14896 results about "World Wide Web" patented technology

Methods and systems are described for facilitating lending of NFTs through an NFT marketplace system. In some embodiments a token marketplace system receives a request from a lender to create an NFT loan listing, verifies the lender's ownership of the token, and creates the listing. When a potential borrower requests to borrow the NFT, the system initiates a series of verification steps. These include requesting permission for a retrieval smart contract to act on behalf of the borrower's account and confirming that these permissions have been granted by the lendee. Upon successful verification, the system initiates a blockchain transaction to transfer the NFT to the borrower's account. The foregoing allows NFT owners to lend their NFTs to lendees in a trustless ecosystem.

An example operation may include one or more of receiving content from a conversation between a user on a user device and a second user on a second user device that is connected to the user device via a network, identifying a topic of the conversation based on execution of a generative artificial intelligence (GenAI) model on the received content from the conversation, identifying a call list that is previously stored in memory that is associated with the topic of the conversation based on keywords included in the identified topic of the conversation, and adding an identifier of the user to the call list stored in memory.

Systems and methods are provided for a natural language question answering service to provide answers to natural language questions regarding network-based services or computing domains. The natural language question answering service may receive the natural language question from a customer computing device. An aggregator of the natural language question answering service can retrieve passages from search systems based on the question and generate a prompt. A large language model (LLM) of the natural language question answering service may receive the prompt and provide an answer. The answer may be verified by a verifier of the natural language question answering service. Attribution may be applied to the answers and retrieved passages to produce references, inline citations, and similar questions. A watermarking module of the natural language question answering service may watermark the answer if it is verified.

An example operation may include one or more of receiving an identifier of a product from a digital wallet on a user device, identifying one or more payment cards stored within the digital wallet on the user device, determining benefits that will be obtained by using each of the one or more payment cards to purchase the product via execution of an LLM on the identifier of the product and a corpus of credit card documents, and displaying a chat message within a chat window on the user device with a description of the determined benefits that will be obtained.

An interactive cyber-security user-interface for cybersecurity components can receive a voice input from a user as well as ii) a text input as a user input. The interactive cyber-security user-interface works with a set of differently trained LLMs to carry out tasks on behalf of the user input. The interactive cyber-security user-interface cooperates with the set of differently trained LLMs, which are grouped together to operate as an orchestrated system to provide different tasks. The tasks can include a collection of supplementary information, a summarization of cyber security information, translating a query in the natural human speech format into the required search syntax, how to integrate with an API, acting as a first line of support to user inquiries, a suggested response to a cyber security issue, etc. The interactive cyber-security user-interface for the cybersecurity components acts as the user interface for one or more of the cybersecurity components.

An example operation may include one or more of storing a database of payment card data, receiving an identifier of a product from a digital wallet on a user device, identifying one or more payment cards stored within the digital wallet on the user device, determining the benefits that will be obtained by using each of the one or more payment cards to purchase the product via execution of an LLM on the identifier of the product and the database of payment card data; and displaying a chat message within a chat window on the user device with a description of the determined benefits that will be obtained.

Large language models (LLMs) are versatile in responding to user questions on a wide variety of topics. However, LLMs suffer from several drawbacks, such as hallucinations, incomplete information, and inability to cite original sources of information. Disclosed herein are systems and methods for using an LLM in a restricted manner to respond to queries regarding document corpora, e.g., documents related to a set of products, such that the impact of these drawbacks is minimized. Information retrieval is coupled with LLMs to build a question and answer (Q&A) system on the text corpora. Complex retrieved information, incorporating human feedback, and recommendations in the Q&A system are provided.

Systems and methods are provided for a natural language question answering service to provide answers to natural language questions regarding network-based services or computing domains. The natural language question answering service may receive the natural language question from a customer computing device. An aggregator of the natural language question answering service can retrieve passages from search systems based on the question and generate a prompt. A large language model (LLM) of the natural language question answering service may receive the prompt and provide an answer. The answer may be verified by a verifier of the natural language question answering service. Attribution may be applied to the answers and retrieved passages to produce references, inline citations, and similar questions. A watermarking module of the natural language question answering service may watermark the answer if it is verified.

Systems and methods are provided for a natural language question answering service to provide answers to natural language questions regarding network-based services or computing domains. The natural language question answering service may receive the natural language question from a customer computing device. An aggregator of the natural language question answering service can retrieve passages from search systems based on the question and generate a prompt. A large language model (LLM) of the natural language question answering service may receive the prompt and provide an answer. The answer may be verified by a verifier of the natural language question answering service. Attribution may be applied to the answers and retrieved passages to produce references, inline citations, and similar questions. A watermarking module of the natural language question answering service may watermark the answer if it is verified.

An application management system may provide, while a user device detects a beacon associated with a medical system, a user of the user device with access to a first set of medical session features of an application executed by the user device. The application management system may also provide, while the user device does not detect the beacon, the user with access to a second set of medical session features of the application, the second set of medical session features being different from the first set of medical session features.

Device, system, and method for automatically detecting and classifying personally identifiable information (PII) in documents and files. A method includes performing a deterministic rule-based search, in a plurality of stored documents, for PII data-items. If the deterministic rule-based search indicates that a particular document is more likely than not to contain a PII data-items then the method includes: extracting a textual snippet from the particular document, wherein the textual snippets surrounds the PII data-item; adding the textual snippet and the particular document to one or more training datasets utilized for training a Large Language Model (LLM) configured to find PII data-items in documents for Named Entity Recognition (NER) in those documents.

Wireless-enabled kiosk systems and associated methods for recycling and performing other processes with mobile phones and other electronic devices are described herein. In various embodiments, the present technology includes systems and methods for wirelessly connecting a consumer-operated kiosk with an electronic device to facilitate processing (e.g., purchasing) the device. In some embodiments, the present technology includes using a wireless link to identify a device, evaluate a device, resolve device issues to enable purchase of the device, locate a device, etc. Various other aspects of the present technology are described herein.

A wearable device that communicates with a host device can be used to initiate a communication functionality of the host device (e.g., telephone calls, text messages). The wearable device can obtain user input indicating a recipient of the communication and in some instances content for the communication and can provide an instruction to the host device. The host device can use the indicated recipient and content to initiate communication and where applicable to send the content. Recipients and / or content can be selected from predefined lists available on the wearable device.

Disclosed here are various embodiments to evaluate a device and present a price quote to the user by detecting a presence of a device in proximity to a wireless charger. The system can utilize a wireless charger to obtain information about the device while charging the device. The information can include the make of the device. The system can guide the user to navigate the device to provide additional information such as model, memory capacity, unique identifier, and carrier associated with the device. Based on the unique identifier, the system can determine whether device has been stolen. If the device has not been stolen, the system can determine a price based on information obtained from the device and can facilitate presenting the price to the user. If the user accepts the price, the system can facilitate purchase of the device.

Systems, devices, apparatuses, and methods for more effectively protecting a user's private data and information regarding their browsing and other on-line activities. Embodiments remove constraints on an application developer by not requiring them to specify an authentication service provider as part of their application, and instead permit a user to make that choice in a protected and anonymous manner.

A method for enhancing agent-customer interactions in a digital engagement service is provided. The method includes receiving a customer's communication request and initiating an asynchronous process to generate a customer profile summary using a customer identifier. This involves querying a customer data platform (CDP) for customer traits and event data, and creating a prompt for a large language model (LLM) to produce a concise customer profile summary. The summary, stored in a data store, is presented to an available agent through a user interface alongside an invitation to accept the incoming communication request. This streamlined approach equips agents with relevant customer insights promptly, improving service quality and response times.

A method and system for linking a physical artifact to a non-fungible token (NFT) with a digital certificate and / or a digital certificate of authenticity (COA) are disclosed herein. The method and system use multiple attestations along with digital ledger technology to provide a digital certificate of authenticity for an object such as a work of art, collectible, or a non-fungible token (NFT) when the NFT is minted. An extended physical backed token (EPBT) is also generated for the physical artifact.

A content editor or a plugin thereto automatically generates authorship tokens that identify content authored by a human author or an artificial author. The authorship tokens are applied to the work while the work is being produced. Thus, subsequent review of the work can identify regions produced by a human author and other regions produced by an artificial intelligence.

The present disclosure provides methods and systems for generative question answering for construction project document. The method comprises: receiving a question from a user via a message interface, wherein the question is related to information from a plurality of construction project documents; identifying, using one or more large language models, one or more relevant documents from the plurality of construction project documents and one or more chunks relevant to the question, and generating an answer based at least in part on the one or more relevant documents and one or more chunks; and providing the answer and one or more links to the one or more relevant documents in a text message in the message interface.

An example operation may include at least one of retrieving vectors from a vector database, where the vectors include previous communication content between a source device and a service provider device, identifying an item of interest that has not been discussed in the previous communication content based on execution of a large language model (LLM) on the vectors, generating content about the item of interest, and outputting the content about the item of interest to at least one of the source device and the service provider device during an active communication session between the source device and the service provider device.

One or more systems, devices, computer program products and / or computer-implemented methods of use provided herein relate to enhancing LLMs using in-context learning and online knowledge. The computer-implemented system can comprise a memory that can store computer executable components. The computer-implemented system can further comprise a processor that can execute the computer executable components stored in the memory, wherein the computer executable components can comprise a semantic retrieval component that can extract information from an online source, according to a query, to generate an in-context learning input utilized by an LLM for responding to the query.

A communications session with a user may be automated using a language model. The language model may be instructed to select a next action to be performed where the next action may include transmitting a responsive communication to the user or performing an API call. The prompt used to query the language model may include one or more of the following: a representation of text of the communications session, a list of available API calls, instructions to select a next action, a representation of API calls performed, or a representation of API call responses received. The language model may be sequentially queried to continue the communications session by transmitting responsive communications or performing API calls. In some implementations, a prompt template may be used to generate the prompt and a prompt template may be selected using text of the communications session.

A content editor or a plugin thereto automatically generates authorship tokens that identify content authored by a human author or an artificial author. The authorship tokens are applied to the work while the work is being produced. Thus, subsequent review of the work can identify regions produced by a human author and other regions produced by an artificial intelligence.

Systems and methods are provided for a natural language question answering service to provide answers to natural language questions regarding network-based services or computing domains. The natural language question answering service may receive the natural language question from a customer computing device. An aggregator of the natural language question answering service can retrieve passages from search systems based on the question and generate a prompt. A large language model (LLM) of the natural language question answering service may receive the prompt and provide an answer. The answer may be verified by a verifier of the natural language question answering service. Attribution may be applied to the answers and retrieved passages to produce references, inline citations, and similar questions. A watermarking module of the natural language question answering service may watermark the answer if it is verified.

A data processing system implements receiving a plurality of natural language prompts for a language model; storing the prompts in a privacy protecting datastore in which the prompts are inaccessible from outside of the privacy protecting datastore; analyzing the prompts stored to generate embedding vectors representing the plurality of natural language prompts; storing the embedding vectors in the privacy protecting datastore; analyzing the embedding vectors using a clustering algorithm to generate clusters of related embedding vectors in the privacy protecting datastore; generating, for each cluster, theme information summarizing the embedding vectors of the cluster; and storing the theme information associated with each cluster of the plurality of clusters in a second datastore outside of the privacy protecting datastore, the second datastore being accessible for querying the data stored therein.

A disclosed data platform may be configured to access a custom policy developed by a particular client entity that uses the data platform. The custom policy may invoke a query that targets a target dataset ingested from a cloud environment and stored in a data store. The data platform may determine that the custom policy is likely to be of value to one or more other client entities, besides the particular client entity, that also use the data platform. In response to the determining that the custom policy is likely to be of value to the one or more other client entities, the data platform may generate a community policy based on the custom policy. The community policy may be available for use by the one or more other client entities. Corresponding methods, systems, and products are also disclosed.

Disclosed herein is a system that allows for the real-time build out of a virtual environment. The system and methods receive, via a web browser, a user selection of a three-dimensional (3D) model in a virtual environment. The user selection is made during an active user session of the user. Based on receiving the user selection, an editor is launched from within the web browser. The editor is used to modify properties of the 3D model in real-time during the active user session. One or more user inputs are received indicating the properties of the 3D model to be modified. Based on the one or more user inputs, the properties of the 3D model are modified in real-time. The 3D model is rendered to reflect the properties within the virtual environment during the active user session.

A system facilitating authoring of content, the system comprising a plurality of catalogues (aka “data catalogues”) associated in memory with, and storing, in the memory, data regarding, a respective plurality of authorized documents, each having content known to be compliant with at least one regulation; and at least one hardware processor configured to interface with plural end-users and to review at least one new document comprising a new version associated by an individual end-user from among the plural end-users with an individual authorized document from among the plurality of authorized documents, by comparing the new document to the catalogue from among the plurality of catalogues which is associated in memory with said individual authorized document and, accordingly, generating at least one output facilitating editing of the new document for compliance with the regulation / s.

A disclosed method facilitates AI-generation of a customized email per a methodology that significantly reduces the risk of the customized email including hallucinated facts or undesirable personal identity information (PII). The method includes identifying an email template and a recipient identifier that identifies a recipient of the customized email based on user inputs to an email application; mining contextual data stored in association with the recipient identifier; generating a large language model (LLM) prompt based on the email template and the contextual data; providing the LLM prompt as input to a trained large language model (LLM); receiving the customized email as an output from the LLM; and returning the customized email to the email application for display within a user interface.