253 results about "Low Confidence" patented technology

An interactive machine learning based system that incrementally learns, on the basis of text data, how to annotate new text data. The system and method starts with partially annotated training data or alternatively unannotated training data and a set of examples of what is to be learned. Through iterative interactive training sessions with a user the system trains annotators, and these are in turn used to discover more annotations in the text data. Once all of the text data or a sufficient amount of the text data is annotated, at the user's discretion, the system learns a final annotator or annotators, which are exported and available to annotate new textual data. As the iterative training process occurs the user is selectively presented for review and appropriate action, system-determined representations of the annotation instances and provided a convenient and efficient interface so that context of use can be verified if necessary in order to evaluate the annotations and correct them, where required. At the user's discretion, annotations that receive a high confidence level can be automatically accepted and those with low confidence levels can be automatically rejected.

Techniques are disclosed for detecting security incidents based on low confidence security events. A security management server aggregates a collection of security events received from logs from one or more devices. The security management server evaluates the collection of security events based on a confidence score assigned to each distinct type of security event. Each confidence score indicates a likelihood that a security incident has occurred. The security management server determines, based on the confidence scores, at least one threshold for determining when to report an occurrence of a security incident from the collection of security events. Upon determining that at least one security event of the collection has crossed the at least one threshold, the security management server reports the occurrence of the security incident to an analyst.

An automated license plate recognition (ALPR) system and method using a human-in-the-loop based adaptive learning approach. One or more images with respect to an automotive vehicle can be segmented in order to determine a license plate of the automotive vehicle within a scene. An optical character recognition (OCR) engine loaded with an OCR algorithm can be further adapted to determine a character sequence of the license plate based on a training data set. A confidence level with respect to the images can be generated in order to route a low confidence image to an operator for obtaining a human interpreted image. The parameters with respect to the OCR algorithm can be adjusted based on the human interpreted image and the actual image of the license plate. A license plate design can be then incorporated into the OCR engine in order to automate the process of recognizing the license plate with respect to the automotive vehicle in a wide range of transportation related applications.

Systems and methods are provided for identifying pages that can be authoritatively, to some confidence level or another, associated with a geographic location, and systems and methods for grouping documents such that authoritative location associations can be propagated from pages with higher location confidence to pages with lower location confidence. Pages might be identified with authoritative indicators, groups of pages identified including at least one addressed page and at least one unaddressed page, wherein an addressed page is a page having a higher confidence level than an unaddressed page, and at least one processing step performed that is location specific. The confidence level assigned to a page as part of the process represents the confidence that the page is associated with an identifiable geographic location, with documents having a high confidence level being determined to be strongly associated with a particular geographic location while documents having a low confidence level being determined to be weakly associated with a particular geographic location or not associated at all with a geographic location.

Systems and methods for active learning of statistical machine translation systems through dynamic creation and updating of parallel corpus. The systems and methods provided create accurate parallel corpus entries from a test set of sentences, words, phrases, etc. by calculating confidence scores for particular translations. Translations with high confidence scores are added directly to the corpus and the translations with low confidence scores are presented to human translations for corrections.

An automatic speech recognition (ASR) system that includes a speech-response application and a speech recognition engine. The ASR system generates user prompts to elicit certain spoken input, and when the spoken input is recognized, the voice-response application performs an action. The recognition engine compares sounds in the input audio signal to phonemes in the acoustic model to identify candidate matching phonemes. A recognition confidence score is calculated for each candidate matching phoneme, and the confidence score is used to aid in the recognition of one or more possible matching phoneme sequences that appear to match the word in the speech-response application's grammar. A confidence score for each phoneme is evaluated against predefined confidence score criteria (eg, a discrimination score below a "low confidence" threshold), and the results of the evaluation are used to influence the selection of subsequent user prompts. One such system uses confidence scores to select cues for object recognition training - encouraging input to be recognized as phonemes with low confidence recognition scores. Another system selects prompts to block input of sounds that are not easily recognizable.

A method and system for classifying documents is provided. A set of document classifiers is generated by applying a classification algorithm to a trusted corpus that includes a set of training documents representing a taxonomy. One or more of the generated document classifiers are executed against a plurality of input documents to create a plurality of classified documents. Each classified document is associated with a classification within the taxonomy and a classification confidence level. One or more classified documents that are associated with a classification confidence level below a predetermined threshold value are selected to create a set of low-confidence documents. The low-confidence documents are disassociated from each of the associated classifications. A user is prompted to enter a classification within the taxonomy for at least one low-confidence document. The low-confidence document is associated with the entered classification and with a predetermined confidence level to create a newly classified document.

Methods and systems for classifying defects detected on a specimen with an adaptive automatic defect classifier are provided. One method includes creating a defect classifier based on classifications received from a user for different groups of defects in first lot results and a training set of defects that includes all the defects in the first lot results. The first and additional lot results are combined to create cumulative lot results. Defects in the cumulative lot results are classified with the created defect classifier. If any of the defects are classified with a confidence below a threshold, the defect classifier is modified based on a modified training set that includes the low confidence classified defects and classifications for these defects received from a user. The modified defect classifier is then used to classify defects in additional cumulative lot results.

The invention relates to the field of double dynamic license plate identification, and provides a character confidence degree-based secondary license plate identification method and apparatus for the problems existent in the prior art. The method comprises the steps of performing character identification through template matching; giving out confidence degrees of identification results; for the results with relatively low confidence degrees, performing video super-resolution processing to obtain a frame of high-quality image; and based on the image, performing secondary license plate identification through a neural network classifier. According to the method and the apparatus, a license plate confidence degree threshold Th is preset; a picture is captured from a front end and license plate locating and segmenting are performed; characters of a license plate are identified; character identification confidence degrees and license plate identification confidence degree are calculated; when the character confidence degrees are all higher than the threshold Th, a license plate identification result is directly given, otherwise, the video super-resolution processing is performed; a frame of high-quality image is obtained by utilizing time domain information; and based on the image, the to-be-identified characters are input to classifiers for performing identification according to a position relationship of the to-be-identified characters, so that a final license plate identification result is obtained.

A computerized neural-network based mechanism for providing an intermediary configured for intervening in searches is described. Corresponding methods, computer-readable media, systems, devices, and apparatuses are also contemplated. The neural network can include a multi-headed attention layer. The intermediary may be, in some embodiments, a human “man in the middle” mechanism invoked where there is low confidence that pre-existing categories map to a user's search string. The mechanism provides a specially configured interface adapted to enable a search specialist to quickly select one or more categories that match or are otherwise associated with the search query from a set of acceptable categories. Received outputs and detected user behaviors are utilized to update a neural network model.

A character based system and method for correcting low confidence characters from an OCR system facilitates operator review, editing and correction of character and field level data generated by an OCR system without the need for an application that is installed at the operator workstation. The system creates a data structure of OCR information and provides that information to an operator through an HTML interface that is rendered using HTML and JavaScript. The data structure includes an OCR confidence level for each character and/or field and the operator is prompted to review only those characters/fields that meet a predetermined threshold for the confidence level. The operator can use an input key (e.g., TAB or ENTER) to navigate to each character/field with a low confidence level and thereby correct or validate each low confidence character/field as appropriate.

Disclosed are methods and apparatus for efficiently setting up and maintaining a defect classification system. In general terms, the setup procedure optionally includes automatically grouping a set of provided defects and presenting a representative set from each defect group to the user for classification. After the initial manual classification of the representative defects, the setup procedure includes an automatic procedure for classifying the non-reviewed or unclassified defects based on the manual class codes from the user-reviewed defects. After the automatic classification operation, the user may also be presented with defects from each class which may require re-classification. In particular embodiments, the user is iteratively presented with defects which have classifications that are suspect, which are near classification boundaries, or have classifications that have a low confidence level until each class is pure or contains a same type of defect classes as assigned by the user.

A trending system and method for trending data in a mechanical system is provided. The trending system includes a sliding window filter. The sliding window filter receives a data set of data points generated by the mechanical system. The sliding window filter partitions the data set into a plurality of data windows, and uses the data windows to calculate upper and lower confidence bounds for the data set. Specifically, the sliding window filter calculates an upper confidence bounds and lower confidence bounds for each data point using each of the multiple data windows that includes the data point. The sliding window filter then selects the upper confidence bounds and the lower confidence bounds that results in the smallest mean prediction confidence interval for that data point. This results in a smoothed estimated trend for the data set that can be used for prognostication and fault detection.

The invention discloses an improved kernel-related filtering tracking method based on ultra-pixel optical flow and self-adaptive learning factor. The appearance reconstruction of target can be realized through ultra-pixel analysis, and the target is divided into ultra-pixel blocks which are clustered into an ultra-pixel center. The displacement change of the optical flow analysis pixel point of each ultra-pixel center is calculated, and the movement offset and scale change of the target can be detected. Based on the predicted parameter, cycled sampling is conducted on each new-frame image, andan improved and gauss kernel-based filtering target tracking method which introduces the self-adaptive learning factor is adopted by each sample, and the accurate position and scale of the target canbe detected. The detection result is detected and corrected through an on-line SVM detection model, and the position with low confidence is corrected, and finally the target position can be accurately positioned and the target accurate scale can be obtained. The invention is advantageous in that the tracking problems like scale change, shielding, deforming, and motion blur, which exit in the target tracking process can be overcome, and real-time and highly-precise target tracking can be realized.

In a conditional multipass automatic speech recognition system, one or more intent templates may be received from an application. A spoken utterance is received and audio frames are generated from the utterance. The audio frames are compared to a first grammar. Recognized speech results are generated and unrecognized audio frames or low confidence frames are collected. One of one or more intent templates and one or more corresponding intent parameters may be determined based on the recognized speech results. The unrecognized audio frames may be conditionally compared to a second grammar in instances when additional information is requested, relative to the determined intent template or the corresponding intent parameters.

An information handling system includes a processor that throttles the instruction fetcher whenever the inaccuracy, or lack of confidence, in branch predictions for branch instructions stored in a branch instruction queue exceeds a predetermined threshold confidence level of inaccuracy or error. In this manner, fetch operations slow down to conserve processor power when it is likely that the processor will mispredict the outcome of branch instructions. Fetch operations return to full speed when it is likely that the processor will correctly predict the outcome of branch instructions.

The invention discloses an image collaborative cutout method based on confidence level. The method aims to conduct collaborative cutout on images with a foreground of slight deformation and a background of large difference. According to the method, front background segmentation is conducted on multiple images by the adoption of a collaborative segmentation algorithm, each image is marked as a mask of a foreground, a background and a region to be solved through morphological operation, cutout is conducted on each source image by the utilization of the source image and the mask by the adoption of an existing single common cutout method, confidence measurement is conducted on the cutout result, pixel points in the region to be solved in all the images are matched, a global optimization function is defined based on the matching so that the cutout effect on all the images is improved in coordination, the method aims to conduct cutout result spread from a high confidence region to a low confidence region matched with the high confidence region, and thus more accurate cutout result is obtained in the corresponding low confidence region. By means of the method, multiple images are input, and the cutout result of the images is output.

Methods for interpreting absolute copy number of complex tumors and for determining the copy number of a genomic region at a detection position of a target sequence in a sample are disclosed. In certain aspects, genomic regions of a target sequence in a sample are sequenced and measurement data for sequence coverage is obtained. Sequence coverage bias is corrected and may be normalized against a baseline sample. Hidden Markov Model (HMM) segmentation, scoring, and output are performed, and in some embodiments population-based no-calling and identification of low-confidence regions may also be performed. A total copy number value and region-specific copy number value for a plurality of regions are then estimated.

The invention provides a model training method which comprises the following steps: taking the same annotated data set as a training data set of different classification models, and training the different classification models; Based on the trained classification model, predicting prediction samples in the unlabeled data set to obtain a prediction result; obtaining Confidence of a prediction result, and marking the prediction sample as a high-confidence prediction sample or a low-confidence prediction sample; Adding prediction samples marked as high-confidence prediction samples in each classification model to training data sets of other classification models; And based on the new training data set, performing preset rounds of iterative training, and obtaining a classification model aftermultiple times of iterative training. The invention further provides a customer service system, a data labeling system and a readable storage medium. The technical problem that the response quality ofa customer service system is poor due to the fact that the obtaining cost of the mark data needed by an existing classification model is high and the quality of the classification model is low is solved.

A method for obtaining a candidate nucleotide sequence S indicative of a sequence of a target polynucleotide molecule that produces a hybridization signal I({right arrow over (x)}) upon incubation with a polynucleotide {right arrow over (x)} for each polynucleotide {right arrow over (x)} in a set E of polynucleotides. For each polynucleotide {right arrow over (x)} in the set E of polynucleotides, a probability P₀({right arrow over (x)}) of the hybridization signal I({right arrow over (x)}) when the sequence {right arrow over (x)} is not complementary to a subsequence of T and a probability P₁({right arrow over (x)}) of the hybridization signal when the sequence {right arrow over (x)} is complementary to a subsequence of T are obtained; so as to obtain a probabilistic spectrum (PS) of T. A score is then assigned to each of a plurality of candidate nucleotide sequences that is being based upon the probabilistic spectrum and upon a reference nucleotide sequence H. A candidate nucleotide sequence having an essentially maximal score is selected and one or more low confidence intervals and one or more reliable intervals in the selected candidate nucleotide sequence are identified. For each low confidence interval detected in the selected candidate nucleotide sequence, a score is assigned to each of a plurality of candidate nucleotide sequences of the low confidence region, where the score is based upon a probabilistic spectrum obtained by filtering from the PS signals the signals present in the reliable regions; and upon an interval of the reference nucleotide sequence H homologous with the low confidence interval. A candidate nucleotide sequence having an essentially maximal score is then selected. A revised candidate sequence S′ is then obtained indicative of the sequence of the target polynucleotide molecule T by substituting the sequence of the low confidence region in the candidate sequence S with the selected candidate sequence.

The invention discloses a multi-characteristic multi-model pedestrian detection method, comprising steps of using an ICF+Adaboost classifier A to process a video frame RGB image, using a foreground-mask-based pedestrian detection classifier to process the foreground mask, combining results of the two classifiers, dividing the results into a high confidence level pedestrian detection result and a low confidence level pedestrian detection result according to a threshold value, using an ICF+Adaboost classifier B and a DPM pedestrian detection classifier to perform respective detection on the low confidence level pedestrian detection result, combining detection results of the two classifiers, using a detection score, an overlapping ratio, a width-height ratio, a classifier sequence number and a foreground ratio of each detected pedestrian as characteristic vectors, inputting the characteristic vectors into a ruling SVM to determine whether the detected pedestrian is correct pedestrian detection, outputting a new pedestrian detection result and combining the new pedestrian detection result and the high confidence level pedestrian detection result into a set as a final detection result. The multi-characteristic multi-model pedestrian detection method effectively solves the problem in the prior art that the misjudgment rate is high, and improves the detection rate.

The invention provides an estimation method of a series system reliability degree lower confidence limit of exponential distribution. The estimation method comprises eight steps. The estimation method comprises the following steps: deducing belief distribution of each unit failure rate lambada i in a system based on belief, obtaining a composition structural relationship of the system from a failure rate angle according to features of the exponential distribution, and an obtaining system failure rate upper limit on the condition that confidence level is given through a Monte Carlo method to obtain the system reliability degree lower confidence limit which is paid special attention on engineering. An accurate method of solving the series system reliability degree lower confidence limit of location lifetime obedience exponential distribution is provided, calculation is simple and convenient, a data filling algorithm is given with regard to random censored data, and a usable range is expanded.