A tourism consumption habits analysis method and system based on big data

Abstract

The embodiment of the present invention relates to the technical field of tourism consumption habit analysis, and specifically discloses a tourism consumption habit analysis method and system based on big data. The embodiment of the present invention obtains the positioning record data and consumption record data of the target user; identifies and analyzes the habit positioning and scenic spot positioning; screens the consumption record data, identifies the consumption order, extracts the tourism consumption data from the consumption record data; performs classification statistics; and analyzes the consumption habits based on big data technology, and generates and displays the consumption habit information. It is possible to obtain the positioning record data and consumption record data, identify and analyze the habit positioning and scenic spot positioning, obtain the tourism positioning time period, and then screen the consumption record data and identify the order, extract the tourism consumption data, and then perform classification statistics and consumption habit analysis, so as to obtain accurate and complete tourism consumption data, and improve the accuracy of the analysis of tourism consumption habits.

Description

Technical Field

[0001] The present invention belongs to the technical field of tourism consumption habit analysis, and in particular relates to a tourism consumption habit analysis method and system based on big data. Background Art

[0002] Tourism consumption habits refer to the specific behavior patterns and preferences that people show in tourism activities. These habits are usually reflected in how individuals or groups plan, choose, purchase and use tourism products and services. Specifically, tourism consumption habits include the following aspects: consumption behavior, consumption decision-making, consumption preferences and consumption motivations.

[0003] In the existing technology, there are many mature technologies for the analysis of tourism consumption habits. However, accurate tourism consumption habit analysis needs to be based on the technology of obtaining accurate and complete tourism consumption data. At present, accurate and complete tourism consumption data is usually not effectively obtained, resulting in the consumption data obtained being inaccurate and incomplete, which affects the accurate judgment of tourism consumption habit analysis. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a method and system for analyzing tourism consumption habits based on big data, aiming to solve the problems raised in the background technology.

[0005] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0006] A method for analyzing tourism consumption habits based on big data, the method specifically comprising the following steps:

[0007] Interact with the target user, obtain the target user's data usage authority, and obtain the target user's location record data and consumption record data based on the data usage authority;

[0008] Identify and analyze the habitual positioning and scenic spot positioning of the positioning record data to obtain the travel positioning period of the target user;

[0009] According to the travel positioning period, the consumption record data is screened, and consumption orders are identified, and travel consumption data is extracted from the consumption record data;

[0010] Classify and count the tourism consumption data, and record tourism consumption classification information;

[0011] Based on big data technology, consumption habit analysis is performed on the tourism consumption classification information to generate and display consumption habit information of target users.

[0012] As a further limitation of the technical solution of the embodiment of the present invention, the interacting with the target user, obtaining the data usage authority of the target user, and obtaining the location record data and consumption record data of the target user according to the data usage authority specifically includes the following steps:

[0013] Generate and send data permission application to target users;

[0014] By applying for data permission, interact with the target user to obtain the target user's location data permission and consumption data permission;

[0015] According to the positioning data permission, obtaining the positioning record data of the target user;

[0016] According to the consumption data authority, the consumption record data of the target user is obtained.

[0017] As a further limitation of the technical solution of the embodiment of the present invention, the identification and analysis of the habitual positioning and the scenic spot positioning of the positioning record data to obtain the travel positioning period of the target user specifically includes the following steps:

[0018] Performing habitual positioning analysis on the positioning record data to obtain the user's habitual positioning range;

[0019] Based on the customary positioning range, performing positioning beyond analysis on the positioning record data, and filtering positioning beyond data from the positioning record data;

[0020] Perform scenic spot location identification on the positioning exceeding data to obtain the scenic spot location time;

[0021] Based on the scenic spot positioning time, the positioning exceeding data is extended to a time period of same-city positioning to obtain a travel positioning time period of a target user.

[0022] As a further limitation of the technical solution of the embodiment of the present invention, the consumption record data is screened according to the tourism positioning period, and the consumption order is identified, and the tourism consumption data is extracted from the consumption record data, which specifically includes the following steps:

[0023] According to the travel location period, the consumption record data is screened to obtain the travel period consumption data;

[0024] Extracting time period consumption order information from the travel time period consumption data;

[0025] Performing tourism consumption identification on the consumption order information during the time period, and recording the tourism consumption identification results;

[0026] According to the tourism consumption identification result, the tourism consumption data is filtered from the tourism period consumption data.

[0027] As a further limitation of the technical solution of the embodiment of the present invention, the classification and statistics of the tourism consumption data and the recording of tourism consumption classification information specifically include the following steps:

[0028] Obtain classification standard information;

[0029] Based on the classification standard information, classify and identify the tourism consumption data, and record the classification identification information;

[0030] According to the classification identification information, classification statistics are carried out to record the tourism consumption classification information.

[0031] As a further limitation of the technical solution of the embodiment of the present invention, the consumption habit analysis of the tourism consumption classification information based on big data technology, and the generation and display of the consumption habit information of the target user specifically include the following steps:

[0032] Based on big data technology, the consumption habit analysis is performed on the tourism consumption classification information to generate consumption habit information;

[0033] Receive information display request from target user;

[0034] Creating an information display interface according to the information display request;

[0035] The consumption habit information is visualized through the information display interface.

[0036] A tourism consumption habit analysis system based on big data, the system comprises a relevant data acquisition unit, a positioning identification analysis unit, a consumption data screening unit, a data classification and statistics unit and a habit analysis and display unit, wherein:

[0037] A related data acquisition unit, used to interact with a target user, obtain the target user's data usage authority, and obtain the target user's location record data and consumption record data according to the data usage authority;

[0038] A positioning identification and analysis unit, used to identify and analyze the habitual positioning and scenic spot positioning of the positioning record data, and obtain the travel positioning period of the target user;

[0039] A consumption data screening unit, used to screen the consumption record data according to the tourism positioning period, identify consumption orders, and extract tourism consumption data from the consumption record data;

[0040] A data classification and statistics unit is used to classify and count the tourism consumption data and record tourism consumption classification information;

[0041] The habit analysis and display unit is used to perform consumption habit analysis on the tourism consumption classification information based on big data technology, and generate and display consumption habit information of target users.

[0042] As a further limitation of the technical solution of the embodiment of the present invention, the relevant data acquisition unit specifically includes:

[0043] The permission application module is used to generate and send data permission applications to target users;

[0044] The permission acquisition module is used to interact with the target user through the data permission application to obtain the location data permission and consumption data permission of the target user;

[0045] A positioning data acquisition module, used to acquire the positioning record data of the target user according to the positioning data authority;

[0046] The consumption data acquisition module is used to acquire the consumption record data of the target user according to the consumption data authority.

[0047] As a further limitation of the technical solution of the embodiment of the present invention, the positioning identification and analysis unit specifically includes:

[0048] A habitual positioning analysis module, used to perform habitual positioning analysis on the positioning record data to obtain the user's habitual positioning range;

[0049] A positioning exceeding analysis module, used for performing positioning exceeding analysis on the positioning record data based on the customary positioning range, and filtering positioning exceeding data from the positioning record data;

[0050] A scenic spot positioning identification module is used to perform scenic spot positioning identification on the positioning exceeding data and obtain the scenic spot positioning time;

[0051] The time period extension module is used to extend the time period of the same-city positioning for the positioning exceeding data based on the scenic spot positioning time, and obtain the travel positioning time period of the target user.

[0052] As a further limitation of the technical solution of the embodiment of the present invention, the consumption data screening unit specifically includes:

[0053] A time period screening module is used to screen the consumption record data according to the travel positioning time period to obtain the travel period consumption data;

[0054] An order information extraction module is used to extract time period consumption order information from the travel time period consumption data;

[0055] A tourism consumption identification module is used to identify tourism consumption for the consumption order information during the time period and record the tourism consumption identification result;

[0056] The consumption data screening module is used to screen the tourism consumption data from the tourism period consumption data according to the tourism consumption identification result.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] The embodiment of the present invention obtains the positioning record data and consumption record data of the target user; identifies and analyzes the habitual positioning and scenic spot positioning; screens the consumption record data and identifies the consumption order, extracts the tourism consumption data from the consumption record data; performs classification statistics; and analyzes the consumption habits based on big data technology, generates and displays the consumption habit information. The positioning record data and consumption record data can be obtained, the habitual positioning and scenic spot positioning can be identified and analyzed, the tourism positioning time period can be obtained, and then the consumption record data can be screened and the order can be identified, the tourism consumption data can be extracted, and then the classification statistics and consumption habit analysis can be performed, so that accurate and complete tourism consumption data can be obtained, and the accuracy of the analysis of tourism consumption habits can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0060] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0061] Figure 2 A flow chart of obtaining positioning record data and consumption record data in the method provided in an embodiment of the present invention is shown.

[0062] Figure 3 A flow chart of obtaining a travel positioning period in the method provided in an embodiment of the present invention is shown.

[0063] Figure 4 A flow chart of extracting tourism consumption data in the method provided by an embodiment of the present invention is shown.

[0064] Figure 5 A flow chart of recording tourism consumption classification information in the method provided by an embodiment of the present invention is shown.

[0065] Figure 6 A flow chart of consumption habit analysis and display in the method provided in an embodiment of the present invention is shown.

[0066] Figure 7 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0067] Figure 8The structure block diagram of the relevant data acquisition unit in the system provided by the embodiment of the present invention is shown.

[0068] Fig. 9 The structure block diagram of the positioning identification and analysis unit in the system provided by the embodiment of the present invention is shown.

[0069] Fig.10 A structural block diagram of a consumption data screening unit in a system provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0070] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0071] It is understandable that there are many mature technologies in the existing technology for the analysis of tourism consumption habits. However, accurate tourism consumption habit analysis needs to be based on the technology of obtaining accurate and complete tourism consumption data. Currently, accurate and complete tourism consumption data is usually not effectively obtained, resulting in the consumption data obtained being inaccurate and incomplete, which affects the accurate judgment of the tourism consumption habit analysis.

[0072] To solve the above problems, the embodiment of the present invention obtains the target user's data usage authority by interacting with the target user, and obtains the target user's positioning record data and consumption record data according to the data usage authority; identifies and analyzes the habitual positioning and scenic spot positioning of the positioning record data to obtain the target user's travel positioning period; screens the consumption record data according to the travel positioning period, identifies the consumption order, and extracts the travel consumption data from the consumption record data; classifies and counts the travel consumption data, and records the travel consumption classification information; based on big data technology, analyzes the consumption habits of the travel consumption classification information, and generates and displays the target user's consumption habit information. It is possible to obtain positioning record data and consumption record data, identify and analyze the habitual positioning and scenic spot positioning, obtain the travel positioning period, and then screen the consumption record data and identify the order, extract the travel consumption data, and then classify and count and analyze the consumption habits, so as to obtain accurate and complete travel consumption data and improve the accuracy of the analysis of travel consumption habits.

[0073] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0074] Specifically, a method for analyzing tourism consumption habits based on big data includes the following steps:

[0075] Step S101 , interacting with a target user, obtaining the target user's data usage authority, and obtaining the target user's location record data and consumption record data according to the data usage authority.

[0076] In an embodiment of the present invention, a data permission application is generated and sent to the user mobile terminal of the target user. The target user can view the data permission application through the user mobile terminal, and when the target user agrees to the data permission application, the target user's positioning data permission and consumption data permission can be obtained, and then the positioning record data of the target user can be obtained based on the positioning data permission, and the consumption record data of the target user can be obtained based on the consumption data permission.

[0077] Specifically, Figure 2 A flow chart of obtaining positioning record data and consumption record data in the method provided in an embodiment of the present invention is shown.

[0078] Among them, in the preferred implementation manner provided by the present invention, the interacting with the target user, obtaining the data usage authority of the target user, and obtaining the location record data and consumption record data of the target user according to the data usage authority specifically includes the following steps:

[0079] Step S1011, generate and send a data permission application to the target user;

[0080] Step S1012, interacting with the target user through the data permission application to obtain the target user's location data permission and consumption data permission;

[0081] Step S1013, obtaining the location record data of the target user according to the location data authority;

[0082] Step S1014: acquiring the consumption record data of the target user according to the consumption data authority.

[0083] Furthermore, the method for analyzing tourism consumption habits based on big data also includes the following steps:

[0084] Step S102, identifying and analyzing the habitual positioning and scenic spot positioning of the positioning record data to obtain the travel positioning period of the target user.

[0085] In an embodiment of the present invention, habitual positioning analysis is performed on the positioning record data to obtain the user's habitual positioning range for work, school, life, etc., and then based on the habitual positioning range, positioning analysis is performed on the positioning record data that exceeds the habitual positioning range, and positioning exceeding data that exceeds the habitual positioning range is screened out from the positioning record data, and then scenic spot positioning identification is performed on the positioning exceeding data to obtain the scenic spot positioning time when the positioning is in the scenic spot, and then based on the scenic spot positioning time, the time of the same city positioning in the scenic spot in the positioning exceeding data is extended to obtain the travel positioning time period of the target user. For example: if the positioning exceeding data has the positioning of "Yellow Crane Tower Scenic Area", the scenic spot positioning time of "Yellow Crane Tower Scenic Area" is obtained, and according to the positioning as "Wuhan", the scenic spot positioning time is extended to obtain the travel positioning time period when the target user is in "Wuhan".

[0086] Specifically, Figure 3 A flow chart of obtaining a travel positioning period in the method provided in an embodiment of the present invention is shown.

[0087] Among them, in the preferred embodiment provided by the present invention, the identification and analysis of the habitual positioning and scenic spot positioning of the positioning record data to obtain the travel positioning period of the target user specifically includes the following steps:

[0088] Step S1021, performing habitual positioning analysis on the positioning record data to obtain the user's habitual positioning range;

[0089] Step S1022, based on the customary positioning range, performing positioning beyond analysis on the positioning record data, and filtering positioning beyond data from the positioning record data;

[0090] Step S1023, performing scenic spot positioning identification on the positioning exceeding data to obtain the scenic spot positioning time;

[0091] Step S1024, based on the scenic spot positioning time, the positioning beyond data is extended to a time period of same-city positioning to obtain a travel positioning time period of the target user.

[0092] Among them, in the preferred implementation mode provided by the present invention, performing habitual positioning analysis on the positioning record data to obtain the user's habitual positioning range specifically includes the following steps:

[0093] Get the geographic coordinates and timestamps of all records from the location record data;

[0094] Convert the timestamp to a decimal representation of hours and minutes to form a time feature;

[0095] The time feature is regarded as the third dimension, and the time feature is weighted and then spliced ​​with the geographic coordinates to form a three-dimensional feature space to obtain space-time feature data;

[0096] The DBSCAN clustering algorithm is used to cluster the spatial-temporal feature data to identify data points that are densely located in space and regular in time;

[0097] Assign a label to each data point to represent the cluster to which the data point belongs, and remove isolated points that are not assigned to any cluster;

[0098] Calculate the time period that each labeled data point stays continuously in the same cluster, and accumulate the time difference between each data point in the same cluster to calculate the total residence time at the corresponding position, and then obtain the total residence time of each cluster;

[0099] Set a time threshold and filter clusters based on the time threshold and the total residence time of each cluster;

[0100] For each retained cluster, the average coordinates of all geographic locations in the cluster are used as the centroid of the cluster. The centroid represents the central activity position of the user in the area, and the user's habitual positioning range is obtained.

[0101] In the embodiment of the present invention, by introducing the time dimension as one of the features into cluster analysis, the user's activity patterns can be captured more comprehensively. This helps to identify those activity areas that are not only close in geographical location but also have regularity in time. This method can identify the user's behavior patterns at different time periods, such as the difference between weekday and weekend activities, or the activity patterns at a specific time of day, and provide more detailed behavior analysis.

[0102] Furthermore, the method for analyzing tourism consumption habits based on big data also includes the following steps:

[0103] Step S103, screening the consumption record data according to the travel positioning period, identifying the consumption order, and extracting travel consumption data from the consumption record data.

[0104] In an embodiment of the present invention, consumption record data is screened according to the travel positioning time period to obtain travel time period consumption data, and then the time period consumption order information is extracted from the travel time period consumption data. Tourism consumption is identified by performing tourism consumption identification on the time period consumption order information, and the tourism consumption identification result is recorded. Then, according to the tourism consumption identification result, consumption data irrelevant to tourism, such as transfers and online shopping, is eliminated, and tourism consumption data related to tourism is screened and obtained from the tourism time period consumption data.

[0105] Specifically, Figure 4A flow chart of extracting tourism consumption data in the method provided by an embodiment of the present invention is shown.

[0106] Among them, in the preferred implementation mode provided by the present invention, the consumption record data is screened according to the tourism positioning period, and the consumption order is identified, and the tourism consumption data is extracted from the consumption record data, which specifically includes the following steps:

[0107] Step S1031, filtering the consumption record data according to the travel positioning period to obtain travel period consumption data;

[0108] Step S1032, extracting time period consumption order information from the travel time period consumption data;

[0109] Step S1033, performing tourism consumption identification on the consumption order information of the time period, and recording the tourism consumption identification result;

[0110] Step S1034, according to the tourism consumption identification result, filter the tourism consumption data from the tourism period consumption data.

[0111] Among them, in the preferred implementation mode provided by the present invention, performing tourism consumption identification on the consumption order information of the time period and recording the tourism consumption identification result specifically includes the following steps:

[0112] Extract the order time of each order in the consumption order information during the period;

[0113] Compare the order time with each time period in the travel time list, filter out non-related orders according to the comparison results to achieve preliminary screening, and obtain travel consumption orders;

[0114] Extract the order description, order location and order amount of each order in the travel consumption order;

[0115] Perform feature extraction on the order description to obtain text features, and then perform semantic analysis on the text features to obtain semantic scores;

[0116] Matching order locations with scenic spot locations to calculate a geographic relevance score based on the proximity of the order location to known tourist attractions;

[0117] The semantic score, geographic relevance score and order amount are combined into an initial multi-dimensional feature vector;

[0118] Perform z-score normalization on the initial multidimensional feature vector to adjust each feature to the same scale and obtain a multidimensional feature vector;

[0119] The pre-trained random forest model is used as the classification model, and the multi-dimensional feature vector is input into the classification model to obtain the classification result.

[0120] In the embodiment of the present invention, by making full use of information from different sources to capture possible interaction effects, a more comprehensive context can be provided for the model, thereby improving the accuracy of the prediction. In addition, tourism consumption identification itself is a classification problem. The random forest model naturally supports binary and multi-classification problems, and no additional adjustments are required to the model. Therefore, the present invention uses a pre-trained random forest model as a classification model, and the random forest model can effectively process high-dimensional data and perform well even if the number of features is large.

[0121] Furthermore, the method for analyzing tourism consumption habits based on big data also includes the following steps:

[0122] Step S104, classify and count the tourism consumption data, and record tourism consumption classification information.

[0123] In an embodiment of the present invention, classification standard information is obtained, and then based on the classification standard information, tourism consumption data is classified and identified for tourism consumption such as accommodation, transportation, tickets, shopping, etc., and the classification identification information is recorded. Then, according to the classification identification information, classification statistics are performed and tourism consumption classification information is recorded.

[0124] Specifically, Figure 5 A flow chart of recording tourism consumption classification information in the method provided by an embodiment of the present invention is shown.

[0125] Among them, in the preferred implementation mode provided by the present invention, the classification statistics of the tourism consumption data and the recording of tourism consumption classification information specifically include the following steps:

[0126] Step S1041, obtaining classification standard information;

[0127] Step S1042, classifying and identifying the tourism consumption data based on the classification standard information, and recording the classification identification information;

[0128] Step S1043, performing classification statistics according to the classification identification information, and recording the tourism consumption classification information.

[0129] Among them, in the preferred implementation mode provided by the present invention, based on the classification standard information, the tourism consumption data is classified and identified, and recording the classification identification information specifically includes the following steps:

[0130] Obtain classification standard information and tourism consumption data;

[0131] Initialize a default classification label for each consumption record in the tourism consumption data;

[0132] Extract the keyword list of each category in the classification standard information, check the category information in the consumption record, and determine whether the category information in the record contains any keyword in the classification standard;

[0133] If it is found that the category information of the consumption record contains a keyword of a certain category, the name of the corresponding category will overwrite the default label as the category label of the current record.

[0134] Furthermore, the method for analyzing tourism consumption habits based on big data also includes the following steps:

[0135] Step S105, based on big data technology, the consumption habit analysis is performed on the tourism consumption classification information to generate and display the consumption habit information of the target user.

[0136] In an embodiment of the present invention, based on big data technology, consumption habit analysis is performed on tourism consumption classification information to generate consumption habit information, and then an information display request from a target user is received. According to the information display request, an information display interface is created, and then the consumption habit information is visualized through the information display interface, so that the target user can intuitively understand the consumption habit information.

[0137] Specifically, Figure 6 A flow chart of consumption habit analysis and display in the method provided in an embodiment of the present invention is shown.

[0138] Among them, in the preferred implementation mode provided by the present invention, the consumption habit analysis of the tourism consumption classification information based on big data technology, and the generation and display of the consumption habit information of the target user specifically include the following steps:

[0139] Step S1051, based on big data technology, analyzing consumption habits of the tourism consumption classification information to generate consumption habit information;

[0140] Step S1052, receiving an information display request from a target user;

[0141] Step S1053, creating an information display interface according to the information display request;

[0142] Step S1054: Visually display the consumption habit information through the information display interface.

[0143] Among them, in the preferred implementation mode provided by the present invention, based on big data technology, the consumption habit analysis is performed on the tourism consumption classification information, and the generation of consumption habit information specifically includes the following steps:

[0144] Extracting date information from the tourism consumption classification information, and performing time series decomposition on the tourism consumption classification information according to the date information, so as to decompose the tourism consumption classification information into time series features including a long-term trend part and a periodic change part;

[0145] The principal component analysis is used to reduce the dimension of tourism consumption classification information and time series characteristics, and then the reduced-dimensional data are combined and clustered using the DBSCAN algorithm to obtain clustering results.

[0146] Each category in the tourism consumption classification information is encoded using unique hot encoding to obtain encoded data;

[0147] The Apriori algorithm is used to calculate the composition frequencies of different categories on the encoded data to obtain frequent item sets;

[0148] Calculate the confidence index and lift index of the frequent item set, and obtain the relevance of each category according to the confidence index and lift index to obtain the association rules;

[0149] The average value of each cluster in the clustering results is calculated to generate summary description information of the cluster, and then the association rules are applied to the summary description information to obtain consumption habit information.

[0150] In the embodiment of the present invention, the advantages of the DBSCAN clustering algorithm are utilized to identify nonlinear and complex consumption patterns, and potential associations between consumption categories can be discovered through association rule mining, providing deep insights into understanding consumer purchasing behavior. Combining the results of the two, the information on consumption habits includes not only the cluster to which each user belongs, but also possible association combinations in the consumption patterns. By deeply mining the consumption habits of users from tourism consumption data, their potential consumption patterns and associations are revealed, providing data support for further market strategies or personalized services. Furthermore, Figure 7 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0151] Among them, in another preferred embodiment provided by the present invention, a tourism consumption habit analysis system based on big data includes:

[0152] The relevant data acquisition unit 101 is used to interact with the target user, obtain the data use authority of the target user, and obtain the location record data and consumption record data of the target user according to the data use authority.

[0153] In an embodiment of the present invention, the relevant data acquisition unit 101 generates a data permission application and sends the data permission application to the user mobile terminal of the target user. The target user can view the data permission application through the user mobile terminal, and when the target user agrees to the data permission application, the target user's positioning data permission and consumption data permission can be obtained, and then the positioning record data of the target user can be obtained based on the positioning data permission, and the consumption record data of the target user can be obtained based on the consumption data permission.

[0154] Specifically, Figure 8 It shows a structural block diagram of the relevant data acquisition unit 101 in the system provided by the embodiment of the present invention.

[0155] Among them, in the preferred implementation mode provided by the present invention, the relevant data acquisition unit 101 specifically includes:

[0156] The permission application module 1011 is used to generate and send a data permission application to a target user;

[0157] The permission acquisition module 1012 is used to interact with the target user through the data permission application to obtain the location data permission and consumption data permission of the target user;

[0158] A positioning data acquisition module 1013 is used to acquire the positioning record data of the target user according to the positioning data authority;

[0159] The consumption data acquisition module 1014 is used to acquire the consumption record data of the target user according to the consumption data authority.

[0160] Furthermore, the tourism consumption habit analysis system based on big data also includes:

[0161] The positioning identification and analysis unit 102 is used to identify and analyze the habitual positioning and scenic spot positioning of the positioning record data to obtain the travel positioning period of the target user.

[0162] In an embodiment of the present invention, the positioning identification and analysis unit 102 performs habitual positioning analysis on the positioning record data to obtain the user's habitual positioning range for work, school, life, etc., and then performs positioning analysis on the positioning record data that exceeds the habitual positioning range based on the habitual positioning range, and screens the positioning exceeding data that exceeds the habitual positioning range from the positioning record data, and then performs scenic spot positioning identification on the positioning exceeding data to obtain the scenic spot positioning time when the positioning is in the scenic spot, and then based on the scenic spot positioning time, the time period of the same city positioning in the scenic spot in the positioning exceeding data is extended to obtain the travel positioning time period of the target user. For example: if the positioning exceeding data has the positioning of "Yellow Crane Tower Scenic Area", the scenic spot positioning time of "Yellow Crane Tower Scenic Area" is obtained, and according to the positioning as "Wuhan", the scenic spot positioning time is extended to obtain the travel positioning time period when the target user is in "Wuhan".

[0163] Specifically, Fig. 9 It shows a structural block diagram of the positioning identification and analysis unit 102 in the system provided by an embodiment of the present invention.

[0164] Among them, in the preferred embodiment provided by the present invention, the positioning identification and analysis unit 102 specifically includes:

[0165] The habitual positioning analysis module 1021 is used to perform habitual positioning analysis on the positioning record data to obtain the user's habitual positioning range;

[0166] A positioning exceeding analysis module 1022 is used to perform positioning exceeding analysis on the positioning record data based on the customary positioning range, and filter positioning exceeding data from the positioning record data;

[0167] A scenic spot positioning identification module 1023 is used to perform scenic spot positioning identification on the positioning exceeding data and obtain scenic spot positioning time;

[0168] The time period extension module 1024 is used to extend the time period of the positioning beyond data for the same city positioning based on the scenic spot positioning time, so as to obtain the travel positioning time period of the target user.

[0169] Furthermore, the tourism consumption habit analysis system based on big data also includes:

[0170] The consumption data screening unit 103 is used to screen the consumption record data according to the travel positioning period, identify the consumption order, and extract the travel consumption data from the consumption record data.

[0171] In an embodiment of the present invention, the consumption data screening unit 103 screens the consumption record data according to the travel positioning period, obtains the travel period consumption data, and then extracts the period consumption order information from the travel period consumption data, performs travel consumption identification on the period consumption order information, records the travel consumption identification result, and then eliminates the travel-irrelevant consumption data including transfers, online shopping, etc. according to the travel consumption identification result, and screens and obtains the travel consumption data related to travel from the travel period consumption data.

[0172] Specifically, Fig.10 It shows a structural block diagram of the consumption data screening unit 103 in the system provided by the embodiment of the present invention.

[0173] Among them, in the preferred embodiment provided by the present invention, the consumption data screening unit 103 specifically includes:

[0174] The time period screening module 1031 is used to screen the consumption record data according to the travel positioning time period to obtain the travel period consumption data;

[0175] The order information extraction module 1032 is used to extract the time period consumption order information from the travel time period consumption data;

[0176] The tourism consumption identification module 1033 is used to identify tourism consumption for the consumption order information during the time period and record the tourism consumption identification result;

[0177] The consumption data screening module 1034 is used to screen the tourism consumption data from the tourism period consumption data according to the tourism consumption identification result.

[0178] Furthermore, the tourism consumption habit analysis system based on big data also includes:

[0179] The data classification and statistics unit 104 is used to classify and count the tourism consumption data and record tourism consumption classification information.

[0180] In an embodiment of the present invention, the data classification and statistics unit 104 obtains classification standard information, and then classifies and identifies tourism consumption data such as accommodation, transportation, tickets, shopping, etc. based on the classification standard information, records the classification identification information, and then performs classification statistics according to the classification identification information, and records the tourism consumption classification information.

[0181] The habit analysis and display unit 105 is used to perform consumption habit analysis on the tourism consumption classification information based on big data technology, and generate and display consumption habit information of target users.

[0182] In an embodiment of the present invention, the habit analysis and display unit 105 performs consumption habit analysis on tourism consumption classification information based on big data technology, generates consumption habit information, then receives information display requests from target users, creates an information display interface according to the information display requests, and then visualizes the consumption habit information through the information display interface, so as to facilitate the target users to intuitively understand the consumption habit information.

[0183] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0184] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0185] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0186] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0187] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for analyzing tourism consumption habits based on big data, characterized in that: The method specifically comprises the following steps: Interact with the target user, obtain the target user's data usage authority, and obtain the target user's location record data and consumption record data based on the data usage authority; Identify and analyze the habitual positioning and scenic spot positioning of the positioning record data to obtain the travel positioning period of the target user; According to the travel positioning period, the consumption record data is screened, and consumption orders are identified, and travel consumption data is extracted from the consumption record data; Classify and count the tourism consumption data, and record tourism consumption classification information; Based on big data technology, the consumption habit analysis is performed on the tourism consumption classification information to generate and display the consumption habit information of the target users; The step of interacting with the target user, obtaining the target user's data usage authority, and obtaining the target user's location record data and consumption record data according to the data usage authority specifically includes the following steps: Generate and send data permission application to target users; By applying for data permission, interact with the target user to obtain the target user's location data permission and consumption data permission; According to the positioning data permission, obtain the positioning record data of the target user; According to the consumption data authority, obtain the consumption record data of the target user; The identification and analysis of the habitual positioning and scenic spot positioning of the positioning record data to obtain the travel positioning period of the target user specifically includes the following steps: Performing habitual positioning analysis on the positioning record data to obtain the user's habitual positioning range; Based on the customary positioning range, performing positioning beyond analysis on the positioning record data, and filtering positioning beyond data from the positioning record data; Perform scenic spot location identification on the positioning exceeding data to obtain the scenic spot location time; Based on the scenic spot positioning time, the positioning beyond data is extended to the time period of the same city positioning to obtain the travel positioning time period of the target user; Performing habitual positioning analysis on the positioning record data to obtain the user's habitual positioning range specifically includes the following steps: Get the geographic coordinates and timestamps of all records from the location record data; Convert the timestamp to a decimal representation of hours and minutes to form a time feature; The time feature is regarded as the third dimension, and the time feature is weighted and then spliced ​​with the geographic coordinates to form a three-dimensional feature space to obtain space-time feature data; The DBSCAN clustering algorithm is used to cluster the spatial-temporal feature data to identify data points that are densely located in space and regular in time; Assign a label to each data point to represent the cluster to which the data point belongs, and remove isolated points that are not assigned to any cluster; Calculate the time period that each labeled data point stays continuously in the same cluster, and accumulate the time difference between each data point in the same cluster to calculate the total residence time at the corresponding position, and then obtain the total residence time of each cluster; Set a time threshold and filter clusters based on the time threshold and the total residence time of each cluster; For each retained cluster, the average coordinates of all geographic locations in the cluster are used as the centroid of the cluster. The centroid represents the central activity location of the user in the area, and the user's habitual positioning range is obtained; The step of screening the consumption record data according to the tourism positioning period, identifying the consumption order, and extracting tourism consumption data from the consumption record data specifically comprises the following steps: According to the travel location period, the consumption record data is screened to obtain the travel period consumption data; Extracting time period consumption order information from the travel time period consumption data; Performing tourism consumption identification on the consumption order information during the time period, and recording the tourism consumption identification results; According to the tourism consumption identification result, the tourism consumption data is screened from the tourism period consumption data; Performing tourism consumption identification on the consumption order information during the time period and recording the tourism consumption identification result specifically includes the following steps: Extract the order time of each order in the consumption order information during the period; Compare the order time with each time period in the travel time list, filter out non-related orders according to the comparison results to achieve preliminary screening, and obtain travel consumption orders; Extract the order description, order location and order amount of each order in the travel consumption order; Perform feature extraction on the order description to obtain text features, and then perform semantic analysis on the text features to obtain semantic scores; Matching order locations with scenic spot locations to calculate a geographic relevance score based on the proximity of the order location to known tourist attractions; The semantic score, geographic relevance score and order amount are combined into an initial multi-dimensional feature vector; Perform z-score normalization on the initial multidimensional feature vector to adjust each feature to the same scale and obtain a multidimensional feature vector; The pre-trained random forest model is used as the classification model, and the multi-dimensional feature vector is input into the classification model to obtain the classification result; The method of analyzing consumption habits of the tourism consumption classification information based on big data technology and generating and displaying consumption habit information of target users specifically includes the following steps: Based on big data technology, the consumption habit analysis is performed on the tourism consumption classification information to generate consumption habit information; Receive information display request from target user; Creating an information display interface according to the information display request; Visually display the consumption habit information through the information display interface; Based on big data technology, the consumption habit analysis of the tourism consumption classification information is performed to generate consumption habit information, which specifically includes the following steps: Extracting date information from the tourism consumption classification information, and performing time series decomposition on the tourism consumption classification information according to the date information, so as to decompose the tourism consumption classification information into time series features including a long-term trend part and a periodic change part; The principal component analysis is used to reduce the dimension of tourism consumption classification information and time series characteristics, and then the reduced-dimensional data are combined and clustered using the DBSCAN algorithm to obtain clustering results. Each category in the tourism consumption classification information is encoded using unique hot encoding to obtain encoded data; The Apriori algorithm is used to calculate the composition frequencies of different categories on the encoded data to obtain frequent item sets; Calculate the confidence index and lift index of the frequent item set, and obtain the relevance of each category according to the confidence index and lift index to obtain the association rules; The average value of each cluster in the clustering results is calculated to generate summary description information of the cluster, and then the association rules are applied to the summary description information to obtain consumption habit information.

2. The method for analyzing tourism consumption habits based on big data according to claim 1 is characterized in that: The classification and statistics of the tourism consumption data and the recording of tourism consumption classification information specifically include the following steps: Get classification standard information; Based on the classification standard information, classify and identify the tourism consumption data, and record the classification identification information; According to the classification identification information, classification statistics are carried out to record the tourism consumption classification information.

3. The method for analyzing tourism consumption habits based on big data according to claim 2 is characterized in that: Based on the classification standard information, the tourism consumption data is classified and identified, and recording the classification identification information specifically includes the following steps: Obtain classification standard information and tourism consumption data; Initialize a default classification label for each consumption record in the tourism consumption data; Extract the keyword list of each category in the classification standard information, check the category information in the consumption record, and determine whether the category information in the record contains any keyword in the classification standard; If it is found that the category information of the consumption record contains a keyword of a certain category, the name of the corresponding category will overwrite the default label as the category label of the current record.

4. A tourism consumption habit analysis system based on big data, the system is applied to the tourism consumption habit analysis method based on big data according to any one of claims 1 to 3, characterized in that: The system includes a relevant data acquisition unit, a positioning identification and analysis unit, a consumption data screening unit, a data classification and statistics unit and a habit analysis and display unit, wherein: A related data acquisition unit, used to interact with a target user, obtain the target user's data usage authority, and obtain the target user's location record data and consumption record data according to the data usage authority; A positioning identification and analysis unit, used to identify and analyze the habitual positioning and scenic spot positioning of the positioning record data, and obtain the travel positioning period of the target user; A consumption data screening unit, used to screen the consumption record data according to the tourism positioning period, identify consumption orders, and extract tourism consumption data from the consumption record data; A data classification and statistics unit is used to classify and count the tourism consumption data and record tourism consumption classification information; The habit analysis and display unit is used to perform consumption habit analysis on the tourism consumption classification information based on big data technology, and generate and display consumption habit information of target users.

Images