395 results about "Input method" patented technology

The invention discloses a consultation method and system based on natural language processing and a legal knowledge graph, and relates to the field of data processing, and the method comprises the steps: receiving a multi-format legal consultation demand of a user, converting the multi-format legal consultation demand into a text, inputting the text into a BERT law NLP model, and analyzing key information through word segmentation, intention recognition and entity extraction; based on a pre-constructed multi-level legal knowledge graph, carrying out accurate and fuzzy retrieval and domain filtering in combination with an analysis result, and obtaining an associated law article, a case and a legal relationship; screening conflict law articles and similar cases, and inputting the conflict law articles and the similar cases into a graph neural network reasoning model to generate a preliminary conclusion; the conclusion is converted into a spoken consultation report through a natural language generation module, and output is customized according to a user scene; and if the user feedback satisfaction degree is less than the threshold value, iteratively optimizing the storage data to the historical library. The method has the advantages that accurate retrieval is realized based on the BERT model and the multi-level knowledge graph in the legal field, the oral personalized conclusion combined with the user scene is generated through GNN reasoning, and iterative optimization is performed through user feedback.

The invention provides a paper file information input method, system and device and a medium, and belongs to the technical field of file information processing. The method comprises the steps of collecting a paper file image, performing preprocessing in sequence to obtain a preprocessed image, and performing region segmentation on the preprocessed image by using a target detection algorithm to generate a region coordinate mapping table; generating a file template by using a predefined file template library according to the region coordinate mapping table; performing printing form recognition and handwritten form recognition on characters in the image by using a sequence generation model to generate a text sequence, and recognizing a table structure by using a two-dimensional convolutional network; according to the text sequence and the table structure data, a named entity recognition model is used for labeling field types, data formats are checked and corrected according to template rules, errors are corrected in combination with context semantic similarity, and structured data are generated; and mapping the structured data to an information system database table according to a template field mapping rule, and inputting the structured data into an information system.

The invention discloses a document information input method and device and a storage medium, and relates to the technical field of electronic digital data processing.The document information input method comprises the steps that a document type is determined according to characters obtained by recognizing a to-be-processed document; calling a large language model to extract an entity in the character, and associating an entity relationship, a service intention, a context and a context relationship corresponding to the entity as reference information of the entity; constructing an extraction problem based on a field in a business data structure file corresponding to the document type; and in combination with the reference information, extracting a target field from the entity through the extraction question. According to the method and the device, the technical effect of efficiently and accurately converting the fragmented characters into the structural data available to the business system can be realized.

The invention discloses a building engineering target cost-oriented multi-dimensional data classification input method and system, and the method comprises the steps: aligning BIM space coordinates, construction progress nodes and purchase order data to a space-time grid in response to a multi-source data input instruction, fusing a field instruction document into the space-time grid through text recognition and key information extraction, and carrying out the recognition of the field instruction document; generating a time-space-cost associated data set; analyzing the data set to eliminate regional term ambiguity and ambiguity term ambiguity; extracting an implicit cost item by using a graph neural network, and mapping the implicit cost item with a target cost model; the priority sequence of data entry is dynamically adjusted according to the sensitivity coefficient of the cost item and the progress deviation early warning level of the grid unit where the cost item is located; and performing real-time integrity verification and conflict detection on the high-priority data, inputting the high-priority data into a target cost database in a classified manner, and generating a cost deviation analysis report. According to the method, deep association and ordered entry of data of different structures are realized, and the data classification efficiency and the accuracy of target cost accounting are improved.

The invention provides a contract input method and device and a storage medium. The method comprises the steps of determining a target contract file; executing optical character recognition on the target contract file in multiple dimensions to obtain multiple contract elements; contract semantic information is added to the multiple contract elements according to a large language model; checking the multiple contract elements carrying the contract semantic information according to contract specifications; and if the multiple contract elements carrying the contract semantic information are successfully verified, mapping the multiple contract elements into a database according to the contract semantic information. According to the embodiment of the invention, through the perception-cognition integrated architecture design, the full-automatic input of the element from the target contract file to the structured contract is realized, the semantic analysis of the contract is provided by the large language model, the dependence on a rule engine is effectively reduced, the adaptability is strong, the precision is high, the maintenance cost is low, and the contract input efficiency is effectively improved.

The invention discloses a work order input method and device based on a large model, equipment and a storage medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: carrying out the data cleaning and preset standardization processing of an initial problem description, so as to determine a target problem description corresponding to the initial problem description; analyzing the target problem description by using the target large model to obtain an analysis result, and extracting key problem information in the target problem description based on the analysis result; matching the key problem information with a preset work order category system to determine a target work order type corresponding to the target problem description; filling the key problem information into a target work order template corresponding to the target work order type to obtain initial work order information corresponding to the target problem description; obtaining feedback information corresponding to the initial work order information, adjusting the initial work order information based on the feedback information to obtain target work order information, and inputting the target work order information into a work order system. The work order processing efficiency can be improved, and the manual operation cost can be reduced.

The invention provides a medical information input method and device, electronic equipment and a readable storage medium, and the method comprises the steps: extracting text content in an image, and inputting the text content and a classification task prompt text into a first large language model, so as to determine a medical category to which the text content belongs; aggregating the text contents belonging to the same medical category to obtain a medical text belonging to the medical category; determining a structured template corresponding to the medical category, and inputting the medical text belonging to the medical category and an extraction task prompt text matched with the structured template into a second large language model, enabling the second large language model to output structured medical extraction data containing medical field values according to format requirements of the structured template; and uploading the structured medical extraction data to an electronic system matched with the medical category to enable the electronic system to carry out medical information input. Through the method, the input efficiency and accuracy of the medical information are improved.

The invention relates to the technical field of input methods, in particular to a full-hybrid input method for Chinese and English input. During initial full-mixed input, after a letter is input into a first key of each word, a background algorithm passes through full spelling, binary spelling and pinyin and two-key shape code letter input channels; after the first key of each word inputs a note isolation, a background algorithm passes through a simple spelling input channel at a time; after the English comma is input into the first key of each word, a background algorithm passes through a full-shape code input channel at a time; after a decimal point is input into the first key of each word, a background algorithm passes through an English input channel once; for single input of various input methods, after needed characters and words are submitted, the input is automatically returned to the initial fully-mixed input; and in a full-spelling and binary-spelling five-sound display mode, inputting a note insulation, inputting a background algorithm through a pinyin and two-key shape code alphabet input channel at a time, inputting pinyin and two-key shape code alphabet at a time, and automatically returning to initial full-mixed input after required words are submitted.

The invention provides a pinyin decoding input method, an embedded system and a storage medium. The method comprises the following steps: constructing a hierarchical code table index database; obtaining a pinyin character string input by a user, and determining a first index of the pinyin character string in the initial index layer according to the initial of the pinyin character string; calculating a Hash value of the pinyin character string by using a Hash algorithm, and obtaining a second index corresponding to the Hash value in a Hash table; searching in the pinyin data block according to the second index to obtain a pointer corresponding to the pinyin character string; and matching in the word data layer by using the pointer to obtain corresponding word data. According to the method, the memory pressure of the embedded system is reduced, the three-layer index structure of the hierarchical code table index database is utilized, and the optimized hash search algorithm is adopted to accelerate data access, so that high-precision matching and quick positioning are realized in an embedded environment.

1. The name of the design product: expression form area of input method expression form aggregation display and interactive graphical user interface for electronic device. 2. The use of the design product: an electronic device. 3. The design points of the design product: the part in the graphical user interface, the part without dotted line is the claimed part. 4. The picture or photo that best shows the design points: front view. 5. The use of the graphical user interface: the whole interface is used to aggregate display various forms of expression content (such as: expression package, expression special effect, quotation, picture, audio / video, etc.) in input method, and can click any form of content to send quickly, chat interaction, etc.; the part of the interface is used to aggregate display various forms of expression content (such as: expression package, expression special effect, quotation, picture, audio / video, etc.) in input method, and can click any form of content to send quickly, etc. 6. The human-computer interaction mode of the graphical user interface: in the front view, when the user continuously slides upwards in the expression form aggregation module in the input method "expression area", all the module contents of the expression form aggregation module are displayed, and the interface changes from the front view to the interface change state view 5. (The interface change state view 1 to the interface change state view 5 are all module contents of the expression form aggregation module displayed after sliding.)

The application discloses a character input method and device, electronic equipment and a storage medium, and belongs to the technical field of electronic equipment. The method comprises the following steps: receiving a first input for inputting a word group pinyin in an input method keyboard; in response to the first input, displaying at least one word group unit corresponding to the word group pinyin, each word group unit comprising at least one candidate word; in response to a second input for selecting a target word group unit from the at least one word group unit, displaying the target word group unit in a text input area corresponding to the input method keyboard.

Methods, systems, and computer program products for synchronizing a plurality of audio inputs may include receiving data inputs including a first data input, a second data input, and a third data input, from one or more data source, providing, as inputs to a media management system, the first data input, the second data input, the third data input, and data associated with a synchronization function with regard to synchronization of the data inputs for use by the media management system to generate an output, and executing a synchronization procedure on the first data input, the second data input, and the third data input to generate the output of the media management system, the output of the synchronization procedure of the media management system including a synchronized audio-video file combining the first data input, the second data input, and the third data input.

The invention belongs to the technical field of electroencephalogram signal processing, and particularly relates to an alternating current auxiliary system for generating a Chinese text based on electroencephalogram. The system comprises: an input module configured to input an electroencephalogram signal; and the electroencephalogram signal classification module is configured to input the electroencephalogram signals into a classification model to obtain a classification result of phonetic alphabets. In order to further generate the Chinese text, the system can further comprise a Pinyin input method module which is configured to convert the classification result of the Pinyin letters into the Chinese text through a Pinyin input method. The Chinese text generated by the system and the method has the characteristics of high efficiency and accuracy, is greatly helpful for communication demands of paralysis, aphasia and asymptomatic diseases caused by stroke, and has a good application prospect.

Embodiments of the present application provide a recommendation method, device and medium. The method specifically comprises: determining matching information between candidate content and user portrait features; the user portrait features are obtained according to user usage behavior data for input method provided candidate items and labels of the candidate items; and the candidate content is recommended according to the matching information. Embodiments of the present application can improve the accuracy of recommendation; in the recommendation scene of the input method, the recommended candidate items can meet the personalized input intention of the user.

The invention discloses a multidirectional sliding Chinese character pinyin input method and a matrix type keyboard layout system, and belongs to the technical field of human-computer interaction of touch screen equipment (IPC classification number: G06F3 / 0488, G06F3 / 0323G06F 40 / 274). Aiming at the problems of complex vowel operation redundancy, initial and final combination conflict and the like in the existing sliding input method, the invention provides the following schemes: 1, the multidirectional sliding input method comprises the following steps of: starting sliding from any initial consonant or vowel (containing a zero initial consonant 0 / er key) on the basis of a matrix keyboard layout; different vowels or vowel combinations are mapped every time sliding is performed by one key in different directions or continuous sliding is performed. 2, multi-direction sliding input logic: defining an 8-direction sliding mapping er to be rightward-or-generated from e in a layout E; the method has the technical effects that the input efficiency is improved by more than 60% (high-frequency syllable steps are reduced by 70%), the false touch rate is lower than 5%, the national standard pinyin library is covered by 100%, and the method is obviously superior to a traditional touch screen input scheme.

The embodiment of the invention provides an information recommendation method and device and electronic device.The method comprises the steps that when an input method interface is called, an intelligent assistant in an input method is started; receiving an awakening operation of a user for the intelligent assistant, and awakening the intelligent assistant; the intelligent assistant performs information recommendation; the intelligent assistant can recommend information to the user; therefore, the diversity of the recommended information can be increased, and user requirements can be better met.

The invention discloses an interactive story machine based on an ROS and a large model and a control method of the interactive story machine. The story machine comprises an input module, an ROS system, a large model module, an audio output unit and a color ink screen. According to the invention, through cooperative work of software and hardware modules, an ROS system is used as an intelligent scheduling center, and meanwhile, a large model module is introduced, so that user interaction input modes and personalized demands of different user types can be understood and responded, and personalized story contents are dynamically generated; for the hearing-impaired user type, based on a barrier-free interaction mode, generating image prompt information and a smooth sign language action sequence, and driving a color ink screen to perform visual presentation through an optimized rendering instruction; and for a non-hearing-impaired user type, synchronously generating a story text fragment, a matched image illustration and voice information based on a multi-mode interaction mode, and providing an immersive story reading environment for different types of child users.

The keyboard according to the present invention is characterized in that a user who is used to input Japanese by using Roman can easily grasp the keyboard without having a large sense of fall, and the number of keystrokes required is greatly reduced compared to Roman input, thereby enabling more efficient input. According to the Japanese keyboard provided by the invention, not only consonants of i sections or a section a, but also large letters (,) of kana (,,), '-', 'hook, large letters (,) of kinphonic sound, small letters (,) of kinphonic sound, continuous characters (-) and full stop '.' in the Japanese keyboard are provided. The Japanese keyboard has the advantages that the consonants are not only consonants of i sections or'a) sections, but also consonants of kana (,,), '-', 'hook', large letters (,) of kinphonic sound, small letters (,) of kinphonic sound; therefore, the number of keystrokes for inputting Japanese can be significantly reduced.

This application provides an input method based on a virtual keyboard, including detecting a first input operation applied to an operation area; mapping the first input operation to the operation of a corresponding key in a key display area to obtain a second input operation for the virtual keyboard, wherein the operation area and the key display area are located in different positions; obtaining an input event based on the second input operation; and responding to the input event by displaying the input information corresponding to the input event in an input box. The input method provided in this application allows the operation area and key display area of ​​the virtual keyboard to be set independently. When applied to widescreen devices, the operation area can be located in an area of ​​the touch screen that is more easily accessible to the user's hands, enabling the user to perform input operations in an area more easily accessible to both hands. The operation input is mapped to the virtual keyboard for input, while the key display area is centrally displayed, allowing the user's gaze to focus on the key display area, reducing the distance the user's gaze travels and improving the user experience.

To obtain a result of character recognition or predictive search desired by a user.SOLUTION: A handwriting input device capable of handwriting input comprises: conversion means of converting a handwritten character string input by handwriting into a recognition result character string through character recognition; search means of searching for a prediction candidate character string corresponding to the recognition result character string; display control means of displaying the prediction candidate character string on a screen in a selectable manner; and expansion means of expanding a search range of the prediction candidate character string by the search means when a handwriting speed of the handwritten character string is lower than a predetermined threshold or when a distance between adjacent characters in the handwritten character string is larger than a predetermined threshold. The display control means displays the prediction candidate character string searched by the search means using the expanded search range on the screen in a selectable manner.SELECTED DRAWING: Figure 5

We provide the system. [Solution] An input method for the user to enter information, A transmission means for sending information from the input means to a server, A generation means that generates information based on the information received from the transmission means, A presentation means for presenting the information generated by the generation means to the user, A system that includes this.

Approaches disclosed herein relate to dynamically determining and assigning user interface (UI) interaction modes across multiple multimodal devices based on real-time detection of input methods and screen sizes. Input methods are detected using web APIs. A screen size is determined using CSS pixel measurements and monitored for changes. CSS media queries are used to detect the effective resolution of the device's display. By applying breakpoints defined in CSS, the screen size can be categorized into predefined groups. The device state may be continuously monitored in real-time to identify any modifications, such as connecting or disconnecting input devices. Events triggered by these changes may be captured using the web APIs and event listeners. Such a system can listen for events like connecting or disconnecting devices to dynamically reassign the interaction mode. Such reassignment can be guided by an algorithm that prioritizes input methods based on the device's screen size and context.

The invention provides a touch screen input method and system, and relates to the technical field of touch recognition of electronic equipment.The touch screen input system comprises the steps that an input completion instruction of a user to a touch screen in each application scene is obtained; according to the input completion instruction, collecting an operation gesture corresponding to completion of the input completion instruction; according to the operation gesture and the application scene thereof, establishing operation sets corresponding to different application scenes; performing gesture analysis on each operation set to obtain a habitual gesture model; detecting a target gesture of the user through the habit gesture model to obtain a detection result; and according to the detection result, matching a corresponding target input completion instruction to complete instruction input. According to the input method and system provided by the invention, the input completion instruction response timeliness and accuracy can be ensured when the user inputs the operation gesture on the touch screen, so that the operation gesture input process is more intelligent.

The invention provides an error correction method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining input information in a current environment, and determining a conventional decoding result and an error correction decoding result corresponding to the input information; based on the input information, determining a first discriminant statement corresponding to the conventional decoding result and a second discriminant statement corresponding to the error correction decoding result; and determining an error correction strategy for the input information based on the semantic smoothness of the first discriminant statement and the semantic smoothness of the second discriminant statement, and driving an error correction decision by constructing the discriminant statements containing the context and utilizing the semantic smoothness difference of the whole statements, so that the error correction accuracy of the input information is improved. According to the method, the input method can judge whether error correction is needed or not according to the context like human beings, real input errors can be accurately captured, disordered error correction of a traditional static rule in a specific context can be effectively restrained, and high-precision and intelligent error correction experience is achieved.

The invention relates to the technical field of garment customization, in particular to a garment size measurement data entry method based on flickering line prompt of a human body line drawing, which comprises the following steps of: S1, displaying a corresponding human body line drawing template according to the gender of a user, and controlling lines corresponding to each measurement part to flicker in sequence or according to a rule, prompting a user to measure the size; s2, a user measures a corresponding part according to the flicker prompt and inputs size data; after the system receives the input, changing the state of the corresponding line from flickering to stable display, and marking as completed; s3, when it is detected that the user presses the line number for a long time, the system triggers the voice module to play the measurement guidance of the part, and dynamic schematic signs of the measurement starting point and the measurement ending point are synchronously displayed on the graph, the personalized human body line drawing is generated based on the filled or missing size, a visual reference is provided for garment customization, virtual fitting and remote customization, and the user experience is improved. And meanwhile, the system is intelligent and good in expansibility.

Methods, systems, apparatuses, and computer program products are provided herein for determining the handedness of input provided by a user via a touch interface. For instance, for each touch-based input detected, a score indicating a probability whether the touch-based input was inputted by a particular hand of the user is generated. A classification for the touch-based input is then generated based on a drift diffusion model-based technique in which inter-dependencies between a series of touch-based input are approximated. The determined classifications are used to determine the handedness of the user.

The invention discloses an information input method and device, electronic equipment, a storage medium and a program product, and belongs to the technical field of artificial intelligence. The method comprises the steps of displaying shortcut input information under the condition that a first interface is displayed; wherein the first interface comprises an information input area and an input keyboard control, the shortcut input information is determined according to memory data and interface content of the first interface, and the memory data is determined according to fragmented information generated in the process that a user uses the electronic equipment; and displaying the shortcut input information in the information input area in response to the first input.

This disclosure provides a processing method, apparatus, computer device, and storage medium for an input method application. The method acquires interaction smoothness optimization instructions for the input method application; collects input event response time and page rendering time within a target acquisition period; performs application stuttering detection on the input method application based on the input event response time and page rendering time, obtaining stuttering detection results; when the stuttering detection results indicate that the input method application experiences stuttering, acquires hardware configuration data and load information of the target terminal; determines multiple target optimization operations from multiple smoothness optimization operations based on the hardware configuration data and load information; and modifies the settings of the input method application based on the multiple target optimization operations. This method can improve the detection efficiency of application pages. This method can improve the stuttering problem of input method applications.

The present disclosure relates to an audio input method, an electronic device, a storage medium and a computer program product, and relates to the technical field of computers. The audio input method comprises: in response to a first operation of a user on an audio input control, collecting audio; in the process of the user performing the first operation on the audio input control, determining an input mode according to a second operation of the user, wherein different input modes correspond to different output modes; and outputting content corresponding to the audio according to the output mode corresponding to the input mode.

This application discloses an input recommendation method, apparatus, electronic device, and storage medium. The method includes: acquiring an input pinyin string and determining the number of preset words matched by the pinyin string in a preset word library; if the number does not exceed a preset threshold, performing word grouping processing on the pinyin string based on the preset word library to obtain a candidate word set; inputting the pinyin string into a syllable segmentation network for syllable segmentation processing to obtain a predicted syllable sequence corresponding to the pinyin string, wherein the syllable segmentation network extracts features for syllable segmentation processing from the pinyin string based on a lightweight convolutional module; inputting the predicted syllable sequence into a word prediction network for word prediction to obtain a predicted word set; and outputting recommended words based on the candidate word set and the predicted word set. This application improves the accuracy and efficiency of input recommendation and is highly suitable for input method recommendation on low-resource devices (such as smartphones).