Heterogeneous information network is a representation form of heterogeneous data. How to integrate the complex semantic information of heterogeneous data is one of the challenges faced by recommendation system. A high-order embedded learning framework for heterogeneous information networks based on weak ties is constructed by using rich semantic information and powerful information transmission capabilities of weak ties, which mainly includes three modules: initial information embedding, high-order information embedding aggregation and recommendation prediction. Initialization information embedded module first adopts the best trust path selection algorithm to avoid information loss caused by sampling a fixed number of neighbors in a full-relational heterogeneous information network. Then network nodes are effectively characterized by filtering out the semantic information of each node using the newly defined multi-task sharing feature importance measurement factor based on multi-head attention and combining it with the interactive structure. The high-order information embedding aggregation module realizes the expression of high-order information by integrating the representational ability of the weak ties and network embedding. And the hierarchical propagation mechanism of heterogeneous information network is utilized to aggregate the characteristics of sampled nodes into the nodes to be predicted. The recommendation prediction module uses the influence recommendation method of high-order information to complete the recommendation. UI-HEHo framework has the characteristics of rich types of embedded nodes, fusion of shared attributes, and implicit interactive information. Finally, the experiments have verified that UI-HEHo can effectively improve the accuracy of rating prediction, as well as the pertinence, novelty and diversity of recommendation generatio. Especially in application scenarios with sparse data,UI-HEHo behaved a good recommendation effect.