249 results about "False recognition" patented technology

The invention relates to the technical field of intelligent home control, and discloses a control method and a control system of an intelligent sound box. The control method of the intelligent sound box is applied to a control device, and specifically comprises the following steps: S101, collecting a voice instruction of a user, carrying out noise reduction processing and voiceprint feature extraction on the voice instruction, transmitting the processed voice instruction to a semantic analysis engine, carrying out intention recognition on voice content based on a deep learning model, and sending the intention recognition result to a semantic analysis engine; generating a structured operation instruction set; and S102, according to the device identifier contained in the structured operation instruction set. Through dual authentication of voiceprint feature extraction and dynamic verification phrase, the illegal access false recognition rate is reduced to below 0.12%, the voiceprint database is combined with the Mel frequency cepstrum coefficient and the dynamic time warping algorithm, accurate matching of user identities is achieved, the dynamically generated verification phrase comprises random initial and final combinations, and recording playback attacks are effectively resisted.

The invention relates to the technical field of wireless, and provides a target sensing method, device and equipment, a storage medium and a program product, the target sensing method is applied to network equipment, and the method comprises the following steps: determining type information of a sensing target in a sensing result based on the sensing result and RID information under the condition that the sensing result and the RID information exist; wherein the sensing result is obtained by performing target sensing by the network equipment; the RID information is sent by the RID receiver. According to the invention, under the condition of determining that the sensing result and the RID information exist, the RID information can be used as the auxiliary information to assist the base station to carry out data processing in the sensing result, and the type information of the sensing target in the sensing result is accurately determined, so that the sensing result and the RID information are fused, and the sensing accuracy is improved. The method can solve the problem that the general sensing integrated system is easy to mistakenly recognize the target type when detecting the target, thereby improving the credibility of the detection result, and guaranteeing the reliability of the general sensing integrated system.

The invention provides a CAD (Computer Aided Design) drawing error recognition method utilizing deep learning, which relates to the technical field of image data processing and comprises the following steps of: constructing a primitive structure by reading primitive information of a CAD drawing; extracting image features of the drawing based on the feature extraction network to perform semantic modeling on the primitive structure to obtain a primitive structure semantic model; identifying a nested primitive pair; performing edge detection and contour fitting on the nested primitives, and extracting nested edge coordinate points; and obtaining nested edge coordinate points of the nested primitives, generating a boundary constraint range by using the nested edge coordinate points to carry out error recognition on the nested edge coordinate points, and carrying out interactive feedback correction according to an output error recognition result. According to the method and the device, the technical problem that errors in a nested structure are difficult to find timely and accurately due to the lack of intelligent recognition capability for the primitive nesting relationship in the prior art is solved, and the technical effect of improving the CAD drawing error recognition accuracy is achieved.

The invention belongs to the technical field of face data dynamic verification, and particularly relates to a centralized dynamic verification and risk defense method based on face data. According to the method, multi-dimensional dynamic indexes such as micro expressions, iris responses and blood flow fluctuations are fused, the detection capacity of attack means such as deep counterfeiting, face masks and picture screenshots is greatly improved, the false recognition rate and the missed recognition rate are reduced, external risks such as equipment integrity, network security and geographical position deviation are fused into comprehensive evaluation, and the method is high in practicability. The face self is concerned, the whole verification environment can be safely controlled, more comprehensive defense is realized, once a threshold alarm is triggered, multi-level defense measures can be immediately started, the defense result is fed back to the model, the discrimination boundary of the generative adversarial network is continuously optimized, and high efficiency and robustness in long-term operation are ensured.

The invention relates to a data correction method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring an original structured statement and original annotation information; determining knowledge data corresponding to the original structured statement in a target knowledge database based on a metadata query engine; the knowledge data comprises graph relation metadata and semantic vector metadata; according to the data correction large model, the graph relation metadata and the semantic vector metadata, error recognition is carried out on the original structured statement and the original annotation information, data correction is carried out on error data obtained through error recognition, and a target structured statement and target annotation information are obtained. By adopting the method, the accuracy of structured statement and annotation error correction can be improved.

The invention relates to the technical field of honing positioning, in particular to an automobile part positioning method and system for numerical control machine tool machining, and the method comprises the steps that a grey-scale map of an engine cylinder body fixed to a station is obtained, and the engine cylinder body is provided with a standard positioning hole; constructing a feature point for each pixel point in the grey-scale map, wherein the feature point represents the position and grey-scale value information of the corresponding pixel point; and classifying the feature points by using a condensation type hierarchical clustering algorithm to obtain a plurality of optimal clusters, calculating the possibility that each optimal cluster is a positioning hole region, taking the region corresponding to the optimal cluster with the possibility located in a preset threshold interval as the region of the positioning hole, and obtaining the position coordinates of the positioning hole. And the positioning center of the engine cylinder body cylinder hole is further obtained. According to the method, the phenomenon of wrong recognition during clustering combination is avoided, and the positioning hole can be accurately recognized and distinguished from other hole areas.

The invention discloses a living body collateral state monitoring method and a related device, and relates to the field of data processing, and the method comprises the steps: obtaining the acoustic features, image features and positioning features of a monitored object, recognizing the scene of the environment where the monitored object is located at present, and determining the target weight distribution matched with the scene. And carrying out weighted fusion on the obtained acoustic features, image features and positioning features of the monitoring object based on the target weight distribution to obtain multi-modal fusion features. And finally, identifying the abnormal state of the monitored object based on the multi-modal fusion feature. According to the method, the complementary effect of the acoustic features, the image features, the positioning features and other dimension features is utilized, the recognition accuracy is improved, and the false recognition rate is reduced. Moreover, the scheme can identify the scene of the current environment and automatically adjust the weight distribution of each modal feature according to the scene characteristics to generate the unique fusion feature vector, and the robustness of the model to the environment is improved.

The invention relates to a voice recognition method and device of a vehicle, the vehicle and a storage medium, and the method comprises the steps: collecting a voice instruction of the vehicle; in response to the voice instruction, acquiring video data corresponding to the voice instruction, and determining weights of the voice instruction and the video data according to the internal noise level of the vehicle; and based on the voice instruction and the weight of the video data, fusing the video data and the voice instruction to identify an actual control intention of the user, and controlling the vehicle to execute a control action corresponding to the actual control intention. According to the embodiment of the invention, the complementarity of the voice data and the video data can be utilized, more accurate voice recognition is realized, the limitation on the pronunciation standard of the user is reduced, the voice recognition is more humanized, the probability of wrong recognition is reduced, and the interaction experience of the user is improved.

The invention discloses an error detection method and system in a programmed task video, relates to a video time sequence action segmentation and anomaly detection technology, and realizes robust error detection aiming at the problem of accuracy of error recognition in the programmed task video. According to the method, firstly, a time sequence action segmentation model is trained, a Gaussian mixture model is trained for each action category by utilizing each frame feature of an intermediate layer of the time sequence action segmentation model, the frame features are sent to the Gaussian mixture model of the corresponding action category to be processed, the log-likelihood score of the frame is obtained, and the detection of the frame level anomaly is realized. According to the method, the problem of error detection in the first-view programmed task video can be effectively solved by combining action segmentation and anomaly detection methods, and the method can be used for scenes requiring accurate recognition of sequence action errors.

A system and method for automated defective data record resolution is disclosed. The method is performed by a remote digital claim remediation service operating within a distributed network of computers. The method includes receiving adverse digital claim data comprising a plurality of data fields, where at least one data field contributes to an adverse action against a target digital claim. A feature extraction model processes the claim data to extract defect feature data. A machine learning model then computes defect inferences, identifying likely defect types and associated confidence values. The method further evaluates these inferences against predefined routing criteria, routing the claim data either to a remediation or disposal queue. For remediable claims, a machine learning model generates remediation inferences, which are applied to adapt and correct the claim. The defect-free claim is then resubmitted in real-time or near real-time, accelerating claim processing and enhancing system efficiency.

The invention relates to the technical field of BIM intelligent design and deep learning, in particular to a graph structure representation and model error recognition method and device of a BIM model, and the method comprises the steps: extracting semantic features, spatial features and topological features among various types of components according to the component information of different types of components in the BIM model; generating corresponding graph structure representation based on the semantic features, the spatial features and the topological features, and constructing a training data set by using the graph structure representation; and training the pre-training graph neural network model by using the training data set to obtain a trained training model, and carrying out transfer learning by using the trained training model to identify an error identification target of the BIM model by using a transfer learning model. Therefore, the problems that in the related technology, specific complex semantics, space and topological features of the BIM bring challenges which are difficult to neglect, and the BIM cannot be perfectly suitable for a pre-training and transfer learning model of the features of the BIM are solved.

The invention belongs to the technical field of medical rehabilitation, and discloses a rehabilitation treatment monitoring system based on multi-modal sensing and AI evaluation. A multi-dimensional skeleton key point confidence evaluation mechanism is established by integrating three types of sensing data of visual skeleton tracking, an inertial measurement unit and pressure distribution, and potential tracking interruption risk frames and error recognition candidate frames are recognized in real time. And a multi-modal fusion correction model is adopted to carry out accurate compensation on error recognition, missing data are reconstructed in combination with a skeleton motion mode memory bank and a bidirectional time sequence prediction algorithm, and a continuous and complete all-day skeleton motion sequence is generated. On the basis of the calculation, the time-phased activity level index and the rehabilitation action completion degree score of the patient are calculated, and an objective and quantitative rehabilitation evaluation basis is provided. According to the invention, the stability and continuity of skeleton tracking in a complex rehabilitation environment are improved, so that a medical team can obtain a real and complete all-day activity portrait of a patient, accurately position a rehabilitation bottleneck, formulate a personalized treatment scheme and promote functional recovery of the patient.

The invention discloses a man-machine text data set construction method and system for AI generated text detection, and relates to the technical field of text detection.The method comprises the steps that a human text is obtained and preprocessed, and metadata annotation is conducted on the preprocessed human text; selecting a plurality of language models, generating an intelligent text by configuring different generation parameter combinations, and performing metadata annotation on the intelligent text; and fusing the human text and the intelligent text subjected to metadata labeling, constructing a structured human-computer text data set, and dividing the human-computer text data set. According to the method, high-quality and large-scale data collection of the data set is ensured through data cleaning, quality screening and source labeling, rich learning samples are provided for the model, misjudgment caused by the quality problem of the existing data set is avoided, the accuracy rate, the precision rate and the recall rate can be improved, the risk of misrecognition is reduced, and the recognition efficiency is improved. And the reliability of detection results is enhanced.

The invention discloses a children voice expression error recognition and correction method based on comparative learning, and the method comprises the steps: carrying out the preprocessing of an inputted children voice signal, obtaining a logarithmic Mel spectrum feature sequence, and converting the logarithmic Mel spectrum feature sequence into voice semantic coding features through an improved Transform encoder; on the basis of an age-adaptive positive and negative sample selection mechanism, voice features are optimized by using a comparative learning method, and an enhanced voice representation vector is obtained; constructing a multi-modal fusion network, combining an enhanced voice vector and BERT language model features, realizing adaptive fusion through multi-head cross attention and a gating mechanism, adopting a bidirectional LSTM to design an error positioning module to recognize the position and the type of a pronunciation error, and using a joint loss function to execute end-to-end training; standard correction audio is generated according to the error type, and correction guidance is provided for children. According to the invention, high-precision recognition, positioning and correction of children's speech expression errors are realized, and technical support is provided for children's language development.

The invention provides a homework correction mark leaving method based on AI. The method is applied to the technical field of teaching and artificial intelligence, and comprises the following steps: S1, obtaining an original input image of a paper job; s2, adopting an OCR model based on a cross attention mechanism to perform accurate text recognition and structured cleaning and preprocessing of text data on the writing content in the original input image to obtain high-dimensional text features; s3, constructing an answer judgment and error recognition model, introducing an improved discrete laying hen algorithm to perform feature selection and model training, and outputting an error classification result; s4, generating a simulation correction trace and a traceable scoring log according to the error classification result and the original homework image; and S5, mapping the error type with a standard knowledge structure in the knowledge point library to generate a customized lecture. According to the invention, the accuracy, interpretability and teaching suitability of homework correction are obviously improved.

The invention relates to the technical field of writing error recognition, and discloses a Chinese writing error intelligent recognition method and system based on a deep neural network, and the method comprises the following steps: 1, obtaining a target single Chinese character image after binarization processing, and obtaining a normalized binary font image; 2, skeleton extraction and node labeling are carried out on the normalized image, and a font topological graph is constructed; 3, determining a structure normal form label based on the topological graph and image projection, and dividing parts to obtain an outer surrounding region, an inner part region, left and right parts and intersection information; step 4, calculating consistency measurement of surrounding, left-right and cross structures; step 5, obtaining a corresponding standard measure in combination with the standard font of the target Chinese character, setting a fixed tolerance to form a standard parameter interval, and generating a structural feature vector; and step 6, outputting a writing error recognition result according to the deep neural network model. According to the invention, automatic identification and error type determination of Chinese writing structural errors are realized.

The present disclosure describes a method and apparatus for an error remediation recommendation process based on multiple data sources. Aspects of the disclosure may provide for processing of a knowledgebase to identify error remediation recommendations, processing of a chat log to identify error remediation recommendations, identification of errors from log data, determination of a corresponding error remediation recommendation from the knowledgebase and / or the chat log, and causing display of output indicating a corresponding error remediation recommendation. Further aspects described may also provide for training of an artificial neural network to determine a corresponding error remediation recommendation. Further aspects described may also provide for a browser extension which scrapes the Document Object Model (DOM) of a web page to identify errors.

The present application relates to the technical field of autonomous driving, and specifically discloses an obstacle filtering method and apparatus, a computer device, and a storage medium. The method comprises: first, acquiring first position information of a first bounding box corresponding to a target vehicle and second position information of a second bounding box corresponding to each candidate obstacle; then on the basis of the first position information and the second position information, determining the degree of overlap between the first bounding box and the second bounding box; and finally, using a candidate obstacle with the degree of overlap reaching a preset overlap level as an obstacle to be filtered and filtering same. The degree of incorrectness of candidate obstacle recognition is determined by determining the degree of overlap between the first bounding box and the second bounding box, and on the basis, whether the incorrect recognition of the current candidate obstacle would trigger incorrect issuing of a driving instruction is determined; and if the degree of overlap reaches the preset overlap level, the candidate obstacle is determined as an obstacle to be filtered and is filtered, thereby avoiding the incorrect issuing of driving instructions, and ensuring the stability and safety of autonomous driving processes.

The invention relates to the technical field of identity verification, in particular to a conference sign-in bimodal identity verification and data automatic matching system, which comprises a bimodal acquisition module for activating a face image sensor to continuously capture multiple frames of face images, synchronously starting a microphone array to directionally pick up voiceprint information in a voice instruction, and generating an original biological data stream. In the invention, through synchronous acquisition of the face image and the voiceprint information, continuous frame image capture and environmental noise reduction are utilized to ensure that high-quality biological characteristic data is obtained, and verification accuracy is effectively improved. The accuracy of identity recognition and risk assessment is enhanced by sensing contextual information such as conference importance level, sign-in time and physical security level in real time and comprehensively considering behavior characteristics of equipment operated by a user at the same time. In the feature matching stage, a facial key point geometrical relationship and a voiceprint Mel-frequency cepstrum coefficient are extracted, and biological feature comparison is carried out, so that the false recognition rate and the missed recognition rate are reduced.

The invention provides a mathematical formula processing method and device, computer equipment and a readable storage medium, and relates to the field of formula editing. The method comprises the following steps: acquiring a mathematical formula text, and identifying a to-be-processed mathematical formula in the mathematical formula text; performing error recognition on the mathematical formula to be processed through a pre-constructed formula error recognition strategy; for non-start-stop character errors existing in the to-be-processed mathematical formula, repairing the non-start-stop character errors of the to-be-processed mathematical formula through a target repairing rule corresponding to the non-start-stop character errors; and aiming at the start-stop character errors existing in the to-be-processed mathematical formula, repairing the start-stop character errors of the to-be-processed mathematical formula through a pre-constructed start-stop character recognition repair model.

The invention provides an application packaging processing method, a storage medium and electronic equipment, and is applied to the technical field of software application. According to the method, a full-process closed-loop mechanism of the front stage, the middle stage and the rear stage of packaging is constructed; before packaging, application codes and key parameters are subjected to security detection; in the packaging process, grammar and semantic errors are deeply recognized through a regular engine, an abstract syntax tree and data flow analysis, and a diagnosis report is generated; and after packaging, executing an automatic test by utilizing the matched test case to obtain an application test result. Based on the diagnosis report and the test result, whether repackaging is needed or not is intelligently analyzed, packaging parameters and test cases are adjusted according to the error types and fed back to a safety detection link in a circulating mode, automatic error recognition and self-adaptive optimization are achieved, and therefore the safety and reliability of application packaging are effectively improved, and the development risk is reduced.

A method or system for enhancing vehicle identification accuracy. The system identifies a gap in a training dataset for training a license plate identification model. The gap represents underrepresented visual characteristics in misidentified license plates. A guidance prompt is generated based on the visual characteristics of the misidentified license plate. Condition embeddings are then generated from the guidance prompt, which are used to condition a diffusion model to create synthetic license plate images. The diffusion model is trained to receive a real license plate image, encode it into a vector, apply forward diffusion to add noise, and then apply reverse diffusion to remove the noise, resulting in a denoised vector that represents a synthetic license plate image conditioned by the condition embeddings. The denoised vector is then decoded to produce the synthetic license plate image. The synthetic images are then used to retrain the license plate identification model.

The invention discloses a blade defect identification model training method and a blade defect identification method, which are applied to the field of blade defect detection, and are characterized in that video images and infrared images collected by a wind turbine generator blade patrolled by an unmanned aerial vehicle are fused to obtain a fused image; performing feature enhancement processing on the fused image to obtain a feature enhanced image, inputting the feature enhanced image into a blade defect recognition model for feature extraction to obtain a feature map, and performing image segmentation on the feature map to output a defect probability map to determine a model loss value under physical constraints; and updating model parameters of the blade defect identification model based on the model loss value until the trained blade defect identification model is obtained. Video images and infrared images are collected through inspection of the unmanned aerial vehicle, fusion and feature extraction are carried out on the images to train the blade defect recognition model to carry out defect recognition, various defects on the blade surface of the wind turbine generator can be rapidly and accurately detected, the detection precision is effectively improved, and the error recognition rate is reduced.

The present invention belongs to the technical field of voiceprint recognition and discloses a feature-based intelligent voiceprint recognition method and system; the method comprises: collecting a plurality of voiceprint data samples and preprocessing each voiceprint data sample to obtain a comprehensive voice sample; constructing a voice directed graph model based on the comprehensive voice sample, and identifying a core voice sample set from the voice directed graph model; extracting features from the core voice sample set to obtain #imgabs0# comprehensive feature vectors; obtaining a sample selection strategy using a clustering algorithm based on the comprehensive feature vectors and the core voice sample set; adaptively training a voiceprint recognition model using the sample selection strategy based on the comprehensive feature vectors; and applying the trained voiceprint recognition model to voiceprint recognition after the training is completed, thereby giving full play to the advantages of deep learning in the field of voiceprint recognition, not only improving the speed and efficiency of voiceprint recognition, but also reducing the system's false recognition rate and missed recognition rate.

The present application relates to the technical field of face recognition, and particularly relates to a recognition method and system based on a dynamic face database, a computing device and a storage medium, comprising a face tracking server configured to acquire face information obtained by a channel camera and a regional camera, and to merge the face information obtained by the channel camera and the regional camera; a central face server configured to store face information left by a user when registering remotely, and to respectively identify face information collected by the face tracking server from the channel camera and the regional camera, and to send the identification results to a channel face server and a regional face server; the present application reduces the number of face databases by using face tracking and face recognition technology, forms a face server with multiple face databases, improves the recognition efficiency by accurately simplifying the face databases, and reduces the false recognition rate of face recognition.

The embodiment of the invention discloses a wrongly written character processing method, device and equipment, and the method comprises the steps: receiving text data of a target domain input by a user, the text data comprising special words of the target domain; performing word segmentation processing on the text data through a preset word segmentation strategy aiming at a target field, and performing identification processing aiming at special words of the target field on segmented words corresponding to the obtained text data to obtain target special words in the segmented words corresponding to the text data; carrying out wrongly written character recognition processing on the target proprietary word through a proprietary word error recognition model for the target field to obtain a first recognition result, and carrying out wrongly written character recognition processing on segmented words, except the target proprietary word, in the segmented words corresponding to the text data through a general word error recognition model to obtain a second recognition result; and based on the first recognition result and the second recognition result, determining wrongly written character information contained in the text data through fusion processing of the two different recognition results.

A user is assisted in performing a voice operation appropriately.A situation determination section determines a situation. A state control section controls a voice command appropriate for the determined situation to put the voice command into a receivable state. For example, the user is informed of what the voice command in a receivable state is, by means of display or voice output. The user can utter a voice command without performing a user action to prevent false recognition, such as the utterance of a wake word. This reduces the troublesomeness and burden of the user.

The application discloses a dynamic image feature capturing method based on deep learning, and relates to the technical field of image recognition. Through optimization of a deep convolutional neural network model, a convolutional layer in the deep convolutional neural network model which does not work or has a negative effect on a recognition result is removed, so that the calculation amount of the deep convolutional neural network model is reduced, and the accuracy of the deep convolutional neural network model is further improved on the basis of having completed training. Meanwhile, after a technical personnel deletes a feature marking frame of an error recognition through a tool, corresponding contrast video frames and original video frames are input as training samples of the deep convolutional neural network model, so that the recognition accuracy of the deep convolutional neural network model is more accurate.

This invention relates to the field of artificial intelligence education technology, specifically to a method and system for reviewing and providing feedback on physics, chemistry, and biology lab reports based on a multimodal large-scale model. The method includes: acquiring lab report question data, student answer data, and scoring standard data; vectorizing the question data and retrieving scoring criteria from a scoring knowledge base; selecting either a text-based or image-based scoring process based on the answer type, and calling a fine-tuned multimodal large-scale language model for scoring reasoning; calling an error identification module and a teaching suggestion generation module based on the scoring results; summarizing the complete review results and calculating the joint confidence level; and determining whether to push the results for manual review based on the confidence level. This invention can improve the accuracy, fine-grained understanding, and quality of teaching feedback in lab report review, enabling the self-evolution of the review system.