CN114706862A - Hotel room state prediction method, device, equipment and storage medium - Google Patents
Hotel room state prediction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114706862A CN114706862A CN202210101416.7A CN202210101416A CN114706862A CN 114706862 A CN114706862 A CN 114706862A CN 202210101416 A CN202210101416 A CN 202210101416A CN 114706862 A CN114706862 A CN 114706862A
- Authority
- CN
- China
- Prior art keywords
- preset
- probability
- order
- ordering
- date
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000012549 training Methods 0.000 claims description 14
- 238000012790 confirmation Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 6
- 230000006872 improvement Effects 0.000 description 6
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000012423 maintenance Methods 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
- 230000002123 temporal effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
- G06F16/2379—Updates performed during online database operations; commit processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a hotel room state prediction method, a hotel room state prediction device, hotel room state prediction equipment and a hotel room state prediction storage medium, wherein the method comprises the following steps: acquiring first historical order data of a preset large customer and second historical order data of a common customer; predicting the ordering probability and the booking quantity of the big client on the date to be predicted according to the first historical order data and a pre-trained big client ordering prediction model; setting the number of bookable rooms, wherein when the lower single probability exceeds a first preset threshold value, the number of bookable rooms is set as the difference value between the maximum number of rooms and the bookable number; when the lower order probability does not exceed a first preset threshold, the number of bookable rooms is set as the maximum number of rooms; predicting the full room probability of the date to be predicted according to the number of the rooms which can be reserved, the second historical order data and a pre-trained full room probability prediction model; and confirming the house state information of the date to be predicted according to the full house probability. By the method, the full house prediction can be performed on house types in time, and warning is performed in advance.
Description
Technical Field
The application relates to the technical field of hotel management, in particular to a hotel room state prediction method, a hotel room state prediction device, hotel room state prediction equipment and a hotel room state prediction storage medium.
Background
With the development of networks, at present, a plurality of enterprises provide services for reserving wineshops for consumers on the internet, but due to untimely room maintenance state of a hotel supplier, over-sale of the hotel and the like, the defects of full room before order confirmation or after order confirmation and the like are easily caused, so that the single ordering experience of a user is seriously influenced, and the enterprise image of the hotel on an OTA (on-line travel website) platform is also influenced.
At present, on most of the booking platforms, because the technology is lack, only the room state can be manually maintained, the room state information on the OTA platform is not updated timely, and further the situation that the room is over-sold or over-ordered possibly occurs is caused, so that the user experience is poor, especially for a big client, when the booking request of the big client cannot be met, the loss of the big client is easily caused, and the loss of a hotel is caused, so that the problem that how to update the room state information of the room prepared for a common client on the OTA platform in time under the condition of ensuring the rights and interests of the big client becomes urgent to be solved by the OTA platform.
Disclosure of Invention
The application provides a hotel room status prediction method, a hotel room status prediction device, hotel room status prediction equipment and a storage medium, which are used for solving the problem that hotel room status information cannot be maintained in time under the condition that the rights and interests of large clients are guaranteed.
In order to solve the technical problem, the application adopts a technical scheme that: provided is a liquor shop state prediction method, including: acquiring first historical order data of a preset large customer and second historical order data of a common customer; predicting the ordering probability and the booking quantity of the big clients on the date to be predicted according to the first historical order data and a pre-trained big client ordering prediction model, wherein the big client ordering prediction model is obtained by training according to the historical order data of all the big clients; setting the number of bookable rooms, wherein when the lower single probability exceeds a first preset threshold value, the number of bookable rooms is set as the difference value between the maximum number of rooms and the booked number; when the lower order probability does not exceed a first preset threshold, the number of the presettable rooms is set as the maximum number of rooms; predicting the full room probability of the date to be predicted according to the number of the rooms which can be reserved, second historical order data and a pre-trained full room probability prediction model, wherein the full room probability prediction model is obtained by training according to the historical order data of all common customers; and confirming the house state information of the date to be predicted according to the full house probability.
As a further improvement of the present application, the method for predicting the probability of full room on the date to be predicted according to the number of bookable rooms, the second historical booking data and the pre-trained full room probability prediction model comprises the following steps: acquiring target historical order data which takes a preset period as an interval and has the same date as the previous period corresponding to the date to be predicted from the second historical order data; and inputting the target historical order data and the number of the bookable rooms into the full room probability prediction model to obtain the full room probability.
As a further improvement of the present application, acquiring, from the second historical order data, the target historical order data on the same date as the previous cycle corresponding to the date to be predicted at intervals of a preset cycle, includes: judging whether the date to be predicted is a preset holiday or not; if yes, acquiring target historical order data of the holidays of the same previous history section; if not, target historical order data of the same date in the previous period is obtained.
As a further improvement of the application, after confirming the room state information of the date to be predicted according to the full room probability, the method further comprises the following steps: and after a new ordering request is received, updating the room state information of the date to be predicted according to the ordering request.
As a further improvement of the present application, after receiving a new ordering request, before updating the room status information of the date to be predicted according to the ordering request, the method further includes: when the full room probability exceeds a second preset threshold value, if an order placing request of a current order placing client is received, obtaining third historical order data of the current order placing client; predicting whether the current order placing client can perform an order releasing operation aiming at the order placing request or not according to the third history order data; when the current ordering client is predicted to be unsubscribed, rejecting an ordering request of the current ordering client; and when the current ordering client is predicted not to unsubscribe, accepting the ordering request of the current ordering client.
As a further improvement of the present application, predicting whether a current order placing client will perform an unsubscribe operation on an order placing request according to third history order data includes: acquiring the total order number according to the third history order data, and dividing the third history order data according to preset dimensions and preset levels corresponding to the preset dimensions to obtain the in-call order number and the out-call order number of each preset level of each preset dimension, wherein the preset dimensions comprise at least one preset order characteristic, and the preset order characteristic comprises a plurality of preset levels set based on preset rules; calculating to obtain the entrance degree of each preset grade of each preset dimension according to the entrance order number and the total order number corresponding to each preset grade of each preset dimension, and calculating to obtain the withdrawal degree of each preset grade of each preset dimension according to the withdrawal order number and the total order number corresponding to each preset grade of each preset dimension; extracting target dimensions and target grades corresponding to each target dimension from ordering request data, and confirming the target admission degree and the target unsubscribing degree of the target grades of each target dimension; accumulating the target entrance degree and the target unsubscribe degree respectively to obtain a first total entrance degree and a first total unsubscribe degree; when the first total entrance degree is higher than the first total unsubscribe degree, predicting that the current order-placing client cannot unsubscribe; and when the first total occupancy is lower than the first total unsubscribe degree, predicting that the current ordering client can unsubscribe.
As a further improvement of the application, after rejecting the new order request of the current order-placing client, the method further comprises the following steps: acquiring all current bookable house type data, and confirming a second total check-in degree and a second total unsubscribing degree of each bookable house type data according to the check-in degree and the unsubscribing degree of each preset grade of each preset dimension of the current ordering client; screening target bookable house type data with the second total entrance degree higher than the second total unsubscribing degree; sorting the target bookable house type data according to the difference value of the second total entrance degree and the second total unsubscribing degree from high to low; and selecting the target bookable house type data with the highest ranking to generate recommended content and sending the recommended content to the ordering terminal of the current ordering client.
In order to solve the above technical problem, another technical solution adopted by the present application is: provided is a hotel room status prediction device, including: the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring first historical order data of a preset large customer and second historical order data of a common customer; the first prediction module is used for predicting the order placing probability and the reserved quantity of the big clients on the date to be predicted according to the first historical order data and a pre-trained big client order placing prediction model, and the big client order placing prediction model is obtained by training according to the historical order data of all the big clients; the setting module is used for setting the number of the bookable rooms, and when the lower single probability exceeds a first preset threshold value, the number of the bookable rooms is set as the difference value between the maximum number of the rooms and the bookable number; when the lower order probability does not exceed a first preset threshold, the number of bookable rooms is set as the maximum number of rooms; the second prediction module is used for predicting the full room probability of the date to be predicted according to the number of the rooms which can be reserved, second historical order data and a pre-trained full room probability prediction model, and the full room probability prediction model is obtained by training according to the historical order data of all common customers; and the confirmation module is used for confirming the house state information of the date to be predicted according to the full house probability.
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, the memory having stored therein program instructions which, when executed by the processor, cause the processor to perform the steps of the hotel room status prediction method as described above.
In order to solve the above technical problem, the present application adopts another technical solution that: a storage medium is provided that stores program instructions that enable the aforementioned hotel room status prediction method.
The beneficial effect of this application is: according to the hotel room state prediction method, the order placing probability and the booking quantity of the large clients are obtained by predicting according to the first historical order data of the large clients, when the order placing probability exceeds a first preset threshold value, room reservation is carried out on the large clients according to the booking data, then room full probability prediction is carried out by combining the room left after reservation and the second historical order data of the common clients, therefore, workers can know the possibility of full room on the date to be predicted and timely maintain room state information on the date with high room full probability, the possibility of full room overdubbing or full room oversaled is avoided, under the condition that the benefit of the large clients is guaranteed, prediction of the room state information is achieved, and user experience is better.
Drawings
Fig. 1 is a schematic flow chart of a hotel room status prediction method according to a first embodiment of the present invention;
fig. 2 is a schematic flow chart of a hotel room status prediction method according to a second embodiment of the present invention;
fig. 3 is a functional block diagram of a hotel room status prediction apparatus according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a computer device according to an embodiment of the present invention;
fig. 5 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 some embodiments of the present application, and not all 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 a relative importance or an implicit 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 indicators (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 indicator is changed accordingly. Furthermore, the terms "comprising" and "having," 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 schematic flow chart of a hotel room status prediction method according to a first embodiment of the present invention. It is noted that the method of the present invention is not limited to the flow sequence shown in FIG. 1 if substantially the same results are obtained. As shown in fig. 1, the method comprises the steps of:
step S101: the method comprises the steps of obtaining first historical order data of a preset large customer and second historical order data of a common customer.
It should be noted that the preset large client in this embodiment may be a client who performs large order ordering and signs a contract in advance, or may be a client who frequently places orders and places a large number of orders by analyzing historical order data. The ordinary customers are the customers who make orders only occasionally.
Specifically, when the house state information of the date to be predicted needs to be predicted, historical order data within a last preset time from the current moment is selected, and then first historical order data belonging to a large customer and second historical order data belonging to a common customer are selected.
Step S102: and predicting the order placing probability and the reserved quantity of the big clients on the date to be predicted according to the first historical order data and a pre-trained big client order placing prediction model, wherein the big client order placing prediction model is obtained by training according to the historical order data of all the big clients.
Specifically, after first historical order data of the large clients are obtained, the first historical order data are input into a pre-trained large client ordering prediction model for prediction, and therefore the ordering probability and the ordering number of the large clients on the date to be predicted are obtained.
Wherein the large customer ordering prediction model is implemented based on an LSTM model. The LSTM model is a neural network based on temporal recursion, suitable for handling and predicting important events with relatively long intervals and delays in the sequence of dates to be predicted. The LSTM model has found many applications in the scientific field. The LSTM model based system may learn tasks such as translating languages, controlling robots, image analysis, document summarization, speech recognition image recognition, handwriting recognition, controlling chat robots, predicting diseases, etc. 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. Forgetting gate is denoted ft＝σ(Wf·[ht-1，wx]+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; input gate is denoted as it＝σ(Wi· [ht-1，xt]+bi)，WiTo input the gate weight parameters, biInputting door deviation parameters; output gate denoted ot＝σ(Wo·[ht-1，xt]+bo)，WoTo output the gate weight parameters, boThe deviation parameter of the output gate is; the current state is denoted Ct，
WcIs a state weight parameter, bcA state bias parameter, tanh being a second activation function; the prediction result is expressed as ht＝ot·tanh(Ct)。
Step S103: setting the number of bookable rooms, wherein when the lower single probability exceeds a first preset threshold value, the number of bookable rooms is set as the difference value between the maximum number of rooms and the bookable number; when the lower probability of ordering does not exceed the first preset threshold, the number of bookable rooms is set to the maximum number of rooms.
It should be noted that the first preset threshold is set according to the experience of the user. The maximum number of rooms may be one set by the hotel party or the maximum number of empty rooms available for the hotel to book.
Specifically, after the order placing probability and the reservation number of the large client are obtained, if the order placing probability is higher than a first preset threshold, the order placing probability of the large client is considered to be high, and rooms are reserved for the large client in order to guarantee the rights and benefits of the large client, so that the number of the bookable rooms on the platform is the difference value between the maximum number of the rooms and the reservation number, and if the order placing probability is lower than the first preset threshold, the order placing probability of the large client is considered to be low, and therefore the rooms do not need to be reserved, the maximum room data of the hotel is set as the number of the bookable rooms.
Step S104: and predicting the full room probability of the date to be predicted according to the number of the rooms which can be reserved, the second historical order data and a pre-trained full room probability prediction model, wherein the full room probability prediction model is obtained by training according to the historical order data of all common customers.
Specifically, after the number of bookable rooms is obtained, forecasting is carried out by combining second historical order data of common customers and a pre-trained full room probability forecasting model, and therefore the full room probability of the date to be forecasted is confirmed.
The full-room probability prediction model is realized based on an XGboost model. The XGboost model is a decision tree algorithm based on iterative accumulation, and mainly accumulates results of a plurality of decision trees as a final prediction result by constructing a group of weak learners. The target algorithm for Xgboost is:
wherein,
representing the predicted value of a sample i, k representing the total number of decision trees, and n representing the number of samples; y denotes the true value of the sample, Ω (f)k) Is the complexity of the K-th decision, T represents the number of leaf nodes of the K-th decision, ωjThe representation prediction is worth regularizing.
Further, in a general case, the hotel booking data presents a periodic similarity degree in a preset period with a fixed time length, the fixed time length may be one week, one month, and the like, for example, booking cases of various hotel room types present a high similarity degree in a period with a week unit, or a booking case of a room type of a day of the week may refer to a booking case of a room type of a last week to a great extent, and therefore, in order to improve the prediction accuracy, in some embodiments, the step of predicting the full room probability of the date to be predicted according to the bookable room number, the second historical order data and the pre-trained full room probability prediction model specifically includes:
1. and acquiring target historical order data which takes a preset period as an interval and has the same date as the previous period corresponding to the date to be predicted from the second historical order data.
Specifically, when a room state prediction request of a date to be predicted is received, target historical order data of the same date corresponding to the date to be predicted in the previous cycle is inquired from second historical order data, and the target historical order data is used as reference data. And then carrying out characteristic engineering on the target history order data and the number of the rooms which can be reserved to obtain first characteristic engineering data, and taking the first characteristic engineering data as the input of a full room probability prediction model, wherein the first characteristic engineering data comprises the following components: the target historical order number, the bookable room number, the date characteristic value of the date to be predicted (date characteristic values 1, 2, 3, …, N, N are set in order for the date in the preset period, where the preset period is preferably set to one week, that is, N is set to 7, and thus, the characteristic values of 1, 2, 3, 4, 5, 6, 7 are set in order for Monday to Sunday, for example, if the date is Monday, the characteristic value of the date is set to 1, and if the date is Tuesday, the characteristic value of the date is set to 2), the holiday characteristic value (the date is divided into holiday and non-holiday, the characteristic value of holiday is set to 1, and the characteristic value of non-holiday is set to 0)
Further, acquiring historical target order data with the same date as the previous period corresponding to the date to be predicted at intervals of a preset period from the second historical order data, includes:
1.1, judging whether the date to be predicted is a preset holiday.
And 1.2, if so, acquiring the target historical order data of the holiday of the same previous historical festival.
And 1.3, if not, acquiring the target historical order data of the same date in the previous period.
It should be understood that the preset holiday in this embodiment refers to special holidays such as fifths, mid-autumn holidays and national celebrations, for such holidays, due to the tourists playing and other reasons, the hotel reservation may have a peak increase different from other time points, and therefore, the historical order data in the holidays other than such holidays lack a reference value, and in this embodiment, when the date to be predicted is determined to be the preset holiday, the target historical order data of the same holiday is referred to, instead of the target historical order data of the same date in the previous period.
2. And inputting the target historical order data and the number of the bookable rooms into the full room probability prediction model to obtain the full room probability.
Step S105: and confirming the house state information of the date to be predicted according to the full house probability.
Specifically, after the full-house probability is obtained, the full-house probability is compared with a preset full-house probability threshold, when the full-house probability is higher than the preset full-house probability threshold, it is considered that the full-house situation occurs on the date to be predicted, and when the full-house probability is lower than the preset full-house probability threshold, it is considered that the date to be predicted is not full. And setting a proper room state updating frequency for the date to be predicted according to whether the room is full, and updating the room state information at a higher frequency when the room is full on the date to be predicted so as to ensure that the room state information is updated in time and avoid overbooking. When the forecast date is less than the full house, the possibility of the overbooking condition is low, so that the house state information can be updated at a low frequency, and the occupation of process system resources to perform updating operation is avoided.
According to the hotel room state prediction method provided by the first embodiment of the invention, the order placing probability and the booking quantity of the large client are obtained by predicting according to the first history order data of the large client, when the order placing probability exceeds the first preset threshold value, the room reservation is carried out on the large client according to the booking data, and then the full room probability prediction is carried out by combining the room left after the reservation and the second history order data of the common client, so that a worker can know the possibility of full room appearing on the date to be predicted and timely maintain the room state information on the date with high full room probability, the possibility of full room overdubbing or full room oversaled is avoided, the prediction on the room state information is realized under the condition of ensuring the rights and interests of the large client, and the user experience is better.
Fig. 2 is a flowchart illustrating a hotel room status prediction method according to a second embodiment of the present invention. It is 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: the method comprises the steps of obtaining first historical order data of a preset large customer and second historical order data of a common customer.
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 predicting the order placing probability and the reserved quantity of the large clients on the dates to be predicted according to the first historical order data and the pre-trained large client order placing prediction model, and training the large client order placing prediction model according to the historical order data of all the large clients to obtain the large client order placing prediction model.
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: setting the number of bookable rooms, wherein when the lower single probability exceeds a first preset threshold value, the number of bookable rooms is set as the difference value between the maximum number of rooms and the bookable number; when the lower probability of ordering does not exceed the first preset threshold, the number of bookable rooms is set to the maximum number of rooms.
In this embodiment, step S203 in fig. 2 is similar to step S103 in fig. 1, and for brevity, is not described herein again.
Step S204: and predicting the full room probability of the date to be predicted according to the number of the rooms which can be reserved, the second historical order data and a pre-trained full room probability prediction model, wherein the full room probability prediction model is obtained by training according to the historical order data of all common customers.
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 confirming the house state information of the date to be predicted according to the full house probability.
In this embodiment, step S205 in fig. 2 is similar to step S105 in fig. 1, and for brevity, is not described herein again.
Step S206: and when the full room probability exceeds a second preset threshold value, if an order placing request of the current order placing client is received, acquiring third history order data of the current order placing client.
It should be noted that the customer may also perform an unsubscription operation after placing an order, and the unsubscription operation may possibly affect the income of the hotel, so that in order to ensure the income of the hotel, the condition of unsubscription of the customer needs to be avoided as much as possible.
Wherein the second preset threshold is preset. When the probability of full housing exceeds a second preset threshold value, the date to be predicted is considered to have a full housing condition, and if an unsubscribe condition occurs, part of clients may unsubscribe and unsubscribe, leaving empty housings, and another client cannot check in due to unsuccessfully booked, which causes waste. At this time, when a request for placing an order is received from a current customer for placing an order, third history order data of the current customer for placing an order is acquired for analyzing the possibility of check-in and the possibility of unsubscription of the current customer for placing an order.
Further, when the full room probability does not exceed a second preset threshold, if an order placing request of a current order placing client is received, the order placing request is directly received.
Specifically, when the probability of full housing does not exceed the second preset threshold, it is indicated that the possibility of full housing of the date to be predicted is low, and there is no need to worry about the occurrence of the overdue condition of full housing, and therefore, the ordering request can be directly received.
Step S207: and predicting whether the current ordering client can perform an order releasing operation aiming at the ordering request or not according to the third history ordering data. When the customer for the current order is predicted to unsubscribe, executing step S208; when it is predicted that the currently ordering customer will not unsubscribe, step S209 is performed.
Specifically, after the third history order data of the current ordering client is acquired, analysis is performed based on the third history order data, so as to determine whether the current ordering client performs an order cancellation operation for the ordering request.
Further, predicting whether the current ordering client will perform an unsubscribing operation for the ordering request according to the third history ordering data specifically includes:
1. acquiring the total order number according to the third history order data, and dividing the third history order data according to the preset dimensionality and the preset grade corresponding to the preset dimensionality to obtain the incoming order number and the outgoing order number of each preset grade of each preset dimensionality, wherein the preset dimensionality comprises at least one preset order characteristic, and the preset order characteristic comprises a plurality of preset grades set based on preset rules.
It should be noted that the total order number refers to all historical order numbers of the current ordering clients, and the preset dimension refers to a dimension set according to hotel characteristic data, in this embodiment, the preset dimension includes at least one of a hotel room type, a hotel price, and a hotel star level, and the preset grade is a preset order characteristic divided for each preset dimension, for example, for the hotel room type dimension, the corresponding preset grade may be divided into a large bed room, a single room, a double room, a business room, a presidential suite, and the like, for the hotel price, the corresponding preset grade may be divided into 100 yuan or less, 100 to 200 yuan, 200 to 300 yuan, 300 to 500 yuan, 500 yuan or more, and the preset grade may be directly divided according to the star level for the hotel star level. The number of orders placed in the house refers to the number of historical orders placed in the house by the customer and successfully placed in the house, and the number of orders placed in the house refers to the number of historical orders placed in the house by the customer, which are not placed in the house, but are placed in the house. It should be understood that the hotel room type, hotel price and hotel star rating can all be obtained from historical order data.
Specifically, after the third history order data of the current ordering client is obtained, the total order number of the history orders of the current ordering client is obtained, and then the third history order data is divided according to the preset dimension and the preset grade, so that the check-in order number and the check-out order number of each preset grade of each preset dimension, for example, the check-in order number and the check-out order number of a large bed room with hotel room type dimension, are obtained.
2. And calculating the entrance degree of each preset grade of each preset dimension according to the entrance order number and the total order number corresponding to each preset grade of each preset dimension, and calculating the withdrawal degree of each preset grade of each preset dimension according to the withdrawal order number and the total order number corresponding to each preset grade of each preset dimension.
Specifically, the degree of occupancy of the preset level of each preset dimension is equal to the amount of occupancy/total amount of the preset level of each preset dimension; the default grade of each default dimension is the default grade of each default dimension, i.e. the default quantity of the back orders/the total orders. It should be understood that the check-in degree of the preset level of each preset dimension reflects the check-in possibility of the client to the preset level of the preset dimension to a large extent, and the unsubscribe degree reflects the unsubscribe possibility of the client to the preset level of the preset dimension. And obtaining the entrance degree and the withdrawal degree corresponding to each preset grade of each preset dimension of the current ordering client through the third history order data of the current ordering client.
3. And extracting target dimensions and target grades corresponding to each target dimension from the ordering request data, and confirming the target admission degree and the target unsubscribing degree of the target grades of each target dimension.
Specifically, target levels of each preset dimension selected by the current order customer when ordering this time are obtained from the order ordering request data, for example, the order ordering request data is assumed to be: a350-yuan one-night large bed room of the three-star hotel has the characteristics that the hotel room type dimension is the large bed room, the hotel price dimension is 300-500 yuan, and the hotel star dimension is three-star, and then the target entrance degree and the target exit degree corresponding to the large bed room, the 300-500 yuan and the three-star are obtained.
4. And accumulating the target entrance degree and the target unsubscribe degree respectively to obtain a first total entrance degree and a first total unsubscribe degree.
Specifically, the target entrance degree and the target unsubscribe degree are accumulated respectively, so that a first total entrance degree and a first total unsubscribe degree of the order placing request data are obtained.
5. And when the first total occupancy is higher than the first total unsubscribe degree, predicting that the current ordering client does not unsubscribe.
6. And when the first total occupancy is lower than the first total unsubscribing degree, predicting that the current ordering client can unsubscribe.
Specifically, whether the customer will unsubscribe or not is predicted according to the magnitude relation between the first total occupancy and the first total unsubscribe degree.
Step S208: and rejecting the order placing request of the current order placing client.
Specifically, when the customer placing an order is predicted to be unsubscribed, in order to guarantee the income of the hotel and avoid the waste situation, the order placing request of the current customer placing an order is rejected, so that the resource is reserved for the customer with lower possibility of unsubscribing, and the income of the hotel is guaranteed.
Further, in order to enhance the user experience and ensure the success rate of entering into the house, after rejecting the new order request of the current order-placing client, the method further includes:
1. and acquiring all current bookable house type data, and confirming the second total check-in degree and the second total unsubscribing degree of each bookable house type data according to the check-in degree and the unsubscribing degree of each preset level of each preset dimension of the current ordering client.
Specifically, after the check-in degree and the unsubscribe degree of each preset level of each preset dimension of the current ordering client are obtained, all current bookable house type data of the hotel are obtained, the bookable house type data comprise house type, price, hotel star level and the like, and then the second total check-in degree and the second total unsubscribe degree of each bookable house type data are confirmed by combining the check-in degree and the unsubscribe degree of each preset level of each preset dimension of the current ordering client.
2. And screening the target bookable house type data with the second total degree of occupancy higher than the second total degree of unsubscribing.
Specifically, the second total degree of occupancy being higher than the second total degree of unsubscribe indicates that the target bookable house type data is more likely to be successfully checked-in than unsubscribed. Accordingly, target bookable house type data having a second total occupancy higher than the second total unsubscribe degree is screened.
3. And sorting the target bookable house type data according to the difference value of the second total occupancy and the second total unsubscribing degree from high to low.
Specifically, when the second total degree of occupancy is higher than the second total degree of unsubscribe, calculating a difference value between the second total degree of occupancy and the second total degree of unsubscribe, wherein the larger the difference value is, the higher the possibility that the current ordering client catches in the target bookable house type data is. Then, the target bookable house type data is sorted in order from high to low according to the difference.
4. And selecting the target bookable house type data with the highest ranking to generate recommended content and sending the recommended content to the ordering terminal of the current ordering client.
Specifically, the target bookable house type data with the highest ranking are selected and recommended to the ordering terminal of the client ordering the current order as the recommended house type, so that the proper house type is recommended to the client ordering the current order, and the probability of ordering the current order and successfully living is improved.
Step S209: and receiving the order placing request of the current order placing client.
Specifically, when it is predicted that the current ordering client will not unsubscribe, the ordering request of the current ordering client can be directly accepted.
Step S210: and after a new ordering request is received, updating the house state information of the date to be predicted according to the ordering request.
Specifically, after the house type information of the date to be predicted is obtained, if an order placing request of a current order placing client is received, whether the order placing request is accepted is determined, and if the order placing request is accepted, the house state information of the date to be predicted is updated according to the order placing request.
The hotel room status prediction method of the second embodiment of the invention confirms the possibility of the room with the expiration date to be predicted through the room fullness probability on the basis of the first embodiment, when the possibility of the room with the expiration date to be predicted is higher, in order to improve the utilization rate of room resources and improve the hotel income, the third history order data of the current ordering client is used for analyzing the possibility of the successful check-in of the client and the possibility of the client for the order to be booked, and when the possibility of the client for the order to be booked is higher, the ordering request of the client is refused, and the room type which is more in line with the preference of the client is recommended to the client, so that the possibility of the client for the order to be booked is reduced, and the utilization rate of hotel room type resources is improved.
Fig. 3 is a functional module schematic diagram of a hotel room status prediction apparatus according to an embodiment of the present invention. As shown in fig. 3, the hotel room status prediction apparatus 30 includes a first obtaining module 31, a first prediction module 32, a setting module 33, a second prediction module 34, and a confirmation module 35.
The first obtaining module 31 is configured to obtain first historical order data of a preset large customer and second historical order data of a common customer;
the first prediction module 32 is used for predicting the order placing probability and the reserved quantity of the big clients on the date to be predicted according to the first historical order data and a pre-trained big client order placing prediction model, and the big client order placing prediction model is obtained by training according to the historical order data of all the big clients;
a setting module 33, configured to set a bookable number of rooms, where the bookable number of rooms is set as a difference between the maximum number of rooms and the bookable number when the lower probability exceeds a first preset threshold; when the lower order probability does not exceed a first preset threshold, the number of bookable rooms is set as the maximum number of rooms;
the second prediction module 34 is used for predicting the full rate of the date to be predicted according to the number of the bookable rooms, second historical order data and a pre-trained full rate prediction model, wherein the full rate prediction model is obtained by training according to the historical order data of all common customers;
and the confirming module 35 is configured to confirm the house status information of the date to be predicted according to the probability of full house.
Optionally, the second prediction module 34 performs an operation of predicting the probability of full room of the to-be-predicted date according to the number of bookable rooms, the second historical order data and the pre-trained full room probability prediction model, and specifically includes: acquiring target historical order data which takes a preset period as an interval and has the same date as the previous period corresponding to the date to be predicted from the second historical order data; and inputting the target historical order data and the number of the bookable rooms into the full room probability prediction model to obtain the full room probability.
Optionally, the second prediction module 34 performs an operation of obtaining, from the second historical order data, the target historical order data on the same date as the previous cycle corresponding to the date to be predicted at intervals of a preset cycle, and specifically includes: judging whether the date to be predicted is a preset holiday or not; if yes, acquiring target historical order data of the same holiday in the previous history; if not, acquiring the target historical order data of the same date in the previous period.
Optionally, after the confirming module 35 performs an operation of confirming the room status information of the date to be predicted according to the probability of full room, the operation is further configured to: and after a new ordering request is received, updating the house state information of the date to be predicted according to the ordering request.
Optionally, the confirming module 35 is further configured to, after accepting a new ordering request, before performing an operation of updating the room status information of the date to be predicted according to the ordering request: when the full room probability exceeds a second preset threshold value, if an order placing request of a current order placing client is received, acquiring third history order data of the current order placing client; predicting whether the current ordering client can perform an order releasing operation aiming at the ordering request or not according to the third history ordering data; when the current ordering client is predicted to be unsubscribed, rejecting an ordering request of the current ordering client; and when the current ordering client is predicted not to unsubscribe, accepting the ordering request of the current ordering client.
Optionally, the determining module 35 performs an operation of predicting whether the current ordering client will perform an unsubscribe operation for the ordering request according to the third history ordering data, and specifically includes: acquiring the total order number according to the third history order number data, and dividing the third history order data according to the preset dimensionality and the preset grade corresponding to the preset dimensionality to obtain the in-call order number and the out-call order number of each preset grade of each preset dimensionality, wherein the preset dimensionality comprises at least one preset order characteristic, and the preset order characteristic comprises a plurality of preset grades set based on a preset rule; calculating to obtain the in-order degree of each preset grade of each preset dimension according to the in-order number and the total order number corresponding to each preset grade of each preset dimension, and calculating to obtain the out-order degree of each preset grade of each preset dimension according to the out-order number and the total order number corresponding to each preset grade of each preset dimension; extracting target dimensions and target grades corresponding to each target dimension from the ordering request data, and confirming the target admission degree and the target unsubscribing degree of the target grades of each target dimension; accumulating the target entering degree and the target unsubscribing degree respectively to obtain a first total entering degree and a first total unsubscribing degree; when the first total check-in degree is higher than the first total unsubscribing degree, predicting that the current ordering client can not unsubscribe; and when the first total occupancy is lower than the first total unsubscribe degree, predicting that the current ordering client can unsubscribe.
Optionally, after the confirming module 35 performs the operation of rejecting the new order request of the current ordering client, it is further configured to: acquiring all current bookable house type data, and confirming a second total check-in degree and a second total unsubscribing degree of each bookable house type data according to the check-in degree and the unsubscribing degree of each preset grade of each preset dimension of the current ordering client; screening target bookable house type data with the second total occupancy degree higher than the second total unsubscribing degree; sorting the target bookable house type data according to the difference value of the second total entrance degree and the second total unsubscribing degree from high to low; and selecting the highest-ranking target bookable house type data to generate recommended content and sending the recommended content to the ordering terminal of the current ordering client.
For further details of the technical solution implemented by each module in the hotel room status prediction apparatus in the above embodiment, reference may be made to the description in the hotel room status prediction method in the above embodiment, and a detailed description thereof is omitted here.
It should be noted that, in this specification, each embodiment is described in a progressive manner, and each embodiment focuses on differences from other embodiments, and portions that are the same as and similar to each other in each embodiment may be referred to. For the device-like embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a computer device according to an embodiment of the present invention. As shown in fig. 4, the computer device 60 includes a processor 61 and a memory 62 coupled to the processor 61, wherein the memory 62 stores program instructions, and when the program instructions are executed by the processor 61, the program instructions cause the processor 61 to execute the steps of the hotel room prediction method according to any one of the embodiments.
The processor 61 may also be referred to as a Central Processing Unit (CPU). The processor 61 may be an integrated circuit chip having signal processing capabilities. The processor 61 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. 5, fig. 5 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 71 capable of implementing all the methods described above, where the program instructions 71 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: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, or various media capable of storing program codes, or a computer device such as a computer, a server, a mobile phone, or a tablet.
In the several embodiments provided in the present application, it should be understood that the disclosed computer device, apparatus 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, each functional unit 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 or applied to other related technical fields are intended to be included in the scope of the present disclosure.
Claims (10)
1. A hotel room status prediction method is characterized by comprising the following steps:
acquiring first historical order data of a preset large customer and second historical order data of a common customer;
predicting the order placing probability and the reserved quantity of the big clients on the dates to be predicted according to the first historical order data and a pre-trained big client order placing prediction model, wherein the big client order placing prediction model is obtained by training according to the historical order data of all the big clients;
setting the number of bookable rooms, wherein when the lower single probability exceeds a first preset threshold value, the number of bookable rooms is set as the difference value between the maximum number of rooms and the booked number; when the ordering probability does not exceed a first preset threshold, the bookable room number is set as the maximum room number;
predicting the full rate of the to-be-predicted date according to the number of the bookable rooms, the second historical order data and a pre-trained full rate prediction model, wherein the full rate prediction model is obtained by training according to the historical order data of all common customers;
and confirming the house state information of the date to be predicted according to the full house probability.
2. The hotel room status prediction method as recited in claim 1, wherein the predicting the probability of full room of the to-be-predicted date according to the bookable room quantity, the second historical order data and a pre-trained full room probability prediction model comprises:
acquiring target historical order data which is at the same date as the previous period and corresponds to the date to be predicted at intervals of a preset period from the second historical order data;
and inputting the target historical order data and the bookable room quantity into the full room probability prediction model to obtain the full room probability.
3. The hotel room status prediction method according to claim 2, wherein the step of obtaining target historical order data which is spaced at preset intervals and has the same date as the previous period corresponding to the date to be predicted from the second historical order data comprises the steps of:
judging whether the date to be predicted is a preset holiday or not;
if yes, acquiring target historical order data of a holiday with the same previous history;
if not, acquiring the target historical order data of the same date in the previous period.
4. The hotel room status prediction method according to claim 1, after confirming the room status information of the date to be predicted according to the full room probability, further comprising:
and after a new ordering request is received, updating the house state information of the date to be predicted according to the ordering request.
5. The hotel room status prediction method according to claim 1, wherein after accepting a new ordering request, before updating the room status information of the date to be predicted according to the ordering request, the method further comprises:
when the full room probability exceeds a second preset threshold value, if an order placing request of a current order placing client is received, acquiring third history order data of the current order placing client;
predicting whether the current ordering client can perform an order releasing operation aiming at the ordering request or not according to the third history ordering data;
when the order placing client is predicted to unsubscribe, rejecting an order placing request of the current order placing client;
and when the current ordering client is predicted not to unsubscribe, accepting the ordering request of the current ordering client.
6. The hotel room status prediction method as set forth in claim 5, wherein the predicting whether the current ordering client will perform an unsubscription operation for the ordering request according to the third history order data comprises:
acquiring the total order number according to the third history order data, and dividing the third history order data according to preset dimensions and preset levels corresponding to the preset dimensions to obtain the number of incoming orders and the number of outgoing orders of each preset level of each preset dimension, wherein the preset dimensions comprise at least one preset order characteristic, and the preset order characteristic comprises a plurality of preset levels set based on preset rules;
calculating to obtain the in-order degree of each preset grade of each preset dimension according to the in-order number corresponding to each preset grade of each preset dimension and the total order number, and calculating to obtain the out-order degree of each preset grade of each preset dimension according to the out-order number corresponding to each preset grade of each preset dimension and the total order number;
extracting target dimensions and target levels corresponding to each target dimension from the ordering request data, and confirming the target entrance degree and the target unsubscribe degree of the target levels of each target dimension;
accumulating the target entrance degree and the target unsubscribe degree respectively to obtain a first total entrance degree and a first total unsubscribe degree;
predicting that the current ordering customer does not unsubscribe when the first total occupancy is higher than the first total unsubscribe degree;
and when the first total occupancy is lower than the first total unsubscribing degree, predicting that the current ordering customer unsubscribes.
7. The hotel room status prediction method as recited in claim 6, further comprising, after rejecting the new order request from the current ordering client:
acquiring all current bookable house type data, and confirming a second total check-in degree and a second total unsubscribing degree of each bookable house type data according to the check-in degree and the unsubscribing degree of each preset grade of each preset dimension of the current ordering client;
screening target bookable house type data with the second total occupancy higher than the second total unsubscribing degree;
sorting the target bookable house type data from high to low according to the difference value between the second total occupancy and the second total unsubscribing degree;
and selecting the highest-ranking target bookable house type data to generate recommended content and sending the recommended content to the ordering terminal of the current ordering client.
8. A hotel room status prediction device, comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring first historical order data of a preset large customer and second historical order data of a common customer;
the first prediction module is used for predicting the order placing probability and the reserved quantity of the big clients on the date to be predicted according to the first historical order data and a pre-trained big client order placing prediction model, and the big client order placing prediction model is obtained by training according to the historical order data of all the big clients;
the setting module is used for setting the number of bookable rooms, and when the ordering probability exceeds a first preset threshold value, the number of bookable rooms is set as the difference value between the maximum number of rooms and the booked number; when the ordering probability does not exceed a first preset threshold, the bookable room number is set as the maximum room number;
the second prediction module is used for predicting the full room probability of the date to be predicted according to the number of the rooms which can be reserved, the second historical order data and a pre-trained full room probability prediction model, and the full room probability prediction model is obtained by training according to the historical order data of all common customers;
and the confirmation module is used for confirming the house state information of the date to be predicted according to the full house probability.
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 program instructions, when executed by the processor, cause the processor to carry out the steps of the hotel room prediction method as claimed in any one of claims 1 to 7.
10. A storage medium storing program instructions capable of implementing the hotel room status prediction method as recited in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210101416.7A CN114706862B (en) | 2022-01-27 | 2022-01-27 | Hotel room state prediction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210101416.7A CN114706862B (en) | 2022-01-27 | 2022-01-27 | Hotel room state prediction method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114706862A true CN114706862A (en) | 2022-07-05 |
| CN114706862B CN114706862B (en) | 2022-11-15 |
Family
ID=82166232
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210101416.7A Active CN114706862B (en) | 2022-01-27 | 2022-01-27 | Hotel room state prediction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114706862B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116258465A (en) * | 2023-03-08 | 2023-06-13 | 深圳市天下房仓科技有限公司 | Hotel data processing method, device, equipment and storage medium |
| CN118278552A (en) * | 2024-06-04 | 2024-07-02 | 山东沃德网络技术有限公司 | Guest room management method, equipment and medium for hotel reservation |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8170971B1 (en) * | 2011-09-28 | 2012-05-01 | Ava, Inc. | Systems and methods for providing recommendations based on collaborative and/or content-based nodal interrelationships |
| CN106295831A (en) * | 2016-08-29 | 2017-01-04 | 徐月明 | Guest room reservation method and system and hotel information management platform |
| CN107506877A (en) * | 2017-09-30 | 2017-12-22 | 携程计算机技术（上海）有限公司 | OTA platforms are to Forecasting Methodology and system of the shop without room |
| WO2018048352A1 (en) * | 2016-09-06 | 2018-03-15 | Starfusion Pte. Ltd. | System and method for online hotel check-in and check-out |
| CN109376891A (en) * | 2018-11-27 | 2019-02-22 | 携程计算机技术（上海）有限公司 | The determination method and system of the full room state of people place |
| CN109685624A (en) * | 2018-12-27 | 2019-04-26 | 宿州学院 | A kind of intelligent hotel housekeeping scheduling system and hotel management method |
| CN110097202A (en) * | 2019-04-30 | 2019-08-06 | 深圳春沐源控股有限公司 | Management method, system, device and the computer storage medium of hotel reservation |
| CN111445046A (en) * | 2020-03-18 | 2020-07-24 | 携程计算机技术（上海）有限公司 | Hotel reservation information processing method and system, electronic equipment and storage medium |
| CN111861801A (en) * | 2020-07-21 | 2020-10-30 | 携程计算机技术（上海）有限公司 | Hotel full room prediction method, system, equipment and storage medium |
| US20210004884A1 (en) * | 2017-04-29 | 2021-01-07 | Mehmet Melih Bas | System and method for creating an online exchange between lodging seekers and lodging providers for negotiating the price of rooms |
| EP3772029A1 (en) * | 2019-07-31 | 2021-02-03 | Ciaomanager Srl | Method and apparatus for assigning rooms to reservations in hotels |
| CN112529333A (en) * | 2020-12-25 | 2021-03-19 | 上海云角信息技术有限公司 | Prediction method, device, equipment and storage medium for overdesigned number of hotel rooms |
| US20210182744A1 (en) * | 2019-12-16 | 2021-06-17 | Industrial Technology Research Institute | Revenue forecasting method, revenue forecasting system and graphical user interface |
-
2022
- 2022-01-27 CN CN202210101416.7A patent/CN114706862B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8170971B1 (en) * | 2011-09-28 | 2012-05-01 | Ava, Inc. | Systems and methods for providing recommendations based on collaborative and/or content-based nodal interrelationships |
| CN106295831A (en) * | 2016-08-29 | 2017-01-04 | 徐月明 | Guest room reservation method and system and hotel information management platform |
| WO2018048352A1 (en) * | 2016-09-06 | 2018-03-15 | Starfusion Pte. Ltd. | System and method for online hotel check-in and check-out |
| US20210004884A1 (en) * | 2017-04-29 | 2021-01-07 | Mehmet Melih Bas | System and method for creating an online exchange between lodging seekers and lodging providers for negotiating the price of rooms |
| CN107506877A (en) * | 2017-09-30 | 2017-12-22 | 携程计算机技术（上海）有限公司 | OTA platforms are to Forecasting Methodology and system of the shop without room |
| CN109376891A (en) * | 2018-11-27 | 2019-02-22 | 携程计算机技术（上海）有限公司 | The determination method and system of the full room state of people place |
| CN109685624A (en) * | 2018-12-27 | 2019-04-26 | 宿州学院 | A kind of intelligent hotel housekeeping scheduling system and hotel management method |
| CN110097202A (en) * | 2019-04-30 | 2019-08-06 | 深圳春沐源控股有限公司 | Management method, system, device and the computer storage medium of hotel reservation |
| EP3772029A1 (en) * | 2019-07-31 | 2021-02-03 | Ciaomanager Srl | Method and apparatus for assigning rooms to reservations in hotels |
| US20210182744A1 (en) * | 2019-12-16 | 2021-06-17 | Industrial Technology Research Institute | Revenue forecasting method, revenue forecasting system and graphical user interface |
| CN111445046A (en) * | 2020-03-18 | 2020-07-24 | 携程计算机技术（上海）有限公司 | Hotel reservation information processing method and system, electronic equipment and storage medium |
| CN111861801A (en) * | 2020-07-21 | 2020-10-30 | 携程计算机技术（上海）有限公司 | Hotel full room prediction method, system, equipment and storage medium |
| CN112529333A (en) * | 2020-12-25 | 2021-03-19 | 上海云角信息技术有限公司 | Prediction method, device, equipment and storage medium for overdesigned number of hotel rooms |
Non-Patent Citations (2)
| Title |
|---|
| 叶飞等: ""酒店+OTA"双渠道供应链超订策略研究", 《运筹与管理》 * |
| 唐若璘: "旅游企业经营战略理论及实践—以经济型酒店"如家快捷"为例", 《现代商业》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116258465A (en) * | 2023-03-08 | 2023-06-13 | 深圳市天下房仓科技有限公司 | Hotel data processing method, device, equipment and storage medium |
| CN118278552A (en) * | 2024-06-04 | 2024-07-02 | 山东沃德网络技术有限公司 | Guest room management method, equipment and medium for hotel reservation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114706862B (en) | 2022-11-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110334289B (en) | Travel destination determining method and target user determining method | |
| EP3471374B1 (en) | Method and device for identifying type of geographic location at where user is located | |
| CN110135901A (en) | A kind of enterprise customer draws a portrait construction method, system, medium and electronic equipment | |
| CN114706862B (en) | Hotel room state prediction method, device, equipment and storage medium | |
| CN111523060A (en) | Network information pushing method and device | |
| CN109816321A (en) | A kind of service management, device, equipment and computer readable storage medium | |
| CN110070382B (en) | Method and device for generating information | |
| CN111161104A (en) | Generation method and device of community user portrait | |
| CN112381514B (en) | Service data reminding method, device and server | |
| Ulukus et al. | Admission and termination control of a two class loss system | |
| WO2022216490A1 (en) | Intelligent scheduling using a prediction model | |
| CN110197426B (en) | Credit scoring model building method, device and readable storage medium | |
| CN114418641A (en) | Automatic dispatching method and device for stock customer access work order and electronic equipment | |
| CN114445138A (en) | Hotel room type pricing method, device, equipment and storage medium | |
| CN112258220A (en) | Information acquisition and analysis method, system, electronic device and computer readable medium | |
| CN112257884A (en) | Order management method and system | |
| CN109636196B (en) | Task scheduling method and device, electronic equipment and storage medium | |
| CN114372735A (en) | Method and device for determining buffer stock quantity data in logistics supply chain | |
| CN110276648A (en) | Client's identification and based reminding method and device | |
| CN115983902A (en) | Information pushing method and system based on user real-time event | |
| CN112396249B (en) | Market demand value calculation method and device based on seat reservation change identification | |
| CN114519554A (en) | Schedule creating method, device, equipment and medium | |
| Abdillah et al. | Implementation of the First Come First Served Algorithm in the Futsal Field Booking Application using Extreme Programming | |
| CN114202292B (en) | Stock information sending method and device, electronic equipment and computer readable medium | |
| CN113313439B (en) | Method and device for calculating time length of tall-in-hand |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |