205 results about "Predictive text" patented technology

The invention discloses a voice recognition model optimization method and device based on reinforcement learning, equipment and a medium, and relates to the technical field of voice recognition, and the method comprises the steps: determining a current optimization strategy of a current time step; randomly selecting one piece of enhanced speech training data and corresponding real text training data from the data training set as target training data, and inputting the target training data into the current automatic speech recognition model for prediction to obtain a plurality of prediction texts output by the current automatic speech recognition model; determining a text matching degree and a semantic similarity between each prediction text and real text training data to obtain a group of target reward values, updating an optimization strategy at the current moment based on the target reward values, and skipping to execute the step of determining the current optimization strategy of the current time step to obtain a target reward value; and outputting the corresponding optimized automatic speech recognition model until the current automatic speech recognition model meets the optimization ending condition. And reasonable optimization of the automatic speech recognition model is realized.

The invention provides a construction and training method and device for an eye fundus image multi-task model, and belongs to the field of image processing, and the method comprises the steps: S1, collecting and sorting a public eye fundus image data set, constructing an image text pair according to a real label, and carrying out the two-stage training of a multi-modal large language model, the multi-mode large language model comprises a visual encoder, a visual projector and a large language model; s2, inputting the image data # imgabs0 # into a visual encoder in the trained multi-modal large language model to obtain an enhanced visual feature # imgabs1 #, and extracting a visual feature # imgabs3 # from the # imgabs2 # through a visual projector; and S3, embedding the text input # imgabs4 # to obtain a text feature # imgabs5 #, splicing the text feature # imgabs5 # with the visual feature # imgabs6 #, and inputting the spliced text feature # imgabs5 # and the visual feature # imgabs6 # into a large language model to generate a prediction text A. According to the method, a wide range of fundus image data is collected for training, multilevel lesion features in the fundus image are fully utilized, and the performance of the model for executing a fundus disease auxiliary diagnosis task can be effectively improved.

The present application provides a training method for a text processing model, a training apparatus for a text processing model, an electronic device, a program product, and a storage medium. The method comprises: acquiring a sample text set; splicing at least two independent sample texts among a plurality of independent samples texts to obtain a plurality of spliced sample texts; on the basis of the plurality of spliced sample texts, calling an initialized text processing model to perform feature extraction processing to obtain a plurality of spliced sample features; on the basis of each spliced sample feature, calling a masked attention mechanism to perform prediction processing to obtain a predicted text, wherein the masked attention mechanism comprises: masking each independent sample in the spliced sample features; on the basis of the difference between the predicted text and a sample label, determining a loss function; and on the basis of the loss function, performing parameter update processing on the text processing model to obtain a trained text processing model.

The invention discloses an emotion prediction and disease derivation method and system based on multi-modal fusion, and the system comprises a data collection and preprocessing module, an emotion fusion module, an abnormal condition detection and cloud uploading module, and a disease possibility derivation module. The data acquisition and preprocessing module comprises a video part, a text part and an audio part, and the video part comprises face emotion recognition and prediction and human motion recognition and prediction; the text part comprises text content emotion recognition and prediction; the audio part comprises voice-to-text and voice tone emotion recognition and prediction, the system comprehensively captures an emotion state by fusing multi-mode information such as video, text and voice, and the accuracy and prediction capability of emotion recognition are improved; and by predicting the future emotion trend, the abnormal condition is warned in advance, and the response timeliness is improved.

The present disclosure relates to systems, non-transitory computer-readable media, and methods for training and implementing a vision-language model using masked distillation and contrastive image-text training. In particular, in one or more embodiments, the disclosed systems generate, utilizing a vision encoder, an image embedding from a masked digital image comprising a digital image with one or more masked patches. In some embodiments, the disclosed systems generate, utilizing a text encoder, a text embedding from a masked text phrase. In one or more embodiments, the disclosed systems generate, utilizing the vision-language model from the image embedding and the text embedding, a predicted text reconstruction of the text description and a predicted image reconstruction of the digital image. In some embodiments, the disclosed systems modify parameters of the vision-language model according to a masked distillation loss between the predicted text reconstruction and a text reconstruction generated by a pretrained large language model.

The invention discloses a speech cloning method and device based on emotion enhancement, and a related medium. The method comprises the following steps: respectively obtaining a reference audio and a prediction text corresponding to the reference audio; respectively preprocessing the reference audio and the prediction text to generate standardized audio data for feature extraction; inputting the standardized audio data into an emotion enhancement module so as to generate acoustic features matched with a target voice style through multi-round feature fusion and an autoregression generation mechanism; and inputting the acoustic features into a speech synthesis module for decoding processing, and outputting predicted speech. According to the invention, by introducing the emotion enhancement module, accurate modeling of the emotion style of the speaker in the acoustic feature generation process is realized, so that the emotion simulation degree and the personality restoration capability of the synthesized speech are significantly improved.

An automatic speech recognition (ASR) computing system and methodology are provided to predict a textual representation of received input speech data. A context acoustic biasing (CAB) engine of the ASR computing system receives historical textual content and an ontology data structure. The CAB engine matches key terms identified in the historical textual content with concepts present in the ontology data structure to generate a contextual term list data structure comprising the concept terms related to concepts matching the key terms. The CAB engine generates acoustic representations of the concept terms in the contextual term list data structure and inputs them to an ASR computer model of the ASR computing system which processes an input speech signal to generate a predicted textual representation of the input speech signal. The predicted textual representation is biased towards the acoustic representations of the concept terms in the contextual term list data structure.

The invention provides a text processing model training method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a sample text set; splicing at least two independent sample texts in the plurality of independent sample texts to obtain a plurality of spliced sample texts; calling an initialized text processing model to perform feature extraction processing based on the plurality of spliced sample texts to obtain a plurality of spliced sample features; based on each spliced sample feature, calling a mask attention mechanism to carry out prediction processing to obtain a predicted text, the mask attention mechanism comprising: respectively masking each independent sample in the spliced sample features; determining a loss function based on the difference between the predicted text and the sample tag; and performing parameter updating processing on the text processing model based on the loss function to obtain a trained text processing model. According to the method and the device, the text prediction accuracy of the text processing model obtained by training can be improved.

A text generation method and apparatus, a storage medium, a computer device, and a program product are provided. The method may include performing similarity calculation on each interactive text pair in an interactive content library to obtain at least one target interactive text pair as an annotation example, the annotation example having a corresponding transformation style; performing semantic similarity retrieval in the annotation example based on text input to obtain a preset number of target annotation examples; constructing a prompt according to the target annotation example, a target style, and the text input, and inputting the prompt into a pretrained model for performing text extension to obtain at least one piece of predicted text; and performing score calculation on the at least one piece of predicted text to determine target text.

The present disclosure relates to a text recognition method and apparatus, and an electronic device and a readable storage medium. The method comprises: processing an original image, so as to obtain at least one text wrapping image, wherein the text wrapping image only includes one line of text content; sequentially performing recognition processing on each text wrapping image, so as to obtain a first text feature vector; performing semantic processing on the first text feature vector, so as to obtain a second text feature vector; and acquiring target predicted text on the basis of the second text feature vector and the first text feature vector. The present embodiment can eliminate the problem of recognition as a single character during image recognition due to misrecognition, the left and right structures not being compact or non-left and right structures being compact, and can achieve an effect of visual and semantic complementation, thereby facilitating an increase in the accuracy of text content recognition.

Embodiments described herein provide systems, methods, and devices for generating enhanced vison-language training data. A method may include: receiving, from a communication interface, a first training dataset of image-text pairs and a second training dataset of annotated image-text pairs; fine-tuning an image-grounded text decoder and an image-grounded text encoder using the second training dataset of annotated image-text pairs; generating, by the fine-tuned image-grounded text decoder, a predicted text based on a training image from the first training dataset; generating, by the fine-tuned image-grounded text encoder, a filtering decision based on the training image and the predicted text; adding the training image and the predicted text to form a third training dataset of image-text pairs depending on the filter decision; and training a vision-language model using the third training dataset of image-text pairs.

The present application relates to a text summarization model training method, a text summarization method, an apparatus, a computer device, a storage medium, and a computer program product. The method comprises: inputting a training text and a corresponding training image set into an initial text summarization model to obtain a predicted text summary, and generating a target loss based on the difference between the predicted text summary and the labeled text summary; inputting masked training data corresponding to the training text and first training data into the initial text summarization model to obtain masked predicted data, and generating a reconstruction loss based on the difference between the masked labeled data and the masked predicted data; adjusting model parameters of the initial text summarization model based on the target loss and the reconstruction loss until convergence conditions are met, thereby obtaining a target text summarization model; and using the target text summarization model to generate a text summary of the text. This method can improve the prediction accuracy of the model and the quality of the generated text summary.

The invention relates to the technical field of neural networks, and discloses a text generation model training method and device. The method comprises the steps of obtaining a training statement set; preprocessing the training statement to obtain a target training statement; inputting the target training statement into an initial text generation model, and sequentially encoding and decoding the target training statement based on an encoder and a decoder to generate a prediction text; constructing a basic loss function based on the prediction text and the reference text; dividing the position of the prediction word in the prediction statement according to a preset pivot point to obtain a first target position and a second target position; determining a target loss function based on the first indicator function, the first coefficient, the second indicator function, the second coefficient and the probability distribution of the prediction word; and training an encoder and a decoder of the initial text generation model according to the target loss function until convergence to obtain a pre-trained text generation model.

Techniques are provided for evaluation of contrast between textual portions and background portions of an image. One method comprises identifying a textual portion in an image; automatically determining a contrast ratio threshold applicable to the textual portion based on one or more font characteristics (e.g., a font size, a font weight and / or a font type) of the textual portion; determining a contrast ratio of the textual portion based on a luminance of a background portion of the image that is adjacent to the textual portion; comparing the contrast ratio and the contrast ratio threshold; and initiating one or more automated actions based on a result of the comparison. Machine learning may be employed to predict one or more of the font characteristics of the textual portion.

The invention belongs to the technical field of computer application, and discloses a video content understanding method and device based on structured grammar information, electronic equipment and a storage medium, and the method comprises the steps: inputting a training sample into a target model for content understanding processing, obtaining a prediction text, and constructing a syntactic tree corresponding to the prediction text; calculating a syntactic tree editing distance between the syntactic tree and the syntactic tree of the reference text; calculating language structure loss by using the syntactic tree editing distance, and updating model parameters of the target model by using the language structure loss; under the condition that the model parameters of the target model are trained, obtaining a target video; and inputting the target video into the target model for processing to obtain a content text of the target video. In the application, the target model is trained based on the language structure loss calculated based on the syntax tree, and the target video can be understood, so that the content text with accurate grammar and reasonable and natural sentence structure is obtained.

The invention relates to the field of artificial intelligence, and particularly provides a contract risk auditing method and device, and the method comprises the following steps: S1, splitting a contract content paragraph, and decomposing a contract text into a plurality of independent paragraph units with a logic relation; s2, converting the contract text into a structured data unit, and performing text analysis and risk factor extraction; s3, table textualization: converting table data in the contract into a plain text format which can be processed by a large model; s4, constructing a list table to systematically organize key information in the contract; s5, performing text semantic analysis to deeply understand the contract text; s6, element checking: carefully reviewing and verifying key elements in the contract text; and S7, risk information summarization: summarizing and analyzing potential risks in the contract text. Compared with the prior art, the method has the advantages that potential risks in the text can be recognized and predicted through learning of a large amount of text data, and therefore the efficiency and accuracy of contract risk auditing are remarkably improved.

The invention discloses a data generation method based on a multi-modal large language model, and the method comprises the steps: obtaining inquiry text information used for representing a business task in a business application scene, and image information associated with the business task, the inquiry text information comprises at least one of task definition information used for representing a service task needing to be completed and task logic information used for representing service logic, reasoning the obtained inquiry text information and the image information based on the trained multi-mode large language model, and obtaining the inquiry text information and the image information. Generating prediction text information used for representing response information of the inquiry text information based on the image information, the prediction text information comprises at least one of entity information used for representing a target image in the image information and image position information where an entity is located, attribute information used for representing additional information of the entity, and rule information used for representing a rule disassembled based on task logic. According to the invention, the generated data has pyramid dimension information.

Embodiments of the present disclosure provide a method, an apparatus and an electronic device for determining a word representation vector, and a computer-readable storage medium, which belong to a field of processing natural languages. The method includes obtaining a set of glyph units of a text; obtaining a context vector of the text based on the set of glyph units; and predicting next word of the text based on the context vector. The method for determining the word representation vector of the present disclosure can effectively obtain a corresponding set of glyph units even for hieroglyphics in which hyperbolic characters are prone to appear or languages evolved from the hieroglyphics, thereby improving an accuracy of determining the word representation vector.

Method, software, and apparatus for improved Augmentative and Alternative Communication (AAC) solutions. In one aspect, a user interface is provided with a set of suggestions comprising text, phrases, etc., and navigation buttons that enable users to select words and phrases to add to be written and / or spoken in a manner that reduces the number of user inputs. The suggestions are displayed in alphabetical order in rows with navigation buttons adjacent to the rows, with activation of a navigation button resulting in generation of updated suggestions having alphabetical ranges that are bounded by suggestions in associated rows. This approach may be combined with predictive text means to enable users to easily formulate text and / or speech content.

The present disclosure relates to a detection model training method and apparatus, and a text bounding box detection method and apparatus. The training method comprises: inputting into a detection model to be trained a sample image carrying a text label, wherein the text label comprises a reference text bounding box and a reference probability value of a preset deletion symbol being drawn on text within the reference text bounding box; performing detection on the sample image by means of the detection model, so as to determine a text detection result of the sample image, wherein the text detection result comprises a predicted text bounding box and a predicted probability value of the preset deletion symbol being drawn on text in the predicted text bounding box; and on the basis of a target loss function, converging the text detection result and the text label, so as to obtain a trained detection model, wherein the target loss function comprises a first loss function used for evaluating the accuracy of the predicted text bounding box, and when the overlap ratio between the predicted text bounding box and the reference text bounding box is in different overlap ratio intervals, the first loss function is configured with penalty terms of different weights.

The invention discloses a handwritten text recognition method and device, equipment and a storage medium, and belongs to the field of text recognition. The method comprises the following steps: acquiring a handwritten text image; extracting handwriting style characteristics according to the handwritten text image, wherein the handwriting style characteristics are used for reflecting a writing style corresponding to the handwritten text image; calibrating a feature extraction position of the handwritten text image according to the handwritten style feature, and extracting a text feature of the handwritten text image according to the calibrated feature extraction position, the text feature being used for reflecting a text in the handwritten text image; and predicting a prediction text corresponding to the handwritten text image according to the text features. According to the method, the accuracy of extracting the text features of the handwritten text image can be improved, so that the recognition performance of handwritten texts of different writing styles is improved.

Methods and systems for improving communication involving a personal with aphasia are disclosed. The methods and systems include: obtaining an audio input indicative of speech of the person with aphasia; providing the audio input to a personalized aphasia translation assistant, wherein the personalized aphasia translation assistant was trained to recognize and translate speech of the person with aphasia using a general dataset of aphasia-speech; determining a plurality of words from the audio input using an aphasia-specific recognition model; inputting the plurality of words into an aphasia generative model, the aphasia generative model comprising a natural language processing machine learning model trained using a general dataset of aphasia sentences and a corresponding dataset of translated sentences; generating one or more formulated and contextual sentences using the personalized aphasia generative assistant; and outputting the one or more formulated and contextual sentences. A further method provides the training of a personalized aphasia communication assistant, in particular the adaptation of a pre-trained speech recognition model and of a pre-trained generative speech model based on predicted text and a user confirmation feedback of the accuracy of the predicted text.

A system includes a memory and processors operably coupled to the memory and configured to receive a request for a software code change to one or more of a first instance of a software application or a plurality of second instances of a software application. The first instance of the software application is represented as a first node of a directed acyclic graph (DAG) and each instance of the plurality of second instances of the software application is represented as one of a plurality of second nodes of the DAG. The processors are further configured to identify relationships between each node impacted by the requested software code change. The processors are further configured to execute a first machine-learning model and a second machine-learning model to generate a prediction of textual software code based on a knowledge graph. The textual software code is to be deployed for updating each node.

The invention relates to a voice recognition method and device, electronic equipment, a storage medium and a program product. The method may comprise the following steps: acquiring a to-be-recognized voice, the to-be-recognized voice comprising a wake-up voice and a target voice; the to-be-recognized voice is input into a pre-trained voice recognition model to obtain a prediction text, the prediction text is a text used for representing voice content of a target user in the target voice, and the target user is a speaker waking up the voice; wherein the speech recognition model comprises a speech encoder, and the speech encoder is used for obtaining a first feature vector comprising semantic features and speaker features according to the speech to be recognized so as to determine a prediction text. Therefore, in a noisy scene such as multiple speakers, the voice content of the target user in the target voice can be accurately recognized. In addition, the voice encoder is subjected to self-supervised training by using single-person voice, so that the dependence on annotated data can be effectively reduced, and the generalization ability and adaptability of the model are enhanced.

A method performed by an electronic device using artificial intelligence according to an embodiment of the present disclosure, the method includes receiving a speech signal; and generating a text corresponding to the speech signal by using the speech signal as input in a pre-trained first artificial intelligence algorithm model, wherein the first artificial intelligence algorithm model including a first model parameter outputs a first predicted text by using a synthetic speech and a reference text as input, extracts a first loss based on the first predicted text and the reference text, and performs a first pre-training based on the first loss, wherein the first artificial intelligence algorithm model that performed the first pre-training includes a second model parameter, wherein the first artificial intelligence algorithm model that performed the first pre-training outputs a second predicted text by using the synthetic speech and the reference text as input, and extracts a second loss based on the second predicted text and the reference text, wherein the electronic device determines a loss rate which is a ratio of the first loss and the second loss, determines an adaptation parameter based on the second model parameter and the second loss if the loss rate is below a threshold value, and determines a third model parameter based on the adaptation parameter and the second model parameter, wherein the first artificial intelligence algorithm model is repeatedly pre-trained such that the first artificial intelligence algorithm model that performed a second pre-training is configured to include the third model parameter.

The invention discloses an audio content generation method, a related device, equipment and a storage medium, and the audio content generation method comprises the steps: obtaining to-be-synthesized text content; synthesizing a content audio of the text content, and predicting a text fragment needing a sound effect and a first description text needing the sound effect in the text content; generating sound effect audio conforming to the first description text; and combining the audio effect audio at the audio position corresponding to the text segment in the content audio to obtain the audio content. According to the scheme, automatic generation of the audio content can be realized, and the requirements of diversity of sound effects and multi-event complex sound effects are met.

The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating and implementing a vision-language model that identifies and understands text-rich content depicted in digital images. For example, the disclosed systems determine, from among a plurality of digital images with at least a threshold probability of depicting text-rich content, a subset of digital images corresponding to a set of text-rich image classifications. In some embodiments, the disclosed systems generate a ground truth text phrase utilizing an optical character recognition model to process a digital image from the subset of digital images. In certain embodiments, the disclosed systems also generate a predicted text phrase utilizing a vision-language model and compare the ground truth text phrase with the predicted text phrase. In some embodiments, the disclosed systems modify parameters of the vision-language model based on comparing the ground truth text phrase and the predicted text phrase.

Systems and methods generate clinical documentation using large language models and artificial intelligence (AI). A template management module is provided to create customizable templates. A processing unit can receive input data from various sources and use AI to generate transcripts, summarize sessions, and produce clinical documentation such as clinical notes. The processing unit may also generate Current Procedural Terminology (CPT) and diagnosis codes, generate after-visit summaries, and generate referral letters. The AI may be trained on past clinical notes and can adapt to the clinician's style over time, with a feedback loop for continuous improvement. Additional features include cohort-based training, real-time language translation, predictive text, and analytics for documentation trends. The system supports customization of note length, style, and keywords, as well as integration with external medical databases and patient portals.

Various embodiments of the present disclosure provide machine learning architectures and data processing techniques for improving computer-based text comprehension. The techniques include generating, using a trained classifier model, target classification probabilities for labelled text-based objects from a testing portion of a labelled training dataset and identifying predictive text-based objects from the labelled text-based objects based on the target classification probabilities. The techniques include applying a staged prompting mechanism with a generative extraction model to identify a target set of explanatory text segments from the predictive text-based objects that may be clustered into semantic segment clusters. The techniques include generating explanatory summary segments respectively corresponding to the semantic segment clusters and generating a target classification signature based on a plurality of terms from the one or more explanatory summary segments.