图3给出了在不同最小支持度阈值的情况下，经典Apriori算法、最小兴

Figure 3 shows the comparison between the classic Apriori algorithm, the improved algorithm with a minimum interest threshold of 0.3, and the improved algorithm with a minimum interest threshold of 0.45 under different minimum support thresholds. It can be clearly seen that the improved algorithm mines fewer association rules under the same minimum support threshold, and the number of association rules mined is inversely proportional to the set minimum interest threshold. When the support threshold is 0.1 The improved algorithm with an interest threshold of 0.3 can effectively delete 50.4% of the association rules that are not of interest to users, while the improved algorithm with an interest threshold of 0.45 can delete 65.8% of the association rules that are not of interest to users. Therefore, in practical applications, relevant experts can set an appropriate minimum interest threshold through experience, so as to filter out association rules that users are not interested in. The algorithm overcomes the shortcomings of the classic Apriori algorithm that may dig out invalid strong association rules. Optimized.

Figure 3 shows the comparison between the classical Apriori algorithm, the improvement algorithm with a minimum interest threshold of 0.3, and the improvement algorithm with a minimum interest threshold of 0.45. It is obvious that the improvement algorithm digs at the same minimum support threshold with fewer association rules, and the number of associated rules mined is inversely proportional to the minimum interest threshold set, and in the case of the support threshold of 0.1, the improvement algorithm with an interest threshold of 0.3 can effectively remove 50.4% of the users are not interested in the associated rules, while the interest threshold of 0.45 improved algorithm removes 65.8% of the user is not interested in the rules. Therefore, in practical application, the relevant experts can set the appropriate minimum interest threshold through experience, so that the user is not interested in the association rules filtered out, the algorithm overcomes the classical Apriori algorithm may mine the disadvantages of invalid strong correlation rules, the algorithm is optimized.

Figure 3 shows the comparison among the classical Apriori algorithm, the improved algorithm with the minimum interest threshold of 0.3 and the improved algorithm with the minimum interest threshold of 0.45 under different minimum support thresholds. It is obvious that the improved algorithm can mine fewer association rules under the same minimum support threshold, and the number of association rules mined is inversely proportional to the set minimum interest threshold. When the support threshold is 0.1, the improved algorithm with interest threshold of 0.3 can effectively delete the association rules that 50.4% users are not interested in, The improved algorithm with interest threshold of 0.45 removes the association rules that 65.8% users are not interested in. Therefore, in practical application, relevant experts can set the appropriate minimum interest threshold through experience, which can filter out the association rules that users are not interested in. The algorithm overcomes the disadvantages of the classical Apriori algorithm that may mine invalid strong association rules, and optimizes the algorithm.<br>