Abstract: Provided are an audio/video processing method and apparatus, a device, and a storage medium. The method comprises: displaying text data corresponding to an audio/video to be edited, wherein the text data has a mapping relation with an audio/video timestamp of said audio/video; displaying said audio/video according to a time axis track; in response to a preset operation triggered for target text data in the text data, determining an audio/video timestamp corresponding to the target text data as a target audio/video timestamp; and processing, on the basis of the preset operation, an audio/video clip corresponding to the target audio/video timestamp in said audio/video.

Abstract: The present invention belongs to the technical field of coal transportation on fully mechanized mining faces, and particularly relates to a double-end chain tension force control system for a cross side-dumping type flight conveyor and a control method therefor. The double-end chain tension force control system includes a tail tensioning system, connected to a reversed loader at a tail of the flight conveyor; a head tensioning system, connected to a head of the flight conveyor, where the tail tensioning system and the head tensioning system together achieve double-end coordinated control of a chain transmission system on the flight conveyor to adjust a tension force; and a control system, collecting information about the tail tensioning system and the head tensioning system and controlling same.

Abstract: The present application provides a large-area perovskite layer and a preparation method thereof. The preparation method includes: dissolving raw materials of a perovskite in an ionic liquid or in a mixture of the ionic liquid and an organic solvent, thereby forming a perovskite precursor, and coating the perovskite precursor onto a surface of a crystalline silicon bottom cell, thereby forming the perovskite layer.

Abstract: The present invention belongs to the technical field of coal gangue recognition and sorting, and in particular, relates to a coal gangue recognition method based on visible-near-infrared spectrum and image multi-modal information fusion.

Abstract: A speech recognition method and apparatus, and an electronic device. The method comprises: obtaining a first speech; obtaining a first text corresponding to a previous segment of speech of the first speech; obtaining a first set, the first set comprising a plurality of text identifications and a text feature corresponding to each of the plurality of text identifications, the text feature being a feature associated with a plurality of subsequent texts of a text corresponding to the text identification, the text feature being associated with frequencies of the plurality of subsequent texts of the text in a text set, and the first set being determined based on the text set; and determining, based on the first text and the first set, text content associated with the first speech.

Abstract: A stacked cell and preparation method thereof. The stacked cell includes: a crystalline silicon cell; a conductive connecting layer located on a surface of the crystalline silicon cell; a first isolation layer extending from a surface of the conductive connecting layer facing away from the crystalline silicon cell to penetrate through the conductive connecting layer, and a perovskite cell located on the surface of the conductive connecting layer facing away from the crystalline silicon cell.

Abstract: Representative embodiments disclose mechanisms to perform visual intent classification or visual intent detection or both on an image. Visual intent classification utilizes a trained machine learning model that classifies subjects in the image according to a classification taxonomy. The visual intent classification can be used as a pre-triggering mechanism to initiate further action in order to substantially save processing time. Example further actions include user scenarios, query formulation, user experience enhancement, and so forth. Visual intent detection utilizes a trained machine learning model to identify subjects in an image, place a bounding box around the image, and classify the subject according to the taxonomy. The trained machine learning model utilizes multiple feature detectors, multi-layer predictions, multilabel classifiers, and bounding box regression.

Abstract: This application provides a camera module and an electronic device. The camera module includes a lens assembly, a sleeve assembly, a substrate, and a conductive assembly. The lens assembly is connected to the substrate via the sleeve assembly. The sleeve assembly includes at least two sleeves nested in sequence. For two adjacent sleeves, a first sleeve is nested in a second sleeve, and the first sleeve is capable of moving away from or toward the substrate relative to an axis of the second sleeve. The lens assembly is mounted in at least one target sleeve and is disposed opposite to a photosensitive chip on the substrate. A first end of the conductive assembly is connected to the substrate, a second end of the conductive assembly is connected to the target sleeve, and the target sleeve is conductively connected to a grounding line of the substrate via the conductive assembly.

Abstract: The present application provides a laminated solar cell and an application thereof. The solar cell comprises a p-type silicon layer (1), connecting layers, a perovskite layer (2), and electrode layers; the connecting layers comprise a first connecting layer (3), a second connecting layer (4), and a third connecting layer (5); the electrode layers comprise a first electrode layer (6) and a second electrode layer (7); and in the direction moving away from the p-type silicon layer (1), the first connecting layer (3), the perovskite layer (2), the second connecting layer (4), and the first electrode layer (6) which are connected in sequence are provided on the front surface of the p-type silicon layer (1), and the third connecting layer (5) and the second electrode layer (7) which are connected in sequence are provided on the back surface of the p-type silicon layer (1).

Abstract: According to the embodiments of the disclosure, a multimedia processing method, device, electronic device, and storage medium are provided by obtaining a first multimedia resource; determining an initial text content corresponding to the first multimedia resource by performing speech recognition on audio data of the first multimedia resource, the audio data of the first multimedia resource comprises speech data of the initial text content; determining an invalid text content in the initial text content, the invalid text content is semantically non-informative; determining a first playing position of speech data of the invalid text content in the first multimedia resource; and cropping the first multimedia resource based on the first playing position to obtain a second multimedia resource, wherein audio data of the second multimedia resource comprises speech data of a target text content but does not comprise the speech data of the invalid text content.

Abstract: A stacked cell and preparation method thereof. The stacked cell includes: a crystalline silicon cell; a conductive connecting layer located on a surface of the crystalline silicon cell; a first isolation layer extending from a surface of the conductive connecting layer facing away from the crystalline silicon cell to penetrate through the conductive connecting layer, and a perovskite cell located on the surface of the conductive connecting layer facing away from the crystalline silicon cell.

Abstract: The present application provides a large-area perovskite layer and a preparation method thereof. The preparation method includes: dissolving raw materials of a perovskite in an ionic liquid or in a mixture of the ionic liquid and an organic solvent, thereby forming a perovskite precursor, and coating the perovskite precursor onto a surface of a crystalline silicon bottom cell, thereby forming the perovskite layer.

Abstract: Disclosed is a wiring support capable of adjusting the width of a wire slot, including: a first end plate and a second end plate, each of the first end plate and the second end plate being provided with at least one wiring through slot; a first support plate and a second support plate that are slidably connected, the first support plate being provided with a plurality of first connecting portions in a sliding direction thereof, the second support plate being provided with a plurality of second connecting portions in a sliding direction thereof; and a separating member, including a folding portion, a first folding plate and a second folding plate, wherein the first folding plate and the second folding plate are connected by means of the folding portion, both the first folding plate and the second folding plate can be folded along the folding portion.

Abstract: Provided are an audio synthesis method and apparatus, an electronic device, and a readable storage medium. In the present solution, conversion from a text to an audio having a target timbre is achieved by means of a pre-trained voice synthesis model, the voice synthesis model comprising a first feature extraction sub-model and a second feature extraction sub-model, wherein the first feature extraction sub-model outputs, according to an inputted text to be processed, an acoustic feature comprising a bottleneck feature; the second feature extraction sub-model outputs, according to the inputted first acoustic features, a Mel spectrum feature corresponding to the text to be processed; according to the Mel spectrum feature corresponding to the text to be processed, the target audio corresponding to the text to be processed is obtained, and the target audio has the target timbre.

Abstract: Provided are an audio/video processing method and apparatus, a device, and a storage medium. The method comprises: displaying text data corresponding to an audio/video to be edited, wherein the text data has a mapping relation with an audio/video timestamp of said audio/video; displaying said audio/video according to a time axis track; in response to a preset operation triggered for target text data in the text data, determining an audio/video timestamp corresponding to the target text data as a target audio/video timestamp; and processing, on the basis of the preset operation, an audio/video clip corresponding to the target audio/video timestamp in said audio/video.

Abstract: Systems and methods directed to returning personalized image-based search results are described. In examples, a query including an image may be received, and a personalized item embedding may be generated based on the image and user profile information associated with a user. Further, a plurality of candidate images may be obtained based on the personalized item embedding. The candidate images may then be ranked according to a predicted level of user engagement for a user, and then diversified to ensure visual diversity among the ranked images. A portion of the diversified images may then be returned in response to an image-based search.

Abstract: According to the embodiments of the disclosure, a multimedia processing method, device, electronic device, and storage medium are provided by obtaining a first multimedia resource; determining an initial text content corresponding to the first multimedia resource by performing speech recognition on audio data of the first multimedia resource, the audio data of the first multimedia resource comprises speech data of the initial text content; determining an invalid text content in the initial text content, the invalid text content is semantically non-informative; determining a first playing position of speech data of the invalid text content in the first multimedia resource; and cropping the first multimedia resource based on the first playing position to obtain a second multimedia resource, wherein audio data of the second multimedia resource comprises speech data of a target text content but does not comprise the speech data of the invalid text content.

Abstract: Embodiments provide a method and an apparatus for determining speech similarity, and a program product, which relate to speech technology. The method includes: playing exemplary audio, and acquiring evaluation audio of a user, where the exemplary audio is audio of specified content that is read by using a specified language; acquiring a standard pronunciation feature corresponding to the exemplary audio, and extracting, from the evaluation audio, an evaluation pronunciation feature corresponding to the standard pronunciation feature, where the standard pronunciation feature is used to reflect a specific pronunciation of the specified content in the specified language; and determining a feature difference between the standard pronunciation feature and the evaluation pronunciation feature, and determining similarity between the evaluation audio and the exemplary audio according to the feature difference.

Abstract: The present disclosure relates to a solar battery including a first cell, and a second cell, and a first charge transport layer, a transparent conductive layer, a second charge transport layer and a polysilicon layer are disposed between the first photoelectric conversion layer of the first cell and the second photoelectric conversion layer of the second cell, and the second charge transport layer is disposed between the polysilicon layer and the transparent conductive layer, and the charge transport property of the second charge transport layer is the same as that of the polysilicon layer. In the solar battery of the present disclosure, a first charge transport layer, a transparent conductive layer, a second charge transport layer and a polysilicon layer are sequentially arranged between the first photoelectric conversion layer and the second photoelectric conversion layer.

Abstract: Aspects of the present disclosure relate to a providing related content recommendations in response to a user search query by supervising the training of pair embeddings using contrastive learning and pairwise co-click signals. The approach combines a two tower model architecture with a cascaded multilayer perceptron model to enable the adoption of variable combinations of input features and more representative learned pair embeddings. The learned embeddings undergo supervised contrastive loss training to generate a related content recommendation model, which is subsequently evaluated using both online and offline metrics. The related content recommendation model can provide results to search queries that improve recommendation quality and increase user engagement, thereby ultimately enhancing long term user experience.