470 results about "Text string" patented technology

Approaches presented herein provide for the generation of a text-based representation of an environment. In particular, a large language model (LLM) can be used to generate a tokenized text string representation of an environment using information such as the semantics, topology, and geometry of the environment. A language model-generated representation can comply with real-world rules and constructs, and can account for omissions or errors in the input data based upon known relationships and semantics for various objects in the environment. Such representations can be used to generate reconstructions of existing environments, correct or augment previously-constructed representations, or generate representations of new but realistic environments that comply with real-world rules. A text-based representation can comprise a one-dimensional string of tokens, which can encapsulate the important spatial information and semantics of an environment.

Approaches presented herein provide for the ability to process, store, index, and search geospatial information such as maps with flexible granularity. A set of observations, such as may include sensor data captured for a region of an environment, can be fed as input to a language model. The language model can generate a tokenized description of the region, as may include a text string of tokens encapsulating semantics, topology, geometry, and / or other aspects of the region. A feature vector or embeddings for the region can be generated based on the tokenized description, and a similarity search performed against a vector database, for example, to identify similar feature vectors corresponding to similar regions or domains. Labels or other information associated with these similar feature vectors can be automatically applied to the example region. Clustering of feature vectors or other embeddings can also be performed based in part on the similarity.

Systems and methods for attribute recognition can include obtaining an image and a text string. The text string can be processed with a language model to generate a set of candidate attributes based on sequence based prediction. The image and the candidate attributes can be processed with an image-text model to determine a likelihood that the respective candidate attribute is depicted in the image. The likelihood determination can then be utilized to determine a predicted attribute for the object of interest.

The present disclosure relates to systems and methods for automatic generation of summaries for record objects using one or more large language models. The system can identify a plurality of electronic activities matched to a record object of a customer relationship management system. The system can generate one or more text strings from the plurality of electronic activities using the large language models. The system can generate a first set of topics by inputting a first set of text strings into the large language models. The system can generate a second set of topics by inputting a first subset of text strings of the first set of text strings into the large language models. The system can transmit one or more topics to a computing device for presentation.

A method for training a text generation machine learning model for prompt generation includes receiving a plurality of training text strings; executing a text generation machine learning model using each of the plurality of training text strings to generate a plurality of training generated text strings, each of the plurality of generated text strings corresponding to generating a content item; executing a content scoring machine learning model using each of the plurality of generated text strings to generate a text performance score for each of the plurality of training generated text strings; for each of the plurality of generated text strings, adjusting one or more weights or parameters of the text generation machine learning model proportional to the text performance score for the generated text string.

The present disclosure relates to systems and methods for automatic generation of datasets for record objects using one or more large language models. A system can identify a plurality of electronic activities. The system can generate, using one or more large language models, a first set of text strings from the electronic activities. The system can store, in one or more data structures, a first association between the first set of text strings and the record object. The system can identify a second electronic activity. The system can generate, using the one or more large language models, a second set of text strings based on data corresponding to the second electronic activity and the first set of text strings. The system can store, in the one or more data structures, a second association between the second set of text strings and the record object.

A mobile electronic device includes a network interface and one or more processors coupled to memory. The one or more processors can be configured to receive a message comprising transaction data regarding a transaction and a request regarding activating a chat application stored in the memory; the chat application, wherein the chat application is configured to execute a large language model using the transaction data and account data as input to generate a first string of text requesting further data regarding the transaction; present the first string of text at a chat interface of the chat application; receive additional transaction data; execute the large language model using the additional transaction data as input to generate a second string of text indicating storage of the additional data in a record; and present the second string of text at the chat interface.

Implementations utilize a smaller LLM to generate content responsive to a user query and cause a portion of the generated content to be rendered as an immediate response to the user query. Implementations further utilize a larger LLM to generate content that starts with the portion of the generated content and that includes a refined portion succeeding the portion of the generated content. The refined portion can be rendered succeeding the portion of the generated content. In some implementations, instead of using the smaller LLM, alternatively, the portion of the generated content rendered as the immediate response can be generated based on a default text string or a template, where the template can be determined / selected from a plurality of predefined templates based on a natural language understanding of the user query.

The present disclosure relates to systems and methods for automatic generation of summaries for record objects using one or more large language models. The system can identify a plurality of electronic activities matched to a record object of a customer relationship management system. The system can generate one or more text strings from the plurality of electronic activities using the large language models. The system can generate a first set of topics by inputting a first set of text strings into the large language models. The system can generate a second set of topics by inputting a first subset of text strings of the first set of text strings into the large language models. The system can transmit one or more topics to a computing device for presentation.

An exemplary method for reducing bias in a training image dataset for training a machine-learning model comprises: receiving a plurality of text strings comprising at least one text string describing each image in the training image dataset; generating a plurality of embeddings based on the plurality of text strings; identifying, based on the plurality of embeddings, a plurality of visual features in the training image dataset; identifying one or more correlations between the plurality of visual features in the training image dataset; receiving a user input identifying at least one biased correlation from the one or more correlations; and training the machine-learning model at least partially by adjusting one or more data sampling weights associated with one or more training images in the training image dataset based on the user input.

The approaches presented here enable the generation of a text-based representation of an environment. In particular, a large language model (LLM) can be used to generate a tokenized text string representation of an environment using information such as the environment's semantics, topology, and geometry. A representation generated by a language model can conform to real-world rules and constructs and can account for omissions or errors in the input data based on known relationships and semantics for different objects in the environment. Such representations can be used to create reconstructions of existing environments, to correct or augment previously created representations, or to create representations of new but realistic environments that conform to real-world rules.A text-based representation comprises a one-dimensional chain of tokens that encapsulates the important spatial information and semantics of an environment.

Approaches presented herein provide for the automated, end-to-end generation of map data based at least in part on sensor data captured for an environment. At least one language model can be used to generate a text-based, tokenized description of the environment that includes semantics, topology, geometry, and / or other information for the environment. A generation pipeline can use one or more language models in one or more stages, and the data passed between stages can be in a determined tokenized representation format, as may correspond to a tokenized text string in a specific structured language.

Generating responses to queries with text extracts from unstructured data using AI models includes (i) extracting text from unstructured data sources to create machine-searchable documents, (ii) replacing PII and PHI with entity types and attributes, (iii) determining text extracts that indicate criteria, (iv) using a small-scale ML model to perform text searches and find conceptually associated text strings, (v) generating a custom context for a large language model (LLM), (vi) prompting the LLM to generate a response, (vii) combining the response with an extractive QA model to obtain relevant text extracts as response basis, and (viii) providing system-generated recommendations for next best actions based on responses that produce the most optimal outcomes in historical input documents for manually selected or automatically recommended resolution paths.

A method for training a text generation machine learning model for prompt generation includes receiving a plurality of training text strings; executing a text generation machine learning model using each of the plurality of training text strings to generate a plurality of training generated text strings, each of the plurality of generated text strings corresponding to generating a content item; executing a content scoring machine learning model using each of the plurality of generated text strings to generate a text performance score for each of the plurality of training generated text strings; for each of the plurality of generated text strings, adjusting one or more weights or parameters of the text generation machine learning model proportional to the text performance score for the generated text string.

An example system includes: a first large language model; a memory storing instructions and one or more processors operable to execute the instruction to: receive a natural language text string from a client device, where the natural language text string comprises a formal rule expressed in natural language; input the natural language text string and a control string into a large language model (LLM), where the control string is configured to cause the LLM to generate a formal expression representing the formal rule of the natural language text string; output, by the large language model, the formal expression to an output device; and evaluate a consistency of the formal expression using a test input.

Methods and systems of displaying substring pairs where visual characteristics delineate adjacent substring pairs from each other, specifically in the case of at least one of the primary text string and the secondary text string, the placement of the first substring alternates position on an electronic display above and below the second substring. The method may comprise receiving a plurality of the primary substrings, a plurality of the secondary substrings, and a plurality of visual characteristics, displaying, on an electronic display, the primary substrings and the secondary substrings arranged into substring pairs, and one of the visual characteristics in each of the correspondence areas. Additional desired visual effects may be achieved through the use of specific demarcations, demarcation placements, and substring modifications.

In one example, a method being performed by a computer system comprises: receiving an image file containing a pathology report; performing an image recognition operation on the image file to extract input text strings; detecting, using a natural language processing (NLP) model, entities from the input text strings, each entity including a label and a value; extracting, using the NLP model, the values of the entities from the input text strings; converting, based on a mapping table that maps entities and values to pre-determined terminologies, the values of at least some of the entities to the corresponding pre-determined terminologies; and generating a post-processed pathology report including the entities detected from the input text strings and the corresponding pre-determined terminologies.

Systems and methods for multimodal query suggestion can include obtaining image data, determining text strings associated with the image data, and providing the text strings as selectable options for performing a multimodal query with the image data. The text strings can be determined based on performing object detection and classification on the image data. The object classifications can then be leveraged for determining potential text queries a user may select for obtaining additional information about the classified object.

An electronic device associated with a media-providing service stores, in a vector space, a plurality of respective vector representations for respective media content items. The electronic device receives a user input, including a text string. The electronic device generates, using a neural network, a structured query based on the text string. The electronic device determines, based on the structured query, whether to generate a vector representation of a portion of the text string. When the electronic device determines to generate the vector representation of the portion of the text string, it generates the vector representation of the portion of the text string, wherein the vector representation is embedded in the vector space, and identifies a set of media items using the vector representation of the portion of the text string. And the electronic device provides one or more select media items from the set of media items to a user.

One example method includes receiving a text string that includes multiple words, tokenizing the text string to create a tokenized text string, substituting each token in the tokenized text string with a mask token to create a masked text string, performing an inference process on the masked text string to obtain a respective probability for each token, determining a respective suspicion level for each probability, modulating the suspicion levels to obtain a respective weighted suspicion score for each token, and comparing each of the weighted suspicion scores with a threshold to determine whether any one or more of the words indicate that the text string includes an attack prompt.

The invention discloses a character recognition method and system based on a large model and an OCR technology, and relates to the technical field of character recognition, and the method comprises the steps: extracting picture information, carrying out the unified preprocessing, generating a text detection box of a character region through a DBNet lightweight text detection model, and obtaining a text position; quickly identifying characters in the textbox by using a lightweight OCR model to obtain text content, and generating an identification information group; carrying out average value calculation on the confidence coefficient of the lightweight OCR model result, and analyzing the overall confidence coefficient; and for the result with low confidence coefficient, inputting the corresponding identification information group into the multi-modal large model, and carrying out secondary identification. According to the method, the text position set and the text character string sequence are combined into the identification information group, so that the effect of structured storage of detection and identification results is achieved, subsequent information retrieval and multi-modal fusion analysis are facilitated, and the effect of optimizing the subsequent processing efficiency and precision is achieved through the combination of the confidence coefficient screening step.

A method for saving prompts on a page of a workspace includes receiving a first input that instantiates a prompt block configured to initiate a generative process to create in-block content. The prompt block is embedded on a first page of a workspace configured to include multiple pages. The first input includes a string of text. The string of text includes instructions that cause a generative artificial intelligence (AI) system to create the in-block content to be displayed on the page. The method includes receiving a second input on the prompt block. In response to the second input, the method includes saving the string of text as a particular prompt. The particular prompt is accessible from the multiple pages of the workspace and the particular prompt is configured to be shared with users of the workspace.

In the disclosed systems and methods for categorizing medical data, a computer system obtains, in electronic form, a plurality of medical records. Each medical record includes corresponding medical data from a respective medical evaluation and corresponding metadata comprising a plurality of attributes about the respective medical evaluation. Each respective attribute comprises a corresponding string of text. The computer system determines, for each respective pair of medical records consisting of a first medical record and a second medical record, a corresponding pairwise similarity between, for each respective attribute in a set of attributes, the corresponding string of text for the first medical record and the corresponding string of text for the second medical record. The computer system identifies a first subset of the plurality of medical records. Each respective medical record in the first subset is connected to each other through pairwise similarities that each satisfies a similarity threshold.

In some aspects, the techniques described herein relate to a method including: receiving, at a query platform, a query text string; tokenizing, by the query platform, the query text string, wherein the tokenizing generates a query vector embedding; determining, by the query platform, a document vector embedding, wherein the document vector embedding is above a similarity threshold with respect to the query vector embedding; retrieving, by the query platform, textual document data related to the document vector embedding; sending, by the query platform, the query text string and the textual document data to a generative model engine; receiving, by the query platform and from the generative model engine, a natural language response to the query text string; and displaying, by the query platform, the natural language response via an interface.

An electronic message content intercepting system has a virtual keyboard installed by an operating system of a supervised mobile communication device which is configured to process keypresses for software applications executed by the supervised mobile communication device. The system is configured to analyse message text input via the keyboard to identify categorised text strings which may be categorised as inappropriate, offensive, abusive and / or the like. Responsive to the disapproval input the system does not process input of the categorised text string so that the categorised text string is not transmitted to a recipient mobile communication device. However, responsive to the approval input, the system is configured to process input of the categorised text string so that the categorised text string is transmitted to the recipient mobile communication device and the text string is also transmitted to the supervisory mobile communication device for display as an alert.

Methods and systems for scalable dataset content embedding for improved searchability. For example, the system may retrieve a first dataset from a first data source. The system may generate a first data profile of the first dataset. The system may generate a latent index of the first data profile based on processing the first data profile using a first embedding algorithm. The system may receive, via a user interface, a first request for a first text string. The system may generate an embedded request corresponding to the first request based on processing the first text string using the first embedding algorithm. The system may process the embedded request using the latent index. The system may generate for display, in the user interface, a result based on processing the embedded request using the latent index.

Provided is a system and method for controlling a plurality of devices. The method includes generating a command script by processing a text string with at least one model, the text string including a natural language input by a user, modifying the command script based on contextual data, the command script including a configuration for at least one device, generating at least one command signal based on the command script, and controlling at least one device based on the at least one command signal.

Devices and techniques are generally described for privacy preservation for computer vision models. In some examples, a first field of text and a second field of text may be detected in a first image. A first alpha-numeric text string may be detected in the first field and a second alpha-numeric text string may be detected in the second field. A first sub-image including the first alpha-numeric text string may be generated and a second sub-image including the second alpha-numeric text string may be generated. The first sub-image may be sent to a first computing device for annotation and the second sub-image may be sent to a second computing device for annotation.

Systems and methods recite a system that expands the available amount of data that may be used for training and / or detecting cyber fraud. In particular, as opposed to limiting training data (and / or successful matches) to patterns of text strings in electronic communications of user records, the systems and methods additionally generate training data (and / or successful matches) on the characteristics of the text strings themselves (e.g., the specific characters used, the length, the uniqueness of the text string, etc.). Moreover, the systems and methods may determine particular rules that an identified text string and / or characteristics thereof violates. The system may then use instances of the identified text string, characteristics thereof, and / or violated rule to supplement existing training data. Thus, the systems and methods mitigate the technical problem related to the limited training data.

A computer-based system and method provides feedback to a student in response to a student text for a provided lesson. An evaluation request including student text response to a lesson passage, a writing prompt, a student identifier, and a lesson identifier is received for evaluation of the student text response. An evaluation rubric is selected from rubrics indexed by the student grade level, student the lesson objective, and / or the lesson identifier. An evaluation data structure corresponding to the request for evaluation is initialized. A large language model (LLM) prompt is formulated based on the evaluation request and the evaluation rubric and provided to an LLM. The evaluation data structure is updated with the response from the LLM and converted to feedback text strings which are presented to the student in the context of the student text response.