Abstract: A system is provided for reranking. The system comprises a user device and one or more servers. The system is configured to receive a plurality of candidate lists, rerank the plurality of candidate lists based on page-level information and a format of a recommendation page, generate recommendation results based on the reranked lists, and send the recommendation results to the user device. Each candidate list comprises a plurality of candidate items. The page-level information comprises interactions between the candidate items in each candidate list and between different candidate lists among the plurality of candidate lists. The reranking comprises using the format of the recommendation page to determine pairwise item influences between candidate item pairs among the candidate items in the candidate lists. The user device is configured to display the recommendation page with the recommendation results from the one or more servers.

Abstract: This disclosure relates to a natural language processing technology, and provides a sentence paraphrase method and apparatus. The method includes: paraphrasing an input sentence by using a sentence paraphrase model, to generate a plurality of candidate paraphrased sentences; and determining a similarity between each of the plurality of candidate paraphrased sentences and the input sentence, to obtain an output sentence whose similarity to the input sentence is greater than or equal to a preset threshold, where each of a plurality of paraphrased sentence generators in the sentence paraphrase model includes one neural network, the plurality of paraphrased sentence generators are trained by using source information and similarity information as a first reward, and the paraphrased sentence is obtained by paraphrasing the training sentence by using the plurality of paraphrased sentence generators.

Abstract: A system is provided for reranking. The system comprises a user device and one or more servers. The system is configured to receive a plurality of candidate lists, rerank the plurality of candidate lists based on page-level information and a format of a recommendation page, generate recommendation results based on the reranked lists, and send the recommendation results to the user device. Each candidate list comprises a plurality of candidate items. The page-level information comprises interactions between the candidate items in each candidate list and between different candidate lists among the plurality of candidate lists. The reranking comprises using the format of the recommendation page to determine pairwise item influences between candidate item pairs among the candidate items in the candidate lists. The user device is configured to display the recommendation page with the recommendation results from the one or more servers.

Abstract: A recommendation device obtains to-be-predicted data and a plurality of target reference samples based on a similarity between the to-be-predicted data and the plurality of reference samples. Each reference sample and the to-be-predicted data each include user feature field data indicating a feature of a target user, and item feature field data indicating a feature of a target item. Each target reference sample and the to-be-predicted data have partially identical user feature field data and/or item feature field data. The recommendation device obtains target feature information of the to-be-predicted data based on the plurality of target reference samples and the to-be-predicted data. The recommendation device then uses the target feature information as input to a deep neural network to obtain a target item that is to be recommended.

Abstract: A neural network building method and apparatus are disclosed, and relate to the field of artificial intelligence. The method includes: initializing a search space and a plurality of building blocks, where the search space includes a plurality of operators, and the building block is a network structure obtained by connecting a plurality of nodes by using the operator; during training, in at least one training round, randomly discarding some operators, and updating the plurality of building blocks by using operators that are not discarded; and building a target neural network based on the plurality of updated building blocks. In the method, some operators are randomly discarded. This breaks association between operators, and overcomes a co-adaptation problem during training, to obtain a target neural network with better performance.

Abstract: A neural network construction method and system in the field of artificial intelligence, to construct a target neural network by replacing a part of basic units in an initial backbone network with placeholder modules, so that different target neural networks can be constructed based on different scenarios. The method may include obtaining an initial backbone network and a candidate set, replacing at least one basic unit in the initial backbone network with at least one placeholder module to obtain a to-be-determined network, performing sampling based on the candidate set to obtain information about at least one sampling structure, and obtaining a network model based on the to-be-determined network and the information about the at least one sampling structure. The information about the at least one sampling structure may be used for determining a structure of the at least one placeholder module.

Abstract: Example user behavior prediction methods and apparatus are described. One example method includes obtaining a first contribution value of each piece of characteristic data for a specified behavior after obtaining behavior prediction information including a plurality of pieces of characteristic data. Every N pieces of characteristic data in the plurality of pieces of characteristic data may be processed by using one corresponding characteristic interaction model, to obtain a second contribution value of the every N pieces of characteristic data for the specified behavior. Finally, an execution probability of executing the specified behavior by a user may be determined based on the obtained first contribution value and the obtained second contribution value, to predict a user behavior. In the example method, interaction impact of the plurality of pieces of characteristic data on the specified behavior is considered during behavior prediction.

Abstract: This disclosure relates to a natural language processing technology, and provides a sentence paraphrase method and apparatus. The method includes: paraphrasing an input sentence by using a sentence paraphrase model, to generate a plurality of candidate paraphrased sentences; and determining a similarity between each of the plurality of candidate paraphrased sentences and the input sentence, to obtain an output sentence whose similarity to the input sentence is greater than or equal to a preset threshold, where each of a plurality of paraphrased sentence generators in the sentence paraphrase model includes one neural network, the plurality of paraphrased sentence generators are trained by using source information and similarity information as a first reward, and the paraphrased sentence is obtained by paraphrasing the training sentence by using the plurality of paraphrased sentence generators.

Abstract: In a recommendation-providing method in the field of artificial intelligence, an apparatus for generating recommendations obtains a recommendation system status parameter based on a plurality of historical recommended objects and a user behavior for each historical recommended object, such as clicks or downloads. The apparatus determines a target set among lower-level sets according to the recommendation system status parameter and a selection policy corresponding to an upper-level set, where the lower-level sets and upper-level set correspond to nodes on a clustering tree representing available to-be-presented objects, and each set corresponds to one selection policy. The apparatus then determines a target to-be-recommended object from the to-be recommended objects in the target set.

Abstract: This application discloses a picture file management method performed at a computing device, and an associated non-transitory computer storage medium. The method includes: obtaining a picture set; extracting, from the picture set, a picture meeting a policy and parsing the picture, to obtain geographical location information related to the picture; obtaining a real-time target location of a terminal according to the geographical location information related to the picture; tagging the real-time target location onto a map page, to generate a location tag for the picture; classifying at least one picture conforming to the real-time target location, to obtain a picture classification result; and obtaining a to-be-released picture according to the picture classification result and the location tag.

Abstract: Example user behavior prediction methods and apparatus are described. One example method includes obtaining a first contribution value of each piece of characteristic data for a specified behavior after obtaining behavior prediction information including a plurality of pieces of characteristic data. Every N pieces of characteristic data in the plurality of pieces of characteristic data may be processed by using one corresponding characteristic interaction model, to obtain a second contribution value of the every N pieces of characteristic data for the specified behavior. Finally, an execution probability of executing the specified behavior by a user may be determined based on the obtained first contribution value and the obtained second contribution value, to predict a user behavior. In the example method, interaction impact of the plurality of pieces of characteristic data on the specified behavior is considered during behavior prediction.

Abstract: Methods, apparatus, and computer-readable media are provided for analyzing a cluster of communications, such as B2C emails, to generate a template for the cluster that defines transient segments and fixed segments of the cluster of communications. More particularly, methods, apparatus, and computer-readable media are provided for generating and/or applying a trained structured machine learning model for a generated template that can be used to determine, for one or more transient segments of subsequent communications, a corresponding probability that a given semantic label is the correct semantic label for extracted content of the transient segment(s).

Abstract: This application discloses a picture file management method performed at a computing device, and an associated non-transitory computer storage medium. The method includes: obtaining a picture set; extracting, from the picture set, a picture meeting a policy and parsing the picture, to obtain geographical location information related to the picture; obtaining a real-time target location of a terminal according to the geographical location information related to the picture; tagging the real-time target location onto a map page, to generate a location tag for the picture; classifying at least one picture conforming to the real-time target location, to obtain a picture classification result; and obtaining a to-be-released picture according to the picture classification result and the location tag.

Abstract: Three-layer full-color dynamic electronic paper, comprising a substrate, a controller, a first EWOD display layer, a second EWOD display layer and a third EWOD display layer, wherein each of the first, second and third EWOD display layer is comprised of an upper transparent electrode plate, a hydrophobic insulating layer, pixel walls, colored ink, colorless liquid, a lower transparent electrode plate, an encapsulation adhesive, and a driving chip connected to the upper transparent electrode plate and the lower transparent electrode plate respectively; the lower transparent electrode plate of the third EWOD display layer is located above the substrate; the colored ink filled in the first, second and third EWOD display layer is cyan ink, magenta ink and yellow ink, respectively; and, the controller controls voltage waveforms of the three driving chips according to a subtractive color mixture principle of three primary colors for printing, so as to realize full-color displaying.