User portrait determination method and device based on sparse matrix

The invention relates to a user portrait determination method and device based on a sparse matrix, electronic equipment and a computer readable medium. The method comprises the following steps: performing word segmentation processing on authorized annotation information to generate a character string set; matching the character string set with a vector mapping table to generate a corresponding information matrix; converting the information matrix into a sparse matrix; inputting the sparse matrix into a trained feature model to determine a user portrait; according to the method, the information of the user can be deeply mined, the user portrait can be quickly and accurately positioned, and the system transaction security is improved while the privacy security of the user is ensured. 本申请涉及一种依据稀疏矩阵的用户画像确定方法、装置、电子设备及计算机可读介质。该方法包括：对经授权后的标注信息进行切词处理以生成字符串集合；将所述字符串集合和向量映射表进行匹配以生成对应的信息矩阵；将所述信息矩阵转化为稀疏矩阵；将所述稀疏矩阵输入至经过训练的特征模型中以确定用户画像；本申请能够深度挖掘用户的信息，快速准确的对用户画像进行定位，在保证用户隐私安全的同时，提高系统交易安全性。