Content recommendation method based on heterogeneous feature deep residual network

Abstract

The invention discloses a content recommendation method based on a heterogeneous feature deep residual network, and the method comprises the steps: obtaining the source data of to-be-recommended content, carrying out the data conversion of the source data, and obtaining weighted hybrid embedded data; obtaining predicted score data according to the weighted hybrid embedded data and a deep residualnetwork model; and obtaining a recommendation result of the content according to the prediction score data. According to the embodiment of the invention, the source data of the domain content is processed, the processed data is input into the residual network model to obtain the predicted score data, and then the domain content is accurately recommended according to the predicted score data, so that the calculation method is high in efficiency, low in resource occupancy. And meanwhile, the diversified data can also avoid cold start when new users are recommended.

Description

technical field [0001] The present invention relates to the field of communication technology, in particular to a content recommendation method based on heterogeneous feature deep residual network. Background technique [0002] With the advent of the era of big data, people have a great demand for content recommendation in fields such as movies, articles, and medical treatment in the era of big data. In order to make good recommendations for content in many fields, many methods have emerged in the existing technology. However, the prior art method will have uncertainties in the steps of decomposing proofs, and the decomposed low-dimensional matrix will increase the time complexity of the algorithm, resulting in high computational consumption and low efficiency, and cold start problems will occur when new users are encountered, and, The prior art methods directly perform calculations on sparse data, resulting in high resource occupation and low algorithm efficiency. [0003]...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a content recommendation method based on a deep residual network with heterogeneous features in order to solve the problem of cold start when new users are encountered in the prior art. , and the prior art methods directly perform calculations on sparse data, resulting in high resource usage and low efficiency of calculation methods

Images