Abstract: The present application discloses a training method and an apparatus for a speech synthesis model, electronic device, and storage medium. The method includes: taking a syllable input sequence, a phoneme input sequence and a Chinese character input sequence of a current sample as inputs of an encoder of a model to be trained, to obtain encoded representations of these three sequences at an output end of the encoder; fusing the encoded representations of these three sequences, to obtain a weighted combination of these three sequences; taking the weighted combination as an input of an attention module, to obtain a weighted average of the weighted combination at each moment at an output end of the attention module; taking the weighted average as an input of a decoder of the model to be trained, to obtain a speech Mel spectrum of the current sample at an output end of the decoder.

Abstract: The present invention discloses an interactive control method executed during instant video communication between a user and one or more other users. The method comprises: monitoring video information collected by a camera during the instant video communication between the user and the one or more other users; performing recognition on the video information after acquiring the video information, to acquire user behavior data inputted by the user in a preset manner; determining whether the user behavior data comprises preset trigger information; when it is determined that the user behavior data comprises the preset trigger information, further determining whether the user behavior data comprises a preset gesture action; and when it is determined that the user behavior data comprises the preset gesture action, determining an operation instruction corresponding to the preset gesture action in a preset operation instruction set, and performing an event corresponding to the operation instruction.

Abstract: Embodiments of the present disclosure disclose a method and apparatus for determining image quality. The method comprises: acquiring a to-be-recognized image and facial region information used for indicating a facial region in the to-be-recognized image; extracting a face image from the to-be-recognized image on the basis of the facial region information; inputting the face image into a pre-trained convolutional neural network to obtain probabilities of each pixel comprised in the face image belonging to a category indicated by each category identifier in a preset category identifier set; inputting the face image into a pre-trained key face point positioning model to obtain coordinates of each key face point comprised in the face image; determining a probability of the face image being obscured on the basis of the probabilities and the coordinates; and determining whether the quality of the face image is up to standard on the basis of the probability.

Abstract: Provided are a data processing method and apparatus, a device, and a storage medium, which relate to the technical field of cloud computing and cloud platform. The specific implementation scheme includes: determining, according to logic information of first data acquired from an ordering tool, first physical addresses, where the first physical addresses are physical addresses of data shards in a physical data group associated with the first data; and sending the first physical addresses to the ordering tool to cause the ordering tool to order the first data according to the first physical addresses.

Abstract: The present application discloses a query auto-completion method and apparatus, a device and a computer storage medium, which relates to the technical field of intelligent search. An implementation includes: acquiring a query prefix input by a user currently, and determining candidate POIs corresponding to the query prefix; acquiring vector representation of query history information of the user and vector representation of each candidate POI; inputting the vector representation of the query history information of the user and the vector representation of each candidate POI into a pre-trained ranking model, so as to obtain a score of each candidate POI; and determining query completion suggestions recommended to the user according to the scores of respective candidate POIs. With the present application, the recommended query completion suggestions may better meet practical requirements of the user.

Abstract: Embodiments of the present disclosure disclose a machine learning training method and a server. The method includes: acquiring training data uploaded by the terminal; creating a trusted execution environment in response to a machine learning training request from the terminal; and performing machine learning training based on the trusted execution environment and the training data.

Abstract: Embodiments of methods and apparatuses for acquiring information are provided. One implementation of the method can include: determining an initial area corresponding to a target point of interest, and dividing the initial area corresponding to the target point of interest into a plurality of grids; and generating annotations of the plurality of grids respectively based on characteristics of the plurality of grids. Therefore, whether the user data associated with the each of the plurality of grids is used to generate the attribute of the target point of interest may be directly determined based on the annotation of the each of the plurality of grids, thereby saving the spending of the process of acquiring the user data required for generating the attribute of the target point of interest in data mining. The operation state of the target point of interest may be determined based on the annotation of the grid.

Abstract: Embodiments of the present disclosure relate to a method and apparatus for evaluating a translation quality. The method may include: acquiring a to-be-evaluated translation and a reference translation; inputting the to-be-evaluated translation and the reference translation into a pre-trained repetition coding model to obtain a semantic similarity between the to-be-evaluated translation and the reference translation, the repetition coding model being a neural network for calculating a probability of a pair of sentences being repetition sentences; analyzing the to-be-evaluated translation and the reference translation into two syntax trees respectively; calculating a similarity between the two syntax trees as a text similarity between the to-be-evaluated translation and the reference translation; and using a weighted sum of the semantic similarity and the text similarity as a translation quality score.

Abstract: The present application discloses a query auto-completion method and apparatus, a device and a computer storage medium, which relates to the technical field of intelligent search. An implementation includes: acquiring a query prefix input by a user currently, and determining candidate Points of Interest (POIs) corresponding to the query prefix; acquiring vector representation of spatial-temporal features of each candidate POI; inputting the vector representation of the spatial-temporal features of each candidate POI into a pre-trained ranking model, so as to obtain a score of each candidate POI; and determining query completion suggestions recommended to the user according to the scores of respective candidate POIs; wherein the spatial-temporal features include at least one of a query time feature and a distance feature between each candidate POI and the user. With the present application, a retrieval intention of the user may be better completed, and practical requirements of the user are met.

Abstract: A method and apparatus for displaying road names and a storage medium, the method comprises: performing collision detecting on and loading planned road names according to planned road name data and priority levels of the planned road names included in a navigation route; and performing collision detecting on and loading annotations of other map contents except the navigation route in a navigation map. The method and apparatus for displaying road names and the storage medium are used to enable a user to view the planned road names of the navigation route on an overview page of the navigational route, thereby improving guidance of map display for navigation.

Abstract: Embodiments of the present disclosure disclose a method and apparatus for processing information. A specific embodiment of the method comprises: determining whether to enable a scenario mode based on received voice information; in response to determining to enable the scenario mode, determining a target scenario according to an analysis result of the voice information; acquiring resource information related to the target scenario; and feeding back the acquired resource information to a user. In the scenario mode, the embodiment may s provide many kinds of information resources at the same time for the user to select. This helps to improve the efficiency of the user in acquiring the information and may improve the efficiency of the human-machine interaction.

Abstract: The present application provides a method and an apparatus for processing webpage, a device and storage medium, involving the terminal vision technology. The specific implementation is: when a server determines that a current network meets a preset condition and a webpage to be displayed includes an image required to be displayed, the server sends a static data resource corresponding to the image required to be displayed to the terminal. The preset condition includes at least one of the following: the current network being a mobile network, a bandwidth of the current network being less than a preset bandwidth, and a rate of the current network being less than a preset rate. Therefore, it is unnecessary to send a static data resource corresponding to an image not required to be displayed to the terminal, thereby reducing a traffic consumption and at the meanwhile, improving an integrity and coherence of the webpage.

Abstract: A response method and an apparatus thereof are provided. The method includes: receiving voice information sent through a client by a user; determining, based on the voice information, a user category to which the user belongs; and using voice matching the user category to respond to the voice information. Accordingly, response voice matches the user category of the user, which implements that the response is performed using the response voice targeted for the user category, and thus, the user experience may be improved.

Abstract: The present disclosure provides a method for extracting a geographic location point spatial relationship, and a method and apparatus for training an extracting model, and relates to the technical field of big data. A specific implementation solution is: obtaining second training data which include: a text, and marks of a geographic location point and geographic location point spatial relationship information in the text; training a geographic location point spatial relationship extracting model with the second training data, the geographic location point spatial relationship extracting model comprising an embedding layer, a transformer layer and a mapping layer; wherein the geographic location point spatial relationship extracting model is used to extract the geographic location point spatial relationship information from the input Internet text.

Abstract: The present disclosure provides a method and an apparatus for managing navigation broadcast, and a device, related to an Intelligent transportation technology field. A specific implementation solution includes: obtaining a geographical identifier of a user; obtaining a statement-conversion template set corresponding to the geographical identifier based on the geographical identifier of the user; converting a standard navigation broadcast statement based on the statement-conversion template set to generate a geographical navigation broadcast statement; and performing navigation broadcast based on the geographical navigation broadcast statement. Thereby, the navigation broadcasts are matched with respective regions, users in different regions are provided with diversified and personalized navigation broadcasts.

Abstract: The present application discloses a method for building a ranking model, a query auto-completion method and corresponding apparatuses, which relates to the technical field of intelligent search. An implementation includes: acquiring from a POI query log a query prefix input when a user selects a POI from query completion suggestions, POIs in the query completion suggestions corresponding to the query prefix and the POI selected by the user in the query completion suggestions; constructing positive and negative example pairs using the POI selected by the user and the POIs not selected by the user in the query completion suggestions corresponding to the same query prefix; and performing a training operation using the query prefix and the positive and negative example pairs corresponding to the query prefix to obtain the ranking model.

Abstract: Embodiments of the present disclosure provide a method and apparatus for performing word segmentation on a text, a device and a medium, which relate to the field of data processing technology and particularly to a smart search technology. The method may include: dividing a to-be-segmented text into at least two layers of character fragment combinations, any layer of character fragments being child character fragments of a previous layer of character fragments and/or parent character fragments of a next layer of character fragments; and segmenting the to-be-segmented text according to a target word granularity based on the at least two layers of character fragment combinations.

Abstract: According to embodiments of the present disclosure, a method and an apparatus for responding to a question, and a storage medium are provided. The method includes: determining a question characteristic representation corresponding to a question for an object; determining a comment characteristic representation corresponding to a first comment for the object; generating a first target characteristic representation by utilizing the question characteristic representation and the comment characteristic representation; and determining an answer for the question based on the first target characteristic representation.

Abstract: The present application provides a method and apparatus for multi-user collaborative creation, and a storage medium, where the method includes: obtaining, by a second terminal, a three-dimensional (3D) creation created by a first creator, the 3D creation including at least one creation element, obtaining creation information corresponding to each creation element according to the 3D creation, and determining the first creator corresponding to each creation element according to the creation information corresponding to each creation element. In the technical solution, the second terminal may conveniently and quickly determine the first creator corresponding to each creation element in the 3D creation, which simplifies the communication process for the creation and improves the creation efficiency.

Abstract: Disclosed embodiments include an NFC payment method and apparatus implemented on a mobile terminal. In some embodiments, an NFC payment function of a mobile terminal is activated; an NFC connection to a POS terminal is directly established in an inactive-screen state, so as to start the current payment process; payment authentication is performed on a user, so as to instruct the POS terminal to make a payment when the authentication is completed. Some embodiments of the present disclosure provides a more convenient and efficient NFC payment manner. In some embodiments, the system can directly invoke NFC quick payment in an inactive-screen state, which significantly reduces an operation time and operation cost of a user. Moreover, the user may need to be authenticated before the payment, which also guarantees the security of the payment. Therefore, some embodiments of the present disclosure provides better mobile quick payment experience for the user.