CN113312399A

CN113312399A - Method and system for processing fare search

Info

Publication number: CN113312399A
Application number: CN202110608656.1A
Authority: CN
Inventors: 余朝
Original assignee: China Travelsky Holding Co
Current assignee: China Travelsky Holding Co
Priority date: 2021-06-01
Filing date: 2021-06-01
Publication date: 2021-08-27
Anticipated expiration: 2041-06-01
Also published as: CN113312399B

Abstract

The invention provides a method and a system for processing fare search, which are used for acquiring a fare search request sent by a target user; constructing a first key according to the fare search request; determining a second key corresponding to the first key as a target key from all second keys contained in a preset database, and acquiring a value corresponding to the target key from the database as a target value; and performing fare prediction on the fare search request according to the fare prediction historical data corresponding to the target value to obtain fare prediction data and feeding the fare prediction data back to the target user. A large amount of fare prediction historical data are obtained in advance in a database, when a user sends a fare search request, fare prediction historical data corresponding to the fare search request are obtained from the database, fare prediction is carried out according to the obtained fare prediction historical data, the fare prediction data are obtained and fed back to a target user to serve as a fare purchasing basis, and user experience is improved.

Description

Method and system for processing fare search

Technical Field

The invention relates to the technical field of data processing, in particular to a method and a system for processing fare search.

Background

With the development of science and technology and the improvement of living standard, an airplane gradually becomes one of the main transportation means selected by people for daily travel.

When buying the air ticket, the user can inquire the corresponding air ticket price through the internet. However, when the air ticket price is inquired through the internet at present, only the air ticket price which can be purchased in the same day can be provided, the air ticket price fluctuates along with the change of the purchasing period, and a user cannot obtain more detailed air ticket price fluctuation information, so that the user cannot determine the optimal ticket purchasing opportunity, and the user experience is poor.

Disclosure of Invention

In view of this, embodiments of the present invention provide a method and a system for processing fare search, so as to solve the problems of poor user experience and the like in the existing fare query manner.

In order to achieve the above purpose, the embodiments of the present invention provide the following technical solutions:

the first aspect of the embodiments of the present invention discloses a method for processing fare search, where the method includes:

obtaining a fare search request sent by a target user, wherein the fare search request at least comprises: origin, destination, trip departure time, and trip type;

constructing a first key according to the origin, the destination, the travel starting time and the travel type contained in the fare search request;

determining a second key corresponding to the first key as a target key from all second keys contained in a preset database, and acquiring a value corresponding to the target key as a target value from the database, wherein the database contains a plurality of second keys and corresponding values, the second keys are constructed according to historical fare search requests in a preset historical time period, the value of the second key is at least constructed from fare prediction historical data, and the fare prediction historical data is obtained by carrying out fare prediction on the historical fare search requests corresponding to the second keys;

and performing fare prediction on the fare search request according to the fare prediction historical data corresponding to the target value to obtain fare prediction data and feeding the fare prediction data back to the target user.

Preferably, the process of constructing the second key and the corresponding value included in the database includes:

obtaining a plurality of historical fare search requests in a preset historical time period, wherein the historical fare search requests at least comprise: origin, destination, trip departure time, trip type, designated features for indicating whether to fly straight, and search time;

aiming at each historical fare search request, constructing a corresponding initial key by using the historical fare search request, and constructing an initial value of the initial key by using the lowest air ticket price in a request result corresponding to the historical fare search request;

according to all the initial values, all the initial keys are arranged in a descending order;

aiming at each initial key after descending order arrangement, constructing a corresponding second key by utilizing a historical fare search request corresponding to the initial key;

for each second key, performing fare prediction on the historical fare search request corresponding to the second key, and constructing the value of the second key by using fare prediction historical data obtained by performing fare prediction;

and storing each second key and the corresponding value in a database.

Preferably, the determining, from all second keys included in a preset database, a second key corresponding to the first key as a target key, and obtaining, from the database, a value corresponding to the target key as a target value includes:

determining second keys with the same origin, the same destination, the same journey starting time and the same journey type as the first keys as target keys from all second keys contained in a preset database;

and inquiring the value of a second key with the same origin, the same destination, the same trip departure time and the same trip type as the first key from the database, and taking the value as the target value corresponding to the target key.

Preferably, the fare prediction data includes at least: and in a preset time period in the future from the search time corresponding to the ticket price search request, the lowest predicted ticket price and the prediction accuracy of each day.

Preferably, the process of feeding back the fare prediction data to the target user comprises:

generating a lowest predicted air ticket price trend graph by using the lowest predicted air ticket price per day in the future preset time period;

feeding back the lowest predicted air ticket price trend graph and the prediction accuracy to the target user.

Preferably, the performing fare prediction on the fare search request according to the fare prediction history data corresponding to the target value to obtain fare prediction data and feeding the fare prediction data back to the target user includes:

and performing fare prediction on the fare search request according to the fare prediction historical data corresponding to the target value and by combining a fare prediction model obtained by pre-training to obtain fare prediction data and feeding the fare prediction data back to the target user.

A second aspect of an embodiment of the present invention discloses a system for processing a fare search, the system including:

an obtaining unit, configured to obtain a fare search request sent by a target user, where the fare search request at least includes: origin, destination, trip departure time, and trip type;

the building unit is used for building a first key according to the origin, the destination, the travel starting time and the travel type contained in the fare search request;

the processing unit is used for determining a second key corresponding to the first key as a target key from all second keys contained in a preset database, and acquiring a value corresponding to the target key from the database as a target value, wherein the database contains a plurality of second keys and corresponding values, the second keys are constructed according to historical fare search requests in a preset historical time period, the value of the second key is at least constructed from fare prediction historical data, and the fare prediction historical data is obtained by performing fare prediction on the historical fare search requests corresponding to the second keys;

and the prediction unit is used for predicting the fare of the fare search request according to the fare prediction historical data corresponding to the target value to obtain fare prediction data and feeding the fare prediction data back to the target user.

Preferably, the processing unit for constructing the second key and the corresponding value included in the database includes:

the acquisition module is used for acquiring a plurality of historical fare search requests in a preset historical time period, wherein the historical fare search requests at least comprise: origin, destination, trip departure time, trip type, designated features for indicating whether to fly straight, and search time;

the system comprises a first construction module, a second construction module and a third construction module, wherein the first construction module is used for constructing a corresponding initial key by utilizing the historical fare search request aiming at each historical fare search request, and constructing an initial value of the initial key by utilizing the lowest air ticket price in a request result corresponding to the historical fare search request;

the sorting module is used for carrying out descending sorting on all the initial keys according to all the initial values;

the second construction module is used for constructing a corresponding second key by utilizing the historical fare search request corresponding to each initial key after descending order arrangement;

the prediction module is used for predicting the fares of the historical fare search requests corresponding to the second keys according to each second key and constructing the value of the second key by using the fare prediction historical data obtained by predicting the fares;

and the storage module is used for storing each second key and the corresponding value into a database.

A third aspect of an embodiment of the present invention discloses an electronic device, including: the system comprises a processor and a memory, wherein the processor and the memory are connected through a communication bus; the processor is used for calling and executing the program stored in the memory; the memory is used for storing a program for implementing the method for processing fare search as disclosed in the first aspect of the embodiments of the present invention.

A fourth aspect of the embodiments of the present invention discloses a computer-readable storage medium, in which computer-executable instructions are stored, and the computer-executable instructions are used for executing the method for processing fare search disclosed in the first aspect of the embodiments of the present invention.

Based on the method and the system for processing fare search provided by the embodiment of the invention, the method comprises the following steps: obtaining a fare search request sent by a target user; constructing a first key according to the origin, the destination, the travel starting time and the travel type contained in the fare search request; determining a second key corresponding to the first key as a target key from all second keys contained in a preset database, and acquiring a value corresponding to the target key from the database as a target value; and performing fare prediction on the fare search request according to the fare prediction historical data corresponding to the target value to obtain fare prediction data and feeding the fare prediction data back to the target user. According to the scheme, a first key is constructed according to a fare search request sent by a target user, a second key corresponding to the first key is inquired from a preset database to serve as the target key, a value corresponding to the target key is obtained from the database to serve as a target value, fare prediction is conducted on the fare search request according to fare prediction historical data corresponding to the target value, fare prediction data are obtained and fed back to the target user, a large amount of fare prediction historical data are obtained in the database in advance, when the user sends the fare search request, the fare prediction historical data corresponding to the fare search request are obtained from the database, the fare prediction is conducted on the fare search request according to the obtained fare prediction historical data, the fare prediction data are obtained and fed back to the target user to serve as a ticket buying basis, and user experience is improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

FIG. 1 is a flow chart of a method of processing a fare search according to an embodiment of the present invention;

FIG. 2 is a schematic diagram illustrating fare prediction data provided in accordance with an embodiment of the present invention;

FIG. 3 is a flowchart of database construction according to an embodiment of the present invention;

fig. 4 is a block diagram illustrating a system for processing a fare search according to an embodiment of the present invention;

fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In this application, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

The background technology shows that when a user inquires the air ticket price through the internet at present, only the air ticket price which can be bought on the same day can be inquired, but the air ticket price fluctuates along with the change of the buying period, the user cannot obtain more detailed air ticket price fluctuation information, the user cannot determine the best ticket buying opportunity, and the user experience is poor.

Therefore, the embodiment of the invention provides a method and a system for processing fare search, a large amount of fare prediction historical data are obtained in advance in a database, when a user sends a fare search request, the fare prediction historical data corresponding to the fare search request are obtained from the database, the fare prediction is carried out on the fare search request according to the obtained fare prediction historical data, the fare prediction data are obtained and fed back to a target user as a fare purchasing basis, and therefore the user experience is improved.

Referring to fig. 1, a flowchart of a method for processing a fare search according to an embodiment of the present invention is shown, where the method includes:

step S101: and obtaining a fare search request sent by a target user.

It should be noted that the fare search request at least includes: an origin, a destination, a trip departure time (also referred to as a trip departure date), and a trip type indicating whether the trip of the target user is a one-way trip (typically denoted by OW) or a round-trip (typically denoted by RT).

It should be further noted that, when the trip type is a one-way trip, the trip departure time represents the departure time, and when the trip type is a return trip, the trip departure time includes the departure time and the return trip departure time.

It will be appreciated that the fare search request also typically includes: the search time corresponding to the ticket price search request is the current time for the target user to search for the air ticket, for example, the target user searches for the price of the air ticket on 3/2/2021, and the target user searches for the search time on 3/2/2021.

In the process of implementing step S101 specifically, a fare search request sent by a target user is acquired, and information such as a corresponding origin, a destination, a travel departure time, a travel type, a search time, and a specific feature for indicating whether to fly straight or not is acquired from the fare search request.

Step S102: and constructing a first key according to the origin, the destination, the travel departure time and the travel type contained in the fare search request.

In the process of implementing step S102 specifically, a first key is constructed according to the origin, the destination, the travel departure time, and the travel type included in the fare search request, and the content of the first key is [ travel type/departure/destination/travel departure time ].

It can be understood from the content of the above step S101 that the fare search request further includes a specified feature for indicating whether to fly straight, so when the first key is constructed, the specified feature for indicating whether to fly straight is usually added to the first key, so the actual content of the first key is [ type of journey/whether to fly straight/origin/destination/departure time ], but when the second key corresponding to the first key is queried from the database, it only needs to query by using the type of journey, origin, destination and departure time in the first key, and details about the content in the database are shown in the following steps.

Such as: the target user needs to inquire a direct flight to Sydney from Beijing in 4/13/2020, the type of the journey is one-way journey, and the content of the first key is [ OW/Y/BJS/SYD/20200413/], wherein OW represents one-way journey, Y represents direct flight, BJS represents Beijing, SYD represents Sydney, 20200413 represents the departure time of the journey, and the content after "20200413" is empty because the type of the journey is one-way journey.

Step S103: and determining a second key corresponding to the first key as a target key from all second keys contained in a preset database, and acquiring a value corresponding to the target key from the database as a target value.

It should be noted that, the historical fare search requests in the preset historical time period are collected in advance, such as: and collecting historical fare search requests of the last half year, and acquiring the lowest air ticket price in the request result corresponding to the search time of the historical fare search requests while collecting the historical fare search requests.

It can be understood that, when the user searches for the air ticket prices at a certain search time (i.e. when the user sends a corresponding air ticket search request), the minimum air ticket prices corresponding to the search time (i.e. the minimum air ticket prices searched for on the current date) will be carried in the request result (the air ticket search feedback result corresponding to the air ticket search request), and the minimum air ticket prices are the minimum air ticket prices corresponding to the travel departure time of the air ticket search request, such as: the user searches the airline tickets flying to xx in 2020 on 4/1/2020, and the request result carries the lowest airline ticket price for flying to xx in 2020 on 5/1/xx in 2020, which is the departure date searched on 4/1/2020.

And constructing a second key in the database by using the collected historical fare search requests, performing fare prediction on the historical fare search requests to obtain corresponding fare prediction historical data, and constructing the value of the second key by using at least the fare prediction historical data.

The ticket price prediction historical data is as follows: predicting the lowest predicted air ticket price of each day in a preset time period in the future of the search time of the historical ticket price search request, such as: the search time of a certain historical fare search request is 12 months and 30 days in 2019, the historical fare search request is an airplane ticket flying to xx in 2 months and 3 days in 2020, and fare prediction historical data of the historical fare search request is as follows: the minimum predicted ticket price for each day that departs from 31/12/2019 to 6/1/2020 is xx to xx on 3/2/2020.

That is to say, the database includes a plurality of second keys and corresponding values, the second keys are constructed according to historical fare search requests in a preset historical time period, the values of the second keys are at least constructed from fare prediction historical data, the fare prediction historical data are obtained by performing fare prediction on the historical fare search requests corresponding to the second keys, and the prediction can be specifically performed through a preset prediction algorithm or a pre-trained fare prediction model.

It will be appreciated that each second key in the database is made up of at least an origin, a destination, a trip departure time, a trip type, and a designated characteristic for indicating whether or not to fly straight.

In the process of specifically implementing step S103, from all the second keys included in the preset database, the second keys having the same origin, the same destination, the same trip departure time, and the same trip type as the first keys are determined as target keys. From the database, the value of the second key with the same origin, the same destination, the same trip departure time and the same trip type as the first key is queried and is taken as the target value corresponding to the target key, that is, the value corresponding to the target key is queried as the target value.

It should be noted that, as can be seen from the above, the second key further includes a specific feature for indicating whether to fly straight (where Y represents a straight flight, and N represents a transit flight), that is, only the origin, the destination, the departure time and the type of the journey of the first key are used to query the corresponding second key from the database, and a plurality of second keys may be queried, that is, although the queried plurality of second keys have the same origin, the same destination, the same departure time and the same type of journey as the first key, some of the queried plurality of second keys have the specific feature of Y (straight flight) and some of the queried second keys have the specific feature of N (transit flight), and in this case, all the queried second keys are used as target keys.

In other words, a second key, which has the same origin, the same destination, the same departure time, and the same type of journey as the first key, is targeted regardless of whether the designated feature is a direct flight or a transit flight.

Step S104: and performing fare prediction on the fare search request according to the fare prediction historical data corresponding to the target value to obtain fare prediction data and feeding the fare prediction data back to the target user.

In the process of implementing step S104 specifically, fare prediction history data corresponding to the target value (one or more) is obtained, and fare prediction is performed on the fare search request of the target user by using the fare prediction history data of the target value as a basis and combining a fare prediction model obtained through pre-training, so as to obtain fare prediction data and feed the fare prediction data back to the target user.

Similarly, the fare prediction historical data of the target value can be used as a basis, and the fare prediction data can be obtained by performing fare prediction on the fare search request of the target user by combining a corresponding prediction algorithm.

It is understood that the fare prediction data corresponding to the fare search request of the target user at least includes: the minimum predicted air ticket price (the minimum predicted air ticket price corresponding to the travel departure time) and the prediction accuracy for each day within a preset time period in the future from the search time corresponding to the ticket price search request are as follows: the lowest predicted ticket price and the prediction accuracy (also referred to as confidence index) per day within 7 days in the future from the search time corresponding to the ticket price search request.

That is, the specific content of the fare prediction data corresponding to the fare search request of the target user is at least: [ minimum predicted ticket price for future day 1/minimum predicted ticket price for future day 2/…/minimum predicted ticket price for future day n/confidence index ].

The obtained fare prediction data is fed back to the target user, and the fare prediction data is displayed at the front end, so that the target user can intuitively know the price fluctuation condition of the air ticket which the target user wants to pay attention to.

The way of feeding back the fare prediction data to the target user specifically is as follows: and generating a minimum predicted air ticket price trend graph by using the minimum predicted air ticket price in a future preset time period every day, and feeding back the minimum predicted air ticket price trend graph and the prediction accuracy to the target user.

It should be noted that, a corresponding trend graph is generated for the lowest predicted air ticket price in the future preset time period every day, so that the target user can more intuitively know the price fluctuation condition of the air ticket, and similarly, the ticket price prediction data can also be displayed to the user by other modes (such as a table), and the display mode of the ticket price prediction data is not specifically limited.

It will be appreciated that while the fare prediction data is presented to the target user, more information may be presented to the target user, such as: the minimum air ticket prices within one month (only used for example) and two months (only used for example) from the search time of the ticket price search request are displayed to the target user, meanwhile, information such as the type of journey, the origin, the destination and the like in the ticket price search request can be simultaneously displayed to the target user, the minimum air ticket prices on the day of the search time of the ticket price search request can be displayed to the target user, and the type of the information required to be displayed to the target user is not specifically limited.

To better explain how the fare prediction data and other information is presented to the target user, this is illustrated by the schematic diagram showing fare prediction data shown in fig. 2, fig. 2 being for example only.

It is assumed that the target user searches for the air ticket price flown from beijing to sydney at the departure time of 2021 year 2/month 13 (search time) on 2021 year 5/month 1, and obtains corresponding ticket price prediction data after the relevant processing from step S101 to step S104, where the ticket price prediction data includes: within 14/2/2021/2/20/20201, the departure time is the lowest predicted air ticket price for each day flown by beijing to sydney in 5/1/2021.

And (3) generating a lowest predicted air ticket price trend chart by combining the lowest air ticket price which is searched for in 2-month and 13-month in 2021 and flies to Sydney from Beijing at the departure time of 5-month and 1-day in 2021 with the ticket price prediction data.

As shown in fig. 2, the lowest predicted ticket price trend graph includes: the lowest ticket prices searched for on the day of 2/13/2021 (3681 yuan), and the lowest predicted ticket prices for each day of 2/14/20201 to 20/2021 (2345 yuan, 3654 yuan, 2480 yuan, 3654 yuan, 2654 yuan, and 1838 yuan, respectively), as well as the origin and destination (BJS-SYD in fig. 2), the type of journey (OW in fig. 2), a specified feature indicating whether to fly straight (Y in fig. 2), the predicted generation date (xxx in fig. 2), the confidence index (66.24% in fig. 2), the lowest ticket prices for two months (1228 yuan in fig. 2), and the lowest ticket prices for one month (1228 yuan in fig. 2), are shown, respectively.

Through the lowest predicted air ticket price trend chart shown in fig. 2, the target user can intuitively know that the lowest air ticket price flying to sydney from beijing at the departure time of 2021 year 5 month 1 can be bought at 20 months of 2021 year 2, and special marks are made at 20 days of 2021 year 2 months, such as: on the broken line of the lowest predicted air ticket price trend graph of fig. 2, the circle indicator symbol corresponding to the 2 nd, 20 th day of 2021 is enlarged and thickened, thereby playing a role of recommending that ticket purchasing is appropriate at the 2 nd, 20 th day of 2021 to the target user.

It should be noted that, for the fare search request sent by the target user, recording and storing are performed, and according to the actual minimum fare price of each day in the future preset time period, the obtained fare prediction data is verified, whether the fare prediction data is correct is verified, and the confidence index is recalculated according to the verification result.

In the embodiment of the invention, a first key is constructed according to a fare search request sent by a target user, a second key corresponding to the first key is inquired from a preset database to be used as a target key, a value corresponding to the target key is obtained from the database to be used as a target value, fare prediction is carried out on the fare search request according to fare prediction historical data corresponding to the target value, fare prediction data are obtained and fed back to the target user to be used as a ticket buying basis, and the user experience is improved.

Referring to fig. 3, a flowchart of a process for constructing a database in step S103 according to the above embodiment of the present invention is shown, where the process includes the following steps:

step S301: and acquiring a plurality of historical fare search requests in a preset historical time period.

It should be noted that, in the field of civil aviation, tens of millions of pieces of relevant data of the searched air tickets are generated every day, and the relevant data are recorded and used as a basis for predicting the fare in the embodiment of the present invention, and the relevant data include, but are not limited to: the data of origin, destination, flight control department, departure date, departure time, arrival time, transit residence time, inquiry time, air ticket prices of different cabins, air ticket taxes, surplus tickets of different cabins, flight control type and the like.

It is to be understood that the historical fare search requests include at least: origin, destination, trip departure time, trip type, specified characteristics for indicating whether to fly straight, and search time.

In the process of implementing step S301 specifically, a plurality of historical fare search requests within a preset historical time period are acquired, and an origin, a destination, a travel departure time, a travel type, a specified feature indicating whether to fly straight, and a search time in each historical fare search request are acquired.

Preferably, the total number of historical fare search requests is counted, and when classification statistics (such as classification statistics according to cities searched by users) are required, the classification statistics can be assisted by the total number obtained through statistics.

Step S302: and aiming at each historical fare search request, constructing a corresponding initial key by using the historical fare search request, and constructing an initial value of the initial key by using the lowest air ticket price in a request result corresponding to the historical fare search request.

In the process of specifically implementing step S302, for each historical fare search request, an initial key corresponding to the historical fare search request is constructed by using the travel type, the origin, the destination, the travel departure time, and the search time in the historical fare search request, that is, the content of the initial key is: [ itinerary type/origin/destination/itinerary departure time/search time ], the lowest ticket price in the request results of the historical ticket price search request is the initial value corresponding to the initial key.

That is, each historical fare search request may construct a pair of key-value pairs (initial key-initial value).

Such as: for a certain historical fare search request, assuming that the historical fare search request is used for searching the air ticket prices of Beijing flying to Shanghai, if the journey type of the historical fare search request is one-way journey, the corresponding initial key is [ OW/BJS/SHA/20200401/20200201], the corresponding initial value is the lowest air ticket price searched for on 2/1/2020, and the journey departure time is 2020, 4/1/4; if the journey type of the historical fare search request is a round-trip journey, the corresponding initial key is [ RT/BJS/SHA/20200401/20200408/20200201], the initial value corresponding to the historical fare search request is the lowest air ticket price searched for on day 2/1 of 2020, the departure time of the first journey is 1/4 of 2020, and the departure time of the second journey is 8/4 of 2020 (equivalent to a return journey).

It should be noted that, in the process of determining the initial key and the initial value, a situation that the lowest air ticket price of the historical air ticket search request is missing may occur, and when the situation occurs, the historical air ticket search request with the missing lowest air ticket price is subjected to the air ticket search again, and the lowest price generated by the search result is supplemented to the corresponding lowest air ticket price.

Step S303: and according to all initial values, all initial keys are sorted in a descending order.

It should be noted that the same historical fare search request may occur, and therefore, there are a plurality of corresponding initial values for the initial key constructed by the historical fare search request. In the process of implementing step S303 specifically, for each initial key, the number of initial values corresponding to the initial key is counted from all the initial values. In this way, the number of initial values corresponding to each initial key is counted.

And sorting all the initial keys in a descending order according to the number of the initial values corresponding to each initial key, such as the contents shown in table 1.

Table 1:

initial key	Number of pieces of initial value
		OW/BJS/HKG/20200401/20200201	1200
OW/SHA/TYO/20200401/20200201	1100
		OW/CAN/LON/20200401/20200201	900
OW/BJS/SEL/20200401/20200201	600

Table 1 is given by way of example only.

It can be understood that after all the initial keys are sorted in a descending order, the popularity value (i.e. the search frequency) of each sorted initial key can be calculated in the following manner: the popularity value is the initial value number of the initial keys to be calculated/the initial value number of the initial keys with the sorting sequence number of 1, wherein the initial keys with the sorting sequence number of 1 are the initial keys with the largest initial value number after descending sorting.

Preferably, the data optimization can be performed on the sequenced initial keys, and the specific optimization process is as follows: calculating the total initial value number corresponding to each sorted initial key, calculating the data proportion of the initial value number of each initial key according to the total initial value number corresponding to each initial key, and only keeping the related data corresponding to the initial keys with the preset proportion (for example, selecting 90% of the previous proportion).

The total initial value number corresponding to each initial key is the initial value number corresponding to itself + the total initial value number corresponding to the initial key of the last sequence number, for example: the total initial value number corresponding to the mth initial key is equal to the initial value number corresponding to the mth initial key + the total initial value number corresponding to the (m-1) th initial key, wherein the total initial value number corresponding to the 0 th initial key is 0.

The data ratio of the initial value number of each initial key is the total initial value number corresponding to itself/the total initial value number corresponding to the last initial key, such as: assuming that there are s initial keys in total after descending sorting, the data proportion of the initial value number of the mth initial key (at this time, m is less than or equal to s) initial key is the total initial value number corresponding to the mth initial key/the total initial value number corresponding to the sth initial key.

To better explain the above contents regarding the popularity value, the total initial value number and the data ratio, the contents shown in table 2 are exemplified, and table 2 is only for example.

Table 2:

step S304: and aiming at each initial key after descending order arrangement, constructing a corresponding second key by utilizing the historical fare search request corresponding to the initial key.

In the process of specifically implementing step S304, after the initial keys are sorted in a descending order, for each initial key after the descending order, a corresponding second key is constructed by using the origin, the destination, the travel departure time, the travel type and the specified feature for indicating whether to fly straight or not in the historical fare search request corresponding to the initial key, where the content of the second key is: type of trip/specified characteristics/origin/destination/departure time of trip.

In the above manner, a plurality of second keys are constructed.

Step S305: and for each second key, performing fare prediction on the historical fare search request corresponding to the second key, and constructing the value of the second key by using the fare prediction historical data obtained by performing the fare prediction.

In the process of specifically implementing step S305, for each second key, performing fare prediction on the historical fare search request corresponding to the second key to obtain fare prediction historical data, and taking the fare prediction historical data as a value of the second key, where the specific content of the value of the second key is: [ minimum predicted ticket price for future day 1/minimum predicted ticket price for future day 2/…/minimum predicted ticket price for future day n/confidence index ].

Preferably, the lowest air ticket price in the recent period of the historical ticket price search request (such as in the past 1 month and in the past 2 months) may also be added to the value of the second key, where the specific content of the value of the second key is: [ minimum predicted ticket price for future day 1/minimum predicted ticket price for future day 2/…/minimum predicted ticket price for future day n/confidence index/minimum ticket price in past 1 month/minimum ticket price in past 2 months ].

In the above manner, the value of each second key is determined.

Step S306: and storing each second key and the corresponding value in a database.

In the process of implementing step S306 specifically, an index such as (second key, value) is constructed in the database with the second key and the corresponding value, and the constructed index is stored in the database.

Such as: assuming that the lowest predicted ticket price is predicted for a maximum of 7 (i.e., where n is 7 in the value above), some index is: the second key is [ OW/Y/BJS/SYD/20200401/], corresponding value is [3681/2345/3654/2480/3654/2654/2654/1838/0.6624/1228/1228 ].

That is, the value corresponding to each second key in the database is the historical data of fare prediction obtained through data processing.

In the embodiment of the invention, a large amount of fare prediction historical data are acquired in advance in the database, when a user sends a fare search request, the fare prediction historical data corresponding to the fare search request are acquired from the database, and the fare prediction is carried out on the fare search request according to the acquired fare prediction historical data, so that the fare prediction data are obtained and fed back to a target user as a fare purchasing basis, and the user experience is improved.

Corresponding to the method for processing fare search provided by the above embodiment of the present invention, referring to fig. 4, an embodiment of the present invention further provides a structural block diagram of a system for processing fare search, where the system includes: an acquisition unit 401, a construction unit 402, a processing unit 403, and a prediction unit 404;

an obtaining unit 401, configured to obtain a fare search request sent by a target user, where the fare search request at least includes: origin, destination, trip departure time, and trip type.

A constructing unit 402, configured to construct the first key according to the origin, the destination, the travel departure time, and the travel type included in the fare search request.

The processing unit 403 is configured to determine, from all second keys included in a preset database, a second key corresponding to the first key as a target key, and obtain, from the database, a value corresponding to the target key as a target value, where the database includes a plurality of second keys and corresponding values, the second keys are constructed according to a historical fare search request in a preset historical time period, the value of the second key is constructed from at least fare prediction historical data, and the fare prediction historical data is obtained by performing fare prediction on the historical fare search request corresponding to the second key.

In a specific implementation, the processing unit 403 is specifically configured to: and determining second keys with the same origin, the same destination, the same journey departure time and the same journey type as the first keys from all second keys contained in a preset database as target keys, inquiring values of the second keys with the same origin, the same destination, the same journey departure time and the same journey type as the first keys from the database, and taking the values as target values corresponding to the target keys.

And the predicting unit 404 is configured to perform fare prediction on the fare search request according to the fare prediction history data corresponding to the target value, obtain fare prediction data, and feed the fare prediction data back to the target user.

In a particular implementation, the fare prediction data includes at least: the prediction unit 404 for feeding back the fare prediction data to the target user within a preset time period in the future from the search time corresponding to the fare search request, the lowest predicted fare price and the prediction accuracy for each day, specifically for: and generating a minimum predicted air ticket price trend graph by using the minimum predicted air ticket price in a future preset time period every day, and feeding back the minimum predicted air ticket price trend graph and the prediction accuracy to the target user.

In another specific implementation, the prediction unit 404 is specifically configured to: and performing fare prediction on the fare search request according to the fare prediction historical data corresponding to the target value and by combining a fare prediction model obtained by pre-training to obtain fare prediction data and feeding the fare prediction data back to the target user.

Preferably, in connection with what is shown in fig. 3, the processing unit 403 for constructing the second key and the corresponding value contained in the database includes: the system comprises an acquisition module, a first construction module, a sequencing module, a second construction module, a prediction module and a storage module, wherein the execution principle of each module is as follows:

the acquisition module is used for acquiring a plurality of historical fare search requests in a preset historical time period, wherein the historical fare search requests at least comprise: origin, destination, trip departure time, trip type, specified characteristics for indicating whether to fly straight, and search time.

And the first construction module is used for constructing a corresponding initial key by using the historical fare search requests according to each historical fare search request, and constructing an initial value of the initial key by using the lowest air ticket price in the request result corresponding to the historical fare search request.

And the sorting module is used for performing descending order arrangement on all initial keys according to all initial values.

And the second construction module is used for constructing a corresponding second key by utilizing the historical fare search request corresponding to the initial key aiming at each initial key after descending order arrangement.

And the prediction module is used for predicting the fares of the historical fare search requests corresponding to the second keys according to each second key and constructing the value of the second key by using the fare prediction historical data obtained by predicting the fares.

And the storage module is used for storing each second key and the corresponding value into the database.

An embodiment of the present invention further provides an electronic device, where the electronic device includes: the processor and the memory are connected through a communication bus; the processor is used for calling and executing the program stored in the memory; a memory for storing a program for implementing a method of processing a fare search.

Referring now to FIG. 5, shown is a schematic diagram of an electronic device suitable for use in implementing embodiments of the present disclosure. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., car navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 5, the electronic device may include a processing means (e.g., central processing unit, graphics processor, etc.) 501 that may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage means 506 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data necessary for the operation of the electronic apparatus are also stored. The processing device 501, the ROM 502, and the RAM503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.

Generally, the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 507 including, for example, a Liquid Crystal Display (LCD), speakers, vibrators, and the like; storage devices 508 including, for example, magnetic tape, hard disk, etc.; and a communication device 509. The communication means 509 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. While fig. 5 illustrates an electronic device having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 509, or installed from the storage means 508, or installed from the ROM 502. The computer program performs the above-described functions defined in the methods of the embodiments of the present disclosure when executed by the processing device 501.

Still further, embodiments of the present invention provide a computer-readable storage medium having stored thereon computer-executable instructions for performing a method of processing a fare search.

The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: obtaining a fare search request sent by a target user; constructing a first key according to the origin, the destination, the travel starting time and the travel type contained in the fare search request; determining a second key corresponding to the first key as a target key from all second keys contained in a preset database, and acquiring a value corresponding to the target key from the database as a target value; and performing fare prediction on the fare search request according to the fare prediction historical data corresponding to the target value to obtain fare prediction data and feeding the fare prediction data back to the target user.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the system or system embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described system and system embodiments are only illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method of processing a fare search, the method comprising:

2. The method of claim 1, wherein the process of building a second key and corresponding value contained in the database comprises:

and storing each second key and the corresponding value in a database.

3. The method according to claim 1, wherein the determining, as the target key, the second key corresponding to the first key from all second keys included in a preset database, and obtaining, as the target value, the value corresponding to the target key from the database includes:

4. The method of claim 1, wherein the fare prediction data includes at least: and in a preset time period in the future from the search time corresponding to the ticket price search request, the lowest predicted ticket price and the prediction accuracy of each day.

5. The method of claim 4, wherein feeding back the fare prediction data to the target user comprises:

6. The method according to claim 1, wherein the performing fare prediction on the fare search request according to the fare prediction history data corresponding to the target value to obtain fare prediction data and feeding the fare prediction data back to the target user comprises:

7. A system for processing a fare search, the system comprising:

8. The system according to claim 7, wherein said processing unit for building a second key and a corresponding value comprised by said database comprises:

9. An electronic device, comprising: the system comprises a processor and a memory, wherein the processor and the memory are connected through a communication bus; the processor is used for calling and executing the program stored in the memory; the memory for storing a program for implementing the method of processing a fare search according to any one of claims 1-6.

10. A computer-readable storage medium having stored thereon computer-executable instructions for performing the method of processing a fare search of any one of claims 1-6.