Abstract: Various methods, apparatuses/systems, and media for automatic real-time identification of dissatisfaction data are disclosed. A receiver receives real-time stream of call transcript data generated during a call or a chat between a customer and an agent. A processor implements a machine learning model that includes predefined complaint data; applies the received call transcript data onto the machine learning model; compares, in response to applying, the call transcript data with predefined complaint data; generates a first similarity score, based on comparing, that identifies how similar the call transcript data is compared to the predefined complaint data; and automatically identifies the call transcript data as a first dissatisfaction data based on determining that the first similarity score is equal to or more than a predetermined threshold value.

Abstract: Example methods and systems for context-based channel recommendation and management are provided. A communication platform accesses a first set of user data associated with a first user on the communication platform and channel data associated with a plurality of chat channels on the communication platform. The communication platform determines one or more recommended chat channels for the first user based on the first set of user data and the channel data. The communication platform provides the one or more recommended chat channels to the first user.

Abstract: Embodiments can relate to a field-programmable gate array having a platform including an interconnect network of configuration blocks. The configuration blocks can include one or more configurable logic blocks (CLBs), one or more connection blocks (CBs), and one or more switch blocks (SBs). Each CLB can include a look-up table (LUT) cell configured to perform a logic operation. Each CB can be configured to connect one or more CLBs to the interconnection network. Each SB can be configured to connect routes between the configuration blocks. One or more or the CBs can include a 1FeFET for a single configuration, one or more of the CBs can include a 2T-2FeFET for a multiple configuration, one or more of the CLBs can include a 1FeFET LUT cell for a single configuration, or one or more of the CLBs can include two 1FeFET LUT cells for a multiple configuration.

Abstract: Systems and methods for integration of anchor information for retrieval augmented generation are provided. A communication platform accesses communication data associated with an enterprise on the communication platform. The communication platform divides the communication data into multiple data chunks. The communication platform generates one or more extended queries for each data chunk of the multiple data chunks using a generative AI model. The communication platform receives a user query, and identifies, from the multiple data chunks, one or more relevant data chunks for the user query at least by comparing the user query with the one or more extended queries associated with each data chunk of the multiple data chunks. The communication platform provides an answer to the user query based on the one or more relevant data chunks.

Abstract: Disclosed are compute-in-memory devices that perform charge-domain MAC operations in a NAND-style string of FeFETs. Memory cells are coupled to word lines and bit lines, each FeFET storing a computational weight as a non-volatile polarization state established by polarization switching of a ferroelectric layer, the polarization state altering channel conduction and modulating gate capacitance. A selected read cell receives an input signal on a bit line, and a neighboring memory cell provides a sense node at its word line formed by the neighboring cell's gate capacitance. A control circuit biases the read and neighboring cells so that application of the input signal to the read cell conditionally transfers charge to the neighboring cell's gate capacitance according to the combination of the input and the read cell's polarization-dependent conduction state. A readout circuit senses an electrical quantity to yield a MAC compute result in the charge domain.

Abstract: Non-volatile memory devices and methods are disclosed. A NAND memory string can include ferroelectric field-effect transistors each having a ferroelectric control gate and a separate non-ferroelectric pass gate. A program or read bias can be applied to the ferroelectric control gate of a selected transistor, while a pass bias is applied to the non-ferroelectric pass gate of at least one unselected transistor with its ferroelectric control gate held at a reference potential. This arrangement reduces depolarization field effects at high-threshold states and screens applied fields at low-threshold states, thereby maintaining stored polarization and reducing pass disturbance.

Abstract: A nonvolatile memory device is disclosed that incorporates a FeFET having a gate stack with a ferroelectric dielectric layer positioned below a charge trapping layer. During programming, polarization switching in the ferroelectric layer drives charge injection from the gate into the overlying trapping layer. The trapped charge combines with the ferroelectric polarization to shift the threshold voltage of the device. A capping dielectric may be included above the trapping layer to improve charge retention. This gate-side charge injection mechanism supports efficient programming while maintaining a compact vertical stack suitable for integration into high-density memory architectures such as vertical NAND.

Abstract: Techniques for implementing hybrid retrieval augmented generation for rich document queries using a large language model (“LLM”) are disclosed. In an example method, a computing system receives documents which are added to databases. The computing system receives a query, from which tokens are generated. The computing system determines a first ranking of the documents using a probabilistic ranking method and a second ranking of the documents in response to a vector database query using an embedded representation. The computing system determines a third ranking of the documents based on the first ranking and the second ranking. The computing system selects top documents from the third ranking. The computing system determines a knowledge graph based on the top documents. The computing system outputs the query, the top documents, and at least a portion of the knowledge graph to an LLM. The computing system receives and outputs a response.

Abstract: A CiM architecture is disclosed, including memory cells each having a nonvolatile memory transistor and a capacitor connected in series between a bit line and a sense node. The transistor is configured to store a programmable state corresponding to a weight value and to selectively conduct based on a control voltage applied to a gate terminal. During a charging phase, the capacitor accumulates charge based on the conduction state of the transistor and an input voltage applied to the bit line. During a compute phase, the sense node exchanges charge with one or more other sense nodes in the array, such that a resulting voltage reflects an analog output of a MAC operation. The disclosed architecture can support binary and/or multi-bit computation and, in some cases, can utilize FeFETs or other nonvolatile devices to perform in-memory operations with improved variation resilience and energy efficiency.

Abstract: Methods and systems for optimizing a product assortment, and managing product fulfillment, are disclosed. One method includes utilizing a model trained on item data to identify item substitution pairs within an item category of an item assortment, the item substitution pairs being identified as having a substitutability score above a predetermined threshold. The method further includes applying an assortment optimization model to generate an assortment recommendation for the item category at an identified retail location. A request for an item not included in the assortment recommendation may result in suggestion of an identified substitutable item from among the item substitution pairs.

Abstract: Systems and methods of evaluating and fine-tuning a generative AI tool on a communication platform. The communication platform accesses a dataset comprising a user query and a response generated by an AI-based query system. The communication platform evaluates the response with respect to the user query using multiple AI-based scoring models to obtain multiple evaluation results. In response to determining that the multiple evaluation results are inconsistent, the communication platform evaluates the response with respect to the user query using a reference large language model (LLM) to provide a reference evaluation result. In response to determining that the reference evaluation result is decisive, the communication platform classifies, based on the reference evaluation result, the dataset to a data category of one or more data categories. The communication platform fine-tunes the AI-based query system based on a group of datasets in the data category.

Abstract: Systems and methods of knowledge graph construction are provided. A communication platform accesses communication data on the communication platform associated with an enterprise. The communication platform extracts a plurality of keywords from the communication data. The communication platform creates a knowledge graph comprising a plurality of nodes. The plurality of nodes comprises a plurality of keyword nodes. The communication platform identifies, using a graph random walk algorithm, one or more keyword nodes in the knowledge graph related to a first keyword node to link the first keyword node with the one or more keyword nodes. The communication platform determines a first keyword node embedding for the first keyword node by aggregating information associated with at least the first keyword node and the one or more keyword nodes using a graph convolutional network algorithm. The communication platform attaches the first keyword node embedding to the first keyword node in the knowledge graph.

Abstract: Example methods and systems for context-based channel recommendation and management are provided. A communication platform creates a user embedding representation for a user based on a set of user data associated with the user on a communication platform. The communication platform creates a plurality of channel embedding representations for a plurality of chat channels on the communication platform based on channel data associated with the plurality of chat channels. The communication platform determines a similarity score corresponding to each of the plurality of chat channels with respect to the user based on the user embedding representation and the plurality of channel embedding representations to obtain a plurality of similarity scores. The communication platform generates a recommendation of one or more chat channels to the user based on the plurality of similarity scores. The communication platform provides the recommendation of one or more chat channels to the user.

Abstract: Embodiments method for configuring a data structure in a nonvolatile memory (NVM) module that includes at least one memory cell. Each memory cell can have two transistors coupled to each other such that a logic value is stored in a complementary manner. The method can involve encrypting the at least one memory cell by generating a cipher text (CT) by performing an XOR operation on plain text (PT) stored in the at least one memory cell, and performing the XOR operation on a corresponding key. In addition, or in the alternative, the method can involve decrypting cipher text (CT) of the at least one memory cell by applying a read voltage pattern to the two transistors, the read voltage pattern being VR/0 or 0/VR based on a key.

Abstract: Embodiments can relate to techniques for sensing capacitor polarization in a random access memory (RAM) cell by: applying a read gate bias to a transistor; allowing or causing ferroelectric polarization (PFE) of a capacitor to set a threshold voltage (VTH); and performing a read operation by sensing polarization in a capacitor. Performing the read operation can occur in a quasi-nondestructive manner due to the structure of the RAM cell, which can include: plural capacitors connected to node 1, each individual capacitor also connected to an individual write bit line (WBL); a write transistor (TW) connected to: node 1, a write word line (WWL), and a write plate line (WPL); and a read transistor (TR) connected to: node 1, a read bit line (RBL), and a read source line (RSL). The RAM cell allows for performing plural read operations without a write-back operation to restore polarization in a capacitor.

Abstract: Methods and systems for optimizing a product assortment, and managing product fulfillment, are disclosed. One method includes utilizing a model trained on item data to identify item substitution pairs within an item category of an item assortment, the item substitution pairs being identified as having a substitutability score above a predetermined threshold. The method further includes applying an assortment optimization model to generate an assortment recommendation for the item category at an identified retail location. A request for an item not included in the assortment recommendation may result in suggestion of an identified substitutable item from among the item substitution pairs.

Abstract: Techniques are disclosed for implementing a multi-agent framework for generating responses to queries. In an example method, a computing system receives, from a client device, a query. The computing system determines one or more query portions based on the query. The computing system determines a domain agent for each query portion, in which each domain agent is configured to determine execution steps for one or more executors to cause the executors to generate a response to the query portion. The computing system provides first information about the one or more query portions and the determined execution steps to the respective determined domain agents. The computing system receives, from the one or more domain agents, response portions. The computing system generates the response using the response portions. The computing system outputs, to the client device, the response to the query.

Abstract: Various methods and processes, apparatuses/systems, and media for data processing are disclosed. A processor accesses a database that stores a plurality of historical data and input data corresponding to a derivative instrument; implements an artificial intelligence deep learning model; trains the artificial intelligence deep learning model with the historical data and the input data corresponding to the derivative instrument for time-series data prediction; learns, in response to training, volatility surface deformation data over time corresponding to the derivative instrument; calculates spot sensitivity data of the derivative instrument based on the volatility surface deformation data output from the artificial intelligence deep learning model; displays the spot sensitivity data onto a user interface; and receives user input via the user interface to conduct a transaction with respect to the derivative instrument.

Abstract: Techniques are disclosed relating to a multi-agent search client. In an example method, a search agent application receives a query. The search agent application determines, using a search agent, one or more agents to each execute a portion of the query. The search agent application outputs, to a domain agent, a portion of the query. The search agent application determines, using the domain agent, an execution step based on the portion of the query and information about an executor. The executor generates instructions based on the execution step that are configured to generate a response to the execution step and outputs a command to execute the instructions. The executor then outputs, to the first domain agent, the response to the execution step. The search agent application outputs, using the search agent, a response to the query based on the response to the execution step.

Abstract: Techniques are disclosed relating to a multi-agent search client. In an example method, a search agent application receives a query. The search agent application determines, using a search agent, one or more agents to each execute a portion of the query. The search agent application outputs, to a domain agent, a portion of the query. The search agent application determines, using the domain agent, an execution step based on the portion of the query and information about an executor. The executor generates instructions based on the execution step that are configured to generate a response to the execution step and outputs a command to execute the instructions. The executor then outputs, to the first domain agent, the response to the execution step. The search agent application outputs, using the search agent, a response to the query based on the response to the execution step.