DOCUMENT SHARING PROTECTION WITH WATERMARK
Granted: September 5, 2024
Application Number:
20240296209
Provided is a computing system for protection against document sharing. The computing system includes a processor having associated memory, the processor being configured to execute instructions using portions of the memory to cause the processor to implement a compliance portal where a policy is established covering a plurality of documents, transmit the policy to a client device having a display screen, and in response to receiving an indication that the client device has triggered the…
RESTRICTING MESSAGE NOTIFICATIONS AND CONVERSATIONS BASED ON DEVICE TYPE, MESSAGE CATEGORY, AND TIME PERIOD
Granted: September 5, 2024
Application Number:
20240297861
A data processing system implements techniques for restricting which notifications and/or conversations are presented on a plurality of user devices associated with a user. Each user device is associated with a device category. The device categories are associated with time category information that associates each of a plurality of time periods with permitted device category information that indicates which categories of user devices associated with the user are permitted to present…
LEVERAGING INFERRED CONTEXT TO IMPROVE SUGGESTED MESSAGES
Granted: September 5, 2024
Application Number:
20240297856
Systems and methods for using a generative artificial intelligence (AI) model to generate a suggested draft reply to a selected message. A message generation system and method are described that use inferred context to improve the suggested draft reply message for the user. Various message data and additional context are obtained and included in a prompt provided to the AI model to improve suggested content. In some examples, the message data and additional context include a message…
METHOD AND SYSTEM OF GENERATING CUSTOMIZED IMAGES
Granted: September 5, 2024
Application Number:
20240296595
A data processing system for requesting a customized image from an image-generating artificial intelligence engine may include a processor and a memory comprising instructions for execution by the processor. The instructions, when executed by the processor, cause the processor to: accept user input from a user, the user input comprising an image; tokenize the image to generate a set of tokens for use by the image-generating artificial intelligence engine; and submit the set of tokens to…
ATTRIBUTION VERIFICATION FOR ANSWERS AND SUMMARIES GENERATED FROM LARGE LANGUAGE MODELS (LLMS)
Granted: September 5, 2024
Application Number:
20240296295
Systems and methods for verifying attribution of quotations, generated by a large language model (LLM), to a source document are disclosed herein. Upon a request to summarize a source document or process a question that is answerable from a document, an LLM prompt is formed with the request or question along with the content of the source document. The LLM prompt is configured to cause an LLM to generate quotes that are intended to be from the source document. The output of the LLM,…
CONFIDENCE ENHANCEMENT FOR RESPONSES BY DOCUMENT-BASED LARGE LANGUAGE MODELS
Granted: September 5, 2024
Application Number:
20240296279
Systems and methods are provided for implementing confidence enhancement for responses by document-based large language models (“LLMs”) or other AI/ML systems. A first prompt is generated based on data items that are previously received or accessed. The first prompt is used by a first LLM or AI/ML system to extract requested information from the data items. One or more citations are generated and presented within a structured object together with a representation of the extracted…
EFFICIENT MULTI-TURN GENERATIVE AI MODEL SUGGESTED MESSAGE GENERATION
Granted: September 5, 2024
Application Number:
20240296278
Systems and methods for using a generative artificial intelligence (AI) model using a multi-turn process to generate a suggested draft reply to a selected message. A first turn of the multi-turn process uses a shorter prompt including at least a portion of the body of the selected message and that requests multiple draft replies from the AI model. The resulting AI-generated draft replies are shortened, summarized, and/or otherwise converted into a plurality of shortened summaries that…
OPTIMIZING DATA TO IMPROVE LATENCY
Granted: September 5, 2024
Application Number:
20240296276
Systems and methods for using a generative artificial intelligence (AI) model to generate a suggested draft reply to a selected message. A message generation system and method are described that optimize input that is provided to the AI model so that it provides the most relevant information. In some examples, input prompts to the AI model are limited in size and latency can be impacted based on the size of the input provided to the AI model. Thus, the method and system identify,…
GUARDRAILS FOR EFFICIENT PROCESSING AND ERROR PREVENTION IN GENERATING SUGGESTED MESSAGES
Granted: September 5, 2024
Application Number:
20240296275
Systems and methods for using a generative artificial intelligence (AI) model to generate a suggested draft reply to a selected message. A message generation system and method are described that use guardrails that prevent unnecessary AI model processing and accidental sending of an AI model-generated draft. In some examples, draft reply-generation is limited to a subset of messages (e.g., focused, non-confidential) and triggering of the draft reply generation is performed only after…
ADVERSE OR MALICIOUS INPUT MITIGATION FOR LARGE LANGUAGE MODELS
Granted: September 5, 2024
Application Number:
20240296219
Systems and methods are provided for implementing adverse or malicious input mitigation for large language models (“LLMs”) or other AI/ML systems. A subset of example pairs of adverse inputs and proper outputs whose inputs are similar to inputs of a current dialogue context is identified. A subset of example pairs of non-adverse inputs and proper outputs whose inputs are similar to the inputs of the current dialogue context may also be identified. The identified subset(s) of similar…
CONVERSATIONAL LARGE LANGUAGE MODEL-BASED USER TENANT ORCHESTRATION
Granted: September 5, 2024
Application Number:
20240296177
Systems and methods are provided for implementing conversational large language model (“LLM”) or other AI/ML-based user tenant orchestration. A first prompt is generated based on natural language (“NL”) input from a user. The first prompt is used by a first LLM or AI/ML system to generate a query to access data items that are stored in a portion of a multitenant data storage system, the portion being accessible by the user. Once accessed and received, the data items are input…
METHODS AND SYSTEMS OF VERIFYING DATA SYNCHRONIZED TO MULTIPLE DATA STORES
Granted: September 5, 2024
Application Number:
20240296155
A data verification agent serves to verify data that is being redundantly stored in both a first data store and a second data store. The data verification agent compares corresponding objects in the first and second data stores to determine any mismatch between the objects. The data verification agent includes a mismatch ignore function causing the agent to skip a comparison of corresponding data objects in the first and second data stores in response to an indication that a mismatch…
SYSTEMS AND METHODS FOR HARDWARE ACCELERATION OF DATA MASKING
Granted: September 5, 2024
Application Number:
20240296133
A field programmable gate array (FPGA) including a configurable interconnect fabric connecting a plurality of logic blocks, the configurable interconnect fabric and the logic blocks being configured to implement a data masking circuit configured to: receive input data including data values at a plurality of indices of the input data; select between a data value of the data values and an alternative value using a masking multiplexer to generate masked data, the masking multiplexer being…
HYBRID WIRE LOCALIZATION LENGTH MEASUREMENT DEVICE
Granted: September 5, 2024
Application Number:
20240295393
A superconductor-semiconductor device is provided, including a hybrid superconductor-semiconductor wire. The superconductor-semiconductor device may further include a hybrid localization length (LL) measurement device including a plurality of contact gates located above the hybrid superconductor-semiconductor wire in a thickness direction. The hybrid LL measurement device may further include a conductance sensor electrically coupled to the plurality of contact gates.
DEVICE AND METHOD FOR TERMINATING OPTICAL FIBRE CABLES
Granted: August 29, 2024
Application Number:
20240288654
A terminator for an optical fibre cable including at least one microstructured optical fibre comprises: a hollow terminating member with a closed end and an opposite open end configured for cooperation with a severed end of an optical fibre cable; and a tubular collar having a first end into which the open end of the terminating member is received in a sealed manner, and an opposite second end to receive the severed end of the optical fibre cable for cooperation with the open end of the…
SEMICONDUCTOR-SUPERCONDUCTOR HYBRID DEVICE, ITS MANUFACTURE AND USES
Granted: August 29, 2024
Application Number:
20240292761
A semiconductor-superconductor hybrid device comprises a semiconductor, a superconductor, and a barrier between the superconductor and the semiconductor. The device is configured to enable energy level hybridisation between the semiconductor and the superconductor. The barrier is configured to increase a topological gap of the device. The barrier allows for control over the degree of hybridisation between the semiconductor and the superconductor. Further aspects provide a quantum…
REPRESENTATIVE MOTION INFORMATION FOR TEMPORAL MOTION PREDICTION IN VIDEO ENCODING AND DECODING
Granted: August 29, 2024
Application Number:
20240292021
Disclosed herein are representative embodiments of generating representative motion information that can be used during processing of a video frame. In one exemplary embodiment disclosed herein, a reference frame comprising a group of blocks is processed, and motion information for the group of blocks is compressed at least by buffering representative motion-vector information and representative reference-frame index information for the group of blocks. The representative reference-frame…
UNIFIED AUDIENCE TARGETING SYSTEM
Granted: August 29, 2024
Application Number:
20240291788
A system for creating a target audience group includes receiving a request from a user interface screen, to create a target audience group from among users of an organization associated with a cloud computing environment, where the request including selected values for a plurality of categories of data associated with the users of the organization. Upon receiving the request; the method creates an audience targeting definition for the target audience group that includes the plurality of…
GENERATING NEW CONTENT FROM EXISTING PRODUCTIVITY APPLICATION CONTENT USING A LARGE LANGUAGE MODEL
Granted: August 29, 2024
Application Number:
20240289360
Systems and methods for generating new content from a machine-learning model. A content generator extracts string content from existing slides of a slide presentation document and generates a text query using the existing slide content as context. The query is directed to a large language model. Additionally, prompt input from a user is received and combined with the context in the query. A response from the large language model is parsed and text output is separated into prospective…
SYSTEMS AND METHODS FOR DEVICE CONFIGURATION USING A CONFIGURATION NORMALIZATION PLATFORM
Granted: August 29, 2024
Application Number:
20240289125
Examples of the present disclosure describe systems and methods for device configuration using a configuration normalization platform. In examples, a system receives, at a device, a configuration request from a first software platform having a first toolset. The configuration request includes a first SCP file in a format that is normalized horizontally with respect to a second software platform having a second toolset that is different from the first toolset. The system parses, based on…
