132results about "Document management systems" patented technology

A system may determine environmental, social, and governance (ESG) goal data for an ESG clause type and determine that a first clause of a first electronic document of a plurality of electronic documents and that a second clause of a second electronic document of the plurality of electronic documents correspond to the ESG clause type. The system may determine first ESG commitment data based on content of the first clause of the first electronic document and determine second ESG commitment data based on content of the second clause of the second electronic document. The system may generate ESG metric data based on the first ESG commitment data and the second ESG commitment data and generate dashboard data based on the ESG metric data. The system may output the dashboard data.

The application provides a document quality governance method and device based on a large language model, and relates to the technical field of natural language processing and document intelligent processing technology.The application realizes the unity of computing efficiency and governance accuracy through the cooperation of a two-stage pre-screening mechanism including coarse screening and fine screening and an adaptive context learning strategy.Firstly, the coarse screening stage uses lightweight calculation to quickly filter out high-quality text slices in most text slices, thereby significantly reducing the overall computing overhead and response time.Then, the fine screening stage accurately locates and classifies a small amount of text slices to be optimized, thereby providing clear guidance for subsequent accurate rewriting.Finally, based on the error labels output by the fine screening, adaptive context learning optimization can match the most relevant examples from a dynamic example library, thereby constructing highly targeted adaptive prompts to guide the large language model to perform efficient and accurate optimization and rewriting, thereby generating optimized text slices.

A screen reader application traverses each node in a document object model (DOM) for the text stylization. Properties for foreground color, background color, font type, font size and font stylization are algorithmically reduced to an identifier. Each node in the DOM with the same identifier has the same text stylization. Unique and infrequent text stylizations by a webpage author signal a point of interest. The screen reader application locates and navigates to that node in the DOM on behalf or in response to the end user. Points of interest are further identified by a number of additional factors. A first includes percentage of text of having the text stylization versus total text in the DOM. A second includes excluding candidate point of interest nodes having more than 250 characters. Others include imposing minimum font sizes and text contrast ratios to qualify as a point of interest.

A system includes a processor configured to receive, from a registrant device, an upload of at least one document such as incapacity or end-of-life documents. The system stores the at least one document and receives access selections designating each of (i) contact and demographic information of one or more designated individuals and (ii) one or more types of entities permitted to request access to the at least one document as permitted entity types. The system receives an access request identifying a registrant for whom the at least one document is sought and verifies that the requester is a designated individual or associated with one of the permitted entity types. The system provides, to the requester device, access to the at least one document.

Disclosed are a method and apparatus for determining a given template of a form used by a filled in instance of that type of form from amongst a great number of form templates (a hundred or more). The given instance is evaluated by a neural network that has been trained by a single example of each template in order to reduce the total number of templates down to a manageable amount. Given a list of closest matching templates, the instance is aligned to each of the closest matching templates. The comparison generates a match score. The form template having the greatest match score is the correct form template. Filtering the instance through a one-shot learning neural network before performing a precise comparison enables the process to scale to any number of template forms.

A comparative editing workflow streamlines drafting by leveraging structured datapoints extracted from multiple matters. After generating normalized values and citations for a current and a prior document set, the system may display the datapoints side by side so differences are apparent. When a user clicks a datapoint in the current matter, a drop down list of candidate values may be dynamically populated from the prior matter and allowable categories; the user may select one of these values or enter a custom value. The platform may locate all instances of the datapoint in the current documents using stored citations and automatically replace them with the chosen value, update the structured record, reextract dependent fields where necessary and preserve version histories. The updated document and datapoints may then be presented for review.

Systems and methods include interpreting a first user input from a first user, the first user input comprising a text flow entry, interpreting a second user input from the first user, the second user input comprising at least one of: an in-line data access entry or a table-based calculation entry, positioning a text entry value on a unified document surface in response to the first user input, creating at least one data structure in response to the second user input, the at least one data structure comprising data from an external data source, the external data source being external to the unified document surface, and positioning the at least one data structure on the unified document surface.

One or more embodiments of a document organization system quickly and conveniently provide digital documents to a user on a client device based on a physical object. In particular, the document organization system can receive an image of a physical document and an identifier from a first client device, identify digital documents that match the physical document, and provide the matching digital documents to a second client device, which displays the identifier. In another embodiment, the document organization system allows a user to bind digital documents to a physical object and later recall the digital documents using the physical object. In addition, the document organization system can store and recall the layout arrangement of digital documents on a client device when binding and recalling the digital documents to the physical object.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for table detection using text streams. One of the methods includes detecting, in a text stream and using column identification data, text for one or more cells in a table; creating, using the text for at least some of the one or more cells in the table, a data structure for the cell a) that associates two or more values from the table and b) for use by a downstream system as part of a natural language analysis process of data from the text stream; and storing, in memory, the data structure.

A target IP search method for a target item according to one embodiment is performed by a computer device. The target IP search method for the target item includes the steps of: obtaining a designating query for the target item; and, based on the query, searching for a plurality of target IPs used in at least one of the research, development and production of the target item. Here, the plurality of target IPs include IP relating to each of at least two components of the components of the target item and / or IP relating to the combined technology of the at least two components used for the performance, operation, production and use of the target item.

A system and method for end-to-end transaction management, for example, for a structured finance market. The system and method digitizes and deconstructs complex interconnected transaction documents. The system creates transparency around the complexities of the transactions, generating significant efficiencies for existing market participants and enabling access to previously hidden and / or inaccessible data. In some embodiments, the platform supports a selected ecosystem (compared to specific use-cases within a market vertical) with a seamless integration of frameworks and schemas for the organization and structure of provisions, analytical tools extracting the required data, and the creation of metrics to informatively assess and calibrate the market. The system advantageously creates a digital language providing a tool, which will further enable the digitization of the finance ecosystem.

A change in documents and search results based on a search query are checked efficiently. A method for outputting a document search result includes a step of specifying at least one document to be searched, a step of searching the at least one document using a search query including at least one keyword, a step of displaying a search result on a screen, and a step of displaying a sentence on the screen. The at least one document includes a plurality of versions. In the step of displaying a search result on a screen, a keyword shown up in each of versions of the document is displayed together with information specifying the version where the keyword is shown up. The sentence is included in the version of the document selected from the search result displayed on the screen.

A method includes discarding a current knowledge corpus; selecting a new knowledge corpus; performing operations as follows using an Artificial Intelligence (AI) retriever engine: dividing the new knowledge corpus into a plurality of sub-documents; encoding a query for the plurality of sub-documents using a query encoding model; encoding each of the plurality of sub-documents using a document encoding model; and determining at least one matching sub-document of the plurality of sub-documents that is a match for containing an answer to the query based on the encoded query and each of the plurality of encoded sub-documents; performing operations as follows using an AI reader engine: generating an inference about the answer to the query based on a concatenation of each of the at least one matching sub-document with the query, each of the at least one matching sub-document having an associated reader loss function result for the inference; identifying one of the at least one matching sub-document having a lowest reader loss function result; and associating the identified one of the at least one matching sub-document with a truth label for the query.

Systems and methods for providing a Spatially Partitioned Ideally Chunked Entity (“SPICE”) tree data structure are provided herein. In an example, a computerized method for using a SPICE tree includes determining a document defined by a SPICE tree data structure and navigating to content within the document based on the SPICE tree data structure. The SPICE tree data structure includes a root chunk containing radar nodes and a plurality of chunks. Each chunk includes one or more object nodes, each of which corresponds to a document attribute. Each of the radar nodes includes a reference to one of the chunks and the object nodes include a placeholder node that provides a reference to another chunk based on a position of the placeholder node within the respective chunk. The root chunk and the chunks are arranged in a hierarchical arrangement with the root chunk being a parent to the chunks.

A machine-learning based (ML-based) system and method for automatically extracting one or more data fields from one or more documents, are disclosed. The ML-based system includes a document obtaining subsystem to obtain documents, a document pre-processing subsystem to generate pre-processed data, a field identifying subsystem to identify data fields using a trained ML model, and a field extracting subsystem to extract financial information. The ML-based system also comprises an output subsystem to deliver the extracted data to end users via user interfaces. The ML model is trained using historical documents, labelled data fields, and features such as distance-based features, direction-based features, dimension-based features, positional features, and value-based features. The M-based system employs hyperparameter optimization, noise removal, and accuracy assessment mechanisms to enhance performance. This ML-based system provides a scalable, accurate, and automated solution for financial information extraction, ensuring efficiency, adaptability, and seamless integration with enterprise systems.

This invention relates to the field of digital archives management technology, specifically to an artificial intelligence-based system for analyzing and warning of abnormal archive behavior. The invention uses a graph construction module to transform archive access logs into a relational topology graph; an attribute propagation module performs weighted transfer and accumulation of weights based on a graph traversal algorithm to calculate the cumulative relational index value of nodes; a connectivity retrieval module retrieves cross-regional links based on partition isolation rules; and an early warning output module generates early warning signals based on index values ​​and link status. This invention utilizes the flow mechanism of feature values ​​in a graph structure to aggregate minute risky behaviors within discrete long-term windows, accurately identifying complex abnormal patterns where a single operation may not violate regulations but the long-term cumulative risk exceeds the limit. This solves the problem that existing static statistical rules are unable to detect hidden logical violations, effectively reducing false alarms and false negatives.

It is difficult for users to quickly find the documents they want. [Solution] The information processing system disclosed herein comprises a storage unit for storing document data, a reception unit for receiving search keywords entered on a search screen displayed on a user terminal, and a search unit for displaying search results obtained by searching document data based on the search keywords on the search screen. The storage unit stores document data associated with complementary keywords, the reception unit displays complementary keywords associated with the received search keywords on the search screen so that the user can select them, and accepts the selected complementary keywords, and the search unit searches document data based on the accepted complementary keywords.

A system for retrieval of images using Retrieval Augmented Generation (RAG) including a tagging engine and a vector engine. The tagging engine is configured to receive an electronic document having an image, determine a location of the image in the electronic document, generate an image localization tag (ILT) based on the location of the image, and replace the image in the electronic document with the ILT to produce a modified electronic document. The vector engine is configured to vectorize and store the modified electronic document in a vector database for subsequent search and retrieval using RAG.

In various examples, a technique for generating a hierarchical representation of a document includes generating, via a first machine learning model, a hierarchical structure associated with a document, wherein the hierarchical structure includes one or more headings and one or more paragraphs. The technique also includes identifying, via the first machine learning model, heading text included in the document and associated with each of the one or more headings and paragraph text included in the document and associated with each of the one or more paragraphs. The technique further includes generating, via a second machine learning model and based at least on the identified heading text included in the document, a formatted listing including the heading text associated with each of the one or more headings and generating a hierarchical document based at least on the formatted listing and the paragraph text associated with the one or more paragraphs.

Methods, systems, and computer-readable storage media for receiving a scenario service request for a scenario of an application, determining a scenario flowchain represented in the scenario service request, retrieving a scenario flowchain configuration of the scenario flowchain from a database, the scenario flowchain configuration including a data object that defines a set of steps that are to be executed in an order, each step being associated with a step type and a set of parameters, executing steps in the set of steps, where at least one step is executed to prompt a large language model (LLM), and returning a result to the application, the result comprising a response from the LLM that is responsive to the prompt.

A system and computer implemented method of patent mapping are provided. The method comprises maintaining a database of patent portfolios and a database of patents, each patent stored in the database of patents associated with one or more patent portfolios stored in the database of patent portfolios; maintaining a database of ontologies, the ontologies including one or more patent concepts in defined groups; receiving a search query associated with a first patent portfolio; searching the first portfolio as a function of the search query; generating search results, the search results including one or more patent claims associated with the search query; and mapping the one or more patent claims to a patent concept in a defined group.

The application relates to the technical field of file data storage management, in particular to a file data storage management method and system based on cloud computing, which comprises the following steps: acquiring file data sets generated in different implementation stages of a project, generating a stage sequence identifier, a data type identifier and a source node identifier for each file data record, and obtaining a file identifier data set; sorting the stage sequence identifiers to construct a stage continuous sequence; mapping the file identifier data set and the stage continuous sequence to obtain a stage-type distribution matrix; calculating the file data structure completeness according to the stage-type distribution matrix; judging the structure completeness to obtain a project structure state identifier; and selecting different storage strategies according to different project structure state identifiers. The application realizes storage strategy switching driven by file data structure completeness, and improves the orderliness and reliability of file data storage management.

A document management system can include an artificial intelligence-based document manager that can perform one or more predictive operations based on characteristics of a user, a document, a user account, or historical document activity. For instance, the document management system can apply a machine-learning model to determine how long an expiring agreement document is likely to take to renegotiate and can prompt a user to begin the renegotiation process in advance. The document management system can detect a change to language in a particular clause type and can prompt a user to update other documents that include the clause type to include the change. The document management system can determine a type of a document being worked on and can identify one or more actions that a corresponding user may want to take using a machine-learning model trained on similar documents and similar users.

Systems and methods for analyzing documents are provided herein. A plurality of documents and user input are received via a computing device. The user input includes hard coding of a subset of the plurality of documents, based on an identified subject or category. Instructions stored in memory are executed by a processor to generate an initial control set, analyze the initial control set to determine at least one seed set parameter, automatically code a first portion of the plurality of documents based on the initial control set and the seed set parameter associated with the identified subject or category, analyze the first portion of the plurality of documents by applying an adaptive identification cycle, and retrieve a second portion of the plurality of documents based on a result of the application of the adaptive identification cycle test on the first portion of the plurality of documents.

A system and method to identify a document including text relating to a merchant system. The document is segmented into a set of sentences. A first machine-learning model executed by a processing device generates an initial topic segmentation corresponding to the set of sentences. A second machine-learning model is applied to the initial topic segmentation to generate a final topic segmentation corresponding to the document.

Embodiments described herein relate to systems and methods for automatically generating content, generating API requests and / or request bodies, structuring user-generated content, and / or generating structured content in collaboration platforms, such as documentation systems, issue tracking systems, project management platforms, and other platforms. The systems and methods described use a network architecture that includes generative interface panel used to access a prompt generation service and a set of one or more purpose-configured large language model instances (LLMs) and / or other trained classifiers or natural language processors used to provide generative responses for content collaboration platforms.

A system (10) for determining report output data associated with a defined report type of a plurality of report types. The system (10) comprises a database (26) including a plurality of database table

Methods, apparatus, and systems to determine a niche market of items or services, the first phase of which identifies a gap between demand and supply for a set of items. Session logs may be evaluated to compare transactions involving a specific item to those of a larger group of items. The resultant information identifies areas of high demand, but with low availability. The niche market information may be provided as direct merchandising items for sellers. In one example, the method generates niche market item web pages in specific categories. Additional methods, apparatus, and systems are disclosed.

Techniques include accessing a set of documents; generating a final unified representation for each document of the set of documents, wherein generating the final unified representation comprises performing an iterative process for each document, and wherein the iterative process comprises: encoding, using a semantic embedding vector, a document's core semantic features in a semantic encoding, mapping a time domain for at least the document into a dimensional vector space to encode temporal information into a temporal encoding, and aggregating the semantic encoding and temporal encoding to generate the final unified representation; generating a query embedding, where the query embedding comprises a time-aware embedding for a query; comparing the query embedding to the final unified representation for each document of the set of documents; identifying one or more documents of the set of documents based on the comparing; and providing the one or more identified documents for downstream use.

An information processing apparatus includes a memory that stores document data and metadata of the document data in association with each other, and circuitry to transmit the document data to a first storage service to store the document data in the first storage service, receive a storage location address of the document data from the first storage service, and transmit the metadata and the storage location address to a second storage service to store the metadata and the storage location address in the second storage service. The second storage service is different from the first storage service.