Abstract: The present disclosure discloses a method of table data verification. Specifically, a user can set a format of a target cell and a data verification condition of the cell, where the data verification condition includes a first format and a data range. That is, the data verification condition can not only verify a format of an input data in the cell, but also verify a range of the input data. In a case that the user inputs the target data into the target cell, the target data is obtained, the format of the target data and the value of the target data are verified using the set data verification condition to obtain a verification result. Here, the format of the target data is the second format corresponding to the target cell.

Abstract: Listwise autocomplete ranking with position debias is described. A computing system can receive a user input indicative of a portion of a search query. The computing system can receive a set of candidate queries for an autocomplete list based on the portion of the search query. The computing system can generate a respective ranking score for each candidate query of the set of candidate queries by calculating, for each candidate query of the set of candidate queries, a respective click probability prediction using a position debiased listwise click-through rate (CTR) prediction model, and calculating, for each candidate query of the set of candidate queries, a respective reward per search. The computing system can order the set of candidate queries according to the respective ranking scores. The computing system can output at least one of the candidate queries based on the ordered set of candidate queries.

Abstract: A top K query directed at a table is received. The table is organized into multiple storage units. The top K query comprises a first clause to sort a result set in order and a second clause that specifies a limit on a number of results provided in response to the query. A table scan operator identifies a first set of rows from the table based on a scan set determined for the table and provides the first set of rows to a top K operator. The top K operator determines a current boundary based on the first set of rows and provides the current boundary to the table scan operator. The table scan operator prunes the scan set based on the current boundary and identifies a second set of rows from the table based on the pruning.

Abstract: An example method includes acquiring data from at least one data source of an enterprise, detecting a plurality of characteristics of the data, selecting, based on the plurality of characteristics, a partitioning technique for partitioning the data, partitioning, using the partitioning technique, the data to produce a plurality of data chunks, generating a plurality of vector embeddings of the plurality of data chunks, selecting metadata with which to augment the plurality of vector embeddings, augmenting the plurality of vector embeddings with the metadata, and applying an indexing algorithm to the plurality of vector embeddings to facilitate a storage of the plurality of vector embeddings.

Abstract: An integration platform, which integrates heterogenous provider systems behinds a normalized interface, accepts a declarative mapping template that specifies field-level relationships and transformations between provider schemas and a normalized schema. The template is validated and processed into compiled transformations. Executing the compiled logic converts provider payloads into the normalized schema for client consumption and applies reverse transformations to map client-supplied normalized data back to provider-native schemas for submissions. Client queries and ordering requests expressed against normalized fields are translated into intermediate, provider-agnostic representations that normalize keys, operators, directions, and typed values. These intermediate filter and order representations are then formatted into provider-native request syntaxes for transmission to provider systems.

Abstract: A method for tagging and organizing data is provided. In one example, physiological data detected from a wearer of a wearable device is received and associated with a tag based, at least in art, on an input by the wearer. The input may be a state of the wearer, such as physical or mental state, or a rule. The collected physiological data may be organized based on the tag and, in some examples, on other types of received data, such as a wearer's personal data. In other example methods, data may be stored in a database based on one or more tags associated with the data.

Abstract: Aspects concern a server configured to receive a request for a search, determine a distance from a location of a computing device to produce a first list of service providers within the distance, rank the first list of service providers based on a plurality of predetermined first factor values including a predicted delivery experience value of each service provider in the first list of service providers, produce a second list of service providers from the first list of service providers based on the rank of each service provider in the first list of service providers, determine whether to filter out a part of the second list of service providers based on a size of the second list of service providers, and filter out the part of the second list of service providers based on the predicted delivery experience value of each service provider in the second list of service providers.

Abstract: In example implementations described herein, systems and methods are presented for predicting a throughput for a production line which can involve collecting a current set of production line data associated with a production line; and computing a predicted production throughput for the production line over a production period based on a boosted gradient decision tree algorithm applied to the current set of production line data, wherein the boosted gradient decision tree algorithm is trained on historical production line data.

Abstract: Implementations relate to storing historical queries processed using a generative model in association with intermediate model outputs generated using the generative model for each of the historical queries. Implementations further relate to receiving a user query processable using the generative model. In response to receiving the user query, the user query can be compared to the historical queries to identify a particular historical query (e.g., having a similarity score satisfying a similarity threshold) that matches the user query. Particular intermediate model output associated with the particular historical query can be selected from all intermediate model outputs stored in association with the particular historical query, and a response to the user query can be generated based at least on the selected particular intermediate model output associated with the particular historical query.

Abstract: Systems and methods for retrieving information using a modular endpoint system are disclosed herein. The system accesses a suite of model-based agents that interface with a plurality of retrieval augmented generation (RAG) endpoints and receives, from a user via an application programming interface (API), (a) a query and (b) session parameters. The system may input the query and the session parameters into a model configured to identify at least one RAG endpoint and, responsive to identifying the at least one RAG endpoint, retrieve a schema specific to the at least one RAG endpoint. Using the function calling capabilities of the model, the system may generate a request for data conforming to the schema and retrieve the data.

Abstract: A computing platform is configured to (i) obtain a first set of watchlist data entries for parties that appear on one or more watchlists and a second set of screened data entries for parties that are to be screened against the one or more watchlists; (ii) determine an initial set of candidate matches between screened data entries and watchlist data entries using a first comparison technique (e.g., a comparison technique that utilizes similarity scores of a first type), and (iii) determine a narrowed set of candidate matches between screened data entries and watchlist data entries using a second comparison technique (e.g., a comparison technique that utilizes similarity scores of a second type).

Abstract: Methods, computing systems, and technology for generating keywords using machine-learned techniques. The system can receive, from a user device, a first keyword associated with a content item of a first content provider. Additionally, the system can access from a keyword database, a plurality of keywords. Moreover, the system can select, using the machine-learned model, a subset of keywords from the plurality of keywords based on the content item. Furthermore, the system can process, using a machine-learned model, the first keyword and a subset of keywords to calculate a similarity score for each keyword in the subset of keywords and the first keyword. The system can determine a suggested keyword from the subset of keywords based on the similarity score for each keyword in the subset of keywords and the first keyword. Subsequently, the system can cause, on a display of the user device, a presentation of the suggested keyword.

Abstract: An example method includes (a) generating a request to obtain log data descriptive of operation of an autonomous vehicle control system in a subject scenario, the log data indexed by an indexing parameter; (b) submitting the request to a log repository service, the log repository service configured to receive the request and serve, responsive to the request, log metadata; (c) loading, based on the log metadata and an index value of the indexing parameter, a log data sketch associated with the index value; and (d) loading, based on the log metadata and the index value, and responsive to an inspection indicator, detailed log data associated with the index value.

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: The present application generally relates to a method for training a machine learning, ML, model using class incremental learning, and to a computer-implemented method and apparatus for using the trained machine learning, ML, model. The method may learn how to update semantic representations of old concepts (classes) by modelling drift of semantic representations.

Abstract: In an example embodiment, prompt compression is used in two different places in the LLM query pipeline to reduce the size of LLM queries, which reduces the time it takes for an LLM to respond to a query and improves scalability. Specifically, the conversation history itself may be run through a token compressor, which acts to eliminate unnecessary tokens from the conversation history and thus also from a rewritten version of the query. Additionally, the context chunks retrieved during RAG are themselves run through a token compressor to eliminate unnecessary tokens from the context chunks. The compressed context chunks and the rewritten query are then passed to the LLM for processing, and since both the context chunks and the rewritten query contain compressed elements, the result is that the LLM processes fewer tokens to respond to the query.

Abstract: Embodiments described herein are generally related to systems and methods for generating data visualization scores, for use with data analytics environments. In accordance with an embodiment, the system can operate in the manner of an expert system, or according to a series of processes or rules, to examine a data visualization of interest, compare a list of found elements with element types specified by an analytics data visualization score matrix, and generate, based on matching found elements with the analytics data visualization matrix, a data visualization score associated with the data visualization. In accordance with an embodiment, the system can operate as a data visualization advisor, during preparation of a data visualization, to provide a user with recommendations or score values indicative of a quality or complexity of their data visualization, which may be helpful in improving their data visualization, for example from a beginner-level to a more advanced-level.

Abstract: Techniques for utilizing machine learning to generate a question and answer pair for a conversational agent are described.

Abstract: Systems and methods for information retrieval and knowledge discovery are disclosed. The method includes, receiving a user input from a user via a user interface, wherein the user input comprises a user requirement and a user preference, identifying a user intent and a context of the received user input by parsing a plurality of keywords within the received user input, and extracting multimedia content from a structured data source based on the identified user intent, the context, the user requirement, and the user preference, wherein the structured data source stores the multimedia content retrieved from a plurality of data repositories.

Abstract: A method for automatically categorizing groups of users in a social network, and using the categories to propose matches between groups or users and groups includes accessing content shared within a group in a social network application, processing the shared content with at least one machine learning model to determine labels for the content, determining categories for the group based on the labels for the content, accessing matching criteria for a user of the social network application, generating a match between the user and the group based on the matching criteria for the user and the categories for the group, supplying data indicative of the match to a client device of the user, receiving a match acceptance from the client device, and in response to receiving the match acceptance, providing the user access to the group in the social network application.