Abstract: Systems and methods for using large language models (LLM) to generate and edit content items are described. The methods generate a template of a content item based on user input and populate the template based on data obtained from querying an LLM-generated semantic graph that includes data sources to which a user has authorized access. Once generated, one or more sources provided are used for editing the identified text of the generated content item. If multiple sources are provided, they are weighted based on factors and their priority is determined. Raw data from the provided source(s) are indexed. An LLM using the identified text as an input, queries the index to identify data relevant for editing the identified text. The relevant data is then used to edit, rewrite and/or regenerate the identified text and make the unedited text in the content item coherent with the edited text.

Abstract: Systems and methods described receive user input or query at a user interface associated with a large language model (LLM) to perform a task. The user intent and persona are determined based on the user input and other user related data. An LLM automatically generates a workflow consisting of a plurality of steps for performing the task received. Each step of the workflow is mapped to a building block that is to be used for processing the step of the workflow. Selection of the building blocks is based on a plurality of factors, including relevancy, complexity, cost, and accuracy. One of the building blocks used is to perform an application programming interface (API) call to one or more external applications for executing a step of the workflow. Parameters for the API call may be obtained from a generated catalog. Results from the workflow may be customized based on the persona.

Abstract: Systems and methods described receive user input or query at a user interface associated with a large language model (LLM) to perform a task. The user intent and persona are determined based on the user input and other user related data. An LLM automatically generates a workflow consisting of a plurality of steps for performing the task received. Each step of the workflow is mapped to a building block that is to be used for processing the step of the workflow. Selection of the building blocks is based on a plurality of factors, including relevancy, complexity, cost, and accuracy. One of the building blocks used is to perform an application programming interface (API) call to one or more external applications for executing a step of the workflow. Parameters for the API call may be obtained from a generated catalog. Results from the workflow may be customized based on the persona.

Abstract: Systems and methods for using large language models (LLMs) to analyze category specific workflows for generating an optimized workflow that can be used in live conversations to provide a response are described. The methods include categorizing a plurality of projects into specific categories. The actions performed by agents for the plurality of projects are translated into workflows. The workflows are analyzed based on optimization factors and clustering options, such as including redundancies in workflow steps, using alternative solutions to a workflow step, determining whether any escalation performed is justified and if so, adopting escalation related steps. The workflows are consolidated and optimized into an optimized workflow that is tested and verified, and then used in a live conversation.

Abstract: Systems and methods for using large language models (LLM) for generating personalized business content items, such as documents and presentations, by generating content item templates having sections and automatically populating content in its sections by leveraging LLM generated semantic graphs are described. A request to generate a content item is received. A table of contents template having a plurality of nested sections is generated based on the received request. Leveraging an LLM, a semantic graph that semantically organized data from a plurality of enterprise private data sources is generated. A query to the semantic graph for the most fine-gained section of the template is made to obtain relevant indexed data. A write operation is performed to write the data in the most fine-gained section. The query and write operation for each section in the template based on the section's hierarchy is made until all template sections are completed.

Abstract: Systems and methods for using large language models (LLM) to generate and edit content items are described. The methods generate a template of a content item based on user input and populate the template based on data obtained from querying an LLM generated semantic graph that includes data sources to which a user is authorized access. Once generated, on or more sources provided are used for editing the identified text of the generated content item. If multiple sources are provided, they are weighted based on factors and their priority is determined. Raw data from the provided source(s) is indexed. An LLM using the identified text as an input, queries the index to identify data relevant for editing the identified text. The relevant data is then used to edit, rewrite and/or regenerate the identified text and make the other unedited text in the content item coherent with the edited text.

Abstract: Systems and methods for using simple and unstructured conversational input, which is a part of an interactive conversation between a user and a system, to automatically generate a workflow for performing an enterprise task is described. The methods include generating a configurable application that includes the workflow, which when executed, performs the enterprise task. A simple conversational input, which is unstructured data, is processed to determine a task to be performed and a persona that will be performing such a task. Deep learning techniques are applied to leverage related data in the same domain from a knowledge base, that is associated with a foundational transformer model. A workflow involving a plurality of steps is automatically generated in-real time, based on the leveraged learning, while the interactive conversation is still in progress. A user interface that displays both the generated workflow and the input conversation is generated.

Abstract: Systems and methods for training and using large language models to respond to queries and cascading to new models when their performance falls below a threshold during the response generation cycle are described. The methods involve receiving and analyzing a query using heuristics to determine the query's categories and a level of granularity at which its response is to be evaluated. Selecting a language model based on the query analysis and during the generation of the response, evaluating the model's performance for its ability to predict the next segment in a response. The methods score the evaluation and use the score to determine whether the language model's performance exceeds a confidence threshold. If it does not, then during the response is being generated, e.g., at a point before the response generation is completed, cascading from the model to a different model that can perform at a higher confidence level.

Abstract: Systems and methods for using enterprise data to train and generate enterprise related large language models (ELLMs) and selectively combining the generated ELLMs and publicly available LLMs to generate a customized LLM for automatically answering queries are disclosed. Enterprise data is obtained, classified, and curated to generate training data that is used to generate a plurality of contextually distinguished ELLMs. The ELLMs differ based on their relation to various enterprise functions, departments, and level of authorized access to enterprise confidential data. When a question is received from a user, both the identity of the user and context of the question are used to select one or more ELLMs and LLMs for processing the question. The processing involves sequential selection of a plurality of ELLMs to process the question, blend the results from the processing, and use the results as input into an ensemble model to obtain a final answer.

Abstract: An example system includes a transceiver. The transceiver communicates multicast frames to a plurality of client devices in a multicast group. The system further includes a controller. The controller determines that a predetermined time has passed since the transceiver most recently sent a unicast transmission to one of the plurality of client devices. The controller instructs the transceiver to transmit a unicast frame to the one of the plurality of client devices. The controller computes a data rate for the one of the plurality of client devices based on the transmission of the unicast frame to the one of the plurality of client devices.

Abstract: An example system includes a transceiver. The transceiver communicates multicast frames to a plurality of client devices in a multicast group. The system further includes a controller. The controller determines that a predetermined time has passed since the transceiver most recently sent a unicast transmission to one of the plurality of client devices. The controller instructs the transceiver to transmit a unicast frame to the one of the plurality of client devices. The controller computes a data rate for the one of the plurality of client devices based on the transmission of the unicast frame to the one of the plurality of client devices.

Abstract: Described herein are techniques for performing a channel scan based on a mobility state of a device. The mobility state of a device relative to an access point may be determined using time-of-flight information. A channel scan may be performed based on the mobility state determination.

Abstract: An example system includes a transceiver. The transceiver communicates multicast frames to a plurality of client devices in a multicast group. The system further includes a controller. The controller determines that a predetermined time has passed since the transceiver most recently sent a unicast transmission to one of the plurality of client devices. The controller instructs the transceiver to transmit a unicast frame to the one of the plurality of client devices. The controller computes a data rate for the one of the plurality of client devices based on the transmission of the unicast frame to the one of the plurality of client devices.

Abstract: A method of determining the location of a mobile computing device includes measuring a first time of flight (ToF) value and a first value of received energy of direct path (EDP) (PR) of a number of acknowledgement (ACK) packets received in response to a number of first probe packets sent to a first mobile device. The method calculates a preliminary distance value (d0) using a ToF-based distance equation, selects an ACK packet with a distance closest to d0 from the number of ACK packets, calculates an initial path loss exponent (?0) of the selected ACK packet sample using d0 and PR. With the access point, the method also includes measuring a second PR for a second number of ACK packets received in response to a number of second probe packets sent to the first mobile device, calculates a supplemental distance value using an EDP-based distance equation and the ?0, and determines the location of the mobile device using multilateration and the supplemental distance value.

Abstract: Described herein are techniques for beamforming a wireless signal to a harvesting device. In an example, a method to increase available energy to a harvesting device is performed by a WiFi transmitting device. The WiFi transmitting device determines a preferred wireless path to the harvesting device using input from a proxy device. The WiFi transmitting device then beamforms a WiFi signal to the harvesting device along the preferred wireless path.

Abstract: In an example, a method for correcting time-of-flight measurements includes receiving a plurality of time-of-flight measurements and determining whether the time-of-flight measurements relate to a strong signal client, a weak signal client, or a preferred signal client. If the time-of-flight measurements relate to a strong signal client or a weak signal client, the method determines whether the time-of-flight measurements constitute two distinct distributions. If the time-of-flight measurements constitute two distinct distributions, a mean value for each distribution is determined. If the mean values differ by a predetermined time delay attributable to automatic gain control processing, the time-of-flight measurements corresponding to the distribution having the lower mean value are used. If the mean values differ by less than the predetermined time delay attributable to automatic gain control processing, the time-of-flight measurements corresponding to both distributions are used.

Abstract: A method of determining the location of a mobile computing device includes measuring a first time of flight (ToF) value and a first value of received energy of direct path (EDP) (PR) of a number of acknowledgement (ACK) packets received in response to a number of first probe packets sent to a first mobile device. The method calculates a preliminary distance value (d0) using a ToF-based distance equation, selects an ACK packet with a distance closest to d0 from the number of ACK packets, calculates an initial path loss exponent (?0) of the selected ACK packet sample using d0 and PR. With the access point, the method also includes measuring a second PR for a second number of ACK packets received in response to a number of second probe packets sent to the first mobile device, calculates a supplemental distance value using an EDP-based distance equation and the ?0, and determines the location of the mobile device using multilateration and the supplemental distance value.

Abstract: Example implementations relate to determining a location using time difference of arrival (TDOA). For example, a computing device may include a first sensor to receive a signal at a first time, where the signal is generated by a user contact at a particular location on a keyboard associated with the computing device. The computing device also includes a second sensor to receive the signal at a second time and a third sensor to receive the signal at a third time. The computing device may also include a processor. The processor may calculate a set of TDOAs associated with the first time, the second time, and the third time. The processor may determine the particular location of the user contact using a triangulation based on the set of TDOAs and may identify a character on the keyboard, where the character is associated with the particular location.

Abstract: An example communications device includes communications circuitry and control circuitry. The communications circuitry may wirelessly communicate with client devices. The control circuitry may determine signal-to-interference-plus-noise ratios (SINRs) for the client devices based on compressed client-side channel state information received from the client devices. The control circuitry may assign the client devices to multi-user-multiple-input-multiple-output (MU-MIMO) groups based on the SINRs.

Abstract: Examples herein disclose capturing a wifi signal from a computing device corresponding to a computing accessory and harvesting energy from the captured wifi signal. The examples power the computing accessory based on the harvested energy.