659 results about "Digital document" patented technology

The invention relates to the technical field of management and control systems, in particular to a digital intelligence system applied to collaborative management and control of water-power engineering construction participating units, which comprises a project data management module covering water-power engineering construction full life cycle management, extracting multi-source information data from various subsystems, and constructing a project view and a project management information base; the project risk analysis module is used for constructing an intelligent risk analysis model for risk analysis and generating a dynamic evaluation result, a graded early warning notification and an auxiliary decision scheme; the project collaborative management module is used for processing graded early warning notification and auxiliary decision-making schemes by using a multi-layer perceptron model, and generating finalizing service achievements and management process records; and the project document management module is used for performing compliance automatic checking and processing on the electronic documents needing to be archived, and dynamically updating and optimizing the project management information base. Through the closed-loop management and control system, the cooperative management and control efficiency of water-power engineering construction participation units is improved.

A method for packaging digital evidence for long term validation comprises forming a package of a digital document (10), an electronic signature (12) for the document (10), together with evidence (16) of the authority of the signature in the document and a time stamp (20) indicating when the document was digitally signed. All of the pieces form parts of the packaged evidence.

A method for AI-driven natural language search includes receiving a user query for one or more items from a user, processing the user query by searching against at least one relational database associated with the query, where the relational database is generated by extracting features from electronic documents of a plurality of items associated with the one or more items and by identifying specifications or respective values corresponding to the extracted features of the plurality of items, generating one or more query results based on the processing of the user query, where the one or more results include at least one item identified from the plurality of items and a justification for explaining an irrelevance of the at least one item, and transmitting the one or more query results to a user device for presentation to the user.

A method, an apparatus, and a computer-readable storage medium for generating a document graph. A plurality of electronic documents is received. Each electronic document has a predetermined document type. A machine learning model is selected from the plurality of machine learning models based on the predetermined document type. The selected machine learning model is instructed to extract a plurality of document portions from each electronic document in the plurality of electronic documents in accordance with the predetermined document type. A relationship between two or more document portions is defined based on the content of each document portion, and the document portions are associated based on the relationship. A graph structure having a plurality of nodes is generated. Each node includes at least one document portion. Each node is connected to another node in accordance with the relationship between document portions included in the nodes. The graph structure is stored.

The present disclosure relates to systems, methods, and non-transitory computer-readable media that iteratively generates, utilizing a machine learning model, text responses to reduce hallucinated content. In particular, in some embodiments, the disclosed systems receive a digital query and selects one or more supporting digital documents for the digital query. Furthermore, in some embodiments the disclosed systems generate a first text response from a first text prompt generated by using the digital query. Moreover, in some embodiments the disclosed systems extract a misalignment portion of the first text response by comparing the first text response and the one or more supporting digital documents. Additionally, from the misalignment portion of the first text response and the digital query, the disclosed systems further generate a second text response.

The invention provides a private deployment-oriented multi-modal AI knowledge base construction system. The private deployment-oriented multi-modal AI knowledge base construction system comprises a knowledge storage module, an intelligent document loading module, a document partitioning engine module, a data enhancement engine module, a multi-language semantic vector alignment module and a private deployment module, the knowledge storage module comprises a knowledge authority management sub-module and a knowledge source management sub-module, the knowledge authority management sub-module is used for managing and storing knowledge from different sources, and the knowledge source management sub-module is used for managing electronic documents and multimedia documents; according to the method, intelligent identification, partitioning, vectorization and source file storage can be carried out on different types of electronic files, knowledge graph construction is carried out for specific fields, semantic relevance between texts and topics and key entities is fully considered, the method has wider applicability, higher robustness and controllability, the data leakage risk is effectively reduced, and the method is suitable for popularization and application. The method is suitable for enterprise sensitive data protection and personal user elastic computing power requirements.

Techniques for hybrid natural language generation (NLG) using a symbolic NLG engine and a large language model (LLM) are disclosed. The techniques include: obtaining a first text segment configuration; obtaining values of at least some of a first set of data variables; generating a first natural language text segment for an electronic document using a first text segment configuration, the values, and the symbolic NLG engine; obtaining an initial text segment; obtaining a second text segment configuration specifying information to use for generating a second natural language text segment using the ML NLG engine from the initial text segment; generating a second natural language text segment for the electronic document by using the initial text segment, the second text segment configuration, and the ML NLG engine; and outputting the generated electronic document.

Embodiments extract a key phrase from an online profile of a user of a professional social network (PSN) and identify a set of skills associated with the key phrase. A set of skill embeddings corresponding to the identified set of skills may be retrieved from a store of skill embeddings. The skill embeddings may be pre-created by a large language model (LLM). The retrieved skill embeddings may be aggregated to create a skill-centric digital representation of the user. Based on the skill-centric digital representation of the user, a subset of digital documents may be identified to present to the user via the PSN.

A method, an apparatus, and a computer-readable storage medium for executing obligation management. One or more document portions are extracted from an electronic document using at least one machine learning model selected from a plurality of machine learning models based on at least one parameter associated with the electronic document. One or more entities are identified in one or more document portions of the electronic document. The entities are sent to a generative artificial intelligence (AI) model. The generative AI model is configured to generate one or more rules defining one or more obligations associated with one or more entities. One or more rules are executed to monitor compliance with one or more obligations by one or more entities.

In various examples, systems and methods are disclosed relating to displaying images in chatbot / NPC / virtual agent / digital avatar / etc. responses. A system can identify text corresponding to an image in an electronic document and can store a representation of the text in association with an identifier of the image. The system can receive an input prompt for a machine-learning model. The system can generate a response to the input prompt using the machine-learning model. The response can include the image responsive to identifying the representation of the text using a searching function and an output of the machine-learning model.

A method, a system, and a computer program product for generating a benchmarking dataset. One or more queries for generation of one or more summaries of one or more electronic documents are received. The queries are modified using one or more parameters associated with the electronic documents to generate modified queries. The electronic documents are sent to a generative artificial intelligence (AI) model. The generative AI model generates summaries of the electronic documents based on at least one of: the initial queries and the modified queries. One or more labels for the electronic documents are generated using the summaries.

Methods, systems, and non-transitory computer readable storage media are disclosed for optimizing computer memory usage for lookup lists in computer memory via probabilistic data structures. For example, the disclosed system generates a probabilistic data structure (e.g., a Bloom filter) to represent data in a lookup list including multi-token items by hashing items of the lookup list to sets of bit values in a bit vector. The disclosed system classifies text content in a digital document by utilizing a maximum number of tokens from multi-token items in the lookup list to select and compare sets of sequential tokens in the digital document to the probabilistic data structure. The disclosed system also iteratively reduces the number of tokens in sets of sequential tokens for subsequent comparisons. Furthermore, in some aspects, the disclosed system causes a computing device to modify a digital document and / or database operations based on the classifications.

The invention provides a campus intelligent terminal paper management service system and method, and the system comprises a data alignment module, a structured storage module, an intelligent query module and an association retrieval module: the data alignment module is used for carrying out the feature extraction and semantic alignment of obtained multi-modal education data, and carrying out the extraction and semantic alignment of the obtained multi-modal education data; obtaining a cross-modal feature data set; wherein the multi-modal education data comprises at least one of a paper homework scanning image, an electronic document and classroom audio and video; the structured storage module is used for constructing a teaching spatio-temporal topology database containing a subject knowledge point graph based on the cross-modal feature data set; the intelligent query module is used for performing semantic analysis on the obtained natural language instruction to generate a composite query instruction; and the association retrieval module is used for executing cross-modal association retrieval on the teaching spatio-temporal topology database based on the composite query instruction and outputting a comprehensive query result. By adopting the system, the paper material management level can be improved, and the teaching quality can be improved.

A computer-implemented method of automatically generating interactive compliance controls by a server computer system to a client computing system is provided. The method includes receiving, by the server computer system, a first input from the client computing system. The first input provides an electronic rules document including a plurality of compliance rules or identifying information for the electronic rules document, and information related to an asset. The method also includes outputting, by the server computer system to the client computing system and in response to the first input, controls corresponding to the compliance rules. The controls being rephrasings of the compliance rules and generated by inputting the electronic document into a first large language model (LLM). The first LLM being pretrained by examples specifying acceptable and unacceptable control outputs for a plurality of compliance rule inputs.

Authentication of electronic document is based on multiple digital signatures incorporated into a blockchain. Structured data, metadata, and instructions may be hashed to generate the multiple digital signatures for distribution via the blockchain. Any peer receiving the blockchain may then verify an authenticity of an electronic document based on any one or more of the multiple digital signatures incorporated into the blockchain.

Thematic summary generation of digital document techniques are described. A one or more semantic groups are parsed having differences, one to another, from first and second digital documents by comparing the first and second digital documents. Text descriptions of the one or more semantic groups are acquired. The text descriptions are generated using generative artificial intelligence as implemented by at least one machine-learning model. One or more clusters are formed based on the text descriptions and a cluster description of the one or more clusters is obtained. The cluster description is generated using generative artificial intelligence as implemented by at least one machine-learning model. A thematic summary is constructed of the differences in the first and second digital documents based on the cluster description for output in a user interface.

The invention discloses a power industry dynamic knowledge base construction method and system based on a large language model, and relates to the field of electric digital data processing, and the method comprises the steps: receiving a power field document imported by a user, and converting the power field document into an electronic document; calling a large language model to analyze the electronic document, extracting a terminology definition, chart position information and a document logic level in the electronic document, and generating a knowledge unit containing a plurality of contexts; connecting the knowledge units into directed knowledge links, calculating semantic similarity between adjacent knowledge units in the directed knowledge links, and segmenting the directed knowledge links to obtain a plurality of knowledge topics; receiving a knowledge retrieval instruction, and determining a target knowledge theme corresponding to the knowledge retrieval instruction; and extracting a corresponding target knowledge unit in the target knowledge theme, and generating a knowledge retrieval result based on a target context of the target knowledge unit. By implementing the method, knowledge base construction can be optimized, and the integrity of knowledge base data is ensured.

A system including a media data optimization engine (MDOE) and a method for automatically creating structured data objects for media content rendered in one or more languages in an electronic document of a business entity are provided. The MDOE identifies non-textual objects including media content rendered in one or more languages in the electronic document and generates textual objects in the corresponding language(s) therefrom. The MDOE transforms the textual objects into structured data objects based on configurable criteria and generates a dynamic index-oriented object for the structured data objects specific to the business entity. The MDOE connects the structured data objects to the dynamic index-oriented object by creating linked data nodes therefrom with the dynamic index-oriented object as a core. The MDOE connects the dynamic index-oriented object with the linked data nodes to the electronic document, thereby facilitating dynamic changes to the electronic document and dynamically optimizing the electronic document.

The invention discloses an electronic document tracing method and device based on dynamic encryption and multi-modal watermarking, and relates to the technical field of information security and digital rights management. The method comprises the following steps: acquiring a PDF document uploaded by a user, encrypting the PDF document by adopting a randomly generated main encryption key, and acquiring and storing the encrypted PDF document; the content of the encrypted PDF document is analyzed, secret information is embedded into a picture in the document based on a two-dimensional discrete cosine transform algorithm, and picture watermark embedding is completed; a self-adaptive watermark embedding algorithm is adopted to embed secret information into a text in the document, and text watermark embedding is completed; related information of the checking operation is written into a block chain database; dynamically extracting watermark information from the divulged PDF document by adopting a watermark extraction algorithm; and querying a traceability database according to the extracted watermark information, and outputting a traceability result by comparing the extracted watermark information with information in a database storing various watermark information. According to the invention, the survival rate and the concealment of the watermark can be improved.

A secure digital management tool for managing real estate ownership and leases, consisting of: a tamper-proof enclosure containing a secure processing module; a biometric authentication module comprising a fingerprint sensor and an iris scanner, which are operationally coupled with a secure biometric engine to verify a user's physical identity; a document integrity module configured to generate a cryptographic hash of a digital document representing a certificate of ownership or a lease agreement; a smart contract engine configured to compile and execute the logic for legal transactions related to ownership in a Turing-complete virtual machine environment, the logic defining obligations, rights, payment schedules or renewal triggers encoded in the lease or ownership contract; a blockchain interface processing unit operationally connected to the document integrity module and the smart contract engine, wherein the blockchain interface processing unit is configured to anchor cryptographic hashes of the documents and the execution status of smart contracts in a decentralized ledger network; a secure element embedded in the secure processing module and configured to store cryptographic private keys and perform isolated signature and encryption operations without exposing confidential key material to general storage space; a communication subsystem that includes at least one of the following elements: a GSM / 4G module, a Wi-Fi 6 module and a GPS receiver, configured for secure network connectivity and geolocation binding of transactions; a touchscreen interface configured for displaying transaction forms, digital agreements, and interactive contract signing interfaces, the interface also including pen input for capturing digital handwritten signatures; and a secure audit trail subsystem configured to maintain a chronologically ordered, append-only log of all biometric access events, document hash generations, blockchain anchoring events, and smart contract lifecycle transitions, with the audit trail regularly hashed and anchored for forensic integrity in a decentralized blockchain network.

Systems, methods, and other embodiments associated with a framework for multi-entity detection, data sourcing, and processing are described. In one embodiment, a multi-entity processing method includes parsing an electronic document being processed in a processing flow for a first entity to detect that the document also concerns a second entity based on entity identifiers in the document. In response to the detection, the method determines an inter-entity agreement that governs processing between the first entity and second entity by matching attributes of the document against stored agreement data structures. The method automatically orchestrates processing of an inter-entity transaction between the first entity and the second entity by generating execution steps according to sequential and parallel dependencies specified by the inter-entity agreement. And, the method generates electronic records in a system of the first entity and a system of the second entity that reflect execution of the inter-entity transaction.

Presented herein are systems and methods of controlling access to values in electronic documents. A first service may receive an electronic document comprising a corresponding plurality of values associated with a corresponding plurality of fields to be provided to at least one of a plurality of client devices. The first service may identify, from the electronic document, a field of the plurality of fields associated with a corresponding value of the plurality of values is to be encrypted. The first service may select, from a plurality of first encryption keys, a first encryption key based on a field type of the field. The first service may generate a token using the value and the first encryption key for the field. The first service may send to a client device of the plurality of client devices, the electronic document comprising the token replacing the value associated with the corresponding field.

A method of digital document review using factor graph document databases comprising an extract method and a summarise method, wherein the extract method uses a Large Language Model (LLM) to decompose into variables and elements a document or series of documents and to identify new terms semantically associated with the description of the interest of the desired audience for the document review process, and representing the variables and elements in a factor graph document database, and wherein the summarise method includes indexing the factor graph document database based on terms of interest to the audience of the review, and inferring which of the new variables and elements are relevant to the audience, and reconstructing a human interpretable document out of the variables and elements inferred in the factor graph document database.

The invention relates to the technical field of information security, and discloses a handwriting dynamic encryption and electronic signature method based on a national secret algorithm, and the method comprises the steps: obtaining the handwriting data of a user, and carrying out the preprocessing of the data to remove noise and errors; carrying out feature extraction on the preprocessed handwriting data, extracting corresponding track features, speed features and pressure features, and generating a feature hash value of a unique identifier through a cryptographic SM3 hash algorithm; splicing and combining the feature hash value and a user private key, deriving a dynamic key through a national secret SM2 algorithm, and generating an electronic signature by using the dynamic key; an electronic signature is combined with a timestamp to form a structured signature packet, and the signature packet is hierarchically encrypted and stored in a database through a national cryptographic SM4 algorithm. According to the method and the system, the handwritten signature picture, the digital signature technology, the electronic signature technology and the biological recognition and layout file processing technology are fused, so that the safety and the reliability of electronic document signing are improved.

The invention discloses a document content generation method based on a title structuring demand and related equipment, and relates to the technical field of artificial intelligence, the method comprises the following steps: performing structured analysis on a target electronic document to extract at least one title element in the target electronic document; receiving personalized requirements input by a user for the title elements, and performing data association on the personalized requirements and the corresponding title elements; the personalized requirements are used for guiding content generation; the title elements and the personalized requirements corresponding to the data association are combined into a generation request, and the generation request is sent to an artificial intelligence model; using an artificial intelligence model to obtain generation content according to the generation request; and inserting the generated content into a position related to the corresponding title element in the target electronic document. According to the method, the document structure can be deeply understood, a user is allowed to set independent generation requirements for different title elements, a document processing scheme for batch generation and selective optimization can be realized, and the flexibility of document processing is greatly improved.

The invention belongs to the technical field of electronic document processing, and particularly relates to an electronic document standardization modeling processing system which comprises a document input preprocessing module, a format standardization conversion module, an analysis reconstruction module, a metadata extraction management module, a quality inspection correction module, an experience optimization module and a security privacy protection module. According to the application, the acceptability of documents of different sources is improved through the document input preprocessing module, it is ensured that various types of electronic documents can be processed, the problem of typesetting disorder caused by format differences is reduced through the format standardization conversion module, and the document appearance consistency is kept through accurate style mapping; the analysis precision is improved through the analysis and reconstruction module, so that the original layout and style are better reserved; through the metadata extraction management module, the document management and retrieval capability is enhanced, and meanwhile, an adjustment space is provided to adapt to requirements under special conditions.

Techniques for identifying a document layout are disclosed. In one embodiment, attribute data associated with an electronic document is accessed. A machine learning model is then applied to the attribute data. The machine learning model is configured to classify the electronic document based on the attribute data and feature sets of a plurality of document classes. Based on the document class predicted by the machine learning model, the system identifies a layout associated with the document class. The layout specifies layout elements and content types associated with the layout elements. The system extracts and stores information from the electronic document according to its content type.

Methods and systems for generating live digital documents are provided. The method includes receiving a static document file including human-readable data. Then, parsing the static document file into a plurality of subunits. Then, generating a sharable document splice of the static document file. The sharable document splice includes access to a subset of the plurality of subunits, and the access is provided through an Application Programming Interface (API) or Software Development Kit (SDK) endpoint for each subunit in the subset. Then, executing a digital thread script to generate the live digital document from the sharable document splice and an input digital model representation, using API or SDK endpoints in the sharable document splice. The live digital document is configured through the digital thread script to reflect changes in the input digital model representation. Finally, adding execution metadata for the execution of the digital thread script to the live digital document.

The invention belongs to the technical field of product production cycle management, and particularly relates to an electronic image-text file remote multi-bin collaborative storage method based on a PLM. Comprising the steps that a 1 + N hybrid storage architecture is constructed, one center bin is deployed in an enterprise headquarter data center and stores full document metadata and latest version files, and N area bins are deployed according to geographic areas and store cache copies and incremental update data of local high-frequency access documents; the remote multi-warehouse document increment synchronization is realized through an intelligent synchronization engine, and the intelligent synchronization engine adopts a content awareness increment synchronization algorithm and a dynamic synchronization strategy based on network quality; version management is realized through a version cooperative control module, and the version cooperative control module is used for establishing a global version number mapping mechanism and a conflict resolution decision tree; cross-warehouse process automation is realized through a cross-warehouse workflow engine, and the cross-warehouse workflow engine integrates a BPM process engine and a message queue; the method can adapt to a remote network environment, and the large file synchronization efficiency is improved.

A server generates a user interface for allowing a user to rewrite portions of text for an electronic document to mitigate detected issues. For an input document, the server generates one or more indications over the one or more phrases in the sentence. An indication for a phrase may be generated based on a respective category associated with the phrase. Responsive to receiving an indication from the user to rewrite the sentence, the server generates a prompt to a machine-learned language model. The server receives a response generated by executing the machine-learned language model on the prompt. The server generates a pane user element to present the candidate sentence and an evaluation of the candidate sentence to the user, and responsive to receiving a selection of a candidate sentence, replacing the sentence in the editor with the selected sentence on the user interface.