When systematically analyzing social, economic and scientific management problems, people often face a complex system composed of many interrelated and mutually restrictive factors, and this system often lacks quantitative data.

In such a system, people are interested in a question: as far as a certain property owned by n different things is concerned, how should we allocate the degree (ranking weight) of any given property so that these values can objectively reflect the differences between different things in this property?

Analytic Hierarchy Process (AHP) provides a new, concise and practical modeling method for decision-making and sequencing of such problems. It decomposes complex problems into constituent factors, forms a hierarchical structure according to the dominant relationship, and then determines the relative importance of decision-making schemes by pairwise comparison.

Analytic Hierarchy Process (AHP) is widely used in management decision-making of economic, scientific, cultural, military, environmental and even social development.

It is often used to solve problems such as comprehensive evaluation, decision-making scheme selection, estimation and prediction, and input distribution.

Using analytic hierarchy process to solve problems can be roughly divided into four steps:

1. Establish the hierarchical structure of the problem; (First, the complex problem is decomposed into components called elements, which are divided into several groups according to different attributes to form different levels. As a rule, elements at the same level dominate some elements at the next level, and at the same time, they are dominated by elements at the next level. This top-down dominant relationship forms a hierarchical system. The top level usually has only one element, which is usually the predetermined goal or ideal result of analyzing the problem. The intermediate levels are generally standards and sub-standards. The bottom layer includes the decision-making scheme. The domination of elements between levels is not necessarily complete, that is, there can be such elements, which do not dominate all elements at the next level. )

2. Construct a pairwise comparison judgment matrix;

3. Calculate the relative weights of comparison elements from the judgment matrix;

4. Calculate the combination weight of elements at all levels.