Abstract: A method for providing document category recommendations may include training a machine learning algorithm; receiving, from a user, a selection of an anchor document; retrieving a user co-viewing sequence; generating, via the trained machine learning algorithm, a sequence embeddings set based on the anchor document and the user co-viewing sequence; comparing the generated embeddings set to respective embeddings for a plurality of candidate sets; determining the candidate set closest to the generated embeddings; and presenting at least one category from the closest candidate set.

Abstract: A method of providing results from a search engine comprises generating an initial set based on a query received from a user; generating an attention value based on the query and on the initial set; applying the attention value to the initial set; and presenting a set of results in response to the query, wherein the results are generated according to the application of the attention value to the initial set.

Abstract: A method for ranking documents in search results includes defining a first training data set, the first training data set including, for each of a plurality of user queries, information respective of a document selected by a user from results responsive to the query and information respective of one or more documents within an observation window after the selected document in the results, and defining a second training data set, the second training data set including, for each of the plurality of user queries, information respective of the selected document. The method further includes training a first machine learning model with the first training data set, training a second machine learning model with the second training data set, and ranking documents of a further search result set according to the output of the first machine learning model and the output of the second machine learning model.

Abstract: A holder for holding a rolled-up newspaper comprises one or more elastic members and a grip that has a shaped surface for positioning against a rolled-up newspaper. When the one or more elastic members are secured to a rear surface of a vehicle seat back or to a literature pocket positioned on the rear surface of a vehicle seat back, the one or more elastic members urge the shaped surface of the grip towards the rear surface of the seat back, or of a literature pocket positioned between the grip and the rear surface of the seat back, such that when a rolled-up newspaper is positioned between the shaped surface of the grip and the rear surface of the seat back or the rear surface of the literature pocket, the newspaper is held in place between the shaped surface of the grip and the seat back or the literature pocket.

Abstract: A robotic cleaning system may include a docking station, a robotic cleaner that includes at least one of a first set of robot charging contacts or a second set of robot charging contacts, the first and second sets of robot charging contacts being configured to electrically couple the robotic cleaner to the docking station, a dust cup configured to removably couple to the robotic cleaner, and a mop module configured to removably couple to the robotic cleaner. When the mop module is coupled to the robotic cleaner, the robotic cleaner may be configured to electrically couple to the docking station using the first set of robot charging contacts. When the mop module is not coupled to the robotic cleaner, the robotic cleaner may be configured to electrically couple to the docking station using the second set of robot charging contacts.

Abstract: A robotic cleaner may include one or more driven wheels, at least one environmental sensor, and a mop module. The mop module may include a tank having a tank inlet and a tank outlet, a pad coupled at a bottom side of the tank, the pad configured to contact a surface to be cleaned and to receive liquid from the tank outlet, and a latch configured to transition between a latched position, a release position, and a refill position. When in the latched position and in the release position, at least a portion of the latch may extend over the tank inlet and, when in the refill position, the latch may be displaced from the tank inlet, exposing the tank inlet.

Abstract: A method for ranking documents in search results includes defining a first training data set, the first training data set including, for each of a plurality of user queries, information respective of a document selected by a user from results responsive to the query and information respective of one or more documents within an observation window after the selected document in the results, and defining a second training data set, the second training data set including, for each of the plurality of user queries, information respective of the selected document. The method further includes training a first machine learning model with the first training data set, training a second machine learning model with the second training data set, and ranking documents of a further search result set according to the output of the first machine learning model and the output of the second machine learning model.

Abstract: A method for training a machine learning model includes receiving a randomly-initialized first version of a machine learning model, conducting first training on the machine learning model first version using first training data, the first training data comprising a first type of information respective of a plurality of documents, adding a layer to the machine learning model first version after conducting the first training to create a machine learning model second version, and conducting second training on the machine learning model second version using second training data, the second training data comprising a second type of information respective of the plurality of documents.

Abstract: A method of determining item features and organizing an interface according to the features includes determining a plurality of features of a plurality of items, the plurality of items accessible through an electronic interface, applying a plurality of machine learning models to the determined features, wherein each of the machine learning models calculates a correlation of each feature to characteristic determinative of user selection on the electronic interface, calculating respective Shapley values of each correlation determined by each of the plurality of machine learning models, determining one or more of the item features that are most strongly correlated with the determinative characteristic according to the respective Shapley values, and causing the electronic interface to be organized according to the determined most strongly correlated item features.

Abstract: An automated or robotic mud-logger having a slurry sampler to collect a slurry sample online from a drilling fluid circuit contemporaneous with drilling of a borehole, the slurry sample including drilling fluid and rock cuttings. A liquid separator removes drilling fluid from the slurry sample and discharges a sample of the rock cuttings. A spectrometer performs elemental analysis of the sample of the rock cuttings substantially in real time with collection of the slurry sample.

Abstract: A method of providing results from a search engine comprises generating an initial set based on a query received from a user; generating an attention value based on the query and on the initial set; applying the attention value to the initial set; and presenting a set of results in response to the query, wherein the results are generated according to the application of the attention value to the initial set.

Abstract: A method for ranking documents in search results includes defining a first training data set, the first training data set including, for each of a plurality of user queries, information respective of a document selected by a user from results responsive to the query and information respective of one or more documents within an observation window after the selected document in the results, and defining a second training data set, the second training data set including, for each of the plurality of user queries, information respective of the selected document. The method further includes training a first machine learning model with the first training data set, training a second machine learning model with the second training data set, and ranking documents of a further search result set according to the output of the first machine learning model and the output of the second machine learning model.

Abstract: Systems and methods for classifying job skills based on a job skill taxonomy built using artificial intelligence are described. The method may include identifying a set of job skill terms from a corpus of job description documents, generating a synonym file by associating each of the job skill terms with a canonical job skill, extracting a set of job skills from the corpus of job description documents using the synonym file, generating job skill relationship information based on the extracted set of job skills, and creating a job skill taxonomy based on the job skill relationship information, wherein the job skill taxonomy comprises a hierarchy of job skills.

Abstract: Techniques are provided for reducing or mitigating phase noise of a digital phase lock loop or the system depending on the digital phase lock loop. In an example, a multiple-mode digital phase lock loop can include a digital phase lock loop (DPLL), multiple frequency scalers configured to receive a reference clock, and a multiplexer configured to receive a mode command signal and to couple an output of one of the multiple frequency scalers to an input of the DPLL in response to a state of the mode command signal.

Abstract: A method includes determining, by a processor of a computing device, user behavior data comprising a plurality of ordered user interactions with a plurality of items via an electronic interface. The method further includes replacing, by the processor, each of the plurality of items in the user behavior data with a respective item type of a plurality of item types and replacing, by the processor, a predetermined number of the respective item types in the plurality of ordered user interactions with a respective parent item type of a plurality of parent item types from an item taxonomy. The method further includes inputting, by the processor, the plurality of ordered user interactions into a machine learning algorithm to train the machine learning algorithm to determine an anchor/accessory relationship between at least one of the plurality of item types and at least one of the plurality of parent item types.

Abstract: A holder for holding a rolled-up newspaper comprises one or more elastic members and a grip that has a shaped surface for positioning against a rolled-up newspaper. When the one or more elastic members are secured to a rear surface of a vehicle seat back or to a literature pocket positioned on the rear surface of a vehicle seat back, the one or more elastic members urge the shaped surface of the grip towards the rear surface of the seat back, or of a literature pocket positioned between the grip and the rear surface of the seat back, such that when a rolled-up newspaper is positioned between the shaped surface of the grip and the rear surface of the seat back or the rear surface of the literature pocket, the newspaper is held in place between the shaped surface of the grip and the seat back or the literature pocket.

Abstract: Systems and methods for classifying job skills based on a job skill taxonomy built using artificial intelligence are described. The method may include identifying a set of job skill terms from a corpus of job description documents, generating a synonym file by associating each of the job skill terms with a canonical job skill, extracting a set of job skills from the corpus of job description documents using the synonym file, generating job skill relationship information based on the extracted set of job skills, and creating a job skill taxonomy based on the job skill relationship information, wherein the job skill taxonomy comprises a hierarchy of job skills.

Abstract: An automated or robotic mud-logger having a slurry sampler to collect a slurry sample online from a drilling fluid circuit contemporaneous with drilling of a borehole, the slurry sample including drilling fluid and rock cuttings. A liquid separator removes drilling fluid from the slurry sample and discharges a sample of the rock cuttings. A spectrometer performs elemental analysis of the sample of the rock cuttings substantially in real time with collection of the slurry sample.

Abstract: Techniques are provided for reducing or mitigating phase noise of a digital phase lock loop or the system depending on the digital phase lock loop. In an example, a multiple-mode digital phase lock loop can include a digital phase lock loop (DPLL), multiple frequency scalers configured to receive a reference clock, and a multiplexer configured to receive a mode command signal and to couple an output of one of the multiple frequency scalers to an input of the DPLL in response to a state of the mode command signal.

Abstract: Sequence trigger circuitry may be configured to repeat command sequences to switch between communication modes of a RFFE. The circuitry may include a first logic circuitry to, in response to a trigger signal, generate a first output signal or a second output signal to activate a first command sequence or a second command sequence, respectively. The circuitry may also include a second logic circuitry to activate a third command sequence based on a comparison of a clock output signal with a first timer value and upon generating the first output signal. The first command sequence and the third command sequence may switch the RFFE into a receive mode of the plurality of modes. The circuitry may include a third logic circuitry to activate a fourth command sequence based on a comparison of the clock output signal with a second timer value and upon generating the second output signal.