Abstract: The present disclosure discloses a method and apparatus for enhancing a PET parameter image, a device, and a storage medium. The method includes: obtaining, based on a preset mapping list, an input image corresponding to an original PET parameter image determined based on a dynamic PET image set; and inputting the input image into an image enhancement model, adjusting a model parameter of the image enhancement model based on the original PET parameter image and an output predicted PET parameter image until a preset number of iterations is met, and using the predicted PET parameter image as a target PET parameter image corresponding to the original PET parameter image; wherein the input image is a noise image, a dynamic PET image corresponding to a preset acquisition time range in the dynamic PET image set or a dynamic SUV image corresponding to the dynamic PET image.

Abstract: A method of forming a semiconductor device includes the following operations. A substrate is provided with a recess therein. An insulating layer is formed on a bottom of the recess. A seed layer is formed on the insulating layer. An epitaxial layer is grown in the recess from the seed layer.

Abstract: Techniques for robust multi-agent reinforcement learning (MARL) are described. An exemplary method includes initializing a plurality of parameters for a plurality of agents including at least policy parameters and action-value (Q) parameters; performing robust multi-agent reinforcement learning to learn polices for the agents, wherein in the learned polices no agent has an incentive to deviate, the agents include an implicit agent that is to select a worst-case at any given time during the learning process; and at least one agent utilizing its learned policy.

Abstract: Provided is a method for controlling a cleaning device, an apparatus for controlling a cleaning device, a cleaning device, and a readable storage medium. The method for controlling the cleaning device includes: obtaining an environmental characteristic parameter by detecting an operation environment of the cleaning device, the environmental characteristic parameter including at least one of a room characteristic parameter and an obstacle parameter; and controlling the cleaning device to perform cleaning according to the at least one of the room characteristic parameter and the obstacle parameter. In this way, the cleaning device can be controlled based on at least one of the room characteristic parameter and the obstacle parameter, which realizes different cleaning control manners in different scenarios, and fully satisfies user's needs.

Abstract: A method for transmission of computing power announcement is performed by a first computing power network element node. The method comprises: sending computing power announcement information of a target computing node to a second computing network element node, wherein the computing power announcement information comprises at least one of the following: first field information used for recording computing service capability information of the target computing node; second field information used for recording a computing resource state of the target computing node; and third field information used for recording a computing service state of the target computing node.

Abstract: The present disclosure relates to the field of display technology, and provides a display panel and a display apparatus. The display panel includes a display area and a frame area surrounding the display area. The display panel includes: a base substrate and a cover plate opposite to each other; one or more convex ribs on at least one of the base substrate and the cover plate, where each convex rib of at least some of the convex ribs includes a plurality of rib segments connected sequentially along an extension trajectory of the convex rib, and an angle is formed between adjacent two of the rib segments; and an encapsulation structure between the base substrate and the cover plate and covering the convex ribs. The present disclosure is capable of improving an encapsulation effect.

Abstract: A ramp generator includes an operational amplifier having an output to generate a ramp signal. An integration current source is coupled to a first input and a reference voltage is coupled to a second input of the operational amplifier. A feedback capacitor and a reset switch are coupled between the first input and the output of the operational amplifier. The reset switch is turned on to reset the ramp generator. A ramp event is configured to be generated in the ramp signal at the output of the operational amplifier in response to the reset switch being turned off. An assist current source is coupled between the output of the operational amplifier and ground. The assist current source is configured to conduct an assist current from the output of the operational amplifier to ground in response to the reset switch being turned off.

Abstract: The disclosure relates to a display panel, a method for fabricating the same, and a display device. The display panel includes: a base substrate including a first base substrate in a blind hole area and a second base substrate, the thickness of the first base substrate is smaller than the thickness of the second base substrate; an anode layer, a light-emitting layer, a cathode layer and an encapsulation layer arranged successively on the second base substrate, and the cathode layer and the encapsulation layer arranged successively on the first base substrate; wherein at least one installation hole is arranged in a display area of the display panel, the at least one installation hole is within the blind hole area and runs through the first base substrate and the respective layers on the first base substrate.

Abstract: A base station of a cleaning device and a cleaning system are provided. The base station of the cleaning device includes: a base station body having an accommodating chamber for accommodating the cleaning device and an opening for the cleaning device to enter or exit the accommodating chamber; and a water injection assembly including a movable base, and a movable plate, a lifting mechanism, and a water injection pipe that are disposed on the movable base. The water injection pipe is configured to inject water into the cleaning device. The lifting mechanism is configured to drive the water injection pipe to move. A first elastic member is disposed between the movable plate and a side wall of the accommodating chamber. The cleaning device is contacted with the movable plate during a water injection process of the water injection assembly.

Abstract: The present disclosure relates to a compound and the use thereof in the preparation of a medicament for treating Alzheimer's disease. The present disclosure provides a method for constructing an animal model of diseases with N-oleoyl-dopamine (OLDA) and the use of the model in drug screening and animal experimental research, wherein the animal model includes at least one of an animal model of neurodegenerative diseases, an animal model of intestinal permeability diseases, and an animal model of inflammatory diseases. The present disclosure is based on the discovery that OLDA has a new use for a neurodegenerative disease, an intestinal permeability disease, and an inflammatory disease, and based on OLDA, compounds that have a therapeutic effect on the above diseases are identified.

Abstract: This application provides a display module and an electronic device. A display module includes a first buffer member, and a first non-bending region, a bending region, and a second non-bending region. A support member is fastened on the display screen. A first metal plate member of the support member faces the first non-bending region. A first connection plate member of the support member faces the bending region. A second metal plate member of the support member faces the second non-bending region. The first connection plate member is provided with grooves. Openings of the grooves are located on a first surface of the metal part. Organic material are located in the grooves, and are connected to the metal part. The first buffer member is located between the first metal plate member and the second metal plate member.

Abstract: Disclosed are a display substrate and a display apparatus. The display substrate includes: a base substrate, including a display region and a non-display region; an encapsulation dam, disposed on the base substrate and located in the non-display region, and annularly surrounding the display region; and an overflow detection structure, disposed on the base substrate and located in the non-display region, and annularly surrounding the display region, where the overflow detection structure is located between a region where the encapsulation dam is located and the display region. The overflow detection structure includes: at least one convex part; and a reflection part on a side, facing away from the base substrate, of the convex part and at least partially covering the at least one convex part.

Abstract: A generative adversarial multi-headed attention neural network self-learning method for aero-engine data reconstruction belongs to the field of end-to-end self-learning of aero-engine missing data. First, the samples are pre-processed, and the machine learning algorithm is used to pre-fill the normalized data first, and the pre-filled information is involved in the network training as part of the training information. Second, a generative adversarial multi-headed attention network model is constructed and the trained sample set is used to train the generative adversarial multi-headed attention network model. Finally, the samples are generated using the trained sample generator G. The method uses the generative adversarial network to better learn the distribution information of the data, and uses parallel convolution and multi-headed attention mechanism to fully exploit the spatial and temporal information among the aero-engine data.

Abstract: The disclosure provides a speech synthesis method, and an electronic device. The technical solution is described as follows. A text to be synthesized and speech features of a target user are obtained. Predicted first acoustic features based on the text to be synthesized and the speech features are obtained. A target template audio is obtained from a template audio library based on the text to be synthesized. Second acoustic features of the target template audio are extracted. Target acoustic features are generated by splicing the first acoustic features and the second acoustic features. Speech synthesis is performed on the text to be synthesized based on the target acoustic features and the speech features, to generate a target speech of the text to be synthesized.

Abstract: A multi-scale hybrid attention mechanism modeling method for aero-engine remaining useful life prediction belongs to the field of health management and prediction technology for aero-engines. Firstly, preprocess the data to obtain the sample, set the RUL label, and obtain the true value of the remaining useful life of the sample. Secondly, a multi-scale hybrid attention mechanism model consisting of position encoding layer, feature extraction layer, and regression prediction layer is constructed. Thirdly, train the model, and make the difference between the predicted value output by the model and the true value of the remaining useful life by minimizing the loss function until it reaches the stop standard. Finally, use the trained model to predict the remaining useful life. The method can achieve full fusion of information from different time steps of a single sample, taking into account the correlation between all samples.

Abstract: A display substrate is provided. The display substrate includes a plurality of islands, a plurality of gaps, and a plurality of bridges; wherein a respective island of the plurality of islands includes a base substrate; one or more light emitting elements on the base substrate; and an encapsulating layer on a side of the one or more light emitting elements away from the base substrate, encapsulating the one or more light emitting elements; the encapsulating layer includes a first inorganic encapsulating sub-layer and a second inorganic encapsulating sub-layer; and in a cross-section along a plane perpendicular to the base substrate and intersecting the first inorganic encapsulating sub-layer and the second inorganic encapsulating sub-layer, an outermost edge of the first inorganic encapsulating sub-layer is encapsulated by the second inorganic encapsulating sub-layer, thereby rendering the outermost edge of the first inorganic encapsulating sub-layer unexposed.

Abstract: The present disclosure discloses a method and a device for controlling a cleaning robot, a cleaning robot, and a storage medium. The method include: acquiring an edge cleaning trajectory of the cleaning robot marked on a grid map; determining a central area grid associated with the cleaning robot in real time; and controlling the cleaning robot to exit an edge cleaning state in response to determining a repeated section of edge cleaning of the cleaning robot based on the edge cleaning trajectory and the central area grid. Compared to the related art, the present disclosure enables the cleaning robot to exit the edge cleaning state in time, avoiding repeated edge cleaning and improving the cleaning efficiency.

Abstract: The present application relates to a method for improving the product quality of an antibody-drug conjugate. The method comprises: conjugating a drug to be conjugated to an antibody to obtain an antibody-drug conjugate; and purifying the antibody-drug conjugate: a regulation solution is added to the antibody-drug conjugate, column chromatography flowthrough is performed to collect a product, and the product is further subjected to ultrafiltration and/or diafiltration concentration to obtain an antibody-drug conjugate with improved product quality. The obtained antibody-drug conjugate has high purity, a uniform DAR, no solvent residue, and stable quality. Moreover, the pretreatment of the antibody does not involve steps such as ultrafiltration and diafiltration, which simplifies antibody purification and reduces production costs.