Abstract: A guided pairing method includes generating a singles list by detecting a plurality of singles at a plurality of detector elements in a detector array, the plurality of singles falling within a plurality of detection windows; for each detection window of the plurality of detection windows in the singles list having exactly two singles of the plurality of singles, determining the line of responses (LORs) for each of the two singles of the plurality of singles; for each detection window of the plurality of detection windows in the singles list having more than two singles of the plurality of singles, determining all coincidences possible based on the more than two singles; generating a weight for said each coincidence of the coincidences based on the determined LORs for said each of the two singles of the plurality of singles; and pairing the more than two singles based on the generated weight for said each coincidence of the coincidences.

Abstract: Provided are an intelligent parking method and apparatus, relating to the technical field of vehicles. The method comprises: determining a target parking route from at least one pre-stored parking route; determining a target position point in the target parking route closest to a vehicle; sending a prompt message for driving the vehicle to the target position point to a driver of the vehicle when a current position point of the vehicle and the target position point satisfy a proximity matching condition; and when the vehicle drives to the target position point, controlling the vehicle to park according to the target parking route from the target position point. Thus, the driver merely needs to drive the vehicle to a vicinity of the target parking route, and the vehicle may perform intelligent parking and may complete intelligent parking at a longer distance.

Abstract: There are provided a display panel and a manufacturing method thereof. The display panel includes first and second display sub-panels with a gap region arranged therebetween; and a light-shielding layer at least located in the gap region, the first and second display sub-panels each include multiple pixel units arranged in an array, each pixel unit includes: a substrate; a data line on the substrate; a black matrix on a side of the data line away from the substrate, an orthographic projection of the data line on the substrate falls within that of the black matrix on the substrate, in at least one of the first and second display sub-panel, the black matrix of the pixel unit closest to the gap region and the light-shielding layer are arranged with an interval therebetween, the black matrix is located on a side of the light-shielding layer away from the gap region.

Abstract: A grafted polypropylene resin is prepared by a grafting reaction of a polar monomer capable of absorbing microwave so as to raise its temperature in a microwave field to more than 200° C. and a solid polypropylene resin using microwave irradiation without adding an initiator. The polar grafted polypropylene resin that does not contain initiator residues and does not have a significant reduction in molecular mass compared with a resin before grafting is obtained.

Abstract: A continuous operation method is employed for the microwave high-temperature pyrolysis of a solid material containing an organic matter. The method includes the steps of mixing a solid material containing an organic matter with a liquid organic medium; transferring the obtained mixture to a microwave field; and in the microwave field, continuously contacting the mixture with a strong wave absorption material in an inert atmosphere or in vacuum. The strong wave absorption material continuously generates a high temperature under a microwave such that the solid material containing an organic matter and the liquid organic medium are continuously pyrolyzed to implement a continuous operation.

Abstract: An online concierge system maintains historical orders received from a user that include one or more items. For items included in one more historical orders, the online concierge system determines an interval between orders including an item, providing an indication of a frequency with which the user orders the item. When the online concierge system receives a request to create an order from the user, in response to an amount of time between a most recently received order including the item and a time when the request was received is within a threshold duration of the interval between orders including the item, the online concierge system selects an item from a category including the item. The selected item may be the item or an alternative item in the category. Subsequently, the online concierge system displays an interface for the user that is prepopulated with information identifying the selected item.

Abstract: An online system trains a machine-learned lift prediction model configured as a neural network. The machine-learned lift prediction model can be used during the inference process to determine lift predictions for users and items associated with the online system. By configuring the lift prediction model as a neural network, the lift prediction model can capture and process information from users and items in various formats and more flexibly model users and items compared to existing methods. Moreover, the lift prediction model includes at least a first portion for generating control predictions and a second portion for generating treatment predictions, where the first portion and the second portion share a subset of parameters. The shared subset of parameters can capture information important for generating both control and treatment predictions even when the training data for a control group of users might be significantly smaller than that of the treatment group.

Abstract: An online system trains a machine-learned lift prediction model configured as a neural network. The machine-learned lift prediction model can be used during the inference process to determine lift predictions for users and items associated with the online system. By configuring the lift prediction model as a neural network, the lift prediction model can capture and process information from users and items in various formats and more flexibly model users and items compared to existing methods. Moreover, the lift prediction model includes at least a first portion for generating control predictions and a second portion for generating treatment predictions, where the first portion and the second portion share a subset of parameters. The shared subset of parameters can capture information important for generating both control and treatment predictions even when the training data for a control group of users might be significantly smaller than that of the treatment group.

Abstract: An online concierge system maintains historical orders received from a user that include one or more items. For items included in one more historical orders, the online concierge system determines an interval between orders including an item, providing an indication of a frequency with which the user orders the item. When the online concierge system receives a request to create an order from the user, in response to an amount of time between a most recently received order including the item and a time when the request was received is within a threshold duration of the interval between orders including the item, the online concierge system selects an item from a category including the item. The selected item may be the item or an alternative item in the category. Subsequently, the online concierge system displays an interface for the user that is prepopulated with information identifying the selected item.

Abstract: System and method for aspect-level sentiment classification. The system includes a computing device, the computing device has a processer and a storage device storing computer executable code. The computer executable code is configured to: receive an aspect term-sentence pair; embed the aspect term-sentence pair; parse the sentence using multiple parsers to obtain dependency trees, and perform edge union to obtain a merged graph; combine the embedding and the merged graph to obtain a relation graph; perform a relation graph neural network on the relation graph; extract hidden representation of the aspect term from updated relation neural network; and classify the aspect term based on the extracted representation to obtain a predicted classification label of the aspect term. During training, the computer executable code is further configured to calculate a loss function based on the predicted label and the ground truth label, and adjust parameters of models.

Abstract: The present invention provides a material conveying device including a material conveying groove, having a traveling track; a material bearing and conveying assembly, including: an annular chain; traveling units arranged on the chain at intervals, drivable by the chain to move on the traveling track along a material conveying direction, and provided with a bottom surface close to the material conveying groove, a top surface opposite the bottom surface and side surfaces extending between the top and bottom surfaces; a belt-shaped elastic material bearing portion, connected to the top surfaces and/or the side surfaces of the two adjacent traveling units; and a driving device to drive the chain to circularly rotate relative to the material conveying groove along the material conveying direction. The working state of material conveying equipment can be improved, and the stability and economic index of the equipment can be enhanced.

Abstract: An online concierge system trains a user interaction model to predict a probability of a user performing an interaction after one or more content items are displayed to the user. This provides a measure of an effect of displaying content items to the user on the user performing one or more interactions. The user interaction model is trained from displaying content items to certain users of the online concierge system and withholding display of the content items to other users of the online concierge system. To train the user interaction model, the user interaction model is applied to labeled examples identifying a user and value based on interactions the user performed after one or more content items were displayed to the user and interactions the user performed when one or more content items were not used.

Abstract: An online concierge system uses a model to predict a user's interaction with an item, based on a user embedding for the user and an item embedding for the item. For the model to account for more recent interactions by users with items without retraining the model, the online concierge system generates updated item embeddings and updated user embeddings that account for the recent interactions by users with items. The online concierge system compares performance of the model using the updated item embeddings and the updated user embeddings relative to performance of the model using the existing item embeddings and user embeddings. If the performance of the model decreases, the online concierge system adjusts the updated user embeddings and the updated item embeddings based on the change in performance of the model. The adjusted updated user embeddings and adjusted updated item embeddings are stored for use by the model.

Abstract: An online concierge system includes sponsored content items in an interface including different slots for displaying content items. A sponsored content item may be displayed in a single slot or in multiple adjacent slots. The online concierge system determines a content score for various sponsored content items indicating a likelihood of a user interacting with a sponsored content item and a position bias for slots in the interface indicating a likelihood of the user interacting with a slot independent of content in the slot. Position biases are different dependent on a number of slots in which a content item is displayed. The online concierge system generates a graph identifying potential placements of sponsored content items in slots by selecting content items in an order according to their content scores. Sponsored content items are positioned in slots according to a path through the graph that has the highest overall expected value.

Abstract: The present invention provides a material conveying device including a material conveying groove, having a traveling track; a material bearing and conveying assembly, including: an annular chain; traveling units arranged on the chain at intervals, drivable by the chain to move on the traveling track along a material conveying direction, and provided with a bottom surface close to the material conveying groove, a top surface opposite the bottom surface and side surfaces extending between the top and bottom surfaces; a belt-shaped elastic material bearing portion, connected to the top surfaces and/or the side surfaces of the two adjacent traveling units; and a driving device to drive the chain to circularly rotate relative to the material conveying groove along the material conveying direction. The working state of material conveying equipment can be improved, and the stability and economic index of the equipment can be enhanced.

Abstract: An online concierge system allows a user to provide a nutritional goal and uses the nutritional goal as a constraint for selecting candidate orders to display to the user. From prior orders from the user, the online concierge system generates order templates including combinations of generic item descriptions corresponding to items previously included in orders from the user. From the order templates, the online concierge system generates candidate orders including specific items from a warehouse corresponding to the generic item descriptions. The online concierge system selects a set of the candidate orders that each include specific items with combined nutritional information satisfying the user's nutritional goal. Based on probabilities of the user purchasing different candidate orders of the set, the online concierge system selects one or more candidate orders of the set for display to the user.

Abstract: An online concierge system trains a user interaction model to predict a probability of a user performing an interaction after one or more content items are displayed to the user. This provides a measure of an effect of displaying content items to the user on the user performing one or more interactions. The user interaction model is trained from displaying content items to certain users of the online concierge system and withholding display of the content items to other users of the online concierge system. To train the user interaction model, the user interaction model is applied to labeled examples identifying a user and value based on interactions the user performed after one or more content items were displayed to the user and interactions the user performed when one or more content items were not used.

Abstract: An online concierge system enables users to create lists of items and generate a link allowing other receiving users to access a list by selecting the link. When a receiving user selects the link, the online concierge system generates a user-specific list from the original list. The user-specific list includes user-specific items selected for the receiving user that replace items in the original list based on item availability to the receiving user, receiving user preferences, and other receiving user-specific criteria. The receiving user can then view the user-specific items in the user-specific list via an interface allowing the user-specific items in the user-specific list to be included in an order in a single interaction.

Abstract: An online concierge system trains a user interaction model to predict a probability of a user performing an interaction after one or more content items are displayed to the user. This provides a measure of an effect of displaying content items to the user on the user performing one or more interactions. The user interaction model is trained from displaying content items to certain users of the online concierge system and withholding display of the content items to other users of the online concierge system. To train the user interaction model, the user interaction model is applied to labeled examples identifying a user and value based on interactions the user performed after one or more content items were displayed to the user and interactions the user performed when one or more content items were not used.

Abstract: The present invention provides a scraper including a scraper body, having opposed bottom and top surfaces and a supporting body, formed on the bottom surface. The supporting body is provided with a mounting surface forming a part of the bottom surface. The mounting surface is provided with a rolling body able to support the scraping body when the scraper is located at a mounting position. The supporting body is a nonmetallic elastomer. The present invention also provides material conveying equipment using the scraper. By changing a contact and friction mode of the scraper and a conveying groove, a working state of the scraper and the a whole load of the conveyor are improved, idle load is reduced, and the whole service life of the scraper and even the scraper conveyor is prolonged.