The implication of mobile English teaching is that English teachers and students use mobile devices for English teaching and communication at the same time. In order to accurately evaluate language interpretation skills, it is necessary to construct a mobile information system sampling model of the restrictive factors of language interpretation skills. Then, the nonlinear information fusion method is combined with the time series cognition method to make a statistical cognition of language interpretation skills. The parameter of language interpretation skills constraint is a set of nonlinear time series. To this end, this paper studies the language interpretation skills mobile information system, proposes language interpretation skills, and constructs the constraint parameters of the language interpretation skills evaluation and cognition using an indicator cognition model. The quantitative recursive cognition method analyzes the language interpretation ability evaluation model and the entropy feature of language interpretation ability and extracts the constraint feature information. The combination of large-scale data information fusion and K-means clustering algorithms provides indexing and integration of index parameters for language interpreting skills. On this basis, the corresponding allocation scheme of teaching resources is formulated to realize the assessment of language interpretation skills. The experimental results of related big data clustering algorithms show that the English teaching method proposed in this paper is highly effective, and the evaluation accuracy and teaching resource utilization rate have been increased by 5% and 6%, respectively.