Abstract: Disclosed are a method for generating a dynamic image based on audio, a device, and a storage medium, relating to the field of natural human-computer interactions. The method includes: obtaining a reference image and reference audio input by a user; determining a target head pose feature and a target expression coefficient feature based on the reference image and a trained generation network model, and adjusting the trained generation network model based on the target head pose feature and the target expression coefficient feature, to obtain a target generation network model; and processing a to-be-processed image based on the reference audio, the reference image, and the target generation network model, to obtain a target dynamic image. An image object in the to-be-processed image is same as that in the reference image. In this case, a corresponding digital person can be obtained based on a single picture of a target person.

Abstract: Disclosed are a gated network-based generator, a generator training method, and a method for avoiding image coordinate adhesion. The generator processes, by using an image input layer, a to-be-processed image as an image sequence and inputs it to a feature encoding layer. Multiple feature encoding layers encode the image sequence by using a gated convolutional network, to obtain an image code. Moreover, multiple image decoding layers decode the image code by using an inverse gated convolution unit, to obtain a target image sequence. Finally, an image output layer splices the target image sequence to obtain a target image. Therefore, a character feature in the obtained target image is more obvious, making details of a facial image of generated digital human more vivid, whereby solving a problem of image coordinate adhesion in a digital human image generated by an existing generator using a generative adversarial network, and improving user experience.

Abstract: Disclosed are a gated network-based generator, a generator training method, and a method for avoiding image coordinate adhesion. The generator processes, by using an image input layer, a to-be-processed image as an image sequence and inputs it to a feature encoding layer. Multiple feature encoding layers encode the image sequence by using a gated convolutional network, to obtain an image code. Moreover, multiple image decoding layers decode the image code by using an inverse gated convolution unit, to obtain a target image sequence. Finally, an image output layer splices the target image sequence to obtain a target image. Therefore, a character feature in the obtained target image is more obvious, making details of a facial image of generated digital human more vivid, whereby solving a problem of image coordinate adhesion in a digital human image generated by an existing generator using a generative adversarial network, and improving user experience.

Abstract: The present invention discloses a hierarchical routing method oriented to a cross-boundary service network. The hierarchical routing method includes the following steps: (1): proposing reference services for services with same or similar functions in a service network, with differences in format and usage mode, and establishing a unified and standardized usage view for a user; and (2): establishing a method for mapping between the reference services and ordinary services to map the multiple ordinary services with similar functions into the unified reference services, and automatically selecting an optimal ordinary service when called by the user. The hierarchical routing method provided by the present invention can implement high-speed routing of service call in the service network, thereby providing a basis for aggregation and interoperation of cross-boundary services.

Abstract: The present invention discloses a hierarchical routing method oriented to a cross-boundary service network. The hierarchical routing method includes the following steps: (1): proposing reference services for services with same or similar functions in a service network, with differences in format and usage mode, and establishing a unified and standardized usage view for a user; and (2): establishing a method for mapping between the reference services and ordinary services to map the multiple ordinary services with similar functions into the unified reference services, and automatically selecting an optimal ordinary service when called by the user. The hierarchical routing method provided by the present invention can implement high-speed routing of service call in the service network, thereby providing a basis for aggregation and interoperation of cross-boundary services.

Abstract: The present invention discloses a service caching method for a cross-border service network, wherein the method includes: a cache space of a service switch node is divided into a resident area, a change area, a pre-reclaimed area and a maintenance index area; among them, a cache hit frequency is: a resident area>a change area>a pre-reclaimed area, and the maintenance index area is used for separate storage services call path. when a service call is generated, a cache content in the cache space is replaced according to a cache value of a missed cache or a hit cache; a service router and service switch nodes in the corresponding area jointly form a hierarchical cache mode. When the cache space of any node in the service switch node is insufficient, the service switch nodes in the same area perform collaborative cache and store them in other cache space of the service switch node through indexing.

Abstract: An imputation method for surface ultraviolet irradiance based on feasible cloud information and machine learning includes: establishing a deep learning model, wherein the deep learning model is designed to be a two-layered stacking ensemble learning model; constructing a first layer of the deep learning model as combination of multiple fundamental machine learning models; constructing a second layer of the deep learning model as Lasso model, which integrates an output from the first layer to obtain a final retrieval result; matching the surface ultraviolet irradiance with input features comprising cloud and meteorological information according to the temporal and spatial variables; establishing a statistical relationship between the surface ultraviolet irradiance and by training the deep learning model; and estimating the surface ultraviolet irradiance based on the trained deep learning model in regions with missing satellite observations of the surface ultraviolet irradiance.

Abstract: A retrieval method for surface ozone based on surface ultraviolet radiation irradiance includes: establishing a deep learning model; establishing a statistical relationship between input variables including surface UV irradiance, column ozone, elevation of a geolocation, year/month/date, latitude and longitude, and surface ozone concentrations at monitoring sites; matching a site-monitored surface ozone concentration with the surface UV irradiance and column ozone; training the deep learning model; estimating surface ozone concentrations in regions with available satellite observations based on the trained deep learning model; and inputting surface UV irradiance, column ozone, elevation of a geolocation, year/month/date, latitude and longitude into the trained deep learning model to estimate surface ozone concentration; evaluating an air quality based on the surface ozone concentration of the geolocation.

Abstract: The present invention discloses a service caching method for a cross-border service network, wherein the method includes: a cache space of a service switch node is divided into a resident area, a change area, a pre-reclaimed area and a maintenance index area; among them, a cache hit frequency is: a resident area>a change area>a pre-reclaimed area, and the maintenance index area is used for separate storage services call path. when a service call is generated, a cache content in the cache space is replaced according to a cache value of a missed cache or a hit cache; a service router and service switch nodes in the corresponding area jointly form a hierarchical cache mode. When the cache space of any node in the service switch node is insufficient, the service switch nodes in the same area perform collaborative cache and store them in other cache space of the service switch node through indexing.

Abstract: A parking lot entrance recognition method comprises the steps: reading GPS data of all vehicles appearing in a specified region within a specified time one-by-one; acquiring discontinuity points after it is confirmed that vehicle position information is lost; and comparing the discontinuity frequency of each discontinuity point with a frequency threshold to determine whether or not the discontinuity point is an entrance of an underground parking lot. In this way, the entrances of parking lots can be rapidly positioned, so that drivers can park conveniently and can also drive purposefully; and meanwhile, based on the analysis of the GPS data, the positioning accuracy is higher.

Abstract: A parking lot entrance recognition method comprises the steps: reading GPS data of all vehicles appearing in a specified region within a specified time one-by-one; acquiring discontinuity points after it is confirmed that vehicle position information is lost; and comparing the discontinuity frequency of each discontinuity point with a frequency threshold to determine whether or not the discontinuity point is an entrance of an underground parking lot. In this way, the entrances of parking lots can be rapidly positioned, so that drivers can park conveniently and can also drive purposefully; and meanwhile, based on the analysis of the GPS data, the positioning accuracy is higher.