Abstract: Methods and systems for managing a configuration of a client deployment to provide a service are disclosed. The configuration may be managed by managing configuration drift that may occur in the configuration of the client deployment. The configuration drift may be managed by monitoring for changes in the configuration and restoring the configuration to a goal configuration. The changes may be monitored by constructing knowledge graphs using the configurations. A knowledge graph of a current configuration may be compared to a knowledge graph of a goal configuration to find a difference. The difference may represent a configuration drift. The configuration drift in the current configuration may be remedied to restore the current configuration to the goal configuration.

Abstract: Disclosed herein are systems and techniques for evaluating prescribed optical devices during use. A method can include matching a user profile with a prescribed optical device, matching the prescribed optical device with a plurality of members of a distribution system of the prescribed optical device, requesting information about the prescribed optical device through a user interface, receiving information in response to requesting the information, and sending feedback based on the received information to one of the members of the distribution system. One or more network devices can generate a user interface including information associated with the prescribed optical device and the user profile. The user interface can be adapted based on a primary or secondary user of the network device. The user interface can also be adapted as the user progresses in age, treatment schedule, and/or other factors that support evaluation of the prescribed optical device.

Abstract: A class related to the xApp registration configuration is correlated to at least one of a class related to the xApp policy, a class related to the xApp messaging configuration, a class related to the xApp enrichment information, and a class related to the xApp API enablement configuration, in the Near-RT RIC (Near-Real Time RAN Intelligent Controller) of the O-RAN. A class related to the xApp registration configuration is correlated to a class related to the xApp RAN function, in the Near-RT RIC (Near-Real Time RAN Intelligent Controller) of the O-RAN.

Abstract: Herein, a “perception statistical performance model” (PSPM) for modelling a perception slice of a runtime stack for an autonomous vehicle or other robotic system may be used e.g. for safety/performance testing. A PSPM is configured to receive a computed perception ground truth, and determine from the perception ground truth, based on a set of learned parameters, a probabilistic perception uncertainty distribution, the parameters learned from a set of actual perception outputs generated using the perception slice to be modelled. A simulated scenario is run based on a time series of such perception outputs (with modelled perception errors), but can also be re-run based on perception ground truths directly (without perception errors). This can, for example, be way to ascertain whether perception error was the cause of some unexpected decision within the planner, by determining whether such a decision is also taken in the simulated scenario when perception error is “switched off”.

Abstract: An analysis device according to the present disclosure is provided with: a data acquisition unit that acquires data detected by an industrial machine; an operation state extraction unit that extracts, from the data, data detected during operation of the industrial machine; an annotation unit that creates a plurality of data set groups by giving, on the basis of a predetermined standard, annotations indicating motion states of the industrial machine to a plurality of data sets segmented by a predetermined standard from the extracted data during the operation; a feature amount extraction unit that extracts a feature amount of data included in each of the data sets; a learning unit that generates decision tree models respectively for the plurality of data set groups; and a display unit that ranks the generated decision tree models on the basis of correct answer rates regarding prediction of the annotations based on predetermined training data and that displays the decision tree models.

Abstract: An information processing method includes: creating a first table by an experimental design method, calculating a first response surface using the first table, setting a fourth level value for a first control factor when the first response surface does not include a target value related to an object variable for the first control factor, creating a second table by the experimental design method by deleting at least one combination of the experimental conditions which include one level value for the first control factor from the first table and adding at least one combination of the experimental conditions based on the plurality of level values including the fourth level value and without including the one level value for the first control factor, calculating a second response surface including the target value using the second table, and outputting the second response surface.

Abstract: A code sequence based intelligent key code identification method includes extracting Smali code sequence by decompiling an application, vectorizing the extracted Smali code sequence to construct a training dataset, training a deep learning model with the vectorized Smali code sequence to generate a classifier, generating a category classification result using Smali code sequence of a target application as input of the classifier, and identifying and providing important Smali code sequence from which the classification result of the target application is derived. Accordingly, it is possible to objectively evaluate the application using Smali code sequence of the application being actually run.

Abstract: Techniques to manage media flows for broadcast with public cloud networks. A request for a media flow is received. A location of the media flow is identified based on a registration database configured to maintain locations of media flows across a media production facility and a public cloud network facility. The media flow is accessed, and at least one of the receiving entity or the requesting entity is configured to generate media based on the media flow.

Abstract: A non-transitory computer-readable storage medium storing an arithmetic operation program that causes at least one computer to execute a process, the process includes searching for first order information such that an evaluation value is updated as a generation progresses by using an evolutionary algorithm for a first individual that is a target of a combinatorial optimization process which includes an array search, the individual including the first order information; generating a first array by using the first order information; converting the first array into a QUBO format; and searching for a combination by using the converted first array.

Abstract: An evolutionary AutoML framework called LEAF optimizes hyperparameters, network architectures and the size of the network. LEAF makes use of both evolutionary algorithms (EAs) and distributed computing frameworks. A multiobjective evolutionary algorithm is used to maximize the performance and minimize the complexity of the evolved networks simultaneously by calculating the Pareto front given a group of individuals that have been evaluated for multiple objectives.

Abstract: Analytics dashboards for critical event management systems that include artificial-intelligence (AI) functionalities, and related software. AI functionalities disclosed include pattern recognition and predictive modelling. One or more pattern-recognition algorithms can be used, for example, to identified patterns or other groupings within stored critical events, which can then be used to improve response performance and/or to inform the generation of predictive models. One or more predictive-modeling algorithms can be used to generate one or more predictive models that can then be used, for example, to make predictions about newly arriving critical events that can then be used, among other things, to provide optimal response performance and allow users to efficiently and effectively manage responses critical events. These and other features are described in detail.

Abstract: A system (100) comprising one or more processors (110) and one or more storage devices (120) is configured to obtain biology-related image-based input data (107) and generate a high-dimensional representation of the biology-related image-based input data (107) by a trained visual recognition machine-learning algorithm executed by the one or more processors (110). The high-dimensional representation comprises at least 3 entries each having a different value. Further, the system is configured to at least one of store the high-dimensional representation of the biology-related image-based input data (107) together with the biology-related image-based input data (107) by the one or more storage devices (120) or output biology-related language-based output data (109) corresponding to the high-dimensional representation.

Abstract: Disclosed herein are systems and method for automated malicious code replacement. In one exemplary aspect, a method may comprise scanning for malicious content in a file comprising a script written in an interpretable programming language, wherein the malicious content triggers malicious activity on a computing device that stores the file. The method may comprise detecting a malware injection in the file based on the scanning, wherein the malware injection comprises at least one operator that enables the malicious activity. The method may comprise identifying a benign operator that can replace the at least one operator to prevent execution of the malicious activity without causing a syntax error. The method may comprise updating the file by replacing the at least one operator with the benign operator.

Abstract: An embodiment for controlling a boundary of an AI system based on an environmental context is provided. The embodiment may include receiving data input from one or more sources. The embodiment may also include identifying one or more contextual situations in a surrounding environment. The embodiment may further include identifying one or more input data collection boundaries and a span of control boundary for an AI-enabled device. The embodiment may also include connecting the AI-enabled device to one or more data generation modules within the one or more input data collection boundaries. The embodiment may further include in response to determining none of the one or more data generation modules are unable to connect, identifying an action to be performed by the AI-enabled device. The embodiment may also include executing the action in a first set of one or more machines within the span of control boundary.

Abstract: Assigning support tickets to support agents is described. A system receives support tickets and trains a machine-learning model to identify support agents who had experiences resolving support tickets of multiple complexities. The system receives a support ticket, identifies a topic of the support ticket, and estimates a complexity of the support ticket. The system identifies support agents who have skills handling the topic of the support ticket. The machine-learning model identifies support agents who have experiences resolving support tickets of the estimated complexity. The system projects workload availabilities, of identified support agents, for the support ticket. The system generates support agent scores based on the skills handling the topic, the experiences resolving support tickets of the estimated complexity, and the projected workload availabilities for the support ticket. The system assigns, based on the support agent scores, the support ticket to an identified support agent.

Abstract: A system and method are disclosed for training a probabilistic graphical model based on historical attributes of a supply chain to represent supply chain performance, selecting supply chain entity target variables, collating with the use of machine learning models, a list of features and classes pertaining to selected supply chain entity target variables, calculating first and second level features associated with the list of features and classes, generating supply chain predictions based on the trained probabilistic graphical model, where the supply chain predictions are based on test data, comparing the supply chain predictions to desired supply chain outputs to determine a delta distance, and generating resolution actions, to decrease the delta distance between the supply chain output predictions and the desired supply chain outputs.

Abstract: A device and method are disclosed for operating a fuel cell system having a fuel cell stack. Data are provided that map input variables of the fuel cell system and a position of a cell of the fuel cell stack on a voltage of the cell. A model is trained to map the input variables of the fuel cell system and the position of a cell of the fuel cell stack on a probability distribution for a prediction of a voltage of the cell. Instantaneous input variables of the fuel cell system are determined. A probability for the voltage of the cell or for a total voltage of the fuel cell stack is determined for a cell of the fuel cell stack based on the input variables using the model based on the probability distribution. A state of the fuel cell system is determined based on the probability.

Abstract: A method and corresponding system for providing patient data to a patient data server following an offline network condition are described. In one arrangement, a healthcare information analysis and presentation system includes a client logic device disposed in wireless communication with a patient data server. The healthcare information analysis and presentation system is configured with an offline functionality that stores patient data on the client logic device, even when not wirelessly connected to the patient data server. Further, the healthcare information analysis and presentation system is configured to allow the end user to begin patient data entry for a new patient, to document an existing case, and to resolve conflicting data following an offline network condition, all while preserving and protecting patient's privacy.

Abstract: A three-phase diagnosis methodology capable of effectively diagnosing and classifying multiple defects in integrated circuits comprises a first phase identifying a defect that resembles traditional fault models, and second and third phases that utilize the X-fault model and machine learning to identify correct candidates.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for machine learning. One of the methods includes receiving a message; parsing the message to identify individual sentences within the message; encoding each sentence into a vector that represents a semantic meaning of the sentence; applying one or more classification models to the message including: providing each vector to a machine learning model, wherein the machine learning model is trained to generate a prediction of one or more classifications for each sentence of the message; generating a predicted classification for the message as a whole; and determining a message routing based on the predicted classification.

Abstract: Various embodiments are provided for automated evaluation of machine learning models in a computing environment by one or more processors in a computing system. A level of robustness of a machine learning model against adversarial whitebox operations may be evaluated and determined by applying a data set used for testing the machine learning model, one or more adversarial operation objectives, an adversarial threat model, and a selected number of hyperparameters. Results from the adversarial operation may be analyzed and a modified machine learning model may be generated while performing the evaluating and determining.

Abstract: The technology disclosed herein enables pushing of access-privilege information from data environments to a graphing service. In a particular embodiment, a method includes registering a data environment to enable the data environment to use Application Programming Interface (API) calls and receiving an API call transmitted from the data environment. The API call provides information about access permissions for the data environment. The method further includes incorporating the information into a privilege graph representing data access authorizations.

Abstract: Methods and systems for performing a combinatorial optimization task are provided. The method includes: receiving a first set of data items and a second set of data items; dividing the second set of data items into a first subset and a second subset; generating, based on the first subset, a first set of subset sums, and storing the first set of subset sums as a list; generating, based on the second subset, a second set of subset sums, and storing the second set of subset sums as a hash-map in conjunction with a corresponding hash function; and detecting, based on the first set of data items, the list, and the hash-map, at least one match between a subset sum that corresponds to the second set of data items and a subset sum that corresponds to the first set of data items.

Abstract: The present disclosure provides an intelligent decision reasoning method for type-based diagnosis and treatment of a cardiovascular disease, a device, and a product, and relates to the medical field. The present disclosure adopts a risk factor mining model of a cardiovascular disease and a drug attribute association mining model of the cardiovascular disease to extract relevant information from cardiovascular data, achieving precise prediction of a fine-grained cardiovascular disease type and effectively promoting precision medicine. Based on a clinical diagnostic dataset and a clinical symptom diagnosis knowledge system of the cardiovascular disease, a type-based auxiliary diagnosis model of the cardiovascular disease is constructed, and intelligent decision reasoning is performed to obtain an association rule.

Abstract: Predefined patterns are detected in streaming data being transmitted in a distributed computing system that contains a plurality of computing devices wherein the plurality of computing devices are collectively configured to execute a distributed software program. A detection engine can be implemented on a computing device and can be configured to receive streaming data that is being transmitted between computing devices of the system. The detection engine can be further configured to analyze the streaming data to determine if the data matches one or more patterns that is specified by a watch point which can be converted into a happened before language expression. The streaming data can be converted into an intermediate log file that is compared against patterns expressed by a regular expression and if a match is found, an alert can be generated.

Abstract: A computing device displays, in a graphical user interface, a canvas region that includes a first scene. The first scene includes a first visualization card having a first data visualization and a first text card, adjacent to the first visualization card. The device receives, via the first text card, (i) text input from a user and (ii) user selection of a first user interface element for linking the first text card to the first visualization card. In accordance with the receiving, the device determines whether the text input includes a first expression having a first time span that intersects with a temporal domain of the first data visualization. In accordance with a determination that the text input includes the first expression, and in response to a first user interaction with a first region of the first text card that includes the first expression, the device visually emphasizes a first portion of the first data visualization, corresponding to the first time span.

Abstract: The embodiments of the present disclosure provide a wireless communication method, a terminal device, and a server. The method includes: obtaining, by a terminal device, at least one application data and/or wireless protocol layer data in the terminal device; and transmitting, by the terminal device, the at least one application data and/or wireless protocol layer data of the terminal device to a data collection server. Therefore, the accuracy of data analysis can be improved.

Abstract: Technologies for providing assistance to a surgeon during a surgical procedure are disclosed. An example method includes identifying a medical condition of a patient and recommending surgical procedures for treatment. An optimal surgical procedure is then determined based on correlations between the medical condition of the patient and outcomes of previous surgical procedures for other patients previously suffering from the medical condition. A 3D model of the patient may be created using current images of an affected area of the patient. Successively, a surgeon is trained using a Virtual Reality simulation. During the training, the surgeon may be allowed to provide annotations. Further, the recommended surgical procedures are based on medical data of the patient, including medical images.

Abstract: A system and a method are disclosed for detecting that a requesting user is transmitting a request to a recipient user to perform one or more tasks with respect to a secure document. The system extracts features associated with the secure document and inputs the features into a machine learning model that outputs one or more probabilities corresponding to a potential failure of the request. Based on the one or more probabilities, the system generates one or more feature modification activities to improve a likelihood of the recipient user completing the request. The system provides the one or more feature modification activities to at least one of the requesting user and the recipient user.

Abstract: Examples disclosed herein relate to a system including: one or more processors and at least one memory device; the one or more processors may receive communication data and initiate a procedure to the received communication data to generate a machine representation of the received communication data, the one or more processors may utilize one or more idea mapping functions on the machine representation to generate one or more identifiers and one or more idea links for the machine representation, the one or more processors may generate an interpreted communication data based on the one or more idea links; and the one or more processors may transmit an initiation action signal based on the one or more idea links.

Abstract: Embodiments of the subject invention comprise a computer based system and methods to collect and compare the attributes of a group of entities using data representing topic data of the entity and interaction data between entities. Embodiments of the invention comprise using minimally invasive means to automatically collect and model both an entity's attributes such as their knowledge/work/interest as well as model the social interactions of the entity together with a means to identify opportunities to influence changes in the entity attributes. Minimally invasive means to collect and model attributes include semantic analysis and topic modeling techniques. Means to model social interactions include social network analysis techniques that can incorporate location data of the entity. Embodiments of the invention further provide a sharable index of the attributes of the entities and the group of entities.

Abstract: Multi-cloud deployment strategy is based on automated analysis of context and requirements for an activity workload. The activity workload is defined by user input including information regarding project cost, performance requirements, and geographical preferences. Selection of cloud-based resources for handling the activity workload is based in part on service availability record, projected cost of resources, and physical geographic locations. A cloud services registry provides cloud service provider data for selection to perform aspects of the activity workload.

Abstract: Disclosed is an adaptive deep learning inference system that adapts to changing network latency and executes deep learning model inference to ensure end-to-end data processing service latency when providing a deep learning inference service in a mobile edge computing (MEC) environment. An apparatus and method for providing a deep learning inference service performed in an MEC environment including a terminal device, a wireless access network, and an edge computing server are provided. The apparatus and method provide deep learning inference data having deterministic latency, which is fixed service latency, by adjusting service latency required to provide a deep learning inference result according to a change in latency of the wireless access network when at least one terminal device senses data and requests a deep learning inference service.

Abstract: The present disclosure includes apparatuses and methods related to performing a debug operation on an artificial intelligence operation. An example apparatus can include a number of memory arrays and a controller, wherein the controller is configured to perform an artificial intelligence (AI) operation on data stored in the number of memory arrays and perform a debug operation on the AI operation.

Abstract: Discovering molecules (which may be known or may never have been cataloged or ever synthesized) that have desired characteristics is addressed using a machine learning approach. As compared to a brute-force search of a database of known molecules, which may not be computationally feasible, the present machine learning approach renders identification of both known and unknown molecules computationally tractable. Furthermore, the computational effort is largely shifted to training of the machine learning system using a database of known molecules, and the generation of molecules to match any particular characteristics requires relatively little computation. The molecules using the present approach may be further studied, for example, with computer-based simulation or after physical synthesis using biological experimentation to ultimately yield useful chemical compounds.

Abstract: Techniques are generally described for modeling seasonal relevance for online search. A first query or item comprising text is received. A language model may be used to generate a plurality of token embeddings representing the text. In some cases, the first neural network may predict a seasonal relevance vector for the first query or item based on the plurality of token embeddings, the seasonal relevance vector being predicted based at least in part on a similarity between the text of the first query or item and at least one other query/item for which monthly concentration data is available. The seasonal relevance vector, including a respective seasonal relevance score for each month of a year, may be output.

Abstract: The systems and methods provide a model deployment criterion. The model deployment criterion indicates a difference in a value against which the proxy model may be measured to determine when, if ever, the proxy model should be deployed to replace the existing rule engine. The model deployment criterion may be keyed to the proxy model (e.g., based on a difference in its size, throughput speed, number of changes, etc.), the existing rule engine (e.g., based on a difference in its age, update occurrences to its rule base, etc.), and/or comparisons between models (e.g., based on differences in results, throughput speed, efficiency, etc.).

Abstract: Recycling of an electrochemical energy storage device is provided. A remaining charge on the electrochemical energy storage device is determined. An impedance profile of the electrochemical energy storage device is determined for the remaining charge. The impedance profile includes an internal impedance of the electrochemical energy storage device at different charge levels from the remaining charge to a complete discharge. A variable discharge load is applied on the electrochemical energy storage device until the complete discharge. The variable discharge load varies with the internal impedance of the electrochemical energy storage device at the different charge levels.

Abstract: Techniques for enhanced table and text question answering based on multi-instance, multi-answer training are presented. An answer extractor component can determine answer scores associated with candidate answer data items based on analysis of a set of data, comprising row data items of a table and passage data items associated with the table, and a context of a query of the set of data. The answer extractor component can be trained based on application of denoised single-instance and multiple-instance answer matching data associated with contexts to an answer extractor model to generate a trained answer extractor model of the answer extractor component. A query response component can determine a correct answer data item responsive to the query from the candidate answer data items based on the answer scores associated with the candidate answer data items, wherein the candidate answer data items can be reranked based on reweighted answer scores.

Abstract: The present disclosure relates to improving recommendations for small shops on an ecommerce platform while maintaining accuracy for larger shops. The improvement is achieved by retraining a machine-learning recommendation model to reduce sample selection bias using a meta-learning process. The retraining process comprises identifying a sample subset of shops on the ecommerce platform, and then creating shop-specific versions of the recommendation model for each of the shops in the subset. Each shop-specific model is created by optimizing the baseline model to predict user-item interactions in a first training dataset for the applicable shop. Each of the shop-specific models is then tested using a second training dataset for the shop. A loss is calculated for each shop-specific model based on the model's predicted user-item interactions and the actual user-item interactions in the second training dataset for the shop.

Abstract: Provided are systems and methods for customizing modifiable videos. An example method includes analyzing recent messages associated with a user in a multimedia messaging application to determine a context of the recent messages, determining, based on the context, a property of a modifiable feature, selecting, based on the context, a list of relevant modifiable videos from a database configured to store modifiable videos associated with a preset modifiable feature, replacing a property of the preset modifiable feature in relevant modifiable videos of the list of relevant modifiable videos with the property of the modifiable feature, and rendering the list of relevant modifiable videos for viewing by the user, where the rendering includes displaying the modifiable feature in the relevant modifiable videos.

Abstract: A method for testing a user interface (UI) includes obtaining a first state of the UI and setting a current position to specified location coordinates. The method includes determining whether the first state satisfies criteria for a goal and, if so, updating a collection of completed tests with a test distance and test data. The method includes, in response to the first state not satisfying the criteria: determining a set of potential user actions to be performed in the first state based on interactive elements of the UI; selecting and executing an action; and updating the test distance based on the current position and location coordinates of the element associated with the action. The method includes determining a shortest path to the goal in the UI based on the collection of completed tests. The method includes, based on the determined shortest path, automatically visually transforming a state of the UI.

Abstract: Embodiments may facilitate event processing for an ABAP platform. A business object data store may include a RAP model, including a behavior definition, for a business object. A framework may automatically transform the behavior definition of the RAP model into a producer event via an event binding and a cloud event standardized format. Information about the producer event may then be passed to an ABAP application associated with a pre-configured destination at an enterprise business technology platform. In some embodiments, a standalone API enterprise hub data store may contain an event specification. An ABAP development tenant of a business technology platform may automatically parse the event specification and translate the parsed information into high-level programming language structures that reflect an event type at runtime. An event consumption model may then be generated based on the event type.

Abstract: One example method includes, beginning at a parent node of a data structure, calculating a first W-index for the parent node and a left child node, calculating a second W-index for the parent node and a right child node, when the first W-index exceeds a threshold ?, marking the left child node as a candidate to be included in a sub-cluster separate from a sub-cluster that includes the parent node, when the second W-index exceeds the threshold ?, marking the right child node as a candidate to be included in a sub-cluster separate from the sub-cluster that includes the parent node, and recursively calculating respective W-indices for all other parent nodes in the data structure until all child nodes of the data structure have been assigned to a sub-cluster.

Abstract: A method for determining a risk for an infectious disease for a patient using a cognitive intelligence platform is disclosed. The method includes receiving, from an authoritative source, factors indicative of a person being infected by the infectious disease, wherein the factors include medical information pertaining to the infectious disease. The method also includes determining whether any of the factors are present in a patient graph of the patient, wherein the patient graph includes medical information pertaining to the patient and the determining is performed by matching the medical information pertaining to the infectious disease to the medical information pertaining to the patient. The method also includes, responsive to determining the factors are present in the patient graph of the patient, determining the risk for the infectious disease for the patient, and performing a preventative action based on the risk for the infectious disease.

Abstract: The present disclosure is directed to systems and methods for extracting unstructured data from a data source in a structure manner. Embodiments provide ways to retrieve unstructured data along from data sources not optimized for automated retrieval. For example, embodiments may generate a branched tree for each data source that maps out paths to individual sites of, for example, a healthcare provider listing the unstructured data. Using this branched tree, tasks can be generated to navigate along a path with the data source to each site and extract the unstructured data from the data source. In this way, embodiments provide the ability to navigate through a site from a base site to a site that has the relevant data.

Abstract: The present invention is a method and system of small construction project management by way of photo imaging and measurement capture for use by do-it-yourselfers, handymen and small contractors. The method and system operates on mobile computing devices and includes an image recognition system. By performing various imaging based measurements and then processing the resultant data, the method and system produces bills of materials. invoices, and receipts for the necessary tools and materials required by a construction project.

Abstract: Embodiments of the disclosed technologies apply a logistic regression model to a set of population data for a set of genes. The set of population data includes a set of features for a variant located at a position within a gene. The set of features includes at least one population frequency meta-feature. The at least one population frequency meta-feature quantifies predictive value of allele frequency in the gene. Using the first set of population data, a variant classification prediction output by the logistic regression model is evaluated based on an expected variant classification. The logistic regression model is adjusted until at least one first performance criterion is satisfied to produce a trained logistic regression model. The trained logistic regression model is capable of outputting variant pathogenicity estimates that satisfy at least one second performance criterion.

Abstract: Arrangements for smart tracking and queue management are provided. In some aspects, in response to detecting a user at an entity location, image data may be captured of the user. The image data may be analyzed using one or more facial recognition techniques to determine whether the user is a recognized user. In some examples, a user or user device may be connected to an entity computing device associated with a shopping cart or other device for capturing items for purchase. The user may gather items for purchase and purchase item data may be transmitted for analysis. In some examples, a request to checkout may be received and, in response, real-time queue data may be requested. The real-time queue data may be analyzed using a machine learning model to determine an optimal queue for the user. A notification identifying the queue may be transmitted to the entity computing device.

Abstract: This application relates to a user tag generation method performed by a computer device, relating to the field of neural networks. The method includes: obtaining discrete user data corresponding to a target user identifier in multiple feature fields respectively; for each feature field, obtaining an intra-field feature corresponding to the target user identifier according to the discrete user data in the feature field; merging the intra-field features to obtain an inter-field feature corresponding to the target user identifier; performing feature crossing on sub-features in the inter-field feature to obtain a cross feature corresponding to the target user identifier; and selecting, from candidate user tags, a target user tag corresponding to the target user identifier according to the inter-field feature and the cross feature. The solutions provided by this application can improve the accuracy of generating user tags.