53 results about "Knowledge evaluation" patented technology

The invention discloses a knowledge evaluation method in an ask-answer community, wherein the knowledge comprises questions and answers. The method comprises the following steps: the questions, answer contents of the answers corresponding to the questions and answer attributes are acquired; and the knowledge is evaluated and the score of the knowledge is calculated according to the answer contents and the answer attributes. The knowledge evaluation method in the ask-answer community combines the answer contents with the answer attributes to evaluate the knowledge and calculate the score of the knowledge, thereby sorting according to the score of the knowledge and bringing convenience for a user to inquire the related knowledge. In addition, the invention also provides a knowledge evaluation system in the ask-answer community.

A network based electronic-learning system, especially a network based electronic-learning system to collect, process, evaluate, report, visualize, and analyze learning data from students. Instructors and students may interact with each other via a website hosted on a server. The system has an instructor dashboard, at least one instructor class room dashboard, at least one instructor assignment dashboard, a student dashboard, a student classroom dashboard, a student assignment dashboard. A library in the system is capable of storing and retrieving the classes, assignments, questions, solutions, and students' responses to solution steps and analytic widgets.

The invention discloses an AI agent design platform decision optimization method based on big data, and particularly relates to the field of artificial intelligence, comprising multi-modal data sensing layer construction, a streaming feature calculation engine, a dynamic index fusion center and an adaptive decision matrix. According to the method, accurate synchronous monitoring of the utilization rate of hardware resources and dynamic collaborative optimization of heterogeneous computing units are achieved, and the resource scheduling efficiency in a complex computing scene is remarkably improved; knowledge system degradation caused by long-term learning is effectively prevented, and the continuous reliability of a cognitive system is ensured. The provided multi-dimensional decision credibility verification system is fused with interpretability penetration analysis, environment coupling modeling and logic drift detection technologies, the limitation of a traditional single credibility index is broken through, the risk prediction and fault-tolerant capability of the decision process is remarkably enhanced, and a full-dimensional safety decision guarantee system is constructed for an intelligent agent.

The invention relates to a photovoltaic power plant output power prediction method based on a weighted FCM clustering algorithm. The method provided by the invention comprises the steps that a weather data sample which matches a meteorological data sample to be predicted and the corresponding photovoltaic power plant output power are selected from the existing photovoltaic power plant operation database and are used as a reference sample; through knowledge evaluation, a typical data matrix is selected and is combined with the meteorological data sample to be predicted; after normalization, a final standard sample matrix is formed and is used as an input variable of the algorithm; and after property-weighted FCM clustering algorithm iteration, output power corresponding to the meteorological data sample to be predicted is acquired. According to the invention, the shortcomings of complex meteorological factors, unbalanced influence on the output power, meteorological data randomness and uncertainty and the like are overcome; the method has the advantages of fast prediction and high accuracy; a prediction result provides a data support for rational resource dispatching and scientific overall planning of the power industry; and good economic and social benefits are acquired.

The invention discloses a self-adaptive network security knowledge evaluation method based on a cognitive diagnosis theory. The self-adaptive network security knowledge evaluation method based on thecognitive diagnosis theory comprises the following steps: S1, an evaluation system generates a network security knowledge graph according to the identity background of a user, and tests the user according to a preset sequence and a knowledge structure; S2, the test system generates a personal basic information database according to the personal identity background information uploaded by the userand a specific format; and S3, the test system traverses according to the structural sequence of the knowledge graph for item-by-item test, and accurate positioning of the knowledge level of the useris realized based on test question extraction of the corresponding difficulty standard. According to the method, a potential knowledge state is obtained through real-time feedback of a user in testing, and a novel cognitive diagnosis model PH-is utilized; And the real knowledge, skill level and corresponding short boards of the user are efficiently reasoned by the DINA, so that efficient and accurate education evaluation is realized, and the learning condition of the user is better reflected.

The invention relates to a method and system for removing character adhesion. The method includes: setting the prior knowledge set of a to-be-processed character image, performing connected domain analysis on the to-be-processed character image, calculating character height H and character width W, and determining connected domains, which need to be separated, in a connected domain analysis result; performing separation point positioning on the connected domains which need to be separated to obtain all separation schemes, using the separation schemes to respectively separate the connected domains which need to be separated, performing OCR on the character separation result corresponding to each separation scheme to obtain the character recognition result of the image, evaluating the character separation result corresponding to each separation scheme according to prior knowledge evaluation function, and using the character recognition result with the most matched evaluation as the recognition result after adhesion removing. By the method, the problem of multi-character adhesion under the condition of unknown adhesion number is solved, and good adhesion removing effect can be achieved.

The invention relates to the field of virtual simulation teaching technology, in particular to a virtual simulation teaching application platform, comprising a system management host, wherein the system management host is respectively connected with a user database, a teaching courseware database and a virtual simulation teaching system by signals, and the virtual simulation teaching system comprises a virtual simulation teaching module. The invention can carry out virtual simulation teaching, let the user carry on the theory knowledge study through the video screen teaching module on this platform, through the three-dimensional simulation exercise module to carry on the operation practice, Moreover, the invention also evaluates the learning situation of the students through the three-dimensional simulation operation evaluation module and the theoretical knowledge evaluation module, so that the students can better understand the learning and mastering situation of the students. The invention does not need to put in real operation practice materials, and achieves the teaching purpose by using the virtual simulation mode.

The invention relates to the technical field of knowledge graph construction and maintenance, and discloses an AI knowledge graph construction and maintenance method based on ontology engineering, and the method comprises the steps: obtaining multi-source heterogeneous data to construct an initial graph ontology model; loading the constraint rules and the entity alignment parameters to carry out cross-modal knowledge fusion, and generating a dynamic knowledge evaluation model; executing ontology topology reasoning based on the model, and constructing time sequence knowledge evolution simulation data; training the semantic conflict resolution model to generate a knowledge fusion optimization model, and outputting map maintenance parameters; knowledge increment simulation information is generated, a multi-dimensional optimization model is constructed to iteratively adjust the ontology structure, and optimal knowledge fusion path parameters are generated; and dynamic ontology matching is realized by combining real-time reasoning and historical track updating maintenance strategies. According to the method, the construction efficiency, the fusion quality and the self-adaptive maintenance capability of the knowledge graph are improved, the method is suitable for an intelligent knowledge management scene of multi-source heterogeneous data, and the defects of a traditional method in the aspects of semantic conflict resolution, ontology dynamic evolution and the like are overcome.

The invention provides an intelligent power utilization control management system. The system comprises multiple sets of acquisition equipment and a cloud platform, wherein the acquisition equipment are used for acquiring the electrical parameters of to-be-monitored electrical equipment through a built-in sensor, converting the electrical parameters into electrical signals, and transmitting the electrical signals to the cloud platform through a network module; and the cloud platform is used for receiving the electrical signals and the dynamic characteristics sent by the acquisition equipment and monitoring the power utilization condition, the on-off state and the safety condition of the electrical equipment, evaluating the current energy efficiency and electrical safety of the electrical equipment according to the electrical signals, the dynamic characteristics, a pre-established fuzzy evaluation model and an event prediction-oriented expert knowledge evaluation library so as to obtain the energy efficiency and electrical safety evaluation result of the electrical equipment, and sending the result to a monitoring terminal. According to the invention, electrical energy efficiency and safety evaluation can be realized automatically and intelligently, so that more scientific, reasonable and effective power consumption management is facilitated.

The invention relates to a scheduling knowledge management system for intelligent manufacturing. The system comprises a scheduling knowledge learning module driven by data, which is used for knowledgemining of scheduling data samples to obtain scheduling knowledge. A scheduling knowledge application module, responsive to receiving a scheduling request, for calling the scheduling knowledge to generate a scheduling policy matching with an intelligent workshop production state and obtaining a scheduling result; An on-line scheduling knowledge evaluation module, responding after obtaining a scheduling result, for judging the validity of the scheduling knowledge according to the scheduling result; The scheduling knowledge updating module responds when the scheduling knowledge is judged to be invalid, and is used for applying an online learning method to adjust the scheduling knowledge on the basis of adding updated samples. Compared with the prior art, the invention can better improve theadaptability of the scheduling knowledge, ensure the scheduling effectiveness, and has the advantages of continuously optimizing the overall performance of the intelligent workshop.

The invention relates to a method for realizing file handling service question answering based on a large language model. The method comprises the following steps: S1, preparing data; s2, inputting a query question by a user, and judging whether the user question is related to the file handling service or not through a knowledge evaluation module; s3, performing retrieval in the file handling service knowledge base by using a knowledge base retrieval module; s4, performing reordering evaluation on the retrieval content in the previous step through a retrieval evaluation module; s5, the retrieval content is added into the cue word template to conduct reasoning generation on the user question; s6, querying a knowledge base document relation graph according to the retrieval content, finding out an associated document, combining the associated document with a user question, and delivering the associated document and the user question to a large language model to predict the next question of the user; and S7, performing question verification on the new question of the user. According to the overall structure provided by the embodiment of the invention, the user query is enabled to generate a plurality of queries in the retrieval enhancement generation process, and the diversity and coverage of retrieval can be improved; and the advantages of the dense retrieval algorithm and the sparse retrieval algorithm can be reserved.

The invention discloses a satellite ground observation system task deduplication method based on knowledge evaluation. The satellite ground observation system task deduplication method comprises the steps that knowledge value evaluation is conducted on each satellite, and when task conflicts exist in observable time windows of the multiple satellites, task time duplication eliminating is performedaccording to knowledge value evaluation scores of the satellites. According to the method, a satellite ground observation system task deduplication method based on knowledge evaluation is realized; knowledge value scores are given to all satellites, a traditional algorithm is optimized to serve as a voucher for task deduplication according to the maximum task execution time, and the maximum observation value can be achieved for an observation user when multiple satellites observe task conflicts.

The invention discloses a personalized teaching method, system and device based on a knowledge mastery degree graph. The method comprises the steps of receiving knowledge evaluation results of students, wherein the knowledge evaluation results are used for representing knowledge mastering conditions of the students; and generating a knowledge mastery degree graph corresponding to the students according to the knowledge evaluation result, wherein the knowledge mastery degree graph is used for representing the mastery proficiency of the students for each knowledge point. According to the technical scheme provided by the embodiment of the invention, the proficiency degree of knowledge mastery degree of the students and the learning grade change of the students are vividly displayed in a dynamic and visual form, teachers are assisted to carry out efficient and targeted teaching for different students, the students carry out missing inspection and vacancy filling on learned knowledge, and the learning efficiency is improved.

The invention relates to the technical field of intelligent coal mine safety production, and discloses an intelligent coal mine safety early warning method and system based on deep learning, and the method comprises the steps: constructing a difficulty evaluation function, and achieving the progressive learning from simple to complex; based on a difficulty assessment result, a model-independent meta-learning algorithm is realized, so that the model quickly adapts to new mining area characteristics; constructing a privacy protection federated learning framework by using the meta-learning model, and realizing multi-mining-area cooperative training; a continuous learning module is constructed, and original experience is reserved when new knowledge is learned; constructing a meta-knowledge evaluation module to realize cross-mining-area safety knowledge sharing; according to the invention, the security risk identification accuracy is improved; multi-mining-area cooperative training is realized on the premise of protecting data privacy; the method has continuous optimization capability and effectively solves the problem of model drift; and efficient sharing and migration of cross-mining-area safety knowledge are realized.

The invention provides a tourism knowledge graph multi-dimensional construction method and system of a deep learning hybrid model, and belongs to the technical field of knowledge graph construction, and the method comprises the steps: S1, data extraction; s2, knowledge extraction; s3, knowledge fusion; s4, knowledge evaluation; and S5, knowledge storage. According to the method, the LLMs and the deep learning technology MLPBoost are combined, so that many problems in the current knowledge graph construction process can be effectively solved, and more accurate and personalized support is provided for intelligent tourism service.

The invention provides a knowledge tracking method based on knowledge evaluation and learner state evaluation, and relates to the technical field of knowledge tracking, and the method comprises the steps: obtaining and processing an answer record and teaching resources, and obtaining historical answer features and teaching resource features; modeling is carried out on the multi-modal course knowledge point information through teaching resource features, and knowledge point proportion weights are obtained; initializing a state matrix of a learner through the teaching resource characteristics; updating a state matrix through knowledge point proportion weights and historical answer features; and predicting the correct answering probability of the learner through the state matrix after state updating, the knowledge point proportion weight and the teaching resource characteristics. According to the method, the knowledge and the state of the learner in the learning process can be effectively evaluated and modeled, and the answer condition of the learner can be accurately predicted.

A method for information processing carried out by an organized group having information processing means independent of one another and each having knowledge, knowledge expression, knowledge evaluation data, a knowledge evaluation function, a concept, and a learning algorithm (hereinafter referred to as knowledge etc). The method comprises a dividing step of dividing the information processing means into groups, a first work step of attaining a result of the information processing achieved by each group, and a second work step of attaining a result of information processing achieved by the whole groups by integrating the results of the information processings carried out by each group. The division performed at the dividing step is made so that the results of the information processings are different from one another. In the first work step, each group conducts a work independently of the others. The second work step includes a first evaluation substep in which each group evaluates the results of the information processings achieved by the other groups by using common evaluation criteria.

The invention discloses a knowledge-intensive task-oriented thinking chain prompt optimization method and system, and belongs to the field of natural language processing. When the model is used for reasoning knowledge-intensive tasks based on thinking chain prompts, the generated thinking chain often has the problems of knowledge missing, irrelevance, even errors and the like. Therefore, a prompt optimization process is improved in a manner of combining knowledge generation and knowledge evaluation, and a thinking chain prompt which more pays attention to knowledge quality is obtained, so that the knowledge integrity, correlation and correctness of a model generated thinking chain are improved. The knowledge generation means that the guide model explicitly generates knowledge fragments in the thinking chain; according to knowledge evaluation, a loss function containing answer accuracy and multi-dimensional knowledge indexes is designed, and gradient information of the loss function is utilized to select an optimal candidate word to update and optimize prompts. The system comprises a thinking chain knowledge generation module, a knowledge evaluation module, a candidate word initialization module, a candidate word gradient calculation module and a prompt updating module.

The invention discloses an evaluation data automatic generation method based on dynamic RAG and multi-language LLM cooperation, and belongs to the technical field of artificial intelligence. Knowledge fragments are extracted from a structured or unstructured document, and a semantic retrieval index is constructed after the knowledge fragments are vectorized through an embedded model. In an evaluation data generation stage, the system calls a vector search engine to retrieve related contents according to a theme input by a user, inputs a result as a context into a large language model, automatically generates a question, a standard answer, an interference item and a corresponding explanation, and supports structured verification and result storage. The method can realize automatic, large-scale and high-quality generation of evaluation data, has the advantages of high accuracy, strong correlation, uniform structure, explanation and the like, and is suitable for scenes of online education, enterprise training, knowledge evaluation and the like.

The invention provides a fermentation process modeling method based on a generative fuzzy system and expert knowledge evaluation. The generation type fuzzy rule can mine own specific information for the fermentation process. The modeling method supports evaluation and optimization of fermentation control parameters by utilizing expert knowledge. Therefore, the fermentation process optimization model can be effectively suitable for a fermentation process optimization scene, and the experiment frequency and the optimization time can be remarkably reduced, so that the cost is reduced and the efficiency is improved. According to the method, the rolling learning method is innovatively designed for the fermentation process optimization model, so that the fermentation process optimization model has excellent adaptive capacity. The adaptive characteristic enables the model to flexibly respond to the dynamic change and uncertainty in the fermentation process, and the robustness of the system is remarkably improved. In addition, automatic optimization and control are achieved through the intelligent characteristic, dependence on artificial experience is reduced, and operation convenience and accuracy are improved.

The invention discloses an end-to-end-based large knowledge graph construction and storage method and system. The system comprises a knowledge graph construction system, a knowledge construction module, a knowledge management module, a knowledge application module, a knowledge extraction module, and a processing and storage module. The knowledge graph construction system is in communication connection with the knowledge construction module, the knowledge management module, the knowledge application module, the knowledge extraction module and the processing storage module. The knowledge construction module comprises a knowledge collection module, a knowledge fusion module, a knowledge evaluation module and a knowledge updating module; the knowledge application module comprises a cognition service module, a language understanding module and an inference engine module; the reasoning engine module is in communication connection with the understanding service module and the language understanding module, and the language understanding module is in communication connection with the understanding service module. According to the invention, required data can be obtained more quickly and efficiently; through cooperation of data integration, data cleaning and data updating in the data cleaning and perfecting module and the processing and storing module, quick search is facilitated.

The invention discloses a personalized training resource recommendation method based on a graph fusion neural network, and the method comprises the steps: obtaining text data information, capturing the global and local information of a text through a convolutional neural network, adjusting a mapping function according to a constraint condition, and obtaining a multi-modal data model; optimizing the performance of the multi-modal data model through cross compression, improving the multi-modal data model by using a loss function, extracting data information of the multi-modal data model, and obtaining a training resource knowledge graph through data fusion; the method comprises the following steps: acquiring user online behavior data, performing modeling and group clustering on user online behaviors, and performing deep knowledge tracking by utilizing CRU to obtain a learner knowledge evaluation and deep learning model; through a graph fusion neural network recommendation algorithm, the training resource knowledge graph is matched with personalized demands of the user, personalized resource recommendation is obtained, richer semantic information is provided, and the recommendation algorithm can more accurately understand the demands and interests of the user.

The invention relates to the field of data processing, in particular to a skill data processing method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining software information data of a software technician; acquiring skill operation data of a software technician according to the software skill identifier; according to the skill operation data, performing operation capability evaluation on the software technician to obtain an operation evaluation result; acquiring a software skill test question corresponding to the time identifier; acquiring skill answer data of the software technician based on answer operation of the software technician on the terminal equipment; performing skill knowledge evaluation on the software technicians according to the skill answer data to obtain a knowledge evaluation result; and inputting the operation evaluation result and the knowledge evaluation result into a comprehensive evaluation model to obtain a skill analysis result of the software technician. According to the invention, the relevance between the skill analysis result and daily operation can be enhanced, and the accuracy of the skill analysis result is improved.

The invention provides a knowledge evaluation method and device, a storage medium and electronic equipment, and the method comprises the steps of building a system question bank based on a knowledge graph; selecting first test question data suitable for the target object from a system question bank, and obtaining a first processing result; dynamically determining a second attribute label suitablefor the target object according to the first attribute label and the first processing result, selecting second test question data matched with the second attribute label from a system question bank, and then obtaining a second processing result; and determining the mastery degree of the target object for the corresponding knowledge points according to the first processing result and the second processing result. According to the knowledge evaluation method and device, the storage medium and the electronic equipment provided by the embodiment of the invention, the test question data of the target object can be dynamically selected in real time, the mastery degree of the target object on knowledge points can be more effectively and accurately determined, and weak knowledge points of the target object can be quickly positioned.

The invention relates to the field of intelligent manufacturing and digital process planning, in particular to a knowledge-driven automatic generation method for a part machining process and a related product, and the method comprises the steps: constructing a machining-process-oriented knowledge graph, and coupling the knowledge graph with a large knowledge model to form a feedback closed loop; extracting process knowledge units from the multi-source data, and performing quantitative scoring and credibility screening on the process knowledge units based on a preset knowledge evaluation algorithm to obtain a high-reliability process knowledge data set; performing fine-grained attribute relation extraction on the process knowledge in the process knowledge data set, structuring an extraction result, and dynamically updating the extraction result to the knowledge graph to realize incremental updating of the knowledge; through collaborative innovation of four core links of efficient and automatic knowledge acquisition, structured and refined process knowledge expression and dynamic extension and real-time updating capability generation, the technical bottleneck in traditional process planning is solved.

The invention discloses a self-adaptive network security knowledge evaluation method based on a cognitive diagnosis theory. The self-adaptive network security knowledge evaluation method based on thecognitive diagnosis theory comprises the following steps: S1, an evaluation system generates a network security knowledge graph according to the identity background of a user, and tests the user according to a preset sequence and a knowledge structure; S2, the test system generates a personal basic information database according to the personal identity background information uploaded by the userand a specific format; and S3, the test system traverses according to the structural sequence of the knowledge graph for item-by-item test, and accurate positioning of the knowledge level of the useris realized based on test question extraction of the corresponding difficulty standard. According to the method, a potential knowledge state is obtained through real-time feedback of a user in testing, and a novel cognitive diagnosis model PH-is utilized; And the real knowledge, skill level and corresponding short boards of the user are efficiently reasoned by the DINA, so that efficient and accurate education evaluation is realized, and the learning condition of the user is better reflected.

The process knowledge evaluation method based on the comprehensive stimulation degree is oriented to practical engineering application and refers to an antibody cell clone selection mechanism in a human immunity principle, and is suitable for knowledge evaluation and filtering in case-form process knowledge retrieval. The method comprises the following three steps: 1, modeling a process knowledgeabstraction relation; 2, calculating the comprehensive stimulation degree of process knowledge; 3, process knowledge evaluation. According to the method, the problem that solution sets tend to be thesame due to the fact that knowledge evaluation indexes are single in process case knowledge reuse is solved, and the diversity of the solutions and the enlightenment to process compilation personnel can be effectively improved.

The invention provides an artificial intelligence auxiliary knowledge assessment method and device for adaptive learning. The problem that a traditional classroom and a traditional intelligent tutoring system cannot provide an adaptive learning environment and cannot timely and effectively assess students is effectively solved. The method comprises the following steps: setting a learning task containing multiple knowledge skills in the digital intelligent courseware system in advance, and obtaining learning data when a student answers the learning task; decomposing the learning task to obtain multiple knowledge skills, mapping the multiple knowledge skills into the learning data, screening out key learning data, and inputting the key learning data into a student model to obtain a corresponding evaluation result; and fusing the plurality of evaluation results to obtain an evaluation level result so as to assist in evaluating the knowledge state of the student based on the evaluation level result, and generating a personalized learning path for adaptive learning of the student.

The present application relates to the field of intelligent manufacturing and digital process planning, and particularly relates to a knowledge-driven automatic generation method for part machining process and related products, which comprises constructing a knowledge graph for machining process, coupling the knowledge graph with a knowledge big model to form a feedback closed loop, extracting process knowledge units from multi-source data, quantitatively scoring and credibility screening the process knowledge units based on a preset knowledge evaluation algorithm to obtain a high-reliability process knowledge dataset, performing fine-grained attribute relationship extraction on the process knowledge in the process knowledge dataset, and dynamically updating the structured extraction results to the knowledge graph to realize incremental updating of knowledge. The present application solves the technical bottleneck in traditional process planning through the synergistic innovation of the four core links of efficient and automatic knowledge acquisition, structured and refined process knowledge expression, and dynamic expansion and real-time updating capability.