CN107506877A - OTA platforms are to Forecasting Methodology and system of the shop without room - Google Patents
OTA platforms are to Forecasting Methodology and system of the shop without room Download PDFInfo
- Publication number
- CN107506877A CN107506877A CN201710919907.1A CN201710919907A CN107506877A CN 107506877 A CN107506877 A CN 107506877A CN 201710919907 A CN201710919907 A CN 201710919907A CN 107506877 A CN107506877 A CN 107506877A
- Authority
- CN
- China
- Prior art keywords
- hotel
- room
- data
- order
- shop
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000003066 decision tree Methods 0.000 claims abstract description 9
- 230000005540 biological transmission Effects 0.000 claims description 8
- 238000011835 investigation Methods 0.000 claims description 8
- 238000012986 modification Methods 0.000 claims description 7
- 230000004048 modification Effects 0.000 claims description 7
- 235000021167 banquet Nutrition 0.000 claims description 6
- 238000012360 testing method Methods 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 244000025254 Cannabis sativa Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0605—Supply or demand aggregation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/12—Hotels or restaurants
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses Forecasting Methodology and system of a kind of OTA platforms to shop without room, the Forecasting Methodology includes：After user places an order, user's order data is obtained；Corresponding with user's order data user's order tentation data, hotel's historical data, the price data of hotel's house type, the nervous degrees of data of hotel's house type and hotel's history are obtained to shop without room rate data according to user's order data；The data of above-mentioned acquisition are handled by Decision Tree Algorithm, user is established and occurs to shop without room Probabilistic Prediction Model to predict with user's order to probability of the shop without room, OTA platforms are sent according to probability to hotel intervenes content.Present invention improves it is existing by the way of manually investigating to the order processing without room may occur to shop, the problem of overall coverage is relatively low be present, realize and intervention processing is carried out to the order for exceeding given threshold to probability of the shop without room automatically, user is reduced to situation of the shop without room, so as to improve Consumer's Experience, brand image is lifted.
Description
Technical field
The present invention relates to grass roots marketing techniques field, more particularly to a kind of OTA (Online Travel Agent, online travelling
Society) platform is to Forecasting Methodology and system of the shop without room.
Background technology
For OTA platforms, when generation user does not have roomed situation to hotel, Consumer's Experience can be not only had a strong impact on,
Can also badly damaged OTA platforms brand image.In the prior art, in order to solve the problem, generally by following two approach come
Improve：A kind of solution way is empirically to judge whether the order can occur to shop without room by the business personnel of OTA platforms,
For that may occur directly to dock session with hotel to order of the shop without room, the mode as manually investigated.But because OTA is put down
The day order volume of platform is huge, and it is manually that impossible look after each the order without room may occur to shop to rely solely on.This
Sample, which can not only be missed, to be occurred to order of the shop without room, cause the loss of OTA platform brand images, it is also possible to can be because user
The reduction of experience causes potential customer loss.Another solution method is carried out pair using self-oriented cast net mode and hotel
Words investigation, this method can effectively be lifted compared to artificial investigation and quantity on order handled in the unit interval, and coverage rate has increased
Add, but because the day order volume because of OTA platforms is huge, for that may occur to order processing of the shop without room totally to cover
Rate is still relatively low.
The content of the invention
The technical problem to be solved in the present invention is to overcome the OTA platforms of prior art by way of manually investigating pair
It may occur to order of the shop without room to be handled, the defects of order processing overall coverage is relatively low be present, it is therefore intended that carry
For Forecasting Methodology and system of a kind of OTA platforms to shop without room.
The present invention is that solve above-mentioned technical problem by following technical proposals：
The present invention provides a kind of OTA platforms to be included to Forecasting Methodology of the shop without room, the Forecasting Methodology：
S1, after user places an order, obtain user's order data, user's order data includes user's order predetermined information
And hotel information；
S2, obtained according to user's order data corresponding with user's order data user's order tentation data,
Hotel's historical data, the price data of hotel's house type, the nervous degrees of data of hotel's house type and hotel's history are to shop without room rate data；
S3, by Decision Tree Algorithm to user's order tentation data, hotel's historical data, the hotel
The price data of house type, the nervous degrees of data of hotel's house type and hotel's history are handled to shop without room rate data,
User is established to shop without room Probabilistic Prediction Model；
S4, according to the user to shop predict that corresponding with user's order data user orders without room Probabilistic Prediction Model
Probability of the shop without room is arrived in single-shot life；
S5, judge it is described whether be more than given threshold to probability of the shop without room, when being judged as YES, the OTA platforms to
Hotel, which is sent, intervenes content.
It is preferred that the intervention content includes IVR (Interactive Voice Response, interactive voice answering)
Patrol room content and/or EBK (Ebooking, electronics subscribe menu manager) push content；
The IVR patrols room and session is docked with hotel's voice for characterizing attending a banquet for OTA platforms, and it is true that hotel carries out artificial investigation
It is fixed that user whether can occur to situation of the shop without room；
The EBK pushes sends stock's house type information, the room rate of house type corresponding to hotel for characterizing OTA platforms to hotel
Information and hotel information.
It is preferred that also include after step S5：
Judge whether the hotel overthrows, when being judged as NO, the OTA platforms are receiving user's determination modification order
Instruction after the current order of user is revised as the order of other house types or user is compensated accordingly；
It is described to overthrow for characterizing when hotel is belonged to and occurred without the prediction of room Probabilistic Prediction Model by the user to shop
When being more than the hotel of given threshold to probability of the shop without room, the hotel patrols the outgoing call inquiry in room in OTA platforms progress IVR
When to the OTA platforms send the first data message, carrying out IVR in the OTA platforms patrols after the outgoing call inquiry in room to the OTA
Platform sends the second data message；
First data message sends the information for having room to the OTA platforms for characterizing the hotel；
Second data message is used to characterize the hotel to information of the OTA platforms transmission without room.
It is preferred that also include before the step of acquisition user order data in step S1：
Judge whether the order that user places an order meets storage condition, when being judged as YES, by the order according to institute
State entry time corresponding to order and carry out storage processing；
The storage condition is used to characterize the situation that the order to have placed an order belongs to non-emergent and non-cancellation.
It is preferred that whether user's order tentation data includes being to retain room information, subscribe number of days information in advance, be predetermined
At least one of room number information, order unit price information and same period last year pricing information；
The hotel room that OTA platforms are directly sold is kept for including hotel in the reservation room；
Classes of cities data, OTA platforms where city level data, hotel where hotel's historical data includes hotel
At least one of ratings data, chain categorical data, hotel's categorical data, Hotel Star data and hotel's sales data；
The price data of hotel's house type includes the price for having directly or indirectly relation with the price of hotel's house type；
What the nervous degrees of data of hotel's house type was used to characterizing hotel sells house type in affiliated city or affiliated commercial circle
In tensity；
Hotel's history occurs to arrive shop to shop without the hotel that room rate is used to characterize in the history house data according to hotel
Number without room accounts for the ratio of same time order total amount.
The present invention also provides a kind of OTA platforms to be included first and obtains list to forecasting system of the shop without room, the forecasting system
Member, second acquisition unit, processing unit, predicting unit and the first judging unit；
The first acquisition unit is used for after user places an order, and obtains user's order data, user's order data bag
Include user's order predetermined information and hotel information；
The second acquisition unit is used for corresponding with user's order data according to user's order data acquisition
User's order tentation data, hotel's historical data, the price data of hotel's house type, the nervous degrees of data of hotel's house type and hotel are gone through
History is to shop without room rate data；
The processing unit is used for by Decision Tree Algorithm to user's order tentation data, hotel's history
Data, the price data of hotel's house type, the nervous degrees of data of hotel's house type and hotel's history are to shop without room rate
Data are handled, and establish user to shop without room Probabilistic Prediction Model；
The predicting unit is used for according to the user to shop without the prediction of room Probabilistic Prediction Model and user's order numbers
Occur to arrive probability of the shop without room according to corresponding user's order；
First judging unit be used to judging it is described whether be more than given threshold to probability of the shop without room, be judged as YES
When, the OTA platforms are sent to hotel intervenes content.
It is preferred that the content of intervening includes the content that IVR patrols the content and/or EBK push in room；
The IVR patrols room and session is docked with hotel's voice for characterizing attending a banquet for OTA platforms, and it is true that hotel carries out artificial investigation
It is fixed that user whether can occur to situation of the shop without room；
The EBK is pushed for characterizing stock's house type information, the room rate information of house type corresponding to OTA platforms to hotel's transmission
With hotel's real time information.
It is preferred that the forecasting system also includes the second judging unit；
Second judging unit is used to judge whether the hotel overthrows, and when being judged as NO, the OTA platforms are connecing
Receive and the current order of user is revised as the order of other house types after user determines the instruction of modification order or user is carried out
Corresponding compensation；
It is described to overthrow for characterizing when hotel is belonged to and occurred without the prediction of room Probabilistic Prediction Model by the user to shop
When being more than the hotel of given threshold to probability of the shop without room, the hotel patrols the outgoing call inquiry in room in OTA platforms progress IVR
When to the OTA platforms send the first data message, carrying out IVR in the OTA platforms patrols after the outgoing call inquiry in room to the OTA
Platform sends the second data message；
First data message sends the information for having room to the OTA platforms for characterizing the hotel；
Second data message is used to characterize the hotel to information of the OTA platforms transmission without room.
It is preferred that the forecasting system also includes the 3rd judging unit；
3rd judging unit is used to judge whether the order that user places an order meets storage condition, is being judged as YES
When, the order is subjected to storage processing according to entry time corresponding to the order；
The storage condition is used to characterize the situation that the order to have placed an order belongs to non-emergent and non-cancellation.
It is preferred that whether user's order tentation data includes being to retain room information, subscribe number of days information in advance, be predetermined
At least one of room number information, order unit price information and same period last year pricing information；
The hotel room that OTA platforms are directly sold is kept for including hotel in the reservation room；
Classes of cities data, OTA platforms where city level data, hotel where hotel's historical data includes hotel
At least one of ratings data, chain categorical data, hotel's categorical data, Hotel Star data and hotel's sales data；
The price data of hotel's house type includes the price for having directly or indirectly relation with the price of hotel's house type；
What the nervous degrees of data of hotel's house type was used to characterizing hotel sells house type in affiliated city or affiliated commercial circle
In tensity；
Hotel's history occurs to arrive shop to shop without the hotel that room rate is used to characterize in the history house data according to hotel
Number without room accounts for the ratio of same time order total amount.
The positive effect of the present invention is：
The present invention is placed an order by user and obtains forms data under user, user's order according to corresponding to obtaining forms data under user
Tentation data, hotel's historical data, the price data of hotel's house type, the nervous degrees of data of hotel's house type and hotel's history to shop without
Room rate data, then the data obtained by Decision Tree Algorithm more than are established to shop without room Probabilistic Prediction Model, prediction
Occur to arrive probability of the shop without room with user；When being more than given threshold to probability of the shop without room, OTA platforms are sent to hotel intervenes
Content, so as to improve in the prior art by the way of manually investigating to the order processing without room may occur to shop, deposit
Order processing overall coverage is relatively low the problem of, realizes and the order for exceeding given threshold to probability of the shop without room is carried out automatically
Intervention is handled, and is reduced user and is occurred to situation of the shop without room, so as to improve Consumer's Experience, lifts brand image.
Brief description of the drawings
Fig. 1 be embodiments of the invention 1 OTA platforms to Forecasting Methodology of the shop without room flow chart；
Fig. 2 be embodiments of the invention 2 OTA platforms to forecasting system of the shop without room structural representation.
Embodiment
The present invention is further illustrated below by the mode of embodiment, but does not therefore limit the present invention to described reality
Apply among a scope.
Embodiment 1
As shown in figure 1, for the present embodiment OTA platforms to Forecasting Methodology of the shop without room flow chart.
The OTA platforms of the present invention include to Forecasting Methodology of the shop without room：
S101, after user places an order, judge whether the order that user places an order meets storage condition, be judged as YES
When, the order is subjected to storage processing according to entry time corresponding to the order；
Wherein, the storage condition is used to characterize the situation that the order to have placed an order belongs to non-emergent and non-cancellation.
Specifically, order determines that the relation between time and order entry time is as follows：
If meet storage condition and the acknowledgement of orders time moves in the 15 of day the previous day in order:Before 00, then the order
Entry time is to move in day the previous day 17:00；If the acknowledgement of orders time for meeting storage condition moves in day the previous day in order
15:00 to moving in 16 on the day of day:Between 00, then the order entry time is 2 hours after the acknowledgement of orders time；If meet
The acknowledgement of orders time of storage condition is 16 on the day of order moves in day:00 to moving in 17 on the day of day:00, then order entry time be
Move in same day day 18:00；If meet the acknowledgement of orders time of storage condition 17 on the day of order moves in day:After 00, then order
Single entry time is the latter hour of acknowledgement of orders time.
S102, user's order data is obtained, user's order data includes user's order predetermined information and hotel information；
S103, corresponding with user's order data user's order predetermined number obtained according to user's order data
According to, the nervous degrees of data of hotel's historical data, the price data of hotel's house type, hotel's house type and hotel's history to shop without room rate number
According to；
Wherein, whether user's order tentation data includes being to retain room information, subscribe number of days information, predetermined room in advance
Between at least one of number information, order unit price information and same period last year pricing informations；
Wherein, the same period last year price refers to the price in last year in same period same house type.
The hotel room that OTA platforms are directly sold is kept for including hotel in the reservation room；
Classes of cities data, OTA platforms where city level data, hotel where hotel's historical data includes hotel
At least one of ratings data, chain categorical data, hotel's categorical data, Hotel Star data and hotel's sales data；
The price data of hotel's house type includes the price for having directly or indirectly relation with the price of hotel's house type；
Wherein, the price for having direct relation with hotel's house type price includes house type price of current order etc.；With hotel room
Type price has indirect relation to include submitting the median of order price to locate with same move in day nearest seven days of physics house type
House type price in middle price section；
What the nervous degrees of data of hotel's house type was used to characterizing hotel sells house type in affiliated city or affiliated commercial circle
In tensity；
Hotel's history occurs to arrive shop to shop without the hotel that room rate is used to characterize in the history house data according to hotel
Number without room accounts for the ratio of same time order total amount.Wherein it is possible to by occurring to arrive situation of the shop without room as user, to the use
The hotel that family is moved in is marked, so as to occur to number of the shop without room to count to the hotel.
S104, by Decision Tree Algorithm to user's order tentation data, hotel's historical data, the wine
The price data of shop house type, the nervous degrees of data of hotel's house type and hotel's history to shop without room rate data at
Reason, establishes user to shop without room Probabilistic Prediction Model；
Specifically, the first step, user's order data of acquisition is handled, forms raw data set；Second step, to original
Beginning data set carries out the data prediction operations such as data cleansing, missing values (i.e. no data) processing；3rd step, by what is handled well
Data are divided into two parts of training data and test data；4th step, training data is instructed by Decision Tree Algorithm
Practice to shop without room Probabilistic Prediction Model, will train to shop and be applied to without room Probabilistic Prediction Model in test data, instructed
Practice effect.
Wherein, it is as follows to offline compliance test result process of the shop without room Probabilistic Prediction Model：
Assuming that there is 4 orders, to predicted value of the shop without room Probabilistic Prediction Model be scores=[0.1,0.4,0.35,
0.8], forecast model actual value is that y=[0,0,1,1] (is expressed as positive sample labeled as 1, negative sample is expressed as labeled as 0
This), 0.35 is set to given threshold of the shop without room Probabilistic Prediction Model, i.e. model predication value score >=0.35 is positive sample.Such as
Shown in table 1：
Table 1
Wherein, the judicious quantity of model={ sample size of scores >=0.35 }, the wrongheaded quantity of model=
{ scores ＜ 0.35 sample size }, the really quantity of negative sample={ model actual value is for 0 }, really positive sample
Quantity={ model actual value is for 1 }.
So as to, accuracy rate=(model sentence correctly and really positive sample)/model total amount=2/ (2+1)=
66.7%；Recall rate=(model sentences correctly and really positive sample)/actual positive sample total amount=2/ (2+1)=
66.7%.Wherein, accuracy rate and recall rate are without the offline measure of effectiveness index of room Probabilistic Prediction Model to shop.
Specifically, for example, it is assumed that there are 4 order O=[O1, O2, O3, O4], occur to have 2 lists altogether to order of the shop without room,
Without room=[O3, O4], then the order whether occur that y=[0,0,1,1] can be expressed as without room to shop, now y is represented true
Value.Assuming that it is existing to shop without room Probabilistic Prediction Model variable add model after, to shop without room Probabilistic Prediction Model obtain scores
=[0.1,0.4,0.35,0.8], and forecast model to given threshold of the shop without room probability be 0.35, represent when score >=
When 0.35, the hotel is likely to occur to situation of the shop without room, when less than 0.35, is then not considered, according to scores
=[0.1,0.4,0.35,0.8] judges whether to occur to be labeled as y=[0,1,1,1] without room to shop, then that establishes is general without room to shop
The accuracy rate and recall rate of rate forecast model are 66.7%.
S105, corresponding with user's order data user predicted without room Probabilistic Prediction Model according to the user to shop
Order occurs to arrive probability of the shop without room；
Whether it is more than given threshold to probability of the shop without room described in S106, judgement, when being judged as YES, the OTA platforms
Sent to hotel and intervene content；
Wherein, the content of intervening includes the content that IVR patrols the content and/or EBK push in room；
The IVR patrols room and session is docked with hotel's voice for characterizing attending a banquet for OTA platforms, and it is true that hotel carries out artificial investigation
It is fixed that user whether can occur to situation of the shop without room；
The EBK pushes sends stock's house type information, the room rate of house type corresponding to hotel for characterizing OTA platforms to hotel
Information and hotel information.
S107, judge whether the hotel overthrows, when being judged as NO, the OTA platforms receive user determine repair
The current order of user is revised as the order of other house types after changing single instruction or user is compensated accordingly；
It is described to overthrow for characterizing when hotel is belonged to and occurred without the prediction of room Probabilistic Prediction Model by the user to shop
When being more than the hotel of given threshold to probability of the shop without room, the hotel patrols the outgoing call inquiry in room in OTA platforms progress IVR
When to the OTA platforms send the first data message, carrying out IVR in the OTA platforms patrols after the outgoing call inquiry in room to the OTA
Platform sends the second data message；
First data message sends the information for having room to the OTA platforms for characterizing the hotel；
Second data message is used to characterize the hotel to information of the OTA platforms transmission without room.
Embodiment 2
As shown in Fig. 2 the present invention also provides a kind of OTA platforms and included to forecasting system of the shop without room, the forecasting system
First acquisition unit 1, second acquisition unit 2, processing unit 3, the judging unit 5 of predicting unit 4 and first, the second judging unit 6
With the 3rd judging unit 7.
The first acquisition unit 1 is used for after user places an order, and obtains user's order data, user's order data bag
Include user's order predetermined information and hotel information；
3rd judging unit 7 is used to judge whether the order that user places an order meets storage condition, is being judged as
When being, the order is subjected to storage processing according to entry time corresponding to the order；
The storage condition is used to characterize the situation that the order to have placed an order belongs to non-emergent and non-cancellation.
Specifically, order determines that the relation between time and order entry time is as follows：
If meet storage condition and the acknowledgement of orders time moves in the 15 of day the previous day in order:Before 00, then the order
Entry time is to move in day the previous day 17:00；If the acknowledgement of orders time for meeting storage condition moves in day the previous day in order
15:00 to moving in 16 on the day of day:Between 00, then the order entry time is 2 hours after the acknowledgement of orders time；If meet
The acknowledgement of orders time of storage condition is 16 on the day of order moves in day:00 to moving in 17 on the day of day:00, then order entry time be
Move in same day day 18:00；If meet the acknowledgement of orders time of storage condition 17 on the day of order moves in day:After 00, then order
Single entry time is the latter hour of acknowledgement of orders time.
The second acquisition unit 2 is used for corresponding with user's order data according to user's order data acquisition
User's order tentation data, hotel's historical data, the price data of hotel's house type, the nervous degrees of data of hotel's house type and hotel are gone through
History is to shop without room rate data；
Wherein, whether user's order tentation data includes being to retain room information, subscribe number of days information, predetermined room in advance
Between at least one of number information, order unit price information and same period last year pricing informations；
Wherein, the same period last year price refers to the price in last year in same period same house type.
The hotel room that OTA platforms are directly sold is kept for including hotel in the reservation room；
Classes of cities data, OTA platforms where city level data, hotel where hotel's historical data includes hotel
At least one of ratings data, chain categorical data, hotel's categorical data, Hotel Star data and hotel's sales data；
The price data of hotel's house type includes the price for having directly or indirectly relation with the price of hotel's house type；
Wherein, the price for having direct relation with hotel's house type price includes house type price of current order etc.；With hotel room
Type price has indirect relation to include submitting the median of order price to locate with same move in day nearest seven days of physics house type
House type price in middle price section；
What the nervous degrees of data of hotel's house type was used to characterizing hotel sells house type in affiliated city or affiliated commercial circle
In tensity；
Hotel's history occurs to arrive shop to shop without the hotel that room rate is used to characterize in the history house data according to hotel
Number without room accounts for the ratio of same time order total amount.Wherein it is possible to by occurring to arrive situation of the shop without room as user, to the use
The hotel that family is moved in is marked, so as to occur to number of the shop without room to count to the hotel.
The processing unit 3 is used to go through user's order tentation data, the hotel by Decision Tree Algorithm
History data, the price data of hotel's house type, the nervous degrees of data of hotel's house type and hotel's history are to shop without room
Rate data are handled, and establish user to shop without room Probabilistic Prediction Model；
The predicting unit 4 is used for according to the user to shop without the prediction of room Probabilistic Prediction Model and user's order numbers
Occur to arrive probability of the shop without room according to corresponding user's order；
First judging unit 5 be used to judging it is described whether be more than given threshold to probability of the shop without room, be judged as
When being, the OTA platforms are sent to hotel intervenes content.
Wherein, the content of intervening includes the content that IVR patrols the content and/or EBK push in room；
The IVR patrols room and session is docked with hotel's voice for characterizing attending a banquet for OTA platforms, and it is true that hotel carries out artificial investigation
It is fixed that user whether can occur to situation of the shop without room；
The EBK pushes sends stock's house type information, the room rate of house type corresponding to hotel for characterizing OTA platforms to hotel
Information and hotel information.
Second judging unit 6 is used to judge whether the hotel overthrows, and when being judged as NO, the OTA platforms exist
Receive and the current order of user is revised as the order of other house types after user determines the instruction of modification order or user is entered
The corresponding compensation of row；
It is described to overthrow for characterizing when hotel is belonged to and occurred without the prediction of room Probabilistic Prediction Model by the user to shop
When being more than the hotel of given threshold to probability of the shop without room, the hotel patrols the outgoing call inquiry in room in OTA platforms progress IVR
When to the OTA platforms send the first data message, carrying out IVR in the OTA platforms patrols after the outgoing call inquiry in room to the OTA
Platform sends the second data message；
First data message sends the information for having room to the OTA platforms for characterizing the hotel；
Second data message is used to characterize the hotel to information of the OTA platforms transmission without room.
Although the foregoing describing the embodiment of the present invention, it will be appreciated by those of skill in the art that these
It is merely illustrative of, protection scope of the present invention is defined by the appended claims.Those skilled in the art is not carrying on the back
On the premise of principle and essence from the present invention, various changes or modifications can be made to these embodiments, but these are changed
Protection scope of the present invention is each fallen within modification.
Claims (10)
1. a kind of OTA platforms are to Forecasting Methodology of the shop without room, it is characterised in that the Forecasting Methodology includes：
S1, after user places an order, obtain user's order data, user's order data includes user's order predetermined information and wine
Shop information；
S2, corresponding with user's order data user's order tentation data, hotel obtained according to user's order data
Historical data, the price data of hotel's house type, the nervous degrees of data of hotel's house type and hotel's history are to shop without room rate data；
S3, by Decision Tree Algorithm to user's order tentation data, hotel's historical data, hotel's house type
Price data, hotel's house type nervous degrees of data and hotel's history handled to shop without room rate data, establish
User is to shop without room Probabilistic Prediction Model；
S4, corresponding with user's order data user's order hair predicted without room Probabilistic Prediction Model according to the user to shop
Probability of the shop without room is arrived in life；
S5, judge it is described whether be more than given threshold to probability of the shop without room, when being judged as YES, the OTA platforms are to hotel
Send and intervene content.
2. OTA platforms as claimed in claim 1 are to Forecasting Methodology of the shop without room, it is characterised in that the intervention content includes
IVR patrols the content in room and/or the content of EBK push；
The IVR patrols room and session is docked with hotel's voice for characterizing attending a banquet for OTA platforms, and hotel, which carries out artificial investigation determination, is
It is no that user can occur to situation of the shop without room；
The EBK pushes sends stock's house type information, the room rate information of house type corresponding to hotel for characterizing OTA platforms to hotel
And hotel information.
3. OTA platforms as claimed in claim 1 are to Forecasting Methodology of the shop without room, it is characterised in that also include after step S5：
Judge whether the hotel overthrows, when being judged as NO, the OTA platforms determine the finger of modification order receiving user
The current order of user is revised as the order of other house types after order or user is compensated accordingly；
Described overthrow can occur to shop for characterizing when hotel is belonged to by the user to shop without the prediction of room Probabilistic Prediction Model
Probability without room be more than given threshold hotel when, the hotel the OTA platforms carry out IVR patrol room outgoing call inquiry when to
The OTA platforms send the first data message, to the OTA platforms after OTA platforms progress IVR patrols the outgoing call inquiry in room
Send the second data message；
First data message sends the information for having room to the OTA platforms for characterizing the hotel；
Second data message is used to characterize the hotel to information of the OTA platforms transmission without room.
4. OTA platforms as claimed in claim 1 are to Forecasting Methodology of the shop without room, it is characterised in that described in step S1 is obtained
Also include before the step of taking family order data：
Judge whether the order that user places an order meets storage condition, when being judged as YES, the order is ordered according to described
Entry time corresponding to list carries out storage processing；
The storage condition is used to characterize the situation that the order to have placed an order belongs to non-emergent and non-cancellation.
5. OTA platforms as claimed in claim 1 are to Forecasting Methodology of the shop without room, it is characterised in that user's order makes a reservation for
Data are included whether to retain room information, reservation number of days information, reservation number information, order unit price information and last year are same in advance
At least one of phase pricing information；
The hotel room that OTA platforms are directly sold is kept for including hotel in the reservation room；
Classes of cities data, the grading of OTA platforms where city level data, hotel where hotel's historical data includes hotel
At least one of data, chain categorical data, hotel's categorical data, Hotel Star data and hotel's sales data；
The price data of hotel's house type includes the price for having directly or indirectly relation with the price of hotel's house type；
What the nervous degrees of data of hotel's house type was used to characterizing hotel sells house type in affiliated city or affiliated commercial circle
Tensity；
Hotel's history occurs to shop without room to shop without the hotel that room rate is used to characterize in the history house data according to hotel
Number account for the ratio of same time order total amount.
6. a kind of OTA platforms are to forecasting system of the shop without room, it is characterised in that the forecasting system include first acquisition unit,
Second acquisition unit, processing unit, predicting unit and the first judging unit；
The first acquisition unit is used for after user places an order, and obtains user's order data, and user's order data includes using
Family order predetermined information and hotel information；
The second acquisition unit is used to obtain user corresponding with user's order data according to user's order data
Order tentation data, hotel's historical data, the price data of hotel's house type, the nervous degrees of data of hotel's house type and hotel's history arrive
Shop is without room rate data；
The processing unit is used for by Decision Tree Algorithm to user's order tentation data, hotel's history number
According to, the nervous degrees of data of the price data of hotel's house type, hotel's house type and hotel's history to shop without room rate number
According to being handled, user is established to shop without room Probabilistic Prediction Model；
The predicting unit is used for according to the user to shop without the prediction of room Probabilistic Prediction Model and user's order data pair
The user's order answered occurs to probability of the shop without room；
First judging unit be used to judging it is described whether be more than given threshold to probability of the shop without room, when being judged as YES,
The OTA platforms are sent to hotel intervenes content.
7. OTA platforms as claimed in claim 6 are to forecasting system of the shop without room, it is characterised in that the intervention content includes
IVR patrols the content in room and/or the content of EBK push；
The IVR patrols room and session is docked with hotel's voice for characterizing attending a banquet for OTA platforms, and hotel, which carries out artificial investigation determination, is
It is no that user can occur to situation of the shop without room；
The EBK is pushed for characterizing stock's house type information, the room rate information of house type and wine corresponding to OTA platforms to hotel's transmission
Shop real time information.
8. OTA platforms as claimed in claim 6 are to forecasting system of the shop without room, it is characterised in that the forecasting system is also wrapped
Include the second judging unit；
Second judging unit is used to judge whether the hotel overthrows, and when being judged as NO, the OTA platforms are receiving
The current order of user is revised as the order of other house types after determining the instruction of modification order or user carried out corresponding by user
Compensation；
Described overthrow can occur to shop for characterizing when hotel is belonged to by the user to shop without the prediction of room Probabilistic Prediction Model
Probability without room be more than given threshold hotel when, the hotel the OTA platforms carry out IVR patrol room outgoing call inquiry when to
The OTA platforms send the first data message, to the OTA platforms after OTA platforms progress IVR patrols the outgoing call inquiry in room
Send the second data message；
First data message sends the information for having room to the OTA platforms for characterizing the hotel；
Second data message is used to characterize the hotel to information of the OTA platforms transmission without room.
9. OTA platforms as claimed in claim 6 are to forecasting system of the shop without room, it is characterised in that the forecasting system is also wrapped
Include the 3rd judging unit；
3rd judging unit is used to judge whether the order that user places an order meets storage condition, when being judged as YES,
The order is subjected to storage processing according to entry time corresponding to the order；
The storage condition is used to characterize the situation that the order to have placed an order belongs to non-emergent and non-cancellation.
10. OTA platforms as claimed in claim 6 are to forecasting system of the shop without room, it is characterised in that user's order makes a reservation for
Data are included whether to retain room information, reservation number of days information, reservation number information, order unit price information and last year are same in advance
At least one of phase pricing information；
The hotel room that OTA platforms are directly sold is kept for including hotel in the reservation room；
Classes of cities data, the grading of OTA platforms where city level data, hotel where hotel's historical data includes hotel
At least one of data, chain categorical data, hotel's categorical data, Hotel Star data and hotel's sales data；
The price data of hotel's house type includes the price for having directly or indirectly relation with the price of hotel's house type；
What the nervous degrees of data of hotel's house type was used to characterizing hotel sells house type in affiliated city or affiliated commercial circle
Tensity；
Hotel's history occurs to shop without room to shop without the hotel that room rate is used to characterize in the history house data according to hotel
Number account for the ratio of same time order total amount.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710919907.1A CN107506877B (en) | 2017-09-30 | 2017-09-30 | OTA platform-to-store no-room prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710919907.1A CN107506877B (en) | 2017-09-30 | 2017-09-30 | OTA platform-to-store no-room prediction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107506877A true CN107506877A (en) | 2017-12-22 |
| CN107506877B CN107506877B (en) | 2020-12-01 |
Family
ID=60700374
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710919907.1A Active CN107506877B (en) | 2017-09-30 | 2017-09-30 | OTA platform-to-store no-room prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107506877B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109376891A (en) * | 2018-11-27 | 2019-02-22 | 携程计算机技术（上海）有限公司 | The determination method and system of the full room state of people place |
| CN109685234A (en) * | 2018-12-27 | 2019-04-26 | 携程计算机技术（上海）有限公司 | The processing method and system subscribed for hotel's house type |
| CN109784848A (en) * | 2018-12-29 | 2019-05-21 | 深圳慧通商务有限公司 | Hotel's order processing method and Related product |
| CN111144598A (en) * | 2019-12-27 | 2020-05-12 | 携程计算机技术（上海）有限公司 | Prediction method of OTA reserved room reliability, model training method and system |
| CN114706862A (en) * | 2022-01-27 | 2022-07-05 | 深圳市天下房仓科技有限公司 | Hotel room state prediction method, device, equipment and storage medium |
| CN116402587A (en) * | 2023-05-26 | 2023-07-07 | 浙江飞猪网络技术有限公司 | House type upgrading method, device and medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106204063A (en) * | 2016-06-30 | 2016-12-07 | 北京奇艺世纪科技有限公司 | A kind of paying customer's method for digging and device |
| CN106780173A (en) * | 2016-12-01 | 2017-05-31 | 携程计算机技术（上海）有限公司 | OTA hotels inventory management method and system |
-
2017
- 2017-09-30 CN CN201710919907.1A patent/CN107506877B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106204063A (en) * | 2016-06-30 | 2016-12-07 | 北京奇艺世纪科技有限公司 | A kind of paying customer's method for digging and device |
| CN106780173A (en) * | 2016-12-01 | 2017-05-31 | 携程计算机技术（上海）有限公司 | OTA hotels inventory management method and system |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109376891A (en) * | 2018-11-27 | 2019-02-22 | 携程计算机技术（上海）有限公司 | The determination method and system of the full room state of people place |
| CN109376891B (en) * | 2018-11-27 | 2022-06-21 | 携程计算机技术（上海）有限公司 | Method and system for determining full house state of residential accommodation |
| CN109685234A (en) * | 2018-12-27 | 2019-04-26 | 携程计算机技术（上海）有限公司 | The processing method and system subscribed for hotel's house type |
| CN109685234B (en) * | 2018-12-27 | 2023-09-05 | 携程计算机技术（上海）有限公司 | Processing method and system for hotel room reservation |
| CN109784848A (en) * | 2018-12-29 | 2019-05-21 | 深圳慧通商务有限公司 | Hotel's order processing method and Related product |
| CN109784848B (en) * | 2018-12-29 | 2021-08-27 | 南京意博软件科技有限公司 | Hotel order processing method and related product |
| CN111144598A (en) * | 2019-12-27 | 2020-05-12 | 携程计算机技术（上海）有限公司 | Prediction method of OTA reserved room reliability, model training method and system |
| CN114706862A (en) * | 2022-01-27 | 2022-07-05 | 深圳市天下房仓科技有限公司 | Hotel room state prediction method, device, equipment and storage medium |
| CN114706862B (en) * | 2022-01-27 | 2022-11-15 | 深圳市天下房仓科技有限公司 | Hotel room state prediction method, device, equipment and storage medium |
| CN116402587A (en) * | 2023-05-26 | 2023-07-07 | 浙江飞猪网络技术有限公司 | House type upgrading method, device and medium |
| CN116402587B (en) * | 2023-05-26 | 2023-09-26 | 浙江飞猪网络技术有限公司 | House type upgrading method, device and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107506877B (en) | 2020-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107506877A (en) | OTA platforms are to Forecasting Methodology and system of the shop without room | |
| CN107844915B (en) | Automatic scheduling method of call center based on traffic prediction | |
| CN107679674B (en) | OTA platform overseas hotel room type service defect prediction method and system | |
| CN106097043B (en) | The processing method and server of a kind of credit data | |
| US11514271B2 (en) | System and method for automatically adjusting strategies | |
| CN104834983B (en) | Business data processing method and device | |
| CN106846041A (en) | The distribution method and system of reward voucher | |
| CN110147803B (en) | User loss early warning processing method and device | |
| CN108629379A (en) | A kind of individual's reference appraisal procedure and system | |
| CN107730019A (en) | User based on user's portrait retrieves method and system | |
| CN110490646A (en) | The determination method and device of automobile brand target user | |
| CN108491480A (en) | Rumour detection method and equipment | |
| CN110796578A (en) | Judgment method and device for grading rescue, computer equipment and storage medium | |
| CN111091460B (en) | Data processing method and device | |
| CN107798522A (en) | A kind of fare pays out method and device | |
| CN113706172B (en) | Customer behavior-based complaint solving method, device, equipment and storage medium | |
| CN107977825A (en) | A kind of method and device for distributing Service events | |
| CN113726963B (en) | Intelligent outbound harassment prevention method, device, equipment and medium | |
| CN113379497B (en) | Order regulation method, order regulation device, computer equipment and computer readable storage medium | |
| CN111353015A (en) | Crowdsourcing question recommendation method, device, equipment and storage medium | |
| CN115147156A (en) | Advertisement accurate delivery method based on neural network | |
| CN114596105A (en) | Method, device, equipment and medium for evaluating credit of charging user | |
| CN113723663A (en) | Power work order data processing method and device, electronic equipment and storage medium | |
| CN113554204A (en) | Method, device, storage medium and electronic equipment for determining event probability | |
| CN112101002B (en) | Big data based case situation perception early warning method, measure recommendation method and device and terminal equipment |
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 |