The invention discloses an inference method facing to indefinite context of general fit calculation, which uses set pair analysis technology and related coefficient concept to infer and integrate primary context data sensed by a bottom sensor so as to acquire a high-layer context information technical proposal in a general fit calculation environment, and uses the set pair analysis technology and vector correlation coefficients to achieve quick, convenient, intuitive and reliable inference for the indefinite context; and the set pair analysis method effectively reflects the opposite unity relation of definite-indefinite systems, accords with natural dialectics and human thinking mode, and has the significance of methodology. In various actual context sensing applications, the set pair analysis method is simpler, more convenient and more effective to describe indefiniteness than the methods using probability theory, fuzzy set and the like. A connection degree expression is written to a form of vector for short as mu (W) = (a, b, c), and is named as identity-diversity reverse vectors of the set pair. The cosine of an included angle between the identity-diversity reverse vectors reflects the closing degree of the identity-diversity reverse vectors, when the cosine value of the included angle is larger, the difference is smaller, and the similarity is larger.