CN109903143A - A kind of flight recommended method based on customer consumption level - Google Patents
A kind of flight recommended method based on customer consumption level Download PDFInfo
- Publication number
- CN109903143A CN109903143A CN201910236215.6A CN201910236215A CN109903143A CN 109903143 A CN109903143 A CN 109903143A CN 201910236215 A CN201910236215 A CN 201910236215A CN 109903143 A CN109903143 A CN 109903143A
- Authority
- CN
- China
- Prior art keywords
- flight
- user
- grade
- level
- customer consumption
- 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.)
- Pending
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention discloses a kind of flight recommended method based on customer consumption level.The described method includes: obtain user input querying condition and User ID, querying condition include departure place, reach and departure date；The characteristic attribute of user is obtained according to the User ID；The consumption grade of user is calculated according to the characteristic attribute of user；Search meets the flight of querying condition, and the grade of flight is calculated according to the characteristic attribute of the flight；The lowest price air ticket with the flight level of customer consumption ratings match is returned to user.The present invention can recommend different grades of Flight Information to the user of the different levels of consumption, to meet the booking demand of all level of consumption users.Solve the problems, such as that of the existing technology push lowest price air ticket is not able to satisfy high-end user and needs.
Description
Technical field
The invention belongs to air ticket inquiring technology fields, and in particular to a kind of flight recommendation side based on customer consumption level
Method.
Background technique
With the quickening pace of modern life, aircraft went out as people because of the advantages that its is quick and convenient, easily comfortable, safe and reliable
Capable first choice.Various, omnifarious air ticket software emerges one after another simultaneously.How to help user from dazzling boat
Best plan of travel is selected in line, flight, is become more and more important.
Traditional flight inquiring mode mainly pushes the lowest price in specific trip date course line to user, to guide
User carries out air ticket selection.But this method is unable to satisfy the different demands of different consumption level users, for example, some are high
End subscriber not only focuses on price factor, and comfortable, the quick degree of trip is more concerned about for relative price.
Summary of the invention
In order to solve the above-mentioned problems in the prior art, the present invention proposes a kind of flight based on customer consumption level
Recommended method.
To achieve the above object, the present invention adopts the following technical scheme:
A kind of flight recommended method based on customer consumption level, comprising the following steps:
Step 1, obtain user input querying condition and User ID, querying condition include departure place, reach and set out
Date；
Step 2, the characteristic attribute of user is obtained according to the User ID；
Step 3, the consumption grade of user is calculated according to the characteristic attribute of user；
Step 4, search meets the flight of querying condition, and the grade of flight is calculated according to the characteristic attribute of the flight；
Step 5, the lowest price air ticket with the flight level of customer consumption ratings match is returned to user.
Compared with prior art, the invention has the following advantages:
The present invention determines the consumption grade of user by obtaining the attributive character of user, and according to the characteristic attribute meter of flight
The grade for calculating flight returns to the lowest price air ticket with the flight level of customer consumption ratings match to user, can disappear to difference
The flat user of water wasting recommends different grades of Flight Information, to meet the booking demand of all level of consumption users.It solves
Of the existing technology push lowest price air ticket is not able to satisfy the problem of high-end user needs.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the flight recommended method based on customer consumption level of the embodiment of the present invention.
Specific embodiment
The present invention is described in further detail below in conjunction with the accompanying drawings.
A kind of flow chart of the flight recommended method based on customer consumption level of the embodiment of the present invention is as shown in Figure 1, described
Method includes:
S101, obtain user input querying condition and User ID, querying condition include departure place, reach and set out day
Phase；
S102, the characteristic attribute that user is obtained according to the User ID；
S103, the consumption grade that user is calculated according to the characteristic attribute of user；
S104, search meet the flight of querying condition, and the grade of flight is calculated according to the characteristic attribute of the flight；
S105, the lowest price air ticket with the flight level of customer consumption ratings match is returned to user.
In the present embodiment, step S101 is mainly used for obtaining querying condition and the user of the user's input inquired
ID.Querying condition generally comprises departure place, reach and departure date, can also include flight number freight space grade etc..
In the present embodiment, step S102 is mainly used for obtaining the characteristic attribute of user according to User ID.After user logs in,
As long as user is not to log in for the first time, so that it may the essential information filled in when finding this user's registration according to User ID, and
User place an order after some other information.It is extracted from these information and the horizontal related characteristic attribute of customer consumption, such as year
Age, educational background, order price etc..It is worth noting that the level of consumption mentioned here, not necessarily only related with economic strength, also
It is related with consumption habit and personal preference etc., for example some economic strengths are not the level of consumption of the very strong people in terms of trip,
Not necessarily just people more very strong than economic strength is low.In general, the quantity of the characteristic attribute of selection is more, estimates customer consumption water
Flat more accurate grade.Therefore, several possible characteristic attributes for influencing the level of consumption of Ying Jinliang multiselect.
In the present embodiment, step S103 is mainly used for calculating the consumption grade of user according to the characteristic attribute of user.Disappear
The number for taking grade can be empirically determined, for example, high and low two grades can be roughly divided into, can also be divided into
High, medium and low three grades can also divide more grades.The method for determining customer consumption grade is also more, simplest side
Method is by calculating each attributive character value and determining consumption grade according to the size with value；It can also be according to each attribute
The size of influence distributes weight, then to each attributive character value weighted sum, determines consumption grade further according to the size with value；
More scientific method is that consumption grade is calculated using classification (such as softmax classification).
In the present embodiment, step S104 is mainly used for the flight that search meets querying condition, and according to the flight
The grade of characteristic attribute calculating flight.The characteristic attribute of flight be primarily referred to as influencing whether admission fee and people like choosing because
Element, for example type and machine age, whether fly nonstop to, go on a journey period and freight space grade etc..In general, the quantity Ying Yuyong of flight level
The quantity that grade is consumed at family is identical, corresponds according to the sequence of consumption grade and flight level.The determination method of flight level
Identical as the determination method of customer consumption grade, which is not described herein again.
In the present embodiment, step S105 is mainly used for returning and the flight level of customer consumption ratings match to user
Lowest price air ticket.It has been observed that customer consumption grade and flight level are correspondingly, therefore, can to inquire from all satisfactions
Selected in the flight of condition with the matched flight of user gradation, and the lowest fare of the grade flight is returned into user.Xiang Yong
The lowest fare being on close level with customer consumption is recommended at family, can satisfy the demand of various level of consumption users, solves existing
Technology is existing not only to be able to satisfy the problem of high-end user needs to user's push lowest price air ticket.
As a kind of alternative embodiment, the characteristic attribute of user includes: gender, the age, city level, educational background, when order
Section, order course line, order freight space grade, order price.
This gives a kind of selection methods of user characteristics attribute.It is worth noting that the present embodiment only with
Example way gives a kind of specific embodiment, does not repel other feasible selection schemes, is increased on this basis
Subtract the protection scope for belonging to the present embodiment.
As a kind of alternative embodiment, the characteristic attribute of flight includes: type and machine age, if flies nonstop to, goes on a journey the period, rises
Drop ground, freight space grade, punctuality rate, aircraft newness degree, amusement equipment, food and drink situation, power conditions, airline service water
It is flat.
This gives a kind of selection methods of flight characteristic attribute.It is worth noting that the present embodiment only with
Example way gives a kind of specific embodiment, does not repel other feasible selection schemes, is increased on this basis
Subtract the protection scope for belonging to the present embodiment.
As a kind of alternative embodiment, the customer consumption grade and flight level include high, medium and low three grades,
Respectively correspond high-end user, travelling merchants user and general user.
This gives a kind of division methods of customer consumption grade and flight level, i.e., include high, medium and low three
A grade respectively corresponds high-end user, travelling merchants user and general user.This is a kind of common, fairly simple division methods,
More grades can also be subdivided into.
As a kind of alternative embodiment, customer consumption grade and flight level are calculated using softmax classification, it is specific to wrap
Include following steps:
Determine the quantity K of wanted divided rank；
To the characteristic value x of each attributeiIt is normalized to obtainI=1,2 ..., N, N are the quantity of attributive character value；
Calculate the score of each grade:
In formula, SkFor the score of k-th of grade, k=1,2 ..., K；θkiFor the power of k-th of grade ith attribute characteristic value
Weight；
Calculate the score of each grade and the ratio of the sum of all ranking scores
If mk1=max { m1,m2,…,mK, 1≤k1≤ K, then required grade is k1.
This gives the specific methods that customer consumption grade and flight level are calculated using softmax classification.
It is identical with the method for flight level to calculate customer consumption grade, it is unique the difference is that corresponding attributive character value is different.softmax
Classification is the mature prior art, and the present embodiment joined the step of characteristic value is normalized, and is to eliminate because each
The influence of the selection disunity In Grade computational accuracy of kind characteristic value size.
As a kind of alternative embodiment, the weight is by using neural network to the training number being made of attributive character value
Optimization is trained according to collection to obtain.
This gives the technical solutions that a kind of pair of attributive character value weight optimizes.Whether weight value is reasonable
Directly affect the computational accuracy of grade, it is therefore desirable to optimize to it.The present embodiment is using neural network to by attributive character
The training dataset of value composition is trained, and corrects the size of weight repeatedly, making calculated value with actual value, (training data is through people
Work point class is good) variance it is minimum, thus the weight after being optimized.
As a kind of alternative embodiment, the S105 returns to price calendar, including continuous more days and customer consumption to user
The lowest price air ticket of the flight level of ratings match.
This gives the another ways pushed to user, i.e., push price calendar to user.For example push is worked as
Even 1 year 120 days flight data, can provide more selections in this way after the preceding date for user, for example, when trip day
When phase is indefinite or selectable range is larger, the flight on cheapest date can choose.
It is above-mentioned that only several specific embodiments in the present invention are illustrated, but can not be as protection model of the invention
Enclose, it is all according to the present invention in the equivalent change or modification made of design spirit or equal proportion zoom in or out, should all
Think to fall into protection scope of the present invention.
Claims (7)
1. a kind of flight recommended method based on customer consumption level, which comprises the following steps:
Step 1, obtain user input querying condition and User ID, querying condition include departure place, reach and departure date；
Step 2, the characteristic attribute of user is obtained according to the User ID；
Step 3, the consumption grade of user is calculated according to the characteristic attribute of user；
Step 4, search meets the flight of querying condition, and the grade of flight is calculated according to the characteristic attribute of the flight；
Step 5, the lowest price air ticket with the flight level of customer consumption ratings match is returned to user.
2. the flight recommended method according to claim 1 based on customer consumption level, which is characterized in that the feature of user
Attribute includes: gender, age, city level, educational background, order period, order course line, order freight space grade, order price.
3. the flight recommended method according to claim 1 based on customer consumption level, which is characterized in that the feature of flight
Attribute includes: type and machine age, and if it flies nonstop to, goes on a journey the period, landing, freight space grade, punctuality rate, aircraft newness degree, joy
Happy equipment, food and drink situation, power conditions, airline's service level.
4. the flight recommended method according to claim 1 based on customer consumption level, which is characterized in that the user disappears
Take grade and flight level includes high, medium and low three grades, respectively corresponds high-end user, travelling merchants user and general user.
5. the flight recommended method according to claim 1 based on customer consumption level, which is characterized in that use
Softmax classification calculates customer consumption grade and flight level, specifically includes the following steps:
Determine the quantity K of wanted divided rank；
To the characteristic value x of each attributeiIt is normalized to obtainN is the quantity of attributive character value；
Calculate the score of each grade:
In formula, SkFor the score of k-th of grade, k=1,2 ..., K；θkiFor the weight of k-th of grade ith attribute characteristic value；
Calculate the score of each grade and the ratio of the sum of all ranking scores
If mk1=max { m1,m2,…,mK, 1≤k1≤ K, then required grade is k1.
6. the flight recommended method according to claim 5 based on customer consumption level, which is characterized in that the weight is logical
It crosses and optimization is trained to the training dataset being made of attributive character value using neural network obtains.
7. the flight recommended method according to claim 1 based on customer consumption level, which is characterized in that the step 5
Price calendar is returned to user, the lowest price air ticket including continuous more days with the flight level of customer consumption ratings match.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910236215.6A CN109903143A (en) | 2019-03-27 | 2019-03-27 | A kind of flight recommended method based on customer consumption level |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910236215.6A CN109903143A (en) | 2019-03-27 | 2019-03-27 | A kind of flight recommended method based on customer consumption level |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109903143A true CN109903143A (en) | 2019-06-18 |
Family
ID=66953870
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910236215.6A Pending CN109903143A (en) | 2019-03-27 | 2019-03-27 | A kind of flight recommended method based on customer consumption level |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109903143A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110415082A (en) * | 2019-07-26 | 2019-11-05 | 华世界网络科技(深圳)有限公司 | Price methods of exhibiting, device, server and storage medium based on ring layer |
| CN110489647A (en) * | 2019-08-15 | 2019-11-22 | 海南太美航空股份有限公司 | A kind of route information recommended method, system, storage medium and computer equipment |
| CN111049810A (en) * | 2019-11-28 | 2020-04-21 | 光通天下网络科技股份有限公司 | Network security suite matching method, device, equipment and medium |
| CN111385351A (en) * | 2020-02-20 | 2020-07-07 | 珠海格力电器股份有限公司 | Cleaning control method, device, terminal and computer readable medium |
| CN111581505A (en) * | 2020-04-28 | 2020-08-25 | 海南太美航空股份有限公司 | Flight recommendation method and system based on combined recommendation |
| CN113487135A (en) * | 2021-06-07 | 2021-10-08 | 海南太美航空股份有限公司 | Flight planning method, system and storage medium based on user requirements |
| CN115880034A (en) * | 2023-01-09 | 2023-03-31 | 河北省气象服务中心(河北省气象影视中心) | Data acquisition and analysis system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009108724A2 (en) * | 2008-02-25 | 2009-09-03 | Atigeo Llc | Platform for data aggregation, communication, rule evaluation, and combinations thereof, using templated auto-generation |
| CN104166713A (en) * | 2014-08-14 | 2014-11-26 | 百度在线网络技术（北京）有限公司 | Network service recommending method and device |
| CN105159933A (en) * | 2015-08-06 | 2015-12-16 | 北京百度网讯科技有限公司 | Tourism information recommendation method and apparatus |
| CN107578184A (en) * | 2017-09-19 | 2018-01-12 | 飞友科技有限公司 | A kind of method for evaluating quality of course line flight |
-
2019
- 2019-03-27 CN CN201910236215.6A patent/CN109903143A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009108724A2 (en) * | 2008-02-25 | 2009-09-03 | Atigeo Llc | Platform for data aggregation, communication, rule evaluation, and combinations thereof, using templated auto-generation |
| CN104166713A (en) * | 2014-08-14 | 2014-11-26 | 百度在线网络技术（北京）有限公司 | Network service recommending method and device |
| CN105159933A (en) * | 2015-08-06 | 2015-12-16 | 北京百度网讯科技有限公司 | Tourism information recommendation method and apparatus |
| CN107578184A (en) * | 2017-09-19 | 2018-01-12 | 飞友科技有限公司 | A kind of method for evaluating quality of course line flight |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110415082A (en) * | 2019-07-26 | 2019-11-05 | 华世界网络科技(深圳)有限公司 | Price methods of exhibiting, device, server and storage medium based on ring layer |
| CN110489647A (en) * | 2019-08-15 | 2019-11-22 | 海南太美航空股份有限公司 | A kind of route information recommended method, system, storage medium and computer equipment |
| CN111049810A (en) * | 2019-11-28 | 2020-04-21 | 光通天下网络科技股份有限公司 | Network security suite matching method, device, equipment and medium |
| CN111385351A (en) * | 2020-02-20 | 2020-07-07 | 珠海格力电器股份有限公司 | Cleaning control method, device, terminal and computer readable medium |
| CN111385351B (en) * | 2020-02-20 | 2021-05-25 | 珠海格力电器股份有限公司 | Cleaning control method, device, terminal and computer readable medium |
| CN111581505A (en) * | 2020-04-28 | 2020-08-25 | 海南太美航空股份有限公司 | Flight recommendation method and system based on combined recommendation |
| CN113487135A (en) * | 2021-06-07 | 2021-10-08 | 海南太美航空股份有限公司 | Flight planning method, system and storage medium based on user requirements |
| CN115880034A (en) * | 2023-01-09 | 2023-03-31 | 河北省气象服务中心(河北省气象影视中心) | Data acquisition and analysis system |
| CN115880034B (en) * | 2023-01-09 | 2023-12-22 | 河北省气象服务中心(河北省气象影视中心) | Data acquisition and analysis system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109903143A (en) | A kind of flight recommended method based on customer consumption level | |
| Brueckner | International airfares in the age of alliances: The effects of codesharing and antitrust immunity | |
| Song et al. | Modelling and forecasting the demand for Hong Kong tourism | |
| Havitz et al. | Leisure involvement revisited: Drive properties and paradoxes | |
| CN109345348A (en) | The recommended method of multidimensional information portrait based on travel agency user | |
| CN110222267A (en) | A kind of gaming platform information-pushing method, system, storage medium and equipment | |
| CN107688606A (en) | The acquisition methods and device of a kind of recommendation information, electronic equipment | |
| CN105791085B (en) | Friend recommendation method in the social networks of position based on position and time | |
| Zhang et al. | Gravity models in air transport research: a survey and an application | |
| CN109325659B (en) | Novel method for sequencing investment of power grid construction project | |
| CN109063945A (en) | A kind of 360 degree of customer portrait construction methods of sale of electricity company based on Value accounting system | |
| CN109636679A (en) | A kind of interactive tour schedule planing method based on artificial intelligence | |
| CN104391849A (en) | Collaborative filtering recommendation method for integrating time contextual information | |
| CN110060129A (en) | A kind of air ticket intelligent recommendation method | |
| CN107133825A (en) | The Forecasting Methodology and device of a kind of businessman's volume of the flow of passengers | |
| WO2022134478A1 (en) | Route recommendation method and apparatus, electronic device, and storage medium | |
| CN108829652A (en) | A kind of picture labeling system based on crowdsourcing | |
| CN112232596B (en) | Multi-mode intermodal transit city optimization method, system, terminal and storage medium | |
| CN104732422A (en) | Mobile user tag based personalized food recommendation method | |
| CN107145506A (en) | A kind of means of agricultural production Method of Commodity Recommendation of the improvement based on content | |
| Fujii et al. | Forecasting travel demand when the explanatory variables are highly correlated | |
| CN112287241B (en) | Travel recommendation method and system | |
| Mohamed et al. | A travel cost analysis of the value of adventure tourism of Kampar, Malaysia | |
| CN108717640B (en) | Data processing method of travel information and electronic equipment | |
| Reddy et al. | Factors Influencing Customer Satisfaction in Bangalore Shopping Malls: Before & During COVID–19 Pandemic |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Lin Xiaolan Inventor after: Zhao Peng Inventor after: Li Shangjin Inventor before: Lin Xiaolan Inventor before: Li Shangjin |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190618 |