16 results about "Word model" patented technology

The invention discloses an intelligent test paper composition and scoring method and system based on a knowledge graph. The method comprises the following steps: S1, constructing a student knowledge graph state sub-graph; s2, constructing a question bank knowledge graph; s3, on the basis of a node embedding modeling method of an improved DeepWalk algorithm, performing joint training and low-dimensional representation learning on knowledge point nodes by utilizing a continuous bag-of-words model of multi-head context aggregation, and constructing a topic adaptation degree scoring index; s4, outputting an optimal test paper scheme set; s5, collecting a current answer record when the student completes the test paper; and S6, extracting a semantic feature vector and a behavior feature vector, constructing a fusion score feature vector, and generating scores of test paper subjective question answers. According to the invention, accurate test paper composition and multi-dimensional subjective question intelligent scoring for individual knowledge states of students are realized, the method is suitable for personalized learning evaluation and teaching feedback scenes in an education evaluation platform, and the method has the advantages of high personalization, fine feedback and automatic scoring.

The invention discloses a power grid operation violation dictionary construction and automatic classification method and system, and relates to the technical field of operation violation classification, and the method comprises the steps: carrying out the text preprocessing of power grid operation data; constructing an initial word vector space based on Jieba word segmentation and a word bag model; considering the problem that an initial violation dictionary obtained by initial word segmentation has many semantic similar or repeated word segmentation redundancy, introducing skewness and kurtosis based on a relative frequency matrix to construct a unique index, selecting key segmented words, further constructing a classical violation dictionary, and forming a keyword vector space; and establishing a violation classifier according to the obtained keyword vector space and the corresponding violation type label, and intelligently realizing automatic classification of violation codes, violation types and problem types. Intelligent classification of violation codes, violation types and problem types is completed according to unstructured text data formed by power grid field operation violation description.

The application discloses a kind of unmanned aerial vehicle monocular vision inertial SLAM loop detection methods based on undergrowth trunk geometry, the method includes the following steps: step 1, trunk region segmentation and three-dimensional point cloud generation;Step 2, trunk clustering detection and position positioning;Step 3, triangular geometric feature construction and screening;Step 4, multidimensional similarity calculation;Step 5, geometric and visual joint decision and loop confirmation.This method extracts stable geometric information of trunk by driving depth data, constructs triangular features with invariance with trunk position as vertex to break through the dependence of visual texture, realizes double-path independent detection and joint decision by combining traditional visual bag-of-words model, balances detection accuracy and real-time through adaptive matching strategy, thereby effectively improves the accuracy, robustness and environmental adaptability of loop detection in undergrowth GNSS-free environment.

The application provides a task allocation model construction method and system for a heterogeneous intelligent agent, and the method comprises the following steps: determining a target heterogeneous intelligent agent in real time, and matching a target performance parameter corresponding to the target heterogeneous intelligent agent in a preset database in real time; creating a corresponding professional term vocabulary according to the target performance parameter based on a preset rule in real time, and converting the professional term vocabulary into a plurality of distributed vectors corresponding thereto through a preset continuous bag-of-words model in real time; and training a task allocation model for the target heterogeneous intelligent agent according to a preset bidirectional long short-term memory network and the plurality of distributed vectors in real time, wherein each distributed vector has uniqueness. The task allocation model can objectively and accurately complete the task allocation of the heterogeneous intelligent agent, and the work efficiency is greatly improved.

The application is suitable for the field of automatic driving technology, and provides a dynamic scene autonomous positioning and mapping method fusing a bag-of-words model, comprising the following steps: recording environment data; constructing a point cloud map and aligning the map to a geodetic coordinate system, selecting a visual key frame and saving the corresponding pose; removing dynamic features in the visual key frame to generate a bag-of-words vector, constructing a mapping relationship between the bag-of-words vector and the pose, and saving the bag-of-words model; in the positioning process, preprocessing the constructed point cloud map, generating a bag-of-words vector by using static features of the camera collected image, searching in the constructed bag-of-words model, and mapping out the initial position of the vehicle; after completing the positioning initialization, performing registration, providing a registration initial value by fusing the bag-of-words model and GPS / IMU, and outputting the pose information of the vehicle in real time. The application solves the problem that the SLAM framework cannot obtain absolute pose and the problem that the autonomous parking positioning information is missing due to the shielding of signals such as GPS.

Embodiments of the present application relate to a positioning method and device of a mobile device, an electronic device and a storage medium. A key frame is acquired by a vision camera installed on the mobile device; mapping information and a feature descriptor of the key frame are determined; a bag-of-words model and a key frame image database are obtained according to the feature descriptor of the key frame; a current image frame is acquired, and the current image frame is converted into a current frame bag-of-words vector based on the bag-of-words model; a candidate key frame with the highest matching score with the current image frame is determined from the key frame image database according to the current frame bag-of-words vector, and a target key frame is determined according to the candidate key frame; a target node index corresponding to the target key frame is determined according to the mapping information, and pose information of the mobile device is calculated according to the target node index, so as to position the mobile device; that is, the prior pose of the mobile device is provided by the bag-of-words model, and the positioning accuracy is improved.

Embodiments of the present application provide a relationship extraction method and device, the method comprising obtaining a first entity set and a first text feature from a corpus corresponding to a first target field, and mapping the first entity set and the first text feature into first vector data through a bag-of-words model, then inputting the first vector data into M classification models respectively to obtain M prediction results, and determining a final relationship of each first entity pair in the first entity set from N candidate relationships according to the M prediction results, each prediction result comprising a prediction probability of an inter-entity relationship of each first entity pair in the first entity set being respectively one of the N candidate relationships, and each classification model being obtained by training an initial model according to a second entity vector with a second relationship vector label and a second text vector of a corresponding source knowledge base. In this way, using transfer learning as a relationship extraction method, the knowledge of the source field is migrated to the target field, and the required professional annotation manpower can be reduced.

This invention relates to a heuristic-based method for generating fault patterns in the aviation field, comprising: S1, extracting features from aviation fault text data using a bag-of-words model and the term frequency-inverse text frequency index method; S2, performing clustering category analysis of aviation fault text data based on k-means heuristics; S3, detecting outliers, extracting faults, and concatenating faults in the aviation fault text data to obtain fault pattern names; and S4, processing the obtained fault description text in real time to generate aviation fault patterns. This invention completes text data clustering category analysis using a bag-of-words model, the term frequency-inverse text frequency index method, and the k-means heuristic method. Furthermore, it obtains fault pattern names through outlier detection, fault extraction, and concatenation, enabling real-time detection of fault text data. By periodically re-clustering, it can discover new fault patterns by utilizing existing prior knowledge, thereby improving the accuracy and effectiveness of fault pattern detection.

This application relates to the field of artificial intelligence technology and discloses a method, apparatus, device, storage medium, and computer program product for enhancing prompt words. The method includes: analyzing the code of the coding development framework on which the multi-agent system depends, constructing the code flow of the multi-agent system based on the analysis results, constructing a business prompt word model based on the code flow, performing multi-dimensional detection on prompt words through the business prompt word model, and enhancing the prompt words based on the detection results. This application achieves full-process tracking of prompt words by analyzing the code of the coding development framework on which the multi-agent system depends, and performs multi-dimensional detection on prompt words by constructing a business prompt word model, thereby identifying complex security issues generated by the interaction of multiple prompt words, providing a systematic prompt word security guarantee mechanism for the multi-agent system, and thus improving the security and reliability of the multi-agent system.

This invention belongs to the field of smart home, specifically an offline voice command word update method, comprising the following steps: S1: hierarchical model construction; S2: dynamic model compression and distribution; S3: hot patch writing in idle frames; S4: hierarchical collaborative recognition. This invention dynamically loads new command word models by allocating a dedicated extended model area, utilizes system idle frames for data writing, achieving "zero downtime" updates. It avoids redundant calculations through a dual-model parallelism and feature sharing mechanism, and only activates the extended model for secondary matching when the confidence of the base model is insufficient. Furthermore, it employs "8-bit vector quantization + cepstral residual coding technology" to compress the extended command words, reducing the size of a single command to an extremely small volume.

The application discloses a stable control system control strategy text vectorization method for strategy quick search, and the method is based on the text information of the stable control system control strategy, specifically including condition information and result information; based on an improved bag-of-words model and specific coding rules, a high-dimensional vector corresponding to the stable control system control strategy text information is obtained, and vectorization of the stable control system control strategy is realized. The method provided by the application gives a new idea for stable control strategy search, changes the control strategy text matching into vector matching, and realizes stable control strategy search with faster speed and higher efficiency. The embodiment shows that the method has significant performance advantages, and the strategy search time is greatly reduced compared with the text matching method, which is of great significance for improving the complex working condition adaptability of the stable control system and guaranteeing the safe and stable operation of the power grid.

The application relates to the field of artificial intelligence and smart home technology, and specifically provides a home algorithm network host application method and system. After the home algorithm network host is powered on, a voice module, a semantic understanding module, an AI monitoring module, a system control module and a communication module are started in sequence; the voice module loads a wake-up word model and VAD parameters, and is ready to receive user voice input; the semantic understanding module realizes semantic analysis and context understanding; the AI monitoring module starts a camera and an environment sensor, realizes real-time collection of video streams and environment data; the system control module initializes a local device interface, and provides interface support for home appliance control; the communication module establishes an internal message queue and an external network interface, and provides guarantee for data interaction among modules and external device communication. Compared with the prior art, the application can construct a high-performance, low-delay, safe and reliable home smart algorithm network host, and provides an integrated solution for home environment control and home security.

The application provides a satellite denial high-altitude hovering positioning method based on visual perception and inertial measurement, which is applied to a UAV control system, and the UAV control system comprises a front-end processing module and a back-end processing module, wherein the front-end processing module performs the following steps: performing ORB feature detection and extraction on a ground environment image shot by a downward-looking binocular camera to obtain spatial coordinate information of feature points; constructing a key frame dictionary library based on a bag-of-words model, and completing loop detection through similarity calculation of the feature points; realizing initial pose estimation based on a PNP algorithm and inertial measurement unit (IMU) pre-integration to generate an initial estimated pose sequence; wherein the back-end optimization module performs the following steps: performing real-time optimization on the initial estimated pose sequence by using a sliding window optimization algorithm; solving maximum a posteriori probability estimation by using an L-M optimization algorithm to determine a target high-altitude hovering positioning pose.

This invention discloses a method for recommending points of interest (POIs) in different locations based on user preferences and personalized preference transfer, belonging to the field of terminal location-based recommendation. The method includes: constructing a heterogeneous hypergraph for five different types of nodes, and obtaining user preference representations through training the hypergraph; constructing a POI-category graph, and learning POI representations through a continuous skipping word model; constructing an attention network with POI representations as input to obtain user-transferable features; constructing a parameter learning network using a multilayer perceptron and user-transferable features as input, and constructing a transfer network with user preference representations as input and the output of the parameter learning network as parameters to achieve personalized user preference transfer; constructing a geographic map between POIs based on latitude and longitude, and learning the embedding representations of different POIs through a convolutional network; calculating the score for each POI by combining the user's transferred preferences with the embedding representations of different POIs, thus completing the final recommendation.

A method and system for geological hazard early warning in tunnel construction by a drill-and-blast method. The method comprises: acquiring construction information of historical tunnels constructed by a drill-and-blast method, and determining risk levels thereof; constructing individual bag-of-words models of the construction information under different risk levels, and constructing a shared-vocabulary bag-of-words model and a full-vocabulary bag-of-words model; calculating the word frequency of each vocabulary item in the full-vocabulary bag-of-words model and the word frequency thereof in each individual bag-of-words model, and constructing a full-vocabulary word frequency table and a risk-level-vocabulary word frequency table; on the basis of the risk-level-vocabulary word frequency table, calculating the risk-level word frequency quotient of each vocabulary item, so as to determine the score of each vocabulary item; and removing, from a bag-of-words model to be tested, vocabulary items in the shared-vocabulary bag-of-words model to obtain a feature bag-of-words model, calculating the word frequency of each vocabulary item in the feature bag-of-words model to obtain a vocabulary word frequency table to be tested, and calculating the word frequency quotient of the vocabulary word frequency table to be tested and the full-vocabulary word frequency table to obtain a hazard early-warning risk level of a tunnel to be tested in a construction period, thereby providing timely hazard early warning for a tunnel under construction.

The embodiment of the invention discloses a method and equipment for optimizing data query based on a quantum technology and a medium. The method comprises the following steps: acquiring query text data of a user at a current moment and in a historical time window, preprocessing the query text data, and constructing a bag-of-words model; performing quantum state coding on the feature vectors in the word bag model, and extracting dominant feature vectors of the query text data through a quantum principal component analysis algorithm; based on the dominant feature vector, retrieving a plurality of data items satisfying a similarity condition with the dominant feature vector from a target database, and generating a preloaded data set; and loading the preloaded data set into the head position of the LRU cache chain table according to the similarity sequence of the preloaded data set and the dominant feature vector. According to the embodiment of the invention, the features of the data can be extracted more quickly, the features of the data can be distinguished, and the data with similar features can be found more quickly in the face of large-data-volume and high-dimension data.