CN109376891B - Method and system for determining full house state of residential accommodation - Google Patents
Method and system for determining full house state of residential accommodation Download PDFInfo
- Publication number
- CN109376891B CN109376891B CN201811426679.5A CN201811426679A CN109376891B CN 109376891 B CN109376891 B CN 109376891B CN 201811426679 A CN201811426679 A CN 201811426679A CN 109376891 B CN109376891 B CN 109376891B
- Authority
- CN
- China
- Prior art keywords
- residential
- full
- state
- house
- room
- 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.)
- Active
Links
- 230000004308 accommodation Effects 0.000 title claims abstract description 75
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000003032 molecular docking Methods 0.000 claims description 5
- 230000007547 defect Effects 0.000 abstract description 9
- 238000012790 confirmation Methods 0.000 description 7
- 238000010801 machine learning Methods 0.000 description 3
- 238000005034 decoration Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response 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
- G06Q10/00—Administration; Management
- G06Q10/02—Reservations, e.g. for tickets, services or events
- G06Q10/025—Coordination of plural reservations, e.g. plural trip segments, transportation combined with accommodation
-
- 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
- G06Q50/16—Real estate
Landscapes
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for determining a full room state of an residential accommodation, wherein the method for determining the full room state of the residential accommodation comprises the following steps: acquiring historical data of residents; establishing a probability prediction model of the residential housing in a full-house state on a reserved living day according to the historical data of the residential housing; obtaining a target booking date, and obtaining a probability prediction value of the full-house state of the target booking date of the residential accommodations according to the probability prediction model; and judging whether the probability predicted value exceeds a first set threshold value, and if so, determining that the residential accommodation is in a full-room state on a reserved target living day. The invention can update the house source state of the residential quarter to be the full house state in time, avoids the situation that the house is full when the user confirms with the residential quarter owner, improves the experience of the user for booking the residential quarter, reduces the service defect index of the OTA platform, improves the enterprise brand image of the OTA platform, improves the working efficiency and reduces the labor cost.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a system for determining a full room state of an accommodation.
Background
At present, residential resources are generally sold in hotel products accessed to an APP (application) side of an OTA (Online Travel Agency) platform.
However, when a user subscribes to a residential home, the user often encounters the situations that the user experience is affected by refusal of the residential home and overtime feedback, and the situations are mainly caused by the following two reasons: 1) the process of reserving the residents is more special, generally, a user is required to confirm whether a room can be reserved with a resident house owner before reservation, after the house owner informs that the room can be reserved, the user submits an order to complete the process of reserving the resident house, namely, the confirmation process is complicated, and the situation that the room is full when the user confirms whether the room exists is easy to happen; 2) the number of residential rooms is generally small, the exposure is increased along with the entering of residents into a large search channel of an OTA platform, the ordering possibility of a user is greatly increased, and when the residential house source is short, the situation that the user confirms whether a room is full or not is easy to happen. And the user confirms whether the room is full or not, so that the experience of booking residents by the user is seriously influenced, the enterprise image of the OTA platform side is seriously damaged, and the loss of the client is caused.
The existing method for solving the problems is that after business personnel analyze data according to long-term accumulated working experience and the condition of orders reserved by residents, the occurrence probability of full rooms when a user confirms whether rooms exist is reduced by adopting a manual telephone investigation mode. However, due to the fact that the number of the residents is large, workload is large, labor cost is too high, working efficiency is low, and the problem that whether the residents are in a full-house state or not is difficult to update timely and accurately is solved.
Disclosure of Invention
The invention aims to solve the technical problems that in the prior art, the situation that the room is full before confirmation is easy to occur when people reserve rooms, and the existing situation that the room is full before confirmation is solved in a manual telephone investigation mode, so that the defects of large workload, overhigh labor cost, low working efficiency and the like exist, and provide a method and a system for determining the full room state of the people reserve rooms.
The invention solves the technical problems through the following technical scheme:
the invention provides a method for determining a full room state of an residential home, which comprises the following steps:
acquiring civilian history data;
the residential history data comprises at least one of house type history data, history characteristic data, history living time data, history order data and history browsing volume data of the residential;
establishing a probability prediction model of the residential housing in a full-house state on a reserved living day according to the historical data of the residential housing;
obtaining a target booking date, and obtaining a probability prediction value of the full-house state of the target booking date of the residential accommodations according to the probability prediction model;
and judging whether the probability predicted value exceeds a first set threshold value, and if so, determining that the residential accommodation is in a full-room state on a reserved target living day.
Preferably, the step of determining whether the probability prediction value exceeds a first set threshold, and if so, determining that the residential accommodation is in a full-room state on a reserved target accommodation date includes:
and judging whether the probability predicted value exceeds the first set threshold value, if so, continuously judging whether the historical browsing volume data of the residential accommodations within set days exceeds a second set threshold value, and if so, determining that the residential accommodations are in a full-room state on the reserved target entering days.
Preferably, the step of determining whether the probability prediction value exceeds a first set threshold, and if so, determining that the residential accommodation is in a full-room state on a reserved target accommodation date includes:
judging whether the probability predicted value exceeds the first set threshold value, if so, continuing to judge whether the historical browsing amount data of the residential accommodations within set days exceeds a second set threshold value, and if so, generating a residential accommodation waiting room inquiring list;
performing IVR (Interactive Voice Response) room inquiry on the residents in the room inquiring list of the residents, and acquiring corresponding feedback information;
the IVR inquiring room is used for representing voice docking conversation between a seat of a power business platform and the residents and determining the room source state of the residents on the reserved target living day;
and when the feedback information shows that the house source state of the target lodging date is in the full house state, determining that the target lodging date is in the full house state.
Preferably, the step of establishing a probability prediction model of the lodging in a full-room state on a reserved check-in date according to the lodging history data comprises:
and establishing a probability prediction model of the full-house state of the residential accommodation on the reserved stay date by adopting an XGboost algorithm (a machine learning algorithm) according to the historical data of the residential accommodation.
The invention also provides a system for determining the full-house state of the residential accommodations, which comprises a data acquisition module, a prediction model establishing module, a target living day acquisition module, a prediction value acquisition module, a judgment module and a determination module;
the data acquisition module is used for acquiring the civilian historical data;
the residential history data comprises at least one of house type history data, history characteristic data, history living time data, history order data and history browsing volume data of the residential;
the prediction model establishing module is used for establishing a probability prediction model of the residential housing in a full-house state on a reserved check-in date according to the historical data of the residential housing;
the target living-in date acquisition module is used for acquiring a reserved target living-in date;
the predicted value obtaining module is used for obtaining a probability predicted value of the state that the target residence date booked by the residents is full of rooms according to the probability prediction model;
the judging module is used for judging whether the probability predicted value exceeds a first set threshold value, and if the probability predicted value exceeds the first set threshold value, the determining module is called to determine that the residential accommodation is in a full-room state on a reserved target living day.
Preferably, the determining module is further configured to, when the probability prediction value exceeds the first set threshold, if the probability prediction value exceeds the first set threshold, continue to determine whether the historical browsing volume data of the residential quarter within a set number of days exceeds a second set threshold, and if the probability prediction value exceeds the second set threshold, invoke the determining module to determine that the residential quarter is in a full-room state on a reserved target living day.
Preferably, the determining system further comprises a list generating module and a feedback information acquiring module;
the judging module is further used for judging whether the probability predicted value exceeds the first set threshold value, if so, continuing to judge whether the historical browsing volume data of the residents within a set number of days exceeds a second set threshold value, and if so, calling the list generating module;
the list generating module is used for generating a residential housing room inquiring list;
the feedback information acquisition module is used for performing IVR room inquiry on the residents in the room inquiring list to acquire corresponding feedback information, and when the feedback information shows that the room source state of the residents on the reserved target living day is in a full room state, the determination module is called to determine that the resident on the reserved target living day is in the full room state;
the IVR inquiring room is used for representing voice docking conversation between the seats of the e-commerce platform and the residents and determining the room source state of the residents on the reserved target living day.
Preferably, the prediction model establishing module is configured to establish a probability prediction model of the residential property in a full-house state on a reserved check-in date according to the historical data of the residential property by using an XGBoost algorithm.
The positive progress effects of the invention are as follows:
according to the method, a probability prediction model that the residential accommodations are in a full-house state on the reserved check-in days is established, a probability prediction value that the residential accommodations are in the full-house state on the reserved target check-in days is obtained, and when the probability prediction value exceeds a first set threshold value, the reserved target check-in days of the residential accommodations are determined to be in the full-house state; or after the probability predicted value exceeds a first set threshold value, by combining historical browsing amount data of the residential accommodators in set days and IVR robot room inquiry, the residential accommodator is finally determined to be in a full-room state on the reserved target living day, so that the room source state of the residential accommodator is timely updated to be in the full-room state, the situation that the residential accommodator is full when a user confirms with the residential accommodator is avoided, the experience of the user for reserving the residential accommodator is improved, the service defect index of the OTA platform is reduced, the enterprise brand image of the OTA platform is improved, the working efficiency is improved, and the labor cost is reduced.
Drawings
Fig. 1 is a flowchart of a method for determining a full room state of an residential quarter according to embodiment 1 of the present invention.
Fig. 2 is a flowchart of a method for determining a full room status of an accommodation in embodiment 2 of the present invention.
Fig. 3 is a flowchart of a method for determining a full room status of an apartment according to embodiment 3 of the present invention.
Fig. 4 is a block diagram of a system for determining a full-room state of an accommodation according to embodiment 4 of the present invention.
Fig. 5 is a block diagram of a system for determining a full room status of an accommodation according to embodiment 6 of the present invention.
Detailed Description
The invention is further illustrated by the following examples, which are not intended to limit the scope of the invention.
Example 1
As shown in fig. 1, the method for determining a full room state of an apartment of the present embodiment includes:
s101, acquiring residential history data;
the residential history data comprises at least one of house type history data, history feature data, history living time data, history order data, history browsing volume data and peripheral heat history data of the residential;
the house type historical data of the residents comprises data of house type storefront price, house type base price, commission rate, whether the residents belong to a promotion house type or not and the like;
the historical characteristic data of the residents comprise the operation time of the residents, the latest decoration time, the user rating, the position rating, the room rating, the comprehensive evaluation of the residents, whether the residents belong to direct connection, whether the residents are in a business circle, whether the residents belong to vacation types, the star level of the residents, the room number and the like;
the historical stay-in-date time data of the residents comprises data such as whether the residents belong to holidays, whether the residents belong to weekends, the number of days reserved in advance, the specific stay-in-date time reserved and the like;
the historical order data comprises data such as order submission days, order incoming days, order quantity in past set days (such as 7 days, 14 days, 30 days and 180 days), order quantity canceling before full room confirmation, order rate canceling before full room confirmation and the like corresponding to parent basic house types and child house types of parent residents and child residents in different communities of different cities;
the surrounding heat history data comprises the number of full rooms of people in different commercial circle star levels of different cities around, the tension (reservation condition), the variation of the tension relative to the tension of the previous batch and the like.
S102, establishing a probability prediction model of the residential housing in a full-house state on a reserved check-in day according to the historical data of the residential housing;
the XGboost algorithm can be used for establishing a probability prediction model of the residential property in a full-house state on the reserved check-in date according to historical data of the residential property, but the XGboost algorithm is not limited to the XGboost algorithm, and other machine learning algorithms capable of establishing the probability prediction model can also be used.
S103, acquiring a reserved target entering date, and acquiring a probability prediction value of the state that the residential quarter is full of rooms on the reserved target entering date according to a probability prediction model;
and S104, judging whether the probability predicted value exceeds a first set threshold value, and if so, determining that the residential accommodation is in a full-room state on a reserved target entrance date.
According to the actual situation, for example, when a user needs to book a target accommodation day (including the day and two consecutive days in the future) on the same day, the probability prediction value of the full accommodation state of the accommodation on the same day and two consecutive days in the future is obtained according to the probability prediction model, when the probability prediction value exceeds a first set threshold value, the full accommodation state of the accommodation on the same day and two consecutive days in the future is determined, then the OTA platform updates the room source state of the accommodation to the full accommodation state in time according to the determination result, and the situation that the user and the accommodation owner have full accommodation when confirming is avoided.
In the embodiment, the probability prediction model that the residential quarter is in the full-house state on the reserved check-in day is established, the probability prediction value that the residential quarter is in the full-house state on the reserved target check-in day is obtained, and when the probability prediction value exceeds a first set threshold value, the reserved target check-in day is determined to be in the full-house state, so that the house source state of the residential quarter is updated to be in the full-house state in time, the condition that the house is full when a user confirms with the residential quarter owner is avoided, the experience of the user for reserving the residential quarter is improved, the service defect index of the OTA platform is reduced, the enterprise brand image of the OTA platform is improved, the working efficiency is improved, and the labor cost is reduced.
Example 2
As shown in fig. 2, the method for determining the full-room state of the residential accommodations in this embodiment is a further improvement of embodiment 1, and specifically:
step S104 includes:
s1041, judging whether the probability predicted value exceeds a first set threshold value, if so, continuously judging whether the historical browsing amount data of the residential accommodations within the set number of days exceeds a second set threshold value, and if so, determining that the residential accommodations are in a full-room state on the reserved target entering day.
In the embodiment, the probability prediction value of the full-house state of the residential home on the reserved target living day is obtained by establishing the probability prediction model of the full-house state of the residential home on the reserved living day, and when the probability prediction value exceeds a first set threshold value, the probability prediction value is combined with historical browsing volume data of the residential home within a set number of days to finally determine that the residential home is in the full-house state on the reserved target living day, so that the house source state of the residential home is updated to be the full-house state in time, the situation that the house is full when a user confirms with the owner of the residential home is avoided, the experience of the user in reserving the residential home is improved, the service defect index of the OTA platform is reduced, the enterprise brand image of the OTA platform is improved, the working efficiency is improved, and the labor cost is reduced.
Example 3
As shown in fig. 3, the method for determining the full-room state of the residential accommodations of the present embodiment is a further improvement of embodiment 2, and specifically:
the step S1041 includes:
s10411, judging whether the probability predicted value exceeds a first set threshold value, if so, continuing to judge whether the historical browsing amount data of the residential accommodations within the set number of days exceeds a second set threshold value, and if so, generating a residential accommodation waiting room inquiring list;
s10412, performing IVR robot room inquiry on the residents in the room inquiry list to be waited by the residents, and acquiring corresponding feedback information;
the IVR robot room inquiring system comprises an IVR robot room inquiring system, a business platform and a client, wherein the IVR robot room inquiring system is used for representing voice butt joint conversation between a seat and a resident through the business platform and determining the room source state of the resident on a reserved target living day;
and S10413, when the feedback information shows that the house source state of the residential accommodation on the reserved target accommodation date is in the full house state, determining that the residential accommodation is in the full house state on the reserved target accommodation date.
In the embodiment, a probability prediction model that the residential quarter is in a full-house state on a reserved check-in day is established, a probability prediction value that the residential quarter is in the full-house state on a reserved target check-in day is obtained, and when the probability prediction value exceeds a first set threshold value, the reserved target check-in day of the residential quarter is determined to be in the full-house state; or after the probability predicted value exceeds a first set threshold value, by combining historical browsing amount data of the residents in set days and IVR house inquiry, the residents are finally determined to be in a full house state on the reserved target living day, so that the house source state of the residents is timely updated to be in the full house state, the situation that the residents are full when the residents and the residents of the residents confirm is avoided, the experience of the users for reserving the residents is improved, the service defect index of the OTA platform is reduced, the enterprise brand image of the OTA platform is improved, the working efficiency is improved, and the labor cost is reduced.
Example 4
As shown in fig. 4, the system for determining a full-room state of an residential quarter in the present embodiment includes a data obtaining module 1, a prediction model establishing module 2, a target date of stay obtaining module 3, a predicted value obtaining module 4, a judging module 5, and a determining module 6.
The data acquisition module 1 is used for acquiring civilian history data;
the residential history data comprises at least one of house type history data, history feature data, history living time data, history order data, history browsing volume data and peripheral heat history data of the residential;
the house type historical data of the residents comprises data of house type storefront price, house type base price, commission rate, whether the residents belong to a promotion house type or not and the like;
the historical characteristic data of the residents comprises the operation time of the residents, the latest decoration time, the user rating, the position rating, the room rating, the comprehensive evaluation of the residents, whether the residents are directly connected, whether the residents are in a business circle, whether the residents belong to vacation types, the resident star level, the room number and the like;
the historical stay-in-date time data of the residents comprises data such as whether the residents belong to holidays, whether the residents belong to weekends, the number of days reserved in advance, the specific stay-in-date time reserved and the like;
the historical order data comprises data such as order submission days, order incoming days, order quantity in past set days (such as 7 days, 14 days, 30 days and 180 days), order quantity canceling before full room confirmation, order rate canceling before full room confirmation and the like corresponding to parent basic house types and child house types of parent residents and child residents in different communities of different cities;
the surrounding heat history data comprises the number of full rooms of people in different commercial circle star levels of different cities around, the tension (reservation condition), the variation of the tension relative to the tension of the previous batch and the like.
The prediction model establishing module 2 is used for establishing a probability prediction model of the residential accommodation in a full-house state on a reserved check-in date according to the historical data of the residential accommodation;
the XGboost algorithm can be used for establishing a probability prediction model of the residential property in a full-house state on the reserved check-in date according to historical data of the residential property, but the XGboost algorithm is not limited to the XGboost algorithm, and other machine learning algorithms capable of establishing the probability prediction model can also be used.
The target entering-life acquisition module 3 is used for acquiring the reserved target entering-life;
the predicted value obtaining module 4 is used for obtaining a predicted probability value of the state that the residents are in a full house state on the booked target entering date according to the probability prediction model;
the judging module 5 is used for judging whether the probability predicted value exceeds a first set threshold value, and if the probability predicted value exceeds the first set threshold value, the determining module 6 is called to determine that the residential accommodation is in a full-room state on the reserved target living day.
According to the actual situation, for example, when a user needs to book a target accommodation day (including the day and two consecutive days in the future) on the same day, the probability prediction value of the full accommodation state of the accommodation on the same day and two consecutive days in the future is obtained according to the probability prediction model, when the probability prediction value exceeds a first set threshold value, the full accommodation state of the accommodation on the same day and two consecutive days in the future is determined, then the OTA platform updates the room source state of the accommodation to the full accommodation state in time according to the determination result, and the situation that the user and the accommodation owner have full accommodation when confirming is avoided.
In the embodiment, the probability prediction model that the residential quarter is in the full-house state on the reserved check-in day is established, the probability prediction value that the residential quarter is in the full-house state on the reserved target check-in day is obtained, and when the probability prediction value exceeds a first set threshold value, the reserved target check-in day is determined to be in the full-house state, so that the house source state of the residential quarter is updated to be in the full-house state in time, the condition that the house is full when a user confirms with the residential quarter owner is avoided, the experience of the user for reserving the residential quarter is improved, the service defect index of the OTA platform is reduced, the enterprise brand image of the OTA platform is improved, the working efficiency is improved, and the labor cost is reduced.
Example 5
As shown in fig. 4, the method for determining a full-room state of an apartment of the present embodiment is a further improvement of embodiment 4, and specifically:
the judging module 5 is further configured to, when judging whether the probability prediction value exceeds a first set threshold, if so, continue to judge whether the historical browsing amount data of the residential accommodations within the set number of days exceeds a second set threshold, and if so, invoke the determining module 6 to determine that the residential accommodations are in a full-room state on the reserved target entering-living day.
In the embodiment, the probability prediction value of the full-house state of the residential home on the reserved target living day is obtained by establishing the probability prediction model of the full-house state of the residential home on the reserved living day, and when the probability prediction value exceeds a first set threshold value, the probability prediction value is combined with historical browsing volume data of the residential home within a set number of days to finally determine that the residential home is in the full-house state on the reserved target living day, so that the house source state of the residential home is updated to be the full-house state in time, the situation that the house is full when a user confirms with the owner of the residential home is avoided, the experience of the user in reserving the residential home is improved, the service defect index of the OTA platform is reduced, the enterprise brand image of the OTA platform is improved, the working efficiency is improved, and the labor cost is reduced.
Example 6
As shown in fig. 5, the system for determining a full room state of an apartment of the present embodiment is a further improvement of embodiment 5, specifically:
the determining system also comprises a list generating module 7 and a feedback information acquiring module 8;
the judging module 5 is further configured to, when judging whether the probability prediction value exceeds a first set threshold, if so, continue to judge whether the historical browsing amount data of the residents within a set number of days exceeds a second set threshold, and if so, invoke the list generating module 7;
the list generating module 7 is used for generating a residential housing room inquiring list;
the feedback information acquisition module 8 is used for carrying out IVR robot room inquiry on the residents in the room inquiring list of the residents, acquiring corresponding feedback information, and calling the determination module 6 to determine that the residents are in a full room state on the reserved target entering date when the feedback information shows that the room source state of the residents on the reserved target entering date is in a full room state;
the IVR robot room inquiring system is used for representing voice docking conversation between seats and residents through a commercial platform and determining the room source state of the residents on the reserved target living day.
In the embodiment, a probability prediction model that the residential quarter is in a full-house state on a reserved check-in day is established, a probability prediction value that the residential quarter is in the full-house state on a reserved target check-in day is obtained, and when the probability prediction value exceeds a first set threshold value, the reserved target check-in day of the residential quarter is determined to be in the full-house state; or after the probability predicted value exceeds a first set threshold value, by combining historical browsing amount data of the residents in set days and IVR house inquiry, the residents are finally determined to be in a full house state on the reserved target living day, so that the house source state of the residents is timely updated to be in the full house state, the situation that the residents are full when the residents and the residents of the residents confirm is avoided, the experience of the users for reserving the residents is improved, the service defect index of the OTA platform is reduced, the enterprise brand image of the OTA platform is improved, the working efficiency is improved, and the labor cost is reduced.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that these are by way of example only, and that the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the spirit and scope of the invention, and these changes and modifications are within the scope of the invention.
Claims (6)
1. A method for determining a full room state of an accommodation, the method comprising:
acquiring civilian history data;
the residential history data comprises at least one of house type history data, history characteristic data, history living time data, history order data and history browsing volume data of the residential;
establishing a probability prediction model of the residential housing in a full-house state on a reserved living day according to the historical data of the residential housing;
acquiring a reserved target living day, and acquiring a probability prediction value of the residential residence in a full house state on the reserved target living day according to the probability prediction model;
judging whether the probability predicted value exceeds a first set threshold value, and if so, determining that the residential accommodation is in a full-room state on a reserved target accommodation date;
the step of judging whether the probability predicted value exceeds a first set threshold value, and if so, determining that the residential accommodation is in a full-room state on a reserved target entrance date comprises the following steps:
and judging whether the probability predicted value exceeds the first set threshold value, if so, continuously judging whether the historical browsing volume data of the residential accommodations within set days exceeds a second set threshold value, and if so, determining that the residential accommodations are in a full-room state on the reserved target entering days.
2. The method for determining the full-room state of the residential quarter as claimed in claim 1, wherein the step of determining whether the predicted probability value exceeds a first set threshold, and if so, determining that the residential quarter is in the full-room state on a reserved target entrance date comprises:
judging whether the probability predicted value exceeds the first set threshold value, if so, continuing to judge whether the historical browsing amount data of the residential accommodations within set days exceeds a second set threshold value, and if so, generating a residential accommodation waiting room inquiring list;
IVR room inquiring is carried out on the residents in the room inquiring list, and corresponding feedback information is obtained;
the IVR inquiring room is used for representing voice docking conversation between a seat of a power business platform and the residents and determining the room source state of the residents on the reserved target living day;
and when the feedback information shows that the house source state of the target lodging date is in the full house state, determining that the target lodging date is in the full house state.
3. The method for determining the full-room status of the residential quarter as claimed in claim 1, wherein the step of establishing the probability prediction model of the residential quarter in the full-room status at the reserved date of residence according to the residential quarter history data comprises:
and establishing a probability prediction model of the full-house state of the residential accommodation on the reserved check-in date according to the historical data of the residential accommodation by adopting an XGboost algorithm.
4. The system for determining the full-house state of the residential accommodations is characterized by comprising a data acquisition module, a prediction model establishing module, a target living day acquisition module, a prediction value acquisition module, a judgment module and a determination module;
the data acquisition module is used for acquiring civilian history data;
the residential history data comprises at least one of house type history data, history characteristic data, history living time data, history order data and history browsing volume data of the residential;
the prediction model establishing module is used for establishing a probability prediction model of the residential housing in a full-house state on a reserved check-in date according to the historical data of the residential housing;
the target living-in date acquisition module is used for acquiring a reserved target living-in date;
the predicted value obtaining module is used for obtaining a probability predicted value of the state that the target residence date booked by the residents is full of rooms according to the probability prediction model;
the judging module is used for judging whether the probability predicted value exceeds a first set threshold value, and if the probability predicted value exceeds the first set threshold value, the determining module is called to determine that the residential accommodation is in a full-room state on a reserved target living day;
the judging module is further used for judging whether the probability predicted value exceeds the first set threshold value, if so, continuously judging whether the historical browsing volume data of the residential accommodations within a set number of days exceeds a second set threshold value, and if so, calling the determining module to determine that the residential accommodations are in a full-house state on the reserved target living days.
5. The system for determining the full housing status of an apartment of claim 4, further comprising a list generation module and a feedback information acquisition module;
the judging module is further used for judging whether the probability predicted value exceeds the first set threshold value, if so, continuing to judge whether the historical browsing volume data of the residents within a set number of days exceeds a second set threshold value, and if so, calling the list generating module;
the list generating module is used for generating a residential housing room inquiring list;
the feedback information acquisition module is used for performing IVR house inquiry on the residents in the resident house inquiry list to acquire corresponding feedback information, and when the feedback information indicates that the house source state of the reserved target living day of the residents is in a full house state, the determination module is called to determine that the reserved target living day of the residents is in a full house state;
the IVR inquiring room is used for representing voice docking conversation between the seats of the e-commerce platform and the residents and determining the condition of the room source state of the residents on the reserved target living day.
6. The system for determining the full-house state of the residential quarter as claimed in claim 4, wherein the prediction model establishing module is configured to establish a probability prediction model of the residential quarter being in the full-house state on a reserved check-in date according to the historical data of the residential quarter by using an XGboost algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811426679.5A CN109376891B (en) | 2018-11-27 | 2018-11-27 | Method and system for determining full house state of residential accommodation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811426679.5A CN109376891B (en) | 2018-11-27 | 2018-11-27 | Method and system for determining full house state of residential accommodation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109376891A CN109376891A (en) | 2019-02-22 |
| CN109376891B true CN109376891B (en) | 2022-06-21 |
Family
ID=65383957
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811426679.5A Active CN109376891B (en) | 2018-11-27 | 2018-11-27 | Method and system for determining full house state of residential accommodation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109376891B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110348632A (en) * | 2019-07-11 | 2019-10-18 | 广东电网有限责任公司 | A kind of wind power forecasting method based on singular spectrum analysis and deep learning |
| 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 |
| CN114706862B (en) * | 2022-01-27 | 2022-11-15 | 深圳市天下房仓科技有限公司 | Hotel room state prediction method, device, equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105243545A (en) * | 2015-09-01 | 2016-01-13 | 张泽 | Multi-platform resource processing method and device |
| CN105354619A (en) * | 2015-12-09 | 2016-02-24 | 姜恒 | Self-service checking-in method and system of hotel |
| CN106296338A (en) * | 2016-07-26 | 2017-01-04 | 斑马信息科技有限公司 | trip order processing method, device and user terminal |
| CN106779119A (en) * | 2016-12-19 | 2017-05-31 | 苏州朗捷通智能科技有限公司 | Hospitality management system |
| 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 |
| CN107679674A (en) * | 2017-10-23 | 2018-02-09 | 携程计算机技术（上海）有限公司 | The Forecasting Methodology and system of the overseas hotel's house type service deficiency of OTA platforms |
| CN107705191A (en) * | 2017-10-25 | 2018-02-16 | 携程计算机技术（上海）有限公司 | The order of OTA platforms strives for method and system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9685061B2 (en) * | 2015-05-20 | 2017-06-20 | Google Inc. | Event prioritization and user interfacing for hazard detection in multi-room smart-home environment |
| CN106295831A (en) * | 2016-08-29 | 2017-01-04 | 徐月明 | Method for booking guest room and system, hotel information management platform |
| CN107256432A (en) * | 2017-06-08 | 2017-10-17 | 柴韦衣 | A kind of guest room platform management method and device |
-
2018
- 2018-11-27 CN CN201811426679.5A patent/CN109376891B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105243545A (en) * | 2015-09-01 | 2016-01-13 | 张泽 | Multi-platform resource processing method and device |
| CN105354619A (en) * | 2015-12-09 | 2016-02-24 | 姜恒 | Self-service checking-in method and system of hotel |
| CN106296338A (en) * | 2016-07-26 | 2017-01-04 | 斑马信息科技有限公司 | trip order processing method, device and user terminal |
| CN106779119A (en) * | 2016-12-19 | 2017-05-31 | 苏州朗捷通智能科技有限公司 | Hospitality management system |
| 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 |
| CN107679674A (en) * | 2017-10-23 | 2018-02-09 | 携程计算机技术（上海）有限公司 | The Forecasting Methodology and system of the overseas hotel's house type service deficiency of OTA platforms |
| CN107705191A (en) * | 2017-10-25 | 2018-02-16 | 携程计算机技术（上海）有限公司 | The order of OTA platforms strives for method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109376891A (en) | 2019-02-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109376891B (en) | Method and system for determining full house state of residential accommodation | |
| CN107679674B (en) | OTA platform overseas hotel room type service defect prediction method and system | |
| KR101903833B1 (en) | Information provision device, information provision method and recording medium | |
| US20180114154A1 (en) | O2O Business Model For Marketing Services | |
| KR101764366B1 (en) | System of fixing housing facilities | |
| US11257164B1 (en) | Home assessment and issue probability generation | |
| CN105164706A (en) | Automated determination of booking availability for user sourced accommodations | |
| CN106780173B (en) | OTA hotel inventory management method and system | |
| WO2012174010A2 (en) | Energy systems | |
| CN105740331A (en) | Information push method and device | |
| KR101651899B1 (en) | System and method for providing storage service in near living, and application for storing recording medium | |
| US20190005516A1 (en) | Real estate expected sales date application | |
| CN109685234B (en) | Processing method and system for hotel room reservation | |
| CN112288508A (en) | House state information updating method, server and storage medium | |
| CN114418641A (en) | Automatic dispatching method and device for stock customer access work order and electronic equipment | |
| JP2020190972A (en) | Group order support system | |
| CN103310316A (en) | Automobile logistics PDI (pre delivery inspection) management system and method based on handheld mobile terminal | |
| US20230141593A1 (en) | System and method for covering cost of delivering repair and maintenance services to premises of subscribers including same day service | |
| KR20200145369A (en) | Rental service system and method for recycling of coded interior materials | |
| CN114706862B (en) | Hotel room state prediction method, device, equipment and storage medium | |
| WO2023081481A1 (en) | System and method for covering cost of delivering repair and maintenance services to premises of subscribers | |
| KR102365102B1 (en) | Cleaning service by on-line | |
| CN115049231A (en) | Outsourcing personnel management system, method, storage medium and electronic device | |
| KR102379153B1 (en) | Roommaid smart matching service providing system, method and application | |
| JP2002133003A (en) | System and method for introducing provider |
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 |