CN113011668A - Hotel room price adjusting system and method based on machine learning and computer device - Google Patents

Hotel room price adjusting system and method based on machine learning and computer device Download PDF

Info

Publication number
CN113011668A
CN113011668A CN202110338492.5A CN202110338492A CN113011668A CN 113011668 A CN113011668 A CN 113011668A CN 202110338492 A CN202110338492 A CN 202110338492A CN 113011668 A CN113011668 A CN 113011668A
Authority
CN
China
Prior art keywords
hotel
price
room
pricing
month
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110338492.5A
Other languages
Chinese (zh)
Inventor
曾玲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN202110338492.5A priority Critical patent/CN113011668A/en
Publication of CN113011668A publication Critical patent/CN113011668A/en
Pending legal-status Critical Current

Links

Images

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
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0206—Price or cost determination based on market factors
    • 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/12—Hotels or restaurants

Abstract

The invention discloses a hotel room price adjusting system, a method and a computer device based on machine learning, wherein the method comprises the steps of determining the hotel grade of a current pricing hotel and the monthly and weekly basic price of each room type of the hotel with the highest peer income; determining a month coefficient ratio and a week coefficient ratio according to the price of each day per month and each day of each house type in the hotels with the highest peer income, wherein the month coefficient ratio is implemented as the ratio of the average price of the hotel with the highest peer income in the month in which the house type rents and the average price of the hotel with the highest peer income in any month before the house type rents, and the week coefficient is implemented as the ratio of the average price of the hotel with the highest peer income in the week in which the month is located and the average price of the hotel with the highest peer income in any week before the house type rents; and determining the house type and pricing time of the hotel priced currently.

Description

Hotel room price adjusting system and method based on machine learning and computer device
Technical Field
The invention relates to a hotel room price adjusting method, in particular to a hotel room price adjusting system and method based on machine learning and a computer device.
Background
With the development of the times, globalization of goods or services is increasingly intensified. The price of goods or services of different quality varies greatly. While for providers of goods or services, maximization of profit is basically required. But maximizing profit corresponds to high pricing and low cost of goods or services. The low cost generally corresponds to low quality, so it is difficult to stimulate the consumers to purchase the corresponding goods or receive the corresponding services.
Hotels provide living convenience for distant users. But as a manager of hotels, benefit maximization is always the goal they pursue. However, when the existing hotel rents and prices hotel rooms, other hotels are referenced blindly, and the existing hotel is unscientific, systematical, lack of effectiveness, instantaneity and stability. It is therefore the price that is built up after adjustment that does not maximize the revenue for the corresponding hotel. Only a few hotel managers of a hotel adjust the rental price of the hotel room through their own experience. However, the immediacy of such manual intervention is not enough, and the error of the manual intervention is very large. As such, the revenue for the hotel is not maximized.
Disclosure of Invention
One advantage of the present invention is to provide a machine learning-based hotel room pricing system network selling method and a computer device, wherein the machine learning-based hotel room pricing system can adjust the price of hotel rooms timely and scientifically.
Another advantage of the present invention is to provide a hotel room pricing system, method and computer apparatus based on machine learning, wherein the hotel room pricing system based on machine learning can automatically adjust the set threshold based on machine learning, thereby making hotel room pricing more suitable for increasing hotel income.
Another advantage of the present invention is to provide a hotel room price adjustment system, method and computer device based on machine learning, wherein the hotel room price adjustment system based on machine learning does not require a hotel manager to modify a hotel, so that the hotel can increase the income of the hotel without increasing the cost.
Another advantage of the present invention is to provide a hotel room pricing system, method and computer apparatus based on machine learning, wherein the hotel room pricing system based on machine learning can increase the income of the hotel economically and effectively.
Another advantage of the present invention is to provide a hotel room price adjusting system, method and computer device based on machine learning, wherein the hotel room price adjusting system based on machine learning can provide a basis for automatically adjusting the price of a hotel, so that the adjusted price of the hotel is competitive, and a manager of the hotel gets a higher profit.
Another advantage of the present invention is to provide a hotel room price adjustment system, method and computer device based on machine learning, wherein the hotel price predicted by the hotel room price adjustment system based on machine learning method can be automatically adjusted online, so that the final hotel price can be updated in real time.
In order to achieve the advantages, the invention provides a hotel room price adjusting method based on machine learning, which comprises the following steps:
s1; determining a basic price of a current pricing hotel;
s2; determining a month coefficient ratio and a week coefficient ratio according to the price of each day per month and week of each house type in the hotel with the highest peer income in the same area as the current hotel, wherein the month coefficient ratio is implemented as the ratio of the average price of the hotel with the highest peer income in the month in which the house type is rented to the average price of the hotel with the highest peer income in any month before the house type is rented, and the week coefficient ratio is implemented as the ratio of the average price of the hotel with the highest peer income in the week in which the month is located in pricing to the average price of the hotel with the highest peer income in any week before the house type is rented;
s3; and according to the determined house type and the pricing time of the current pricing hotel, taking the product of the determined monthly coefficient ratio, the determined weekly coefficient ratio and the monthly basic price of each house type of the hotel with the highest peer income as the daily basic price of the corresponding house type of the current hotel.
According to an embodiment of the present invention, in the step S1, determining the hotel grade of the currently priced hotel comprises the following steps:
the determination is made by assigning a rating value to at least one of pricing of a hotel room type, a rating of a competitor, a geographical location, a freshness of the hotel, an investment, and a human-room ratio (number of service persons corresponding to each room).
According to an embodiment of the present invention, in the step S2, the month coefficient ratio is implemented as a ratio of an average price of the hotel with highest peer income in the month in which the house type rental is located to an average price of the hotel with highest peer income in the month of the year 1, wherein the week coefficient is implemented as a ratio of an average price of the hotel with highest peer income in the week in which the month is located to an average price of the hotel with highest peer income on any monday before the house type rental is priced.
According to an embodiment of the invention, the price adjusting method for hotel rooms based on machine learning comprises the following steps:
s4; determining whether influence factors and influence rates influencing the current hotel base price exist or not;
s5; modifying the base price of step S3 according to the determined influencing factors and influencing factors.
According to an embodiment of the present invention, the step S4 of determining whether there are influencing factors and influencing factors influencing the current hotel base price includes the following steps:
s41: determining whether meeting activities exist in the area where the current hotel is located or not and determining the influence rate of the meeting activities;
s42: determining whether the pricing day of the area where the current hotel is located is a holiday and the influence rate of the holiday;
step S5; modifying the base price of step S3 according to the determined impact factors and impact rates includes:
s51; comparing the impact rates of the conference activity and the holiday determined in the step S41 and the step S42, respectively;
s52; modifying the base price by taking the product of the maximum value and the base price determined in the above step S3 as an embedded price.
According to an embodiment of the present invention, the influencing factors include an empty room rate, and the step S4 determining whether the influencing factors and the influencing rates influencing the current hotel base price exist includes the following steps:
s43: determining the size relation between the empty room rate of the house type currently scheduled in a preset time period before the house type is initially checked and a set threshold, wherein the empty room rate refers to the ratio of the number of rooms which are not currently scheduled to the total number of the rooms of the house type;
step S5; modifying the base price of step S3 according to the determined impact factors and impact rates includes:
s53, when the empty rate is lower than the threshold value, increasing the basic price of the hotel; when the empty rate is higher than the threshold value, the basic price of the hotel is reduced.
According to an embodiment of the present invention, the influencing factor includes the progress of the sale, and the step S4 of determining whether the progress of the sale is lower than the threshold value includes the steps of:
s43: determining a sale speed in each time period of the house type of the current scheduled date of the earliest stay and a speed threshold set in each time period, wherein the sale speed is implemented by the number of times of the house type scheduled in each unit time;
accordingly, step S5; modifying the base price of step S3 according to the determined impact factors and impact rates includes:
s54, when the sale speed is lower than the speed threshold value, reducing the basic price of the hotel; and when the empty room rate is higher than the threshold value, improving the basic price of the hotel.
According to another aspect of the present invention, a computer apparatus is disclosed, the computer apparatus comprising a memory and a processor, the memory storing a computer program, the computer program, when executed by the processor, causing the processor to perform the above mentioned method of price adjustment for hotel rooms based on machine learning.
According to another aspect of the present invention, the present invention discloses a hotel room price adjustment system, comprising:
the data acquisition module is set to be capable of acquiring data of all hotels and related data of current hotels so as to determine the basic price of the current hotels;
an analysis module communicatively coupled to the data collection module, wherein the analysis module is configured to determine a basic monthly and weekly price for the current priced hotel tier and the hotel type with the highest peer revenue based on the collected data, and determining the monthly coefficient ratio and the weekly coefficient ratio according to the price of each house type in the hotel with the highest profit at the same level, wherein the month coefficient ratio is implemented as a ratio of an average price of the highest sibling hotel for the month at which the room-type rental was made to an average price of the highest sibling hotel for any one month prior to the room-type rental, wherein the week coefficient is implemented as a ratio of an average price of the hotel with the highest peer income for the week on which the month is located at the time of pricing to an average price of the hotel with the highest peer income for any one week before the house type renting; and
and the pricing module is set to take the product of the determined monthly coefficient proportion, the determined weekly coefficient proportion and the monthly basic price of each room type of the hotel with the highest peer income as the daily basic price of the corresponding room type of the current hotel according to the determined room type and the pricing time of the current pricing hotel.
According to an embodiment of the present invention, the hotel room pricing system further includes a modification module, the pricing module is configured to determine whether there are influencing factors and influencing rates influencing the current hotel base price, and the modification module is configured to modify the base price formed by the pricing module according to the determined influencing factors and influencing rates.
Drawings
Fig. 1 shows a flow chart of the pricing method for hotel rooms based on machine learning.
Fig. 2 shows a block diagram of the hotel room pricing system based on machine learning.
Detailed Description
The following description is presented to disclose the invention so as to enable any person skilled in the art to practice the invention. The preferred embodiments in the following description are given by way of example only, and other obvious variations will occur to those skilled in the art. The basic principles of the invention, as defined in the following description, may be applied to other embodiments, variations, modifications, equivalents, and other technical solutions without departing from the spirit and scope of the invention.
It will be understood by those skilled in the art that in the present disclosure, the terms "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like are used in an orientation or positional relationship indicated in the drawings for ease of description and simplicity of description, and do not indicate or imply that the referenced devices or components must be in a particular orientation, constructed and operated in a particular orientation, and thus the above terms are not to be construed as limiting the present invention.
It is understood that the terms "a" and "an" should be interpreted as meaning that a number of one element or element is one in one embodiment, while a number of other elements is one in another embodiment, and the terms "a" and "an" should not be interpreted as limiting the number.
Referring to fig. 1 to 2, a machine learning-based hotel room pricing system, a method and a computer device according to a preferred embodiment of the present invention will be described in detail below, wherein the machine learning-based hotel room pricing system is configured to estimate prices of each room type of a hotel so as to be able to automatically adjust prices appropriately according to the result predicted by the machine learning-based hotel room pricing system.
The hotel room price adjusting method based on machine learning comprises the following steps:
s1; determining the basic price of each house type of the current pricing hotel;
s2; determining a month coefficient ratio and a week coefficient ratio according to the price of each day per month and week of each house type in the hotel with the highest peer income in the same area as the current hotel, wherein the month coefficient ratio is implemented as the ratio of the average price of the hotel with the highest peer income in the month when the house type is rented to the average price of the hotel with the highest peer income in any month before the house type is rented, and the week coefficient is implemented as the ratio of the average price of the hotel with the highest peer income in the week when the month is used to be priced to the average price of the hotel with the highest peer income in any week before the house type is rented;
s3; and according to the determined house type and the pricing time of the current pricing hotel, taking the product of the determined monthly coefficient ratio, the determined weekly coefficient ratio and the monthly basic price of each house type of the hotel with the highest peer income as the daily basic price of the corresponding house type of the current hotel.
Preferably, in step S1, the basic price for each room type of the current hotel is determined by determining the grade of the current hotel and the basic price for each room type of the hotel with the highest peer income per month and week.
It is worth mentioning that determining the hotel rating of the currently priced hotel comprises the steps of:
the determination is made by assigning a rating value to at least one of pricing of a hotel room type, a rating of a competitor, a geographical location, a freshness of the hotel, an investment, and a human-room ratio (number of service persons corresponding to each room).
It is also worth mentioning that data related to hotel room prices can be collected to determine the current hotel level of the hotel, where the data related to hotel room prices include, but are not limited to, hotel level, hotel type (regional, out-of-hotel, comprehensive, etc.), room type, zip code of the area where the hotel is located, city, hotel type. The acquisition mode is that the crawler can be used for downloading the contemporaneous price of the peripheral hotel, the establishment time of the hotel, the overhaul time of the hotel, the allocation proportion of the hotel personnel and rooms, and the average score of the hotel in the past three months such as distance carrying, beauty group and the like on a large-scale three-party platform and the latest one month, the contemporaneous room price of the hotel is inspected, the contemporaneous room price of the hotel is taken as a variable and other factors are taken as independent variables, different data models such as but not limited to a multivariate linear regression model, a random forest, a decision tree, XGboost and Light GBM are established by using data collected by computer learning analysis, and the optimal model for determining the price of the hotel and the price factor which is most important to the price of the hotel are found and applied to the hotel price strategy in the text.
It is more worth mentioning that, in the step S2, the month coefficient ratio is implemented as a ratio of an average price of the hotel with the highest peer income in the month in which the house type rental is located to an average price of the hotel with the highest peer income in the month of the year 1, wherein the week coefficient ratio is implemented as a ratio of an average price of the hotel with the highest peer income in the week in which the month is located to an average price of the hotel with the highest peer income in any monday before the house type rental is priced.
For example, in one example, the current hotel is level 7, and the day that needs to be priced is tuesday of february, while the average prices for AA house type january and february of the determined highest revenue peer hotel are: 112. 128, and the average prices for monday and tuesday in february are: 112. 130. Similarly, the monthly coefficient ratio for february is 128/112 and the weekly coefficient for tuesday is 130/112.
Determining the base price of the current hotel in this manner enables the price of the current hotel to be better suited to the pricing of the hotel price with the best revenue class, which potentially enables the price acceptance of the current hotel to be higher.
It is also worth mentioning that the price adjustment method for hotel rooms based on machine learning comprises the following steps:
s4; determining whether influence factors and influence rates influencing the basic price of the current hotel exist in the same area of the current hotel;
s5; modifying the base price of step S3 according to the determined influencing factors and influencing factors.
It is worth mentioning that the influencing factors include, but are not limited to: whether meeting activities exist in the area where the current hotel is located, whether the pricing day of the area where the current hotel is located is a holiday, whether the vacant house rate is higher than a threshold value or whether the sales progress is lower than the threshold value, and the like.
Specifically, the step S4 of determining whether there are influencing factors and influencing factors influencing the current hotel base price includes the following steps:
s41: and determining whether meeting activities exist in the same area with the current hotel or not and determining the influence rate of the meeting activities.
It can be understood that, whether a large exhibition exists in the current area, the scale of the exhibition, the number of persons participating in the exhibition, whether activities similar to marathon exist, the number of persons participating in the conference, and the like can be obtained from specific network data, so as to determine whether conference activities exist.
And the influence rate of the conference activities is determined by comparing the number of the conference activities, the influence scale of the conference activities, whether the hotel is in the busiest season, and the like with the influence rate threshold of the conference activities. For example, the number of people in the meeting activity is less than 500, the pricing date is not the busiest season of the hotel, the influence scale of the meeting is small and defined as level 1, and the corresponding influence rate is defined as 100%; the number of people for the conference activity 1000- > 2000 is defined as level 2, and the corresponding impact rate is defined as 120%. If there is a level 2 meeting activity on the current hotel lease pricing date, the modified current hotel price is the product of the base price and the impact rate defined as 120%. Preferably, the impact rate threshold associated with setting the meeting activity is repeatedly redefinable by the industrial value created. For example, line statistical ranking can be performed through review in the local area over the past year, with the created industrial value as the ranking, the top 20% being defined as large, 21% to 70% as medium, and the remainder as small. If there are 10 meetings, the production value is from large to small, the first two scales are defined as large, 3-7, and 8-10 small.
Preferably, the step S4 of determining whether there are influencing factors and influencing rates influencing the current hotel base price includes the following steps:
s42: and determining whether the pricing day in the same area with the current hotel is a holiday and the influence rate of the holiday. Similarly, whether the current hotel area is priced as a holiday or not can be acquired in a specific network platform. And, the influence rate of the holiday can also be determined by the number of days of the holiday, the distance value between the current hotel and a specific location (such as a tourist area, a city center, a railway station, etc.), and the like.
It is worth mentioning that the influence rate of the holidays can be determined by a preset influence rate threshold of the holidays. More particularly, the holiday impact rate threshold may be repeatedly redefined by the enthusiasm of the market target population for the holiday. For example, after the current hotel operation is performed for a preset time, statistical analysis can be performed on the ages of the staff who live in holidays in the past year, wherein the ages are 18-30 years old, 30-50 years old and more than 50 years old, and the three groups are respectively in certain proportion, wherein 70% or more of any group is ultrahigh, 40-69% is high, 20-39% is medium and less than 20% is low.
Preferably, step S5; modifying the base price of step S3 according to the determined impact factors and impact rates includes:
s51; comparing the impact rates of the conference activity and the holiday determined in the step S41 and the step S42, respectively;
s52; modifying the base price by taking the product of the maximum value and the base price determined in the above step S3 as an embedded price.
It is worth mentioning that by the above mode, the basic price is modified, so that not only can the final price pricing of the current hotel be more reasonable, but also the price of the current hotel can be adjusted according to the change of the influence factors.
Further, the step S4 of determining whether there are influencing factors and influencing rates influencing the current hotel base price includes the following steps:
s43: and determining the size relation between the empty room rate of the house type currently scheduled in a preset time period before the house type is initially checked in and a set threshold value, wherein the empty room rate refers to the ratio of the rooms not currently scheduled to the total number of the rooms of the house type.
Accordingly, step S5; modifying the base price of step S3 according to the determined impact factors and impact rates includes:
s53, when the empty rate is lower than the threshold value, increasing the basic price of the hotel; when the empty rate is higher than the threshold value, the basic price of the hotel is reduced.
Preferably, said predetermined time period prior to the earliest stay of the type of house currently reserved is implemented as at least one week. It can be understood that by controlling the empty room amount of the same type of room before the user first enters the same type of room, the situation that most of the rooms are sold at low price and the subsequent same type of room can be sold at high price but no room is sold can be effectively prevented.
Further, the step S4 of determining whether the progress of the sale is lower than the threshold value includes the steps of:
s43: determining a sale speed in each time period of the house type of the current scheduled date of the earliest stay and a speed threshold set in each time period, wherein the sale speed is implemented by the number of times of the house type scheduled in each unit time;
accordingly, step S5; modifying the base price of step S3 according to the determined impact factors and impact rates includes:
s54, when the sale speed is lower than the speed threshold value, reducing the basic price of the hotel; and when the empty room rate is higher than the threshold value, improving the basic price of the hotel.
According to another aspect of the invention, the invention also provides a computer arrangement comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to carry out the steps of the method of: determining the hotel grade of the current pricing hotel and the basic monthly and weekly price of each room type of the hotel with the highest peer income; determining a month coefficient ratio and a week coefficient ratio according to the price of each day per month and week of each house type in the hotels with the highest peer income, wherein the month coefficient ratio is implemented as the ratio of the average price of the hotel with the highest peer income in the month in which the house type rents and the average price of the hotel with the highest peer income in any month before the house type rents the house type, and the week coefficient is implemented as the ratio of the average price of the hotel with the highest peer income in the week in which the month exists in which the house type rents the house type and the average price of the hotel with the highest peer income in any week before the house type rents the house type; and according to the determined house type and the pricing time of the current pricing hotel, taking the product of the determined month coefficient and week coefficient and the monthly and weekly basic price of each house type of the hotel with the highest peer income as the basic price of the current hotel on the day corresponding to the house type.
According to another aspect of the present invention, the present invention further provides a hotel room pricing system, wherein the hotel room pricing system comprises a data collecting module 10, an analyzing module 20 and a pricing module 30.
The data acquisition module 10 is configured to acquire data of all hotels and data related to the current hotel. The analysis module 20 is communicably connected to the data collection module 10, wherein the analysis module 20 is configured to determine, according to the collected data, a hotel class of the currently priced hotel and a basic monthly and weekly price of each room type of the hotel with the highest peer income, and determine a month coefficient ratio and a week coefficient ratio according to a price per month and each day per month of each room type of the hotel with the highest peer income, wherein the month coefficient ratio is implemented as a ratio of an average price of the hotel with the highest peer income in the month in which the room type is rented to an average price of the hotel with the highest peer income in any month before the room type is rented, and wherein the week coefficient is implemented as a ratio of an average price of the hotel with the highest peer income in the week in which the month is located at the time of pricing to an average price of the hotel with the highest peer income in any one week before the room type is rented.
The pricing module 30 is configured to take the product of the determined month coefficient and week coefficient and the monthly and weekly basic price of each room type of the hotel with the highest peer profit as the daily basic price of the current hotel corresponding to the room type according to the determined room type and the pricing time of the current pricing hotel.
Still further, the pricing module 30 is configured to determine whether there are influencing factors and influencing factors that influence the current hotel base price. The hotel room pricing system further includes a modification module 40. The modification module 40 is configured to modify the base price formed by the pricing module 30 based on the determined influencing factors and influencing rates.
It is worth mentioning that the influencing factors include, but are not limited to: whether meeting activities exist in the area where the current hotel is located, whether the pricing day of the area where the current hotel is located is a holiday, whether the vacant house rate is higher than a threshold value or whether the sales progress is lower than the threshold value, and the like.
It will be appreciated by persons skilled in the art that the embodiments of the invention described above and shown in the drawings are given by way of example only and are not limiting of the invention. The advantages of the present invention have been fully and effectively realized. The functional and structural principles of the present invention have been shown and described in the examples, and any variations or modifications of the embodiments of the present invention may be made without departing from the principles.

Claims (10)

1. A hotel room price adjusting method based on machine learning is characterized by comprising the following steps:
s1; determining a basic price of a current pricing hotel;
s2; determining a month coefficient ratio and a week coefficient ratio according to the price of each day per month and week of each house type in the hotel with the highest peer income in the same area as the current hotel, wherein the month coefficient ratio is implemented as the ratio of the average price of the hotel with the highest peer income in the month in which the house type is rented to the average price of the hotel with the highest peer income in any month before the house type is rented, and the week coefficient ratio is implemented as the ratio of the average price of the hotel with the highest peer income in the week in which the month is located in pricing to the average price of the hotel with the highest peer income in any week before the house type is rented;
s3; and according to the determined house type and the pricing time of the current pricing hotel, taking the product of the determined monthly coefficient ratio, the determined weekly coefficient ratio and the monthly basic price of each house type of the hotel with the highest peer income as the daily basic price of the corresponding house type of the current hotel.
2. The machine learning-based hotel room pricing method of claim 1, wherein in the step S1, determining the hotel grade of the currently priced hotel comprises the steps of:
the determination is made by assigning a rating value to at least one of pricing of a hotel room type, a rating of a competitor, a geographical location, a freshness of the hotel, an investment, and a human-room ratio (number of service persons corresponding to each room).
3. The machine-learning-based hotel room pricing method of claim 1, wherein in the step S2, a month coefficient ratio is implemented as a ratio of an average price of a hotel with highest peer income in a month when a house type rental is located to an average price of a hotel with highest peer income in a month of the year 1, wherein a week coefficient is implemented as a ratio of an average price of a hotel with highest peer income in a week when a month is located to an average price of a hotel with highest peer income on any monday before the house type rental.
4. The machine learning-based hotel room pricing method of claim 1, wherein the machine learning-based hotel room pricing method comprises the steps of:
s4; determining whether influence factors and influence rates influencing the basic price of the current hotel exist in the same area of the current hotel;
s5; modifying the base price of step S3 according to the determined influencing factors and influencing factors.
5. The machine learning-based hotel room pricing method of claim 4, wherein the step S4 determining whether there are influencing factors and influencing rates influencing the current hotel base price comprises the steps of:
s41: determining whether meeting activities and the influence rate of the meeting activities exist in the same area with the current hotel;
s42: determining whether the pricing day in the same area as the current hotel is a holiday and the influence rate of the holiday;
step S5; modifying the base price of step S3 according to the determined impact factors and impact rates includes:
s51; comparing the impact rates of the conference activity and the holiday determined in the step S41 and the step S42, respectively;
s52; modifying the base price by taking the product of the maximum value and the base price determined in the above step S3 as an embedded price.
6. The machine learning-based hotel room pricing method of claim 4, wherein the influencing factors include a vacant room rate, and the step S4 determining whether the influencing factors and the influencing rates influencing the current hotel base price exist comprises the steps of:
s43: determining the size relation between the empty room rate of the house type currently scheduled in a preset time period before the house type is initially checked and a set threshold, wherein the empty room rate refers to the ratio of the number of rooms which are not currently scheduled to the total number of the rooms of the house type;
step S5; modifying the base price of step S3 according to the determined impact factors and impact rates includes:
s53, when the empty rate is lower than the threshold value, increasing the basic price of the hotel; when the empty rate is higher than the threshold value, the basic price of the hotel is reduced.
7. The machine-learning based hotel room pricing method of claim 4, wherein the influencing factor comprises a progress of sales, the step S4 determining whether the progress of sales is below a threshold value comprises the steps of:
s43: determining a sale speed in each time period of the house type of the current scheduled date of the earliest stay and a speed threshold set in each time period, wherein the sale speed is implemented by the number of times of the house type scheduled in each unit time;
accordingly, step S5; modifying the base price of step S3 according to the determined impact factors and impact rates includes:
s54, when the sale speed is lower than the speed threshold value, reducing the basic price of the hotel; and when the empty room rate is higher than the threshold value, improving the basic price of the hotel.
8. A computer arrangement, characterized in that the computer arrangement comprises a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to carry out the method of price adjustment of a machine learning based hotel room as claimed in any one of the claims 1 to 8.
9. A hotel room pricing system, the hotel room pricing system comprising:
the data acquisition module is set to be capable of acquiring data of all hotels and related data of current hotels so as to determine the basic price of the current hotels;
an analysis module communicatively coupled to the data collection module, wherein the analysis module is configured to determine a basic monthly and weekly price for the current priced hotel tier and the hotel type with the highest peer revenue based on the collected data, and determining the monthly coefficient ratio and the weekly coefficient ratio according to the price of each house type in the hotel with the highest profit at the same level, wherein the month coefficient ratio is implemented as a ratio of an average price of the highest sibling hotel for the month at which the room-type rental was made to an average price of the highest sibling hotel for any one month prior to the room-type rental, wherein the week coefficient is implemented as a ratio of an average price of the hotel with the highest peer income for the week on which the month is located at the time of pricing to an average price of the hotel with the highest peer income for any one week before the house type renting; and
and the pricing module is set to take the product of the determined monthly coefficient proportion, the determined weekly coefficient proportion and the monthly basic price of each room type of the hotel with the highest peer income as the daily basic price of the corresponding room type of the current hotel according to the determined room type and the pricing time of the current pricing hotel.
10. The hotel room pricing system of claim 9, further comprising a modification module, the pricing module configured to determine whether there are influencing factors and influencing factors that influence a current hotel base price, the modification module configured to modify the base price formed by the pricing module based on the determined influencing factors and influencing factors.
CN202110338492.5A 2021-03-30 2021-03-30 Hotel room price adjusting system and method based on machine learning and computer device Pending CN113011668A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110338492.5A CN113011668A (en) 2021-03-30 2021-03-30 Hotel room price adjusting system and method based on machine learning and computer device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110338492.5A CN113011668A (en) 2021-03-30 2021-03-30 Hotel room price adjusting system and method based on machine learning and computer device

Publications (1)

Publication Number Publication Date
CN113011668A true CN113011668A (en) 2021-06-22

Family

ID=76409154

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110338492.5A Pending CN113011668A (en) 2021-03-30 2021-03-30 Hotel room price adjusting system and method based on machine learning and computer device

Country Status (1)

Country Link
CN (1) CN113011668A (en)

Similar Documents

Publication Publication Date Title
CA2455639C (en) Automated listing management
US6434533B1 (en) Method for the exchange, analysis, and reporting of performance data in businesses with time-dependent inventory
Mearns Sustaining livelihoods on Mongolia's pastoral commons: Insights from a participatory poverty assessment
DE69936594T2 (en) NETWORK OF SELLING MACHINES INTERACTIVATED WITH MAIN CALCULATOR FOR DATABANKING
Telfer et al. Linkages between tourism and food production
US20170083833A1 (en) Sports and concert event ticket pricing and visualization system
CN103020308A (en) Method and device for recommending travel strategy project
US20070143157A1 (en) Computer-implemented systems and methods for resource allocation
US20100217679A1 (en) Ticket trading method
MX2011001757A (en) Automated decision support for pricing entertainment tickets.
CN107657385A (en) A kind industry data system
AU2023201296A1 (en) Apparatus and methods for providing queue messaging over a network
CN112927042A (en) Hotel self-service shopping settlement platform and system
CN101180644A (en) Apparatus and methods for providing queue messaging over a network
Durbarry et al. Tourism Taxation in the UK
Ingerson A comparison of the economic contribution of hallmark sporting and performing arts events
CN108229894A (en) Cargo configuration method, device, terminal and system based on vending machine
CN113011668A (en) Hotel room price adjusting system and method based on machine learning and computer device
US20120078733A1 (en) System and method for managing advertising campaigns
CN113011618A (en) Hotel income management system and method
CN113850625A (en) Marketing teaching management system
KR102113107B1 (en) Provincial and municipal win-win employment and information service system utilizing public data
CN111311375A (en) Cloud farm transaction platform and transaction method thereof
US10607282B2 (en) Opentap alcohol inventory bidding application
Kobyak et al. Guidelines for enhancing the effective management of hotel enterprises

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