Search-based travel hotspot analysis method, system, device and storage medium

Abstract

The application provides a search-based travel hotspot analysis method, system, device and storage medium, which comprises the following steps: collecting user search behavior data, and then uploading the data to a server for storage through a client; preprocessing and filtering the user search behavior data, filtering invalid search data, and saving real user search behavior data to a database; extracting scenic spot related data from the real user search behavior data by using an aggregation algorithm based on a preset dimension combination to obtain popular scenic spot information; aggregating the popular scenic spot information to preset popular themes in a future preset period; and pushing travel products matching the popular themes to the client of a user meeting the preset dimension combination in the future preset period. The application can realize travel market hotspot analysis based on search data, automatically obtain travel market hotspot information through query optimization, and accurately predict seasonal trend data by relying on a large amount of real search data of users.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of tourism big data, in particular, to a search-based tourism hotspot analysis method, system, device and storage medium. BACKGROUND

[0002] Market hotspot analysis is the foothold of enterprise marketing, and the market information behind the market hotspot information is huge. Under the background of information explosion and rapid change of hotspot trends, the cost of obtaining key information for users, platforms and supply chains is also huge. For the tourism market, hotspot analysis is particularly important. Analyzing the tourism market hotspot can automatically obtain hotspot information, extract seasonal trend data in real time, and obtain complete data solution guidance. On the other hand, it realizes automatic hotspot data mining and analysis, promotes the sales of hot commodities, and promotes the revenue of the tourism market.

[0003] There are many studies on the analysis of tourism market hotspots, but there are still some problems:

[0004] (1) Most of them focus on tourism order sales, but these data have a certain lag, which is not conducive to the timely control of hotspots, and the "hotspots" revealed by order sales are local;

[0005] (2) Lack of direct analysis of the initial intention of user search, which easily loses the behavior data formed by the user initially and misses potential hotspots. Finally, based on big data, the underlying data of market hotspot analysis is huge, and the query performance and information storage are highly dependent.

[0006] Therefore, the present application provides a search-based tourism hotspot analysis method, system, device and storage medium. SUMMARY

[0007] In view of the problems in the prior art, the purpose of the present application is to provide a search-based tourism hotspot analysis method, system, device and storage medium, which overcomes the difficulties of the prior art and can realize tourism market hotspot analysis based on search data. Relying on a large amount of real search data of users, through query optimization, the tourism market hotspot information is automatically obtained, and the seasonal trend data is accurately predicted.

[0008] The embodiment of the present application provides a search-based tourism hotspot analysis method, comprising the following steps:

[0009] S110, collecting user search behavior data, and then uploading to the server through the client for saving;

[0010] S120, preprocessing and filtering the user search behavior data, filtering invalid search data, and saving the real user search behavior data to the database;

[0011] S130, extracting scenic spot related data from real user search behavior data by using an aggregation algorithm based on a preset dimension combination to obtain popular scenic spot information;

[0012] S140, aggregating based on the popular scenic spot information to preset a popular theme in a future preset period;

[0013] S150, pushing a tourism product matching the popular theme to a client of a user meeting a preset dimension combination in the future preset period.

[0014] Preferably, in the step S110, the user search behavior data includes user behavior data, occurrence time, occurred page, user geographic information, and user personal attribute information.

[0015] Preferably, in the step S120, the step includes:

[0016] S1201, a security analysis module analyzes user search behavior data saved by a server according to a crawler judgment module in a database, and if the user search behavior data is determined as a crawler behavior, the security analysis module feeds back to the server; if the user search behavior data is determined as a safe behavior, the security analysis module proceeds to a step S1202;

[0017] S1202, filtering the user search behavior data, discarding invalid search words, and retaining real search words and parsed search words;

[0018] S1203, storing the filtered search words into a database.

[0019] Preferably, in the step S130, the step includes: based on the real search words and the parsed search words, mining popular scenic spot data in different dimensions, including destination and departure place dimensions, domestic and foreign dimensions, different heat period dimensions, and supplementing scenic spot attribute information.

[0020] Preferably, S141, establishing popular city scenic spot data through the popular scenic spot data;

[0021] S142, establishing popular province scenic spot data through the popular city scenic spot data;

[0022] S143, aggregating popular themes in different dimensions based on the popular scenic spot data, the popular city scenic spot data, and the popular province scenic spot data;

[0023] S144, constructing a mapping relationship between a theme and a scenic spot, and predicting a future popular theme.

[0024] Preferably, in the step S144, the historical time series data and the date attribute of the theme hotness are combined by using XGBOOST to predict the hotness data of the theme in the future date; the newly predicted theme hotness data is supplemented to the training set, the model is retrained to obtain the theme hotness data of the next day; and the iteration is implemented to realize the prediction of the theme hotness data in the next 30 days.

[0025] Preferably, in the step S144, the 30 days are divided into the first 15 days and the last 15 days, and the theme prediction in the future date is realized by calculating the comprehensive hotness index of the ring increase and the ring ratio.

[0026]

[0027] wherein, is the theme hotness value of the day, is the historical time series data based on the theme hotness of the day;

[0028]

[0029] wherein, is the theme hotness value of the next day, is the historical time series data based on the theme hotness of the next day;

[0030]

[0031] wherein, H t+30 is the prediction value of the theme hotness data in the next 30 days, is the theme hotness value of the next 30 days, H t′-15 is the prediction value of the theme hotness data in the next 15 days, H t′-15 is the prediction value of the theme hotness data in the next 16 to 30 days;

[0032] ΔH=H t′+15 -H t′-15 (4)

[0033] wherein, ΔH is the ring increase value between the prediction value of the theme hotness data in the next 15 days and the prediction value of the theme hotness data in the next 16 to 30 days;

[0034]

[0035] wherein, ΔB is the ring ratio value between the prediction of the theme hotness data in the next 15 days and the prediction of the theme hotness data in the next 16 to 30 days, avgΔH is the ring increase average value between the prediction of the theme hotness data in the next 15 days and the prediction of the theme hotness data in the next 16 to 30 days, avg H t′-15 is the prediction average value of the theme hotness data in the next 16 to 30 days;

[0036]

[0037] score is a comprehensive heat index based on ring increase and ring ratio, max(ΔH) is the maximum value in the heat data prediction value of the theme in the future 15 days, and max(ΔB) is the maximum value in the ring ratio value between the heat data prediction of the theme in the future 15 days and the heat data prediction of the theme in the future 16 to 30 days.

[0038] Embodiments of the present application also provide a search-based travel hotspot analysis system for implementing the search-based travel hotspot analysis method described above, and the search-based travel hotspot analysis system comprises:

[0039] a user data collection module that collects user search behavior data and then uploads the user search behavior data to a server for storage through a client;

[0040] a search behavior filtering module that pre-processes and filters the user search behavior data, filters invalid search data, and saves real user search behavior data to a database;

[0041] a popular scenic spot information module that extracts scenic spot related data from the real user search behavior data by using an aggregation algorithm based on a preset dimension combination to obtain popular scenic spot information;

[0042] a popular theme prediction module that aggregates the popular scenic spot information to predict popular themes in a preset time period in the future;

[0043] a popular travel product module that pushes travel products matching the popular themes to the client of a user meeting the preset dimension combination in the preset time period in the future.

[0044] Embodiments of the present application also provide a search-based travel hotspot analysis device, which comprises:

[0045] a processor;

[0046] a memory in which executable instructions of the processor are stored;

[0047] The processor is configured to execute the steps of the search-based travel hotspot analysis method described above by executing the executable instructions.

[0048] Embodiments of the present application also provide a computer readable storage medium for storing a program, and the program is executed to implement the steps of the search-based travel hotspot analysis method described above.

[0049] The application aims to provide a search-based tourism hotspot analysis method, system, device and storage medium, which can realize tourism market hotspot analysis based on search data, automatically obtain tourism market hotspot information through query optimization, and accurately predict seasonal trend data based on a large amount of real search data of users. BRIEF DESCRIPTION OF DRAWINGS

[0050] Other features, objects, and advantages of the application will become more apparent from the following detailed description of non-limiting embodiments with reference to the drawings.

[0051] Figure 1 is a flowchart of the search-based tourism hotspot analysis method of the application.

[0052] Figure 2 is a flowchart of the steps of the search-based tourism hotspot analysis method of the application.

[0053] Figure 3 is a structural block diagram of the analysis system for running the search-based tourism hotspot analysis method of the application.

[0054] Figure 4 is a structural schematic diagram of the search-based tourism hotspot analysis device of the application.

[0055] Figure 5 is a structural schematic diagram of the search-based tourism hotspot analysis device of the application.

[0056] Figure 6 is a structural schematic diagram of the computer-readable storage medium of an embodiment of the application. DETAILED DESCRIPTION

[0057] The implementation manners of the application are described below through specific and concrete examples, and other advantages and effects of the application can be easily understood by those skilled in the art based on the disclosure of the application. The application can also be implemented or applied in different specific implementation manners, and the details in the application can be modified or changed based on different viewpoints and application systems without departing from the spirit of the application. It should be noted that the embodiments in the application and the features in the embodiments can be combined with each other without conflict.

[0058] The embodiments of the application are described in detail below with reference to the drawings, so that those skilled in the art can easily implement the application. The application can be embodied in various different forms, and is not limited to the embodiments described here.

[0059] In the present specification, expressions such as "one embodiment", "some embodiments", "exemplary", "detailed example", or "some examples" mean including at least one of the particular features, structures, materials, or characteristics described in connection with that embodiment or example. The appearances of the expressions "in one embodiment", "in some embodiments", "in an exemplary embodiment", "in a specific example" or "in some examples" in various places in the specification are not necessarily referring to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples. Moreover, the usage of "a" or "an" terms is taken as meaning "one", but is also taken as meaning "any one or more". Unless otherwise noted, the different embodiments or examples presented herein are not meant to be mutually exclusive, but rather can be combinable in any suitable manner.

[0060] Furthermore, the terms "first", "second", "third", "fourth", "fifth", "sixth", etc. merely identify the names of particular features described herein, and do not limit the features to the name provided by the term. Thus, a feature described as a "first" feature can also be a "second" feature or a "third" feature. Furthermore, the terms "front", "back", "top", "bottom", "over", "under", and the like as may be used in this description

[0061] In order to clearly illustrate the present application, devices that are not related to the description are omitted, and the same or similar constituent elements are denoted by the same reference numerals throughout the whole description.

[0062] In the present specification, when a device is said to be "connected" to another device, this includes not only a case where it is "directly connected" but also a case where it is "indirectly connected" with other elements interposed therebetween. In addition, when a device is said to "include" a certain constituent element, unless specifically noted otherwise, other constituent elements are not excluded, but it means that other constituent elements can also be included.

[0063] When a device is said to be "on" another device, it can be directly on the other device, but it can also be accompanied by other devices therebetween. When it is said in contrast that a device is "directly on" another device, there are no other devices therebetween.

[0064] Although the terms first, second, etc. are used herein to refer to various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first interface and a second interface, etc. are distinguished from each other. Also, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises", "comprising", "includes" and / or "including", when used herein, specify the presence of stated features, steps, operations, elements, components, items, and / or groups but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, items, and / or groups thereof. As used herein, the terms "or" and "and / or" are to be interpreted as inclusive, i.e., as meaning one or any combination of items. Thus, "A, B or C" or "A, B and / or C" means any of the following: A; B; C; A and B; A and C; B and C; A, B and C. This definition applies regardless of the manner in which the items are presented or described in the claims.

[0065] The technical and scientific terms used herein are intended to refer to the terms as commonly understood by one of ordinary skill in the art to which the application pertains, unless otherwise explicitly defined herein. Accordingly, no unnecessary extensive explanation is intended for the terms of usual use. The terms defined in a general dictionary are to be interpreted as having the same meaning as those consistent with the context of relevant technical documents and the present disclosure, unless otherwise defined. The singular forms are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising", when used herein, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0066] The technical and scientific terms used herein are intended to refer to the terms as commonly understood by one of ordinary skill in the art to which the application pertains, unless otherwise explicitly defined herein. Accordingly, no unnecessary extensive explanation is intended for the terms of usual use. The terms defined in a general dictionary are to be interpreted as having the same meaning as those consistent with the context of relevant technical documents and the present disclosure, unless otherwise defined. The singular forms are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising", when used herein, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0067] Figure 1 is a flowchart of a search-based travel hotspot analysis method of the present application. As shown in Figure 1 , the search-based travel hotspot analysis method of the present application includes:

[0068] S110, collecting user search behavior data, and then uploading to the server through the client for saving;

[0069] S120, preprocessing and filtering the user search behavior data, filtering invalid search data, and saving the real user search behavior data to the database;

[0070] S130, extracting the scenic spot related data from the real user search behavior data by using an aggregation algorithm based on the preset dimension combination to obtain the popular scenic spot information;

[0071] S140, aggregating based on the popular scenic spot information to preset a popular theme in a future preset period;

[0072] S150, pushing the tourism product matching the popular theme to the client of the user meeting the preset dimension combination in the future preset period.

[0073] In a preferred embodiment, in step S110, the user search behavior data includes user behavior data, occurrence time, occurrence page, user geographic information, and user personal attribute information.

[0074] In a preferred embodiment, in step S120, the following steps are included:

[0075] S1201, the security analysis module analyzes the user search behavior data saved by the server according to the crawler judgment module in the database, and if it is determined as a crawler behavior, it is fed back to the server; if it is determined as a safe behavior, step S1202 is performed;

[0076] S1202, filtering the user search behavior data, discarding invalid search words, and retaining real search words and parsed search words;

[0077] S1203, storing the filtered search words into the database.

[0078] In a preferred embodiment, in step S130, the following steps are included: based on the real search words and the parsed search words, mining popular scenic spot data of different dimensions, including destination and departure city dimensions, domestic and foreign dimensions, different heat period dimensions, and supplementing scenic spot attribute information.

[0079] In a preferred embodiment, S141, establishing popular city scenic spot data through the popular scenic spot data;

[0080] S142, establishing popular province scenic spot data through the popular city scenic spot data;

[0081] S143, aggregating popular themes in different dimensions based on the popular scenic spot data, the popular city scenic spot data, and the popular province scenic spot data;

[0082] S144, constructing a mapping relationship between the theme and the scenic spot, and predicting the future popular theme.

[0083] In a preferred embodiment, in step S144, the XGBOOST is used to combine the historical time series data of the topic heat and the date attribute to predict the heat data of the topic in the future date; the newly predicted topic heat data is supplemented to the training set, the model is retrained to obtain the topic heat data of the next day in the future; and the iteration is implemented to realize the prediction of the topic heat data in the future 30 days.

[0084] In a preferred embodiment, in step S144, the 30 days are divided into the first 15 days and the last 15 days, and the topic prediction in the future date is realized by calculating the comprehensive heat index of the ring increase and the ring ratio.

[0085]

[0086] wherein, is the topic heat value of the day, is the historical time series data based on the topic heat of the day;

[0087]

[0088] wherein, is the topic heat value of the next day, is the historical time series data based on the topic heat of the next day;

[0089]

[0090] wherein, H t+30 is the prediction value of the topic heat data in the future 30 days, is the topic heat value of the next 30 days, H t′-15 is the prediction value of the topic heat data in the future 15 days, H t′_15 is the prediction value of the topic heat data in the future 16 to 30 days;

[0091] ΔH=H t′+15 -H t′-15 (4)

[0092] wherein, ΔH is the ring increase value between the prediction value of the topic heat data in the future 15 days and the prediction value of the topic heat data in the future 16 to 30 days;

[0093]

[0094] wherein, ΔB is the ring ratio value between the prediction of the topic heat data in the future 15 days and the prediction of the topic heat data in the future 16 to 30 days, avgΔH is the ring increase average value between the prediction of the topic heat data in the future 15 days and the prediction of the topic heat data in the future 16 to 30 days, avg H t′-15is the average value of the heat data prediction of the topic in the next 16 to 30 days;

[0095]

[0096] The score is a comprehensive heat index based on the ring increase and the ring ratio, max (Delta H) is the maximum value in the heat data prediction of the topic in the next 15 days, and max (Delta B) is the maximum value in the ring ratio between the heat data prediction of the topic in the next 15 days and the heat data prediction of the topic in the next 16 to 30 days.

[0097] When the application is used, the client collects user search behavior data, which is uploaded to the server for storage through the client; the security analysis module analyzes the user search data to determine whether it is a crawler behavior; the search term filtering module filters the search term model and distinguishes the search term type; the filtered search term is stored in the data set; based on different types of search terms, hot scenic spot data in different dimensions is mined; based on the hot scenic spot data of the fifth step, hot city data is mined; based on the hot scenic spot data and the hot city data of the fifth step, hot province data is mined; the sixth step can be implemented in parallel, the hot topic is aggregated through the hot scenic spot data, and the topic prediction is realized; the tourism market hotspots are integrated, the marketing activities are combined, and the front end is displayed; the hotspot data scheme guidance is provided.

[0098] The specific implementation process of the application includes the following:

[0099] The user search behavior data is collected, and then uploaded to the server for storage through the client; the user search behavior data includes user behavior data, occurrence time, occurrence page, user geographic information, and user personal attribute information.

[0100] The security analysis module analyzes the user search behavior data saved by the server according to the crawler judgment module in the database, and feeds back to the server if it is determined to be a crawler behavior; if it is determined to be a safe behavior, the user search behavior data is filtered, invalid search terms are discarded, and real search terms and parsed search terms are retained; the filtered search terms are stored in the database.

[0101] The aggregation algorithm based on the preset dimension combination is used to extract scenic spot related data from the real user search behavior data to obtain hot scenic spot information; based on the real search terms and the parsed search terms, hot scenic spot data in different dimensions is mined, including destination and departure dimension, domestic and foreign dimension, and different heat period dimension, and scenic spot attribute information is supplemented.

[0102] The popular city scenic spot data is established through the popular scenic spot data, the popular province scenic spot data is established through the popular city scenic spot data, the popular theme under different dimensions is aggregated based on the popular scenic spot data, the popular city scenic spot data and the popular province scenic spot data, the mapping relationship of the theme and the scenic spot is constructed, and the future popular theme is predicted. The XGBOOST is utilized to combine the historical time series data of the theme heat and the date attribute, the heat data of the theme in the future date is predicted, the newly predicted theme heat data is supplemented to the training set, the model is retrained, and the theme heat data of the next day is obtained; the iteration is realized, and the heat data prediction of the theme in the future 30 days is realized. The 30 days in the embodiment are divided into the first 15 days and the last 15 days, the comprehensive heat index of the ring increase and the ring ratio is calculated, and the theme prediction of the future date is realized:

[0103]

[0104] Wherein, is the theme heat value of the day, is the historical time series data based on the theme heat of the day;

[0105]

[0106] Wherein, is the theme heat value of the next day, is the historical time series data based on the theme heat of the next day;

[0107]

[0108] Wherein, H t+30 is the heat data prediction value of the theme in the future 30 days, is the theme heat value of the next 30 days, H t′-15 is the heat data prediction value of the theme in the future 15 days, H t′_15 is the heat data prediction value of the theme in the future 16 to 30 days;

[0109] ΔH=H t′+15 -H t′-15 (4)

[0110] Wherein, ΔH is the ring increase value between the heat data prediction value of the theme in the future 15 days and the heat data prediction value of the theme in the future 16 to 30 days;

[0111]

[0112] Wherein, Delta B is the ratio between the hotness data prediction of the theme in the next 15 days and the hotness data prediction of the theme in the next 16-30 days, avg Delta H is the average of the ratio between the hotness data prediction of the theme in the next 15 days and the hotness data prediction of the theme in the next 16-30 days, avg H t′-15 is the average of the hotness data prediction of the theme in the next 16-30 days;

[0113]

[0114] The score is a comprehensive hotness index based on the ring increase and the ring ratio, max (Delta H) is the maximum value in the hotness data prediction of the theme in the next 15 days, and max (Delta B) is the maximum value in the ratio between the hotness data prediction of the theme in the next 15 days and the hotness data prediction of the theme in the next 16-30 days.

[0115] Finally, the tourism product matching the hot theme is pushed to the client of the user meeting the preset dimension combination within a future preset period.

[0116] The present application provides a search data-based query optimization market hotspot analysis method in a tourism scenario, and the tourism market hotspot is mainly based on the search hotness of a scenic spot and a city. Figure 2 is a step flow chart of the search-based tourism hotspot analysis method of the present application. Please refer to Figure 2 A search data-based tourism market hotspot mining method, which provides the following technical scheme:

[0117] S1, the client collects user search behavior data, and then uploads the user search behavior data to the server through the client for storage: the user search behavior data includes user behavior data, occurrence time, occurrence page, user geographic information, user personal attributes and other information;

[0118] S2, the security analysis module analyzes the user search behavior data stored in the server according to the crawler judgment module of the crawler, and if it is determined as a crawler behavior, it is fed back to the server; if it is determined as a safe behavior, S3 is performed;

[0119] S3, the user search behavior data is filtered, invalid search words are discarded, and real search words and parsed search words are retained;

[0120] S4, the filtered search words are stored in the database;

[0121] S5 mines hot scenic spot data in different dimensions based on the real search words and the parsed search words, including the destination and departure place dimension, the domestic and foreign dimension, the different heat period dimension, and supplements the scenic spot attribute information. Since the scenic spot data screening dimension is high, the SQL is complex, the joined tables are extremely large, the data volume is up to the order of 10 billion, and the daily increment is up to the order of 100,000, the application uses the StarRocks data analysis system which naturally supports join, and through the simplified architecture, the efficient vector engine and the newly designed cost-based optimizer (CBO), it can meet the needs of more users for fast analysis of data. The core only has FE (Frontend) and BE (Backend) two types of processes, among which FE is mainly responsible for parsing the query statement (SQL), optimizing the query and scheduling the query, and BE is mainly responsible for reading data from the data lake and completing a series of Filter and Aggregate operations. Query optimization mainly relies on the StarRocks optimizer (CBO), which fully supports the TPC-DS 99 SQL, realizes public expression reuse, related subquery rewriting, Lateral Join, CTE reuse, Join Rorder, Join distributed execution strategy selection, Runtime Filter pushdown, low-base number dictionary optimization and other important functions and optimizations. Query optimization is also reflected in: MPP execution and vectorized execution engine. MPP (massively parallel processing) is the abbreviation of large-scale parallel computing, the core method is to split the query Plan into many computing instances that can be executed on a single node, and then multiple nodes are executed in parallel. Each node does not share CPU, memory and disk resources. The core of operator and expression vectorized execution is batch column execution, batch execution, which can have fewer virtual function calls and fewer branch judgments compared with single-row execution; column execution is more friendly to CPU Cache and easier to optimize with SIMD compared with row execution. Figure 3 The overall architecture diagram of StarRocks.

[0122] S6 establishes a hot city mining module through the hot scenic spot data;

[0123] S7 establishes a hot province mining module through the hot city scenic spot data;

[0124] S8 constructs the mapping relationship between the theme and the scenic spot, aggregates the hot theme in different dimensions, and predicts the future hot theme, and the specific formula is as follows:

[0125]

[0126] Among them, is the theme heat value of the day, is the historical time series data of the theme heat based on the current day;

[0127]

[0128] wherein, is the theme heat value of the next day, is the historical time series data of the theme heat based on the next day;

[0129]

[0130] wherein, H t+30 is the theme heat data prediction value within the next 30 days, is the theme heat value of the next 30 days, H t′-15 is the theme heat data prediction value within the next 15 days, H t′-15 is the theme heat data prediction value within the next 16 to 30 days;

[0131] ΔH = H t′+15 -H t′-15 (4)

[0132] wherein, ΔH is the ring increase value between the theme heat data prediction value within the next 15 days and the theme heat data prediction value within the next 16 to 30 days;

[0133]

[0134] wherein, ΔB is the ring ratio value between the theme heat data prediction within the next 15 days and the theme heat data prediction within the next 16 to 30 days, avgΔH is the ring increase average value between the theme heat data prediction within the next 15 days and the theme heat data prediction within the next 16 to 30 days, avg H t′-15 is the theme heat data prediction average value within the next 16 to 30 days;

[0135]

[0136] score is the comprehensive heat index based on the ring increase and the ring ratio, max(ΔH) is the maximum value in the theme heat data prediction value within the next 15 days, max(ΔB) is the maximum value in the ring ratio value between the theme heat data prediction within the next 15 days and the theme heat data prediction within the next 16 to 30 days.

[0137] S9 integrates the hot spot data of the tourism market for front-end display, combined with marketing activities;

[0138] S10 provides complete hot spot guidance schemes according to the hot spot data: including hot spot heat comparison, product coverage of suppliers related to hot spots, and suggestions for distribution, etc.

[0139] Figure 3 is a structural block diagram of an analysis system running the search-based travel hotspot analysis method of the present application. Please refer to Figure 3 , a search data-based travel market hotspot analysis method system mainly includes:

[0140] A client is used to collect user search behavior data, and then upload the data to the server through the client for storage;

[0141] A security analysis module is used to determine whether the search behavior is crawler data according to the crawler judgment rule, and select the real user behavior data

[0142] A search term filtering module is used to preprocess and filter the user search behavior data, discard invalid search data, and save the effective results to the corresponding table in the database;

[0143] A popular scenic spot mining module is used to separate scenic spot related data from user search behavior data by using different dimension aggregation algorithms, and realize different levels of popular scenic spot mining;

[0144] A popular city mining module is mainly based on the popular scenic spot mining module, captures hot spots from the city dimension, and is convenient for users to directly obtain city hot spots and select popular cities;

[0145] A popular province mining module is mainly based on the popular city mining module, captures hot spots from the province dimension, and is convenient for users to directly obtain province hot spots and make decisions on tourism provinces;

[0146] A popular theme mining module is used to aggregate scenic spot heat to themes by using scenic spot information, condense seasonal information, and realize the purpose of users' atmosphere tourism. By using XGBOOST combined with historical time series data of theme heat and date attribute d t (factors such as whether it is a weekend, whether it is a weekday, whether it is a holiday, etc.), the heat data of the theme in the future date is predicted. The newly predicted theme heat data is supplemented to the training set, and the model is retrained to obtain the theme heat data of the next day in the future. Through iteration, the heat data of the theme in the next 30 days is predicted. The 30 days are divided into the first 15 days and the last 15 days, and by calculating the comprehensive heat index of the ring increase and the ring ratio, the theme prediction of the future date is realized,

[0147] Figure 4 is a module schematic diagram of the search-based travel hotspot analysis system of the present application. As Figure 4 shown, the embodiment of the present application also provides a search-based travel hotspot analysis system for realizing the search-based travel hotspot analysis method described above. The search-based travel hotspot analysis system 5 includes:

[0148] The user data collection module 51 collects user search behavior data and then uploads the data to the server for storage through the client;

[0149] The search behavior filtering module 52 pre-processes and filters the user search behavior data, filters invalid search data, and saves the real user search behavior data to the database;

[0150] The popular scenic spot information module 53 extracts scenic spot related data from the real user search behavior data using an aggregation algorithm based on a preset dimension combination to obtain popular scenic spot information;

[0151] The popular theme prediction module 54 aggregates the popular scenic spot information to predict popular themes in a future preset period;

[0152] The popular travel product module 55 pushes travel products matching the popular themes to the client of a user meeting the preset dimension combination in the future preset period.

[0153] In a preferred embodiment, the user data collection module 51 is configured to collect user search behavior data including user behavior data, occurrence time, occurrence page, user geographic information, and user personal attribute information.

[0154] In a preferred embodiment, the search behavior filtering module 52 is configured to analyze the user search behavior data saved by the server according to the database and the crawler judgment module. If the behavior is determined to be a crawler behavior, the server is fed back. If the behavior is determined to be a safe behavior, the user search behavior data is filtered, invalid search words are discarded, real search words and parsed search words are retained, and the filtered search words are stored in the database.

[0155] In a preferred embodiment, the popular scenic spot information module 53 is configured to mine popular scenic spot data in different dimensions based on real search words and parsed search words, including destination and departure location dimensions, domestic and foreign dimensions, and different heat period dimensions, and supplement scenic spot attribute information.

[0156] In a preferred embodiment, the popular theme prediction module 54 is configured to establish popular city scenic spot data based on the popular scenic spot data, establish popular province scenic spot data based on the popular city scenic spot data, aggregate popular themes in different dimensions based on the popular scenic spot data, the popular city scenic spot data, and the popular province scenic spot data, construct a mapping relationship between themes and scenic spots, and predict future popular themes.

[0157] In a preferred embodiment, the hot topic prediction module 54 is further configured to predict the hotness data of the topic in the future date by using XGBOOST combined with the historical time series data of the topic hotness and the date attribute; supplement the newly predicted topic hotness data to the training set, retrain the model to obtain the topic hotness data of the next day; iterate in this way to realize the prediction of the topic hotness data within the next 30 days.

[0158] In a preferred embodiment, the hot topic prediction module 54 is further configured to divide the 30 days into the first 15 days and the last 15 days, and realize the prediction of the topic in the future date by calculating the comprehensive hotness index of the ring increase and the ring ratio:

[0159]

[0160] wherein, is the topic hotness value of the day, is the historical time series data based on the topic hotness of the day;

[0161]

[0162] wherein, is the topic hotness value of the next day, is the historical time series data based on the topic hotness of the next day;

[0163]

[0164] wherein, H t+30 is the prediction value of the topic hotness data within the next 30 days, is the topic hotness value of the next 30 days, H t′-15 is the prediction value of the topic hotness data within the next 15 days, H t′-15 is the prediction value of the topic hotness data within the next 16 to 30 days;

[0165] ΔH=H t′+15 -H t′-15 (4)

[0166] wherein, ΔH is the ring increase value between the prediction value of the topic hotness data within the next 15 days and the prediction value of the topic hotness data within the next 16 to 30 days;

[0167]

[0168] wherein, ΔB is the ring ratio value between the prediction value of the topic hotness data within the next 15 days and the prediction value of the topic hotness data within the next 16 to 30 days, avgΔH is the ring increase average value between the prediction value of the topic hotness data within the next 15 days and the prediction value of the topic hotness data within the next 16 to 30 days, avg H t′-15is the average of the heat data prediction of the topic in the next 16 to 30 days;

[0169]

[0170] score is a comprehensive heat index based on ring increase and ring ratio, max(ΔH) is the maximum value in the heat data prediction of the topic in the next 15 days, and max(ΔB) is the maximum value in the ring ratio between the heat data prediction of the topic in the next 15 days and the heat data prediction of the topic in the next 16 to 30 days.

[0171] The search-based tourism hotspot analysis system of the present application can realize tourism market hotspot analysis based on search data, automatically obtain tourism market hotspot information through query optimization, and accurately predict seasonal trend data by relying on a large amount of real search data of users.

[0172] The embodiment of the present application also provides a search-based tourism hotspot analysis device, which comprises a processor and a memory having executable instructions of the processor stored therein.

[0173] As shown above, the search-based tourism hotspot analysis device of the present application can realize tourism market hotspot analysis based on search data, automatically obtain tourism market hotspot information through query optimization, and accurately predict seasonal trend data by relying on a large amount of real search data of users.

[0174] Those skilled in the art can understand that various aspects of the present application can be implemented as a system, a method or a program product. Therefore, various aspects of the present application can be embodied as a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, which can be collectively referred to as "circuitry", "module" or "platform" herein.

[0175] Figure 5 is a structural schematic diagram of the search-based tourism hotspot analysis device of the present application. The electronic device 600 according to this embodiment of the present application will be described below with reference to Figure 5 Figure 5 The displayed electronic device 600 is only an example and should not impose any limitation on the functions and use range of the embodiments of the present application.

[0176] As Figure 5 ​As shown, the electronic device 600 is in the form of a general computing device. Components of the electronic device 600 can include, but are not limited to, at least one processing unit 610, at least one storage unit 620, a bus 630 that connects the various platform components including the storage unit 620 and the processing unit 610, a display unit 640, and the like.

[0177] The storage unit stores program code that can be executed by the processing unit 610 to cause the processing unit 610 to perform the steps described in the above electronic prescription flow processing method section of the specification in accordance with various example embodiments of the present application. For example, the processing unit 610 can perform the steps shown in the flowchart of FIG. 6. Figure 1

[0178] The storage unit 620 can include a readable medium in the form of volatile storage such as a random access memory (RAM) 6201 and / or cache memory 6202, and can further include a read-only memory (ROM) 6203.

[0179] The storage unit 620 can also include program / utility 6204 having a set of programs / modules 6205, including an operating system, one or more application programs, other program modules, and program data, each of which can include an implementation of a network environment, or a portion thereof, as described in each of these examples or a combination thereof.

[0180] The bus 630 can represent one or more of several types of bus structures, including a storage bus or bus controller, a peripheral bus, a graphics bus (e.g., an Accelerated Graphics Port, or AGP bus) and a local bus using any of a variety of bus architectures.

[0181] The electronic device 600 can also communicate with one or more external devices 700 such as a keyboard or pointing device, a Bluetooth device, etc.; other devices that enable a user to interact with the electronic device 600; and / or one or more devices that enable the electronic device 600 to communicate with one or more other computing devices. Such communication can be via an input / output (I / O) interface 650. Similarly, the electronic device 600 can communicate with one or more networks, such as a local area network (LAN), a wide area network (WAN), and / or the Internet, via a network adapter 660. The network adapter 660 can communicate with the other components of the electronic device 600 via the bus 630. It should be appreciated that, although not shown, other hardware and / or software components that can be used in conjunction with the electronic device 600 can include, but are not limited to, microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival storage systems, etc.​

[0182] The embodiment of the present application also provides a computer readable storage medium for storing a program, the program being executed to implement the steps of the search-based travel hotspot analysis method. In some possible implementation manners, various aspects of the present application can also be implemented in the form of a program product, which includes program codes for causing a terminal device to perform the steps of the various exemplary embodiments of the present application described in the above electronic prescription flow processing method part of the specification when the program product is run on the terminal device.

[0183] As shown above, the search-based travel hotspot analysis system of the embodiment of the present application can implement travel market hotspot analysis based on search data, automatically obtain travel market hotspot information through query optimization, and accurately predict seasonal trend data by relying on a large amount of real search data of users.

[0184] Figure 6 is a structural schematic diagram of the computer readable storage medium of the present application. Referring to Figure 6 As shown in the figure, the program product 800 for implementing the above method according to the embodiment of the present application can be in the form of a portable compact disc read-only memory (CD-ROM) and include program codes, and can be run on a terminal device such as a personal computer. However, the program product of the present application is not limited to this, and in this document, the readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, device or apparatus.

[0185] The program product can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include an electrical connection having one or more wires, a portable disc, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0186] The computer readable storage medium can include a computer-readable medium in baseband or propagated as a carrier wave in a propagated signal, wherein the propagated signal is one example of a carrier wave. Computer readable storage medium can also be any medium that can be read by a machine, including but not limited to read-only memory (ROM), random access memory (RAM), nonvolatile memory (e.g., flash memory, ferroelectric memory, etc.), or any other suitable medium. The computer readable storage medium can be a computer readable storage medium that is part of a computer system or a computer network, or it can be a computer program product such as a compact disk, a diskette, a tape, a cassette, a cartridge, etc. The computer readable program code can be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the above.

[0187] Program code used by or in connection with the described embodiments, when implemented in software can be stored in various portions of volatile or non-volatile storage. The memory can also store other data and / or program code relating to the application. The application can be stored on or transmitted across some type of computer readable media, which can be any available media that can be accessed by a general purpose or special purpose computer system. By way of example, and not limitation, such computer readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other volatile or non-volatile storage medium.

[0188] In summary, the present application aims to provide a search-based tourism hotspot analysis method, system, device and storage medium, which can realize tourism market hotspot analysis based on search data, automatically obtain tourism market hotspot information through query optimization, and accurately predict seasonal trend data based on a large amount of real search data of users.

[0189] The above is a further detailed description of the present application in combination with specific preferred embodiments, and the specific implementation of the present application cannot be limited to these descriptions. For those skilled in the art to which the present application belongs, without departing from the concept of the present application, a number of simple deductions or replacements can be made, which should be considered as falling within the protection scope of the present application.

Claims

1. A search-based travel hotspot analysis method, characterized by, The method comprises the following steps: S110, collecting user search behavior data and then uploading to the server through the client for storage; S120, preprocessing and filtering the user search behavior data, filtering invalid search data, and saving the real user search behavior data to the database; S130, extracting scenic spot related data from the real user search behavior data by using an aggregation algorithm based on a preset dimension combination to obtain popular scenic spot information; S140, establishing popular city scenic spot data through the popular scenic spot data; establishing popular province scenic spot data through the popular city scenic spot data; aggregating popular themes in different dimensions based on the popular scenic spot data, the popular city scenic spot data and the popular province scenic spot data; constructing a mapping relationship between the theme and the scenic spot, predicting future popular themes, predicting the theme heat data of future dates by using XGBOOST in combination with historical time series data and date attributes of the theme heat; supplementing the newly predicted theme heat data to the training set, retraining the model, and obtaining theme heat data of a new day in the future; Through iteration, the theme heat data prediction within 30 days in the future is realized, including: dividing the 30 days into the first 15 days and the last 15 days, realizing the theme prediction of future dates by calculating the comprehensive heat index of the ring increase and the ring ratio: wherein, is the topic heat value of the day, is the historical time series data based on the topic heat of the day; wherein, is the topic heat value of the following day, is historical time series data based on the topic heat of the following day; wherein H "+30 is a predicted value of the heat data of the theme in the next 30 days, is the heat value of the theme in the next 30 days, H t′-15 is a predicted value of the heat data of the theme in the next 15 days, H t′+15 is a predicted value of the heat data of the theme in the next 16 to 30 days; ΔH = H t′+15 -H t′-15 (4) Wherein, ΔH is the ring increase value between the theme heat data prediction within the future 15 days and the theme heat data prediction within the future 16 to 30 days; wherein, ΔB is the year-on-year value between the hotness data prediction of the topic in the next 15 days and the hotness data prediction of the topic in the next 16 to 30 days, avgΔH is the average year-on-year increase between the hotness data prediction of the topic in the next 15 days and the hotness data prediction of the topic in the next 16 to 30 days, avgH t′+15 is the average hotness data prediction of the topic in the next 16 to 30 days; Score is the comprehensive heat index based on the ring increase and the ring ratio, max(ΔH) is the maximum value in the ring increase value between the theme heat data prediction within the future 15 days and the theme heat data prediction within the future 16 to 30 days, and max(ΔB) is the maximum value in the ring ratio value between the theme heat data prediction within the future 15 days and the theme heat data prediction within the future 16 to 30 days; S150, pushing the tourism product matching the popular theme to the client of the user meeting the preset dimension combination within a future preset period.

2. The search-based travel hotspot analysis method of claim 1, wherein, In the step S110, the user search behavior data comprises user behavior data, occurrence time, occurrence page, user geographic information and user personal attribute information.

3. The search-based travel hotspot analysis method of claim 1, wherein, In the step S120, the following steps are included: S1201, the security analysis module analyzes the user search behavior data saved by the server according to the crawler judgment module in the database, and if it is determined as a crawler behavior, it is fed back to the server; if it is determined as a safe behavior, the step S1202 is performed; S1202, filtering the user search behavior data, discarding invalid search words, and retaining real search words and parsed search words; S1203, storing the filtered search words in the database.

4. The search-based travel hotspot analysis method of claim 1, wherein, In the step S130, the following steps are included: based on the real search words and the parsed search words, hot scenic spot data in different dimensions are mined, including destination and departure dimension, domestic and foreign dimension, different heat period dimension, and scenic spot attribute information is supplemented.

5. A search-based travel hotspot analysis system for implementing the search-based travel hotspot analysis method of claim 1, characterized by, The method comprises the following steps: A user data collection module collects user search behavior data and then uploads to the server through the client for storage; The search behavior filtering module pre-processes and filters the user search behavior data, filters invalid search data, and saves the real user search behavior data to a database. The popular scenic spot information module extracts scenic spot related data from the real user search behavior data using an aggregation algorithm based on a preset dimension combination to obtain popular scenic spot information. The popular theme prediction module establishes popular city scenic spot data based on the popular scenic spot data, establishes popular province scenic spot data based on the popular city scenic spot data, aggregates popular themes in different dimensions based on the popular scenic spot data, the popular city scenic spot data, and the popular province scenic spot data, constructs a mapping relationship between themes and scenic spots, predicts future popular themes, predicts theme heat data in future dates using XGBOOST in combination with historical time series data and date attributes of theme heat, supplements the newly predicted theme heat data to the training set, re-trains the model, and obtains theme heat data for the next day. This iteration realizes the prediction of theme heat data within the next 30 days, including: dividing the 30 days into the first 15 days and the last 15 days, calculating the comprehensive heat index of the ring increase and the ring ratio, and realizing the prediction of themes in future dates: wherein, is the topic heat value of the day, is the historical time series data based on the topic heat of the day; wherein, is the topic heat value of the following day, is historical time series data based on the topic heat of the following day; wherein H "+30 is a predicted value of the heat data of the theme in the next 30 days, is the heat value of the theme in the next 30 days, H t′-15 is a predicted value of the heat data of the theme in the next 15 days, H t′+15 is a predicted value of the heat data of the theme in the next 16 to 30 days; ΔH = H t′+15 - H t′-15 (4) Wherein, ΔH is the ring increase value between the theme heat data prediction within the next 15 days and the theme heat data prediction within the next 16 to 30 days; wherein, ΔB is the year-on-year value between the hotness data prediction of the topic in the next 15 days and the hotness data prediction of the topic in the next 16 to 30 days, avgΔH is the average of the year-on-year increase between the hotness data prediction of the topic in the next 15 days and the hotness data prediction of the topic in the next 16 to 30 days, avgH t′+15 is the average of the hotness data prediction of the topic in the next 16 to 30 days; Score is the comprehensive heat index based on the ring increase and the ring ratio, max(ΔH) is the maximum value in the ring increase value between the theme heat data prediction within the next 15 days and the theme heat data prediction within the next 16 to 30 days, and max(ΔB) is the maximum value in the ring ratio value between the theme heat data prediction within the next 15 days and the theme heat data prediction within the next 16 to 30 days; The popular travel product module pushes the travel product matching the popular theme to the client of the user satisfying the preset dimension combination within the future preset period.

6. A search-based travel hotspot analysis device, characterized by, It includes: A processor; A memory having executable instructions of the processor stored therein; The processor is configured to execute the executable instructions to perform the steps of the search-based tourism hotspot analysis method of any one of claims 1 to 4.

7. A computer readable storage medium for storing a program, characterized in that, The program is executed by the processor to realize the steps of the search-based tourism hotspot analysis method of any one of claims 1 to 4.

Images