CN114445138A - Hotel room type pricing method, device, equipment and storage medium - Google Patents
Hotel room type pricing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114445138A CN114445138A CN202210102905.4A CN202210102905A CN114445138A CN 114445138 A CN114445138 A CN 114445138A CN 202210102905 A CN202210102905 A CN 202210102905A CN 114445138 A CN114445138 A CN 114445138A
- Authority
- CN
- China
- Prior art keywords
- price
- predicted
- target
- historical
- booking rate
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000012549 training Methods 0.000 claims description 16
- 230000015654 memory Effects 0.000 claims description 11
- 230000033228 biological regulation Effects 0.000 claims description 8
- 230000003828 downregulation Effects 0.000 claims description 4
- 238000003064 k means clustering Methods 0.000 claims description 4
- 230000003827 upregulation Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 8
- 230000006872 improvement Effects 0.000 description 7
- 238000003062 neural network model Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0283—Price estimation or determination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Accounting & Taxation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Finance (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a hotel room type pricing method, a device, equipment and a storage medium, wherein the method comprises the following steps: acquiring target historical price data and a target historical booking rate of a target house type on the same date of a previous period corresponding to a date to be predicted in a preset period; based on a price prediction model trained in advance, predicting by using target historical price data to obtain an initial predicted price of a target house type on a date to be predicted; predicting and obtaining the predicted booking rate of the target house type of the date to be predicted by using the target historical booking rate based on a pre-trained booking rate prediction model; and comparing the predicted booking rate with the expected booking rate acquired in advance to determine a price adjusting coefficient, and adjusting the initial predicted price according to the price adjusting coefficient to obtain the final predicted price. The price and the booking rate of the date to be forecasted are forecasted respectively, the price adjusting coefficient is confirmed according to the booking rate, and the forecasted price is adjusted, so that the pricing is more reasonable.
Description
Technical Field
The application relates to the technical field of hotel information platform management, in particular to a hotel room type pricing method, device, equipment and storage medium.
Background
The guest rooms are the basic facilities of the hotel, and undoubtedly the main source of the hotel for obtaining business income, and the daily income of the hotel depends on the number of the sold guest rooms and the price of each sold guest room. The hotel can be through setting up the polymorphic type guest room of different price levels to and different room price rules and products, thereby subdivide different sources of guests, obtain higher income finally. There are many factors that determine the business recipients of a guest room, one of the most important of which is the room price, which thus becomes an important economic lever for regulating the market of the hospitality industry. Reasonable and attractive room price, satisfaction of customers and improvement of the income of the hotel. Then, how to maximize the income of the hotel, the income management is an important indispensable link.
The income management is a dynamic management process which continuously optimizes products, prices and sales channels, improves product sales volume and sales price and realizes income maximization by analyzing and predicting the market supply-demand relationship and the purchasing habits of consumers. In the case of the hotel industry, revenue management can be understood as a strategy for maximizing the revenue of a hotel by selling a suitable product to a suitable guest at a suitable price through a suitable channel at a suitable time by the hotel. The price of the guest room reflects the income condition of the hotel most directly, and the income and the profitability of the hotel can be further improved by adjusting the price of the guest room of the hotel, so that the maximization of the total income is realized.
However, the traditional hotel pricing is often based on experience to make decisions, which is generally limited by the work experience and the reading of a pricing person, and the traditional hotel pricing has strong subjectivity and cannot effectively improve the total income.
Disclosure of Invention
The application provides a hotel room type pricing method, device, equipment and storage medium, and aims to solve the problems that existing hotel room type pricing is unreasonable and income is not high enough.
In order to solve the technical problem, the application adopts a technical scheme that: provided is a hotel room type pricing method, comprising the following steps: acquiring target historical price data and a target historical booking rate of a target house type on the same date of a previous period corresponding to a date to be predicted in a preset period; based on a price prediction model trained in advance, predicting by using target historical price data to obtain an initial prediction price of a target house type on a date to be predicted, and training the price prediction model according to historical price data of various house types to obtain the initial prediction price; based on a pre-trained booking rate prediction model, predicting the predicted booking rate of a target house type of a date to be predicted by using the target historical booking rate, wherein the booking rate prediction model is obtained by training according to historical booking data of various house types; and comparing the predicted booking rate with the expected booking rate acquired in advance to determine a price adjusting coefficient, and adjusting the initial predicted price according to the price adjusting coefficient to obtain the final predicted price.
As a further improvement of the present application, acquiring target historical price data and a target historical booking rate of a target house type on the same date as a previous period corresponding to a date to be forecasted at a preset period includes: judging whether the date to be predicted is a preset holiday or not; if yes, acquiring target historical price data and a target historical booking rate of the holidays in the same previous historical festival; if not, acquiring the target historical price data and the target historical booking rate of the same date in the previous period.
As a further improvement of the present application, comparing the predicted booking rate with the expected booking rate to determine a price adjustment coefficient, and adjusting the initial predicted price according to the price adjustment coefficient to obtain a final predicted price, includes: taking the ratio of the absolute value of the difference between the predicted booking rate and the expected booking rate to the expected booking rate as a price adjusting coefficient; when the predicted booking rate is higher than the expected booking rate, carrying out price up-regulation on the initial predicted price according to the price regulation coefficient to obtain a final predicted price; when the predicted booking rate is lower than the expected booking rate, if the difference value between the predicted booking rate and the expected booking rate does not exceed a preset threshold value, carrying out price down-regulation on the initial predicted price according to a price regulation coefficient to obtain a final predicted price; and if the difference value between the predicted booking rate and the expected booking rate exceeds a preset threshold value, taking the preset reserve price as the final predicted price.
As a further improvement of the present application, after obtaining the final predicted price, the method further includes: judging whether the final predicted price falls into the price fluctuation range or not; if the final predicted price does not fall into the price fluctuation range, when the final predicted price is lower than the minimum price value of the price fluctuation range, taking the minimum price value as the final predicted price; and when the final predicted price is higher than the maximum price value of the price fluctuation range, taking the maximum price value as the final predicted price.
As a further improvement of the application, before judging whether the final predicted price falls within the price fluctuation range, the method further comprises the following steps: and acquiring a plurality of historical price data of the target house type and a plurality of historical periods corresponding to the date to be predicted, wherein the historical periods have the same date, and determining the price fluctuation range by using the minimum historical price data and the maximum historical price data.
As a further improvement of the present application, after obtaining the final predicted price, the method further includes: acquiring all price data of the same house type of all hotels meeting preset conditions in a preset radius range on a date to be predicted by taking the geographic position of the hotel as the center of a circle; performing K-Means clustering on all price data to obtain a plurality of clustering clusters; judging whether the final predicted price is in the maximum cluster; if not, calculating a target point which is closest to the point corresponding to the final predicted price in the maximum clustering cluster, and taking the price corresponding to the target point as the final predicted price.
As a further improvement of the present application, after obtaining the final predicted price, the method further includes:
obtaining historical user data of a target house type, and dividing the historical user data according to preset user tags to obtain a plurality of user groups;
selecting a target user group with the number of users lower than a preset group number threshold from a plurality of user groups, and acquiring a target user label corresponding to the target user group;
calculating the average value of the historical price data of the target user group, calculating the difference between the average value and the final predicted price, and setting a user preferential strategy according to the difference;
and when the user conforming to the target user label browses the target house type, sending a preferential strategy to the user.
In order to solve the above technical problem, another technical solution adopted by the present application is: there is provided a hotel room type pricing apparatus, comprising: the acquisition module is used for acquiring target historical price data and a target historical booking rate of a target house type on the same date as the previous period corresponding to the date to be predicted in a preset period; the first prediction module is used for predicting and obtaining an initial prediction price of a target house type of a date to be predicted by using target historical price data based on a pre-trained price prediction model, and the price prediction model is obtained by training according to the historical price data of various house types; the second prediction module is used for predicting the predicted booking rate of the target house type of the date to be predicted by utilizing the target historical booking rate based on a pre-trained booking rate prediction model, and the booking rate prediction model is obtained by training according to the historical booking data of various house types; and the adjusting module is used for comparing the predicted booking rate with the expected booking rate acquired in advance to determine a price adjusting coefficient, and adjusting the initial predicted price according to the price adjusting coefficient to obtain the final predicted price.
In order to solve the above technical problem, the present application adopts another technical solution that: there is provided a computer device comprising a processor, a memory coupled to the processor, having stored therein program instructions which, when executed by the processor, cause the processor to perform the steps of the hotel room type pricing method as described above.
In order to solve the above technical problem, the present application adopts another technical solution that: there is provided a storage medium storing program instructions capable of implementing the hotel room type pricing method described above.
The beneficial effect of this application is: according to the hotel room type pricing method, historical sales data of a hotel are divided according to a period, the price and the booking rate of a target room type on a date to be predicted are predicted by utilizing similar characteristics on the period, an initial predicted price and a predicted booking rate are obtained, an expected booking rate is compared with the predicted booking rate to confirm a price adjusting coefficient, the initial predicted price is adjusted according to the price adjusting coefficient, and a final predicted price is obtained.
Drawings
Fig. 1 is a schematic flow chart of a hotel room type pricing method according to a first embodiment of the present invention;
fig. 2 is a flow chart diagram of a hotel room type pricing method according to a second embodiment of the present invention;
fig. 3 is a flow chart diagram of a hotel room type pricing method according to a third embodiment of the invention;
FIG. 4 is a functional block diagram of a hotel room type pricing device of an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of a computer device according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a storage medium according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "first", "second" and "third" in this application are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any indication of the number of technical features indicated. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of the feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless explicitly specifically limited otherwise. All directional indications (such as up, down, left, right, front, and rear … …) in the embodiments of the present application are only used to explain the relative positional relationship between the components, the movement, and the like in a specific posture (as shown in the drawings), and if the specific posture is changed, the directional indication is changed accordingly. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
Fig. 1 is a flow chart of a hotel room type pricing method according to a first embodiment of the present invention. It should be noted that the method of the present invention is not limited to the flow sequence shown in fig. 1 if the results are substantially the same. As shown in fig. 1, the method comprises the steps of:
step S101: and acquiring target historical price data and a target historical booking rate of the target house type on the same date as the previous period corresponding to the date to be predicted at a preset period.
It should be understood that in a typical case, the booking data of the hotel presents a periodic similarity over a period of fixed length of time, which may be one week, one month, etc., for example, various hotel room type booking cases present a high similarity over a period of time in units of weeks, or the room type booking case of the day of the week may be referred to a room type booking case of the day of the week to a large extent.
Specifically, in step S101, when a price pricing request of a target house type on a date to be predicted is received, a previous period is first queried, and target historical price data of the target house type on the same date corresponding to the date to be predicted is used as reference data, and a target historical booking rate needs to be acquired, so as to correct the predicted price data later.
Further, step S101 specifically includes:
1. judging whether the date to be predicted is a preset holiday or not;
2. and if so, acquiring the target historical price data and the target historical booking rate of the holiday of the same previous historical festival.
3. If not, acquiring the target historical price data and the target historical booking rate of the same date in the previous period.
It should be understood that the preset holiday in this embodiment refers to a special holiday such as five-year, mid-autumn, national day, etc., for such holiday, due to the tourists playing, the hotel reservation will have a peak increase different from other time points, and therefore, the historical price data in the holiday period other than such holiday is lack of reference value, and therefore, in this embodiment, when the date to be predicted is determined to be the preset holiday, the target historical price data and the target historical reservation rate of the same holiday in the previous period are referred to, instead of the historical data of the same date in the previous period.
Step S102: and based on a price prediction model trained in advance, predicting by using target historical price data to obtain the initial predicted price of the target house type on the date to be predicted, and training the price prediction model according to the historical price data of various house types to obtain the price.
The price prediction model is trained based on historical price data prepared in advance. When the price prediction model is trained, firstly, prepared historical sample data is divided according to periods, and then the divided historical sample data is input into the price prediction model according to the periods so as to train the price prediction model.
Step S103: and based on a pre-trained booking rate prediction model, predicting the predicted booking rate of the target house type on the date to be predicted by using the target historical booking rate, wherein the booking rate prediction model is obtained by training according to the historical booking data of various house types.
It should be noted that the booking rate prediction model is trained based on historical price data prepared in advance. When the price prediction model is trained, firstly, prepared historical sample data is divided according to periods, and then the divided historical sample data is input into the booking rate prediction model according to periods so as to train the booking rate prediction model.
In this embodiment, the price prediction model and the booking rate prediction model are constructed based on a long-term and short-term memory neural network model.
The long and short memory neural network is a neural network based on time recursion, and is suitable for processing important events with relatively long intervals and delays in a date sequence to be predicted. The long and short memory neural network model has a plurality of applications in the technical field. The system based on the long and short memory neural network model can learn and translate languages, control robots, analyze images, abstract documents, recognize voice recognition images, recognize handwriting, control chat robots, predict diseases and other tasks. The long and short memory neural network model is a variant of a cyclic neural network model, and is characterized in that the combination of predicting partial information contents can be completed by judging and accepting or rejecting time series information through a control gate, and the model is characterized by a forgetting gate, an input gate, an output gate and state updating.
Specifically, in this embodiment, the specific steps of obtaining an initial predicted price of the date to be predicted based on the target historical price data and obtaining a predicted booking rate of the date to be predicted based on the target historical booking rate by using the long and short memory neural network model include:
calculating the value f of a forgetting gate of a date to be predictedt，ft＝σ(Wf·[ht-1，xt]+bf)，WfTo forget the weight parameter of the door, bfTo forget the door deviation parameter, ht-1For an output vector a fixed length of time before the date to be predicted, xtThe input vector of the date to be predicted is sigma, and the sigma is a first activation function;
value i of input gate for calculating date to be predictedt，it＝σ(Wi·[ht-1，xt]+bi)，WiTo input the gate weight parameters, biInputting door deviation parameters;
calculating the value o of the output gate of the date to be predictedt，ot＝σ(Wo·[ht-1，xt]+bo)，WoTo output the gate weight parameters, boThe deviation parameter of the output gate is;
calculating the value C of the current state of the date to be predictedt，
WcIs a state weight parameter, bcA state bias parameter, tanh being a second activation function;
calculating an initial predicted price or predicted booking rate h for a date to be predictedt，ht＝ot·tanh(Ct)。
Step S104: and comparing the predicted booking rate with the expected booking rate acquired in advance to determine a price adjusting coefficient, and adjusting the initial predicted price according to the price adjusting coefficient to obtain the final predicted price.
Wherein, the booking rate refers to the ratio of the number of booked current house types to the total number of current house types.
Specifically, after the predicted booking rate is obtained, the predicted booking rate is compared with a pre-acquired expected booking rate, wherein the expected booking rate can be preset by a user, and the initial predicted price is adjusted according to the relation between the predicted booking rate and the expected booking rate, so that the hotel income is improved under the condition that the satisfaction of the client is ensured.
Specifically, the step S104 specifically includes:
1. and taking the ratio of the absolute value of the difference between the predicted booking rate and the expected booking rate to the expected booking rate as a price adjusting coefficient.
For example, when the predicted booking rate is 70% and the expected booking rate is 80%, the price adjustment coefficient is: 70% -80% |/80% >, 12.5%.
2. And when the predicted booking rate is higher than the expected booking rate, carrying out price up-regulation on the initial predicted price according to the price regulation coefficient to obtain the final predicted price.
Specifically, when the predicted booking rate is higher than the expected booking rate, it indicates that the current customer source is good, and in order to maximize the hotel profit, the price may be adjusted up according to the price adjustment coefficient, for example, when the initial predicted price is 500 yuan and the price adjustment coefficient is 12.5%, the final predicted price after the adjustment up is: 500 × (100% + 12.5%) -562.5.
3. When the predicted booking rate is lower than the expected booking rate, if the difference value between the predicted booking rate and the expected booking rate does not exceed a preset threshold value, carrying out price down-regulation on the initial predicted price according to a price regulation coefficient to obtain a final predicted price; and if the difference value between the predicted booking rate and the expected booking rate exceeds a preset threshold value, taking the preset guaranteed price as the final predicted price.
Specifically, when the predicted booking rate is lower than the expected booking rate, which indicates that the current customer resource situation is not ideal, in order to attract the customer resources and increase the profit as much as possible, the price may be adjusted downward according to the price adjustment coefficient, for example, when the initial predicted price is 500 yuan and the price adjustment coefficient is 12.5%, the final predicted price after the downward adjustment is: 500 x (100% -12.5%) 437.5. It should be understood that in some special cases, a temporary large amount of missing of the customer source may occur, which results in a predicted booking rate being significantly lower than the expected booking rate, and at this time, if the price is adjusted according to the price adjustment coefficient obtained from the predicted booking rate and the expected booking rate, the price may be significantly dropped, which results in a loss situation, so that when the difference value between the predicted booking rate and the expected booking rate exceeds the preset threshold value, the preset guaranteed price is directly used as the final predicted price.
Further, after obtaining the final predicted price, the method further includes:
1. and obtaining historical user data of the target house type, and dividing the historical user data according to preset user labels to obtain a plurality of user groups.
Specifically, the historical user data includes characteristic data of the user's name, age, gender, and the like. Specifically, the predicted user tag may be set according to a single feature data, or may be set according to a plurality of feature data, for example, when the preset user tag is set according to age individually, the preset user tag includes age tags corresponding to a plurality of age groups, such as a youth tag, a middle-aged tag, and an old tag, and when the preset user tag is set according to a combination of feature data, such as a youth tag, a girl middle-aged tag, a male middle-aged tag, and a male old tag.
2. And selecting a target user group with the number of users lower than a preset group number threshold from the plurality of user groups, and acquiring a target user label corresponding to the target user group.
Specifically, the preset group number threshold is preset, the target user group is one of a plurality of user groups, the preset group number thresholds corresponding to each user group are different, and when the number of the target user group is lower than the preset group number threshold, it is indicated that the number of target house types subscribed by the user group is less, and the possibility of customer loss exists. The target user label is a preset user label corresponding to the target user group.
3. And calculating the average value of the historical price data of the target user group, calculating the difference between the average value and the final predicted price, and setting a user preference strategy according to the difference.
Specifically, the average value of the historical price data of the target user group may reflect to some extent that the target user group prefers the target house type of the price segment, and therefore, when the price is in the price segment, the probability of ordering the order by the user is higher. Therefore, after the final predicted volume price is obtained, a corresponding user preference strategy is set for each target user group according to the average value of the target user groups and the difference of the final predicted price, and therefore ordering of users of each target group is attracted.
Preferably, the user preference policy is a coupon, and the coupon quota is the same as the allowance.
4. And when the user conforming to the target user label browses the target house type, sending the preferential strategy to the user.
Specifically, when a user clicks and browses a target house type, user data is obtained, which user group the user belongs to is confirmed according to the user data, and when the user group has a corresponding user preference policy, the user preference policy is pushed to the user.
In the embodiment, after the user is divided into a plurality of groups according to the preset user tags, the corresponding preferential strategies are respectively set for each user group, and when the user browses the target house type, the corresponding preferential strategies can be received, so that the current user is attracted to place an order, and the booking success rate of the target house type is improved.
According to the hotel room type pricing method, after historical sales data of a hotel are divided according to a period, the price and the booking rate of a target room type on a date to be predicted are predicted by utilizing similar characteristics on the period, an initial predicted price and a predicted booking rate are obtained, an expected booking rate is compared with the predicted booking rate to confirm a price adjusting coefficient, the initial predicted price is adjusted according to the price adjusting coefficient, and a final predicted price is obtained.
Fig. 2 is a flow chart of a hotel room type pricing method according to a second embodiment of the present invention. It should be noted that the method of the present invention is not limited to the flow sequence shown in fig. 2 if the results are substantially the same. As shown in fig. 2, the method comprises the steps of:
step S201: and acquiring target historical price data and a target historical booking rate of the target house type on the same date as the previous period corresponding to the date to be predicted at a preset period.
In this embodiment, step S201 in fig. 2 is similar to step S101 in fig. 1, and for brevity, is not described herein again.
Step S202: and based on a pre-trained price prediction model, predicting by using target historical price data to obtain the initial predicted price of the target house type of the date to be predicted, and training the price prediction model according to the historical price data of various house types.
In this embodiment, step S202 in fig. 2 is similar to step S102 in fig. 1, and for brevity, is not described herein again.
Step S203: and based on a pre-trained booking rate prediction model, predicting the predicted booking rate of the target house type on the date to be predicted by using the target historical booking rate, wherein the booking rate prediction model is obtained by training according to the historical booking data of various house types.
In this embodiment, step S203 in fig. 2 is similar to step S103 in fig. 1, and for brevity, is not repeated herein.
Step S204: and comparing the predicted booking rate with the expected booking rate acquired in advance to determine a price adjusting coefficient, and adjusting the initial predicted price according to the price adjusting coefficient to obtain the final predicted price.
In this embodiment, step S204 in fig. 2 is similar to step S104 in fig. 1, and for brevity, is not described herein again.
Step S205: and acquiring a plurality of historical price data of the target house type and a plurality of historical periods corresponding to the date to be predicted, wherein the historical periods have the same date, and determining the price fluctuation range by using the minimum historical price data and the maximum historical price data.
Specifically, the present embodiment preferably determines the price fluctuation range with the minimum and maximum historical price data among the historical price data on the same date of a plurality of historical periods that are the latest date to be predicted as a reference.
Step S206: and judging whether the final predicted price falls into the price fluctuation range.
Step S207: if the final predicted price does not fall into the price fluctuation range, when the final predicted price is lower than the minimum price value of the price fluctuation range, taking the minimum price value as the final predicted price; and when the final predicted price is higher than the maximum price value of the price fluctuation range, taking the maximum price value as the final predicted price.
Specifically, when the final predicted price does not fall within the price fluctuation range, it indicates that the price prediction result has a large fluctuation, and therefore, when the final predicted price is lower than the minimum price value of the price fluctuation range, the minimum price value is taken as the final predicted price; when the final predicted price is higher than the maximum price value of the price fluctuation range, the maximum price value is taken as the final predicted price, so that the price fluctuation is within a certain range.
According to the hotel room type pricing method provided by the second embodiment of the invention, on the basis of the first embodiment, the final predicted price is limited through the price fluctuation range obtained based on the historical price data, so that sudden price fluctuation is avoided, the price prediction rationality is ensured, and the possibility of price abnormity is reduced.
Fig. 3 is a flowchart illustrating a hotel room type pricing method according to a third embodiment of the present invention. It should be noted that the method of the present invention is not limited to the flow sequence shown in fig. 3 if the results are substantially the same. As shown in fig. 3, the method comprises the steps of:
step S301: and acquiring target historical price data and a target historical booking rate of the target house type on the same date as the previous period corresponding to the date to be predicted at a preset period.
In this embodiment, step S301 in fig. 3 is similar to step S101 in fig. 1, and for brevity, is not described herein again.
Step S302: and based on a pre-trained price prediction model, predicting by using target historical price data to obtain the initial predicted price of the target house type of the date to be predicted, and training the price prediction model according to the historical price data of various house types.
In this embodiment, step S302 in fig. 3 is similar to step S102 in fig. 1, and for brevity, is not described herein again.
Step S303: and based on a pre-trained booking rate prediction model, predicting the predicted booking rate of the target house type on the date to be predicted by using the target historical booking rate, wherein the booking rate prediction model is obtained by training according to the historical booking data of various house types.
In this embodiment, step S303 in fig. 3 is similar to step S103 in fig. 1, and for brevity, is not described herein again.
Step S304: and comparing the predicted booking rate with the expected booking rate acquired in advance to determine a price adjusting coefficient, and adjusting the initial predicted price according to the price adjusting coefficient to obtain the final predicted price.
In this embodiment, step S304 in fig. 3 is similar to step S104 in fig. 1, and for brevity, is not described herein again.
Step S305: and acquiring all price data of the same house type of all hotels meeting preset conditions in a preset radius range on the date to be predicted by taking the geographic position of the hotel as the center of a circle.
The preset condition refers to a hotel with hardware facilities and service conditions similar to each other, or a hotel with similar star level.
Step S306: and performing K-Means clustering on all price data to obtain a plurality of clustering clusters.
Specifically, after all price data are obtained, each price data is regarded as an object point, a plurality of points are randomly selected from the object points to serve as initial clustering centers, then the distance from other object points to each clustering center is calculated, and the other object points are classified into the class where the clustering center closest to the other object points is located; and calculating the coordinate average value of all the points in each cluster, taking the average value as a new cluster center, repeatedly clustering the points by using the new cluster center, and adjusting the position of the cluster center until the cluster center does not move in a large range any more or the clustering frequency reaches the preset requirement, thereby finally obtaining a plurality of cluster clusters.
Step S307: and judging whether the final predicted price is in the maximum cluster. If yes, the final prediction result is directly input without correcting the final prediction price. If not, go to step S308.
Step S308: and calculating a target point which is closest to the point corresponding to the final predicted price in the maximum clustering cluster, and taking the price corresponding to the target point as the final predicted price.
Specifically, in the embodiment, in addition to the historical price data of the hotel itself as a reference, the reference can be made according to other hotels around the hotel to ensure that the finally set price is reasonable, the method comprises the steps of acquiring price data of other hotels in a preset range around the hotel, clustering the price data, judging whether the final predicted price is in the maximum cluster, wherein, the maximum cluster can reflect the price trend of the target house type in the region to a certain extent, therefore, in order to enhance the competitiveness with the surrounding hotels and avoid the problems of low booking rate caused by high price or poor income caused by low price, and when the final predicted price is not in the maximum cluster, calculating a target point which is closest to the point corresponding to the final predicted price in the maximum cluster, and taking the price corresponding to the target point as the final predicted price. According to the hotel room type pricing method provided by the third embodiment of the invention, on the basis of the first embodiment, reference is made according to other hotels around the hotel, so that the final predicted price not only has competitiveness with the surrounding hotels, but also can ensure the income of the hotel to a certain extent, and the rationality of the hotel price setting is further improved.
Fig. 4 is a functional block diagram of a hotel room type pricing apparatus according to an embodiment of the present invention. As shown in fig. 4, the hotel room type pricing apparatus 40 includes an obtaining module 41, a first forecasting module 42, a second forecasting module 43, and an adjusting module 44.
An obtaining module 41, configured to obtain, at a preset period, target historical price data and a target historical booking rate of a target house type on the same date as a previous period corresponding to a date to be predicted;
the first prediction module 42 is used for predicting and obtaining an initial predicted price of a target house type of a date to be predicted by using target historical price data based on a pre-trained price prediction model, and the price prediction model is obtained by training according to the historical price data of various house types;
the second prediction module 43 is configured to predict, based on a pre-trained booking rate prediction model, a predicted booking rate of a target house type of a date to be predicted by using a target historical booking rate, where the booking rate prediction model is obtained by training according to historical booking data of various house types;
and the adjusting module 44 is configured to compare the predicted booking rate with a pre-obtained expected booking rate to determine a price adjusting coefficient, and adjust the initial predicted price according to the price adjusting coefficient to obtain a final predicted price.
Alternatively, the obtaining module 41 performs obtaining the target historical price data and the target historical booking rate of the target house type on the same date as the previous period corresponding to the date to be predicted at a preset period, including: judging whether the date to be predicted is a preset holiday or not; if yes, acquiring target historical price data and a target historical booking rate of the holidays in the same previous historical festival; if not, acquiring the target historical price data and the target historical booking rate of the same date in the previous period.
Optionally, the adjusting module 44 performs an operation of comparing the predicted booking rate with the expected booking rate to determine a price adjusting coefficient, and adjusting the initial predicted price according to the price adjusting coefficient to obtain a final predicted price, which specifically includes: taking the ratio of the absolute value of the difference between the predicted booking rate and the expected booking rate to the expected booking rate as a price adjusting coefficient; when the predicted booking rate is higher than the expected booking rate, carrying out price up-regulation on the initial predicted price according to the price regulation coefficient to obtain a final predicted price; when the predicted booking rate is lower than the expected booking rate, if the difference value between the predicted booking rate and the expected booking rate does not exceed a preset threshold value, carrying out price down-regulation on the initial predicted price according to a price regulation coefficient to obtain a final predicted price; and if the difference value between the predicted booking rate and the expected booking rate exceeds a preset threshold value, taking the preset guaranteed price as the final predicted price.
Optionally, after the adjusting module 44 performs the operation of obtaining the final predicted price, it is further configured to: judging whether the final predicted price falls into the price fluctuation range or not; if the final predicted price does not fall into the price fluctuation range, when the final predicted price is lower than the minimum price value of the price fluctuation range, taking the minimum price value as the final predicted price; and when the final predicted price is higher than the maximum price value of the price fluctuation range, taking the maximum price value as the final predicted price.
Optionally, before the adjusting module 44 performs the operation of determining whether the final predicted price falls within the price fluctuation range, the adjusting module is further configured to: and acquiring a plurality of historical price data of the target house type and a plurality of historical periods corresponding to the date to be predicted, wherein the historical periods have the same date, and determining the price fluctuation range by using the minimum historical price data and the maximum historical price data.
Optionally, after the adjusting module 44 performs the operation of obtaining the final predicted price, it is further configured to: taking the geographical position of the hotel as the center of a circle, acquiring all price data of the same house type of all hotels meeting preset conditions in a preset radius range on a date to be predicted; performing K-Means clustering on all price data to obtain a plurality of clustering clusters; judging whether the final predicted price is in the maximum cluster; if not, calculating a target point which is closest to the point corresponding to the final predicted price in the maximum clustering cluster, and taking the price corresponding to the target point as the final predicted price.
Optionally, after the adjusting module 44 performs the operation of obtaining the final predicted price, it is further configured to: obtaining historical user data of a target house type, and dividing the historical user data according to preset user tags to obtain a plurality of user groups; selecting a target user group with the number of users lower than a preset group number threshold from a plurality of user groups, and acquiring a target user label corresponding to the target user group; calculating the average value of the historical price data of the target user group, calculating the difference between the average value and the final predicted price, and setting a user preferential strategy according to the difference; and when the user conforming to the target user label browses the target house type, sending a preferential strategy to the user. .
For other details of the technical solution implemented by each module in the hotel room type pricing device in the above embodiment, reference may be made to the description of the hotel room type pricing method in the above embodiment, and details are not repeated here.
It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other. For the device-like embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
Referring to fig. 5, fig. 5 is a schematic structural diagram of a computer device according to an embodiment of the present invention. As shown in fig. 5, the computer device 50 comprises a processor 51 and a memory 52 coupled to the processor 51, wherein the memory 52 stores program instructions, and the program instructions, when executed by the processor 51, cause the processor 51 to perform the steps of the hotel room type pricing method according to any of the embodiments described above.
The processor 51 may also be referred to as a CPU (Central Processing Unit). The processor 51 may be an integrated circuit chip having signal processing capabilities. The processor 51 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a storage medium according to an embodiment of the invention. The storage medium of the embodiment of the present invention stores program instructions 61 capable of implementing all the methods described above, where the program instructions 61 may be stored in the storage medium in the form of a software product, and include several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, or computer equipment, such as a computer, a server, a mobile phone, and a tablet.
In the several embodiments provided in the present application, it should be understood that the disclosed computer apparatus, device and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit. The above embodiments are merely examples and are not intended to limit the scope of the present disclosure, and all modifications, equivalents, and flow charts using the contents of the specification and drawings of the present disclosure or those directly or indirectly applied to other related technical fields are intended to be included in the scope of the present disclosure.
Claims (10)
1. A hotel room type pricing method is characterized by comprising the following steps:
acquiring target historical price data and a target historical booking rate of a target house type on the same date of a previous period corresponding to a date to be predicted in a preset period;
based on a price prediction model trained in advance, predicting by using the target historical price data to obtain an initial predicted price of a target house type of a date to be predicted, wherein the price prediction model is obtained by training according to historical price data of various house types;
predicting and obtaining the predicted booking rate of a target house type on a date to be predicted by using the target historical booking rate based on a pre-trained booking rate prediction model, wherein the booking rate prediction model is obtained by training according to historical booking data of various house types;
and comparing the predicted booking rate with a pre-acquired expected booking rate to determine a price adjustment coefficient, and adjusting the initial predicted price according to the price adjustment coefficient to obtain a final predicted price.
2. The hotel room type pricing method according to claim 1, wherein the acquiring the target historical price data and the target historical booking rate of the target room type of the same date as the previous period corresponding to the date to be forecasted at a preset period comprises:
judging whether the date to be predicted is a preset holiday or not;
if yes, acquiring target historical price data and a target historical booking rate of the holidays in the same previous historical festival;
if not, acquiring the target historical price data and the target historical booking rate of the same date in the previous period.
3. The hotel room type pricing method of claim 1, wherein the comparing the predicted booking rate and the expected booking rate to determine a price adjustment coefficient and adjusting the initial predicted price according to the price adjustment coefficient to obtain a final predicted price comprises:
taking a ratio of an absolute value of a difference between the predicted booking rate and the desired booking rate to the desired booking rate as the price adjustment coefficient;
when the predicted booking rate is higher than the expected booking rate, carrying out price up-regulation on the initial predicted price according to the price regulation coefficient to obtain the final predicted price;
when the predicted booking rate is lower than the expected booking rate, if the difference value between the predicted booking rate and the expected booking rate does not exceed a preset threshold value, carrying out price down-regulation on the initial predicted price according to the price regulation coefficient to obtain the final predicted price; and if the difference value between the predicted booking rate and the expected booking rate exceeds a preset threshold value, taking a preset insurance bottom price as the final predicted price.
4. The hotel room type pricing method of claim 1, further comprising, after obtaining the final predicted price:
judging whether the final predicted price falls into a price fluctuation range or not;
if the final predicted price does not fall into the price fluctuation range, taking the minimum price value as the final predicted price when the final predicted price is lower than the minimum price value of the price fluctuation range; and when the final predicted price is higher than the maximum price value of the price fluctuation range, taking the maximum price value as the final predicted price.
5. The hotel room type pricing method of claim 4, wherein before determining whether the final predicted price falls within a price fluctuation range, further comprising:
and acquiring a plurality of historical price data of the target house type and a plurality of historical periods corresponding to the date to be predicted, wherein the historical periods have the same date, and determining the price fluctuation range according to the minimum historical price data and the maximum historical price data.
6. The hotel room type pricing method of claim 1, further comprising, after obtaining the final predicted price:
acquiring all price data of the same house type of all hotels meeting preset conditions in a preset radius range on the date to be predicted by taking the geographic position of the hotel as the center of a circle;
performing K-Means clustering on all the price data to obtain a plurality of clustering clusters;
judging whether the final predicted price is in the maximum cluster;
if not, calculating a target point which is closest to the point corresponding to the final predicted price in the maximum clustering cluster, and taking the price corresponding to the target point as the final predicted price.
7. The hotel room type pricing method of claim 1, further comprising, after obtaining the final predicted price:
obtaining historical user data of the target house type, and dividing the historical user data according to a preset user label to obtain a plurality of user groups;
selecting a target user group with the number of users lower than a preset group number threshold from the plurality of user groups, and acquiring a target user label corresponding to the target user group;
calculating the average value of the historical price data of the target user group, calculating the difference between the average value and the final predicted price, and setting a user preference strategy according to the difference;
and when the user conforming to the target user label browses the target house type, sending the preferential strategy to the user. .
8. A hotel room type pricing device, comprising:
the acquisition module is used for acquiring target historical price data and a target historical booking rate of a target house type on the same date as the previous period corresponding to the date to be predicted in a preset period;
the first prediction module is used for predicting and obtaining an initial prediction price of a target house type of a date to be predicted by using the target historical price data based on a pre-trained price prediction model, and the price prediction model is obtained by training according to the historical price data of various house types;
the second prediction module is used for predicting and obtaining the predicted booking rate of the target house type of the date to be predicted by utilizing the target historical booking rate based on a pre-trained booking rate prediction model, and the booking rate prediction model is obtained by training according to the historical booking data of various house types;
and the adjusting module is used for comparing the predicted booking rate with a pre-acquired expected booking rate to determine a price adjusting coefficient, and adjusting the initial predicted price according to the price adjusting coefficient to obtain a final predicted price.
9. A computer device, characterized in that the computer device comprises a processor, a memory coupled to the processor, in which memory program instructions are stored which, when executed by the processor, cause the processor to carry out the steps of the hotel room type pricing method according to any of claims 1-7.
10. A storage medium storing program instructions capable of implementing the hotel room type pricing method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210102905.4A CN114445138A (en) | 2022-01-27 | 2022-01-27 | Hotel room type pricing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210102905.4A CN114445138A (en) | 2022-01-27 | 2022-01-27 | Hotel room type pricing method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114445138A true CN114445138A (en) | 2022-05-06 |
Family
ID=81370609
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210102905.4A Pending CN114445138A (en) | 2022-01-27 | 2022-01-27 | Hotel room type pricing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114445138A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115953268A (en) * | 2023-01-04 | 2023-04-11 | 广州辰亿信息科技有限公司 | Hotel data processing system based on big data |
| CN116166889A (en) * | 2023-02-21 | 2023-05-26 | 深圳市天下房仓科技有限公司 | Hotel product screening method, device, equipment and storage medium |
-
2022
- 2022-01-27 CN CN202210102905.4A patent/CN114445138A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115953268A (en) * | 2023-01-04 | 2023-04-11 | 广州辰亿信息科技有限公司 | Hotel data processing system based on big data |
| CN115953268B (en) * | 2023-01-04 | 2024-05-24 | 广州辰亿信息科技有限公司 | Hotel data processing system based on big data |
| CN116166889A (en) * | 2023-02-21 | 2023-05-26 | 深圳市天下房仓科技有限公司 | Hotel product screening method, device, equipment and storage medium |
| CN116166889B (en) * | 2023-02-21 | 2023-12-12 | 深圳市天下房仓科技有限公司 | Hotel product screening method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9980011B2 (en) | Sequential delivery of advertising content across media devices | |
| US10812870B2 (en) | Yield optimization of cross-screen advertising placement | |
| CN108476334B (en) | Cross-screen optimization of advertisement placement | |
| US10891592B2 (en) | Electronic job posting marketplace | |
| CN110334289B (en) | Travel destination determining method and target user determining method | |
| CN114445138A (en) | Hotel room type pricing method, device, equipment and storage medium | |
| US20170004404A1 (en) | Demand prediction method, demand prediction apparatus, and non-transitory computer-readable recording medium | |
| US20190279297A1 (en) | Credit scoring method and server | |
| US20200279191A1 (en) | Personalized merchant scoring based on vectorization of merchant and customer data | |
| US11521243B2 (en) | Method and apparatus for managing allocations of media content in electronic segments | |
| CN109685234B (en) | Processing method and system for hotel room reservation | |
| EP3403411A1 (en) | Yield optimization of cross-screen advertising placement | |
| JP4804372B2 (en) | Advertisement distribution order determination method, advertisement distribution system, advertisement distribution order determination apparatus, and computer program | |
| US20220327495A1 (en) | Intelligent scheduling using a prediction model | |
| CN111566684A (en) | Method and system for optimizing user grouping of advertisements | |
| CN110880127A (en) | Consumption level prediction method and device, electronic equipment and storage medium | |
| CN111429054A (en) | Product inventory prompting method, device, equipment and storage medium | |
| Das et al. | A framework of hiring strategy for manpower hiring in a hyper-local food delivery organization | |
| CN116739665A (en) | Information delivery method and device, electronic equipment and storage medium | |
| Prakash et al. | BayesRec: Personalize search ranking with customer attribute-level willingness-to-pay using heterogeneous booking choice data | |
| US11631102B2 (en) | Optimization of markdown schedules for clearance items at physical retail stores | |
| US20230259846A1 (en) | Communications apparatus and method for estimating potential demand for improved forecasting and resource management | |
| CN113946753B (en) | Service recommendation method, device, equipment and storage medium based on location fence | |
| US20210304279A1 (en) | Information processing method, electronic device and computer-readable storage medium | |
| CN115374361A (en) | House lease information recommendation method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220506 |
|
| RJ01 | Rejection of invention patent application after publication |