CN113761384A - Tourist classification data processing method and system based on big data - Google Patents
Tourist classification data processing method and system based on big data Download PDFInfo
- Publication number
- CN113761384A CN113761384A CN202111323075.XA CN202111323075A CN113761384A CN 113761384 A CN113761384 A CN 113761384A CN 202111323075 A CN202111323075 A CN 202111323075A CN 113761384 A CN113761384 A CN 113761384A
- Authority
- CN
- China
- Prior art keywords
- product
- user
- page
- ranking
- grading
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
- G06F16/9562—Bookmark management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/14—Travel agencies
Abstract
The invention relates to the field of data processing, in particular to a tourist classification data processing method and a system based on big data. The method and system are used for executing the following steps: page marking: as an overall product page library; and (4) judging by the user: judging whether the user is a new user or an old user; pushing once, and randomly calling part of page tags to push to a user side; basic analysis: setting an initial rating for the user; updating and pushing: generating a new basic page list by combining the initial push list and the exceptional page tags, replacing the original basic page list, and pushing the new basic page list to the client; exception record: recording the grading information of the exceptions browsed by the user; big data analysis: calculating the data ratio of each page set according to the number of pages in each page set; and generating an iteration page list, and updating the basic page list in an iteration mode. The invention makes up the defect of single data sample through the iterative correction of the push label, improves the push accuracy and improves the data interaction efficiency.
Description
Technical Field
The invention relates to the field of data processing, in particular to a tourist classification data processing method and a system based on big data.
Background
In the travel industry, there is a diversity in the classification of travel items and user preferences. For example, different users often have different preferences for travel items in natural scenic spots, human scenic spots, recreational activities, overseas, and the like. In order to better approach to the consumption habits and consumption abilities of users, the existing online tourism platform and tourism service organization often perform big data collection and operation according to the browsing history, consumption history and related information of the users, portray each user through algorithms such as cluster analysis and the like, acquire parameters such as consumption preference, consumption level and the like of each user, and push related product introduction to the users according to the obtained portraits of the users, so that the achievement rate of advertisement push is improved, the receiving rate of irrelevant information of the users is reduced, and the efficiency of information interaction is improved.
However, as the awareness of people to protect personal data information is strengthened and the monitoring is becoming stricter, the authority for obtaining information, such as detailed location information and identity information, of a user, which is closely related to the user's individual is restricted, and as for the trend, such information cannot be actively collected any more later, so that the object capable of performing big data analysis only has a few main indexes, such as search records, browsing records and consumption records of the user on a single platform, and the accuracy of user images performed through only a few indexes and a small amount of data is greatly reduced compared with the past, which causes the accuracy of pushed contents to be correspondingly reduced, and reduces the efficiency of information interaction. Therefore, how to still improve the accuracy of pushing without collecting personal information of a user becomes a problem to be solved urgently in the industry.
Disclosure of Invention
In a first aspect, the present invention provides a big data based guest ranking data processing method that addresses the above-mentioned deficiencies.
The method comprises the following steps:
s1, page marking: generating a product page for browsing and a page label corresponding to each product page corresponding to each travel service product, marking travel product grading and consumption grading for the product page, and combining the travel product grading and the consumption grading into product grading which is used as a product page library of service products which can be provided by the whole;
s2, judging by the user: judging whether the user is a new user or an old user, wherein the new user goes down from the step S3, and the old user goes down from the step S5;
s3, pushing once, randomly calling partial page tags from the product page library, randomly sequencing to form a basic page tag list, and pushing the basic page tag list to a user side;
s4, basic analysis: collecting one or more of search records, product page browsing records and consumption records of a user, determining the grade of the tourism product through the search records and/or the browsing records, determining the consumption grade through the browsing records and/or the consumption records, and combining the grade of the tourism product and the consumption grade as the initial grade of the user;
s5, updating and pushing: calling a corresponding page tag according to the initial classification of a user to generate an initial push list, randomly inserting a group of exception page tags which are not directly related to at least one of the classification of the initially classified tourism products and the classification of consumption of the user, generating a new basic page list by combining the initial push list and the exception page tags, replacing the original basic page list, and pushing the new basic page list to a client;
s6, exception record: recording the grading information of a product page corresponding to the exceptional page tag browsed by the user;
s7, big data analysis: acquiring corresponding product pages in search records and browsing records related to initial classification of each user group with the same initial classification, and product pages of the search records and browsing records corresponding to exceptional page tags to form a plurality of page sets, and then calculating the data proportion of each page set according to the number of pages in each page set;
s8, iterative pushing: and calling page labels from the product page library according to the proportion according to the data proportion of each page set of each user group with the same initial grade to generate an iteration page list, and iteratively updating the basic page list.
After the method is adopted, the initial grading of the user can be preliminarily determined by collecting the search record, the browsing record and the consumption record of a single user with a relatively single data sample, then the browsing record and the consumption record of the indirectly related supplementary tags are used as variable factors for correcting the initial grading of the user, finally, a final pushed tag set is obtained by comprehensively calculating the initial grading and the variable factors of the collective user, the defect that the data sample is relatively single is made up by iterative correction of the pushed tags, the pushing accuracy is improved, and the data interaction efficiency is improved.
In a possible implementation manner, when determining the base product ranking through the search record in step S4, the result list corresponding to the search record is read, the product ranking codes read from the tags in the result list, and the product ranking codes of most results are used as the product ranking codes corresponding to the search record.
In a second aspect, the present invention also provides a big data based guest ranking data processing system, which is characterized in that the system comprises:
the user interface module is used for acquiring input information of a user and displaying data to the user;
the user management module is in data communication with the user interface module and stores input information acquired by a user from the user interface module;
the product label library module is used for storing a product page and a page label corresponding to each travel service product;
the product grading writing module is in data communication with the product label base module and is used for defining the product grading of the travel service product and writing the product grading into a corresponding product label in the product label base module;
the pushing module is in data communication with the user interface module and the product label library module, and is used for calling corresponding page labels from the product grading module according to the input information of the user received from the user interface module to form a pushing list and pushing the pushing list to the user interface module;
the basic analysis module is used for reading one or more of search records, browsing records and consumption records in the input information acquired by the user management module, acquiring the grades of the tourist products from the product grading writing module through the search records and/or the browsing records, acquiring the consumption grades from the product grading writing module through the browsing records and/or the consumption records, combining the grades of the tourist products and the consumption grades as the initial grades of the user, and sending the initial grades to the user management module;
the push updating module is in data communication with the user management module, reads the initial grading in the user management module, generates an initial push list according to initial grading information, inserts a group of exception page tags which are not directly related to at least one of the tourism product grading and the consumption grading of the initial grading of the user, and updates the basic list by combining the initial push list and the exception page tags to form an updated list and push the updated list to the user interface module;
the exception record storage module is in data communication with the user interface module and records the grading information of the product page corresponding to the exception page tag which is not directly related and browsed by the user;
the big data analysis module is in data communication with the user management module and the basic analysis module, acquires the sum of the number of corresponding product pages in the search record, the browsing record and the consumption record of each user with the same initial grade and the sum of the number of product grades of the browsing record and the consumption record corresponding to the exceptional page tags, and calculates the proportion of the page tags corresponding to the user group with the same initial grade in the searching, browsing and consumption behaviors in the total amount;
and the pushing iteration module is in data communication with the user management module, the big data analysis module and the pushing module, and calls page tags from the product tag library according to the proportion of the total amount of the page tags corresponding to the searching, browsing and consuming behaviors of each user group with the same initial grade and updates the update list of the corresponding user group in an iteration mode.
Drawings
Fig. 1 is a schematic flow chart of the first embodiment.
Fig. 2 is a detailed flowchart of step S1 in the second embodiment.
Fig. 3 is a detailed flowchart of step S4 in the first and second embodiments.
Fig. 4 is a detailed flowchart of step S5 of the first and second embodiments.
Fig. 5 is a block configuration diagram of the overall system of the third embodiment.
Fig. 6 is a block configuration diagram of a user interface module of the third embodiment.
Fig. 7 is a block diagram of a product hierarchy writing module of the third embodiment.
Fig. 8 is a block configuration diagram of a basic analysis module of the third embodiment.
Fig. 9 is a block configuration diagram of a big data analysis block of the third embodiment.
Detailed Description
The general concepts and systems of the various embodiments of the present invention are first described in general. In the existing big data analysis, when portrait analysis is performed on a user, a lot of data and information need to be called, for example, the user can obtain the commodity and service preference according to browsing information of a user browser, search information of a search engine and purchasing records of online shopping, the consumption capability of the user can be obtained by obtaining detailed position information of the user, such as an address and a working unit, and the information of the user, such as gender, age, native place and the like, can be obtained through the identity card number of the user to supplement and adjust the user preference and the consumption capability, so that accurate portrait of the user is obtained, proper information is pushed to the user, and the accuracy of information delivery is improved. However, with the development of privacy information protection systems and techniques, none of the information can be acquired without user permission. The most important identity card information is used as important privacy information of individuals, information of addresses, work units and the like, and when the identity card information is used as business information, strict regulation is faced, and the requirements of non-necessary collection are met. Detailed external information of a user, browsing information of a user browser, searching information of a search engine, purchasing records of online shopping and other information are collected only by obtaining permission of the user, and the user tends to be conservative for disclosure of the information, so that a user portrait strategy based on all-around big data faces the problems of insufficient data sources and key information loss in the future, and an artificial intelligence operation and recommendation algorithm of the user portrait based on the big data also faces failure.
The existing e-commerce platforms have algorithms for recommending product lists according to search, browse, collection and purchase records of users, the algorithms are used for recommending lists based on product or brand keywords, the recommendation result is large in limitation, the algorithms are mainly used in use scenes with clear user requirements, the exploration degree of derived requirements of the users is insufficient, and the mining of the requirements is not deep enough.
The following embodiments of the present invention therefore focus on processing a single user's data and then generating a recommendation list through a large data analysis of all users. The recommendation list contains important critical information, derived demand information and demand development information of the user, and customer service and product recommendation are better performed.
The first embodiment mainly introduces the basic steps of a big data-based guest ranking data processing method, as shown in fig. 1 to 4, specifically including the steps of:
s1, page marking: generating a product page for browsing and a page label corresponding to each product page corresponding to each travel service product, marking travel product grading and consumption grading for the product page, and combining the travel product grading and the consumption grading into product grading which is used as a product page library of service products which can be provided by the whole;
specifically, the method can be performed according to the following steps:
s11, respectively defining character string identifications for different product types and price intervals according to the product types and price intervals of the travel products corresponding to the product pages;
s12, defining a product grading variable, merging and writing the character string identification corresponding to the product type and the character string identification corresponding to the price interval into the product grading variable to obtain a product grading code of the same product type and the same price interval;
and S13, marking the corresponding product page by using the product grading code.
For the travel products, the core contents of the travel products are firstly classified according to the interest orientation, and for the classification of the travel products, landscape products taking landform landscapes such as mountains, forests and seas and the like as main bodies of the travel, such as Huangshan, Zhangjia, Sanxia, Jiuzhaigou, Sansui and the like; scenic spot products taking historical humanistic scenic spots as main bodies of tourism, such as yellow crane buildings, terracotta warriors, tombstone, palace and the like; tourist parks with theme playing facilities as the theme of the tour, such as Disneyland, Changhong water park, animal and plant park, and movie city; the general interest tendencies of the user groups can be judged according to the types, so that the user groups can be graded, for example, natural scenery is distributed as A grade, human scenery is distributed as B grade, theme park is distributed as C grade, and in addition, unspecified tourism products such as overseas and overseas can be distributed as D grade, or one scenery can be distributed in multiple grades, for example, Songshan Shaolin Temple, Wudangshan Daojie building group, and the scenery with both natural scenery of mountain forest and religious culture sceneries, and the scenery can be distributed with two grades, namely A grade and B grade. According to the characteristics of travel products, besides being used as core content of tourism, matched transportation and accommodation services are often packaged, and according to the difference of the transportation and accommodation conditions, the overall price is often greatly different, for example, for the play in the same scenic spot, the price of a service pack containing an airplane ticket and a five-star hotel is often greatly different from the price of a service pack containing a train ticket and a common hotel, so that the service pack faces users with different consumption levels according to the difference of price intervals. Therefore, in addition to the classification of the travel products, the consumption levels are also classified, for example, 0-2000 is class 01, 2001-5000 is class 02, 5001-10000 is class 03, 10001-20000 is class 04, and above 20001 is class 05. After the classification of the tourism products and the consumption classification are finished, the tourism products and the consumption classification are combined into a whole to form a product classification, such as A03, C02, D05 and the like, namely, products which are positioned in the same consumption interval and aim at the same type of tourism projects are classified into the same classification according to the product classification.
S2, judging by the user: judging whether the user is a new user or an old user, wherein the new user goes down from the step S3, and the old user goes down from the step S5;
when a user uses the system, the user needs to be judged first, the new user is a user who never searches and checks records, the old user searches and checks records, and the old user need to pass different strategies when pushing, so that different pushing processes need to be distinguished and designated.
S3, pushing once, randomly calling partial page tags from the product page library, randomly sequencing to form a basic page tag list, and pushing the basic page tag list to a user side; for a new user, when pushing for the first time, because information about the interest range and the like of the new user is not acquired yet, content pushing needs to be actively and randomly performed for the user, a basic interface for acquiring user input operation is provided, so that the user can browse and view according to the interest range, and browsing records of the user are stored.
S4, basic analysis: collecting one or more of search records, product page browsing records and consumption records of a user, determining the grade of the tourism product through the search records and/or the browsing records, determining the consumption grade through the browsing records and/or the consumption records, and combining the grade of the tourism product and the consumption grade as the initial grade of the user;
after a user performs one or more of searching, browsing and consuming behaviors, determining an initial rating for a page searched, browsed and consumed by the user, the basic format of the initial rating being consistent with a product rating, and merging a travel product rating and a consumption rating as the initial rating for the user comprising the steps of:
s41, creating an initial grading variable under the account of the user;
s42, merging and writing the character string identifications corresponding to the obtained travel product grades and the consumption grades into initial grading variables, and creating the initial grading codes of the users.
It should be noted that, since the page corresponding to the consumption record is necessarily from the page existing in the browsing record, the consumption record is an optional addition, and only the search record and the browsing record may be considered in actual implementation.
S5, updating and pushing: calling a corresponding page tag according to the initial classification of a user to generate an initial push list, randomly inserting a group of exception page tags which are not directly related to at least one of the classification of the initially classified tourism products and the classification of consumption of the user, generating a new basic page list by combining the initial push list and the exception page tags, replacing the original basic page list, and pushing the new basic page list to a client;
specifically, generating an initial push list according to the initial ranking of the user includes the steps of:
s51, according to the initial hierarchical code of the user, searching the same product hierarchical code as the initial hierarchical code in the label library:
s52, reading the product label under the product grading code;
and S53, sorting the read product labels to form an initial push list.
Wherein the supplementary tags not directly related to at least one of the travel product rating and the consumption rating of the initial rating of the user include a product tag corresponding to a product rating code different from the product rating code of the initial rating code, a product tag corresponding to a product rating code different from the consumption rating code of the initial rating code, and a product tag corresponding to a product rating code different from both the travel product rating and the consumption rating code of the initial rating code.
For example, the initial rating of the user is B03, then the product page with the product rating of B03 is the underlying invocation object. Meanwhile, in order to expand the push targeting range and achieve the purpose of exploring the user requirements, in the embodiment, product pages with the same travel product grade and close consumption grade are used as calling objects, such as B02 and B04; in addition, additional product pages with the same consumption grade but different travel products are added as calling objects around the consumption range of the initial grade, such as A03 and C03. In addition, it is desirable to leave a small proportion of product pages with both non-travel product ratings and consumption ratings different from the initial ratings, e.g., C01, D05. At this time, the product page object set forming the new push list is selected, and the proportion of each part in the product page object set at this time can be randomly selected or set manually, and proportion shares can be distributed from large to small according to the degree of association with the initial classification of the user, for example, 50% of proportion fully related to the initial classification, 20% of proportion related to a single item in the initial classification, and 10% of proportion unrelated to the initial classification, where the proportion is merely an example, and the actual proportion can be set as required.
After the new push list is formed, the new push list is inserted into the original list from the extreme end of the displayed list of the list pushed once in step S3, the part of the original list not displayed is replaced, the new push list is formed, and the user can view the new push list by directly sliding down the original interface.
S6, exception record: recording the grading information of a product page corresponding to the exceptional page tag browsed by the user;
the step records browsing records of the product pages which are completely not corresponding to the tourism product classification and the consumption classification and the initial classification of the user, and records the ratio of the browsing records of the completely not corresponding product pages to the total browsing records. According to the proportion, included product grades can be changed as much as possible on the premise of the proportion, and the interest points of users on travel products in different directions are comprehensively explored without influencing the overall push content.
The above steps are directed to record analysis of the query and browsing records of a single user and designation of a pushing mechanism, but query and browsing operations of the single user have large uncertainty, and since the query and browsing records of the single user are limited in number, contents of a pushing list obtained according to the above steps often have individuality, that is, for users of the same type with the same initial classification, the obtained list contents often have large difference, so that the data needs to be further processed based on the above steps to obtain a pushing list suitable for a plurality of users of the same type, and the overall accuracy of pushing is further improved, so as to achieve the purpose of improving the transaction rate. The process of step S7 is further performed based on the processing result of the above-described step.
S7, big data analysis: acquiring corresponding product pages in search records and browsing records related to initial classification of each user group with the same initial classification, and product pages of the search records and browsing records corresponding to exceptional page tags to form a plurality of page sets, and then calculating the data proportion of each page set according to the number of pages in each page set;
in step S7, based on the foregoing step of processing data of a single user, further processing the whole data of the same type of user with the same initial rank, further processing the total amount of product pages corresponding to the whole search records and browsing records of the same type of user to obtain page sets corresponding to each different product rank, and calculating the total amount of each page set according to the number of pages in each page set.
For example, in the user group composed of similar users initially classified as A02, the product ranking corresponding to the overall viewed product page includes A02. Wherein according to the calculated proportions, A02 (64%), C03 (17%), D02 (7%), A01 (6%), B05 (4%), A03 (1%), E04 (1%) are obtained.
S8, iterative pushing: and calling page labels from the product page library according to the proportion according to the data proportion of each page set of each user group with the same initial grade to generate an iteration page list, and iteratively updating the basic page list.
After obtaining the ratio obtained in step S7, for the user initially classified as a02, that is, the user calls the page tags in the corresponding ratio from the product page library according to the obtained ratio to form a new push list, and inserts the new push list into the updated push list in step S5 to perform a second update. After the new push list is formed, the new push list is inserted into the original list from the end of the displayed list of the updated push list in step S5, the part of the original list not displayed is replaced, the new push list is formed, and the user can view the new push list by directly sliding down the original interface.
With the increase of the browsing number of the users and the increase of the user amount, the occupation ratio of the page set number and the page set continuously changes, so that the list continuously iterates by self, and a more accurate pushing effect is achieved.
By adopting the method of the first embodiment, the initial grading of the user can be preliminarily determined by collecting the search record, the browsing record and the consumption record of a single user with a relatively single data sample, then the browsing record and the consumption record of the indirectly related supplementary tag are used as variable factors for correcting the initial grading of the user, finally, a final pushed tag set is obtained by comprehensively calculating the initial grading and the variable factors of the collective user, the defect that the data sample is relatively single is made up by the iterative correction of the pushed tag, the pushing accuracy is improved, and the data interaction efficiency is improved.
In the first embodiment, when the product classification is determined by searching the record, since the search behavior is often the input operation of the keyword at the user end, and the keyword itself does not carry the encoding information required for the product classification, it is often necessary to allocate a corresponding product classification code to the keyword through intelligent semantic analysis to match with the subsequent data processing step. The form and content of the keywords are very flexible, the intelligent semantic analysis algorithm is used for distributing proper product hierarchical codes to the keywords, the complexity of the algorithm and the operation speed of the server are greatly increased, and in order to simplify the algorithm, a second embodiment is further provided on the basis of the first embodiment.
The second embodiment is mainly based on the processing of the search record in step S4 of the first embodiment, and when the base product ranking is determined by the search record in step S4, the result list corresponding to the search record is read, the product ranking code read from the tag in the result list is used, and the product ranking code of the majority of results is used as the product ranking code corresponding to the search record.
After the processing method is adopted, a search result list is obtained by means of common search operation, and the hierarchical codes of the products which account for most of the search results are used as the hierarchical codes of the products corresponding to the search records, so that the hierarchical codes of the products corresponding to the search keywords can be distributed only by adding one counting calculation, the scale and the complexity of the algorithm are greatly simplified, and the operation efficiency is improved.
A third embodiment of the present invention provides a big data based guest ranking data processing system, as shown in fig. 5, comprising:
the user interface module 1 is used for acquiring input information of a user and displaying data to the user; the user interface module 1 is located at a user end, is a computing terminal with instruction input and display output, and can be a computer, a mobile communication device and the like which are networked.
The user management module 2 is in data communication with the user interface module and stores input information acquired by a user from the user interface module;
the information input by the user is stored and comprises information such as an account registered by the user, a query browsing record of the content and the like.
The product label library module 3 is used for storing a product page and a page label corresponding to each travel service product;
the product grading write-in module 4 is in data communication with the product label base module 3 and is used for defining the product grading of the travel service product and writing the product grading into a corresponding product label in the product label base module 3;
the pushing module 5 is in data communication with the user interface module 1 and the product label library module 3, and is used for calling corresponding page labels from the product grading module 3 according to the input information of the user received from the user interface module 1 to form a pushing list and pushing the pushing list to the user interface module 1;
the basic analysis module 6 is used for reading one or more of search records, browsing records and consumption records in the input information acquired by the user management module 2, acquiring the grades of the tourist products from the product grading writing module through the search records and/or the browsing records, acquiring the consumption grades from the product grading writing module 4 through the browsing records and/or the consumption records, combining the grades of the tourist products and the consumption grades as the initial grades of the user, and sending the initial grades to the user management module 2;
the pushing updating module 7 is in data communication with the user management module 2, reads the initial grading in the user management module 2, generates an initial pushing list according to the initial grading information, inserts a group of exceptional page tags which are not directly related to at least one of the tourism product grading and the consumption grading of the initial grading of the user, and updates the basic list by combining the initial pushing list and the exceptional page tags to form an updating list and pushes the updating list to the user interface module 1;
the exception record storage module 8 is in data communication with the user interface module 1 and records the grading information of the product page corresponding to the exception page tag which is not directly related and browsed by the user;
the big data analysis module 9 is in data communication with the user management module 2 and the basic analysis module 6, obtains the sum of the number of corresponding product pages in the search record, the browsing record and the consumption record of each user with the same initial grade, and calculates the proportion of the page tags corresponding to the search, browsing and consumption behaviors of each user group with the same initial grade in the total number by combining the sum of the product grades of the browsing record and the consumption record corresponding to the exception page tags in the exception record storage module 8;
and the pushing iteration module 10 is in data communication with the user management module 2, the big data analysis module 9 and the pushing module 5, and calls page tags from the product tag library 3 according to the proportion of the total amount of the page tags corresponding to the searching, browsing and consuming behaviors of each user group with the same initial grade and updates the update list of the corresponding user group in an iteration mode.
In this embodiment, as shown in fig. 6 and 7, the user interface module 1 includes a search unit 11, a push list display unit 12, and a page tag recording unit 13 that records a product tag corresponding to browsing and consumption; the product grading write-in module 4 comprises a grading definition unit 41 for grading products of the travel product service and a label write-in unit 42 for writing the product grading information generated by the definition unit into the product label base module 3;
in this embodiment, as shown in fig. 8, the basic analysis module 6 includes a record reading unit 61 for obtaining data from the tag recording unit 13 of the user interface module 1, a user ranking unit 62 for generating an initial ranking of the user according to the travel product ranking information and the consumption ranking of the tags in the record reading unit 61, and a user ranking writing unit 63 for sending the user ranking unit 62 to the corresponding user management module.
In this embodiment, as shown in fig. 9, the big data analysis module 9 includes a data obtaining unit 91 for retrieving all product tags corresponding to a group of search records, browsing records, and consumption records of users with the same initial rating from all the user management modules 2, a classifying unit 92 for classifying the obtained product tags according to product ratings, a counting unit 93 for counting the total amount of product tag data in each classification, and a proportion calculating unit 94 for calculating the proportion of the counted total amount of data.
In general, the data processing system of the third embodiment executes the data processing methods described in the first and second embodiments on the basis of respective modules and units.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. The method for processing the guest grading data based on the big data is characterized by comprising the following steps:
s1, page marking: generating a product page for browsing and a page label corresponding to each product page corresponding to each travel service product, marking travel product grading and consumption grading for the product page, and combining the travel product grading and the consumption grading into product grading which is used as a product page library of service products which can be provided by the whole;
s2, judging by the user: judging whether the user is a new user or an old user, wherein the new user goes down from the step S3, and the old user goes down from the step S5;
s3, pushing once, randomly calling partial page tags from the product page library, randomly sequencing to form a basic page tag list, and pushing the basic page tag list to a user side;
s4, basic analysis: collecting one or more of search records, product page browsing records and consumption records of a user, determining the grade of the tourism product through the search records and/or the browsing records, determining the consumption grade through the browsing records and/or the consumption records, and combining the grade of the tourism product and the consumption grade as the initial grade of the user;
s5, updating and pushing: calling a corresponding page tag according to the initial classification of a user to generate an initial push list, randomly inserting a group of exception page tags which are not directly related to at least one of the classification of the initially classified tourism products and the classification of consumption of the user, generating a new basic page list by combining the initial push list and the exception page tags, replacing the original basic page list, and pushing the new basic page list to a client;
s6, exception record: recording the grading information of a product page corresponding to the exceptional page tag browsed by the user;
s7, big data analysis: acquiring corresponding product pages in search records and browsing records related to initial classification of each user group with the same initial classification, and product pages of the search records and browsing records corresponding to exceptional page tags to form a plurality of page sets, and then calculating the data proportion of each page set according to the number of pages in each page set;
s8, iterative pushing: and calling page labels from the product page library according to the proportion according to the data proportion of each page set of each user group with the same initial grade to generate an iteration page list, and iteratively updating the basic page list.
2. The big-data based guest ranking data processing method of claim 1, wherein step S1 further includes the steps of:
s11, respectively defining character string identifications for different product types and price intervals according to the product types and price intervals of the travel products corresponding to the product pages;
s12, defining a product grading variable, merging and writing the character string identification corresponding to the product type and the character string identification corresponding to the price interval into the product grading variable to obtain a product grading code of the same product type and the same price interval;
and S13, marking the corresponding product page by using the product grading code.
3. The big-data-based guest ranking data processing method according to claim 2, wherein in step S4, when determining the basic product ranking from the search record, the result list corresponding to the search record is read, the product ranking code read from the tag in the result list is used, and the product ranking code of the majority of results is used as the product ranking code corresponding to the search record.
4. The big data-based guest ranking data processing method of claim 3, wherein the merging of the travel product ranking and the consumption ranking as the initial ranking of the user in step S4 comprises the steps of:
s41, creating an initial grading variable under the account of the user;
s42, merging and writing the character string identifications corresponding to the obtained travel product grades and the consumption grades into initial grading variables, and creating the initial grading codes of the users.
5. The big data-based guest ranking data processing method of claim 4, wherein the step of generating an initial push list according to the initial ranking of the user in step S5 includes the steps of:
s51, according to the initial hierarchical code of the user, searching the same product hierarchical code as the initial hierarchical code in the label library:
s52, reading the product label under the product grading code;
and S53, sorting the read product labels to form an initial push list.
6. The big-data based guest ranking data processing method of claim 5, wherein the supplementary tags in step S5 not directly related to at least one of the user' S initially ranked travel product ranking and consumption ranking include product tags corresponding to product ranking codes different from the product ranking code of the initial ranking code, product tags corresponding to product ranking codes different from the consumption ranking code of the initial ranking code, and product tags corresponding to product ranking codes different from both the travel product ranking and the consumption ranking of the initial ranking code.
7. Big data based guest ranking data processing system, the system comprising:
the user interface module is used for acquiring input information of a user and displaying data to the user;
the user management module is in data communication with the user interface module and stores input information acquired by a user from the user interface module;
the product label library module is used for storing a product page and a page label corresponding to each travel service product;
the product grading writing module is in data communication with the product label base module and is used for defining the product grading of the travel service product and writing the product grading into a corresponding product label in the product label base module;
the pushing module is in data communication with the user interface module and the product label library module, and is used for calling corresponding page labels from the product grading module according to the input information of the user received from the user interface module to form a pushing list and pushing the pushing list to the user interface module;
the basic analysis module is used for reading one or more of search records, browsing records and consumption records in the input information acquired by the user management module, acquiring the grades of the tourist products from the product grading writing module through the search records and/or the browsing records, acquiring the consumption grades from the product grading writing module through the browsing records and/or the consumption records, combining the grades of the tourist products and the consumption grades as the initial grades of the user, and sending the initial grades to the user management module;
the push updating module is in data communication with the user management module, reads the initial grading in the user management module, generates an initial push list according to initial grading information, inserts a group of exception page tags which are not directly related to at least one of the tourism product grading and the consumption grading of the initial grading of the user, and updates the basic list by combining the initial push list and the exception page tags to form an updated list and push the updated list to the user interface module;
the exception record storage module is in data communication with the user interface module and records the grading information of the product page corresponding to the exception page tag which is not directly related and browsed by the user;
the big data analysis module is in data communication with the user management module and the basic analysis module, acquires the sum of the number of corresponding product pages in the search record, the browsing record and the consumption record of each user with the same initial grade and the sum of the number of product grades of the browsing record and the consumption record corresponding to the exceptional page tags, and calculates the proportion of the page tags corresponding to the user group with the same initial grade in the searching, browsing and consumption behaviors in the total amount;
and the pushing iteration module is in data communication with the user management module, the big data analysis module and the pushing module, and calls page tags from the product tag library according to the proportion of the total amount of the page tags corresponding to the searching, browsing and consuming behaviors of each user group with the same initial grade and updates the update list of the corresponding user group in an iteration mode.
8. The big data based guest ranking data processing system of claim 7 wherein the user interface module includes a search unit, a push list display unit, and a page tab recording unit that records browsing and consuming corresponding product tabs; the product grading writing module comprises a grading definition unit for grading products of the travel product service and a label writing unit for writing the product grading information generated by the definition unit into a product label library.
9. The big data based guest ranking data processing system of claim 8 wherein the basic analysis module includes a record reading unit to obtain data from the tag recording unit of the user interface module, a user ranking unit to generate an initial ranking of the user according to the travel product ranking information and the consumption ranking of the tags in the record reading unit, and a user ranking writing unit to transmit the user ranking unit to the corresponding user management module.
10. The big data based guest ranking data processing system of claim 9 wherein the big data analysis module includes a data acquisition unit that retrieves all search records, browsing records and consumption records of a group of users with the same initial ranking from all user management modules corresponding to product tags, a classification unit that classifies the acquired product tags according to product ranking, a statistic unit that counts the total amount of product tag data in each classification, and a proportion calculation unit that calculates the proportion of the counted total amount of data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111323075.XA CN113761384B (en) | 2021-11-10 | 2021-11-10 | Tourist classification data processing method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111323075.XA CN113761384B (en) | 2021-11-10 | 2021-11-10 | Tourist classification data processing method and system based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113761384A true CN113761384A (en) | 2021-12-07 |
| CN113761384B CN113761384B (en) | 2022-02-08 |
Family
ID=78784808
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111323075.XA Active CN113761384B (en) | 2021-11-10 | 2021-11-10 | Tourist classification data processing method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113761384B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116756427A (en) * | 2023-06-27 | 2023-09-15 | 鼎翰文化股份有限公司 | Travel information pushing system based on big data |
| CN116756427B (en) * | 2023-06-27 | 2024-05-14 | 鼎翰文化股份有限公司 | Travel information pushing system based on big data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040019561A1 (en) * | 2002-05-07 | 2004-01-29 | Gabriela Isturiz | Electronic billing system utilizing a universal billing format data transmission |
| US20140180808A1 (en) * | 2012-12-22 | 2014-06-26 | Coupons.Com Incorporated | Generation and management of dynamic electronic offers |
| CN109582876A (en) * | 2018-12-19 | 2019-04-05 | 广州易起行信息技术有限公司 | Tourism industry user portrait building method, device and computer equipment |
-
2021
- 2021-11-10 CN CN202111323075.XA patent/CN113761384B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040019561A1 (en) * | 2002-05-07 | 2004-01-29 | Gabriela Isturiz | Electronic billing system utilizing a universal billing format data transmission |
| US20140180808A1 (en) * | 2012-12-22 | 2014-06-26 | Coupons.Com Incorporated | Generation and management of dynamic electronic offers |
| CN109582876A (en) * | 2018-12-19 | 2019-04-05 | 广州易起行信息技术有限公司 | Tourism industry user portrait building method, device and computer equipment |
Non-Patent Citations (1)
| Title |
|---|
| 田伟业等: "中外葡萄酒产品等级分级评价及启示", 《管理与营销》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116756427A (en) * | 2023-06-27 | 2023-09-15 | 鼎翰文化股份有限公司 | Travel information pushing system based on big data |
| CN116756427B (en) * | 2023-06-27 | 2024-05-14 | 鼎翰文化股份有限公司 | Travel information pushing system based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113761384B (en) | 2022-02-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Önder et al. | Tracing tourists by their digital footprints: The case of Austria | |
| CN102549563B (en) | Semantic trading floor | |
| Alegre et al. | Repeat visitation in mature sun and sand holiday destinations | |
| Comber et al. | What is land cover? | |
| CN110110221A (en) | Government data intelligent recommendation method and system | |
| CN106095738B (en) | Recommending form fragments | |
| CN107944898A (en) | The automatic discovery of advertisement putting building information and sort method | |
| CN111639988B (en) | Broker recommendation method, device, electronic equipment and storage medium | |
| CN103038769A (en) | System and method for directing content to users of a social networking engine | |
| Kim et al. | Assessing and mapping cultural ecosystem services of an urban forest based on narratives from blog posts | |
| US20120143598A1 (en) | Server, dictionary creation method, dictionary creation program, and computer-readable recording medium recording the program | |
| CN113393306A (en) | Product recommendation method and device, electronic equipment and computer readable medium | |
| CN114936301A (en) | Intelligent household building material data management method, device, equipment and storage medium | |
| CN104050243A (en) | Network searching method and system combined with searching and social contact | |
| CN115422438A (en) | Railway material supply resource recommendation method, system and storage medium | |
| CN104615636A (en) | Individual and business resource matching method based on internet | |
| CN113327132A (en) | Multimedia recommendation method, device, equipment and storage medium | |
| CN113761384B (en) | Tourist classification data processing method and system based on big data | |
| Sarkaleh et al. | Designing a tourism recommender system based on location, mobile device and user features in museum | |
| CN117194780A (en) | Travel route customization method, device and equipment for generating artificial intelligence | |
| CN101482881A (en) | Methods and systems for determining a meaning of a document to match the document to content | |
| Andrunyk et al. | Information System of Photostock Web Galleries Based on Machine Learning Technology. | |
| CN115033805A (en) | Preschool children picture book intelligent recommendation method and picture book management system | |
| CN111460300A (en) | Network content pushing method and device and storage medium | |
| JP2022178650A (en) | Information processing device, information processing method, and information processing program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |