15 results about "Standard Chinese" patented technology

The invention is suitable for the technical field of semantic understanding, and provides a dialogue type AI multi-intention understanding and decision-making method for a tourism scene, and the method comprises the steps: obtaining a tourism scene dialogue text which is input by a user and is expressed by a dialect; dialect expression is converted into standard Chinese statements through a dialect translation engine, and translation semantic deviation is corrected through a semantic correction model; performing multi-intention modeling on the converted standard Chinese statements, adopting a pre-training language model to combine with dynamic word segmentation processing, aligning special words of dialects to a standard Chinese word list through a dialect word mapping table, and adjusting semantic representation to adapt to dialect features; generating word list probability distribution, and generating a dialect compatible reply containing a multi-intention decision result in combination with an autoregression model; a dialogue state tracking model is trained according to geographic information, user historical interaction data and a cross-dialect corpus, intention switching and composite requests in multiple rounds of dialogues are analyzed, and dialect compatibility and intention recognition accuracy are effectively improved.

The invention discloses a Chinese character recognition method based on Chinese character similarity algorithm joint optimization. Comprising the steps of obtaining a to-be-recognized Chinese character image, inputting the preprocessed image into a convolutional neural network classifier, and outputting a Chinese character category prediction result; obtaining a corresponding standard Chinese character image from the Chinese character database, and respectively calculating stroke similarity, structural similarity and topological similarity between the to-be-recognized image and the standard image; calculating a Chinese character similarity score based on multiple similarity fusion; and constructing a joint loss function containing classification loss and similarity loss, and carrying out joint training on the classifier network. By introducing a stroke template feature extraction and dynamic time warping algorithm, accurate matching of stroke forms and sequences is realized. The technical problem that similar Chinese characters are difficult to distinguish in a traditional recognition method is effectively solved, deep fusion and collaborative optimization of classification and similarity information are achieved, the accuracy and stability of Chinese character recognition are remarkably improved, and the method is suitable for diversified application scenes.

A storage format of Chinese language (“Readable Hanyu Expression” or “RHE”) and the related processing methods and systems. Unlike current Chinese processing methods which directly code Chinese characters into fonts for display, RHE takes an indirect approach by storing Chinese language in the RHE storage format that can be mapped to several display forms including simplified and traditional Chinese characters, Hanyu Pinyin, etc. In the RHE storage format, each Chinese word is stored as an RHE storage element having the format (Syllable+Tone)n+Mark, where n is the number of syllables (Chinese characters) in the word, Syllable represents the pronunciation (without the tone) of the character, Tone represents the tone of the pronunciation, and Mark is a value that differentiates different words having the same pronunciations and tones. Various mapping tables are used to map RHE storage elements to standard Chinese character codes (such as Unicode) and Pinyin expressions.

The invention discloses a handwritten Chinese character recognition and error correction method based on artificial intelligence. The method comprises the following steps: establishing a data sample set corresponding to Chinese characters of various non-standard types; performing preprocessing of noise disturbance addition on the data sample set to obtain sample coefficients of various non-standard types; constructing a Chinese character recognition attention model; taking the preprocessed data sample set as a training set to train a Chinese character recognition attention model; collecting and preprocessing a handwritten Chinese character image to be recognized to generate a handwritten Chinese character image to be processed; inputting the handwritten Chinese character image to be processed into the trained Chinese character recognition attention model, and outputting the non-standard type of the handwritten Chinese character to be recognized; and correcting the non-standard type in the recognition result based on the graph convolutional neural network. According to the method, non-standard Chinese character initial classification is carried out on the image through the Chinese character recognition attention model, and secondary fine classification is carried out on the image through the graph convolutional neural network, so that the non-standard Chinese character recognition speed is high, and the non-standard Chinese character correction accuracy is high.

The invention relates to the technical field of general standard Chinese character education, and discloses a Chinese character form intention spectrum construction method and system based on a key thing topology network. According to the method, a three-layer topology network model of'key things-form meaning source components-general standard Chinese characters' is established, abstract classification of a six-book theory is converted into concrete cultural gene traceability, and memory fragmentation is eliminated; a structural weight engine is used for accurately quantifying a composite character component relation, and the deconstruction limitation of a radical retrieval method on form and meaning logic is solved; a cross-culture cognition bridge is constructed through a natural domain / humanistic domain bipartite system, the understanding deviation rate of international students is reduced, finally, a form and meaning association graph of a general standard Chinese character total word stock is achieved, and a Chinese character cognition normal form with culture depth and learning efficiency is formed.

The application discloses a kind of foreign language place name translation software quality evaluation method, comprising the following steps: step one, constructing place name database;Step two, the component annotation of foreign language place name in the data set to be measured;Step three, foreign language place name is input foreign language place name translation software one by one, if corresponding standard Chinese translation name can be directly inquired from reference data set, then quality evaluation score is the highest score;Otherwise, enter step four;Step four, translation and calculate quality evaluation score.Step five, traverse data set to be measured, obtain the quality evaluation score of each foreign language place name.Step six, the score of foreign language place name translation software is calculated.The method of the application is simple, reasonable in design, aimed at Chinese translation name acquisition place name component, for different place name component reasonable distribution confidence, output accurate quality evaluation score, and place name is divided into superior data and data that need to be approved, clear the focus of manual review, improve the efficiency of evaluation method, improve the adaptability of evaluation method.

The application relates to the field of data processing, in particular to an address standardization method and device, electronic equipment and a storage medium, which comprises the following steps: acquiring an address text; predicting based on the address text to determine the predicted administrative regions of each level corresponding to the address text; acquiring the administrative region codes corresponding to the predicted administrative regions of each level respectively, and generating an address file in a preset format based on the address text, the predicted administrative regions of each level and the administrative region codes corresponding to the predicted administrative regions of each level respectively. The application has the effect of improving the accuracy of standardizing non-standard Chinese addresses.

This invention discloses a method for Chinese character input combining eye-tracking and P300 technology. The method utilizes the spatial modulation information of the eye-tracking device to select a mode: the eye-tracking device collects the user's visual trajectory in real time, obtaining the coordinates of the user's eye movement points. When the user gazes at the start option, the system detects this intention and generates a command to activate the spelling process. Combining the eye-tracking device and P300 technology, the initials and finals of the Chinese characters are selected. The method then integrates with a Pinyin input method to achieve the function of inputting Chinese characters: after selecting the initials and finals, the user switches to the Pinyin input method, selects the target Chinese character, and thus achieves the Chinese character input function. This invention, combining eye-tracking and P300 technology for Chinese character input, allows users to achieve computer typing functions without taking any action, relying solely on their eyes and brain. Furthermore, the use of a standard Chinese input method's character library enables matching Chinese characters after spelling. This expands the scope of assistive devices for people with movement disorders beyond computer devices themselves, and has significant practical implications.

The invention belongs to the technical field of artificial intelligence and robot control, and particularly relates to a handwriting trajectory self-adaptive correction method for a calligraphy practicing robot. The method aims at solving the problems that a traditional calligraphy practicing robot is difficult to adapt to individual writing styles, and trajectory correction intelligence is insufficient. The pen wielding track, the pressure, the speed and the pen tip inclination angle of a user are collected in real time through a high-density pressure sensing array and a high-speed visual sensor, and a multi-modal data stream is formed; a personalized handwriting feature model is constructed by adopting a long-short-term memory network, and dynamic features such as starting strength and turning acceleration are extracted; generating an initial expected track matched with a user style in combination with the standard Chinese character path; in the execution process, the inertia measurement unit and the electromagnetic positioning module are used for feeding back an actual track in real time. According to the method, the track naturalness and the correction accuracy are improved, the writing texture consistency is guaranteed, and multi-user concurrent and long-term personalized teaching is supported.

The invention discloses a dialect speech recognition method and device based on acoustic anchor points, and the method comprises the steps: constructing a mixed word list; performing character labeling on the dialect audio according to the mixed word list to obtain a dialect seed bank; obtaining a mandarin corpus, and performing feature extraction and splicing on mandarin audios in the mandarin corpus and dialect audios in the dialect seed bank to obtain an artificial mixed sample data set; obtaining a mixed language video, extracting text content and audio corresponding to the text content, and performing language recognition and voice recognition to obtain a natural mining sample data set; according to the mandarin corpus, the artificial mixed sample data set and the natural mining sample data set, carrying out staged progressive training with different proportions on the dialect speech recognition model so as to carry out dialect speech recognition by adopting the trained dialect speech recognition model; therefore, accurate recognition of dialect speech is realized under the condition of low resources.

The invention relates to the field of power grid monitoring information processing, in particular to a power grid monitoring information standardized mapping method, device and equipment. Analyzing the monitoring information table and the telecontrol configuration description file, and respectively extracting a point number and a Chinese description and a point number and a data object reference name corresponding to each piece of monitoring information in the monitoring information table and the telecontrol configuration description file; the point number is used as an association key, and the Chinese description of the same monitoring information is matched with the data object reference name; for each piece of monitoring information, respectively carrying out similarity calculation on the Chinese description and the data object reference name of each piece of monitoring information and a standard Chinese description and a standard data object reference name of each piece of standard monitoring information in a standard information model library to obtain a corresponding Chinese description similarity and a corresponding data object reference name similarity; and on the basis of the double-similarity calculation result, judging standard monitoring information to which the monitoring information should be mapped, and establishing a standardized mapping relationship. And a unified and reliable data basis is provided for deep utilization of monitoring information in advanced applications such as risk early warning and fault diagnosis.

The invention relates to a real-time feedback handwritten Chinese character image evaluation and optimization system in the technical field of image recognition. The system comprises a preprocessing module, a recognition module, a storage remark module, a feedback optimization module and a comprehensive evaluation module, the preprocessing module comprises a recording unit, a denoising unit, a feature extraction unit and a segmentation unit; the identification module comprises a superposition mark comparison unit, an association extension unit and an abnormal mark unit; the storage remark module comprises a common and false character storage unit, a special-shaped character storage unit and a standard Chinese character storage unit; the feedback optimization module comprises a writing optimization unit, a content optimization unit and a written optimization unit; the comprehensive evaluation module comprises a comparison standard unit, a visual recognition display unit and a visual abnormity display unit, and through the handwritten Chinese character image evaluation and optimization system, the recognition accuracy of handwritten Chinese characters can be comprehensively improved, and comprehensive real-time evaluation and optimization feedback can be carried out on handwritten Chinese characters of a writer.

The present application relates to the technical field of artificial intelligence, and particularly provides a writing Chinese character evaluation method, device and medium, aiming at solving the problem of unreasonable writing Chinese character evaluation. For this purpose, the writing Chinese character evaluation method provided by the present application comprises: acquiring a writing Chinese character image and identifying each writing Chinese character in the image; acquiring a standard Chinese character image and identifying the standard Chinese character corresponding to each writing Chinese character in the image; respectively evaluating the composition layout score, font structure score and font stroke score of each writing Chinese character according to the standard Chinese character corresponding to each writing Chinese character; and acquiring the font score of each writing Chinese character according to the composition layout score, font structure score and font stroke score of each writing Chinese character; determining and outputting writing evaluation information according to the font score of each writing Chinese character, wherein the writing evaluation information at least includes the font score, writing problem and solution thereof. Through the above-mentioned mode, the user's writing Chinese character can be evaluated from multiple angles, and a reasonable evaluation can be obtained.

The invention provides a data standard recommendation method and device. The accuracy of data standard recommendation can be improved. The data standard recommendation method comprises the steps of obtaining standard information and to-be-treated data in a preset standard pool; wherein the standard information comprises a standard English name field, a standard Chinese name field, a standard description field and a data type field; dividing the standard information in the preset standard pool according to a preset hierarchy to obtain a hierarchical structure and a hierarchical priority; vectorizing the standard information divided into hierarchical structures and hierarchical priorities, and constructing a standard vector library; based on a hierarchical structure and a hierarchical priority, performing hierarchical matching on the to-be-treated data from the standard vector library to obtain a recommendation result; wherein the recommendation result represents standard information correspondingly associated with the recommended to-be-governed data.

The invention relates to the field of translation, and discloses an English translation system based on machine learning, which comprises a database used for storing a translation set comprising an English-standard language-common language mapping set; the voice receiving module is used for receiving the voice of the user and carrying out noise reduction and impurity removal processing on the voice; the translation module is used for mutually translating English and standard language; the selection module is used for selecting a common language corresponding to the standard Chinese language in the database; the output module is used for outputting common languages; the learning module receives the language of the user, learns the common language habits of the user, establishes a corresponding relation with the standard language and stores the corresponding relation into the database, and the English translation system based on machine learning can realize learning according to the voice habits of the user, so that the translated language and semantics are accurate and vivid in expression.