Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

OTA reservation house reliability prediction method, model training method and system

A model training and reliability technology, applied in the field of computer information, can solve the problems of unreliability of reserved rooms and poor user experience, and achieve the effect of improving user experience and reducing service defects

Pending Publication Date: 2020-05-12
CTRIP COMP TECH SHANGHAI
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to overcome the defect in the prior art that user orders cannot be confirmed due to the unreliability of the reserved room, which leads to poor user experience, and to provide a method that can predict the reliability of the reserved room in time to improve the user's experience. Model training method, training system, prediction method, prediction system, electronic equipment and storage medium for OTA reserved room reliability prediction of OTA reserved room reliability based on room reservation experience

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • OTA reservation house reliability prediction method, model training method and system
  • OTA reservation house reliability prediction method, model training method and system
  • OTA reservation house reliability prediction method, model training method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] This embodiment provides a model training method for predicting the reliability of an OTA reserved room, figure 1 A flowchart of the model training method is shown, including:

[0066] Step 101, obtaining historical orders of reserved rooms on the OTA website.

[0067] Step 102, judging whether the reservation of the reserved room in the historical order is successful, if not, execute step 103, and if yes, execute step 104.

[0068] Step 103, label the historical order as a first probability value.

[0069] Step 104, label the historical order as a second probability value.

[0070] Step 105. Divide the tagged historical orders into a training set and a test set.

[0071] Step 106: Input the historical orders in the training set and the first probability value or the second probability value of the corresponding mark into the deep machine learning model for training.

[0072] Step 107: Input the historical orders in the test set into the trained deep machine learnin...

Embodiment 2

[0087] This embodiment provides a method for predicting the reliability of an OTA reserved room, figure 2 A flowchart showing the forecasting method, including:

[0088] Step 201, obtaining the room type number and check-in date corresponding to the reserved room.

[0089] Step 202: Input the room type number and check-in date of the reserved room into the reliability prediction model to obtain the predicted risk value of the reserved room.

[0090] Step 203 , judging whether the predicted risk value is greater than a risk threshold, if so, execute step 204 , if not, execute step 205 .

[0091] Step 204, confirming that the reserved room of the said room type is unreliable.

[0092] Step 205, confirming that the reserved room of the said room type is reliable.

[0093] Wherein, the reliability prediction model is trained by the model training method in Embodiment 1.

[0094] In order to prevent problems before they happen, to prevent the user from unsuccessfully booking a...

Embodiment 3

[0100] This embodiment provides a model training system for predicting the reliability of an OTA reserved room, image 3 A schematic diagram of the modules of the model training system in this embodiment is shown, including: a historical order acquisition module 301 , a historical reservation judgment module 302 , a division module 303 , a training module 304 , a prediction module 305 and an evaluation index judgment module 306 .

[0101] The historical order obtaining module 301 is used to obtain the historical orders of reserved rooms in the OTA website, and the historical orders include historical room type numbers and historical check-in dates.

[0102]The historical reservation judging module 302 is used to judge whether the reservation of the reserved room in the historical order is successful, if not, then label the historical order as the first probability value, and if so, label the historical order as the first probability value. Two probability values.

[0103] The...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a model training method, a training system, a prediction method, a prediction system, an electronic device and a storage medium for OTA reserved house reliability prediction. The model training method comprises the steps of obtaining a historical order of a reserved house; judging whether the reserved house in the historical order is successfully reserved or not, and labeling the historical order according to a judgment result; dividing the labeled historical orders into a training set and a test set; inputting the training set into a deep machine learning model for training; inputting the test set into the trained deep machine learning model to obtain a predicted risk value; judging whether the evaluation index of the prediction risk value reaches an evaluation threshold value or not; according to the method, the reliability degree of the reserved house can be predicted in advance, the reserved house which is low in reliability degree and high in service defectrisk can be found out to take preventive measures in advance, and therefore the purposes of reducing service defects and improving user experience are achieved.

Description

technical field [0001] The present invention relates to the field of computer information technology, in particular to a model training method, a training system, a method for predicting the reliability of an OTA reserved room, a prediction system, electronic equipment and a storage medium for predicting the reliability of an OTA reserved room. Background technique [0002] There is a commodity called "reserved room" in the OTA (Online Travel Agency) industry. Specifically, the OTA and the hotel sign a cooperation agreement. Within a certain period of time, if a user places an order to book these rooms through OTA and meets the conditions stipulated in the agreement, the hotel should ensure that there are still remaining rooms available to the user, which is the so-called "reservation" for the OTA. Different from other sales resources that need to be manually confirmed by the hotel after the user makes a reservation, for reserved rooms, there are usually remaining rooms and ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/02G06Q10/04G06Q50/12G06Q50/14G06K9/62G06N3/04
CPCG06Q10/02G06Q10/04G06Q50/12G06Q50/14G06N3/045G06F18/24323
Inventor 黎建辉周振伟胡泓
Owner CTRIP COMP TECH SHANGHAI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com