Abstract: The present disclosure provides a corpus cleaning method and a corpus entry system. The method includes: obtaining an input utterance; generating a predicted value of an information amount of each word in the input utterance according to the context of the input utterance using a pre-trained general model; and determining redundant words according to the predicted value of the information amount of each word, and determining whether to remove the redundant words from the input utterance. In such a manner, the objectivity and accuracy of corpus cleaning can be improved.

Abstract: Systems, devices, media, and methods are presented for composing and sharing a message based on the motion of a handheld electronic device such as a ring. The methods in some implementations include presenting a keyboard on a display, collecting course data associated with a course traveled by the ring, and overlying a trace onto the keyboard, such that the trace is correlated in near real-time with the course traveled by the ring. In some implementations the display element is part of a portable device, such as the lens of an electronic eyewear device. Based on the course data relative to the key locations on the keyboard, the system identifies and presents candidate words to be included in a message.

Abstract: A hybrid entity recognition system and accompanying method identify composite entities based on machine learning. An input sentence is received and is preprocessed to remove extraneous information, perform spelling correction, and perform grammar correction to generate a cleaned input sentence. A POS tagger tags parts of speech of the cleaned input sentence. A rules based entity recognizer module identifies first level entities in the cleaned input sentence. The cleaned input sentence is converted and translated into numeric vectors. Basic and composite entities are extracted from the cleaned input sentence using the numeric vectors.

Abstract: A natural language model can be primed utilizing optimized examples generated from a labeled knowledge graph corresponding to an independently developed application program. Parsing of the labeled knowledge graph can include the identification of triples, comprising a source node, a destination node, and a link between them, each of which can be labeled. One or more natural language input examples can be generated from an individual triple by concatenating the natural language words or phrases utilized to label the source node in the link. Determinations that subsequently received natural language user input is similar to the generated examples can result in an identification of the triple, which can, in turn, trigger the performance of a function associated with the destination node of the triple. Labels can include preferred labels and alternative labels, and various permutations thereof can be concatenated to generate alternative natural language input examples.

Abstract: A method and device for keyword extraction and a storage medium. The method includes receiving, at a terminal, an original document, acquiring, at the terminal, a candidate set by extracting at least one candidate phrase from the original document, acquiring, at the terminal, an association degree between the at least one candidate phrase in the candidate set and the original document, acquiring, at the terminal, a divergence degree of the at least one candidate phrase in the candidate set, and updating, at the terminal, a key phrase set of the original document by selecting the at least one candidate phrase from the candidate set as at least one key phrase based on the association degree and the divergence degree.

Abstract: A system and method for classifying digital images is presented. The method includes extracting a plurality of descriptive data items of a transaction evidence from a digital image indicating a plurality of purchased items; searching in data source for informative data based on the extracted plurality of descriptive data items, wherein the informative data includes a price; determining a correlated amount for each of at least one of the plurality of descriptive data items, wherein the correlated amount determined for one of the descriptive data items defines a paid price for the descriptive data item; determining, based on at least one expense type classification rule, a primary expense type of the transaction evidence, wherein the at least one expense type classification rule is applied to the plurality of descriptive data items and each of the correlated amount; and classifying the digital image based on the primary expense type.

Abstract: Examples of the present disclosure describe systems and methods for automatically assisting conversations using a graph database. In order to minimize misunderstanding of words and phrases used by participants during a conversation, phrases from the conversation may be received by conversation assistance application as the conversation takes place. Entities may be extracted from the phrase based on natural language recognition according to a domain context of the participant being assisted. One or more tags may be looked up from a graph database, and may be provided to the participant as a list of hashtags related to the conversation. Links to documents may be extracted based on the tags for the participant for viewing during the conversation.

Abstract: Methods and system for determining a similarity relationship between a plurality of digital assets and a target digital asset comprises creating a normalized semantic feature vector associated with a search query, discovering the target asset based on the normalized semantic feature vector, generating a normalized latent feature vector associated with the target asset, comparing the normalized semantic feature vector with semantic feature vectors for each of the digital assets to generate a semantic comparison value, comparing the normalized target latent feature vector with latent feature vectors for each of the digital assets to generate a latent comparison value, blending the semantic comparison vector value with the latent feature comparison vector value to create a target comparison value for each of the digital assets, and reporting the digital assets having the highest target comparison values to the user or group of users.

Abstract: A digital attribution system is described to generate predictions of word attributions from subject data, e.g., titles, subject lines of emails, and so on. To do so, an attribution score is first generated by the digital attribution system that describe an amount to which respective words in the subject data cause performance of a corresponding outcome. The attribution scores are then used by the digital attribution system to generate representations for display in a user interface for respective words in the subject data and may also be used to generate attribution recommendations of changes to be made to the subject data.

Abstract: Methods, apparatuses, and computer program products are described herein that are configured to express a time in an output text. In some example embodiments, a method is provided that comprises identifying a time period to be described linguistically in an output text. The method of this embodiment may also include identifying a communicative context for the output text. The method of this embodiment may also include determining one or more temporal reference frames that are applicable to the time period and a domain defined by the communicative context. The method of this embodiment may also include generating a phrase specification that linguistically describes the time period based on the descriptor that is defined by a temporal reference frame of the one or more temporal reference frames. In some examples, the descriptor specifies a time window that is inclusive of at least a portion of the time period to be described linguistically.

Abstract: Provided is a method including obtaining a first data object including a first set of data entries, wherein each data entry of the first set of data entries includes text content associated with a time entry. The method includes generating a first data object score using the text content and the time entries included in the first set of data entries and using scoring parameters, determine that the first data object score satisfies a data object score condition; perform in response to the first data object score satisfying the data object score condition, a condition-specific action associated with the data object score condition.

Abstract: A computing system can include one or more machine-learned models configured to receive context data that describes one or more entities to be named. In response to receipt of the context data, the machine-learned model(s) can generate output data that describes one or more names for the entity or entities described by the context data. The computing system can be configured to perform operations including inputting the context data into the machine-learned model(s). The operations can include receiving, as an output of the machine-learned model(s), the output data that describes the name(s) for the entity or entities described by the context data. The operations can include storing at least one name described by the output data.

Abstract: Techniques are disclosed for determining a target language for a communication session and configuring a language mode of an input method editor (IME) to the target language. An example methodology implementing the techniques includes, by a computing device, detecting a communication to a recipient via a software application running on the computing device, determining a target language for the communication, and configuring a language mode of an input method editor to the target language. The target language may be determined based on an attribute or attributes of the recipient of the communication. In some cases, the target language may be determined based on an attribute or attributes of a contents of a prior communication.

Abstract: An embodiment may involve a database containing a first user profile that specifies a first preferred language of a first user and a second user profile that specifies a second preferred language of a second user. The embodiment may also involve one or more processors configured to: receive, from the first user and within a chat session, a first set of messages in the first preferred language; cause the first set of messages to be translated into the second preferred language; provide, to the second user and within the chat session, the first set of messages as translated; receive, from the second user and within the chat session, a second set of messages in the second preferred language; cause the second set of messages to be translated into the first preferred language; and provide, to the first user and within the chat session, the second set of messages as translated.

Abstract: Systems and methods for profile-based language translation and filtration are provided. A user language profile specifying one or more translation rules may be stored in memory for a user. A current communication session associated with a user device of the user may be monitored. The current communication session may includes messages from one or more other user devices of one or more other users. A language set in at least one of the messages of the current communication session may be detected as triggering at least one of the translation rules in real-time. The language set in the at least one message may further be filtered in real-time based on the at least one translation rule, which may thereby modify the at least one message. Further, a presentation of the current communication session that is provided to the user device may be modified to include the filtered language set of the modified message instead of the triggering language set.

Abstract: A document translation method includes: displaying a source text display region, a translated text region, and an editing region, wherein textual content in a document to be translated is displayed in the source text display region, and reference translated text for the textual content is displayed in the translated text region; and providing a translated text recommendation from the reference translated text according to input from a user within the editing region. The method further includes: displaying the translation recommendation in the editing area as a translation result, if a confirmation operation for the translation recommendation is detected; and receiving a translation inputted by the user that is different from the translation recommendation and displaying the translation inputted by the user in the editing area as the translation result, if a non-confirmation operation for the translation recommendation is detected.

Abstract: A radio frequency identification (RFID) transponder includes a current control module for controlling a current consumption of a memory based on an amount of available power, and a control logic for controlling a memory operation in response to the control of the current consumption by the current control module. The RFID transponder further includes a power detector that is configured to continuously monitor and detect the amount of available power and output a power-dependent control signal. The power-dependent control signal is used by the RFID transponder to control the current consumption of the memory in dependence on the available power.

Abstract: An active radio frequency identification (“RFID”) tag receives an RFID interrogation signal via a first antenna. An integrated frequency reference in the RFID chip recovers the clock from the RFID interrogation and generates a reference clock for transmitting data responsive to the RFID interrogation. The integrated frequency reference generates the reference clock at the same frequency as the RFID interrogation for transmitting the response via the first antenna. The integrated frequency reference generates the reference clock at a different frequency for transmitting the response using a Bluetooth beacon message or a WiFi message via a second antenna. A mobile computing device can interrogate the RFID tag via an NFC interface and receive a response via a Bluetooth beacon messages or WiFi message received via a Bluetooth or wireless interface of the mobile computing device.

Abstract: Systems and methods for determining radio-frequency identification (RFID) tag proximity groups are provided. The method includes receiving RFID tag readings from multiple RFID tags. The method includes determining signal strengths of the RFID tag readings. The method includes determining pairs of RFID tags based on the RFID tag readings. The method also includes implementing a twin recurrent neural network (RNN) to determine proximity groups of RFID tags based on distance similarity over time between each of the pairs of the RFID tags.

Abstract: A tag reading apparatus comprises a passage that is configured to receive an RFID-tagged article that is to be registered in a transaction. The passage has an inlet end and an outlet end separated from each other in a first direction and width in a second direction. An antenna is in the passage at a position between the inlet and outlet ends in the first direction. An RFID reader is provided to read an RFID tag according to a response wave from the RFID tag received via the antenna. A controller is configured to identify the RFID-tagged article as being in the transaction according to a change in the response wave (such as a phase difference or intensity) corresponding to a movement of the RFID-tagged article from the inlet end to the outlet end.

Abstract: A display apparatus includes a sensor layer including sensors; a pixel layer disposed on the sensor layer and including pixel areas and pixels in the pixel areas; and an opaque layer disposed between the sensor layer and the pixel layer and having holes corresponding to light-transmitting areas of pixel areas in which pixels that emit light of a specific color are disposed.

Abstract: Techniques are disclosed relating to scoring partial matches between words. In certain embodiments, a method may include receiving a request to determine a similarity between an input text data and a stored text data. The method also includes determining, based on comparing one or more words included in the input text data with one or more words included in the stored text data, a set of word pairs and a set of unpaired words. Further, in response to determining that the set of unpaired words passes elimination criteria, the method includes calculating a base similarity score between the input text data and the stored text data based on the set of word pairs. The method also includes determining a scoring penalty based on the set of unpaired words and generating a final similarity score between the input text data and the stored text data by modifying the base similarity score based on the scoring penalty.

Abstract: In another aspect, a system for machine learning using a distributed framework, includes a computing device communicatively connected to a plurality of remote devices, the computing device designed and configured to select at least a remote device of a plurality of remote devices, determine a confidence level of the at least a remote device, and assign at least a machine-learning task to the at least a remote device, wherein assigning further comprises assigning at least a secure data storage task to the at least a remote device and assigning at least a model-generation task to the at least a remote device.

Abstract: A computer-implemented method for calculating Scalable Attributed Graph Embedding for Large-Scale Graph Analytics that includes computing a node embedding for a first node-attributed graph in a node embedded space. One or more random attributed graphs is generated in the node embedded space. A graph embedding operation is performed using a dissimilarity measure between one or more raw graphs and the one or more generated random graphs, and an edge-attributed graph into a second node-attributed graph using an adjoint graph.

Abstract: Embodiments are directed to data ingestion over a network. Raw data and integrated data associated with a plurality of separate data sources may be provided such that the raw data includes content associated with a plurality of subjects. Categorization models may be employed to categorize the raw data based on various features, such as, format, structure, data source, variability, volume, or associated entities. Matching models may be determined based on the categorization of the of the raw data, the integrated data and the content associated with the plurality of subjects. Matching models may generate a plurality of unified facts based on the raw data and the integrated data such that each unified fact is associated with a score associated with a quality of its match with a unified schema.

Abstract: Systems and methods for displaying a visual interface in a display of a head-mounted wearable device when the display may occlude objects in the user's physical environment while in use. An image detection device oriented generally in-line with the user's line of sight is used to capture at least one image. One or more objects are detected in the at least one image and, based on the detection of the one or more objects, an environmental interaction mode may be activated or deactivated. In the environmental interaction mode, the user interface may be modified or disabled to facilitate viewing of the physical environment.

Abstract: One or more computing devices, systems, and/or methods for hyper parameter optimization for machine learning ensemble generation are provided. For example, one or more base models are trained using diverse sets of hyper parameters, wherein different sets of hyper parameters (e.g., hyper parameters with different values) are used to train different base models. A matrix, populated with predictions from the set of base models, is generated. A machine learning ensemble is generated by processing the matrix utilizing a meta learner.

Abstract: A method is for matching a set of first classes assigned to a first data set with a set of second classes assigned to a second data set. The method includes constructing, via a set of pre-processing functions, a plurality of alignment profiles such that at least one alignment profile is assigned to each of the first classes and each of the second classes. The method includes generating a comparison matrix for each group of the alignment profiles, such that each group includes at least one of the first classes and at least one of the second classes. The method includes training a first machine learning model, through supervised training, based on the generated comparison matrices and based on probabilistic labels generated by a second machine learning model.

Abstract: A training method for an image denoising model that can include collecting multiple sample image groups through a shooting device, each sample image group including multiple frames of sample images with a same photographic sensitivity and sample images in different sample image groups having different photographic sensitivities.

Abstract: Systems and methods for semantic labeling of point clouds using images. Some implementations may include obtaining a point cloud that is based on lidar data reflecting one or more objects in a space; obtaining an image that includes a view of at least one of the one or more objects in the space; determining a projection of points from the point cloud onto the image; generating, using the projection, an augmented image that includes one or more channels of data from the point cloud and one or more channels of data from the image; inputting the augmented image to a two dimensional convolutional neural network to obtain a semantic labeled image wherein elements of the semantic labeled image include respective predictions; and mapping, by reversing the projection, predictions of the semantic labeled image to respective points of the point cloud to obtain a semantic labeled point cloud.

Abstract: Various embodiments, methods and systems for implementing a distributed computing system machine-learning training service are provided. Initially a machine learning model is accessed. A plurality of synthetic data assets are accessed, where a synthetic data asset is associated with asset-variation parameters that are programmable for machine-learning. The machine learning model is retrained using the plurality of synthetic data assets. The machine-learning training service is further configured for executing real-time calls to generate an on-the-fly-generated synthetic data asset such that the on-the-fly-generated synthetic data asset is rendered in real-time to preclude pre-rendering and storing the on-the-fly-generated synthetic data asset.

Abstract: Techniques for building a machine learning framework with tracking, model building and maintenance, and feedback loop are provided. In one technique, a prediction model is generated based on features of multiple entities. For each entity indicated in a first database, multiple feature values are identified, which include feature values stored in the first database and feature values based on sub-entity data regarding individuals associated with the entity. The feature values are input into the prediction model to generate a score for the entity. Based on the score, a determination is made whether to add, to a second database, a record for that entity. The second database is analyzed to identify other entities. For each such entity, a determination is made whether to generate a training instance; if so, a training instance is generated and added to training data, which is used to generate another prediction model.

Abstract: A method can include identifying a first key value of a first cell of a first grid of grids of cells to which a first feature maps, embedding the first grid into each cell of a second grid, identifying a second key value of a second cell of the second grid to which a second feature maps, the second key value representative of the first and second key values, comparing the identified key value to the key values of a memory, in response to determining the identified key value is in the memory, and providing data indicating a class associated with the identified key value in the memory.

Abstract: A computer-implemented method for reliably identifying objects in a sequence of input images received with the aid of an imaging sensor, positions of light sources in the respective input image being ascertained from the input images in each case with the aid of a first machine learning system, in particular, an artificial neural network, and objects from the sequence of input images being identified from the resulting sequence of positions of light sources, in particular, with the aid of a second machine learning system, in particular, with the aid of an artificial neural network.

Abstract: Methods, systems, an apparatus, including computer programs encoded on a storage device, for training an image classifier. A method includes receiving an image that includes a depiction of an object; generating a set of poorly localized bounding boxes; and generating a set of accurately localized bounding boxes. The method includes training, at a first learning rate and using the poorly localized bounding boxes, an object classifier to classify the object; and training, at a second learning rate that is lower than the first learning rate, and using the accurately localized bounding boxes, the object classifier to classify the object. The method includes receiving a second image that includes a depiction of an object; and providing, to the trained object classifier, the second image. The method includes receiving an indication that the object classifier classified the object in the second image; and performing one or more actions.

Abstract: Systems and methods for construction zone segmentation are provided. The system aligns image level features between a source domain and a target domain based on an adversarial learning process while training a domain discriminator. The target domain includes construction zones scenes having various objects. The system selects, using the domain discriminator, unlabeled samples from the target domain that are far away from existing annotated samples from the target domain. The system selects, based on a prediction score of each of the unlabeled samples, samples with lower prediction scores. The system annotates the samples with the lower prediction scores.

Abstract: Computer-implemented techniques for managing transactions of machine learning algorithm updates are described. In one embodiment, a computer-implemented is provided that comprises receiving, by a system operatively coupled to a processor, a request for an update to a machine learning model associated with a software program, wherein the request is received in accordance with a defined blockchain protocol, and wherein the request comprises model development data used in association with optimization of an instance of the machine learning model. The method further comprises, employing, by the system, a blockchain network to facilitate managing fulfillment of the request.

Abstract: A system for locating according to a data description includes an interface and a processor. The interface is configured to receive the data description. The processor is configured to create a model-based item identification job based at least in part on the data description; provide the model-based item identification job to a set of vehicle event recorder systems, wherein the model-based item identification job uses a model to identify sensor data resembling the data description; receive the sensor data from the set of vehicle event recorder systems; and store the sensor data associated with the model-based item identification job.

Abstract: An approach for improving determining a significant slice associated with a tumor from a volume of medical images is disclosed. The approach is based on the annotation of tumor range and the slice index in which the tumor appears to have the largest area. The approach infer a tumor growth classifier on sliding window of the volume slices and creates a discrete integral function out of the classifier predictions. The approach applies post processing on the discrete integral function which can include a smoothing function and a bias correction. The approach selects the slice index of maximum value from the post processing step.

Abstract: An improvement to automatic classifying of threat level of objects in CT scan images of container content, methods include automatic identification of non-classifiable threat level object images, and displaying on a display of an operator a de-cluttered image, to improve operator efficiency. The de-cluttered image includes, as subject images, the non-classifiable threat level object images. Improvement to resolution of non-classifiable threat objects includes computer-directed prompts for the operator to enter information regarding the subject image and, based on same, identifying the object type. Improvement to automatic classifying of threat levels includes incremental updating the classifying, using the determined object type and the threat level of the object type.

Abstract: Embodiments detect fraud of risk targets that include both customer accounts and cashiers. Embodiments receive historical point of sale (“POS”) data and divide the POS data into store groupings. Embodiments create a first aggregation of the POS data corresponding to the customer accounts and a second aggregation of the POS data corresponding to the cashiers. Embodiments calculate first features corresponding to the customer accounts and second features corresponding to the cashiers. Embodiments filter the risk targets based on rules and separate the filtered risk targets into a plurality of data ranges. For each combination of store groupings and data ranges, embodiments train an unsupervised machine learning model. Embodiments then apply the unsupervised machine learning models after the training to generate first anomaly scores for each of the customer accounts and cashiers.

Abstract: A non-transitory computer-readable medium stores computer-readable instructions configured to, when executed by a processor of an electronic device, cause the electronic device to display on a screen of a display an object for receiving an instruction to cause the electronic device to perform a specific operation including controlling an image processing device, obtain a position of the object in the screen, obtain a position of the indicator based on output signals from a millimeter wave radar, determine whether the position of the indicator is within a particular range relative to the position of the object, and when determining that the position of the indicator is within the particular range, transmit to the image processing device a preliminary operation command instructing the image processing device to start a preliminary operation to shorten a time required to complete the specific operation.

Abstract: In a printing device, a supply portion is configured to convey a tape in its longitudinal direction. The tape includes: a plurality of labels arranged continuously in the longitudinal direction; and a plurality of storage elements provided on respective ones of the plurality of labels. A first storage element is provided on a first label and configured to store first authentication data. The second storage element is provided on a second label and configured to store second authentication data. A printing portion is configured to print on the plurality of labels. A controller is configured to perform: reading the first authentication data from the first storage element and the second authentication data from the second storage element by a reading portion; and determining whether the first authentication data is correlated to the second authentication data to meet an authentication condition.

Abstract: Aspects described herein may allow for a payment card assembly including a payment card having a first surface, an opposed second surface, and an aperture extending through the payment card from the first surface to the second surface. An insert may be removably received in the aperture. Each of a plurality of identification elements may be configured to be removably received in the aperture and have an identification characteristic different than an identification characteristic of each of the other identification elements.

Abstract: Examples described herein describe a battery charger for a transaction card. According to some implementations, a charging device may detect a transaction card is received within a charging slot when an integrated circuit (IC) chip of the transaction card is in contact with a charging terminal; request a user device to provide power to charge the transaction card via the charging terminal, wherein the user device is communicatively coupled to the charging terminal; receive the power from the user device; and provide the power to the transaction card to charge a battery of the transaction card.

Abstract: An integrated circuit having Radio Frequency Identification components and circuitry used for authentication is discussed. The RFID components and circuitry include two or more coils and corresponding electrical circuits that are tuned to use two or more different resonant frequencies including: a first resonant RF used for power generation and a second resonant RF used for data communication. The integrated circuit contains a unique signature that is used for the authentication with two or more aspects including i) a first aspect that is a programmed password in a memory embedded on the integrated circuit, and ii) a second aspect that is a unique, randomly generated code based upon a physical characteristic of the integrated circuit.

Abstract: A multizone equipment tracking solution includes radio frequency identification (RFID) tags affixed to items of inventoried equipment; a plurality of RFID readers deployed in a plurality of different zones, including a transit zone and a storage zone, wherein an RFID reader in a transit zone comprises a mobile reader and a wireless signal strength measurement component; and a monitoring node. The RFID readers read tag codes from items that are in the different zones, and report the information to the monitoring node, permitting a real-time, end-to-end view of inventoried equipment across different zones. The RFID reader in the transit zone also measures a wireless signal strength (e.g., cellular) along a transit route and reports the measurements, thereby reducing a need for dedicated monitoring efforts by the wireless network operator. Reported data, may be advantageously mined to provide value for inventory management, while also providing cost savings for wireless network management.

Abstract: Embodiments of the present disclosure are directed towards a memory device removably couplable with a mobile device. In some embodiments, the memory device may include a PCB insertable in the mobile device. The PCB may include a first chip (a micro SD device); a second chip (a SIM card); a first contact electrically coupled with the first chip, to provide a first communication interface between the first chip and the mobile device; and a second contact electrically coupled with the second chip, to provide a second communication interface between the second chip and the mobile device. The first and second communication interfaces may provide for respective communications between the micro SD device and the mobile device, and between the SIM card and the mobile device, at the same time, when the PCB is removably coupled with the mobile device.

Abstract: A liquid lens includes a substrate, an anti-reflection (AR) coating, and a chipless radio frequency identification (RFID) tag. The substrate includes central and peripheral portions. The AR coating is disposed on the substrate. The chipless RFID tag is disposed in the peripheral portion to uniquely identify the liquid lens.

Abstract: The disclosure generally relates to networking infrastructure and, more particularly, to installing transient infrastructure for ubiquitous networking applications. A wireless gateway device is sent to physical premises with a parcel. After the wireless gateway device is delivered to the physical premises, a processor of the wireless gateway device draws power from the energy source to perform operations comprising executing program code stored in non-transitory processor-readable medium to establish a wireless communications connection with a network service through a first type of wireless communications interface. The wireless gateway device performs operations comprising establishing wireless communications with one or more wireless peripheral devices in the physical premises through the second type of wireless communications interface.