CN112507207B - Travel recommendation method and device - Google Patents
Travel recommendation method and device Download PDFInfo
- Publication number
- CN112507207B CN112507207B CN202011182364.8A CN202011182364A CN112507207B CN 112507207 B CN112507207 B CN 112507207B CN 202011182364 A CN202011182364 A CN 202011182364A CN 112507207 B CN112507207 B CN 112507207B
- Authority
- CN
- China
- Prior art keywords
- travel
- target user
- product
- user
- travel product
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000006399 behavior Effects 0.000 claims description 37
- 238000012545 processing Methods 0.000 claims description 30
- 238000004590 computer program Methods 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 description 15
- 238000007405 data analysis Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 238000010200 validation analysis Methods 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000010606 normalization Methods 0.000 description 4
- 230000003542 behavioural effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000010006 flight Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000006386 memory function Effects 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000009182 swimming Effects 0.000 description 1
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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/02—Reservations, e.g. for tickets, services or events
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the technical field of Internet, and discloses a travel recommendation method and device, aiming at improving recommendation reliability by determining a travel strategy of a user by combining behavior preference of the user on travel products and a record of browsing the travel products. The method comprises the following steps: acquiring portrait labels of target users, wherein the portrait labels are used for indicating behavior preferences of the users for travel products; acquiring record information generated by browsing at least one travel product by a target user, wherein the record information comprises product information of the at least one travel product; and determining the trip strategy of the target user according to the portrait tag and the product information of at least one trip product.
Description
Technical Field
The embodiment of the application relates to the technical field of Internet, in particular to a travel recommendation method and device.
Background
With the development of internet technology, people are gradually used to booking product services related to travel such as air tickets, hotels and the like on a network platform. The prices of the products such as airplane tickets, hotels and the like reserved at different moments are different, and when the products are more preferential, the price is a concern of people.
In the prior art, the preferred reservation time of the relevant airlines or the preferred reservation time of the relevant hotels is usually determined by means of the average reservation price per day in different reservation dates. For example, for a route of Beijing flying to Shanghai in month 21, the average reservation price of the air ticket in month 20 is 700, and the average reservation price of the air ticket in month 18 is 650, it is determined that the route of Beijing flying to Shanghai should be reserved two days in advance. Such a way is considered to be more single and less reliable.
Disclosure of Invention
The embodiment of the application provides a travel recommendation method and device, aiming at improving recommendation credibility by determining travel strategies of users by combining the behavior preference of the users on travel products and the browsing records of the travel products.
In a first aspect, an embodiment of the present application provides a travel recommendation method, including: acquiring portrait tags of target users, wherein the portrait tags are used for indicating behavior preferences of the users for travel products; acquiring record information generated by browsing at least one travel product by the target user, wherein the record information comprises product information of the at least one travel product; and determining the trip strategy of the target user according to the portrait tag and the product information of the at least one trip product.
According to the embodiment of the application, the travel strategy is recommended to the user by analyzing the behavior preference of the user on the travel products and the browsing records of the travel products and considering the time change, the user preference and other factors, so that the recommendation reliability can be improved, and the actual demands of the user can be met.
In an alternative implementation, the effective dates of the at least one travel product are the same and/or the corresponding places of the at least one travel product are the same.
In an optional implementation manner, the obtaining the record information generated by the target user browsing at least one travel product includes: if the fact that the target user does not have a historical trip order is determined, recording information generated by browsing at least one trip product by the target user before the current moment is obtained; or determining that the target user has subscribed a first travel product, and acquiring record information generated by browsing at least one travel product by the target user before a first moment; the first moment is the moment when the target user subscribes to the first travel product; the first travel product is any one of at least one travel product.
In an optional implementation manner, if it is determined that the target user does not have a historical trip order, determining a trip policy of the target user according to the portrait tag and product information of the at least one trip product includes: determining a target travel product matched with the portrait tag of the target user in the at least one travel product; and determining a travel strategy of the target user, wherein the travel strategy is used for indicating the user to subscribe the target travel product.
In an optional implementation manner, if it is determined that the target user has subscribed to the first travel product, determining a travel policy of the target user according to the portrait tag and product information of the at least one travel product includes: determining a target travel product matched with the portrait tag of the target user in the at least one travel product; determining a travel strategy of the target user based on the moment when the target user browses the target travel product and the first moment, wherein the travel strategy is used for indicating the advance time amount of the user booking a second travel product; the location corresponding to the second travel product is the same as the location corresponding to the first travel product.
In an optional implementation manner, the type of the at least one travel product is an air ticket, and the routes corresponding to the at least one travel product are the same; or the type of the at least one travel product is a hotel product, and the hotel places corresponding to the at least one travel product are the same.
In an alternative implementation, obtaining the portrait tag of the target user includes: determining that the target user has a historical travel order, and determining an portrait tag of the target user according to product information of travel products contained in the historical travel order; or determining that the target user does not have a historical trip order, and determining the portrait tag of the target user group as the portrait tag of the target user; the target user group comprises the target users, and the portrait tag of the target user group is determined according to the portrait tag of at least one user with a historical trip order in the target user group.
In an alternative implementation, the method further includes: grouping a plurality of users according to their demographics, determining at least one user group including the target user group; wherein the plurality of users includes the target user and the demographic includes age and/or gender.
In a second aspect, an embodiment of the present application provides a travel recommendation device, including: the processing module is used for acquiring portrait labels of target users, and the portrait labels are used for indicating the behavior preference of the users on travel products; the acquisition module is used for acquiring record information generated by browsing at least one travel product by the target user, wherein the record information comprises product information of the at least one travel product; and the processing module is also used for determining the trip strategy of the target user according to the portrait tag and the product information of the at least one trip product.
According to the embodiment of the application, the travel strategy is recommended to the user by analyzing the behavior preference of the user on the travel products and the browsing records of the travel products and considering the time change, the user preference and other factors, so that the recommendation reliability can be improved, and the actual demands of the user can be met.
In an alternative implementation, the effective dates of the at least one travel product are the same and/or the corresponding places of the at least one travel product are the same.
In an alternative implementation, the processing module is further configured to determine whether the target user has a historical travel order; the acquisition module is used for acquiring record information generated by browsing at least one travel product by the target user before the current moment when the processing module determines that the target user does not have a historical travel order; or the acquisition module is used for acquiring record information generated by browsing at least one travel product by the target user before the first moment when the processing module determines that the target user has subscribed the first travel product; the first moment is the moment when the target user subscribes to the first travel product; the first travel product is any one of at least one travel product.
In an alternative implementation, the processing module, when determining that the target user has no historical travel order, is further configured to: determining a target travel product matched with the portrait tag of the target user in the at least one travel product; and determining a travel strategy of the target user, wherein the travel strategy is used for indicating the user to subscribe the target travel product.
In an alternative implementation, the processing module, when determining that the target user has subscribed to the first travel product, is further configured to: determining a target travel product matched with the portrait tag of the target user in the at least one travel product; determining a travel strategy of the target user based on the moment when the target user browses the target travel product and the first moment, wherein the travel strategy is used for indicating the advance time amount of the user booking a second travel product; the location corresponding to the second travel product is the same as the location corresponding to the first travel product.
In an optional implementation manner, the type of the at least one travel product is an air ticket, and the routes corresponding to the at least one travel product are the same; or the type of the at least one travel product is a hotel product, and the hotel places corresponding to the at least one travel product are the same.
In an alternative implementation, the processing module is further configured to: determining that the target user has a historical travel order, and determining an portrait tag of the target user according to product information of travel products contained in the historical travel order; or determining that the target user does not have a historical trip order, and determining the portrait tag of the target user group as the portrait tag of the target user; the target user group comprises the target users, and the portrait tag of the target user group is determined according to the portrait tag of at least one user with a historical trip order in the target user group.
In an alternative implementation, the processing module is further configured to: grouping a plurality of users according to their demographics, determining at least one user group including the target user group; wherein the plurality of users includes the target user and the demographic includes age and/or gender.
In a third aspect, an embodiment of the present application provides an electronic device, including: a processor and a memory;
The memory is used for storing a computer program;
The processor is configured to execute the computer program stored in the memory, so that the electronic device performs the method in any possible implementation manner of the first aspect.
In a fourth aspect, an embodiment of the present application provides an electronic device, including: a processor and interface circuit;
the interface circuit is used for receiving code instructions and transmitting the code instructions to the processor;
the processor is configured to execute the code instructions to perform the method of any of the possible implementations of the first aspect.
In a fifth aspect, embodiments of the present application provide a computer readable storage medium storing instructions that, when executed, cause a method in any one of the possible implementations of the first aspect to be implemented.
Drawings
FIG. 1 is a schematic diagram of a data analysis system according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a travel recommendation method according to an embodiment of the present application;
FIG. 3 is a schematic flow chart of a data analysis method according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a travel recommendation device according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
Fig. 6 is a second schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail below with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The term "plurality" as used herein means two or more. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. In addition, it should be understood that although the terms first, second, etc. may be used in describing various data in embodiments of the present invention, these data should not be limited to these terms. These terms are only used to distinguish one data element from another.
Currently, the way to recommend the reservation time of the preferred air ticket and hotel for the user mainly depends on the comparison of the average reservation price per day in different reservation dates. The differences of the preferences of different users are not considered, and the differences of the products inquired at different time points are not considered, so that the obtained conclusions are compared on one side. The following examples are:
TABLE 1
As shown in table 1 above, the user U01 subscribes to the air ticket 1800 for the route of the current day, shenzhen, to beijing and the hotel 600 for the current day to check in to beijing on day 6 months and 10 days. The users subscribed 1 day in advance have U02, U03 and U04, and the average ticket price of the air ticket is 1000 yuan { = (1000+1200+800)/3) }, and the average hotel is rent yuan { = (550+500+570)/3) }; the users subscribed 2 days in advance have U05, U06, U07, the average fare of the air ticket is 640 { = (540+700+680)/3 }, the average fare of the hotel rent { = (550+510+500)/3) }. Concluding that: reservation is carried out 1 day in advance, the air ticket is saved by 800 yuan, and the hotel is saved by 60 yuan/night; reservation 2 days in advance, air ticket saving 1160 yuan, hotel saving 80 yuan/night. Such an approach does not take into account the variability of the product and the user's own preferences. Such as different take-off times, airlines, billboards and the like of the air ticket products, different star grades, brands, facilities, geographic positions and the like of the hotel products; some users prefer a large voyage with 10:00-12:00 take-off, and some users prefer a 4-5 star hotel with swimming pools in urban areas. It is obvious that the conclusions are not persuasive and the reliability is poor.
Based on the above, the embodiment of the application provides a travel strategy recommendation method and device, which can be applied to some business systems for providing product booking services such as air ticket booking, hotel booking and the like. And recommending the travel strategy to the user by combining the behavior preference of the user on the travel products and the browsing record of the travel products so as to improve the recommendation credibility. The method and the device are based on the same inventive concept, and because the principles of solving the problems of the method and the device are similar, the implementation of the method and the device can be mutually referred to, and the repetition is not repeated.
An embodiment of determining a user's behavioral preferences for travel products is described in detail below.
Referring to fig. 1, an embodiment of the present application provides a schematic structure of a data analysis system 100. The data analysis system can acquire information such as historical travel orders of the user and records of browsing travel products of the user from the service systems for providing travel product reservation services such as air ticket reservation, hotel reservation and the like. Optionally, the data analysis system may be used as a background of the service system and deployed in the same server as the service system; the data analysis may be a stand-alone system that interacts with the business system through a corresponding interface. The embodiments of the present application are not limited in this regard.
As shown in FIG. 1, the data analysis system 100 includes a plurality of subsystems, such as a distributed publish-subscribe messaging system (kaflka), a distributed file system (Hadoop distributed FILE SYSTEM, HDFS), a data warehouse (Hive), and an analysis modeling system (OneAI).
The distributed publish-subscribe message system is configured to receive data reported by the service system, for example, record information of browsing at least one travel product by a user, and in fig. 1, the record information is simply referred to as query data. Also, for example, order information of a user's historical travel order, which is simply referred to as reservation data in fig. 1. Optionally, the service system may carry the user identifier (memberid) in the reported query data/predetermined data, so as to facilitate a subsequent personalized accurate analysis for the behavior preference of the individual user.
The service system may respond to the travel information, the flight information and the query conditions of a user on which to query the air ticket, and return the query result to the user through a preset user interface, and record the query result as query data of the user on the air ticket and report the query result to the distributed publish-subscribe message system. The service system can also record the order information of the user on the air ticket and report the order information as the reservation data of the user on the air ticket to the distributed publishing and subscribing message system.
The service system can respond to the house type information, the name information and the query conditions of a user for querying the hotel, returns the query result to the user through a preset user interface, records the query result as query data of the user for hotel products and reports the query result to the distributed publishing and subscribing message system. The business system can also record the order information of the user on the hotel products and report the order information to the distributed publishing and subscribing message system as the booking data of the user on the hotel.
The distributed file system is used to read data from Kafka at regular time by a collection tool (jump) and store directory files. Such as producing a daily log list: YYYYMMDD, the YYYYMMDD may use the current time of the system processing the read data to store txt files such as: t_air_querydata. Txt, t_hot_list_querydata. Txt, t_hot_detail_querydata. Txt.
The data warehouse is used for reading the analysis file from the distributed file system through the timing task, and expanding text information in the file into a certain data structure (such as ORC format) and storing the text information in Hive. Such as: based on directories in a distributed file system. Automatically processing files in the directory created the day before. And establishing a data model, designing a database table structure, field parameter names and the like. And writing the information development horizontal structure in the file into a corresponding table. For example, the query data of the air ticket may be unwrapped and written: ods_t_air_ querydata _ YYYYMMDD; expanding and writing hotel list data: ods_t_hotel_list_ querydata _ YYYYMMDD.
The analysis model building system is used for building an analysis model by utilizing data in Hive, and obtaining a corresponding analysis conclusion according to the analysis model. In embodiments of the present application, the analytical model building system may build user features from demographic and historical order information dimensions, respectively. Specifically, the analysis model building system can divide the user groups according to the demographic characteristics of different users; the analysis model building system can determine the behavior preference of the users on the travel products based on the data corresponding to the subscription data of some users reported by the business system in Hive. For users without historical travel orders, the analysis model building system can also determine the behavior preference of the users according to the behavior preference of the user group to the travel products.
An embodiment of grouping is described in detail below. First, discretizing is performed on demographic characteristics including, but not limited to, gender, age, job position, level, etc. For example, for the span age, the span age can be discretized into [0,2], (2, 5], (5, 10), 10+four feature classes, if the user belongs to a certain feature class, the user is marked with 1 in the class value, otherwise marked with 0, for example, if the span age of the user is 3, the discretization feature class can be marked with 0100, for the gender, the gender discretization process can be marked with 1 for the male, the female is marked with 0, if the user is the male, the discretization feature class can be marked with 1 for the female, otherwise, if the male is marked with 0, the female is marked with 1 for the female, the discretization feature class can be marked with 0 for the user, for the age, normalization process can be adopted, for example, the min-max normalization process can be adopted, the actual age (x× * =x-min/max-min) of the user after the normalization process is converted, wherein min represents the minimum age of the user without history order, the max represents the maximum age of the user without history order, the user is marked with the discretization feature class, the male is marked with 1 for the male, the female is marked with the high grade, the high grade of the span age is marked with the high grade, and the span age is classified into the high grade of the group is the high grade, for the span age is marked with 0, for the high grade is marked with the high grade, for the span age is classified into the high grade, for the user class is marked with the high grade, for the user class is classified into the user class is the high grade.
Alternatively, a clustering algorithm may be further adopted, and based on the demographic characteristics after pretreatment such as discretization or normalization, a plurality of users are classified into different clusters, each cluster represents a user group, and the users belonging to the same cluster have the same user characteristics. Specifically, K user preprocessed demographic characteristics may be selected randomly as initialized cluster centers, and then, for any one of the other users, the distance between the user preprocessed demographic characteristics and each initialized cluster center is calculated, and the initial cluster center closest to the user is selected as its category. Then calculate the central point of these K categories again, repeat the above-mentioned process until the central point is unchanged. The embodiment of the application also provides a mode for determining the optimal K, which is described below.
And determining the optimal K by adopting a contour coefficient method. The contour coefficient S of a certain sample point X (i) is defined as:
Where a is the average distance of X (i) from other samples in the same cluster, called the degree of aggregation; b is the average distance of X (i) from all samples in the nearest cluster class, called the degree of separation. The definition of the nearest cluster is:
where p is a sample in a certain cluster C (k). The average distance of all samples from X (i) to a certain cluster is taken as the distance from the point to the certain cluster, and then one cluster nearest to X (i) is selected as the nearest cluster.
The average profile factor is obtained based on the average of the profile factors of all the samples. The value range of the average contour coefficient is [ -1,1], and the closer the sample distance in the cluster is, the farther the sample distance between clusters is, the larger the average contour coefficient is, and the better the clustering effect is. Therefore, K having the largest average profile coefficient is determined as the optimal cluster number, i.e., the aforementioned optimal K.
An embodiment of determining a user's behavioral preference for a travel product is described in detail below for a user with a historical travel order, including the following flows A1-A2.
A1, extracting order features based on reservation data.
Specifically, different order features can be respectively extracted according to different travel product types aiming at the reservation data of the user. The order features include product information for products ordered for travel, such as air ticket type order features including, but not limited to, number of turns, transit stay, price, voyage, departure time, arrival time, bunk, etc. Hotel class order features include, but are not limited to, hotel brands, hotel stars, hotel locations, hotel rooms, hotel prices, and the like.
A2, calculating preference coefficients of the order features extracted in the A1, and determining the behavior preference of the user on the travel products according to the preference coefficients of the order features.
Alternatively, a model may be constructed that calculates the preference coefficients, with the order features such as those listed in S1 as input parameters of the foregoing model, and the preference coefficients for the respective order features are output through model calculation.
The specific calculation mode is as follows: and performing frequency calculation on the order features with fixed variable value, and determining the preference coefficients of the order features according to the calculation result. For example, for a bunk, the number of times a user takes an economy, a business, a first class, etc., can be obtained based on a historical order, and the user's preference factor for a bunk of a certain class is equal to the bunk number/number of air ticket orders. For example, if a user has 10 ticket orders in history, wherein 8 economic cabins, 1 public service cabin and 1 first cabin are adopted, the economic cabin preference coefficient of the user is 0.8, the public service cabin and first cabin preference coefficients are all 0.1, the user is preferentially considered to subscribe to the economic cabin, and the behavior preference of the user to the cabin of the ticket is determined to be the economic cabin.
For the order feature with variable value not fixed, especially for continuous variable (or random variable) like air ticket price, each quantile of the variable in the model sample (namely the extracted order feature) can be firstly taken, and then converted into a plurality of intervals, and then statistical frequency is carried out, so as to calculate the price preference coefficient of each interval, and further determine the behavior preference of the user on the price of the travel product. For example, for the price, a searched flight price list is extracted, a feature minimum price, a 10% quantile price, a 25% quantile price, a 50% quantile price, a 75% quantile price, a 90% quantile price and a highest price are created, the number of times the price appears in the section class is used as the value of the corresponding feature according to the historical order, and the price preference coefficient of the user is equal to the number of times of the price in each section/the number of air ticket orders. For users who have had hotel orders, the user's past N years of hotel order data is aggregated to obtain the preferences of the user's order features. For another example, for hotel brand preference, the number of times that the user selects the high-end, medium-end and low-end brands can be obtained according to the historical orders, and the brand preference coefficient of the user is equal to the number of times of each brand/the number of hotel orders.
Optionally, portrait tags can be added to the user according to the determined behavior preference of the user on the travel products.
An embodiment of determining a user's behavioral preference for a travel product is described in detail below for a user without a historical travel order, including the following flows B1-B3.
B1, determining a user group to which the user belongs according to the demographic characteristics of the user without the historical travel order.
Optionally, the demographic characteristics of the user may be pre-processed, such as discretized, normalized, etc., in accordance with the previous embodiments. And matching the preprocessed demographic characteristics with the user characteristics of the user group to determine the user group to which the user belongs.
And B2, determining the behavior preference of the user group on the travel products.
Optionally, order data of users having historical travel orders in the user group may be integrated, and each order feature may be extracted from the integrated order data. And determining preference coefficients of the order features, and determining the behavior preference of the user group on the travel products according to the preference coefficients of the order features.
Alternatively, a minority-compliance majority mechanism may be employed to determine the behavior preferences for the travel product for a majority of users within the user group having the same order characteristics as the corresponding behavior preferences for the user group.
And B3, for the users without historical travel orders, determining the behavior preference of the user group to which the users belong for travel products as the behavior preference of the users.
Optionally, for a user without a historical trip order, a portrait tag can be added to the user according to the behavior preference of the user group to the trip product.
Further, the analysis model building system can also determine the travel strategy of the user based on the behavior preference of the user on the travel products and the related query data.
As shown in fig. 2, an embodiment of the present application provides a travel recommendation method, which includes the following steps.
S201, obtaining portrait labels of target users, wherein the portrait labels are used for indicating behavior preferences of the users on travel products. It should be noted that "travel product" is a general concept, and does not specifically mean a certain travel product. Optionally, the travel products include products with large price real-time variation fluctuation, such as air tickets, hotel products and the like.
Optionally, the portrait tag of the target user is determined according to two conditions based on whether the target user has a history travel order:
Case one: and determining that the target user has a historical travel order, and determining the portrait tag of the target user according to the product information of the travel product contained in the historical travel order. Specifically, the method can be implemented with reference to the above-mentioned processes A1 to A2, and the embodiments of the present application will not be described in detail.
And a second case: determining that the target user has no historical trip order, and determining the portrait tag of the target user group as the portrait tag of the target user; the target user group comprises the target users, and the portrait tag of the target user group is determined according to the portrait tag of at least one user with a historical trip order in the target user group. Specifically, the implementation can be performed with reference to the above-mentioned processes B1 to B3, and the embodiments of the present application will not be repeated.
S202, acquiring record information generated by browsing at least one travel product by the target user, wherein the record information comprises product information of the at least one travel product.
Alternatively, at least one travel product may be defined to have the same date of effectiveness and/or the same location corresponding to the at least one travel product. The analysis of the specific journey individualization for the target user is realized.
Optionally, based on whether the target user has a history trip order, the record information corresponding to the browsing of the target user can be determined and acquired in two cases.
Case one: and if the target user does not have the historical travel order, acquiring record information generated by browsing at least one travel product by the target user before the current moment.
The record information comprises product information of at least one travel product browsed, such as information of airlines, flights, billboards, ticket prices and the like of the air ticket; and information such as hotel location, house type, service facilities, etc.
And a second case: and if the target user is determined to have subscribed to the first travel product, acquiring record information generated by browsing at least one travel product by the target user before the first moment.
The first moment is the moment when the target user subscribes to the first travel product; the first travel product is any one of at least one travel product. The recorded information comprises product information of at least one travel product browsed, such as information of airlines, flights, billboards, ticket prices and the like of the air ticket; and information such as hotel location, house type, service facilities, etc.
Optionally, the method specifically may include acquiring the corresponding record information browsed by the target user at a different time before the first time. And consideration of the change of dynamic time factors is introduced, so that the follow-up determination of the user trip strategy is more reasonable.
S203, determining the trip strategy of the target user according to the portrait tag and the product information of the at least one trip product.
Optionally, a travel policy browsed by the target user can be determined in two cases based on whether the target user has a history travel order.
Case one: for the case where it is determined that the target user does not have a history of travel orders, it may be implemented with reference to the following steps S231a to S232 a.
S231a, determining a target travel product matched with the portrait tag of the target user in the at least one travel product.
Specifically, the product information of each travel product in at least one travel product can be converted into a dummy variable characteristic according to the portrait tag of the target user, and the product information is endowed with a preference value. For example, the target user has a economy class for the ticket, i.e. the portrait tag of the target user includes the economy class, the economy class in the ticket class may be set to have a preference value of 1, the public service class has a preference value of 0, and the first class has a preference value of 0.
And then obtaining preference coefficients of product information related to the historical travel orders of the target users. For example, the embodiment in the foregoing step A2: assuming that the target user has 10 ticket orders in history, wherein 8 economic cabins, 1 public service cabin and 1 first cabin are adopted, the economic cabin preference coefficient of the target user is 0.8, and the public service cabin preference coefficient and the first cabin preference coefficient are all 0.1.
And further, calculating the matching degree of each travel product and the portrait tag of the target user based on the preference coefficient and the preference value of different product information. Specifically, the matching degree M corresponding to any travel product is calculated through the following formula:
Wherein a ij represents a preference coefficient of a j-th attribute type in the i-th product information, for example, a travel product such as an air ticket, the included i-th product information is a cabin, and the cabin has 3 attribute types which are economy cabin, public service cabin, first class cabin and the like. Then j takes a natural number from 1 to S, S being 3. When j is taken to be 1, a i1 represents the preference coefficient of the economy class.
X ij represents the preference value of the jth attribute type in the ith product information, for example, the travel product of the air ticket, wherein the ith product information is a cabin, and the total 3 attribute types of the cabin are economy cabin, public service cabin, first class cabin and the like. Then j takes a natural number from 1 to S, S being 3. When j is 1, a i1 represents the preference value of the economy class.
N is the item number of the product information included in any travel product, and i is a natural number from 1 to N.
Finally, sorting the matching degree of at least one travel product, and determining the travel product with the matching degree value larger than a preset threshold value as a target travel product; or determining the travel product with the largest matching degree value as the target travel product.
S232a, determining a travel strategy of the target user, wherein the travel strategy is used for indicating the user to subscribe the target travel product.
And a second case: for the case that it is determined that the target user has a historical travel order, for example, the target user subscribes to a certain travel product browsed by the target user at the first moment, the following steps S231 b-S232 b may be referred to.
And S231b, determining a target travel product matched with the portrait tag of the target user from the at least one travel product.
Specific reference may be made to S231a, and this will not be described in detail in the embodiments of the present application.
S232b, determining a travel strategy of the target user based on the moment when the target user browses the target travel product and the first moment, wherein the travel strategy is used for indicating the advance time amount of the user booking a second travel product; the location corresponding to the second travel product is the same as the location corresponding to the first travel product.
Specifically, the matching degree of the target travel product and the target user portrait tag can be quantified, and the matching degree of the travel product reserved by the target user at the first moment and the target user portrait tag can be calculated. And comparing the matching degree corresponding to the target travel product with the matching degree corresponding to the travel product reserved by the target user, and determining the party with larger matching degree, namely the party closer to the portrait label of the user.
Further, the preferred advance amount of time for the subsequent reservation is determined based on the time (browsing time or reservation time) corresponding to the party having the higher degree of matching. For example, if it is determined that the matching degree corresponding to the target travel product is larger, and the first time falls on the effective date of the travel product reserved by the target user, it may be determined that the amount of time in advance for the user to reserve the second travel product is the difference between the time when the target user browses the target travel product and the first time, where the difference may be counted in units of days, hours, minutes, and the embodiment of the present application does not limit this.
According to the embodiment of the application, the travel strategy is recommended to the user by analyzing the behavior preference of the user on the travel products and the browsing records of the travel products and considering the time change, the user preference and other factors, so that the recommendation reliability can be improved, and the actual demands of the user can be met.
Based on the above embodiment, as shown in fig. 3, the present application further provides a data analysis method, which can be applied to the analysis model building system, and determines the difference of different time reservations by analyzing the reservation data, the query data, etc. of the travel products by the user. The analysis model creation system may suggest an optimal subscription time to the user based on which to draw conclusions, which may assist the enterprise in formulating travel policies, reducing travel costs. Specifically, the data analysis method comprises the following procedures.
S301, data preparation: the actual subscription data of the user is obtained, order features of the user are extracted from the actual subscription data, and demographic features of the user are obtained.
S302: preference acquisition: a user preference model is built based on the order features/demographics of the user. Wherein, the behavior preference of the user on the travel product can be determined through the user preference model.
S303: query data at different times, such as, for example, multiple query data in the time range of T1 to Tn as illustrated in FIG. 3, including product information of travel products, are obtained.
S304: and respectively calculating the quasi-booking data corresponding to the different time inquiry data, wherein the quasi-booking data refers to the actual booking data of the user, which is not the actual booking data of the user, on the assumption that the user bookes the travel product when inquiring the travel product, and the quasi-booking data comprises the product information of the hypothetical booking travel product.
Optionally, each piece of quasi-booking data in the time range from T1 to Tn is compared with the behavior preference of the user for the travel product, and quasi-booking data matched with the behavior preference of the user for the travel product is screened out from each piece of quasi-booking data in the time range from T1 to Tn, as shown in fig. 3, the quasi-booking data matched with the behavior preference of the user for the travel product is screened out to include the quasi-booking data of T1 and T2, and the quasi-booking data of T1 and T2 can be recommended to the user.
S305: determining analysis conclusion: comparing the actual booking data of the user with the calculated quasi booking data to obtain a conclusion of whether the actual booking of the user is saving or loss; the optimal point in time or range of purchase is determined based on the conclusion.
Optionally, the actual subscription data of the user is compared with the quasi-subscription data matched with the user behavior preference, so that the optimal purchase time point or time range is determined by combining the user preference, the actual requirement of the user can be met, and the user experience is improved.
The data analysis method provided by the embodiment of the present application is illustrated in the following in conjunction with the first example and the second example.
Example one
Assuming that user ID01 exists, the historical air ticket order for user ID02 is shown in Table 2 below. The user ID01 also browses the tickets for the same airline and validation time at a different time prior to booking the tickets in table 2, as shown in table 3 below.
TABLE 2
TABLE 3 Table 3
The reservation times of Table 2 and the inquiry times of Table 3 above are combined to see: user ID01 was 10:17 on day 29 of 5 months, and wanted to reserve flights from the sea opening to Beijing on day 29 of 5 months. Near take-off booking, the user can only see two flight slots with inquiry ID of C03 when inquiring at the time, and the user ID01 finally bookes the Y slot of the flight HU7281, and the ticket price is 2000 yuan.
For the case of date of validation of 5 months 29 days, route of sea to Beijing, if the user subscribes 1 day ahead (e.g., 5 months 28 days 9:00), four flight slots with query ID C02 can be seen. Assuming that the portrait tag of the user obtained by determining the behavior preference of the user according to the foregoing embodiment is "departure time 12:00-18:00, low price priority", using the recommendation algorithm, the X cabin of the flight HU7281 is most likely to be selected by the user ID01, and the fare is 1000 yuan.
For the case of an effective date of 5 months 29 days, a route from sea to Beijing, if the user subscribes 2 days in advance (e.g., 5 months 27 days 9:00), six flight slots with a query ID of C01 can be seen. Assuming that the portrait tag of the user obtained by determining the behavior preference of the user according to the foregoing embodiment is "departure time 12:00-18:00, low-priced priority", a recommendation algorithm is used to obtain a P cabin in which the user ID01 is most likely to select the flight CA1370, and the fare is 750 yuan.
From this, it can be concluded that: a 1000-ary (=2000-1000) can be saved if the user ID01 subscribes to the air ticket 1 day ahead of the user ID01 actual on-day subscription, and a 1250-ary (=2000-750) can be saved if the user ID01 subscribes to the air ticket 2 days ahead of the user ID01 actual on-day subscription. Therefore, the user ID01 can be determined, and the travel policy for the route from the sea opening to the Beijing is: the airline ticket was reserved two days earlier than the validation date.
Similarly, assume that there is no case of Table 2, i.e., user ID01 has no historical airline orders. The closest or matching ticket may be determined from among the tickets viewed (or queried) at different times for user ID01 as shown in Table 3 based on the portrait notes for user ID 01. And then determining the trip strategy of the user ID01 according to the best matched air ticket. As in the example above, if user ID01 subscribes to the ticket 1 day ahead of the day of travel (i.e., ticket validation date), user ID01 is most likely to select the X bay of flight HU7281 with a ticket face price of 1000 yuan; if user ID01 subscribes to the airline ticket 2 days ahead of the current day of travel, user ID01 is most likely to select the P-bay of flight CA1370 with a fare of 750 yuan. Referring to the portrait tag of user ID01 as "departure time 12:00-18:00, low price priority", based on the ticket price (1000) advanced by 1 day and the ticket price (750) advanced by 2 days, user ID01 can be determined as follows for the travel policy of the route from sea to Beijing: the airline ticket was reserved two days earlier than the validation date.
Example two
Suppose there is a historical hotel order for user ID03 as shown in Table 4 below. User ID03 also browses hotels in the same area and for the time of validation at different times prior to booking the hotels in table 4, as shown in table 5 below.
TABLE 4 Table 4
TABLE 5
The reservation times of Table 4 and the inquiry times of Table 5 above are combined to see: user ID03 was 10:00 on 29 th 5 months and wanted to book a hotel in Beijing on 1 th 6 months. As shown in table 5, the user can only see two hotel room types with a query ID of C03 when querying at the time. Finally, a business large bed room of the holiday hotel in the Beijing Cheng Tiantan is reserved, and the average is rent yuan, and the business large bed room stays for 2 nights.
The date of validation is: in the case of Beijing at 1 day 6, if the user subscribes 1 day earlier than the actual subscription (e.g., 9:00 on 28 days 5 months), four hotel rooms with a query ID of C002 can be seen. Assume that the portrait tag of the user ID03 obtained by determining the behavior preference of the user according to the foregoing embodiment is "traffic convenience, preference 4-5 star, travel standard 500 yuan". Using the recommendation algorithm, it can be derived that user ID03 is most likely to select the administrative large bedroom of the Hotel, on average rent yuan.
The date of validation is: in the case of Beijing at 1 day 6, if the user subscribes 2 days earlier than the actual subscription (e.g., 9:00 on 27 days 5 months), six hotel rooms with query ID C001 can be seen. Assume that the portrait tag of the user ID03 obtained by determining the behavior preference of the user according to the foregoing embodiment is "traffic convenience, preference 4-5 star, travel standard 500 yuan". Using the recommendation algorithm, we get the administrative big-bed room where user ID03 is most likely to select the celebrity, average rent yuan.
In summary, it is concluded that: the user ID01 can save 100 yuan (=500×2-450×2) when booking a hotel 1 day in advance, and save 100 yuan (=500×2-450×2) when booking a hotel 2 days in advance. So the user ID03 can be determined, and the trip policy for the hotel subscribed to beijing is: hotel is booked 3-4 days earlier than the effective date.
Based on the same concept, referring to fig. 4, an embodiment of the present application provides a travel recommendation device 400, which includes a processing module 401 and an obtaining module 402.
The processing module 401 is configured to obtain a portrait tag of a target user, where the portrait tag is used to indicate a behavior preference of the user for a travel product.
The obtaining module 402 is configured to obtain record information generated by browsing at least one travel product by the target user, where the record information includes product information of the at least one travel product.
The processing module 401 is further configured to determine a trip policy of the target user according to the portrait tag and product information of the at least one trip product.
According to the embodiment of the application, the travel strategy is recommended to the user by analyzing the behavior preference of the user on the travel products and the browsing records of the travel products and considering the time change, the user preference and other factors, so that the recommendation reliability can be improved, and the actual demands of the user can be met.
In an alternative embodiment, the at least one travel product has the same date of effectiveness and/or the at least one travel product corresponds to the same location.
In an alternative embodiment, the processing module 401 is further configured to determine whether the target user has a historical trip order; the obtaining module 402 is configured to obtain record information generated by browsing at least one travel product by the target user before the current moment when the processing module 401 determines that the target user does not have a historical travel order; or the obtaining module 402 is configured to obtain record information generated by browsing at least one travel product by the target user before the first moment when the processing module 401 determines that the target user has subscribed to the first travel product; the first moment is the moment when the target user subscribes to the first travel product; the first travel product is any one of at least one travel product.
In an alternative embodiment, the processing module 401, when determining that the target user has no historical travel order, is further configured to: determining a target travel product matched with the portrait tag of the target user in the at least one travel product; and determining a travel strategy of the target user, wherein the travel strategy is used for indicating the user to subscribe the target travel product.
In an alternative embodiment, the processing module 401, when determining that the target user has subscribed to the first travel product, is further configured to: determining a target travel product matched with the portrait tag of the target user in the at least one travel product; determining a travel strategy of the target user based on the moment when the target user browses the target travel product and the first moment, wherein the travel strategy is used for indicating the advance time amount of the user booking a second travel product; the location corresponding to the second travel product is the same as the location corresponding to the first travel product.
In an optional implementation manner, the type of the at least one travel product is an air ticket, and the corresponding airlines of the at least one travel product are the same; or the type of the at least one travel product is a hotel product, and the hotel places corresponding to the at least one travel product are the same.
In an alternative embodiment, the processing module 401 is further configured to: determining that the target user has a historical travel order, and determining an portrait tag of the target user according to product information of travel products contained in the historical travel order; or determining that the target user does not have a historical trip order, and determining the portrait tag of the target user group as the portrait tag of the target user; the target user group comprises the target users, and the portrait tag of the target user group is determined according to the portrait tag of at least one user with a historical trip order in the target user group.
In an alternative embodiment, the processing module 401 is further configured to: grouping a plurality of users according to their demographics, determining at least one user group including the target user group; wherein the plurality of users includes the target user and the demographic includes age and/or gender.
Further, as shown in fig. 5, an electronic device 500 is provided in the present application. The electronic device 500 may be applied to a travel recommendation apparatus. When the electronic device 500 is applied to the travel recommendation device, the electronic device 500 may be specifically the travel recommendation device, or may be another device capable of supporting implementation of the travel recommendation method in any of the foregoing embodiments. The memory 520 holds the necessary computer programs, program instructions and/or data to implement the trip recommendation methods in any of the embodiments described above. The processor 510 may execute the computer program stored in the memory 520 to implement the trip recommendation method in any of the above embodiments. The electronic device 500 may be a chip or a system-on-chip, for example. Alternatively, the chip system in the embodiment of the present application may be formed by a chip, and may also include a chip and other discrete devices.
The electronic device 500 may include at least one processor 510 and the electronic device 500 may also include at least one memory 520 for storing computer programs, program instructions, and/or data. Memory 520 is coupled to processor 510. The coupling in the embodiments of the present application is an indirect coupling or communication connection between devices, units, or modules, which may be in electrical, mechanical, or other forms for information interaction between the devices, units, or modules. Processor 510 may operate in conjunction with memory 520. The processor 510 may execute a computer program stored in the memory 520. Optionally, at least one of the at least one memory 520 may be included in the processor 510.
A transceiver 530 may also be included in the electronic device 500, and the electronic device 500 may interact with other devices via the transceiver 530. The transceiver 530 may be a circuit, bus, transceiver, or any other device that may be used to interact with information.
The specific connection medium between the transceiver 530, the processor 510, and the memory 520 is not limited in the embodiment of the present application. In the embodiment of the present application, the memory 520, the processor 510 and the transceiver 530 are connected by a bus, which is shown by a thick line in fig. 5, and the connection manner between other components is only schematically illustrated, but not limited thereto. The buses may be classified as address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 5, but not only one bus or one type of bus.
In an embodiment of the present application, the processor may be a general purpose processor, a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and may implement or execute the methods, steps, and logic blocks disclosed in the embodiments of the present application. The general purpose processor may be a microprocessor or any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in the processor for execution.
In the embodiment of the present application, the memory may be a nonvolatile memory, such as a hard disk (HARD DISK DRIVE, HDD) or a solid-state disk (SSD), or may be a volatile memory (RAM). The memory may also be any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to such. The memory in embodiments of the present application may also be circuitry or any other device capable of implementing a memory function for storing a computer program, program instructions and/or data.
Based on the above embodiments, referring to fig. 6, another electronic device 600 is further provided in the embodiment of the present application, and the electronic device 600 may be applied to a travel recommendation device. Comprising the following steps: an interface circuit 610 and a processor 620;
interface circuit 610 for receiving code instructions and transmitting to the processor;
and a processor 620 configured to execute the code instructions to perform the trip recommendation method in any of the foregoing embodiments.
Based on the above embodiments, the present embodiments also provide a readable storage medium storing instructions that, when executed, cause the method of any of the above embodiments to be implemented. The readable storage medium may include: various media capable of storing program codes, such as a U disk, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk.
Embodiments of the present application provide a computer program product comprising instructions which, when run on a computer, cause the above-described method embodiments to be performed.
Some or all of the operations and functions described in the above-described method embodiments of the present application may be implemented using a chip or an integrated circuit.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various modifications and variations can be made to the embodiments of the present application without departing from the scope of the embodiments of the application. Thus, if such modifications and variations of the embodiments of the present application fall within the scope of the claims and the equivalents thereof, the present application is also intended to include such modifications and variations.
Claims (13)
1. A travel recommendation method, comprising:
Acquiring portrait tags of target users, wherein the portrait tags are used for indicating behavior preferences of the users for travel products;
Determining that the target user subscribes to a first travel product at a first moment, and acquiring record information generated by browsing at least one travel product by the target user before the first moment; the first travel product is any travel product in at least one travel product, and the recorded information of the at least one travel product comprises product information of the at least one travel product;
Determining a target travel product matched with the portrait tag of the target user in the at least one travel product; determining a travel strategy of the target user based on the moment when the target user browses the target travel product and the first moment, wherein the travel strategy is used for indicating the advance time amount of the user booking a second travel product; the location corresponding to the second travel product is the same as the location corresponding to the first travel product.
2. The method of claim 1, wherein the at least one travel product has the same date of effectiveness and/or the at least one travel product corresponds to the same location.
3. The method of claim 1, wherein the type of the at least one travel product is an air ticket, and wherein the corresponding airlines of the at least one travel product are identical; or the type of the at least one travel product is a hotel product, and the hotel places corresponding to the at least one travel product are the same.
4. A method according to any one of claims 1-3, wherein obtaining the representation tag of the target user comprises:
Determining that the target user has a historical travel order, and determining an portrait tag of the target user according to product information of travel products contained in the historical travel order; or alternatively
Determining that the target user has no historical trip order, and determining the portrait tag of the target user group as the portrait tag of the target user; the target user group comprises the target users, and the portrait tag of the target user group is determined according to the portrait tag of at least one user with a historical trip order in the target user group.
5. The method of claim 4, wherein the method further comprises:
grouping a plurality of users according to their demographics, determining at least one user group including the target user group; wherein the plurality of users includes the target user and the demographic includes age and/or gender.
6. A travel recommendation device, characterized by comprising:
The processing module is used for acquiring portrait labels of target users, and the portrait labels are used for indicating the behavior preference of the users on travel products;
The acquisition module is used for acquiring record information generated by browsing at least one travel product by the target user before the first moment when the processing module determines that the target user subscribes to the first travel product at the first moment; the first travel product is any one of at least one travel product, and the recorded information comprises product information of the at least one travel product;
The processing module is further used for determining a target travel product matched with the portrait tag of the target user in the at least one travel product;
Determining a travel strategy of the target user based on the moment when the target user browses the target travel product and the first moment, wherein the travel strategy is used for indicating the advance time amount of the user booking a second travel product; the location corresponding to the second travel product is the same as the location corresponding to the first travel product.
7. The apparatus of claim 6, wherein the at least one travel product has an identical date of effectiveness and/or the at least one travel product corresponds to an identical location.
8. The apparatus of claim 6, wherein the at least one travel product is of the type of airline ticket and corresponds to the same airline; or the type of the at least one travel product is a hotel product, and the hotel places corresponding to the at least one travel product are the same.
9. The apparatus of any of claims 6-8, wherein the processing module is further to:
Determining that the target user has a historical travel order, and determining an portrait tag of the target user according to product information of travel products contained in the historical travel order; or alternatively
Determining that the target user has no historical trip order, and determining the portrait tag of the target user group as the portrait tag of the target user; the target user group comprises the target users, and the portrait tag of the target user group is determined according to the portrait tag of at least one user with a historical trip order in the target user group.
10. The apparatus of claim 9, wherein the processing module is further to:
grouping a plurality of users according to their demographics, determining at least one user group including the target user group; wherein the plurality of users includes the target user and the demographic includes age and/or gender.
11. An electronic device, comprising: a processor and a memory;
The memory is used for storing a computer program;
The processor configured to execute a computer program stored in the memory, to cause the electronic device to perform the method of any one of claims 1 to 5.
12. An electronic device, comprising: a processor and interface circuit;
the interface circuit is used for receiving code instructions and transmitting the code instructions to the processor;
the processor is configured to execute the code instructions to perform the method of any one of claims 1 to 5.
13. A computer readable storage medium storing instructions which, when executed, cause the method of any one of claims 1 to 5 to be implemented.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011182364.8A CN112507207B (en) | 2020-10-29 | 2020-10-29 | Travel recommendation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011182364.8A CN112507207B (en) | 2020-10-29 | 2020-10-29 | Travel recommendation method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112507207A CN112507207A (en) | 2021-03-16 |
CN112507207B true CN112507207B (en) | 2024-06-14 |
Family
ID=74954395
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011182364.8A Active CN112507207B (en) | 2020-10-29 | 2020-10-29 | Travel recommendation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112507207B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115660728B (en) * | 2022-10-11 | 2023-10-20 | 南京意博软件科技有限公司 | Air ticket sales order prediction method and device, electronic equipment and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106897782A (en) * | 2017-01-05 | 2017-06-27 | 北京趣拿信息技术有限公司 | The method and apparatus of information alert |
CN108470308A (en) * | 2018-03-29 | 2018-08-31 | 百度在线网络技术(北京)有限公司 | air travel information recommendation method and device |
CN109615408A (en) * | 2018-10-24 | 2019-04-12 | 中国平安人寿保险股份有限公司 | Advertisement placement method and device, storage medium, electronic equipment based on big data |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160125069A1 (en) * | 2014-11-03 | 2016-05-05 | Amadeus S.A.S. | Dynamic database object management |
KR101811274B1 (en) * | 2015-08-21 | 2018-01-25 | (주) 플라이트그래프 | System and method for follow air ticket searching |
CN107368488A (en) * | 2016-05-12 | 2017-11-21 | 阿里巴巴集团控股有限公司 | A kind of method for determining user behavior preference, the methods of exhibiting and device of recommendation information |
US20180025292A1 (en) * | 2016-07-19 | 2018-01-25 | Mastercard International Incorporated | Systems and methods for optimizing travel bookings |
CN107909473A (en) * | 2017-12-27 | 2018-04-13 | 中国银行股份有限公司 | A kind of Web bank's marketing method and device based on user behavior analysis |
CN109582876B (en) * | 2018-12-19 | 2021-05-11 | 广州易起行信息技术有限公司 | Tourist industry user portrait construction method and device and computer equipment |
CN111047405A (en) * | 2019-12-10 | 2020-04-21 | 上海博泰悦臻电子设备制造有限公司 | Information acquisition method, information acquisition system, terminal and storage medium |
CN111831710B (en) * | 2020-07-17 | 2023-09-22 | 深圳市活力天汇科技股份有限公司 | Air ticket fuzzy search method |
-
2020
- 2020-10-29 CN CN202011182364.8A patent/CN112507207B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106897782A (en) * | 2017-01-05 | 2017-06-27 | 北京趣拿信息技术有限公司 | The method and apparatus of information alert |
CN108470308A (en) * | 2018-03-29 | 2018-08-31 | 百度在线网络技术(北京)有限公司 | air travel information recommendation method and device |
CN109615408A (en) * | 2018-10-24 | 2019-04-12 | 中国平安人寿保险股份有限公司 | Advertisement placement method and device, storage medium, electronic equipment based on big data |
Also Published As
Publication number | Publication date |
---|---|
CN112507207A (en) | 2021-03-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10572833B2 (en) | Determining host preferences for accommodation listings | |
CN104169950B (en) | Utilize the Database Systems of the calculating towards batch processing | |
Clayton et al. | Autonomous vehicles: who will use them, and will they share? | |
CN101520784B (en) | Information issuing system and information issuing method | |
US20130073586A1 (en) | Database system using batch-oriented computation | |
US10607160B2 (en) | Unique accommodation search improvement founded in listing booking conversion | |
JPH10320416A (en) | Information delivery system and machine-readable record medium where program is recorded | |
WO2014159053A2 (en) | Generating data records based on parsing | |
US20200202365A1 (en) | Demand forecast system and method | |
CN102027492A (en) | Methods and systems for group data management and classification | |
CN112632405A (en) | Recommendation method, device, equipment and storage medium | |
KR20210082103A (en) | An apparatus and a method for calculating expected real estate transaction price based on real estate transaction price by using a machine learning model | |
CN112800210B (en) | Crowd portrayal algorithm based on mass public transport data | |
CN114912717B (en) | Smart city guarantee housing application risk assessment method and system based on Internet of things | |
CN112507207B (en) | Travel recommendation method and device | |
CN109377301A (en) | A kind of Feature Extraction Method based on Airline reservation behavioral data | |
Mahmud et al. | Truck parking usage patterns by facility amenity availability | |
Lee et al. | Taxi vacancy duration: a regression analysis | |
Kamola et al. | Improving time-series demand modeling in hospitality business by analytics of public event datasets | |
CN111373395A (en) | Artificial intelligence system and method based on hierarchical clustering | |
Garcia Pozo | A nested housing market structure: additional evidence | |
Jorge-González et al. | Univariate and multivariate forecasting of tourism demand using state-space models | |
CN113434678B (en) | Item type-based item reminding method, device, equipment and storage medium | |
US11257011B2 (en) | Booked-blocked classifier | |
CN114648010A (en) | Data table standardization method, device, equipment and computer storage medium |
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 |