Abstract: An information recommendation method, an apparatus, a device, and a medium based on embedding table compression are provided. The method includes: determining, based on a preset compression ratio, to-be-compressed features and non-compressed features in a to-be-compressed embedding table of a recommendation model, generating a similarity index matrix based on a similarity between the to-be-compressed features and the uncompressed features; generating an index dictionary based on the similarity index matrix; substituting a first feature mapping dictionary based on the index dictionary to generate a second feature mapping dictionary, wherein the first feature mapping dictionary is generated based on a data set; and acquiring to-be-recommended data, replacing features in the to-be-recommended data according to the second feature mapping dictionary, inputting replaced features into the recommendation model, and outputting a prediction result.

Abstract: The present invention discloses a method for controlling QoS, including setting a QPC for each kind of QoS guaranted services in a bearer network; transmitting a QoS guaranteed service to a corresponding QPC by the bearer network, transferring the service and carrying QoS related information in the service by the QPC, and transmitting the service to a QoS WAN according to the QoS related information by the bearer network. The present invention also discloses a kind of QPC. Through the scheme of the present invention, the services can be differentiated according to service type, so that the QoS guaranteed services can be accessed into a QoS WAN. Moreover, the existing network does not need much modification, and only a QPC loosely coupling with a bearer network needs to be added in the existing network. In addition, the scheme of the present invention further realizes service differentiation according to service type and user.