Abstract: The invention provides an electrostatic air purifier, including a housing, a high-voltage circuit control module, an electrostatic generation module, and a collection module. The high-voltage circuit control module is fixed on an outside wall of the housing. Three fixing holes are formed on the housing. The high-voltage circuit control module includes three conductive assemblies, and the three conductive assemblies respectively extend into an interior of the housing from the fixing holes. An insulating sleeve is sleeved on the conductive assembly, and the insulating sleeve abuts against a hole wall of the fixing hole. One of the conductive assemblies is connected to the electrostatic generation module, and the other two conductive assemblies are connected to the collection module. An insulating sleeve is sleeved on the conductive assembly, and the insulating sleeve abuts against the hole wall of the fixing hole, thereby achieving isolation between the housing and the conductive assembly.

Abstract: Techniques for handling natural language query processing are described. In some examples, semantic meanings of words are determined during the natural language query processing. These semantic meanings are generated from metadata associated with the query and are to be used by an entity linker to help the linker link candidates to columns.

Abstract: A method includes obtaining a user input for an artificial intelligence (AI) coding assistant, where the user input requests generation, modification, or analysis of code. The method also includes generating a prompt for the AI coding assistant using the user input and additional data relevant to the user input. The method further includes providing the prompt to the AI coding assistant. The additional data is included in the prompt and informs the AI coding assistant of a context associated with the user input. The additional data customizes the AI coding assistant to generate code in a coding language on which the AI coding assistant is not trained by providing curated examples of coding language syntax designed for consumption by the AI coding assistant.

Abstract: Random token segmentation may be implemented for next token prediction. Text data may be received for training a machine learning model to predict a next token given input text tokens. Multiple tokens may be determined from the text data. Different ones of the multiple token may be randomly segmented in to sub-tokens. The machine learning model may then be trained using the multiple tokens including the respective sub-tokens as a training data set.

Abstract: Code completion suggestions may be proactively obtained and validated. An event that triggers obtaining a code completion suggestion for inclusion in a code file being edited using an integrated development environment may be detected. The code completion suggestion may be obtained. The characters of the code completion suggestion may be compared with characters added to the code file after the detection of the event that triggered obtaining the code completion suggestion to determine whether the code completion suggestion is valid. A valid code completion suggestion may then be displayed.

Abstract: A foundation model is trained on time series-related data. The foundation model is configured to take as input time series data (e.g., asset prices in a market, power demand in a power grid, scores in baseball games, etc.) as well as related time-stamped exogenous data having a different modality from the time-series data (e.g., news headlines). Once the foundation model is trained, it may be fine-tuned for different decoder heads to make predictions for a range of time series values.

Abstract: Techniques for handling natural language query processing are described. In some examples, entities are recognized during an entity recognition phase and then relations between those entities are determined. Those relations are fed to an entity linker to help the linker link candidate to columns and/or a intent representation generator to help parse multiple values and column pairs of a natural language query.

Abstract: Techniques for using a quantized and/or fused model are described. In some examples, a service is to receive a request to use a trained model, the request including input data; apply a trained model to the input data, the application of the trained model includes fusing one or more matrix multiplication operations with element-wise operations; and output a result from the trained model.

Abstract: Systems and methods develop and apply one or more extractive summarization models for locating contact center conversation details in a transcript, extracting pertinent verbiage, and, in a transformation of the communication details, automatically generating summaries at one or more levels of abstraction, the summaries in full sentences, in a manner that a contact center agent understands. The models are trained using machine learning algorithms.

Abstract: A schema and cell value aware Named Entity Recognition (NER) model is used to perform natural language queries. Natural language queries may be received via an interface of a natural language query processing system. A fuzzy search may be performed that allows non-exact matches for column names or cell values of data sets potentially used to answer the natural language query. An NER model that adds a type embedding for an exact match of a column name or cell found in the fuzzy search that corresponds to a span of one or more words may be applied as part of generating the entity prediction for the natural language query. One or more queries to at least one of the data sets may be performed to return a result to the natural language query using the entity prediction generated by the NER machine learning model.

Abstract: Techniques for handling natural language query processing are described. In some examples, a sequence-to-sequence model is used to handle a natural language query. Post-processing of a result of the sequence-to-sequence model utilizes fine-grained information from an entity linker. In some examples, the sequence-to-sequence model and aspects of a natural language query pipeline are used to handle a natural language query.

Abstract: Techniques for predicting an answer to a question using a machine learning model are described. In some examples, the model predicts one or more answers to the question by: predicting at least two answers to the question using a first component of the question-answer model from a set of passages, generating, using a second component of the question-answer model, at least one question for each of the predicted at least two answers, and performing roundtrip predictions until each generated question only has one answer.

Abstract: The described system provides a dual-model framework for data retrieval from complex data environments such as webpages on the internet. It combines a traditional similarity model that identifies relevant data from vast amounts of data and a large language model that delves deeper into the relevant data to uncover specifics. The models, in conjunction, provide a method for providing responses to structured queries about an entity. A source investigator receives a request for information about an entity alongside a set of keywords. A source datastore is identified for the entity and a similarity model is applied to the datastore to determine relevancy scores for data within. Data and/or nodes above a relevancy threshold are stored as relevant data. Then, using the large language model, the investigator generates responses to the structured queries based on the relevant data and provides responses to the user system.

Abstract: Evaluation data sets may be programmatically generated for code generation models. An evaluation data set is obtained that includes items that correspond to different evaluation tests for a code generation system. The individual items of the evaluation data set maybe converted, including the conversion of a function signature for the items, the test statements for the items and using a code generation system to generate the body of the function.

Abstract: Pre-fix matching may constrain the generation of next token predictions. Input text to perform a next token prediction may be received. Multiple tokens may be determined from the input text, including a partial token. From possible tokens, one or more matching possible tokens with the partial token may be identified. Next token predictions may then be filtered using the identified possible tokens in order to ensure that the partial token is matched.

Abstract: Interactive assistances for executing natural language queries to data sets may be performed. A natural language query may be received. Candidate entity linkages may be determined between an entity recognized in the natural language query and columns in data sets. The candidate linkages may be ranked according to confidence scores which may be evaluated to detect ambiguity for an entity linkage. Candidate entity linkages may be provided to a user via an interface to select an entity linkage to use as part of completing the natural language query.

Abstract: Code completion suggestions may be proactively obtained and validated. An event that triggers obtaining a code completion suggestion for inclusion in a code file being edited using an integrated development environment may be detected. The code completion suggestion may be obtained. The characters of the code completion suggestion may be compared with characters added to the code file after the detection of the event that triggered obtaining the code completion suggestion to determine whether the code completion suggestion is valid. A valid code completion suggestion may then be displayed.

Abstract: Random token segmentation may be implemented for next token prediction. Text data may be received for training a machine learning model to predict a next token given input text tokens. Multiple tokens may be determined from the text data. Different ones of the multiple token may be randomly segmented in to sub-tokens. The machine learning model may then be trained using the multiple tokens including the respective sub-tokens as a training data set.

Abstract: Pre-fix matching may constrain the generation of next token predictions. Input text to perform a next token prediction may be received. Multiple tokens may be determined from the input text, including a partial token. From possible tokens, one or more matching possible tokens with the partial token may be identified. Next token predictions may then be filtered using the identified possible tokens in order to ensure that the partial token is matched.