Entefy Inc.

Brienne Ghafourifar

Alston Ghafourifar

Mehdi Ghafourifar

Neil Achtman

Philip Nathan Greenberg

Improved intelligent personal assistant (IPA) software agents are disclosed that are configured to interact with various people, service providers, files, and/or smart devices. More particularly, this disclosure relates to an improved Natural Language Processing (NLP) Intent Determination Service (IDS) that is able to determine the likely best action to take in response to generic user commands and queries. The disclosed NLP IDS automatically selects valid (or potentially valid) API paths (e.g., sequence of API calls) to produce desired actions. Associated system actions and known API sequencing rules may then be used to process the incoming user command or query. A feedback loop is also disclosed to identify newly available APIs and success criteria for selected API paths. Discovery of API paths may be performed using predefined information, monitored information, programmatically determined interfaces, and programmatically tested interfaces. A directed graph model may be used to represent potential API paths.

Automatic application program interface (API) selector for unsupervised natural language processing (NLP) intent classification

This disclosure relates to systems, methods, and computer readable media for performing multi-format, multi-protocol message threading in a way that is most beneficial for the individual user. Users desire a system that will provide for ease of message threading by 'stitching' together related communications in a manner that is seamless from the user's perspective. Such stitching together of communications across multiple formats and protocols may occur, e.g., by: 1) direct user action in a centralized communications application (e.g., by a user clicking 'Reply' on a particular message); 2) using semantic matching (or other search-style message association techniques); 3) element-matching (e.g., matching on subject lines or senders/recipients/similar quoted text, etc.); and 4) “state-matching” (e.g., associating messages if they are specifically tagged as being related to another message, sender, etc. by a third-party service, e.g., a webmail provider or Instant Messaging (IM) service).

System and method of context-based predictive content tagging for segmented portions of encrypted multimodal data

A system and method for transforming location-based data queries into temporal domain by leveraging a location-to-time knowledge conversion graph. In some systems which contain diverse sets of data objects, only certain objects may contain explicit location data, while others may not. Therefore, queriability of this diverse data by location properties would likely yield incomplete results. In some embodiments, this method allows for the transformation and augmentation of a given data query containing location-based filtering properties into a time-region-based lookup, wherein a given location has been assigned to a time region in the given data graph and all data events within that time region may be augmented with location metadata automatically in the knowledge graph. Over time, a system utilizing these embodiments can offer comprehensive location-based data services and insights with a diverse set of data objects that exists and not all objects contain explicit location information.

Temporal transformation of location-based queries

Disclosed are apparatuses, methods, and computer readable media for improved multi-datatype searching comprising receiving a search query of a first datatype, generating a vector of the first datatype describing the search query, expanding the vector of the first datatype to include a second datatype vector, wherein the second datatype vector is different from the first datatype but may be conceptually equivalent, and wherein the second datatype is associated with the vector of the first datatype, and performing a search based on the first datatype and a search on the second datatype.

System and method for unifying feature vectors in a knowledge graph

This disclosure relates to systems, methods, and computer readable media for performing multi-format, multi-protocol message threading in a way that is most beneficial for the individual user. Users desire a system that will provide for ease of message threading by 'stitching' together related communications in a manner that is seamless from the user's perspective. Such stitching together of communications across multiple formats and protocols may occur, e.g., by: 1) direct user action in a centralized communications application (e.g., by a user clicking 'Reply' on a particular message); 2) using semantic matching (or other search-style message association techniques); 3) element-matching (e.g., matching on subject lines or senders/recipients/similar quoted text, etc.); and 4) 'state-matching' (e.g., associating messages if they are specifically tagged as being related to another message, sender, etc. by a third-party service, e.g., a webmail provider or Instant Messaging (IM) service).

System and method of context-based predictive content tagging for encrypted data

A system and method for transforming location-based data queries into temporal domain by leveraging a location-to-time knowledge conversion graph. In some systems which contain diverse sets of data objects, only certain objects may contain explicit location data, while others may not. Therefore, queriability of this diverse data by location properties would likely yield incomplete results. In some embodiments, this method allows for the transformation and augmentation of a given data query containing location-based filtering properties into a time-region-based lookup, wherein a given location has been assigned to a time region in the given data graph and all data events within that time region may be augmented with location metadata automatically in the knowledge graph. Over time, a system utilizing these embodiments can offer comprehensive location-based data services and insights to a given system or user wherein a diverse set of data objects exists and not all objects contain explicit location information.

System and method of message threading for a multi-format, multi-protocol communication system

Disclosed are apparatuses, methods, and computer readable media for improved message presentation to a user with respect to correlation of messages in a multi-participant message thread. Conversational awareness may be determined by analyzing contents of individual messages and assigning them to an existing context or creating a new context. Association of messages to contexts allows for grouping related messages related to their subject matter. Further, analysis of individual users within a multi-party communication stream (e.g., a thread with a group of participants) can be used to report previous and predict future user activity of a specific user. Groups of different sizes have been determined to sometimes have different participation dynamics. For example, people communicate differently in small groups versus large groups and within a given group, individual participation dynamics can be further analyzed. Disclosed systems learn and leverage this communication dynamic.

Methods and systems to support adaptive multi-participant thread monitoring

Disclosed are apparatuses, methods, and computer readable media for improved intelligent personal assistant (IPA) software agents that are configured to interact with various people, service providers, and/or smart devices across multiple connection protocols, communications formats, and communication protocols in a seamless and more accurate fashion. More particularly, but not by way of limitation, this disclosure relates to apparatuses, methods, and computer readable media for an improved Message Understanding Service (MUS) that is able to match generic user commands and queries (i.e., commands and queries that are not explicitly directed to a particular service endpoint or smart device) with the service endpoint(s) that have the greatest confidence level of being able to handle the generic command or query.

Distributed natural language message interpretation engine

This disclosure relates to systems, methods, and computer readable media for performing multi-format, multi-protocol personalized searching in a manner that is most beneficial for the individual user. Personalized searching can be achieved by obtaining a plurality of data objects for a first user. The data objects can exist in a wide variety of formats and can be received via a number of protocols. One or more message objects can be created for each of the data objects, according to a standardized format and stored. The universal message objects can be indexed in a manner that is personal to the user, and in accordance with one or more parameters that can be updated on an ongoing or periodic basis, in accordance with the actions of the user, or any combination thereof.

Systems and methods for multi-protocol, multi-format universal searching

Techniques disclosed herein decouple a document's structure from its general content wherein the structure is retained in plaintext (both at a client device and in a server system) and the data is retained in cyphertext, and where the cloud-based server system is not tasked with the saving or management of the relevant cryptographic keys. Because the network- or cloud-based server system has 'zero-knowledge' about the document's data content or the relevant cryptographic keys, an attack on the server system does not put the security of the document's data at risk. In addition, the network- or cloud-based server system may be used to perform the computationally intensive tasks of converting the document between a first format (often associated with a full-function document processing application not supported by the client device) and a second format (easily displayed and manipulated by a client device).

Growing community of inventors

Los Altos Hills, CA, United States of America

Brienne Ghafourifar