[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN117649151A - Hotel background data analysis system - Google Patents

Hotel background data analysis system Download PDF

Info

Publication number
CN117649151A
CN117649151A CN202410107579.5A CN202410107579A CN117649151A CN 117649151 A CN117649151 A CN 117649151A CN 202410107579 A CN202410107579 A CN 202410107579A CN 117649151 A CN117649151 A CN 117649151A
Authority
CN
China
Prior art keywords
data
passenger flow
week
room type
predicted
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.)
Withdrawn
Application number
CN202410107579.5A
Other languages
Chinese (zh)
Inventor
范子昕
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.)
Shenzhen Xiaomi Real Estate Network Technology Co ltd
Original Assignee
Shenzhen Xiaomi Real Estate Network Technology Co ltd
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 Shenzhen Xiaomi Real Estate Network Technology Co ltd filed Critical Shenzhen Xiaomi Real Estate Network Technology Co ltd
Priority to CN202410107579.5A priority Critical patent/CN117649151A/en
Publication of CN117649151A publication Critical patent/CN117649151A/en
Withdrawn legal-status Critical Current

Links

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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • 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
    • G06Q30/0202—Market predictions or forecasting for commercial activities
    • 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—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)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • Game Theory and Decision Science (AREA)
  • Data Mining & Analysis (AREA)
  • Educational Administration (AREA)
  • Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a hotel background data analysis system, which relates to the technical field of data analysis and comprises a data acquisition module, a first customer flow prediction module, a second customer flow prediction module, a comprehensive customer flow prediction module and a price adjustment module. Acquiring customer evaluation, weather, holidays and season data and house type historical housing data from a hotel background; and predicting the passenger flow volume through three prediction modules: the first prediction considers customer loyalty and scores, the second prediction is based on weather, holidays and seasons, and the third prediction combines the data of the first two modules to form a comprehensive prediction; finally, the house price is adjusted according to the house type requirement. This design helps hotels predict passenger traffic more accurately, optimizing resource allocation and pricing policies.

Description

Hotel background data analysis system
Technical Field
The invention relates to the technical field of data analysis, in particular to a hotel background data analysis system.
Background
With the rapid growth of the tourism industry, the hotel industry is also becoming one of the important props for economic development; however, the increasing market competition has made hotel operators face a number of challenges, one of which is how to better manage hotel traffic and resource utilization through accurate data analysis; passenger flow prediction becomes an indispensable ring in hotel management, and can help operators predict the number of clients, optimize resource allocation, and improve service quality and profitability.
Traditional hotel background data analysis systems rely primarily on historical passenger flow data, external environmental factors (e.g., weather, holidays, etc.), and simple customer behavior data (e.g., check-in and check-out times) to make predictions and decisions; however, these approaches often ignore the impact of customer loyalty, scoring, etc. internal factors on customer flow predictions, as well as the fine-grained need for room price adjustment. Accordingly, there is a need for a more comprehensive data analysis system for hotels that improves the accuracy of their predictions and decisions.
Disclosure of Invention
Aiming at the technical problems in the background technology, the invention provides a hotel background data analysis system, which acquires customer evaluation, weather, holiday and season data and house type historical housing data from the hotel background; and predicting the passenger flow volume through three prediction modules: the first prediction considers customer loyalty and scores, the second prediction is based on weather, holidays and seasons, and the third prediction combines the data of the first two modules to form a comprehensive prediction; finally, adjusting the house price according to the house type requirement; the hotel system is beneficial to predicting the passenger flow more accurately, so that the resource allocation and pricing strategy are optimized.
In order to achieve the above purpose, the invention is realized by the following technical scheme:
hotel background data analysis system, comprising:
the data acquisition module acquires customer evaluation data in the hotel of the previous week, weather forecast data, holiday data and season data of the next week from the background of the hotel at the end of each week; summarizing historical housing and scoring data of each customer in the historical data, and passenger flow data of various weather, holidays and seasons; acquiring predicted passenger flow data and actual passenger flow data of the previous four weeks;
a first customer flow prediction module for calculating loyalty of each customer to each house type based on historical house data of each customerAnd combine each of the previous weekThe scores of individual house type customers after entering form a comprehensive score of each house type in the last weekThe method comprises the steps of carrying out a first treatment on the surface of the Calculating the first predicted passenger flow rate of each room type of the next week according to the linear fitting function of the comprehensive score and the passenger flow rate of each room type in the previous four weeks>；
The second passenger flow quantity prediction module is used for calculating the average passenger flow quantity corresponding to each type of weather, each holiday and each season according to the passenger flow quantity data of each type of weather, each holiday and each season in the historical data; predicting the passenger flow volume of each day of the next week according to the weather forecast data, holiday data and season data of the next week, wherein the sum of the predicted passenger flow volume values of each day is the second predicted passenger flow volume；
The comprehensive passenger flow volume prediction module is used for calculating second predicted passenger flow volume of each room type in the second predicted passenger flow volume data based on the passenger flow volume proportion of each room type in the first predicted passenger flow volume data; calculating influence indexes of the first and second predicted passenger flows according to the relation between the first and second predicted passenger flow data and the actual passenger flow data of each room type in the historical analysis data, and combining specific values of the first and second predicted passenger flows of each room type with the corresponding influence indexes to form comprehensive predicted passenger flow of each room type；
The price adjusting module is used for setting the passenger flow threshold value of each room type according to the number of rooms of each room type and comprehensively predicting the passenger flow of each room type according to the calculated next weekAnd adjusting the price of each room type in the next week.
Specifically, the check-in of each room type of the previous week is obtained from the hotel backgroundThe living data comprises passenger flow data of each room type and evaluation data after living; the passenger flow data of each room are as followsWherein->The total number of the room types in the hotel; taking the number of stars taken after the user is lived as the score +.>And->；
The hotel backstage is connected with the weather forecast component and the calendar component through interfaces and is used for acquiring weather information, season information and holiday information of the next week; wherein use is made ofTo indicate the weather of each day, < >>The time is indicated as sunny day>The time is indicated as cloudy day, and the person is treated with->The time is expressed as rainy and snowy days; use->To indicate seasons, & gt>The time is denoted as spring->The time is expressed as summer->The time is expressed as autumn->The time is expressed as winter; use->Indicates the category of holidays in the following week,indicates weekend day, ->Representing legal holidays,/->Representing a non-holiday;
historical housing data of each customer in the historical data and passenger flow data of various weather, holidays and seasons are summarized.
Further, the names of the subscribers of each house type are extracted from the background data of the previous week, and the historical housing data of the customers are found out from the historical data, wherein each customer has loyalty to each house typeThe expression is:
；
wherein,indicate->The individual customer is at->Total number of reservations for individual rooms, +.>Indicating the first week->The total number of bookings for individual rooms, +.>Is no greater than->Is a positive integer of (2);
loyalty to each house type by each customer based on the last weekCalculation of data of the last week with actual scoring data comprehensive score of each house type of the last week +.>The expression is:
；
wherein,indicate->Individual customer pair->Evaluation of individual house types.
Specifically, the comprehensive scoring data of each room type in the first, second and third weeks and the actual passenger flow data of each room type in the first, second and third weeks are taken out from the historical data; the comprehensive score of each room type in the first week is used for predicting the passenger flow volume corresponding to the room type in the first week, the comprehensive score of each room type in the third week is used for predicting the concrete in the first week, and the comprehensive score data of each room type in the first, third and fourth weeks and the actual passenger flow volume data of each room type in the first, second and third weeks are taken out from the historical data; wherein the comprehensive score of each room type in the first second week is used for predicting the passenger flow volume corresponding to the room type in the first week, and the comprehensive score of each room type in the third weekThe score is used for predicting the passenger flow volume corresponding to the room type in the second week before, and the comprehensive score of each room type in the fourth week before is used for predicting the passenger flow volume corresponding to the room type in the third week before; based on linear regression equationFitting three sets of data, wherein +.>Indicate the%>Zhou->Actual passenger flow of individual rooms, +.>Indicate the%>Zhou->Comprehensive scoring of individual house types; calculating the slope of the fitting straight line by the least square method>Intercept->The final fitting equation is obtained as +.>；
Calculating the first predicted passenger flow volume of each room type of the next week by using the calculated fitting function of the customer of the previous week to each room typeThe expression is: />。
Further, history is toSummarizing actual passenger flow data of various weather, holidays and seasons in the data, and calculating average passenger flow corresponding to each holiday and each season、/>And +.>The method comprises the steps of carrying out a first treatment on the surface of the And calculating influence weight of weather, season and holiday on passenger flow by using analytic hierarchy process +.>、/>And +.>；
Combining weather forecast data, holiday data and seasonal data of each day of the next week, namely, weather, season and holiday corresponding to each day, and calculating the daily predicted passenger flow according to the average passenger flow and influence weight of the corresponding weather, season and holidayThe expression is:
；
wherein,、/>and +.>Respectively +.>Weather data, season data, holiday data for days;
the calculated predicted passenger flow amount of each day in the next weekAdding to obtain the second predicted passenger flow volume of the next weekThe expression is: />。
Further, calculating the ratio of the predicted passenger flow value of each room type in the first customer flow prediction module to the total passenger flow valueThe expression is->The method comprises the steps of carrying out a first treatment on the surface of the The ratio of each room type and the second predicted passenger flow calculated by the second passenger flow prediction module are added>Combining to obtain second predicted passenger flow +.>The expression is: />。
Specifically, the analysis data of the first three weeks and the actual passenger flow data of each room type are obtained, wherein the passenger flow data comprises the first and second predicted passenger flow data of each room type obtained by analysis in the first two to the first four weeksAnd->Actual passenger flow per room type from the previous one to the previous three weeksVolume data->Wherein->First and second predicted traffic data representing each room at the previous second weekAnd->And the actual passenger flow data per room type for the first week +.>And->The method comprises the steps of carrying out a first treatment on the surface of the Calculating the relative error of the first and second predicted passenger flow data and the actual passenger flow data of each room type obtained by each analysis>And->The expression is: />、/>。
Further, the relative error of the first and second predicted passenger flow data of each room type and the actual passenger flow data of each room type in the first three weeksAnd->Averaging to obtain +.>And->The method comprises the steps of carrying out a first treatment on the surface of the Normalizing to obtain the influence index of the first and second predicted passenger flows of each house type>And->The prediction accuracy of the first and second predicted passenger flows to the actual passenger flow is the same;
the first and second predicted passenger flow volume of each room type are combined with the corresponding influence indexAnd->Combining to form the comprehensive predicted passenger flow +.>The expression is: />。
Further, setting the passenger flow threshold of each room type according to the number of rooms of each room typeAnd->The method specifically comprises the following steps:、/>wherein->Is->Number of rooms of individual house->Is->Maximum number of load-bearing persons in individual rooms;
when (when)When the passenger flow of the next week is less, the price of the house type needs to be reduced to attract more clients to check in;
when (when)When the passenger flow of the next week is moderate, the price of the house type does not need to be adjusted;
when (when)And the next week is represented by more passenger flow, and the price of the house type needs to be raised to obtain more profits.
The invention provides a hotel background data analysis system, which has the following beneficial effects:
1. the data acquisition module acquires various data from the hotel background, including customer evaluation, weather forecast, holiday and season data and the like, and provides comprehensive data support for subsequent passenger flow prediction; meanwhile, summarizing and analyzing historical data is helpful for hotels to know client demands and behaviors in depth, so that inaccurate and untimely problems caused by subjective judgment and intuition are avoided, and a powerful basis is provided for subsequent decisions;
2. the first customer flow prediction module and the second customer flow prediction module predict the customer flow from both an internal (customer loyalty and scoring) and an external (weather, holidays and seasons) perspective, respectively; the comprehensive prediction method can more comprehensively consider various factors influencing the passenger flow, and improves the accuracy of prediction;
3. the comprehensive passenger flow volume prediction module combines the first prediction result and the second prediction result to form comprehensive predicted passenger flow volume of each room type; the comprehensive analysis method can better reflect the differentiation and change of the house type requirement and provide more accurate basis for price adjustment;
4. the price adjustment module adjusts the price of the house according to the house demand and the predicted passenger flow, so that the price strategy is more flexible and finer; and the passenger flow threshold is set by combining the number of rooms, and the system can automatically adjust the room price so as to meet market demands and maximize hotel benefits.
Drawings
Fig. 1 is a schematic structural diagram of a hotel background data analysis system provided by the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention provides a hotel background data analysis system, comprising:
the data acquisition module acquires customer evaluation data in the hotel of the previous week, weather forecast data, holiday data and season data of the next week from the background of the hotel at the end of each week; summarizing historical housing and scoring data of each customer in the historical data and passenger flow data of various weather, holidays and seasons;
the total passenger flow of the next week and the passenger flow of each room type are predicted at the end of each week, wherein the passenger flow data and evaluation data of each room type in the hotel can directly influence the selection condition of people on the hotel, and further influence the change of the passenger flow of the hotel in a future period of time; in addition, weather forecast data, holiday data and season data can directly influence travel and travel plans of people, so that passenger flow data of hotels are influenced;
obtaining check-in data of each room type of the last week from hotel background, includingIndividual house type passenger flow data and evaluation data after check-in; the passenger flow data of each room are as followsWherein->The total number of the room types in the hotel; taking the number of stars taken after the user is lived as the score +.>And->The method comprises the steps of carrying out a first treatment on the surface of the The passenger flow information and the scoring information of the previous week are displayed in the small program, and the higher the passenger flow of the hotel or the higher the scoring, the more customers are attracted, so that the passenger flow of the hotel is improved;
the hotel backstage is connected with the weather forecast component and the calendar component through interfaces and is used for acquiring weather information, season information and holiday information of the next week; wherein use is made ofTo indicate the weather of each day, < >>The time is indicated as sunny day>The time is indicated as cloudy day, and the person is treated with->The rainy and snowy days are indicated, and more people can be attracted to travel on a sunny day generally, so that the passenger flow of a hotel is improved; use->To indicate seasons, & gt>The time is denoted as spring->The time is expressed as summer->The time is expressed as autumn->The time is expressed as winter, and generally summer is the season most suitable for traveling, spring and autumn; use->Indicates the category of holidays in the following week, < ->Indicates weekend day, ->Representing legal holidays,/->Representing non-holidays, people usually select holidays to travel, so that the passenger flow of a hotel is improved;
in addition, the historical housing data of each customer in the historical data and the passenger flow data of various weather, holidays and seasons are summarized for the prediction processing of the subsequent passenger flow.
A first customer flow prediction module for calculating loyalty of each customer to each house type based on historical house data of each customerAnd the scores after the customers of each room form in the previous week are combined to form a comprehensive score of each room form in the previous weekThe method comprises the steps of carrying out a first treatment on the surface of the Calculating the first predicted passenger flow rate of each room type of the next week according to the linear fitting function of the comprehensive score and the passenger flow rate of each room type in the previous four weeks>；
Predicting the passenger flow of each room type in the next week based on the score of each room type customer after entering in the last week, wherein the method specifically comprises the following steps:
s1, extracting names of subscribers of various house types from background data of the last week, and finding out historical housing data of the customers from the historical data, wherein each customer has loyalty to each house typeThe expression is:
；
wherein,indicate->The individual customer is at->Total number of reservations for individual rooms, +.>Indicating the first week->The total number of bookings for individual rooms, +.>Is no greater than->Is a positive integer of (2); the more reservations in the hotel, the more reference the score is, so the loyalty of each customer to each house type is calculated>For more accurately predicting the passenger flow volume of the next week from the psychological viewpoint of the customers;
S2loyalty to each house type based on each customer in the last weekCalculation of data of the last week with actual scoring data comprehensive score of each house type of the last week +.>The expression is:
；
wherein,indicate->Individual customer pair->Evaluating individual house types;
s3, taking out comprehensive scoring data of each room type in the first, second and third weeks and actual passenger flow data of each room type in the first, second and third weeks from the historical data; the comprehensive score of each room type in the first week is used for predicting the passenger flow volume corresponding to the room type in the first week, the comprehensive score of each room type in the third week is used for predicting the passenger flow volume corresponding to the room type in the first week, and the comprehensive score of each room type in the fourth week is used for predicting the passenger flow volume corresponding to the room type in the third week; based on linear regression equationFitting three sets of data, wherein +.>Indicate the%>Zhou->Real of individual house typeFlow of the person in the middle of the passenger, the person in the passenger can be treated with->Indicate the%>Zhou->Comprehensive scoring of individual house types; calculating the slope of the fitting straight line by the least square method>Intercept->The final fitting equation is obtained as +.>；
S4, calculating the first predicted passenger flow volume of each room type in the next week according to the calculated fitting function of the customers in the previous week to each room typeThe expression is: />；
The loyalty of each customer to each house type is calculated, and the time lag effect, namely the different influence of scores of different weeks on the predicted future passenger flow is considered, so that the prediction is closer to the actual situation, and the conversion between house types and the change of customer reservation habits can be reflected better.
The second passenger flow quantity prediction module is used for calculating the average passenger flow quantity corresponding to each type of weather, each holiday and each season according to the passenger flow quantity data of each type of weather, each holiday and each season in the historical data; predicting the passenger flow volume of each day of the next week according to the weather forecast data, holiday data and season data of the next week, wherein the sum of the predicted passenger flow volume values of each day is the second predicted passenger flow volume；
Predicting daily passenger flow in the next week based on the historical data on average passenger flow in each type of weather, each holiday and each season, wherein the specific steps comprise:
t1, summarizing actual passenger flow data of various weather, holidays and seasons in the historical data, and calculating average passenger flow corresponding to each holiday in each weather and season、/>And +.>The method comprises the steps of carrying out a first treatment on the surface of the And calculating influence weight of weather, season and holiday on passenger flow by using analytic hierarchy process +.>、/>And +.>The method comprises the steps of carrying out a first treatment on the surface of the The weight analysis method is a qualitative and quantitative research method for calculating weight, adopts a pairwise comparison method, establishes a matrix, and finally calculates the importance of each factor by utilizing the principle that the larger the number is, the higher the important weight is according to the relativity of the number size; the method comprises the steps of carrying out weight analysis on selected features according to related data in a history log and whether faults exist or not to obtain the weight of each feature; this weight will change correspondingly as the data increases;
t2, combining weather forecast data, holiday data and seasonal data of each day of the next week, namely, weather, seasons and holidays corresponding to each day, and calculating predicted passenger flow of each day according to average passenger flow and influence weights of the corresponding weather, seasons and holidaysThe expression is:
；
wherein,、/>and +.>Respectively +.>Weather data, season data, holiday data for days;
t3, predicting the passenger flow rate of each day of the next weekAdding to obtain second predicted passenger flow +.>The expression is: />；
The second passenger flow volume prediction module is used for predicting the passenger flow volume daily in the next week according to the passenger flow volume data of various weather, holidays and seasons in the historical data; the influence of various factors on the passenger flow volume can be comprehensively considered, including weather, holidays, seasons and the like, so that the accuracy and the reliability of passenger flow volume prediction are improved; this can provide valuable reference information to the hotel operator in advance, helping them better formulate marketing strategies and adjust resource allocation to better meet customer needs and improve business efficiency.
The comprehensive passenger flow volume prediction module calculates a second prediction based on the passenger flow volume proportion of each room type in the first prediction passenger flow volume dataSecond predicted traffic for each of the room types in the traffic data; calculating influence indexes of the first and second predicted passenger flows according to the relation between the first and second predicted passenger flow data and the actual passenger flow data of each room type in the historical analysis data, and combining specific values of the first and second predicted passenger flows of each room type with the corresponding influence indexes to form comprehensive predicted passenger flow of each room type；
Calculating the ratio of the predicted passenger flow value of each room type to the total passenger flow value in the first customer flow prediction moduleThe expression is->The method comprises the steps of carrying out a first treatment on the surface of the The proportion of each room type is compared with the second predicted passenger flow volume calculated by the second passenger flow volume prediction moduleCombining to obtain second predicted passenger flow +.>The expression is: />；
Acquiring analysis data of the first three weeks and passenger flow data of each real room type, wherein the passenger flow data comprises first and second predicted passenger flow data of each room type obtained by analysis in the first two to the first four weeksAnd->And the actual passenger flow data for each house pattern from the previous week to the previous three weeks +.>Wherein->First and second predicted traffic data representing each house pattern at the previous second week +.>Andand the actual passenger flow data per room type for the first week +.>And->The method comprises the steps of carrying out a first treatment on the surface of the Calculating the relative error of the first and second predicted passenger flow data and the actual passenger flow data of each room type obtained by each analysis>And->The expression is: />、/>；
Relative error of the first and second predicted passenger flow data of each room type and the actual passenger flow data of each room type in the first three weeksAnd->Averaging to obtain +.>And->The method comprises the steps of carrying out a first treatment on the surface of the And normalize it to obtain the first of each house type1. Influence index of second predicted passenger flow +.>And->The prediction accuracy of the first and second predicted passenger flows to the actual passenger flow is the same;
the first and second predicted passenger flow volume of each room type are combined with the corresponding influence indexAnd->Combining to form the comprehensive predicted passenger flow +.>The expression is: />。
The price adjusting module is used for setting the passenger flow threshold value of each room type according to the number of rooms of each room type and comprehensively predicting the passenger flow of each room type according to the calculated next weekAdjusting the room price of each room in the next week;
setting a passenger flow threshold of each room type according to the number of rooms of each room typeAnd->The method specifically comprises the following steps:、/>wherein->Is->Number of rooms of individual house->Is->Maximum number of load-bearing persons in individual rooms;
when (when)When the passenger flow of the next week is less, the price of the house type needs to be reduced to attract more clients to check in;
when (when)When the passenger flow of the next week is moderate, the price of the house type does not need to be adjusted;
when (when)And the next week is represented by more passenger flow, and the price of the house type needs to be raised to obtain more profits.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in accordance with embodiments of the present invention are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable devices. The computer instructions may be stored in or transmitted across a computer storage medium.
The computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by a wired (e.g., coaxial cable, fiber optic, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). Computer storage media may be any available media that can be accessed by a computer or data storage devices, such as servers, data centers, etc. that contain an integration of one or more of the available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a Solid State Disk (SSD)), or the like.
The foregoing is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present disclosure, and all changes and substitutions are intended to be covered by the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (9)

1. Hotel backstage data analysis system, its characterized in that: comprising the following steps:
the data acquisition module acquires customer evaluation data in the hotel of the previous week, weather forecast data, holiday data and season data of the next week from the background of the hotel when the week ends; summarizing historical housing and scoring data of each customer in the historical data, and passenger flow data of various weather, holidays and seasons; acquiring predicted passenger flow data and actual passenger flow data of the previous four weeks;
a first customer flow prediction module for calculating loyalty of each customer to each house type based on historical house data of each customerAnd combining the scores of the house type customers in the previous week to form a comprehensive score of each house type in the previous week>The method comprises the steps of carrying out a first treatment on the surface of the Calculating the first room type of the next week according to the linear fitting function of the comprehensive score and the passenger flow volume of each room type in the previous four weeksPredicted passenger flow->；
The second passenger flow quantity prediction module is used for calculating the average passenger flow quantity corresponding to each type of weather, each holiday and each season according to the passenger flow quantity data of each type of weather, each holiday and each season in the historical data; predicting the passenger flow volume of each day of the next week according to the weather forecast data, holiday data and season data of the next week, wherein the sum of the predicted passenger flow volume values of each day is the second predicted passenger flow volume；
The comprehensive passenger flow volume prediction module is used for calculating second predicted passenger flow volume of each room type in the second predicted passenger flow volume data based on the passenger flow volume proportion of each room type in the first predicted passenger flow volume data; calculating influence indexes of the first and second predicted passenger flows according to the relation between the first and second predicted passenger flow data and the actual passenger flow data of each room type in the historical analysis data, and combining specific values of the first and second predicted passenger flows of each room type with the corresponding influence indexes to form comprehensive predicted passenger flow of each room type；
The price adjusting module is used for setting the passenger flow threshold value of each room type according to the number of rooms of each room type and comprehensively predicting the passenger flow of each room type according to the calculated next weekAnd adjusting the price of each room type in the next week.
2. The hotel background data analysis system of claim 1, wherein:
acquiring check-in data of each room type in the last week from a hotel background, wherein the check-in data comprises passenger flow data of each room type and evaluation data after check-in; each of which isThe room-type passenger flow data is thatWherein->The total number of the room types in the hotel; taking the number of stars taken after the user is lived as the score +.>And->；
The hotel backstage is connected with the weather forecast component and the calendar component through interfaces and is used for acquiring weather information, season information and holiday information of the next week; wherein use is made ofTo indicate the weather of each day, < >>The time is indicated as sunny day>The time is indicated as cloudy day, and the person is treated with->The time is expressed as rainy and snowy days; use->To indicate seasons, & gt>The time is denoted as spring->The time is expressed as summer->The time is expressed as autumn->The time is expressed as winter; use->Indicates the category of holidays in the following week, < ->Indicates weekend day, ->Representing legal holidays,/->Representing a non-holiday;
historical housing data of each customer in the historical data and passenger flow data of various weather, holidays and seasons are summarized.
3. The hotel background data analysis system of claim 2, wherein:
extracting names of reservation persons of various house types from background data of the last week, and finding historical house data of the customers from the historical data, wherein each customer has loyalty to each house typeThe expression is:
；
wherein,indicate->The individual customer is at->Total number of reservations for individual rooms, +.>Indicating the first week->The total number of bookings for individual rooms, +.>Is no greater than->Is a positive integer of (2);
loyalty to each house type by each customer based on the last weekCalculation of data of the last week with actual scoring data comprehensive score of each house type of the last week +.>The expression is:
；
wherein,indicate->Individual customer pair->Evaluation of individual house types.
4. The hotel background data analysis system of claim 3, wherein:
taking out the comprehensive scoring data of each of the first, second and third room types and the actual passenger flow data of each of the first, second and third room types from the historical data; the comprehensive score of each room type in the first week is used for predicting the passenger flow volume corresponding to the room type in the first week, the comprehensive score of each room type in the third week is used for predicting the passenger flow volume corresponding to the room type in the first week, and the comprehensive score of each room type in the fourth week is used for predicting the passenger flow volume corresponding to the room type in the third week; based on linear regression equationFitting three sets of data, wherein +.>Indicate the%>Zhou->Actual passenger flow of individual rooms, +.>Indicate the%>Zhou->Comprehensive scoring of individual house types; calculating the slope of the fitting straight line by the least square method>Intercept of andthe final fitting equation is obtained as +.>；
Calculating the first predicted passenger flow volume of each room type of the next week by using the calculated fitting function of the customer of the previous week to each room typeThe expression is: />。
5. The hotel background data analysis system of claim 4, wherein:
summarizing actual passenger flow data of various weather, holidays and seasons in the historical data, and calculating average passenger flow corresponding to each holiday and each season、/>And +.>The method comprises the steps of carrying out a first treatment on the surface of the And calculating influence weight of weather, season and holiday on passenger flow by using analytic hierarchy process +.>、/>And +.>；
Combining weather forecast data, holiday data and seasonal data of the next week, namely weather, season and holiday corresponding to each day, according to average passenger flow and influence weight of corresponding weather, season and holidayWeight, calculating predicted daily passenger flowThe expression is:
；
wherein,、/>and +.>Respectively +.>Weather data, season data, holiday data for days;
the calculated predicted passenger flow amount of each day in the next weekAdding to obtain second predicted passenger flow +.>The expression is: />。
6. The hotel background data analysis system of claim 5, wherein:
calculating the ratio of the predicted passenger flow value of each room type to the total passenger flow value in the first customer flow prediction moduleThe expression is->The method comprises the steps of carrying out a first treatment on the surface of the The ratio of each room type and the second predicted passenger flow calculated by the second passenger flow prediction module are added>Combining to obtain second predicted passenger flow +.>The expression is: />。
7. The hotel background data analysis system of claim 6, wherein:
acquiring analysis data of the first three weeks and passenger flow data of each real room type, wherein the passenger flow data comprises first and second predicted passenger flow data of each room type obtained by analysis in the first two to the first four weeksAnd->And the actual passenger flow data for each house pattern from the previous week to the previous three weeks +.>Wherein->First and second predicted traffic data representing each house pattern at the previous second week +.>And->And the actual passenger flow data per room type for the first week +.>And->The method comprises the steps of carrying out a first treatment on the surface of the Calculating the relative error of the first and second predicted passenger flow data and the actual passenger flow data of each room type obtained by each analysis>And->The expression is:、/>。
8. the hotel background data analysis system of claim 7, wherein:
relative error of the first and second predicted passenger flow data of each room type and the actual passenger flow data of each room type in the first three weeksAnd->Averaging to obtain +.>And->The method comprises the steps of carrying out a first treatment on the surface of the Normalizing to obtain the influence index of the first and second predicted passenger flows of each house type>And->The prediction accuracy of the first and second predicted passenger flows to the actual passenger flow is the same;
the first and second predicted passenger flow volume of each room type are combined with the corresponding influence indexAnd->Combining to form the comprehensive predicted passenger flow +.>The expression is: />。
9. The hotel background data analysis system of claim 8, wherein:
setting a passenger flow threshold of each room type according to the number of rooms of each room typeAnd->The method specifically comprises the following steps: />、Wherein->Is->Number of rooms of individual house->Is->Maximum number of load-bearing persons in individual rooms;
when (when)When the house type price is reduced, more clients are attracted to the house type price;
when (when)When the house type price does not need to be adjusted;
when (when)And when the house type price is increased.
CN202410107579.5A 2024-01-26 2024-01-26 Hotel background data analysis system Withdrawn CN117649151A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410107579.5A CN117649151A (en) 2024-01-26 2024-01-26 Hotel background data analysis system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410107579.5A CN117649151A (en) 2024-01-26 2024-01-26 Hotel background data analysis system

Publications (1)

Publication Number Publication Date
CN117649151A true CN117649151A (en) 2024-03-05

Family

ID=90048002

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410107579.5A Withdrawn CN117649151A (en) 2024-01-26 2024-01-26 Hotel background data analysis system

Country Status (1)

Country Link
CN (1) CN117649151A (en)

Similar Documents

Publication Publication Date Title
Göb et al. Electrical load forecasting by exponential smoothing with covariates
US10007957B2 (en) Selecting search results for responding to search query
CN107240033B (en) Method and system for constructing electric power identification model
CN102254277A (en) Data processing system and method for real estate valuation
CN108388974A (en) Top-tier customer Optimum Identification Method and device based on random forest and decision tree
CN116601652A (en) Expert matching system for supporting entrepreneur
US11381635B2 (en) Method of operating a server apparatus for delivering website content, server apparatus and device in communication with server apparatus
CN106780173A (en) OTA hotels inventory management method and system
KR101725228B1 (en) System and method for bidding automatically based on bidding related history data in keyword advertisement, and bidding management server
CN107578277A (en) A Method for Locating Rental House Customers Used in Power Marketing
US20150310570A1 (en) Open pricing and pricing rules
US12131277B2 (en) System and method of predicting a repair project
CN112907362A (en) Loan transaction processing method and device, electronic equipment and storage medium
Zhang et al. Daily tourism forecasting through a novel method based on principal component analysis, grey wolf optimizer, and extreme learning machine
CN112561552A (en) Method and device for adjusting value attribute of article
CN110348922B (en) Method and apparatus for generating information
Garcia Pozo A nested housing market structure: additional evidence
CN113807597A (en) Network scheduling method, device, equipment and storage medium
CN118916399A (en) Intelligent data analysis recommendation engine and system
CN117649151A (en) Hotel background data analysis system
CN115496304B (en) Three-dimensional comprehensive evaluation method and system for agency purchase electricity quantity prediction algorithm
CN116187960A (en) Data processing method, device and processor for determining labor cost
KR101734108B1 (en) System and method for bidding automatically based on set rule in keyword advertisement, and bidding management server
KR20180082214A (en) Risk value evaluating system for unclaimed construction and risk value evaluating apparatus for unclaimed construction
CN119693038B (en) Intelligent ticketing system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
WW01 Invention patent application withdrawn after publication
WW01 Invention patent application withdrawn after publication

Application publication date: 20240305