question to be recommended; and after iteration is finished, generating a question recommendation result according to the authority of each question to be recommended. Questioned questions are abstracted as hub pages in the HITS algorithm, to-be-recommended questions are abstracted as authoritative pages in the HITS algorithm, and dynamic recommendation of the questions is realized through iterative updating of hub degrees and authoritative degrees.

The invention provides a role recommendation method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to the field of natural language processing and the field of large models. According to the specific implementation scheme, the method comprises the following steps: recalling roles for replying a question to obtain a plurality of candidate roles; on the basis of the recall mode and the recall parameter corresponding to each candidate role, respectively determining the role score of each candidate role; and based on the role score of each candidate role, determining a target role for replying the question in the plurality of candidate roles.

The invention provides a knowledge question and answer method and device, electronic equipment and a storage medium, and the method comprises the steps: receiving a question input by a user, generating a question vector corresponding to the question according to the question, determining a target corpus vector matched with the question vector from a preset first database according to the question vector, and sending the target corpus vector to the user; determining a target corpus vector, determining an identifier of the target corpus vector as a target corpus identifier, determining a knowledge type corresponding to the target corpus identifier from a corpus data table in a preset second database according to the target corpus identifier, and according to the knowledge type corresponding to the target corpus identifier and a target corpus, determining a knowledge type corresponding to the target corpus identifier from a knowledge data table corresponding to the knowledge type in the second database, and obtaining query knowledge information, generating reply information corresponding to the question according to the query knowledge information, and pushing the reply information to the user. Therefore, interactive personalized question and answer service can be provided for the user, and the question and answer efficiency and accuracy are improved.

The invention discloses a college interview simulation method and system and a computer program product, and relates to the technical field of simulation training, and the method comprises the steps: obtaining personal resume data inputted by a current user, and constructing a user feature database according to the personal resume data; generating an initial interview question based on the user feature database and a preset field interview knowledge base; collecting an initial answer of the current user for the initial interview question, and generating a question-chasing question according to the initial answer through a preset natural language model; and inputting the initial interview question, the initial answer, the question asking question and the corresponding question asking answer into a preset evaluation model to obtain an interview evaluation report. Through personalized question generation and evaluation feedback, the reality and effectiveness of user interview preparation can be efficiently improved.

The application discloses a kind of based on knowledge verification's trusted question and answer method, including the following steps: identifying and eliminating the reference and omission content in user's asking question, restating user's asking question, and extracting the keyword expressing user's intention.Use the keyword set after restating as query, retrieve relevant articles, calculate the relevance score of the content retrieved and the asking question, and filter out the highest relevance score multi-modal knowledge.Generating multi-modal statements about search results, multi-round, multi-path verification and reasoning are carried out on the multi-modal statements.The authenticity of the iterated multi-modal statements is verified, and the filtered and verified knowledge and evidence are integrated to generate the final trusted user reply.Compared with the prior art, the application can eliminate references and omissions by injecting associated historical context information during the question representation process, and obtain trusted multi-modal knowledge using retrieval enhancement and self-checking mechanisms, thereby more accurately answering the questions asked by the user.

An object of the system according to the embodiment is to quickly and appropriately answer questions asked by students in a recorded class video.SOLUTION: A system includes a question input unit, an analysis unit, an answer generation unit, and a provision unit. The question input part inputs a question from the student. The analysis unit analyzes the question input by the question input unit. The answer generation unit generates an answer based on the question analyzed by the analysis unit. The providing unit provides the answer generated by the answer generating unit to the student.SELECTED DRAWING: Figure 1

This invention discloses a disease retrieval method and apparatus based on a knowledge graph-enhanced large language model, relating to the fields of large language models and knowledge graph question answering technology. The method includes: constructing a question-answering dataset based on triples; storing and visualizing a knowledge graph of five specialized diseases using Neo4j; obtaining medical questions posed by users; progressively expanding the input questions to obtain sub-questions based on thought chain reasoning; performing relational path retrieval and knowledge subgraph retrieval based on a pre-trained model; fine-tuning the large language model to generate factual knowledge text based on the sampled answer subgraph; constructing a knowledge-enhanced prompt template by combining the input questions and factual knowledge, and feeding it into the large language model to obtain the final medical answer. This solution utilizes a knowledge graph-enhanced large language model, guiding it to reason and retrieve within efficient knowledge paths, enabling accurate and professional answers to users' specialized medical questions.

The objective is to provide a program and information processing device that efficiently support learning specifically for qualification exams where past exam questions are highly valued. [Solution] The system includes a past question data acquisition unit that acquires past question data containing textual information about past questions asked in qualification exams, a necessary knowledge data generation unit that generates necessary knowledge data which is textual information about the knowledge needed to answer the questions in the acquired past question data, and an important knowledge data generation unit that generates important knowledge data which is textual information about common knowledge from a plurality of necessary knowledge data generated from each of a plurality of past question data, wherein at least one of the necessary knowledge data generation unit or the important knowledge data generation unit is configured to generate information based on a pre-trained model that has been trained in advance by inputting at least knowledge data which is textual information containing the knowledge necessary to pass the qualification exam.

The invention provides a method and a device for improving recall capability of an RAG system. The method comprises the following steps: S1, carrying out structured analysis on a document; s2, performing semantic hierarchical segmentation on the document content by adopting a multi-scale semantic partitioning strategy to generate a multi-granularity index unit; s3, performing semantic enhancement and optimization on the query based on a query rewriting strategy of a large language model; and S4, combining the optimized query with the multi-scale semantic index, and executing a retrieval and generation task. According to the multi-scale semantic chunk strategy, the similarity is calculated by applying a vector model, knowledge is divided into a plurality of blocks with different semantic information, and the vector representation capability is enhanced. An LLM-based question rewriting strategy can effectively identify intention words and keywords in user query, and particularly for a multi-question question, the multi-question question can be split into a plurality of independent sub-questions for multi-path recall. According to the method, the accuracy and efficiency of intelligent query in the vertical field can be remarkably improved, and the query experience of a user is improved.

A processing device (10) comprises: a question extraction unit (11) that, using an LLM (20), extracts, from a plurality of dialogues between an expert and a user, questions asked by the expert in order to elicit information from the user; a proposal extraction unit (12) that, using the LLM (20), extracts, from the plurality of dialogues, proposals made by the expert in order to solve the problem of the user; a structuring unit (13) that, using the LLM (20), converts a dialogue between the expert and the user into a flow having information indicating a question, the user's answer to the question, and the proposal accepted by the user; and a chart construction unit (14) that statistically constructs, on the basis of a plurality of the flows, one flowchart indicating the tacit knowledge and judgment of the expert.

The application provides a large model-based intelligent question and answer method and system, which mainly proceeds from two aspects: 1, through accurate question classification and matching of different answering strategies, the answering efficiency and quality of the system are effectively improved. 2, in the "guess you want to ask" question recommendation link, the relevance and logicality of the dialogue context are fully considered, and an intention attenuation coefficient is introduced to calculate the weight of the recommended question, so as to improve the accuracy of the recommendation result. For standard answering type questions, the system searches and matches effective, concise and accurate answers in the database; for non-standard answering type questions, the system generates detailed and comprehensive answer content through the RAG method. In the recommendation process of the "guess you want to ask" question, the relevance and logicality of the current question and the historical dialogue of the user are comprehensively considered, and the current intention of the user is described through the intention attenuation coefficient, and accordingly the weight of the recommended question is adjusted, and then the rationality and accuracy of the recommendation result are improved.

A governance, risk, and compliance (GRC) system includes a user interface, one or more processors, and computer-readable memory encoded with instructions. The instructions, when executed by the one or more processors, cause the GRC system to receive a client instruction indicating one or more applicable information security and / or privacy standards of pre-defined information security and / or privacy standards that include corresponding requirements and select a set of requirements according to the client instruction, access a requirement dependencies map that represents dependencies between multiple requirements, and generate a set of dependency-mapped requirements. The instructions further cause the GRC system to access a question inventory, select applicable questions from the question inventory, generate a curated question set using the applicable questions, provide the curated question set to one or more users, receive responses to corresponding questions, and output a recommendation based on the responses and the corresponding questions.

An information processing device (100) has an acquisition unit (120) and a control unit (160). The acquisition unit (120) acquires an answer to a question asked in the past, and a route of a questioner of the question. The control unit (160) executes a first control process for performing control to display the answer on at least one display present on the route, or a second control process for performing control such that a terminal having a display displays the answer while moving on the route.

The application relates to an intelligent question and answer method in the field of wind power, which comprises the following steps: acquiring knowledge documents in the field of wind power, and generating question and answer pairs according to the knowledge documents, which are saved in a vector database after being vectorized; wherein the knowledge documents are divided into short documents and long documents according to length, an information constraint mechanism is established for the short documents, so that the generated question and answer pairs are limited within the range of original information; for the long documents, a two-stage memory processing strategy of a focused dialogue mechanism is adopted; a user's question is acquired, the question is vectorized, and a hybrid retrieval mechanism is adopted to combine fusion sorting to retrieve multiple question and answer pairs in the vector database corresponding to the question; according to the user's question, a prompt word is constructed, input into a large language model, and based on the intermediate output result of the large language model of each question and answer pair combined with the prompt word and the intermediate output result of the large language model of the prompt word input alone, a final answer output corresponding to the question is obtained by integration.

This invention discloses a question-and-answer method, apparatus, and related equipment for case acceptance scenarios. The method receives the current case cause and case description information input by the user, and performs multi-dimensional feature recognition on the case description information to obtain multi-dimensional case feature tags; based on the case feature tags and the current case cause, it extracts corresponding question content from a pre-set question database; based on the case feature tags, it performs guided transformation on the question content to obtain guided questions; it receives the user's answer content input based on the guided questions, and performs semantic parsing on the answer content to obtain key case information; it stores the key case information in a structured manner and matches it with the core information items corresponding to the current case cause, determining the information completeness based on the information matching results; and it determines whether to continue questioning based on the information completeness. This method sets up multi-dimensional feature recognition for judicial case acceptance scenarios, which can comprehensively reflect the information quality of the parties' answers.

To provide a system for preventing a new graduate or a former graduate from failing to make a proper answer at the time of interviewing because of insufficient self-PR or corporate research in job hunting.SOLUTION: A specific processing part 290 of a data processor 12 in this system, when receiving an input of a company name and business type information desired by a user, collects a URL of a news article related to the received company name / business type, analyzes text data, and extracts an important keyword from the news article by using a natural language processing technology. Then, expected interview questions are generated and stored on the basis of the extracted keywords and company information. Then, the questions generated in the mock interview format are sequentially displayed to the users, the answers of the users to the questions are analyzed, and feedback is generated and displayed. Further, a question asked by the user in the actual interview is added to the database and reflected on the update of the next question.SELECTED DRAWING: Figure 2

The invention relates to the technical field of information processing, and discloses an adaptive semantic matching RAG retrieval enhanced information processing method. The method comprises the following steps: if a plurality of historical questions continuously asked by a user and a current question both comprise at least one same keyword, acquiring the plurality of historical questions continuously asked by the user; determining a weight according to the semantic difference between the current problem and the plurality of historical problems, and constructing a weighted semantic vector matrix of the current problem according to the weight; performing semantic extraction on each knowledge fragment in the knowledge base to obtain a knowledge semantic vector matrix; screening a plurality of knowledge fragments according to the similarity between the weighted semantic vector matrix and the knowledge semantic vector matrix; and inputting the plurality of knowledge fragments and the current question into a language model to obtain an answer output by the language model. The method improves the integrating degree of the answer of the language model and the question, and prevents the user from asking questions repeatedly.

The invention discloses an automatic test method, device and equipment for an AI terminal application, and the method comprises the steps: receiving a test demand which comprises a question mode, a question theme, a to-be-tested object and an evaluation target; the questioning mode is used for indicating a mode of questioning a question to the to-be-tested object; the question theme is used for indicating the type of a question asked to the to-be-tested object; the evaluation target is used for indicating content needing to be evaluated for the to-be-tested object; based on the question mode and the question theme, determining question content from a multi-mode data set pre-constructed for different types of preset question themes; the multi-modal data set corresponding to each type of preset question theme comprises question content of at least one modal; determining an interface interaction step based on the question content and the interaction mode of the to-be-tested object; and testing the to-be-tested object based on the evaluation target and the interface interaction step. According to the application, the multi-mode input is automatically simulated according to the test requirement, and the automatic test of the AI terminal application is realized.

Methods and systems provide for extracting engaging questions from a communication session. In one embodiment, the system connects to a communication session with a number of participants; receives a transcript of a conversation between the participants produced during the communication session; extracts, from the transcript, utterances including one or more sentences spoken by the participants; identifies a subset of the utterances spoken by a subset of the participants associated with a prespecified organization; extracts engaging questions within the subset of utterances, the engaging questions each including a question asked by the participant associated with the organization that is immediately answered in the following utterance by a participant not associated with the organization; and presents, for display at one or more client devices, data corresponding to the extracted engaging questions.

The invention discloses an intelligent question and answer method and device, a storage medium and computer equipment, and relates to the technical field of digital medical treatment and the technical field of financial science and technology. Comprising the steps that question description information input through a target question asking object is received, and whether first answer information matched with the question description information exists or not is inquired in cached historical question and answer information; if first answer information matched with the question description information exists in the cached historical question and answer information, feeding back the first answer information to the target question asking object; if the first answer information matched with the question description information does not exist in the cached historical question and answer information, question complexity is determined based on the question description information, a target scale large model matched with the question complexity is selected, the target scale large model is called to generate second answer information corresponding to the question description information, and the second answer information corresponds to the question description information. And feeding back the second answer information to the target question asking object.

Methods and system for augmenting the intelligence of a chatbot by integrating a transformer-based tabular question-answering model with a dynamic vector dataset generation system. The methods and system may include receiving a question from a user. The methods and system may include sending the question to a retriever model and tokenizing the question into an input vector. The methods and system may include returning vectors having a threshold level of association with the input vector. The methods and system may include processing the vectors and the input vector using a transformer-based table reader pretrained for answering questions about relevant tables. The methods and system may include providing the user an answer to the question based on the processing without needing to perform additional logic and preprocessing on the relevant tables prior to sending the vectors to the transformer-based table reader.