Abstract: An energy storage system and a thermal management method therefor are provided. The method includes: loading a multi-agent reinforcement learning model pre-trained and optimized through a simulation environment; receiving state observation data at a current time instant; inputting the state observation data into the multi-agent reinforcement learning model for reinforcement learning and reasoning to output multi-control action information; and generating a control action information instruction based on the multi-control action information, transmitting the control action information instruction to a cooling system in the energy storage system, and performing by the cooling system, thermal management on the energy storage system in response to the control action information instruction.

Abstract: Methods and systems are presented for providing a computer platform that manages the impacts of government regulations on existing software processes of an online service provider. A regulation document is obtained from a government agency. The regulation document is processed, and legal obligations relevant to an online service provider are extracted from the regulation document. An ensemble machine learning model is used to recommend, for each of the legal obligations, software controls that can be implemented within one or more software processes of the online service provider to mitigate a risk of the legal obligations. The ensemble machine learning model may include an attribute-based model and a text-based model. An explainable visual interface is provided to present the recommended software controls and context that indicates to a user how the software controls are determined for the legal obligations.

Abstract: A conversion power supply and an autonomous electric energy replenishment method for an energy storage system are provided. An output terminal of the power supply module is connected to a second side of a first DC-DC converter through an energy storage element. A first side of the first DC-DC converter is connected to battery clusters of the energy storage system through a DC interface of the conversion power supply, so that under control by a conversion power supply controller, in a case that a voltage of a battery cluster is lower than a preset threshold, the first DC-DC converter receives the electric energy on the second side, and transmit the electric energy to the first side of the first DC-DC converter, to realize a electric energy replenishment function for at least one of the battery clusters and prevent battery failure due to over-discharge.

Abstract: Systems and methods are provided for automatically allocating test protocols to a plurality of test locations. Once such method includes a computing device executing a first stage machine learning prediction model (MLPM) based on protocol data for multiple test protocols for a test experiment to generate a first stage output. The first stage MLPM is trained based on historical allocation data for one or more prior test experiments. Multiple test sets are associated with the test protocols, and the first stage output includes, for multiple test locations, allocation prediction scores for the test protocols. Based on the first stage output, the computing device executes a second stage optimization model to generate a second stage output. The second stage output includes an allocation plan for the test protocols. The allocation plan identifies one or more of the test locations for each of the test protocols.

Abstract: The disclosure relates to a packaging structure for a power module, a packaging method and an electric vehicle. The packaging structure includes: a circuit board; at least one power chip, where each power chip is fastened on the circuit board, and each power chip is integrated with a sensor that is capable of detecting a working state of the power chip; and a signal chip, where the signal chip is fastened on the circuit board and separated from the power chip, a compiling program is preset in the signal chip, the signal chip is in a communication connection with each sensor, and the signal chip is configured to be capable of being in a communication connection with a predetermined device, so as to output working state data of each power chip to the predetermined device. By detecting the working state of each power chip, the power chip can be protected precisely in real time.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a robotic control policy to perform a particular task. One of the methods includes performing a meta reinforcement learning phase including using training data collected for a plurality of different robotic control tasks and updating a robotic control policy according to the training data, wherein the robotic control policy is conditioned on an encoder network that is trained to predict which task is being performed from a context of a robotic operating environment; and performing an adaptation phase using a plurality of demonstrations for the particular task, including iteratively updating the encoder network after processing each demonstration of the plurality of demonstrations, thereby training the encoder network to learn environmental features of successful task runs.

Abstract: The present disclosure is applicable to the technical field of metering and distributing of an adhesive dispensing machine, and provides a machine learning-based flexible intelligent adhesive dispensing method.

Abstract: The present invention relates to the fields of medicinal chemistry and pharmacotherapeutics, and in particular to a 2-cyano-3,12-dioxoolean-1,9(11)-dien-17-phenylacrylamide derivative and a preparation method thereof; and the present invention further relates to use of the novel compound in the preparation of an anticancer medicament.

Abstract: A method of quantization evaluation, including, receiving a floating point data set, determining a floating point neural network model output utilizing the floating point data set, quantizing the floating point data set utilizing a quantization model yielding a quantized data set, determining a quantized neural network model output utilizing the quantized data set, determining whether an accuracy error between the floating point neural network model output and the quantized neural network model output exceeds an predetermined error tolerance, determining a floating point neural network tensor output utilizing the floating point data set if the predetermined error tolerance is exceeded, determining a quantized neural network tensor output utilizing the quantized data set if the predetermined error tolerance is exceeded, determining a per-tensor error based on the floating point neural network tensor output and the quantized neural network tensor output and updating the quantization model based on the per-tenso

Abstract: Methods and systems are presented for providing a computer platform that manages the impacts of government regulations on existing software processes of an online service provider. A regulation document is obtained from a government agency. The regulation document is processed, and legal obligations relevant to an online service provider are extracted from the regulation document. An ensemble machine learning model is used to recommend, for each of the legal obligations, software controls that can be implemented within one or more software processes of the online service provider to mitigate a risk of the legal obligations. The ensemble machine learning model may include an attribute-based model and a text-based model. An explainable visual interface is provided to present the recommended software controls and context that indicates to a user how the software controls are determined for the legal obligations.

Abstract: Methods and systems are presented for providing a computer platform that manages the impacts of government regulations on existing software processes of an online service provider. A regulation document is obtained from a government agency. The regulation document is processed, and legal obligations relevant to an online service provider are extracted from the regulation document. An ensemble machine learning model is used to recommend, for each of the legal obligations, software controls that can be implemented within one or more software processes of the online service provider to mitigate a risk of the legal obligations. The ensemble machine learning model may include an attribute-based model and a text-based model. An explainable visual interface is provided to present the recommended software controls and context that indicates to a user how the software controls are determined for the legal obligations.

Abstract: Methods and systems are presented for providing a computer platform that manages the impacts of government regulations on existing software processes of an online service provider. A regulation document is obtained from a government agency. The regulation document is processed, and legal obligations relevant to an online service provider are extracted from the regulation document. An ensemble machine learning model is used to recommend, for each of the legal obligations, software controls that can be implemented within one or more software processes of the online service provider to mitigate a risk of the legal obligations. The ensemble machine learning model may include an attribute-based model and a text-based model. An explainable visual interface is provided to present the recommended software controls and context that indicates to a user how the software controls are determined for the legal obligations.

Abstract: Methods and systems are presented for providing a computer platform that manages the impacts of government regulations on existing software processes of an online service provider. A regulation document is obtained from a government agency. The regulation document is processed, and legal obligations relevant to an online service provider are extracted from the regulation document. An ensemble machine learning model is used to recommend, for each of the legal obligations, software controls that can be implemented within one or more software processes of the online service provider to mitigate a risk of the legal obligations. The ensemble machine learning model may include an attribute-based model and a text-based model. An explainable visual interface is provided to present the recommended software controls and context that indicates to a user how the software controls are determined for the legal obligations.

Abstract: Systems and methods for use in identifying weights to be employed in a selection algorithm associated with plant advancement are disclosed. One example method includes identifying a start set of weights for a selection algorithm associated with a breeding program, and for each scale parameter value in a schedule, and for each of N iterations, modifying the start set of weights based on the scale parameter value, identifying a set of germplasm based on at least the modified set of weights, advancing the modified set of weights to a next iteration as the start set of weights when certain criteria are satisfied, and identifying the modified set of weights as an output when the iteration is equal to N.

Abstract: The disclosure relates to a display device including: an organic light-emitting diode display panel, a fingerprint recognition layer located below the organic light-emitting diode display panel, and a light filtering layer located between the organic light-emitting diode display panel and the fingerprint recognition layer, where the light filtering layer is configured to filter out light rays with an incidence angle greater than a filter angle among light rays carrying fingerprint line information, and to transmit light rays with an incidence angle smaller than or equal to the filter angle, where the incidence angle is the angle between the light rays carrying fingerprint line information, and the direction perpendicular to the fingerprint recognition layer.

Abstract: A prism sheet, a backlight module, a display and a preparation method of the prism sheet are provided. The prism sheet includes a base layer and a prism layer located on a surface of a first side of the base layer, holes are provided inside the base layer, so that light received from a second side of the base layer reaches the prism layer through the holes, and the first side of the base layer and the second side of the base layer are opposite to each other.

Abstract: The disclosure relates to a display device including: an organic light-emitting diode display panel, a fingerprint recognition layer located below the organic light-emitting diode display panel, and a light filtering layer located between the organic light-emitting diode display panel and the fingerprint recognition layer, where the light filtering layer is configured to filter out light rays with an incidence angle greater than a filter angle among light rays carrying fingerprint line information, and to transmit light rays with an incidence angle smaller than or equal to the filter angle, where the incidence angle is the angle between the light rays carrying fingerprint line information, and the direction perpendicular to the fingerprint recognition layer.