54 results about "Correction text" patented technology

The invention discloses a foreign language writing automatic error correction method and system. The method comprises the steps of pre-building an error correction model used for foreign language statement automatic error correction; obtaining a foreign language statement written by a user; extracting word vectors of words in the statement and sentence vectors of the statement; inputting the word vectors of the words in the statement and the sentence vectors of the statement to the error correction model, obtaining corrected word vectors of the words output by the error correction model, and generating an error correction text according to the corrected word vectors of the words; and displaying the error correction text. By utilizing the method and the system, automatic error correction of statement errors in foreign language writing can be realized and the writing and learning effects of students can be improved.

The invention provides a voice recognition error correction method and device based on artificial intelligence, and a readable medium. The method comprises the following steps: determining the targetfield of voice recognition; when the voice recognition original text has the original fragment having the smoothness which is not larger than the preset smoothness threshold value in the target field,performing the ED fragment recalling on the original fragment needing to be corrected, and obtaining a candidate fragment set of the original fragment; scoring each candidate fragment by means of thepre-trained fragment scoring model; according to the scoring of each candidate fragment, obtaining a target fragment corresponding to each original fragment in the target field by means of decoding,and obtaining a correction text for voice recognition in the target field. According to the technical scheme, the defects in the prior art are overcome, and the voice recognition error correction scheme is provided, the error fragment in the voice recognition original text can be corrected, and the accuracy of voice recognition is effectively improved.

The embodiment of the invention discloses an error correction method and device for a voice recognition text. The error correction method for the voice recognition text comprises the steps that at least one candidate error correction text used for error correction of a result text is obtained according to the multi-layer K-Gram index of the voice recognition result text, the fuzzy sound editing distance matrix between the at least one candidate error correction text and the result text is determined, the fuzzy sound editing distance between the at least one candidate error correction text and the result text and a candidate error correction boundary are obtained according to the determined fuzzy sound editing distance matrix, an error correction text is selected according to the fuzzy sound editing distance corresponding to the at least one candidate error correction text, and error correction is conducted on the result text according to the candidate error correction boundary corresponding to the error correction text. By the adoption of the error correction method and device for the voice recognition text, accurate error correction of the voice recognition result text is achieved.

The invention relates to a speech recognition text correction method and device, computer equipment and a storage medium. The method comprises the steps of obtaining pinyin of each word in a recognition text obtained through speech recognition; determining a candidate text based on a corpus and the fuzzy sound of the sound unit in the pinyin of each word; Wherein the sound unit comprises at leastone of an initial consonant, a vowel and an overall recognition pronunciation section; determining an editing distance corresponding to the candidate text according to the word number difference between the recognition text and the candidate text, the total pinyin alphabet number and the total word number; and screening a correction text from the candidate text according to the editing distance. By adopting the editing distance method provided by the invention to screen the correction text of the candidate text, the speech recognition text can be effectively corrected when the recognition textis long, and the correction accuracy is improved.

The invention discloses an error correction processing method and device, a storage medium and a processor. The error correction processing method comprises the steps: obtaining suspected error information in a to-be-detected text; obtaining at least one piece of candidate correction information of the suspected error information; correcting the to-be-detected text by using the at least one pieceof candidate correction information to obtain at least one target candidate text; determining the confusion degree of the at least one target candidate text; and determining a target correction text from the at least one target candidate text according to the confusion degree. According to the error correction processing method, the context information of the text is considered during text error correction, so that the error correction effect is enhanced, and the error correction result is more accurate, and the technical problem of poor error correction effect in related technologies is solved.

The embodiment of the invention discloses a text information processing method and device, and relates to the field of cloud computing. A specific embodiment of the method comprises the steps of identifying a to-be-processed text from an image comprising the to-be-processed text; inputting the to-be-processed text into a pre-trained recurrent neural network language model, and identifying wronglywritten characters in the to-be-processed text; inputting the wrongly written characters in the to-be-processed text into a pre-trained text error correction model to obtain similar characters corresponding to the wrongly written characters; and determining correct characters corresponding to the wrongly written characters in the similar characters by utilizing the text error correction model based on the coherence of the to-be-processed text, and replacing the wrongly written characters with the correct characters to obtain an error correction text of the to-be-processed text. The wrongly written characters are recognized through the pre-trained recurrent neural network language model, and the correct characters of the wrongly written characters are obtained through the pre-trained text error correction model, so that the error correction text is obtained, and the accuracy of a recognition result is improved.

The present invention provides a speech identification method and apparatus, and a washing machine. The method comprises: obtaining a speech signal of a user; identifying the speech signal to obtain text content corresponding to the speech signal; analyzing the text content to obtain at least one keyword of the text content; according to the keywords, querying an error correction database to obtain error correction words with the same pinyin as the keywords, wherein the error correction database stores: at least one error correction word and pinyin of error correction words, and the at least one error correction word is the terminal device-related word; and according to the error correction words with the same pinyin as the keywords, generating error correction text content corresponding to the text content. According to the technical scheme of the present invention, the speed signal of the user can be identified as a word related to the terminal device rather than other words with thesame pinyin or the similar pinyin, so that the user requirements can be accurately identified, the accuracy and efficiency of speech identification are improved, and the user experience in using thewashing machine can be improved.

The invention discloses a method for correcting wrong content in sent communication text. The method includes the steps that a terminal displays the wrong content in the communication text through a specific method when detecting that errors exist in the sent communication text, can operate the wrong content and input error correction content, just packages the error correction content into first error correction text according to a preset format, and sends the first error correction text to an opposite-terminal device so that the opposite-terminal can renew the received communication text. Based on the same invention concept, the invention further provides a device, and under the condition that no new communication text needs to be additionally sent, the various problems caused when the wrong content is sent by a user in instant messaging can be solved.

The invention provides a long text error correction method and device based on artificial intelligence, and a computer readable medium. The method comprises the following steps that: when the originalfragment of a nondedicated noun is present in a long text, according to a preset PT (Phrase Table) in the field of the long text, carrying out PT segment recalling on the original segment which needsto be subjected to error correction to obtain the candidate segment set of the original segment, utilizing a pre-trained segment marking model to independently carry out marking on each candidate segment in the candidate segment set, wherein the candidate segment set comprises a plurality of candidate segments; and according to the score of each candidate segment, through a decoding way, obtaining a target segment corresponding to each original segment from the candidate segment set of each original segment, which needs to be subjected to the error correction, of the long text, and therefore,obtaining the error correction text of the long text. Through the technical scheme of the invention, deficiencies in the prior art are made up, a long text error correction scheme is provided, wrongsegments in the long text can be corrected, and the editing quality of the long text is effectively improved.

The invention relates to a text processing method and device. The method comprises the steps of obtaining a to-be-corrected initial text; performing spelling error correction processing on the initialtext to obtain a corresponding corrected text; conducting grammar error correction processing on the correction text through a forward codec and a reverse codec which are pre-trained, and obtaiing afirst candidate text and a second candidate text; performing language evaluation processing based on the first candidate text and the second candidate text to obtain an evaluation score; and determining a target text corresponding to the initial text according to the evaluation score and according to the first candidate text and the second candidate text. According to the scheme provided by the invention, the text error correction accuracy can be improved.

The invention discloses a text error correction method and device, equipment and a storage medium, and relates to the field of cloud computing and natural language processing. The specific implementation scheme comprises the steps of receiving a target text; performing error correction on the target text by utilizing a pre-trained text error correction model to obtain an error-corrected text; determining the error correction probability of the error correction text by using a pre-trained classification model; and outputting an error correction text in response to determining that the error correction probability is less than the preset threshold. According to the implementation mode, the accuracy of text error correction can be improved, the error correction rate is reduced, and the method is closer to real appeals of users.

The invention discloses a text information processing method, system and device and a computer readable storage medium. According to the method, the error correction model obtained by training the error correction training set corresponding to the type of the to-be-processed text is adopted in advance, error correction processing is conducted on the to-be-processed text, at least one correction text of the to-be-processed text is obtained, and correction of glyph errors and the like in the to-be-processed text is achieved; a named entity recognition model is obtained by training a structured feature training set corresponding to the type of a to-be-processed text in advance; extracting structural features of the corrected text; matching the structural features of the corrected text with the structural features of each part of standard text information in a trusted data set; and determining standard text information corresponding to the corrected text, thereby further correcting named entity errors existing in the corrected text through the structured features, and improving the accuracy of text information recognition.

The invention relates to an artificial intelligence technology, can be applied to the field of smart cities, and discloses an intelligent text error correction method. The method comprises the steps of performing unsupervised training on an original text error correction model by utilizing an unmarked text set to obtain a primary text error correction model, supervising and training the primary text error correction model by utilizing a marked text set to obtain a standard text error correction model, executing text shielding operation on the error correction text to obtain a shielded text; and inputting the shielded text into the standard text error correction model to obtain a prediction text and a prediction probability value of the prediction text, and performing text error correctionon the to-be-corrected text according to the prediction text when the prediction text is different from the to-be-corrected text and the prediction probability value is greater than the preset probability value. The invention further provides an intelligent text error correction device, electronic equipment and a computer readable storage medium. According to the method, the text error correctioneffect can be improved on the premise of not excessively consuming manpower and computer resources. In addition, the invention also relates to a blockchain technology, and the text and the text set can be stored in the blockchain.

The invention relates to a sample picture label correction method and device, computer equipment and a storage medium. The method comprises the steps of obtaining a picture sample set; wherein the picture sample set comprises training pictures and annotation text labels corresponding to the training pictures; detecting whether a labeled text label corresponding to the training picture is an abnormal text label; if yes, correcting the abnormal text label by adopting a preset label correction model to obtain a corrected text label corresponding to the abnormal text label; wherein the label correction model is obtained by training based on a label sample set, and the label sample set comprises an abnormal text label and a label correction text label corresponding to the abnormal text label. By adopting the method, manpower and time can be saved.

The invention provides a multimedia information title correction method and device based on artificial intelligence, electronic equipment and a computer readable storage medium. The method comprises the following steps: performing type identification processing on multimedia information to obtain the type of the multimedia information; performing error identification processing on the title of themultimedia information to obtain an error position in the title; searching a candidate correction database corresponding to the type according to the text of the error position to obtain a pluralityof candidate correction texts for correcting the text of the error position; and screening the plurality of candidate correction texts, taking the candidate correction texts obtained after screening as correction texts, and replacing the text at the error position of the title with the correction texts so as to form a correct title of the multimedia information. According to the invention, the title of the multimedia information can be automatically and accurately corrected, and the title correction efficiency is improved.

The embodiment of the invention provides a method for determining error-correcting text and related equipment, which is used for improving the error-correcting speed of searching text. The method comprises the following steps of: obtaining a target search text input by a user; Segmentation of the target search text to obtain a segmentation set; Determining an initial error correction word corresponding to each participle in the participle set from a corpus; Calculating an error correction probability of an initial error correction word corresponding to each word in the word segmentation set; Determining an initial error correction word having an error correction probability greater than a first preset threshold value as a target error correction word for each word in the word segmentationset; A target error correction text of that target search text is determine from a target error correction word of each word in the word segmentation set according to a preset rule.

The invention discloses a voice recognition method and device, a computer and a storage medium. The method comprises the steps that testing voice data input in the product defect testing process is acquired; the testing voice data is subjected to voice recognition through a voice recognition model, and the recognition text of the testing voice data is acquired; a trained Markov model is obtained;the recognition text is input into the Markov model, the recognition text is recognized through the Markov model, and the output probability of all correction texts output by the Markov model are acquired; the correction text corresponding to the recognition text is determined according to the output probability of the correction texts. According to the proposal, the Markov model is introduced, the recognition text obtained after common voice recognition is carried out on the testing voice data is corrected, then the correction text corresponding to the testing voice data is obtained, the efficiency of a tester of submitting testing defect data is improved, and the user experience is improved.

The invention relates to the technical field of computers, in particular to an OCR-based post-loan inspection method. The method comprises the following steps: S1, shooting and extracting a text picture of a photocopy of customer data; S2, inputting the text picture into a pre-trained text correction network model; S3, correcting the text picture and the classification saliency map by utilizing astrip-shaped region transformation algorithm; S4, outputting an identification text by adopting an optical character identification technology; S5, determining an error correction word corresponding to an error segmentation word with an identification error in the identification text; S6, determining an error correction confidence degree corresponding to the error correction candidate text througha neural network model, and taking the error correction candidate text of which the error correction confidence degree is greater than a first threshold value as an error correction text; S7, performing information comparison according to the error correction text, judging whether the information comparison is consistent or not, and if not, prompting manual recheck. According to the invention, the technical problem that the content of a photoprint with poor photoprint quality is inaccurately identified and captured by using an OCR technology is solved.

The invention discloses an error correction method and system for a real-time translated text, a storage medium and a device, and relates to the field of voice error correction. The method comprises the steps that: an ASR translation text in real-time live broadcast is acquired, the ASR translation text is interpreted through a trained BERT error correction model, and a first error correction text is output; the ASR translation text is interpreted through the trained GPT error correction model, a second error correction text is output, the first error correction text and the second error correction text are combined to obtain an error correction target text, and end-to-end error correction is performed on the ASR translation text content in the live broadcast scene through the scheme, the character accuracy of the ASR on an audio translated text can be effectively improved, and the method can be quickly applied to the field of live broadcast.

The invention provides a grammar error correction method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the error detection of a to-be-corrected text, and obtaining an error text segment; performing error correction on the error text fragment to obtain a corrected text fragment corresponding to the error text fragment; determining an error type corresponding to the error text fragment based on the interaction vector between the error text fragment and the correction text fragment, wherein the interaction vector is used for representing difference characteristics and common characteristics between the error text fragment and the correction text fragment. According to the grammar error correction method and device, the electronic equipment and the storage medium, error detection and error correction are carried out on the to-be-corrected text to obtain the error text fragment and the correction text fragment, and the error type corresponding to the error text fragment is determined based on the interaction vector between the error text fragment and the correction text fragment, therefore, the grammar error correction method provided by the embodiment of the invention has interpretability.

The invention discloses methods, devices and equipment for correcting a categorizer and constructing a categorizing corpus and a medium. The method for correcting the categorizer includes the steps that category center vectors corresponding to two or more text categories of the categorizer are obtained; a correction text of a set text category and text feature vectors of the correction text are obtained; according to the similarity of the text feature vectors and the category center vectors of all the current text categories of the categorizer and the text category of the correction text, thecategory center vectors corresponding to all the text categories in the categorizer are corrected; execution is performed again to obtain the correction text of the set text category and operation ofthe text feature vectors of the correction text until correction-ending conditions are met, so that the corrected categorizer is obtained. Through the method, influences on the category center vectorsof a text with wrong categorization are larger, and the error rate of text categorization is decreased.

The invention discloses a text error correction method and device and electronic equipment, and relates to the field of artificial intelligence, in particular to natural language processing. According to the specific implementation scheme, the method comprises: generating a first similar proper noun according to an original text and a low-frequency proper noun library; querying a high-frequency proper noun library according to the first similar proper noun to obtain a comparison text; and inputting the original text and the comparison text into a text comparison model, and obtaining a correction text corresponding to the original text. According to the embodiment of the invention, the corresponding corrected text can be obtained according to the original text. According to the embodiment of the invention, error correction is carried out on the proper nouns in the original text, so that wrong proper nouns in the original text can be avoided, and the accuracy of text error correction is improved.