Research on Precision Marketing Strategy of Rural Tourism Combining Big Data and Cloud Computing Technology

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

The integration similarity of some users

User	1	2	3	4	5	6	7	8	9
1	1.000	0.416	0.346	0.445	0.267	0.403	0.000	0.000	-0.282
2	0.406	1.000	0.331	0.461	0.349	0.376	0.311	0.020	-0.251
3	0.352	0.358	1.000	0.465	0.289	0.341	0.016	0.068	-0.242
4	0.444	0.429	0.409	1.000	0.336	0.367	0.013	-0.031	-0.306
5	0.256	0.326	0.288	0.349	1.000	0.562	0.041	0.267	-0.395
6	0.386	0.358	0.281	0.336	0.518	1.000	0.011	0.162	-0.368
7	0.052	0.276	0.059	0.027	0.026	0.016	1.000	0.077	0.031
8	0.000	0.032	0.030	-0.001	0.239	0.225	0.077	1.000	0.122
9	-0.263	-0.266	-0.208	-0.322	-0.402	-0.371	0.017	0.108	1.000

The interest similarity of some users

User	1	2	3	4	5	6	7	8	9
1	1.000	0.057	0.007	0.069	0.058	0.104	0.060	0.000	0.107
2	0.068	1.000	0.008	0.038	0.119	0.054	0.042	0.067	0.000
3	0.000	0.014	1.015	0.057	0.052	0.010	0.055	0.109	0.051
4	0.053	0.065	0.045	1.000	0.049	0.007	0.049	0.020	0.017
5	0.048	0.098	0.044	0.037	1.000	0.113	0.063	0.007	0.017
6	0.101	0.044	0.009	0.004	0.109	1.000	0.011	0.008	0.011
7	0.070	0.053	0.053	0.047	0.062	0.012	1.000	0.116	0.006
8	0.000	0.056	0.119	0.003	0.000	0.009	0.099	1.000	0.008
9	0.109	0.000	0.039	0.003	0.002	0.009	0.000	0.008	1.000

Collection of sites recommended by similar users

Sites	Bada mountain	Gulang island	Dujiang ancient city	Jade dragon snow mountain	Potala Palace	Huaqing Palace
Similarity	0.625	0.572	0.413	0.221	0.192	0.082

Clustering of tourist behavior preferences and basic property distribution

	Gender			Age
Cluster	Male	Female		<15	[15,25]	[26,45]	[46,65]	>65
1	58.65%	41.35%		1.44%	14.5%	28.23%	35.29%	20.54%
2	20.82%	79.18%		1.11%	40.31%	31.18%	16.8%	10.6%
3	50.27%	49.73%		1.25%	30.26%	32.31%	31.57%	4.61%
4	57.30%	42.70%		0%	18.14%	20.5%	40.08%	21.28%
Cluster	Monthly income			The biggest consumer project
	<5000	[5000, 10000]	>10000	Food	Dorm	Shop	Recreation	Scenic spot project
1	19.33%	56.13%	24.54%	12.09%	14.22%	26.12%	38.16%	9.41%
2	49.12%	37.93%	12.95%	26.6%	16.32%	3.3%	21.86%	31.92%
3	34.01%	32.53%	33.46%	15.07%	23.83%	16.22%	23.41%	21.47%
4	12.46%	37.92%	49.62%	25.42%	28.12%	5.99%	12.01%	28.46%

The result of the tourist behavior clustering (n=255)

Indicator	Behavior cluster result				F	Sig.
	1	2	3	4
1	-7	-8	9	-2	5.543	0.007
2	-6	17	-7	15	8.025	0.000
3	-16	14	3	6	4.141	0.014
4	12	3	3	-30	15.076	0.000
5	-2	4	-1	-1	0.191	0.002
…	…	…	…	…	…	…
31	-20	4	2	4	2.673	0.008
32	-23	-7	6	25	4.963	0.000
33	2	-8	-6	-8	19.907	0.004
34	-20	6	12	-4	5.092	0.014
35	15	-11	-17	20	16.198	0.000