A customer data analysis method and system for amusement device recommendation

Abstract

This invention relates to the field of data processing technology, and more particularly to a customer data analysis method and system for recommending amusement park rides. A customer data analysis method for recommending amusement park rides includes the following steps: S1: Obtaining cultural conflict elements of customers and equipment-related data for amusement park rides, and based on the customer's cultural conflict elements and equipment-related data, obtaining the number of spare non-cultural conflict equipment and the number of cultural conflict equipment in use for each amusement park ride; S2: Using a first recommendation formula based on the number of spare non-cultural conflict equipment, the number of cultural conflict equipment in use, and the equipment switching cost for each amusement park ride, obtaining the first recommendation degree of the target amusement park ride. This invention, by comprehensively considering the customer's cultural conflict elements, more comprehensively reflects the real needs of the customer group, and, combined with the actual operating status of the amusement park rides, formulates a recommendation scheme with strong adaptability and a high degree of personalization.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a customer data analysis method and system for recommending amusement equipment. Background Technology

[0002] With the diversified development of modern amusement parks and entertainment facilities, customer needs are showing a trend towards personalization, diversification, and group-based approaches. Traditional amusement equipment recommendations often focus on methods based on single indicators or static rules, such as recommending based on user interests, real-time equipment load, or queue length. These methods might match similar rides by analyzing users' historical play records or consumption data, or dynamically adjust recommendation priorities based on equipment idle status. However, they fail to consider conflicts between users' cultural background and the cultural elements of the amusement equipment (such as religious taboos or sensitivity to cultural symbols), leading to user rejection or equipment downtime. Furthermore, they neglect users' considerations regarding the functionality of each ride, thus failing to achieve precise amusement equipment recommendations based on customer data analysis. Therefore, an intelligent recommendation method that can improve user experience and operational efficiency is urgently needed. Summary of the Invention

[0003] To overcome the shortcomings of failing to accurately match recommendations based on group needs, this invention provides a customer data analysis method and system for recommending amusement equipment.

[0004] The technical solution is: a customer data analysis method for recommending amusement equipment, comprising the following steps:

[0005] S1: Obtain the customer's cultural conflict elements and equipment-related data of the amusement equipment, and based on the customer's cultural conflict elements and equipment-related data of the amusement equipment, obtain the number of spare non-cultural conflict equipment and the number of cultural conflict equipment used for each amusement project;

[0006] S2: Based on the number of spare non-cultural conflict equipment, the number of cultural conflict equipment used, and the equipment switching cost of each amusement attraction, the first recommendation formula is used to obtain the first recommendation degree of the target amusement attraction;

[0007] S3: Obtain group booking data of the target customer group, and use the demand detection model based on the group booking data to obtain the degree of demand for deepening intra-group relationships and the degree of demand for establishing inter-group relationships of the target customer group;

[0008] S4: Based on the degree of need to deepen relationships within the target customer group, the degree of need to establish relationships outside the group, and relevant recommendation data, use the second recommendation formula to obtain the second recommendation degree of the target amusement project;

[0009] S5: Based on the first and second recommendation levels of each amusement park attraction, priority recommendation attractions are obtained, and the priority recommendation attractions are displayed on the screen.

[0010] S6: Based on the customer's historical average consumption price and the consumption price of each amusement park attraction in the priority recommended projects, the priority recommended projects are further filtered to obtain the final recommended projects, and a route planning recommendation is made based on the final recommended projects.

[0011] Preferably, the step of acquiring customer data on cultural conflict elements and amusement equipment, and acquiring the number of spare non-cultural conflict equipment and the number of cultural conflict equipment in use for each amusement attraction based on the customer data on cultural conflict elements and amusement equipment, includes: acquiring customer data on cultural conflict elements and amusement equipment, wherein the equipment-related data includes the number of spare equipment for each amusement attraction, the number of cultural equipment in use for each amusement attraction, and the equipment switching cost for each amusement attraction; and acquiring the number of spare non-cultural conflict equipment and the number of cultural conflict equipment in use for each amusement attraction based on the customer data on cultural conflict elements, the number of spare equipment for each amusement attraction, and the number of cultural equipment in use for each amusement attraction, wherein the number of spare non-cultural conflict equipment is the number of spare equipment that does not have cultural conflict elements; and the number of cultural conflict equipment in use is the number of equipment with cultural conflict elements currently in use for the amusement attraction.

[0012] Preferably, the step of obtaining the first recommendation degree of the target amusement project using a first recommendation formula based on the number of spare non-cultural conflict equipment, the number of cultural conflict equipment in use, and the equipment switching cost of each amusement project includes: normalizing the number of spare non-cultural conflict equipment, the number of cultural conflict equipment in use, and the equipment switching cost of each amusement project, and then using the first recommendation formula to obtain the first recommendation degree of the target amusement project, wherein the first recommendation formula is:

[0013] ;

[0014] In the formula, The top recommendation for the target amusement park attraction; The number of backup non-cultural conflict equipment for the target amusement park project; The number of facilities used to address cultural conflicts in target amusement park attractions; Equipment switching costs for the target amusement park attraction; This is an adjustment factor.

[0015] Preferably, the equipment switching cost of each amusement attraction includes: obtaining the switching cost factors of each amusement attraction, including labor operation cost, consumable loss cost, downtime loss cost and energy loss cost at different time periods, and obtaining the equipment switching cost of each amusement attraction by weighted averaging the switching cost factors.

[0016] Preferably, the step of acquiring group booking data of the target customer group and using a demand detection model based on the group booking data to obtain the degree of demand for deepening intra-group relationships and the degree of demand for establishing inter-group relationships of the target customer group includes: acquiring group booking data of the target customer group, inputting the group booking data into the demand detection model to obtain the degree of demand for deepening intra-group relationships and the degree of demand for establishing inter-group relationships, wherein the group booking data includes group size, historical number of trips together, social connection strength and consumption level dispersion.

[0017] Preferably, the step of obtaining the second recommendation degree of the target amusement project using a second recommendation formula based on the target customer group's need to deepen intra-group relationships, need to establish inter-group relationships, and relevant recommendation data includes: obtaining relevant recommendation data for the target amusement project, wherein the relevant recommendation data includes the target amusement project's need to deepen intra-group relationships, need to establish inter-group relationships, the suitability of the target amusement project for the target customer group's thematic preferences, and the number of sensory dimensions of the target amusement project; and obtaining the second recommendation degree of the target amusement project using a second recommendation formula, wherein the second recommendation formula is:

[0018] ;

[0019] In the formula, The second highest recommendation for the target amusement park attraction; To deepen the need for relationships within the target customer group or to establish relationships outside the group; The degree of need to deepen relationships within the group or establish relationships outside the group for the target amusement project; The degree of fit between the target amusement attraction and the theme preferences of the i-th customer within the target customer group; The number of sensory dimensions for the target amusement attraction; This is the weighting adjustment coefficient; The weighted influence coefficient between the target amusement project and the i-th customer within the target customer group.

[0020] Preferably, the step of obtaining priority recommended projects based on the first recommendation degree and the second recommendation degree of each amusement project, and recommending projects for screen display based on the priority recommended projects, includes: selecting amusement projects with a first recommendation degree greater than or equal to a first preset threshold as first recommended projects; selecting amusement projects with a second recommendation degree greater than or equal to a second preset threshold as second recommended projects; taking the intersection of the first recommended projects and the second recommended projects as priority recommended projects; and obtaining a third recommendation degree by weighting the first recommendation degree and the second recommendation degree of the priority recommended projects; and recommending amusement projects based on the third recommendation degree.

[0021] Preferably, the step of obtaining the final recommended items after secondary screening of the priority recommended items based on the customer's historical average consumption price and the consumption price of each amusement item in the priority recommended items, and then performing path planning recommendation based on the final recommended items, includes: obtaining the customer's historical average consumption price and the consumption price of each amusement item in the priority recommended items; using the difference between the consumption price of each amusement item in the priority recommended items and the customer's historical average consumption price as a consumption level difference; removing amusement items whose consumption level difference is greater than a preset consumption threshold to obtain the final recommended items; and using Dijkstra's algorithm to perform path planning based on the third recommendation degree of each amusement item in the final recommended items.

[0022] Preferably, the step of using Dijkstra's algorithm to perform path planning based on the third recommendation degree of each amusement park attraction in the final recommended project includes: combining the third recommendation degree of each amusement park attraction in the final recommended project with geographical distance to form a comprehensive weight, and using Dijkstra's algorithm to perform path planning for the final recommended project based on the comprehensive weight.

[0023] Preferably, a customer data analysis system for recommending amusement equipment further includes:

[0024] The data acquisition module is used to acquire data on cultural conflict elements of customers and equipment-related data of amusement equipment, and based on the data on cultural conflict elements of customers and equipment-related data of amusement equipment, to acquire the number of spare non-cultural conflict equipment and the number of cultural conflict equipment in use for each amusement project;

[0025] The first recommendation module is used to apply the first recommendation formula based on the number of spare non-cultural conflict equipment for each amusement attraction, the number of cultural conflict equipment in use, and the equipment switching cost for each amusement attraction.

[0026] The equipment switching cost module is used to obtain the equipment switching costs for each amusement attraction.

[0027] The demand classification module is used to obtain group booking data of the target customer group, and use the demand detection model based on the group booking data to obtain the degree of demand for deepening relationships within the group and the degree of demand for establishing relationships outside the group of the target customer group.

[0028] The second recommendation degree acquisition module is used to obtain the second recommendation degree of the target amusement project by using the second recommendation formula based on the degree of need for deepening the relationship within the target customer group, the degree of need for establishing the relationship outside the group, and recommendation-related data.

[0029] The recommendation display module is used to obtain priority recommendation items based on the first recommendation degree and the second recommendation degree of each amusement project, and to display and recommend the priority recommendation items on the screen.

[0030] The route planning module is used to perform a secondary screening of the priority recommended projects based on the customer's historical average consumption price and the consumption price of each amusement project in the priority recommended projects, and then perform route planning and recommendation based on the final recommended projects.

[0031] The beneficial effects are:

[0032] 1. This invention dynamically generates recommendations by quantifying the number of backup non-cultural conflict devices and the usage of cultural conflict devices, combined with equipment switching costs, to ensure that the recommended devices are in line with the user's cultural background, reduce the risk of downtime and user complaints caused by cultural conflicts, and formulate a highly adaptable and personalized recommendation scheme.

[0033] 2. Based on group reservation data, a demand detection model is built to quantify the demand for deepening relationships within the group and establishing relationships outside the group, and to recommend amusement projects that are suitable for group interaction, thereby improving group play satisfaction.

[0034] 3. Quantitative analysis of different dimensions is performed using the first and second recommendation formulas respectively, and then the third recommendation degree is calculated by weighted average, so that the final recommendation result can not only meet the individual preferences of customers, but also take into account the interaction needs between teams.

[0035] 4. In the secondary screening, by comparing users' historical spending levels with the prices of amusement park attractions, recommended attractions that exceed their willingness to pay are eliminated, thus avoiding recommendation failures due to price factors and improving conversion rates. Attached Figure Description

[0036] Figure 1 This is a flowchart of the customer data analysis method for recommending amusement equipment according to the present invention;

[0037] Figure 2 This is a schematic diagram of the customer data analysis system for recommending amusement equipment according to the present invention. Detailed Implementation

[0038] The technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0039] Example 1: A customer data analysis method for recommending amusement park equipment, such as... Figure 1 As shown, it includes the following steps:

[0040] S1: Obtain the customer's cultural conflict elements and equipment-related data of the amusement equipment, and based on the customer's cultural conflict elements and equipment-related data of the amusement equipment, obtain the number of spare non-cultural conflict equipment and the number of cultural conflict equipment used for each amusement project;

[0041] The system acquires data related to cultural conflict elements and amusement equipment from the client. This data includes the number of spare equipment for each amusement attraction, the number of cultural equipment in use for each attraction, and the equipment switching cost for each attraction. Based on the client's cultural conflict elements, the number of spare equipment for each attraction, and the number of cultural equipment in use, the system obtains the number of spare non-cultural conflict equipment and the number of cultural conflict equipment in use for each attraction. The number of spare non-cultural conflict equipment refers to the number of spare equipment that does not contain cultural conflict elements; the number of cultural conflict equipment in use refers to the number of equipment with cultural conflict elements currently in use for the amusement attraction.

[0042] It should be noted that, through pre-set data interfaces or sensing devices, the cultural conflict elements of customers are acquired. These cultural conflict elements include the customer's sensitivity and preference for cultural symbols, patterns, colors, or other cultural attributes. Equipment-related data for amusement rides is also acquired, specifically including three aspects: the number of spare equipment for each amusement ride; the number of cultural equipment currently in use for each amusement ride that possesses cultural conflict elements; and the equipment switching costs for each amusement ride, including various costs incurred when switching equipment from a spare state to an active state. Based on the acquired customer cultural conflict elements and the aforementioned equipment-related data, the spare equipment for each amusement ride is further categorized: the number of spare non-cultural conflict equipment (the number of spare equipment in each amusement ride that does not possess attributes related to the customer's cultural conflict elements, i.e., after comparison, spare equipment that does not match the customer's cultural conflict elements is selected); and the number of cultural conflict equipment currently in use for each amusement ride that possesses attributes related to the customer's cultural conflict elements.

[0043] S2: Based on the number of spare non-cultural conflict equipment, the number of cultural conflict equipment used, and the equipment switching cost of each amusement attraction, the first recommendation formula is used to obtain the first recommendation degree of the target amusement attraction;

[0044] After normalizing the number of spare non-cultural conflict equipment, the number of cultural conflict equipment in use, and the equipment switching costs for each amusement attraction, the first recommendation formula is used to obtain the first recommendation degree of the target amusement attraction, where the first recommendation formula is:

[0045] ;

[0046] In the formula, The top recommendation for the target amusement park attraction; The number of backup non-cultural conflict equipment for the target amusement park project; The number of facilities used to address cultural conflicts in target amusement park attractions; Equipment switching costs for the target amusement park attraction; This is an adjustment factor.

[0047] It should be noted that the number of spare non-cultural conflict equipment, the number of cultural conflict equipment used, and the equipment switching costs for each amusement ride were normalized to eliminate differences between data of different dimensions. In the formula... This primarily reflects the positive impact of the number of backup non-cultural conflict devices on the recommendation rate; This mainly reflects the constraint of equipment switching costs.

[0048] The switching cost factors for each amusement attraction include labor operation costs, consumable consumption costs, downtime loss costs at different times, and energy consumption costs. The equipment switching cost for each amusement attraction is obtained by weighted averaging of these switching cost factors.

[0049] It should be noted that: Labor operation cost refers to the human resources and related expenses incurred by staff during the operation, adjustment, and maintenance of equipment when switching from standby to operational status; consumable cost refers to the cost of materials (such as lubricants, seals, and replacement parts) consumed during equipment switching; downtime loss cost at different times is used to quantify downtime losses, as equipment switching requires a certain downtime, and downtime at different times (such as peak and off-peak periods) will result in different economic losses; energy loss cost refers to the cost of electricity and fuel consumed during equipment startup and changes in operating status during equipment switching. When processing the above-mentioned switching cost factors, a weighted average method is used to integrate the cost factors.

[0050] S3: Obtain group booking data of the target customer group, and use the demand detection model based on the group booking data to obtain the degree of demand for deepening intra-group relationships and the degree of demand for establishing inter-group relationships of the target customer group;

[0051] Obtain group booking data for the target customer group, and input the group booking data into the demand detection model to obtain the degree of demand for deepening relationships within the group and the degree of demand for establishing relationships outside the group. The group booking data includes group size, number of historical trips together, strength of social connection and dispersion of consumption level.

[0052] It should be noted that group size refers to the number of customers participating in the reservation or the total number of people in the team participating in the activity, reflecting the overall size of the team; historical number of joint visits refers to the number of times the group has participated in recreational activities together in the past period, reflecting the frequency of activities and the closeness of interaction within the team; social connection strength quantifies the closeness of social connections among team members by analyzing social relationships, interaction frequency, and related data on social platforms; and consumption level dispersion refers to the degree of difference in consumption levels among team members, reflecting the consistency or diversity of team members in terms of consumption capacity and preferences. The group reservation data obtained above is used as input and sent to a pre-built demand detection model. The demand detection model performs comprehensive calculations based on the input data and outputs two key demand indicators: the degree of demand for deepening relationships within the group, reflecting the size of the target customer group's desire to further deepen their relationships through joint activities, with higher values ​​indicating a stronger demand; and the degree of demand for establishing relationships outside the group, reflecting the size of the target customer group's desire to establish connections with other external teams or individuals and expand their social network through activities. The demand detection model adopts a machine learning model.

[0053] S4: Based on the degree of need to deepen relationships within the target customer group, the degree of need to establish relationships outside the group, and relevant recommendation data, use the second recommendation formula to obtain the second recommendation degree of the target amusement project;

[0054] Obtain relevant recommendation data for the target amusement attraction. This data includes the degree of need for deepening intra-group relationships, the degree of need for establishing extra-group relationships, the suitability of the attraction's theme preferences for the target customer group, and the number of sensory dimensions associated with the attraction. Use a second recommendation formula to obtain the second recommendation score for the target amusement attraction. The second recommendation formula is:

[0055] ;

[0056] In the formula, The second highest recommendation for the target amusement park attraction; To deepen the need for relationships within the target customer group or to establish relationships outside the group; The degree of need to deepen relationships within the group or establish relationships outside the group for the target amusement project; The degree of fit between the target amusement attraction and the theme preferences of the i-th customer within the target customer group; The number of sensory dimensions for the target amusement attraction; This is the weighting adjustment coefficient; The weighted influence coefficient between the target amusement project and the i-th customer within the target customer group.

[0057] It should be noted that the "Demand for Deepening Intra-Group Relationships in the Target Attraction" data represents the demand for deepening relationships among group members during group activities. This demand level is calculated from historical data or a pre-set deep learning model. The "Demand for Building Extra-Group Relationships in the Target Attraction" data reflects the effectiveness of the target attraction in promoting relationships between the group and external stakeholders. This data is obtained through statistical analysis of group booking data and interaction behavior. The "Theme Preference Suitability of the Target Attraction and the Target Customer Group" data measures whether the theme of the target attraction aligns with the interests of the target customer group. The suitability score is obtained by comparing customer group preference data with the theme attributes of the attraction. The "Number of Sensory Dimensions of the Target Attraction" data reflects the diversity of sensory experiences offered by the target attraction, encompassing visual, auditory, and tactile aspects. Ensuring... and Identity, that is, when When there is a need to deepen the group relationships within the target customer group, The need to deepen relationships within the group for the target amusement park attraction should be addressed; when When establishing external relationships for the target customer group, Establish the level of demand for external relationships for the target amusement projects; at the same time, ensure that all data are normalized to avoid bias in recommendation results due to inconsistent units of measurement.

[0058] S5: Based on the first and second recommendation levels of each amusement park attraction, priority recommendation attractions are obtained, and the screen display recommendations are made based on the priority recommendation attractions;

[0059] Amusement attractions with a first recommendation score greater than or equal to a first preset threshold are designated as first recommended attractions; amusement attractions with a second recommendation score greater than or equal to a second preset threshold are designated as second recommended attractions; the intersection of the first recommended attractions and the second recommended attractions is designated as priority recommended attractions; and a third recommendation score is obtained by weighted averaging the first recommendation score and the second recommendation score of the priority recommended attractions. Amusement attractions are recommended based on the third recommendation score.

[0060] It should be noted that, based on the calculated third recommendation score, the attractions are sorted in descending order, and the sorting results are displayed on the screen to recommend them to customers. This ensures that customers can intuitively obtain information on the most suitable attractions for their needs. When the intersection of the first recommended attraction and the second recommended attraction is an empty set, the third recommendation score is obtained by weighted averaging of the first and second recommendation scores of each attraction, and then recommendations are made based on the third recommendation score.

[0061] S6: Based on the customer's historical average consumption price and the consumption price of each amusement park attraction in the priority recommended projects, the priority recommended projects are further filtered to obtain the final recommended projects, and a route planning recommendation is made based on the final recommended projects.

[0062] The system obtains the customer's historical average spending price and the spending price of each amusement park attraction in the priority recommended projects. Based on these prices, the difference between the spending price of each attraction in the priority recommended projects and the customer's historical average spending price is used as the spending level difference. Amusement parks attractions with spending level differences greater than a preset spending threshold are removed to obtain the final recommended projects. Based on the third recommendation degree of each attraction in the final recommended projects, Dijkstra's algorithm is used for path planning.

[0063] It should be noted that the historical average spending price is calculated by statistically analyzing customers' past spending data on amusement park rides, reflecting their price sensitivity when choosing rides. For the priority recommended rides, the current spending price information is further obtained to ensure the real-time nature and accuracy of the price data. If the difference in spending price between an amusement park ride and the customer's historical average spending price is greater than a preset spending threshold, the ride is considered to be out of the final recommended ride list. If the difference in spending price is within the preset spending threshold, the ride passes a second screening and is included in the final recommended ride set.

[0064] The third recommendation score of each attraction in the final recommended project is combined with the geographical distance to form a comprehensive weight, and the Dijkstra algorithm is used to plan the path of the final recommended project based on the comprehensive weight.

[0065] It should be noted that the comprehensive weight is obtained using the comprehensive weight calculation formula in this embodiment, where the comprehensive weight calculation formula is: In the formula, the geographical distance is the actual geographical distance between two attractions. By using the Dijkstra algorithm with comprehensive weights, it is ensured that attractions with high recommendation rates and close proximity are visited first.

[0066] Example 2: Based on Example 1, a customer data analysis system for recommending amusement equipment, such as... Figure 2 As shown, it also includes:

[0067] The data acquisition module is used to acquire data on cultural conflict elements of customers and equipment-related data of amusement equipment, and based on the data on cultural conflict elements of customers and equipment-related data of amusement equipment, to acquire the number of spare non-cultural conflict equipment and the number of cultural conflict equipment in use for each amusement project;

[0068] The first recommendation module is used to apply the first recommendation formula based on the number of spare non-cultural conflict equipment for each amusement attraction, the number of cultural conflict equipment in use, and the equipment switching cost for each amusement attraction.

[0069] The equipment switching cost module is used to obtain the equipment switching costs for each amusement attraction.

[0070] The demand classification module is used to obtain group booking data of the target customer group, and use the demand detection model based on the group booking data to obtain the degree of demand for deepening relationships within the group and the degree of demand for establishing relationships outside the group of the target customer group.

[0071] The second recommendation degree acquisition module is used to obtain the second recommendation degree of the target amusement project by using the second recommendation formula based on the degree of need for deepening the relationship within the target customer group, the degree of need for establishing the relationship outside the group, and recommendation-related data.

[0072] The recommendation display module is used to obtain priority recommendation items based on the first recommendation degree and the second recommendation degree of each amusement project, and to display the recommendations on screen 3 based on the priority recommendation items;

[0073] The route planning module is used to perform a secondary screening of the priority recommended items based on the customer's historical average consumption price and the consumption price of each amusement item in the priority recommended items to obtain the final recommended items, and then perform route planning and recommendation based on the final recommended items. Although the invention has been described with reference to exemplary embodiments, it should be understood that the invention is not limited to the disclosed exemplary embodiments. The scope of the following claims should be given the broadest interpretation in order to cover all variations and equivalent structures and functions.

Claims

1. A customer data analysis method for amusement equipment recommendation, characterized in that, Includes the following steps: S1: Obtain the customer's cultural conflict elements and equipment-related data of the amusement equipment, and based on the customer's cultural conflict elements and equipment-related data of the amusement equipment, obtain the number of spare non-cultural conflict equipment and the number of cultural conflict equipment used for each amusement project; S2: Based on the number of spare non-cultural conflict equipment, the number of cultural conflict equipment used, and the equipment switching cost of each amusement attraction, the first recommendation formula is used to obtain the first recommendation degree of the target amusement attraction; S3: Obtain group booking data of the target customer group, and use the demand detection model based on the group booking data to obtain the degree of demand for deepening intra-group relationships and the degree of demand for establishing inter-group relationships of the target customer group; S4: Based on the degree of need to deepen relationships within the target customer group, the degree of need to establish relationships outside the group, and relevant recommendation data, use the second recommendation formula to obtain the second recommendation degree of the target amusement project; S5: Based on the first and second recommendation levels of each amusement park attraction, priority recommendation attractions are obtained, and the attractions are displayed on the screen accordingly. S6: Based on the customer's historical average consumption price and the consumption price of each amusement park attraction in the priority recommended projects, the priority recommended projects are further filtered to obtain the final recommended projects, and a route planning recommendation is made based on the final recommended projects; The step of obtaining the first recommendation degree of the target amusement project based on the number of backup non-cultural conflict equipment, the number of cultural conflict equipment in use, and the equipment switching cost of each amusement project using a first recommendation formula includes: normalizing the number of backup non-cultural conflict equipment, the number of cultural conflict equipment in use, and the equipment switching cost of each amusement project, and then using the first recommendation formula to obtain the first recommendation degree of the target amusement project, wherein the first recommendation formula is: ； In the formula, The top recommendation for the target amusement park attraction; The number of backup non-cultural conflict equipment for the target amusement park project; The number of facilities used to address cultural conflicts in target amusement park attractions; Equipment switching costs for the target amusement park attraction; For adjustment factors; The step of obtaining a second recommendation score for a target amusement attraction based on the target customer group's need to deepen intra-group relationships, establish inter-group relationships, and relevant recommendation data, using a second recommendation formula, includes: acquiring relevant recommendation data for the target amusement attraction, wherein the relevant recommendation data includes the target amusement attraction's need to deepen intra-group relationships, the target amusement attraction's need to establish inter-group relationships, the target amusement attraction's thematic preference compatibility with the target customer group, and the number of sensory dimensions of the target amusement attraction; and using a second recommendation formula to obtain the target amusement attraction's second recommendation score, wherein the second recommendation formula is: ； In the formula, The second highest recommendation for the target amusement park attraction; To deepen the need for relationships within the target customer group or to establish relationships outside the group; The degree of need to deepen relationships within the group or establish relationships outside the group for the target amusement project; For the target amusement projects and target customer groups Theme compatibility with individual customer preferences; The number of sensory dimensions for the target amusement attraction; This is the weighting adjustment coefficient; For the target amusement projects and target customer groups The weighting influence coefficient of each customer.

2. A customer data analysis method for recommending amusement equipment according to claim 1, characterized in that, The process of acquiring customer data on cultural conflict elements and amusement equipment, and based on this data, determining the number of backup non-cultural conflict equipment and the number of cultural conflict equipment in use for each amusement attraction, includes: acquiring customer data on cultural conflict elements and amusement equipment, wherein the data includes the number of backup equipment for each amusement attraction, the number of cultural conflict equipment in use for each amusement attraction, and the equipment switching cost for each amusement attraction; and determining the number of backup non-cultural conflict equipment and the number of cultural conflict equipment in use for each amusement attraction based on the customer data on cultural conflict elements, the number of backup equipment for each amusement attraction, and the number of cultural conflict equipment in use for each amusement attraction, wherein the number of backup non-cultural conflict equipment refers to the number of backup equipment that does not contain cultural conflict elements; and the number of cultural conflict equipment in use refers to the number of equipment with cultural conflict elements currently in use for the amusement attraction.

3. A customer data analysis method for recommending amusement equipment according to claim 2, characterized in that, The equipment switching cost for each amusement attraction includes: obtaining the switching cost factors for each amusement attraction, including labor operation costs, consumable consumption costs, downtime loss costs at different time periods, and energy consumption costs; and obtaining the equipment switching cost for each amusement attraction by weighted averaging the switching cost factors.

4. A customer data analysis method for recommending amusement equipment according to claim 1, characterized in that, The step of obtaining group booking data of the target customer group and using a demand detection model based on the group booking data to obtain the degree of demand for deepening intra-group relationships and establishing inter-group relationships of the target customer group includes: obtaining group booking data of the target customer group, inputting the group booking data into the demand detection model to obtain the degree of demand for deepening intra-group relationships and establishing inter-group relationships, wherein the group booking data includes group size, number of historical trips together, social connection strength and consumption level dispersion.

5. A customer data analysis method for recommending amusement equipment according to claim 1, characterized in that, The step of obtaining priority recommended projects based on the first and second recommendation scores of each amusement project, and then recommending projects for screen display based on the priority recommended projects, includes: designating amusement projects with a first recommendation score greater than or equal to a first preset threshold as first recommended projects; designating amusement projects with a second recommendation score greater than or equal to a second preset threshold as second recommended projects; designating the intersection of the first and second recommended projects as priority recommended projects; and obtaining a third recommendation score by weighted averaging the first and second recommendation scores of the priority recommended projects, and then recommending amusement projects based on the third recommendation score.

6. A customer data analysis method for recommending amusement equipment according to claim 1, characterized in that, The process of obtaining final recommended items by performing a secondary screening of the priority recommended items based on the customer's historical average consumption price and the consumption price of each amusement item in the priority recommended items, and then performing path planning recommendations based on the final recommended items, includes: obtaining the customer's historical average consumption price and the consumption price of each amusement item in the priority recommended items; using the difference between the consumption price of each amusement item in the priority recommended items and the customer's historical average consumption price as a consumption level difference; removing amusement items whose consumption level difference is greater than a preset consumption threshold to obtain the final recommended items; and using Dijkstra's algorithm to perform path planning based on the third recommendation degree of each amusement item in the final recommended items.

7. A customer data analysis method for recommending amusement equipment according to claim 6, characterized in that, The step of using Dijkstra's algorithm for path planning based on the third recommendation degree of each amusement park attraction in the final recommended project includes: combining the third recommendation degree of each amusement park attraction in the final recommended project with geographical distance to form a comprehensive weight, and using Dijkstra's algorithm to plan the path of the final recommended project based on the comprehensive weight.

8. A customer data analysis system for recommending amusement equipment, comprising a customer data analysis method for recommending amusement equipment according to any one of claims 1-7, characterized in that it further includes... include: The data acquisition module is used to acquire data on cultural conflict elements of customers and equipment-related data of amusement equipment, and based on the data on cultural conflict elements of customers and equipment-related data of amusement equipment, to acquire the number of spare non-cultural conflict equipment and the number of cultural conflict equipment in use for each amusement project; The first recommendation module is used to apply the first recommendation formula based on the number of spare non-cultural conflict equipment for each amusement attraction, the number of cultural conflict equipment in use, and the equipment switching cost for each amusement attraction. The equipment switching cost module is used to obtain the equipment switching costs for each amusement attraction. The demand classification module is used to obtain group booking data of the target customer group, and use the demand detection model based on the group booking data to obtain the degree of demand for deepening relationships within the group and the degree of demand for establishing relationships outside the group of the target customer group. The second recommendation degree acquisition module is used to obtain the second recommendation degree of the target amusement project by using the second recommendation formula based on the degree of need for deepening the relationship within the target customer group, the degree of need for establishing the relationship outside the group, and recommendation-related data. The recommendation display module is used to obtain priority recommendation items based on the first recommendation degree and the second recommendation degree of each amusement project, and to display and recommend the priority recommendation items on the screen. The route planning module is used to perform a secondary screening of the priority recommended projects based on the customer's historical average consumption price and the consumption price of each amusement project in the priority recommended projects, and then perform route planning and recommendation based on the final recommended projects.

Images