Abstract: Follow ups to user queries are generated in text-to-database query conversion services based on context provided by generated database queries and/or database query execution results. A query generation service extracts an entity type(s) from a database query generated from a user query and, if applicable, from the execution results. The query generation service retrieves a user query template(s) and corresponding database query template(s) for a same table of a target database as the database query and have parameters of the same types as the extracted entity type(s). The query generation service populates the parameter(s) of each user query template and database query template with an entity name(s) that correspond to the entity type(s) and were extracted from the database query and/or database query execution result. The populated user query templates are provided in response to the user query as follow up queries.

Abstract: Techniques for machine learning for prioritizing traffic in multi-purpose inline cloud analysis (MICA) to enhance malware detection are disclosed. In some embodiments, a system, a process, and/or a computer program product for machine learning for prioritizing traffic in multi-purpose inline cloud analysis (MICA) to enhance malware detection includes processing a set of data for network security analysis to extract a file; determining that the file is to be offloaded to a cloud security entity for security processing based at least in part on a prefilter model that is implemented as a machine learning model; forwarding the file to the cloud security entity using a multi-purpose inline cloud analysis (MICA) channel; and performing an action in response to receiving a verdict from the cloud security entity.

Abstract: The present application discloses a method, system, and computer system for classifying stream data at an edge device. The method includes obtaining a stream of a file at the edge device, aligning a predetermined amount of data in chunks associated with the stream of the file, processing a plurality of aligned chunks associated with the stream of the file using a machine learning model, and classifying, at the edge device, the file based at least in part on a classification of the plurality of aligned chunks.

Abstract: A recording method and device uses a low-power-consumption recording system; an operation mode of the low-power-consumption recording system is configured, where the operation mode includes a first-stage operation mode, a second-stage operation mode, and a third-stage operation mode; switching is performed to a current operation mode based on a trigger condition of each operation mode; and power-on/off processing logic of each unit in the low-power-consumption recording system is scheduled based on the current operation mode, to perform video recording. Therefore, energy consumption is optimized, a continuous video monitoring capability is maintained, and a missed recording problem is resolved when a camera with a battery triggers and starts video recording through heat source sensing.

Abstract: The present application provides an inductor structure, a circuit board and an electronic device. The inductor structure includes a magnetic core column and a wire. The magnetic core column includes a first part, a second part and a third part arranged sequentially along a first direction, the first part has a first side wall facing away from the second part, and the third part has a second side wall facing away from the second part. The wire is wound around the magnetic core column and is configured to be electrically connected to the circuit board.

Abstract: The present disclosure provides a method and system for predicting effluent ammonia nitrogen (NH4—N) and an electronic device. The method includes: obtaining data to be tested; and inputting the data to be tested into a trained deep echo state network, to obtain predicted NH4—N concentration. A method for establishing the deep echo state network includes: establishing an original network, where the original network includes a plurality of input variables and reservoirs, and a principal component analysis (PCA) mapping layer is added between adjacent ones of the reservoirs; initializing the original network to obtain an initialized network; performing parameter optimization on the initialized network by a matrix generation method of singular value decomposition and a competitive swarm optimizer (CSO) algorithm, to obtain an optimized network; and training and testing the optimized network, to obtain the trained deep echo state network.

Abstract: An aerosol-generating device includes: a housing having a liquid storage cavity for accommodating an aerosol-generating substrate; a metal element arranged outside the liquid storage cavity; a static electricity generating assembly including a positive terminal and a negative terminal, one of the positive terminal and the negative terminal being electrically connected to the metal element so as to cause a part of the aerosol-generating substrate that is close to the metal element in the liquid storage cavity to be charged by electrostatic induction when the static electricity generating assembly is electrified; and a vaporization sheet, that, when electrified, vaporizes the charged aerosol-generating substrate to generate a charged aerosol.

Abstract: A pipeline performs automated generation of database queries for a database and corresponding questions comprising natural language text. The pipeline generates database query templates based at least partly on a schema of the database and populates the query templates based on values identified from the records sampled from the database to generate valid database queries. The pipeline then generates abstract representations of each of the generated database queries and, for each abstracted database query, prompts a language model to generate a corresponding question in natural language. The pipeline prompts another language model to evaluate similarity of each abstracted database query and corresponding natural language question. The natural language questions and database queries associated with the corresponding abstractions that are sufficiently similar are provided for use.

Abstract: Techniques for machine learning for prioritizing traffic in multi-purpose inline cloud analysis (MICA) to enhance malware detection are disclosed. In some embodiments, a system, a process, and/or a computer program product for machine learning for prioritizing traffic in multi-purpose inline cloud analysis (MICA) to enhance malware detection includes processing a set of data for network security analysis to extract a file; determining that the file is to be offloaded to a cloud security entity for security processing based at least in part on a prefilter model that is implemented as a machine learning model; forwarding the file to the cloud security entity using a multi-purpose inline cloud analysis (MICA) channel; and performing an action in response to receiving a verdict from the cloud security entity.

Abstract: Techniques for a neural architecture for explainable classification (XCLS) with natural language justification and explicit saliency detection are disclosed. In some embodiments, a system/process/computer program product for a neural architecture for XCLS with natural language justification and explicit saliency detection includes generating a classifier (e.g., a neural network that co-trains the discriminator for security classification and the generator for natural language explanation) that is applied to perform the following: (1) force an explicit selection of salient input regions and (2) co-train a discriminator for security classification and a generator for natural language explanation with shared weights; applying the discriminator, the generator (e.g.

Abstract: The present disclosure discloses a denoising method and a system for preserving amplitude variation with offset (AVO) features of pre-stack seismic data. The method includes: acquiring seismic wave data at at least one receiving point through a seismic signal acquisition device, and storing the seismic wave data in a memory; in response to ending of an acquisition operation of the seismic signal with the seismic signal acquisition device, determining, based on the seismic wave data in the memory, pre-denoising angle gather data through a processing device; and obtaining and outputting a denoised angle gather signal through inputting the pre-denoising angle gather data to a denoising device and performing denoising processing on the pre-denoising angle gather data based on the denoising device.

Abstract: The present disclosure provides a method, apparatus and system for monitoring ultra-high frequency partial discharge of a hydro-generator, and belongs to the technical field of hydro-generator partial discharge monitoring. The method includes: cleaning a partial discharge pulse sequence using a cleaning threshold to obtain a valid pulse sequence; performing redundant data filtering on each data unit divided from the valid pulse sequence to obtain a first target pulse sequence for short-period partial discharge monitoring; determining sub-sequences that are partial discharge events from the valid pulse sequence, forming a second target pulse sequence after associating an amplitude statistical feature of the sub-sequences, and storing the second target pulse sequence.

Abstract: A knowledge base is built, maintained, and utilized for responding to user queries. The knowledge base is populated with queries and corresponding answers that have been generated based on prompting a foundation model with documents included in a datastore used for RAG. Embeddings of the queries are generated and stored in the knowledge base with their corresponding query-answer pairs. To manage changes to the documents in the datastore, updates, deletions, and/or additions to documents in the datastore are periodically identified, and the query-answer pairs that are associated with changes to documentation can be updated accordingly. As a support service receives user queries, the support service searches the knowledge base for queries that are sufficiently similar to the user query based on comparing the associated embeddings. The support service generates a response to the user query based on the answer that corresponds to the most similar query in the knowledge base.

Abstract: A recording method and device uses a low-power-consumption recording system; an operation mode of the low-power-consumption recording system is configured, where the operation mode includes a first-stage operation mode, a second-stage operation mode, and a third-stage operation mode; switching is performed to a current operation mode based on a trigger condition of each operation mode; and power-on/off processing logic of each unit in the low-power-consumption recording system is scheduled based on the current operation mode, to perform video recording. Therefore, energy consumption is optimized, a continuous video monitoring capability is maintained, and a missed recording problem is resolved when a camera with a battery triggers and starts video recording through heat source sensing.

Abstract: Semiconductor structure and fabricating methods are provided. In some implementations, a disclosed semiconductor structure comprises a lower semiconductor layer, an upper semiconductor layer, and an insulating layer between the lower semiconductor layer and the upper semiconductor layer. A first thickness of the upper semiconductor layer in a first region is greater than a second thickness of the upper semiconductor layer in a second region.

Abstract: Detection of malicious files is disclosed. A set comprising a plurality of sample classification models is received and stored. A determination is made that n-gram analysis should be performed on a sequence of received packets associated with a received file. Performing the n-gram analysis includes using a determined filetype associated with the sequence of received packets to select at least one stored sample classification model included in the set for use in performing the n-gram analysis. A determination is made that the received file is malicious based at least in part on the n-gram analysis of the sequence of received packets. In response to determining that the file is malicious, propagation of the received file is prevented.