1823 results about "Electronic mail" patented technology

Systems and methods for detecting a phishing attack in an email message. The method includes intercepting and evaluating an email, and generating a reputation score based on the evaluation of the email message. If the malicious component is detected, the email is blocked, if not, a trust score is generated. A determination is made whether the email is generated by AI, based on LLM. A certainty score is generated which is indicative of intentions and context of the email message being malicious. When the certainty score is higher than a threshold, a combined score by combining the reputation score, the trust score, and the certainty score. When the combined reputation score is higher than a threshold, the email is blocked, and if lower, a summary is generated by a summary AI engine. Based on a comparison with known malware summaries, the email is flagged or blocked.

An AI-powered agile project management system for automatic risk assessment and mitigation, including: a risk identification module configured to extract project data from agile project management tools, including but not limited to Jira, Trello, Asana, and Monday.com, and identify potential risks using machine learning and NLP; a risk analysis module configured to assign risk scores based on probability, impact, and severity using predictive analytics, where the module uses historical data, real-time project status, and external dependencies to determine the severity and impact of risks; a real-time monitoring module configured to continuously track project conditions, detect anomalies, and generate immediate notifications via email, mobile apps, or messaging platforms when high-risk events are identified; a risk mitigation module configured to dynamically recommend and execute proactive corrective actions such as task reassignment, resource optimization, schedule adjustments, and implementation of alternative strategies using AI-driven decision-making, where the actions can be automated through predefined workflows or manually adjusted based on AI recommendations; an AI-driven task prioritization module configured to dynamically prioritize tasks based on risk factors, project deadlines, and team workload distribution; an integration module configured to ensure seamless compatibility with existing Agile project management frameworks through API-based synchronization; a learning and continuous improvement module configured to refine risk prediction models over time using machine learning and historical risk mitigation results, with AI-driven models continuously updating risk assessment mechanisms based on evolving project conditions, industry-specific risk factors, and historical performance metrics; a compliance and audit reporting module configured to automatically generate risk reports, audit logs, and compliance checklists; a customizable risk assessment configuration module configured to allow project managers to define custom risk parameters, probability thresholds, and mitigation preferences; an interactive dashboard module configured to visualize data in real time, including risk trends, effectiveness of remedial actions, and analysis of project progress; and a scalability feature configured to be used in industries such as IT, healthcare, finance, construction, and manufacturing.

Original content of an email message is verified upon receipt of the email message at a receiver mail server prior to presenting the email message to a recipient. Determination of original content is made by comparing a verification hash value to a calculated hash value of the received email message. When the verification hash value does not match the calculated hash value, an invalidity warning is presented to the recipient with an option to view the invalid email message.

A method for efficiently generating a plurality of personalized email strategies and corresponding personalized emails for campaign recipients is disclosed. Multi-dimensional data comprising account data, recipient data, and seller data is received from one or more data sources. The received multi-dimensional data is processed to extract relevant features. A dynamic feature hierarchy is generated using the extracted features. A pre-trained machine learning model is fine-tuned using the dynamic feature hierarchy to generate email strategies, wherein model parameters are adjusted based on the hierarchy during fine-tuning. A plurality of email strategies is generated for each recipient by applying the fine-tuned model's recommendations. An email strategy is selected from the plurality of strategies based on one or more factors. A personalized email corresponding to the selected email strategy is generated. The personalized email and the selected email strategy used to generate it are displayed to a user.

In some implementations, a phishing test engine may receive a set of email messages that are associated with a set of users and with an indication of legitimacy. The phishing test engine may perform clustering on the set of email messages to identify a subset of similar email messages and a subset of users. The phishing test engine may generate an email template based on the subset of similar email messages and including an indicator of phishing. The phishing test engine may generate, from the email template, a test email message addressed to a user in the subset of users and may transmit the test email message to the user. The phishing test engine may receive an indication of an interaction with the test email message and may update a policy associated with the set of users based on the indication of the one or more interactions.

A security awareness training system can include a recognition module, a mapping module, a customized training module, and an authentication module. The recognition module can detect when behavioral activity by an end user on an endpoint device creates one or more of i) a model breach indicative of a potential cyber threat and ii) a violation of a network policy, an email policy, or a cloud policy. The authentication module can cooperate with the recognition module to provide just-in-time cyber security awareness training on a display screen of the endpoint device associated with that specific end user, at a time when the behavioral activity by the end user on the endpoint device creates the one or more of i) the model breach indicative of the potential cyber threat and ii) the violation of the network policy, the email policy, or the cloud policy. The authentication module can cooperate with a mapping module and a customized training module to provide the just-in-time cyber security awareness training on the endpoint device associated with that specific end user at the time when the behavioral activity by the end user on the endpoint device triggers a need for the cyber security awareness training, which causes more relevant and better learning for the end user. The mapping module can correlate the just-in-time cyber security awareness training to the behavioral activity by the end user on the endpoint device that created the model breach and / or the violation.

A machine learning-based fraud detection system (100) for financial transactions, comprising the following: a data collection and preprocessing module configured to capture transaction data from financial institutions, payment gateways and bank modules, and to perform data cleansing, normalization and format conversion; a module for creating user profiles and behavioral analyses, configured to create dynamic user profiles based on historical transaction patterns, spending habits, device usage, and geographic location; an anomaly detection and risk assessment module configured to use machine learning algorithms to detect deviations from normal transaction patterns and assign a dynamic risk rating to each transaction; a fraud detection module configured to classify transactions as legitimate or fraudulent based on supervised and unsupervised learning techniques, including decision trees, support vector machines (SVMs), and deep learning models; a rule-based and hybrid fraud detection module configured to integrate predefined rule-based fraud detection mechanisms with AI-driven anomaly detection to improve fraud detection accuracy; a real-time fraud detection and warning module configured to monitor transactions in real time and generate security alerts via SMS, email or mobile app when suspicious activity is detected; a transaction verification and multi-factor authentication (MFA) module configured to implement adaptive authentication measures, including biometric verification, one-time passwords (OTP), and challenge-response authentication for high-risk transactions; a self-learning and model-updating module configured to dynamically update fraud detection models using reinforcement learning and federated learning techniques; a data encryption and security module configured to protect transaction data using encryption techniques, including AES-256 and RSA, to prevent unauthorized access and data breaches; and A dashboard and reporting module configured to provide real-time analytics, visualizations, and fraud detection reports for financial institutions to monitor, track, and mitigate fraudulent activity.

Some embodiments of the present disclosure may include a method for processing request emails using a Generative AI email platform, including receiving a request email from a sender. Some embodiments may also include identifying the sender of the request email. Some embodiments may also include determining whether the sender may be an authenticated user. Some embodiments may also include, if the sender may be not an authenticated user, generating a reply email inviting the sender to sign up. Some embodiments may also include, if the sender may be an authenticated user, determining a prompt from the request email and inputting the prompt into the AI model. Some embodiments may also include receiving an output from the AI model based on the prompt. Some embodiments may also include generating a reply email based on the output and transmitting the reply email to the sender and / or another address.

Methods, systems, and computer storage media for providing a data analysis pipeline using a data analysis pipeline engine in a data intelligence system are described. A data analysis pipeline refers to a structured sequence of data processing steps that support transforming raw data into meaningful insights or actionable outcomes. The data analysis pipeline engine is an unsupervised learning pipeline based on clustering, topic modeling, and Large Language Models (LLMs). For example, the data analysis pipeline can use advanced machine learning techniques to automatically categorize emails into semantically similar clusters, enabling the data intelligence system to quickly identify and prioritize potentially high-risk emails for further investigation. The data analysis pipeline employs AI agents for context-aware graph induction relevance assessment. The AI agents employ induction and deduction loops to build and refine a data feature hypergraph (e.g., vulnerability hypergraph) that encompasses identified relevant data providing a holistic view of a contextual landscape.

An AI-powered system for optimizing industrial workflows and predictive maintenance, which includes the following: a network of sensors configured to collect real-time data from industrial plants, including temperature, pressure, vibration, and energy consumption metrics; a central control unit configured to process and analyze the collected data using machine learning algorithms that continuously improve by learning from both historical and real-time data to increase prediction accuracy; a predictive maintenance module configured to analyze data to predict potential equipment failures, schedule proactive maintenance tasks, and prioritize maintenance activities based on the predicted impact of the failure and the criticality of the equipment; a workflow optimization module configured to dynamically adjust operating parameters to optimize the process flow, including the detection of inefficiencies and the suggestion of improvements in real time; an integration module configured to connect and interact with existing industrial control systems and ERP (Enterprise Resource Planning) software to ensure a seamless flow of data between the platforms; a user interface configured to visualize data in real time, provide alerts and customizable dashboards, and is accessible via desktop and mobile devices for remote monitoring and management; an alarm and notification module configured to deliver critical alarms and maintenance notifications via email, SMS and in-app notifications to ensure a timely response; a cloud-based architecture configured to facilitate scalable data storage, remote access, and management across multiple industrial sites; a reporting module configured to generate comprehensive reports on plant performance, maintenance history, and workflow efficiency for analysis and decision-making; A security protocol to protect data integrity and ensure secure communication between all system components.

Systems and methods are described for a connected AI agent for managed multidimensional search based on an electronic message and management policies. A messaging application at a client device can send a new electronic message, such as an email, to a connector service. An attachment can be ingested and stored in a vector database. Then one or more artificial intelligence (“AI”) agents can be selected for responding to the body of the email, such as a query in the body. The responses can be formatted and sent to multiple parties, such as a sending user of the electronic message and a recipient that was copied or also sent the new electronic message. The AI agents can use different AI models, prompts, and vector databases depending on user permissions. This allows for building up vector databases with relevant content items and answering user questions based on those vector databases.

Processes and machines are disclosed for detecting malicious email campaigns based on unique but similarly spelled attachments. Email log(s) from network appliances are retrieved, filtered, normalized, and converted into field-based organized data for comprehensive analysis. Cluster analysis is performed. Filenames of email attachments are transformed into numerical vectors and a cosine similarity termset analysis is performed on the numerical vectors. Data is organized into time bins for burst detection. Statistical analysis is performed on the time bins. Pattern recognition is performed to identify alphanumeric similarities in the filenames of the attached files in order to detect malicious email campaigns. Machine learning may be used to optimize the cosine similarity threshold and other query variables, and to update existing cybersecurity filters and firewalls. Mitigation can be performed to remove malicious emails that were delivered to recipient mailboxes.

The present technology provides methods and systems for enhanced email communication by generating sender-centric responses in an email client. The email client takes sender-specific data and data used to determine the relationship between the sender and receiver. This data is then used as input for a trained receiver-specific generative AI model. The generative AI model generates a custom response for a new inbound email which is displayed on the email client.

The technology disclosed allows for leveraging decentralized credentials to achieve bidirectional authentication between two actors leveraging a messaging platform / system, such as email or another text-based system, verifiable credentials (VCs), and secure web endpoints. It empowers one party (“Sender”) to send a message enclosed with a Verifiable Presentation which allows another party (“Recipient”) to authenticate the message's provenance and the identity of the sender. Moreover, the message contains a link to a secure web endpoint, where the recipient can submit a response signed by their own Verifiable Presentation, allowing the Sender to authenticate the identity of the Recipient. In this way, both participants are able to authenticate each other's identities with an additional factor of authentication, with neither participant being required to share a single service.

Methods, apparatuses, and systems are described for generating customized content such as pitch communications, tailored pitch emails, press releases, customized user biographies, and posts, such as blog posts, byline posts, and social media posts. A content platform may be configured to use one or more machine learning models to generate the customized content based one or more user inputs and send the customized content to one or more target recipients.

Computerized systems and methods for automated Access Permissions Review in an organization. A method includes: (a) receiving a textual description of an Access Review Policy; (b) constructing a trigger for automatically initiating an Access Review process; (c) automatically collecting organizational data that pertains to: (i) roles and positions of users, (ii) user-specific characteristics, (iii) email messages sent and received by users, (iv) description of events in which users had accessed elements of the Organizational Resource. Upon a triggering of the trigger, the method provides to a fine-tuned Large Language Model (LLM), the Access Review Policy and augmentation data from the organizational data, and a prompt instructing the LLM to generate a proposal to revoke, modify, add or maintain the Access Permissions of a particular user, and further instructing the LLM to generate output that describes reasoning and supporting evidence for the proposal.

An AI-powered dispute triage and classification system (100) that includes: (a) a dispute input module configured to receive dispute inputs from multiple communication channels, including text, voice, email and chatbot interfaces; b) a Natural Language Understanding (NLU) module that uses machine learning models to extract intent, sentiment and contextual metadata from the dispute content; (c) a classification and prioritization module configured to categorize disputes into predefined taxonomies and assign priority levels based on predefined rules and AI-based predictions; (d) an intelligent routing module that routes disputes to specific human agents, automated systems or escalation paths based on classification results and organizational policies; (e) a solution assistance module configured to suggest or autonomously execute solution actions using AI-generated answers or predefined templates; and (f) a continuous learning module configured to retrain AI models using feedback data from dispute outcomes, user interactions and resolution performance, enabling automatic triage and classification of disputes in real time to optimise resolution time, accuracy and resource utilisation.

To provide a system.SOLUTION: A system comprises: means for analyzing the content of a junk mail; means for analyzing the transmission mail address of the junk mail; and means for blocking the junk mail on the basis of the analysis result.SELECTED DRAWING: Figure 1

Systems and methods are provided for managing AI (Artificial Intelligence) agents interactions with electronic communications that are displayed at an electronic communications interface, such as an email interface. The systems parse electronic communications to determine whether they correspond to new or existing requests and actions to be performed when responding to the request(s). The systems also generate notifications identifying the set of actions with visual identifiers that visually distinguish the set of actions based on whether they have been completed or not and whether they need authorization to be completed. The systems also display selectable controls for controlling how the AI agent performs the actions.

The intelligent automated assistant system engages with the user in an integrated, conversational manner using natural language dialog, and invokes external services when appropriate to obtain information or perform various actions. The system can be implemented using any of a number of different platforms, such as the web, email, smartphone, and the like, or any combination thereof. In one embodiment, the system is based on sets of interrelated domains and tasks, and employs additional functionally powered by external services with which the system can interact.

The present disclosure describes a customized voice messaging platform. The customized voice message placement can enhance engagement using personalized audio content. The platform can generate authentic-sounding voice messages using Al-driven processes, including text-to-speech (TTS) technology and audio concatenation, to create personalized audio content. The platform supports various delivery channels such as SMS, email, podcasts, and streaming services. The platform can incorporation visual elements like brand logos and animations into personalized messages. The platform can provide campaign creation functionality, enabling users to create campaigns deliver customized messages across multiple channels. The platform can provide message suggestions, automated testing, and other features. The platform can support rules for determining when to send messages and / or the content of messages.

A peer-to-peer (P2P) distributed data management system (DDMS) may operate as an operating system on which P2P distributed applications are utilized to manage data on distributed ledgers, such as blockchains. The DDMS may enable fast development of secure and scalable enterprise P2P distributed applications that support permanent control of every piece of data on a distributed ledger, synchronization, normalization of the data, and encryption of the data. Security of the data in the distributed ledger means that even if someone hacks into the distributed ledger, access is only gained to one block of data (e.g., single email) and not all blocks of data (e.g., entire email account). The DDMS may be integrated into Internet-of-Things (IoT) devices. The DDMS further automatically supports sequential smart contracts on the distributed ledger.

This disclosure describes techniques and mechanisms to retroactively identifying, classifying, categorizing, and / or remediating campaigns by an email threat defense system. The described techniques may perform a time-series analysis on record data associated with emails and identify campaigns that have bypassed threat detection mechanisms. The described techniques may extract and correlate features of the record data in order to label and determine whether a campaign is malicious. Where the email campaign is malicious, remedial action(s) can occur. Accordingly, the described techniques may remediate false negatives in a network and improve network security.

Disclosed herein are system, method, and computer program product embodiments for a customer records management translation extension. A computer system receives customer data comprising a first name, last name, an email address, and a phone number from a front-end interface of an agent workstation. Based on the customer data, the computer system obtains one or more customer objects from a customer object database, wherein each of the customer object comprises a customer identifier. The computer system selects the customer object that best matches the customer data and obtains a customer lead identifier from the customer object database that corresponds to the customer identifier of the selected customer object. Based on the customer lead identifier, the computer system obtains a lead object from a lead object database and generates a link to the lead object. Finally, the computer system transmits the link to the front-end interface of the agent workstation.

The present disclosure relates to the field of email security detection. Disclosed are an email security detection apparatus, method and device, and a storage medium. The method includes: an email feature extraction component, configured to collect and extract the behavior features of a sender and a recipient of an email, and the main body features of the email; a behavior feature analysis component, configured to comprehensively analyze the extracted behavior features of the sender and the receiver to identify a suspicious phishing email; a main body feature analysis component, configured to detect and analyze the extracted main body features of the email, and identify a suspicious phishing email; and an email filtering and alarming component, configured to perform filtering and real-time alarming and pushing on the suspicious phishing email identified by at least one of the behavior feature analysis component and the main body feature analysis component.

Systems and methods are provided for facilitating automated administration of email messages received by a customer service representative including a service email administrator system that reviews incoming email messages, analyzes the content, assesses emotional sentiment, urgency, and determines the best course of action. The conversation administrator is configured to use natural language processing and machine learning algorithms to generate automated responses, provide email response drafts for customer service representative (CSR) review, or route emails to CSRs based on the sentiment or urgency.

Systems and methods are provided for implementing deep search functionality using large language models (“LLMs”). In various examples, a computing system uses at least one LLM to generate intents based on a user query, to generate alternative queries based on a selected or identified primary intent, and to generate a relevance score for each search result that is obtained from a search utility (e.g., an Internet search engine, a file storage search utility, an email search utility, or a document storage search utility) in response to a primary query (corresponding to the primary intent) and the generated alternative queries being entered into the search utility. The search results from the search utility are sorted based on the corresponding generated relevance scores, and the sorted search results are caused to be displayed to the user as a deep search response to the user query.

Aspects of the disclosure relate to data loss prevention. A computing platform may detect input of a first target recipient domain into a first email message. The computing platform may identify, in real time and prior to sending the first email message, that the first target recipient domain comprises an unintended recipient domain instead of an intended recipient domain. The computing platform may send, based on the identification of the unintended recipient domain and to a user device, a notification that the first target recipient domain is flagged as an unintended recipient domain and one or more commands directing the user device to display the notification.

A system and method for privacy-preserving communication validation and multi-attribute trust scoring is disclosed. The system analyzes communication metadata to determine pattern legitimacy by comparing current communication patterns against relationship fingerprints without accessing communication content. The system validates relationship context between communicating parties using interaction graph analysis and historical communication data. Cross-network intelligence correlation compares current patterns against aggregated patterns across voice, email, and messaging services, creating a self-strengthening security framework that recognizes emerging threat patterns while validating legitimate communication behaviors. The system generates comprehensive multi-attribute trust assessments comprising individual trust attribute scores including engagement rate, reliability index, channel preference, temporal pattern, and behavioral pattern, combined into overall trust levels. Trust context is displayed through a user interface presenting simplified, intuitive, and actionable information with progressive disclosure capabilities, enabling informed user decisions while preserving privacy. Communication processing actions provide users with appropriate engagement options tailored to specific trust assessment results.

The disclosed techniques provide improved methods of operating system (OS) search. Users are enabled to search for documents, emails, presentations, content they entered into a web form, meetings they participated in, and other interactions they had with their computing device. To accomplish this, screenshots are periodically captured and indexed. Machine learning models are used to infer embeddings for visual elements of the screenshots and / or text extracted from the screenshots. A full text index of a relational database may also be populated with text extracted from the screenshots. The embeddings and full text index may then be used to retrieve screenshots in response to a user history query. For example, screenshots of embeddings within a defined distance of an embedding of the user history query may be selected. Query results from different embedding indices and relational databases may be ordered by applying different weights to different kinds of search scores.