Patents
Literature
15results about How to "Broaden their knowledge" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Construction method, system and equipment of power dispatching knowledge question-answering system and storage medium
PendingCN119311826AHigh precisionimprove performanceData processing applicationsNatural language data processingRelevant informationTheoretical computer science
The invention discloses a construction method, system and equipment of a power dispatching knowledge question-answering system and a storage medium. The construction method comprises the steps of obtaining a power dispatching semantic document needing to be processed by the power dispatching knowledge question-answering system; sequentially carrying out character-based segmentation, proposition conversion and proposition combination on the power dispatching semantic document on the basis of the large language model and the related cue words to obtain a plurality of text blocks; based on the large language model and the related prompt words, identifying and extracting entities related to power dispatching and relationships among the entities from each text block; constructing a local graph for each text block on the basis of the large language model and the related prompt words, the entities extracted from each text block and the relationship among the entities; traversing each text block, and combining all the local graphs into a global graph; and on the basis of the large language model and the related prompt words, according to the question type queried by the user, a reply text is correspondingly generated by matching a minimum local graph which is most related to the global graph in the global graph.
Owner:NORTH CHINA BRANCH OF STATE GRID CORPORATION OF CHINA +1
Archaeological cultural relic model training method and system
ActiveCN119443284AGuaranteed accuracyeasy to understandBiological modelsNatural language data processingData setEngineering
The invention discloses a model training method and system for archaeological cultural relics, and mainly relates to the technical field of artificial intelligence. Comprising the following steps: processing original archaeological cultural relic data, constructing an archaeological cultural relic knowledge base, and establishing a multi-modal data set; according to the established multi-modal data set and a public cultural relic multi-modal data set, training a multi-modal large model; and reasoning according to the user question in combination with an archaeological cultural relic knowledge base. The beneficial effects of the invention are that the method can better process and analyze archaeological cultural relic data, and provides a sustainable model training method for archaeological cultural relic research.
Owner:海看网络科技(山东)股份有限公司 +1
Touch and talk pen with AI interaction function
ActiveCN222545820Uachieve learningImprove interactivityElectrical appliancesComputer graphics (images)Human–computer interaction
The utility model discloses a touch and talk pen with an AI interaction function, and belongs to the technical field of touch and talk pens. Comprising a touch and talk pen point, a touch and talk pen holder, a display screen, a touch and talk module installed in the touch and talk pen holder, and a loudspeaker, a microphone and a control button which are installed on the side wall of the touch and talk pen holder. Wherein the touch and talk module is connected with the display screen, the touch and talk pen, the loudspeaker, the microphone and the control button, and communicates with an external AI server. The touch and talk pen provided by the utility model has multimedia interaction capability, and can realize AI autonomous teaching and learning.
Owner:东莞市臻兴电子科技有限公司
Phase change thermoacoustic engine experimental device
The utility model relates to a phase change thermo-acoustic engine experimental device which comprises a thermo-acoustic conversion system and an acoustic-electric conversion system. The thermo-acoustic conversion system comprises a sound production module and a Helmholtz resonant cavity, a ceramic plate stack soaked with water exists in the sound production module, and the stable temperature difference needed for generating the thermo-acoustic effect at the two ends of the ceramic plate stack is reduced. Sound waves generated by the thermoacoustic effect form standing waves in the Helmholtz resonant cavity, and the sound intensity is amplified; the acoustic-electric conversion system comprises piezoelectric ceramics and a triode common-emitter amplification circuit, the piezoelectric ceramics are arranged at the tail end of the resonant cavity and convert acoustic energy into electric energy, and the electric energy is amplified by the triode common-emitter amplification circuit and then drives a nixie tube to display. The experimental device integrates thermodynamics, fluid mechanics, acoustics, material science and electronic technology, has the characteristics of simple structure, low cost, rich physical process and strong exploration, is suitable for experimental teaching, particularly suitable for new engineering teaching requirements, and is beneficial to improving the multidisciplinary cross practice ability of students.
Owner:NANKAI UNIV
Personalized scenic spot content generation method, system and equipment based on multi-modal knowledge graph, and medium
PendingCN121958670Aclear structureClear depth of interestData processing applicationsDigital data information retrievalPersonalizationKnowledge graph
The invention relates to the technical field of smart tourism, in particular to a personalized scenic spot content generation method, system and device based on a multi-modal knowledge graph and a medium, and the method comprises the steps: collecting multi-modal data of a scenic spot, and constructing a structured multi-modal scenic spot knowledge graph based on the multi-modal data; obtaining personalized data provided by the tourist, and constructing a personalized portrait of the tourist based on the personalized data; in response to an operation of acquiring an image in a scenic spot, identifying the scenery in the image, and extracting a corresponding initial knowledge subset from the multi-modal scenic spot knowledge graph according to an identification result; performing personalized screening and expansion on the knowledge nodes in the initial knowledge subset by calculating the matching degree between the knowledge nodes in the initial knowledge subset and the tourist interest in the personalized portrait of the tourist, and dynamically binding multi-modal resources to generate a personalized knowledge graph; and presenting the personalized knowledge graph. According to the invention, the multi-mode scenic spot knowledge experience of which the structure is matched with the interest and the knowledge background can be provided for tourists.
Owner:SHANDONG LANGCHAO SMART CULTURAL TOURISM IND DEV CO LTD
DFA test case generation system and method based on vertical large language model
PendingCN119597655Aimprove interpretabilityEasy to adjustError detection/correctionNatural language data processingLinguistic modelAlgorithm
The invention discloses a DFA test case generation system based on a vertical large language model, and the system comprises an input module which is used for inputting a test specification document and reading data in the document; the preprocessing module is used for representing a small model which is exclusively used for processing and marking Chinese test specification documents and is finely adjusted and trained by a BERT word segmentation device through a two-way encoder of a Transform, and completing a document preprocessing task; the DFA construction module is used for converting unstructured data in the preprocessed test specification document into an exclusive coarse-grained DFA process framework with variables, states and state transition information generation test cases, and generating a stable and available DFA in a manner of fine tuning of an established DFA process generation large model; and outputting the function point DFA process data of the test specification document. The invention further discloses a DFA test case generation method based on the vertical large language model. According to the method, the accuracy rate and the coverage rate of the result are improved, and it is ensured that the generated test case can be directly applied to the actual test process.
Owner:SHANGHAI RUIN INTELLIGENT TECHNOLOGY CO LTD
A method and system for evaluating eco-design of express packaging products based on big data
ActiveCN118551646Bimprove accuracyHigh precisionData processing applicationsEnsemble learningEvaluation resultEcological data
The present invention discloses a method and system for evaluating the ecological design of express packaging products based on big data, including collecting ecological test data and production data of express packaging products, preprocessing the ecological test data and the production data, obtaining environmental ecological data through the ecological test data, performing ecological analysis on the production data to obtain process ecological data, performing fusion analysis on the environmental ecological data and the process ecological data to obtain an ecological function, constructing an ecological design evaluation model for express packaging products according to the ecological function, inputting express packaging product design data into the express packaging product ecological design evaluation model, and outputting an evaluation result. This method can not only improve the accuracy of ecological design evaluation of express packaging products based on big data, but also has good interpretability, and can be directly applied to the ecological design evaluation system of express packaging products.
Owner:CHINA NAT INST OF STANDARDIZATION
Intravenous infusion treatment management training method and system based on patient safety target
PendingCN119673409AImprove skills shortcomingsImprove professional qualityData processing applicationsDrug and medicationsCare personnelStatistical analysis
The invention relates to the technical field of medical training, in particular to an intravenous infusion treatment management training method and system based on a patient safety target. Presetting an evaluation time point, and carrying out capability evaluation on the nursing personnel based on a plurality of preset evaluation indexes; performing statistical analysis on an evaluation result of the evaluation index to obtain a first score corresponding to the evaluation index; setting a first weight for the evaluation index, and multiplying the first score by the first weight to obtain a first result; calculating a capability assessment score of the nursing personnel according to all the first results; dividing a plurality of ability grades based on the ability evaluation score, and determining a to-be-trained person according to the ability grades; determining training content based on the evaluation indexes of the to-be-trained personnel; acquiring a skill brief introduction of a nursing lecturer; matching the training content with the skill brief introduction, and determining a current training lecturer; a training time point is preset, and the current training lecturer trains the to-be-trained person based on the training content. The post competency of nursing personnel is rapidly improved, and the safety of patients is guaranteed.
Owner:SICHUAN ACADEMY OF MEDICAL SCI SICHUAN PROVINCIAL PEOPLES HOSPITAL
AI-based weekly report processing method, apparatus and device, and medium
PendingCN119396309Ashorten the timeReduce labor intensityNatural language data processingOffice automationInput controlProcess engineering
The invention provides an AI-based weekly report processing method and device, equipment and a medium, and the method comprises the steps: responding to a first triggering operation, and displaying a first input control in a target document; the user determines creation requirements through selection operation and provides input content through input operation; and after the input content is confirmed, generating corresponding first target content by utilizing the AI, and inserting the first target content into the target document after the user confirms the first target content. The weekly report processing efficiency can be improved.
Owner:CHINA LIFE INSURANCE CO LTD SHANGHAI DATA CENT
Digital service platform for rural integrated economic development
PendingCN119539510AImprove publicityeasy to manageData processing applicationsData displayData acquisition
The invention relates to the technical field of digital service platforms, and provides a digital service platform for rural integrated economy development, which comprises a data acquisition module, the data acquisition module is in communication connection with a data transmission module, and the data transmission module is in communication connection with a data detection module. The data detection module is in communication connection with a data analysis module, the data analysis module is in communication connection with an information integration module, the information integration module is in communication connection with a data display module, and the data display module is in communication connection with a new media sharing module; and through the data display module, the staff can more conveniently propagandize and popularize the economic industry reversal trend, so that a more convenient and better effect is achieved, the working intensity of the staff is reduced, the scope of knowledge of the public is widened, and a better and wider development direction is achieved. Through the technical scheme, the problems of manpower consumption and low economic development efficiency in the prior art are solved.
Owner:HUNAN SANTONG HUILIAN TECH CO LTD
Intelligent sound equipment audio playing control method and system
PendingCN121862120Aunderstanding subjectivityUnderstand the needsSpeech recognitionPersonalizationInteractive technology
The invention discloses an intelligent sound equipment audio playing control method and system, and belongs to the technical field of voice interaction. The method comprises the following steps: obtaining current multi-dimensional context information; if the voice instruction is a semantic fuzzy instruction appearing for the first time, creating an initial semantic anchor point, and storing the initial semantic anchor point into a personalized semantic network; positioning context coordinates based on the personalized semantic network; judging the type of the voice instruction intention; if the instruction intention is a playing request, obtaining a target audio and playing the target audio; if the instruction intention is meta inquiry, knowledge answers are generated and output; and monitoring a subsequent feedback behavior of the user on the playing result. According to the method, the personalized semantic network is constructed to analyze the semantic fuzzy instruction, refined retrieval is realized based on context sensing, and a meta-inquiry processing mechanism is established to generate the knowledge answer, so that the problems that in the prior art, the intelligent sound equipment cannot understand abstract description, is difficult to process negative instructions and cannot answer related inquiry of audio content are solved.
Owner:ZHUHAI FULLWING ELECTRONIC CO LTD
An interview guidance method and system based on big model and artificial intelligence
ActiveCN118606453Bimprove abilitiesBroaden their knowledgeSpecial data processing applicationsNeural learning methodsLinguistic modelData set
The present invention proposes an interview guidance method and system based on a large model and artificial intelligence, the method comprising: collecting interview guidance data; performing preprocessing, using a large model to convert the data into a high-dimensional vector, using a machine learning model to extract semantic features and time series features according to semantic information, and extracting emotional features; constructing a dynamic knowledge graph database according to semantic features, time series features and emotional features; using natural language processing technology to extract key features and construct an interview guidance model; constructing a deep learning interview score prediction model to predict interview scores according to a recommended user data set; designing a user privacy mechanism; designing a simulated interviewer model according to a recommended user data set, and obtaining a result to form a report output to the user. The present invention integrates a large language model, natural language processing, machine learning technology and privacy protection technology, and uses a number of advanced technologies and design concepts to improve the success rate of user interviews.
Owner:北京粉笔蓝天科技有限公司
Three-dimensional cultural relic multi-angle rotating display device
Owner:XIAN EURASIA UNIVERSITY
A child camera
ActiveCN224555705Uimprove cognitive abilityBroaden their knowledgeComputer graphics (images)Radiology
The application discloses a child camera, which comprises a shell, a main control module arranged in the shell, a camera module, a display module and an audio module which are electrically connected to the main control module respectively, the camera module and the display module are arranged on opposite two end faces of the shell respectively, the camera module comprises at least two cameras, at least one of which has an optical zoom function, the main control module is further communicatively connected to an object recognition module, the object recognition module is adapted to recognize objects in images captured by at least one of the cameras and acquire text, picture and / or sound information related to the objects, and the main control module is adapted to receive the relevant text, picture and / or sound information and control the display module to display the text and / or the picture and control the audio module to play the sound information, so as to help children understand the name, characteristics, use and other information of the objects and promote the improvement of their cognitive ability.
Owner:NINGBO TIANTIAN STATIONERY CO LTD
Loom spliced toy for children
The utility model discloses a loom spliced toy for children, which belongs to the technical field of toys for children and comprises a stone-shaped base, a loom fixing rod is vertically inserted into one end of the top of the stone-shaped base, a rotating shaft is vertically inserted into the top of the side edge of the loom fixing rod, and a spherical protrusion is arranged at one end of the rotating shaft. The end, away from the protrusion, of the rotating shaft penetrates through the loom fixing rod, and a tail end fixing cover for limiting the position of the rotating shaft is inserted into the end, away from the protrusion, of the rotating shaft. According to the utility model, the loom is combined with the tenon-and-mortise structure to design a modularized toy model, so that the working principle of a real loom can be simulated, children can learn spinning knowledge during playing, and the children can deeply understand the wonderful of the tenon-and-mortise structure and the charm of the traditional wooden skill by splicing the tenon-and-mortise components personally; meanwhile, a brand-new toy product which can be used for entertainment and education is provided, so that children can learn traditional culture during playing, the insight is increased, and the ability is improved.
Owner:FOSHAN UNIVERSITY