931 results about "Identification error" patented technology

System and method for identifying speeding violations, comprising determining a current speed and a current location of a vehicle, determining a posted speed limit for the current location from a speed-by-street database, comparing the current speed of the vehicle to the posted speed limit, and evaluating whether the current speed exceeds the posted speed limit. Errors are identified in the speed-by-street database by storing a plurality of speeding violation records, wherein the speeding violation records each include a speeding event location; analyzing the speeding violation records to identify one or more speeding event locations having multiple speeding violations; comparing a posted speed limit at the one or more speeding event locations having multiple speeding violations to corresponding speed limit data in the speed-by-street database; and identifying one or more speed limit entries in the speed-by-street database that do not match the posted speed limit.

A speech recognition system in which a user may correct a recognition error resulting from speech recognition more efficiently and easily. Speech recognition means compares a plurality of words inputted from speech input means with a plurality of words stored in dictionary means, respectively, and determines a most-competitive word candidate. Word correction means has a word correction function of correcting the words constituting a word sequence displayed on a screen. Competitive word display commanding means selects one or more competitive words having competitive probabilities close to the competitive probability of the most-competitive word candidate and displays the one or more competitive words adjacent to the most-competitive word candidate. Competitive word selection means selects an appropriate correction word from the one or more competitive words. Word replacement commanding means causes one of the most-competitive word candidate to be replaced with the correction word selected by the competitive word selection means.

System and method for identifying speeding violations, comprising determining a current speed and a current location of a vehicle, determining a posted speed limit for the current location from a speed-by-street database, comparing the current speed of the vehicle to the posted speed limit, and evaluating whether the current speed exceeds the posted speed limit. Errors are identified in the speed-by-street database by storing a plurality of speeding violation records, wherein the speeding violation records each include a speeding event location; analyzing the speeding violation records to identify one or more speeding event locations having multiple speeding violations; comparing a posted speed limit at the one or more speeding event locations having multiple speeding violations to corresponding speed limit data in the speed-by-street database; and identifying one or more speed limit entries in the speed-by-street database that do not match the posted speed limit.

The invention discloses an interactive speech recognition system which comprises an acoustic model, a language model selection module, a speech and sentence extraction module, a speech recognition module, a word candidate generation and error correction module and an interaction module, wherein the acoustic model and the language model selection module are used for selecting an acoustic model which is the most similar to an object to be recognized in the pronunciation characteristic for the object to be recognized and a language model which is the most similar to the object to be recognized in the field for the whole recognition process according to the information of the object to be recognized; the speech and sentence extraction module is used for segmenting the whole section of a speech signal into a plurality of speeches and sentences, extracting the segmented speeches and sentences and sending to the speech recognition module; the speech recognition module is used for recognizing the speeches and the sentences extracted by the speech sentence extraction module and outputting an intermediate recognition result; the word candidate generation and error correction module is used for processing the intermediate recognition result to generate a candidate assembly and correcting recognition errors according to selected candidates or input correct data to obtain a final recognition result; and the interaction module is used for sending data input by a user to the acoustic model and the language model selection module and feeding back the recognition result of the word candidate generation and error correction module to the user.

The present invention provides an image display device which includes a photo-sensing circuit capable of high-speed light signal reading at high S / N ratio and has a touch-panel function with less influence by disturbance light and less wrong recognition.The image display device comprises a display unit in which display pixels having thin-film transistors are arranged in a matrix and a plurality of light detection pixels within the display unit. The image display device is configured in such a way that a first light sensing element that receives observation light and a second light sensing element that does not receive observation light are electrically connected, and that a blue color filter and the first light detection pixel are overlapped and a green or a red color filter and the second light detection pixel are overlapped at a light sensing element that outputs potential modulation at the connection point of the first and second light sensing elements.

An automatic speech recognition system recognizes user changes to dictated text and infers whether such changes result from the user changing his / her mind, or whether such changes are a result of a recognition error. If a recognition error is detected, the system uses the type of user correction to modify itself to reduce the chance that such recognition error will occur again. Accordingly, the system and methods provide for significant speech recognition learning with little or no additional user interaction.

A method and apparatus are provided for automatically training or modifying one or more models of acoustic units in a speech recognition system. Acoustic models are modified based on information about a particular application with which the speech recognizer is used, including speech segment alignment data for at least one correct alignment and at least one wrong alignment. The correct alignment correctly represents a phrase that the speaker uttered. The wrong alignment represents a phrase that the speech recognition system recognized that is incorrect. The segment alignment data is compared by segment to identify competing segments and those that induced the recognition error. When an erroneous segment is identified, acoustic models of the phoneme in the correct alignment are modified by moving their mean values closer to the segment's acoustic features. Concurrently, acoustic models of the phoneme in the wrong alignment are modified by moving their mean values further from the acoustic features of the segment of the wrong alignment. As a result, the acoustic models will converge to more optimal values based on empirical utterance data representing recognition errors.

An aircraft synthetic vision system (100) is provided for increasing data input to a pilot (109) during approach and landing flight operations, and includes a runway assistance landing system (114) and a plurality of databases (106, 108, 110, 112) which may include, for example, a terrain database (106), an obstacle database (112); and a validated runway database (110). The processor (104) detects the likelihood of an error in determining the altitude from at least one of the runway assistance landing system (114), the plurality of databases (106, 108, 110, 112), and identifies the error. The processor (104) further determines augmented coordinates, and a processor (104) generates symbology commands to a first display (116) for displaying a runway environment in response to data provided to the processor (104) from each of the runway assistance landing system (114), the plurality of databases (106, 108, 110, 112), and the processor (104).

The invention discloses a Chinese text automatic correction method. The method comprises the following steps of: a) inputting a to-be-corrected Chinese text, and performing word segmentation preprocessing on the Chinese text sentence by sentence; b) searching for one-character words, two-character words or disperse strings of three or more than three characters occurring in the text subjected to word segmentation sentence by sentence; c) performing continuous determination on the disperse strings occurring in the text subjected to word segmentation by adopting an N-gram model, and checking text word level errors for each single sentence in combination with a word forming probability of separate characters; and d) constructing an error correction knowledge base to generate an error correction candidate text. According to the Chinese text automatic correction method provided by the invention, the one-character words, two-character words or disperse strings of three or more than three characters occurring in the text subjected to word segmentation are searched for sentence by sentence, the disperse strings occurring in the text subjected to word segmentation are subjected to continuous determination by adopting the N-gram model to determine identification errors, and the error correction knowledge base is constructed to generate the error correction candidate text, so that error checking and correcting processes are combined very well, and the method has the characteristics of high error checking speed and high error correcting efficiency.

A speech recognition system comprises at least a speech recognition engine and a display device that contains a signal status interface and a textual interface. The signal status interface is used to show a recording status, a speech processing status, or a complete speech recognition status based on waveforms display. The textual interface is used to show word units of the speech recognition results. Two sets of commands are connected with each waveform unit on the signal status interface and each word unit on the textural interface, respectively, in order to allow users to correct the recognition errors or to adjust the speech recognition system.

An ATA-compatible drive interface with error correction and detection capabilities is disclosed. Being fully ATA backward compatible, this interface functions with the same physical cable and connectors as current ATA systems, employs bus drivers that are the same as or backward compatible with those provided by earlier versions of the ATA standard and uses signals with cable signal transitions no faster than those presently seen by current ATA devices. The error detection feature indicates when a data block is erroneously transferred between the device and host; the error correction feature identifies the words transmitted in error and corrects those words on the receiving side of the interface. So that ATA backward compatibility is maintained, the data integrity checking feature does not require additional words in a data transfer, and the data correction feature does not require new data transfer protocols or additional data transfer overhead. Also disclosed are interface circuitry and a new ATA-compatible transfer mode capable of transferring data at 40 MB / sec, the rate supported by local bus adapters for disk drives. Given the physical limits of the ATA cables and connectors, the error correction and detection features are especially useful for correcting data words corrupted during high-speed transmission; however, error correction and detection can also operate independently of the fast transfer mode. Consistent with full backward compatibility, a hard drive configured with the new, fast, error-correcting interface is transparently functional when plugged into a current ATA adapter provided by a legacy computer system.

Electronic discovery on computer systems and archives is provided by using statement analysis of to identify false statements so as to retrieve relevant impeachment data and other evidence related to recorded statements. The recorded statement is analyzed for possible false statements and corresponding transcript data of the false statement, any precipitating question, and any follow-up questions are selected for use in the query. The selected text can be further processed before being used in the query. The query can be used in a search engine or used to train smart search agents. The search engine query or smart search agents are released onto target computer systems and / or archives to search for responsive data and documents. Notification, reports, and indexing of responsive data and documents can be provided to produce relevant results. The analysis of the recorded statement is preferably done by voice stress analysis.

The invention discloses a method and a device for identifying the category of an image, an image search method and an image search device. The method for identifying the category of an image comprises the following steps: getting an image to be identified; determining a first confidence that the image to be identified belongs to each predetermined category; when the number of categories of which the first confidence is greater than a first threshold is smaller than a predetermined number, calculating a second confidence that the image to be identified belongs to each of corresponding cross-correlated categories for the categories of which the first confidence is between a second threshold and the first threshold; and selecting a plurality of target categories with higher second confidence, and taking the categories of which the first confidence is greater than the first threshold and the target categories as the identification result of the category of the image to be identified. By using the method, category identification error caused by the difference between the features of images of the same category and the overlap between the features of images of different categories is inhibited as much as possible, and the accuracy of category identification is improved effectively.

A method for reducing recognition errors. The method includes receiving an N-best list associated with an input of a computer based recognition system. The N-best list includes one or more hypotheses and associated confidence values. The input is classified in response to the N-best list, resulting in a classification. A re-scoring algorithm that is tuned for the classification is selected. The re-scoring algorithm is applied to the N-best list to create a re-scored N-best list. A hypothesis for the value of the input is selected based on the re-scored N-best list.

The sequencing of individual monomers (e.g., a single nucleotide) of a polymer (e.g., DNA, RNA) is improved by reducing the motion of the polymer due to thermally-driven diffusion to reduce the spatial error in the position of the polymer within a measurement device. A major system parameter, such as average translocation velocity or measurement time, is selected based on the characteristics of the sensing system utilized, and an algorithm jointly optimizes the sequencing order error rate and the monomer identification error rate of the system.

The invention discloses a device, a method and a system for realizing address order identification of an embedded device. In the system, all devices are connected through field buses, and are connected in series in turn through interface units arranged on the devices to form an address control signal transmission line for transmitting a slave strobe signal; moreover, every two devices are in cascade connection through a controllable connection unit, and the control end of each controllable connection unit is correspondingly connected with the output end of a delayed control signal of one device; and each controllable connection unit is used to keep or cut off the connection of a device and the address control signal transmission line according to the delayed control signal output by the device connected with the unit. The device, the method and the system solve the problems of bus conflict or identification error, and the like caused by the address loss of the device, realize automatic order identification and allocation of the address during putting the device into service, and are suitable for a network in which no communication is carried out among slave devices.

Pattern recognition capable of robust identification for the variance of an input pattern is performed with a low processing cost while the possibility of identification errors is decreased. In a pattern recognition apparatus which identifies the pattern of input data from a data input unit (11) by using a hierarchical feature extraction processor (12) which hierarchically extracts features, an extraction result distribution analyzer (13) analyzes a distribution of at least one feature extraction result obtained by a primary feature extraction processor (121). On the basis of the analytical result, a secondary feature extraction processor (122) performs predetermined secondary feature extraction.

There is provided a management apparatus associated detachably with a cash cassette for managing the cash cassette storing bills or coins for cash transactions with users at an automatic teller machine. The cash cassette includes an error information recording area for recording identification information identifying a type of error in the event of occurrence of the error, and a count information recording area for recording count information indicating the number of bills or coins expected to be in the cash cassette. Based on the identification information acquired from the error information recording area, the management apparatus determines whether a predetermined type of error has occurred. When determining that such a type of error has occurred, the management apparatus outputs an instruction to management staff to count the number of bills or coins in the cash cassette, or when determining that such a type of error has not occurred, it outputs the count information from the count information recording area.

For a flexible error trace mechanism, embodiments may be implemented for C / C++ interface libraries, or in programs written in C / C++ or other programming languages. In one embodiment, when an error occurs in a function call, a trace element may be recorded that may include the source file name, function name, line number and other information that may be used to identify the error. In one embodiment, the library function may call a plurality of library functions in a function call stack. For each of the plurality of library functions, if the library function generates an error, an error trace element may be added to the error trace. After completion of the library function, the program may obtain the error trace for the library function. The error(s), if any, may be debugged using the information in the obtained error trace.

An error management system and process can be used to identify an erroneous data packet in a data stream. In response to identifying the erroneous data packet, a subsequent valid data packet is located in the data stream. In one embodiment, a plurality of candidate locations of header checksum windows are searched and checked for a valid checksum. Multiple integrity checks of multiple header checksums can be used to reduce the probability of a false positive integrity check. In another embodiment, one or more information data fields can used for determining packet integrity by determining if the fields contain valid information bits.

Methods are described for solving the problems associated with error messages by providing methods for unique identification of error messages to allow for resolving one or several messages to information, such as a knowledge base article. The methods include a method for reporting errors by generating an error message box upon determination that an error occurred, displaying the error message box to a user and allowing a user to interact with the error message box by selecting a universal resource locator (URL) in the error message box to connect to product support. The user can cause passing of a string to product support including an error message identifier to enable a search to match the error message identifier to information concerning the error. The information could be information about the error or a bug submission form for assisting product support to isolate a new error in the application.

The invention provides a parking charge method completely based on license plate recognition in a parking lot. By means of establishing an automatic reexamining mechanism for license plate recognition at a headstock and a tailstock, the effect that a parking information table created automatically in real time by the parking lot is 100% correct is ensured, the fastness and reliability of a technological base for follow-up charge operation of the parking lot are further ensured, and parking charge conflicts caused by license plate recognition errors are avoided.

A control apparatus capable of improving the control accuracy and stability when controlling a controlled object with a predetermined restraint condition between a plurality of model parameters, or a controlled object having a lag characteristic, using a control target model of a discrete-time system. The control apparatus has an ECU which arranges a control target model including two model parameters such that terms not multiplied by the model parameters and terms multiplied by the same are on different sides of the model, respectively. Assuming the different sides represent a combined signal value and an estimated combined signal value, respectively, the ECU calculates onboard identified values of the model parameters such that an identification error between the signal values is minimized, and calculates an air-fuel ratio correction coefficient using the identified values and a control algorithm derived from the control target model.

The invention discloses a convolutional neural network-based character recognition method, and mainly aims at solving the problem that existing manual engineering drawing data input is time-consuming,labor-consuming and high in error rate. The method comprises the following main steps of: 1) converting grayscale images into binary images by adoption of Otsu method-based optimal global threshold value processing; 2) rotating to correct inclined images; 3) extracting a table box by adoption of a mathematic morphological algorithm; 4) obtaining an area where characters are located; 5) rotating inclined character strings for a corresponding angle to a horizontal direction; 6) searching circles in the images by adoption of a circular Hough transformation algorithm, and extracting welding beadnumbers in an engineering drawing; 7) carrying out image-text recognition on the engineering drawing by adoption of a convolutional neural network method; 8) correcting simple errors through an encoding rule and automatically correcting recognition errors; and 9) outputting and storing the drawing data. In image-text recognition of engineering drawings, the method has high correctness and timeliness, and is capable of realizing efficient recording and management of engineering drawing data.

A diagnostic system provides help to a user utilizing a data store that stores one or more solutions to at least one error. A storage component logs error data and associates errors, responses to the errors, and information indicative of whether each of the error responses was successful or unsuccessful. A linking component receives the error data from a source and identifies an appropriate solution to the error data from the information logged in the storage component. A presentation component presents the appropriate solution to a user.

A lithography mask layout is designed and verified incrementally to help reduce the amount of time to produce the mask layout. For one embodiment, a layout defining a target pattern may be processed to produce a mask layout, and the mask layout may be verified to identify errors. Rather than processing and verifying the entire mask layout for error correction over one or more subsequent iterations, sub-layouts having errors may be removed or copied from the mask layout for separate processing and verification. Because the amount of data defining a sub-layout is relatively small, the time to design and verify the mask layout is reduced. The resulting mask layout having one or more processed and verified sub-layout(s) may then be used to manufacture a mask set to help print the target pattern in manufacturing integrated circuits (ICs), for example.

A sounds-like spelling group is generated in which scores are used for word descriptions. A user selects a correct sounds-like spelling from a generated sounds-like spelling group, and a group of base forms is generated with scores provided for the selected sounds-like spelling and the reading of the word. In this fashion, a base form having a score that exceeds a reference value is registered without a voice recording being required. During the speech recognition process as performed by a user, when a predetermined error state is detected, e.g., when the number of recognition errors exceeds N, a panel is output requesting that the user register the inscription, the sounds-like spelling and the pronunciation inscription for the word and that the user record a corresponding pronunciation. In accordance with the pronunciation provided by the user, the base form is obtained and is re-registered in the speech recognition dictionary.