Special　external　environments　will　lead　to　significant　changes　in　the　use　behavior　and　dependence　degree　of　different　PT　travellers,　but　it　is　difficult　to　analyze　the　mechanism　of　the　hierarchy　shift　of　travelers＇　public　transportation　(PT)　dependence.　Exploring　travelers＇　dependence　on　PT　is　conducive　to　understanding　individuals＇　travel　choice　behavior　and　optimizing　PT　operation　organizations.　Developing　methods　for　analyzing　the　internal　causal　relationship　between　travelers＇　dependence　on　PT　and　the　key　influencing　factors　under　the　special　condition　is　an　issue.　Therefore,　the　individual　travel　chains　are　constructed　by　associating　and　matching　the　multisource　PT　big　data　and　travel　survey　data.　Thereafter,　the　K-means　algorithm　and　an　improved　Apriori　algorithm　are　developed　to　mine　the　frequent　association　rules　of　groups,　and　a　framework　of　cross-hierarchy　policy　implications　is　derived　based　on　the　differences　in　association　rules.　Finally,　the　stated　preference　survey　method　is　used　to　measure　the　effectiveness　of　the　policies.