Abstract: The present disclosure discloses a method and an apparatus for generating a vector representation of a knowledge graph, and relates to a field of a field of artificial intelligence technologies. The detailed implementing solution is: obtaining a knowledge graph, the knowledge graph including a plurality of entity nodes; obtaining a context type and context data corresponding to the knowledge graph; and generating vector representations corresponding to the plurality of entity nodes by a context model based on the context data and the context type.

Abstract: Embodiments of the present disclosure relate to a method and apparatus for generating a neural network. The method includes: acquiring a target neural network, the target neural network corresponding to a preset association relationship, and being configured to use two entity vectors corresponding to two entities in a target knowledge graph as an input, to determine whether an association relationship between the two entities corresponding to the inputted two entity vectors is the preset association relationship, the target neural network comprising a relational tensor predetermined for the preset association relationship; converting the relational tensor in the target neural network into a product of a target number of relationship matrices, and generating a candidate neural network comprising the target number of converted relationship matrices; and generating a resulting neural network using the candidate neural network.

Abstract: Embodiments of the present disclosure are directed to a method and an apparatus for generating training data for a visual question answering (VQA) system, and a computer readable medium. The method for generating training data for a visual question answering system includes: obtaining a first set of training data of the visual question answering system, the first set of training data comprising a first question for an image in the visual question answering system and a first answer corresponding to the first question; obtaining information related to the image; generating a second question corresponding to the first answer based on the information to obtain a second set of training data for the image in the visual question answering system, the second set of training data comprising the second question and the first answer.

Abstract: Embodiments of the present disclosure relate to a method, an apparatus, a device and a computer readable medium for generating VQA training data. The method comprises: obtaining a first group of training data of the VQA system, the first group of training data including a first question for an image in the VQA system and a first answer corresponding to the first question; determining a second question associated with the first question in term of semantic; and determining a second answer corresponding to the second question based on the first question and the first answer, to obtain a second group of training data for the image in the VQA system, the second group of training data including the second question and the second answer.

Abstract: Embodiments of the present disclosure provide a method, apparatus, electronic device, and computer readable storage medium for image-based data processing. The method includes: determining, in response to an inputted query for an image, an attribute associated with an object presented in the image based on a preset mapping between the object and the attribute, further includes: determining a degree of correlation between the object and the query based on the object and the attribute, and still further includes: providing a response to the query based on the degree of correlation between the object and the query. The embodiments of the present disclosure can improve the performance of the system for image-based data processing.

Abstract: Embodiments of the present disclosure disclose a method, apparatus, device, and readable storage medium for image-based data processing. The method comprises: acquiring an image and a to-be-processed text; extracting features of a plurality of objects in the image, and extracting a feature of the text; fusing the features of the plurality of objects into a fused feature of the image based on a matching degree between the feature of the text and a feature of each object of the plurality of objects; and processing the text based on the fused feature of the image and the feature of the text. Embodiments of the present disclosure can accurately learn an association relationship between a text and each object in an image, and improve the processing accuracy.

Abstract: A method, apparatus, device, and storage medium for expanding data are disclosed. The method includes: acquiring a triplet from a knowledge graph; mining a relationship path equivalent to a relationship in the triplet from the knowledge graph, a subject in the triplet being used as a start point of the relationship path, and an object in the triplet being used as an end point of the relationship path; and expanding the triplet based on the relationship path to generate an expanded triplet. This implementation expands the triplet in the knowledge graph, and strengthens the association between the subject and the object in the triplet in a larger context, such that the association between the subject and the object in the triplet is more global.

Abstract: Embodiments of the present disclosure disclose a visual question answering model, an electronic device and a storage medium. The visual question answering model includes an image encoder and a text encoder. The text encoder is configured to perform pooling on a word vector sequence of a question text inputted, so as to extract a semantic representation vector of the question text; and the image encoder is configured to extract an image feature of a given image in combination with the semantic representation vector.

Abstract: Embodiments of the present disclosure relate to a method and apparatus for generating a neural network. The method includes: acquiring a target neural network, the target neural network corresponding to a preset association relationship, and being configured to use two entity vectors corresponding to two entities in a target knowledge graph as an input, to determine whether an association relationship between the two entities corresponding to the inputted two entity vectors is the preset association relationship, the target neural network comprising a relational tensor predetermined for the preset association relationship; converting the relational tensor in the target neural network into a product of a target number of relationship matrices, and generating a candidate neural network comprising the target number of converted relationship matrices; and generating a resulting neural network using the candidate neural network.

Abstract: Embodiments of the present disclosure disclose a method, apparatus, device, and readable storage medium for image-based data processing. The method comprises: acquiring an image and a to-be-processed text; extracting features of a plurality of objects in the image, and extracting a feature of the text; fusing the features of the plurality of objects into a fused feature of the image based on a matching degree between the feature of the text and a feature of each object of the plurality of objects; and processing the text based on the fused feature of the image and the feature of the text. Embodiments of the present disclosure can accurately learn an association relationship between a text and each object in an image, and improve the processing accuracy.

Abstract: Embodiments of the present disclosure provide a method, apparatus, electronic device, and computer readable storage medium for image-based data processing. The method includes: determining, in response to an inputted query for an image, an attribute associated with an object presented in the image based on a preset mapping between the object and the attribute, further includes: determining a degree of correlation between the object and the query based on the object and the attribute, and still further includes: providing a response to the query based on the degree of correlation between the object and the query. The embodiments of the present disclosure can improve the performance of the system for image-based data processing.

Abstract: Embodiments of the present disclosure relate to a method, an apparatus, a device and a computer readable medium for generating VQA training data. The method comprises: obtaining a first group of training data of the VQA system, the first group of training data including a first question for an image in the VQA system and a first answer corresponding to the first question; determining a second question associated with the first question in term of semantic; and determining a second answer corresponding to the second question based on the first question and the first answer, to obtain a second group of training data for the image in the VQA system, the second group of training data including the second question and the second answer.

Abstract: Embodiments of the present disclosure are directed to a method and an apparatus for generating training data for a visual question answering (VQA) system, and a computer readable medium. The method for generating training data for a visual question answering system includes: obtaining a first set of training data of the visual question answering system, the first set of training data comprising a first question for an image in the visual question answering system and a first answer corresponding to the first question; obtaining information related to the image; generating a second question corresponding to the first answer based on the information to obtain a second set of training data for the image in the visual question answering system, the second set of training data comprising the second question and the first answer.

Abstract: A touch panel is provided, which includes a sensing electrode layer formed on a strengthened upper-cover substrate. The sensing electrode layer includes a plurality of sensing electrodes, wherein at least one end of each of sensing electrode has a comb-shaped terminal extending outwards. The comb-shaped terminal includes at least one branch. A masking layer is formed on the sensing electrode layer and at least a part of the masking layer overlaps the comb-shaped terminal. Furthermore, a touch display using the touch panel is also provided.

Abstract: A touch panel is provided, which includes a sensing electrode layer formed on a strengthened upper-cover substrate. The sensing electrode layer includes a plurality of sensing electrodes, wherein at least one end of each of sensing electrode has a comb-shaped terminal extending outwards. The comb-shaped terminal includes at least one branch. A masking layer is formed on the sensing electrode layer and at least a part of the masking layer overlaps the comb-shaped terminal. Furthermore, a touch display using the touch panel is also provided.

Abstract: A lampholder and a luminaire are provided. The lampholder includes a recess, a base of which has a luminous unit installing side; and a reflecting flank, extending from the recess and having a reflecting face facing the luminous unit installing side. The luminaire includes the lampholder. With the lampholder and the luminaire, conventionally discrete lampholder and light reflecting shade are made into an integral lampholder, so that structure is more simple, and the connecting step of a light emitting shade and a lampholder is cut down. In addition, the recess configuration of the lampholder is usable for accommodating an externally arranged power supply of a luminous unit, thereby saving the storage space, and reducing the warehousing and logistics costs.

Abstract: A downlight is provided. The downlight includes an insulating housing, a power supply assembly, a reflection cup, a LED light source, and a diffusion cover, wherein, the interior of the insulating housing is divided into a first cavity and a second cavity, the power supply assembly is arranged in the first cavity, the reflection cup is arranged in the second cavity, the LED light source is arranged in the reflection cup and connected with the power supply assembly, the reflection cup is configured to dissipate the heat of the LED light source and reflect the light from it to the open end of the second cavity, and the diffusion cover encapsulated in the open end of the second cavity is configured to diffuse the light.

Abstract: A downlight is provided. The downlight includes an insulating housing, a power supply assembly, a reflection cup, a LED light source, and a diffusion cover, wherein, the interior of the insulated housing is divided into a first cavity and a second cavity, the power supply assembly is arranged in the first cavity, the reflection cup is arranged in the second cavity, the LED light source is arranged in the reflection cup and connected with the power supply assembly, the reflection cup is configured to dissipate the heat of the LED light source and reflect the light from it to the open end of the second cavity, and the diffusion cover encapsulated in the open end of the second cavity is configured to diffuse the light.

Abstract: A downlight is provided. The downlight includes an insulating housing, a power supply assembly, a reflection cup, a LED light source, and a diffusion cover, wherein, the interior of the insulated housing is divided into a first cavity and a second cavity, the power supply assembly is arranged in the first cavity, the reflection cup is arranged in the second cavity, the LED light source is arranged in the reflection cup and connected with the power supply assembly, the reflection cup is configured to dissipate the heat of the LED light source and reflect the light from it to the open end of the second cavity, and the diffusion cover encapsulated in the open end of the second cavity is configured to diffuse the light.

Abstract: A touch display having a laminated structure is provided in present disclosure. The touch display comprises a touch panel, a display module, and a step-shaped gasket element. The display module has a step-shaped structure formed due to a height difference, wherein the step-shaped structure is located in an edge area of the display module. The gasket element inosculates with the step-shaped structure of the display module to fill the height difference in the edge area of the display module. In accordance with present disclosure, the gasket element is not in a suspended state usually caused when the gasket element is not being supported by display module and is effectively laminated to an outer frame of display module, thereby enhancing the reliability of lamination of touch panel and display module. Moreover, a laminated structure and a laminating method for touch display having the laminated structure are provided in present disclosure.