Abstract: The provided is a method and system for trajectory prediction based on Cro-IntentFormer. The method starts by preprocessing vehicle trajectory data collected by sensors to produce raw data suitable for model input. Vehicles are treated as nodes, and the distance between vehicles serves as the basis for determining whether there is an edge between two vehicle nodes. A physical relationship graph is constructed and, along with the raw data, input into a spatio-temporal feature extraction module to obtain the spatio-temporal features of the trajectory. The spatio-temporal feature matrix is then input into an intent prediction module to determine the predicted intentions of the vehicles. Based on the intent information output by the intent prediction module, a semantic relationship graph is reconstructed and input, along with the raw data, into the spatio-temporal feature extraction module to derive the semantic features of the trajectory.

Abstract: A system and method for training a neural network. In some embodiments, the system includes: a graphics processing unit cluster; and a computational storage cluster connected to the graphics processing unit cluster by a cache-coherent system interconnect. The graphics processing unit cluster may include one or more graphics processing units. The computational storage cluster may include one or more computational storage devices. A first computational storage device of the one or more computational storage devices may be configured to (i) store an embedding table, (ii) receive an index vector including a first index and a second index; and (iii) calculate an embedded vector based on: a first row of the embedding table, corresponding to the first index, and a second row of the embedding table, corresponding to the second index.

Abstract: The present invention discloses an iron-based cathode material for a sodium-ion battery, which comprises a Na3Fe2(SO4)3F material and a carbon-based material embedded into the bulk structure of Na3Fe2(SO4)3F material. The weight percentage of the carbon-based material is ranked between 1% and 10%. The present invention also provides a method for preparing the above-mentioned iron-based cathode material for a sodium-ion battery, and a corresponding sodium-ion full battery using the Na3Fe2(SO4)3F-based cathode material. The Na3Fe2(SO4)3F cathode material ensures desired electrochemical sodium storage performance, involving high specific sodium storage capacity, improved cycle stability and superior rate performance in comparison with that of various pristine NaxFey(SO4)z materials.

Abstract: Disclosed are reactive dyes and preparation methods thereof. The reactive dye may be prepared using heterocyclic primary amine as a diazo component, 4,4?-diamino-2,2?-stilbenedisulfonic acid, s-triazine, or ethylenediamine as a bridging group, and a dimonochlortriazine group as an active group. The color-changing compound is covalently bonded into the fiber chemical structure by nucleophilic substitution reaction between monochlorotriazine and the hydroxyl group in a textile structure, and the size of the conjugated system and the range of electron delocalization of the dye are changed by a reversible isomerization reaction of the hydroxyl group adjacent to the diazo group and the diazo group under different pH regulations. Moreover, the dye has a double color changing structure, which improves the capability of the dye combined with —H/—OH. The pH value range that can cause color changes in the dye is effectively expanded to include weak alkali, weak acid or even neutral conditions.

Abstract: The present invention discloses an iron-based cathode material for a sodium-ion battery, which comprises a Na3Fe2(SO4)3F material and a carbon-based material embedded into the bulk structure of Na3Fe2(SO4)3F material. The weight percentage of the carbon-based material is ranked between 1% and 10%. The present invention also provides a method for preparing the above-mentioned iron-based cathode material for a sodium-ion battery, and a corresponding sodium-ion full battery using the Na3Fe2(SO4)3F-based cathode material. The Na3Fe2(SO4)3F cathode material ensures desired electrochemical sodium storage performance, involving high specific sodium storage capacity, improved cycle stability and superior rate performance in comparison with that of various pristine NaxFey(SO4)z materials.

Abstract: A method of processing data may include receiving a stream of first keys associated with first data, receiving a stream of second keys associated with second data, comparing, in parallel, a batch of the first keys and a batch of the second keys, collecting one or more results from the comparing, and gathering one or more results from the collecting. The collecting may include reducing an index matrix and a mask matrix. Gathering one or more results may include storing, in a leftover vector, at least a portion of the one or more results from the collecting. Gathering one or more results further may include combining at least a portion of the leftover vector from a first cycle with at least a portion of the one or more results from the collecting from a second cycle.

Abstract: A character defect detection method and device are disclosed. The character defect detection method comprises: acquiring an image to be inspected containing a character and a template character image corresponding to the character, and converting the image to be inspected into an image having a format consistent with a format of the template character image; extracting a first valid area containing the character from the image to be inspected, and extracting a second valid area containing a template character from the template character image; obtaining a first image based on the first valid area, and obtaining a second image based on the second valid area; calculating a transformed image indicating an information difference between the first image and the second image based on the first image and the second image; and obtaining a character defect detection result of the image to be inspected based on information of the transformed image.

Abstract: Disclosed are reactive dyes and preparation methods thereof. The reactive dye may be prepared using heterocyclic primary amine as a diazo component, 4,4?-diamino-2,2?-stilbenedisulfonic acid, s-triazine, or ethylenediamine as a bridging group, and a dimonochlortriazine group as an active group. The color-changing compound is covalently bonded into the fiber chemical structure by nucleophilic substitution reaction between monochlorotriazine and the hydroxyl group in a textile structure, and the size of the conjugated system and the range of electron delocalization of the dye are changed by a reversible isomerization reaction of the hydroxyl group adjacent to the diazo group and the diazo group under different pH regulations. Moreover, the dye has a double color changing structure, which improves the capability of the dye combined with —H/—OH. The pH value range that can cause color changes in the dye is effectively expanded to include weak alkali, weak acid or even neutral conditions.

Abstract: A system and method for training a neural network. In some embodiments, the system includes: a graphics processing unit cluster; and a computational storage cluster connected to the graphics processing unit cluster by a cache-coherent system interconnect. The graphics processing unit cluster may include one or more graphics processing units. The computational storage cluster may include one or more computational storage devices. A first computational storage device of the one or more computational storage devices may be configured to (i) store an embedding table, (ii) receive an index vector including a first index and a second index; and (iii) calculate an embedded vector based on: a first row of the embedding table, corresponding to the first index, and a second row of the embedding table, corresponding to the second index.

Abstract: A system and method for training a neural network. In some embodiments, the system includes a computational storage device including a backing store. The computational storage device may be configured to: store, in the backing store, an embedding table for a neural network embedding operation; receive a first index vector including a first index and a second index; retrieve, from the backing store: a first row of the embedding table, corresponding to the first index, and a second row of the embedding table, corresponding to the second index; and calculate a first embedded vector based on the first row and the second row.

Abstract: A lens system having reduced physical size. The lens system includes multiple metalenses, lenses with metasurfaces, that integrate the lens and the free space and compress them into multiple layers of metasurfaces, significantly reducing the overall volume and weight of the imaging system while increasing its efficiency. The lens system also provides for tools that can accurately model 3D multilayer metasurfaces, carry out inverse design to find the optimal and fault-tolerant structure, fabricate the metasurfaces with multi-project wafer service, assemble them with a 3D-printed holder, and characterize the performance of the resulting ultra-compact imaging system.

Abstract: A method and device for testing product quality are disclosed. The method for testing product quality comprises: acquiring an image of a product to be tested; testing the image by using a pre-trained neural network model to obtain a testing result output by the neural network model; when the testing result indicates that the product to be tested is a defective product, performing a secondary judgment on the testing result according to position information of defective feature pixels in the image in the testing result, and determining whether the product to be tested is qualified according to a secondary judgment result. The method has high test accuracy, ensures the quality of product and facilitates reducing the labor cost of test.

Abstract: The present application provides a method and device for obtaining a predicted image of a truncated portion, an imaging method and system, and a non-transitory computer-readable storage medium. The method for obtaining a predicted image of a truncated portion comprises preprocessing projection data to obtain, by reconstruction, an initial image of the truncated portion; and calibrating the initial image based on a trained learning network to obtain the predicted image of the truncated portion.

Abstract: A method of processing data may include receiving a stream of first keys associated with first data, receiving a stream of second keys associated with second data, comparing, in parallel, a batch of the first keys and a batch of the second keys, collecting one or more results from the comparing, and gathering one or more results from the collecting. The collecting may include reducing an index matrix and a mask matrix. Gathering one or more results may include storing, in a leftover vector, at least a portion of the one or more results from the collecting. Gathering one or more results further may include combining at least a portion of the leftover vector from a first cycle with at least a portion of the one or more results from the collecting from a second cycle.

Abstract: A character defect detection method and device are disclosed. The character defect detection method comprises: acquiring an image to be inspected containing a character and a template character image corresponding to the character, and converting the image to be inspected into an image having a format consistent with a format of the template character image; extracting a first valid area containing the character from the image to be inspected, and extracting a second valid area containing a template character from the template character image; obtaining a first image based on the first valid area, and obtaining a second image based on the second valid area; calculating a transformed image indicating an information difference between the first image and the second image based on the first image and the second image; and obtaining a character defect detection result of the image to be inspected based on information of the transformed image.

Abstract: A computer aided scanning method for a medical device is provided in the present invention, comprising step 1: recognizing and analyzing a pre-scan image through a pre-trained neural network to determine and identify a region of interest in the pre-scan image; and step 2: determining, according to feature information of the identified region of interest, scanning parameters for further scanning of the region of interest. A medical device employing the above method and a computer readable storage medium for performing the method are further provided in the present invention. The method, the medical device, and the readable storage medium provided by the present invention can automatically identify a region of interest, determine a corresponding auxiliary line and subsequent scanning parameters, and improve the scanning efficiency and accuracy of the medical device.

Abstract: The present disclosure provides an elevator control method, apparatus, electronic device, storage medium and system, which relate to artificial intelligence technology. The method includes: obtaining a user instruction, where the user instruction is determined by a speech device based on a user's speech content; recognizing the user instruction and converting the user instruction into an elevator control instruction; and controlling an elevator via the elevator control instruction. The elevator control method provided by the present disclosure enables the user to control the elevator through the speech device without touching the elevator, and thereby reducing potential safety risk caused by multiple people touching the elevator.

Abstract: The present invention discloses an iron-based cathode material for a sodium-ion battery, which comprises a Na3Fe2(SO4)3F material and a carbon-based material embedded into the bulk structure of Na3Fe2(SO4)3F material. The weight percentage of the carbon-based material is ranked between 1% and 10%. The present invention also provides a method for preparing the above-mentioned iron-based cathode material for a sodium-ion battery, and a corresponding sodium-ion full battery using the Na3Fe2(SO4)3F-based cathode material. The Na3Fe2(SO4)3F cathode material ensures desired electrochemical sodium storage performance, involving high specific sodium storage capacity, improved cycle stability and superior rate performance in comparison with that of various pristine NaxFey(SO4)z materials.

Abstract: A method and device for dispatching service robots are disclosed. The method comprises: receiving a current task in real time, and acquiring effective robots matched with the current task in a working area according to a preset judging rule based on the current task; and selecting an optimum robot from the effective robots according to the current task and a preset dispatching rule, and sending the current task to the optimum robot, to execute a job corresponding to the current task; and adding the current task to a task set corresponding to the optimum robot. The present disclosure solves the problem of the conventional service robots of low work efficiency in use.

Abstract: The present application provides a method and device for obtaining a predicted image of a truncated portion, an imaging method and system, and a non-transitory computer-readable storage medium. The method for obtaining a predicted image of a truncated portion comprises preprocessing projection data to obtain, by reconstruction, an initial image of the truncated portion; and calibrating the initial image based on a trained learning network to obtain the predicted image of the truncated portion.