CN109886737A - Needing forecasting method, device, electronic equipment and readable storage medium storing program for executing - Google Patents
Needing forecasting method, device, electronic equipment and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN109886737A CN109886737A CN201910082390.4A CN201910082390A CN109886737A CN 109886737 A CN109886737 A CN 109886737A CN 201910082390 A CN201910082390 A CN 201910082390A CN 109886737 A CN109886737 A CN 109886737A
- Authority
- CN
- China
- Prior art keywords
- sales volume
- demand
- history
- target hotel
- hotel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Embodiment of the disclosure provides a kind of needing forecasting method, device, electronic equipment and readable storage medium storing program for executing, which comprises determines the history sales volume in target hotel;The sales volume Reduction parameter in the target hotel is determined according to the reference history sales volume in the target hotel and reference pass room time, described is respectively the corresponding history sales volume with reference to hotel in the target hotel, pass room time with reference to history sales volume, with reference to the pass room time;It is adjusted according to history sales volume of the sales volume Reduction parameter to the target hotel;According to the demand of target hotel at the appointed time described in the history Method for Sales Forecast after adjustment.The history sales volume in target hotel can be adjusted according to the history sales volume in reference hotel, pass room time, the prediction accuracy of demand is helped to improve using more accurate history sales volume.
Description
Technical field
Embodiment of the disclosure is related to online sale technical field more particularly to a kind of needing forecasting method, device, electronics
Equipment and readable storage medium storing program for executing.
Background technique
With the development of network, hotel can also make a reservation on network.For online sale Hotel Products, online sale is flat
Platform needs Accurate Prediction demand, facilitates stock control, avoids the excessive sale of inventory endless or shortage of stock influence sales volume.
In the prior art, a kind of hotel group is proposed application No. is 2016108745399 patent application to divide and demand
The method of prediction.Key step includes: firstly, using the latitude and longitude information in each hotel with same city attribute, commercial circle
Attribute, the first history sales volume information are modified multiple commercial circles in the same city;Secondly, using each revised described
The comment score, Hotel Star in each hotel, comment number, hotel's average price, the first history sales volume, traffic convenience in commercial circle
All hotels in each revised commercial circle are divided into multiple hotel groups by degree;Finally, utilizing each hotel group's
History predetermined number, the second history sales volume, predict month user's pageview, predict month Webpage pageview, recently
Conclusion of the business increasing value is calculated as parameter, obtains each hotel group in the requirement forecasting result in prediction month.
As can be seen that above scheme passes through history predetermined number, history Method for Sales Forecast demand, only due to online sale platform
It can get oneself history predetermined number, the limitation of history sales volume, rather than the total history predetermined number of Hotel Products, history pin
Amount causes prediction result inaccurate.
Summary of the invention
Embodiment of the disclosure provides a kind of needing forecasting method, device, electronic equipment and readable storage medium storing program for executing, to solve
The above problem of prior art hotel Demand Forecast.
It is according to an embodiment of the present disclosure in a first aspect, providing a kind of needing forecasting method, which comprises
Determine the history sales volume in target hotel;
The sales volume in the target hotel is determined also according to the reference history sales volume in the target hotel and with reference to the room time is closed
Original parameter, it is described with reference to history sales volume, with reference to close the room time be respectively the corresponding history sales volume with reference to hotel in the target hotel,
Close the room time;
It is adjusted according to history sales volume of the sales volume Reduction parameter to the target hotel;
According to the demand of target hotel at the appointed time described in the history Method for Sales Forecast after adjustment.
Second aspect according to an embodiment of the present disclosure, provides a kind of demand-prediction device, and described device includes:
History sales volume determining module, for determining the history sales volume in target hotel;
Sales volume Reduction parameter determining module, for the reference history sales volume according to the target hotel and with reference to the pass room time
Determine the sales volume Reduction parameter in the target hotel, it is described with reference to history sales volume, with reference to the room time is closed be respectively the target wine
The corresponding history sales volume with reference to hotel in shop, pass room time;
History sales volume adjusts module, for being carried out according to history sales volume of the sales volume Reduction parameter to the target hotel
Adjustment;
Demand Forecast module, at the appointed time for the target hotel according to the history Method for Sales Forecast after adjustment
Demand.
The third aspect according to an embodiment of the present disclosure, provides a kind of electronic equipment, comprising:
Processor, memory and it is stored in the computer journey that can be run on the memory and on the processor
Sequence, which is characterized in that the processor realizes aforementioned need prediction technique when executing described program.
Fourth aspect according to an embodiment of the present disclosure provides a kind of readable storage medium storing program for executing, when in the storage medium
Instruction by electronic equipment processor execute when so that electronic equipment is able to carry out aforementioned need prediction technique.
Embodiment of the disclosure provides a kind of needing forecasting method, device, electronic equipment and readable storage medium storing program for executing, described
Method comprises determining that the history sales volume in the target hotel;According to the reference history sales volume in the target hotel and with reference to pass room
Time determines the sales volume Reduction parameter in the target hotel, it is described with reference to history sales volume, with reference to the room time is closed be respectively the mesh
Mark the corresponding history sales volume with reference to hotel in hotel, pass room time;The target hotel is gone through according to the sales volume Reduction parameter
History sales volume is adjusted;According to the demand of target hotel at the appointed time described in the history Method for Sales Forecast after adjustment.It can be with
The history sales volume in target hotel is adjusted according to the history sales volume in reference hotel, pass room time, using more accurate history
Sales volume helps to improve the prediction accuracy of demand.
Detailed description of the invention
In order to illustrate more clearly of the technical solution of embodiment of the disclosure, below by the description to embodiment of the disclosure
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only the implementation of the disclosure
Some embodiments of example for those of ordinary skill in the art without any creative labor, can be with
It obtains other drawings based on these drawings.
Fig. 1 shows the needing forecasting method flow chart of steps in a kind of embodiment of the disclosure;
Fig. 2 shows the needing forecasting method flow chart of steps in another embodiment of the disclosure;
Fig. 3 shows the structure chart of the demand-prediction device in a kind of embodiment of the disclosure;
Fig. 4 shows the structure chart of the demand-prediction device in another embodiment of the disclosure;
Fig. 5 shows the structure chart of the electronic equipment in a kind of embodiment of the disclosure.
Specific embodiment
Below in conjunction with the attached drawing in embodiment of the disclosure, the technical solution in embodiment of the disclosure is carried out clear
Chu is fully described by, it is clear that described embodiment is embodiment of the disclosure a part of the embodiment, rather than whole realities
Apply example.Based on the embodiment in embodiment of the disclosure, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, belong to embodiment of the disclosure protection range.
Embodiment one
Referring to Fig.1, it illustrates the step flow charts of the needing forecasting method in a kind of embodiment of the disclosure, specifically such as
Under.
Step 101, the history sales volume in target hotel is determined.
Embodiment of the disclosure is suitable for the prediction to commodity demand volume, especially for the prediction of hotel's demand.It can
To understand, embodiment of the disclosure can be applied to the commodity of various on-line sellings, be not limited to Hotel Products.
Wherein, history sales volume is the sales volume of the unit time in certain historical time section.For example, according in nearly 1 year
Sales situation, the sales volume of statistical average every month is as history sales volume, or, statistics is every according to the sales situation in nearly 1 year
The sales volume in week is as history sales volume.
Step 102, the target hotel is determined according to the reference history sales volume in the target hotel and with reference to the room time is closed
Sales volume Reduction parameter, it is described with reference to history sales volume, with reference to the room time is closed be respectively that the target hotel is corresponding with reference to hotel
History sales volume closes the room time.
Wherein, sales volume Reduction parameter is for being adjusted to history sales volume close to true history sales volume.In practical applications,
Since inventory is nervous or other are special, so that the quantity of inventory becomes actual sales volume, but the actual sales volume is inaccurate.
The sales volume Reduction parameter adjusts the target hotel with reference to history sales volume and reference lockup according to described
History sales volume,
It is appreciated that bigger with reference to history sales volume, then sales volume Reduction parameter is bigger;It is smaller with reference to history sales volume, then sales volume
Reduction parameter is smaller.
Closing the room time be that can sell the modification time of state, wherein can sell whether status representative commodity can be sold, including can sell with
Two states can not be sold.In practical applications, after hotel room has been sold, hotel room sells state by that can sell status maintenance
It is changed to that state can not be sold, to stop the sale of hotel room.
It can be the similar hotel in target hotel with reference to hotel, can specifically be judged by city, commercial circle, star.Example
Such as, same city is in target hotel, in same commercial circle, and the hotel with identical star is with reference to hotel.
Wherein, commercial circle can the business scope of region division then can be with for example, to Mr. Yu landmark building A according to
Certain area is as commercial circle A around A, so that hotel in the area belongs to commercial circle A.It is appreciated that the division of commercial circle can
It is divided with other non-buildings according to building, park etc., can divide, can also be advised according to other demands according to entity area
Then divided.
Star is the grade of service by certification.For example, hotel can be divided into it is three-star, four-star, five-star.
It is appreciated that can be all average sales volumes with reference to hotel within the unit time with reference to history sales volume.
With reference to closing, the room time is smaller, then shows that hotel room has been sold more early, is represented the hotel room and is more easy to appear library
Inadequate situation is deposited, so that it corresponds to higher sales volume Reduction parameter;With reference to closing, the room time is bigger, then shows that hotel room is sold
It is complete more late, it represents the hotel room and is less susceptible to the inadequate situation of inventory occur, so that it corresponds to lower sales volume Reduction parameter.
For example, closing the hotel room that the room time is 08:00 in morning, sales volume Reduction parameter is than closing the hotel room that the room time is evening 6:00
Greatly.
Step 103, it is adjusted according to history sales volume of the sales volume Reduction parameter to the target hotel.
Specifically, sales volume Reduction parameter is bigger, and the history sales volume before adjustment is bigger, then the history sales volume after adjusting is got over
Greatly;Sales volume Reduction parameter is smaller, and the history sales volume before adjustment is smaller, then the history sales volume after adjusting is smaller.
In practical applications, further deformation can also be carried out to sales volume Reduction parameter to calculate.For example, taking logarithm, referring to
Several or linear transformation etc..
Step 104, the demand of target hotel at the appointed time according to the history Method for Sales Forecast after adjustment.
Wherein, specified time is current time or future time.
Demand can sell required commodity amount as unit of in the time.For example, selling required commodity number in one day
Amount sells required commodity amount or sells required commodity amount in one month in one week.Demand and history sales volume can
It, can also be according to different time granularities to use identical time granularity.For example, history sales volume can be daily average pin
The amount of selling, and demand can be commodity amount needed for interior sale in one day or one week.When the two time granularity difference, need into
Row conversion, is often that required commodity amount is sold in one day according to the demand that daily average sales volume prediction obtains, then
Commodity amount needed for sale in one week can be obtained multiplied by 7 to required commodity amount is sold in one day.
Specifically, history sales volume is bigger, and demand is bigger;History sales volume is smaller, and demand is smaller.
In conclusion embodiment of the disclosure provides a kind of needing forecasting method, which comprises determine target wine
The history sales volume in shop;The pin in the target hotel is determined according to the reference history sales volume in the target hotel and with reference to the pass room time
Reduction parameter is measured, described is respectively the corresponding history for referring to hotel in the target hotel with reference to history sales volume, with reference to the pass room time
Sales volume closes the room time;It is adjusted according to history sales volume of the sales volume Reduction parameter to the target hotel;According to adjustment
The demand of target hotel at the appointed time described in history Method for Sales Forecast afterwards.Can according to the history sales volume in reference hotel, close
The room time is adjusted the history sales volume in target hotel, and the prediction of demand is helped to improve using more accurate history sales volume
Accuracy.
Embodiment two
Referring to Fig. 2, it illustrates the specific steps processes of the needing forecasting method in another embodiment of the disclosure
Figure, it is specific as follows.
Step 201, the history sales volume in target hotel is determined.
The step is referred to the detailed description of step 101, and details are not described herein.
Step 202, the average value for calculating the reference history sales volume in the target hotel, obtains average reference history sales volume.
It is appreciated that average reference history sales volume is bigger, sales volume Reduction parameter is bigger;Average reference history sales volume is smaller,
Sales volume Reduction parameter is smaller
Step 203, the average value of room time is closed in the reference for calculating the target hotel, obtains average reference and closes the room time.
It is appreciated that average reference closes, the room time is bigger, and sales volume Reduction parameter is smaller;The average reference pass room time is smaller,
Sales volume Reduction parameter is bigger.
Step 204, room time calculating sales volume reduction ginseng is closed according to the average reference history sales volume and the average reference
Number, described is respectively the corresponding history sales volume with reference to hotel in the target hotel, pass room with reference to history sales volume, with reference to the pass room time
Time.
In embodiment of the disclosure, sales volume Reduction parameter can be directly determined, can also determine inventory's anxiety journey first
Parameter is spent, sales volume Reduction parameter is then determined according to inventory's tensity parameter.
For example, determining sales volume Reduction parameter according to following Table A.Further, it is also possible to which the relationship in reference table A, establishes sales volume
Reduction parameter and average reference close the functional relation between room time, average reference history sales volume, thus according to functional relation
Formula calculates sales volume Reduction parameter.
Further, it is also possible to determine inventory's tensity by table B first, then, also according to inventory's tensity and sales volume
Relational expression between original parameter calculates sales volume Reduction parameter.Wherein, inventory's tensity and sales volume Reduction parameter pass in direct ratio
It is formula.
It should be noted that when determining the relationship of average reference history sales volume and sales volume Reduction parameter, it is possible, firstly, to will
Whole hotels are divided into multiple set according to city, commercial circle, star, according to the detailed description in step 101 to reference hotel
It is found that the hotel in each set refers to hotel each other;Then, the average reference history pin in the hotel each set Zhong Ge is calculated
Amount;Finally, descending arrangement is carried out according to average reference history sales volume, so that the set of sequence earlier above corresponds to biggish sales volume reduction
Parameter, inventory's tensity, the set after sequence relatively correspond to lesser sales volume Reduction parameter, inventory's tensity.Such as Table A or B
In, room time, the corresponding sales volume Reduction parameter of preceding 30% set, inventory's tensity, than preceding are closed for same average reference
The corresponding sales volume Reduction parameter of 30% to 50% set, inventory's tensity are big;Similarly, preceding 30% to 50% set is corresponding
Sales volume Reduction parameter, inventory's tensity, sales volume Reduction parameter more corresponding than preceding by 50% to 100% set, inventory are nervous
Degree is big.
It respectively can be the similar hotel in target hotel with reference to hotel, can specifically be judged by city, commercial circle, star
It is appreciated that relationship shown in Table A and table B can be not to fix according to practical application scene appropriate adjustment
Value, as long as embody sales volume Reduction parameter, inventory's tensity respectively with average reference close room time, average reference history sales volume
Relationship trend and Table A and table B in it is consistent.
Table A
Table B
Step 205, the product for calculating the history sales volume in the sales volume Reduction parameter and the target hotel, is adjusted it
History sales volume afterwards.
Specifically, the reduction of history sales volume is referred to following formula:
HSN=APRHSN'(1)
Wherein, HSN is the history sales volume after reduction, and HSN' is the history sales volume before restoring, and APR is sales volume reduction ginseng
Number.
Step 206, determine that the target hotel is corresponding according to the history sales volume in the target hotel and data degree of saturation
Divide barrel type.
Wherein, data saturation degree can be described according to the smoothness of data, for example, for a Hotel Products, if continuously
It is every daily to have sale, and sales volume is substantially steady, then it is assumed that the data saturation degree of the Hotel Products is larger;If sales volume is neglected height and is neglected
It is low, or even do not have directly, then data saturation degree is smaller.
In embodiment of the disclosure, first, in accordance with the hotel Xian Shang history sales volume maximum value and minimum value, data are full
Divide barrel type and corresponding history sales volume range and data saturation degree range with the maximum value and minimum value of degree.For example,
Can be by history sales volume less than 100, data saturation degree is less than 2 as barrel type 1 is divided, and by history sales volume less than 100, data are saturated
Degree is greater than or equal to 2, and less than 8 as barrel type 2 is divided, history sales volume is greater than or equal to 100, data saturation degree is made less than 2
To divide barrel type 3, history sales volume is greater than or equal to 100, data saturation degree is greater than or equal to 2, and is used as less than 8 and divides barrel type
4。
Specifically, for each point of barrel type, history sales volume range and data saturation degree range are corresponded to.Hence for mesh
Hotel is marked, can choose history sales volume within the scope of history sales volume, data saturation degree divides bucket within the scope of data saturation degree
Type divides barrel type as target hotel.
Step 207, divide barrel type corresponding Demand Forecast model described in determining.
Wherein, Demand Forecast model divides barrel type and different for different.
In practical applications, Demand Forecast model is obtained by demand sample set by XGBOOST model training.Its
In, demand sample set obtains as follows: firstly, obtaining hotel complete or collected works from line, and filtering out history sales volume and is less than
Certain threshold value or data saturation degree are less than the hotel of certain threshold value, so that remaining hotel divides barrellled wine shop collection as candidate;So
Afterwards, barrellled wine shop is divided to determine that candidate divides what barrellled wine shop concentrated each hotel to divide bucket class candidate according to history sales volume and data saturation degree
Type;Finally, for each hotel of same point of barrel type of correspondence, history sales volume, predetermined number, pricing information, user are browsed
Information, static labels information, holiday information, Weather information, traffic information and actual demand amount, as demand sample set
This is trained to divide barrel type corresponding Demand Forecast model.
Wherein, history sales volume is the actual history sales volume that candidate divides barrellled wine shop.
Predetermined number can as unit of in the time hotel predetermined number.It is appreciated that predetermined number is bigger, demand is got over
Greatly;Predetermined number is smaller, and demand is smaller.
User browses information and can be indicated with the number that user in the unit time browses hotel.It is appreciated that number is bigger,
Demand is bigger;Number is smaller, and demand is smaller.
Static labels can include but is not limited to: temporal characteristics and provincial characteristics, wherein temporal characteristics include: days again
Day numerical value, whether vacation, whether working day, festivals or holidays coding, apart from the workaday number of days of up/down, workaday apart from up/down
Number of days;Provincial characteristics include: city level, whether tourist city, ChengShi Hotel number, commercial circle hotel number, Hotel Star, whether
Progress is consumed for standard/hotel Gao Xing, hotel's history.
Holiday information includes: the history sales volume mean value of festivals or holidays, non-festivals or holidays, festivals or holidays and non-festivals or holidays history sales volume
The ratio of mean value, if there are festivals or holidays to break out effect.It can reflect out the growth feelings of festivals or holidays demand by festivals or holidays feature
Condition, the demand of festivals or holidays is more much higher than on ordinary days, and so as to be reflected by feature, festivals or holidays feature can characterize POI
Whether there is the case where demand increase in festivals or holidays.
Weather information includes but is not limited to: the information such as fine day, cloudy day, temperature.It is appreciated that under different weather situation,
The demand in hotel is different.
Traffic information includes but is not limited to: the distance apart from bus station, public transport quantity.
Actual demand amount can sales volume as unit of in the time.
Step 208, using Demand Forecast model target according to the history Method for Sales Forecast after the adjustment
The demand in hotel.
Specifically, history sales volume is input to the demand in the target hotel predicted in Demand Forecast model.
Optionally, in another embodiment of the disclosure, above-mentioned steps 208 include sub-step 2081 to 2082:
Sub-step 2081 obtains fixed reference feature, and the fixed reference feature includes at least: the predetermined number in the target hotel,
The pricing information in the target hotel, the target hotel user browse information, the static labels information in the target hotel,
The traffic information of holiday information, Weather information and the target hotel is one such.
Fixed reference feature is referred to corresponding detailed description in step 207, and details are not described herein.
History sales volume, fixed reference feature after adjustment is input in the Demand Forecast model, obtains by sub-step 2082
To the demand in the target hotel.
It is appreciated that fixed reference feature can also increase other features, embodiment of the disclosure according to practical application scene
It is without restriction to its.
Step 209, target Hotel Products are determined at the appointed time according to the demand of the target hotel at the appointed time
Demand.
The demand in hotel can be split as the demand of Hotel Products by embodiment of the disclosure, more accurately description
Demand.
Wherein, target Hotel Products can be the featured major products or the higher product of sales volume or inventory out in hotel
Nervous product etc..
Optionally, in another embodiment of the disclosure, above-mentioned steps 209 include sub-step 2091 to 2092:
Sub-step 2091 counts the history sales volume of the target Hotel Products.
It is appreciated that the history sales volume of target Hotel Products is different from the history sales volume in target hotel, target Hotel Products
The sum of history sales volume be less than or equal to the history sales volume in target hotel.
Sub-step 2092, according to accounting, the target of the history sales volume of the target Hotel Products in total sales volume
The demand of hotel at the appointed time determines the demand of the target Hotel Products at the appointed time, and the total sales volume is each
The sum of history sales volume of target Hotel Products.
Specifically, for each target Hotel Products, can by the accounting in target hotel multiplied by the demand in target hotel,
Obtain the demand of target Hotel Products.
In addition, if can also determine target Hotel Products when target Hotel Products are not all products in target hotel
Demand before, the demand in target hotel is distributed to target Hotel Products and non-targeted Hotel Products.So as to keep away
Exempt from the demand that the sum of the demand of target Hotel Products and the demand of non-targeted Hotel Products are greater than target hotel, avoids this
The appearance of inconsistency.
Embodiment of the disclosure can distribute higher demand to the higher Hotel Products of sales volume, to the lower wine of sales volume
Shop product distributes lower demand, so as to effectively improve profit of operation.
Optionally, in another embodiment of the disclosure, above-mentioned steps 209 include sub-step 2093:
Sub-step 2093, according to the pricing information of target Hotel Products, the demand of the target hotel at the appointed time
Determine the demand of the target Hotel Products at the appointed time.
In practical applications, since the Hotel Products sales volume of low price is higher, so as to be the production of the hotel of low price
Product distribute higher demand;Lower demand is distributed for the Hotel Products of high price.
Embodiment of the disclosure can distribute higher demand for the Hotel Products of low price, can effectively improve hotel
Sales volume.
Step 210, for the second designated time period before the specified time, real demand amount and forecast demand are calculated
The difference of amount.
Wherein, real demand amount can be subject to effective sale amount.
Predicted required amount is the demand using model prediction.It in practical applications, can be with after each predicted required amount
The predicted required amount is saved, the predicted value for demand after adjusting.
It is appreciated that the second designated time period as far as possible close to specified time, thereby may be ensured that the adjustment of demand is accurate
Degree.
Step 211, the demand of the target hotel at the appointed time is adjusted according to the difference.
It specifically, can be using the sum of difference and demand as the demand after adjustment.
In practical applications, the ratio of real demand amount and predicted required amount can also be calculated, and by the ratio and target
The product of the demand in hotel, as the demand after adjustment.
Embodiment of the disclosure can further be adjusted according to the demand of prediction after predicted value, facilitate further
Improve the prediction accuracy of demand.
Step 212, the demand of the target hotel at the appointed time is adjusted according to the real-time sales volume of the specified time.
Wherein, real-time sales volume represents real-time condition of sales, if sales volume is excessively high in real time, demand can suitably be turned up
Amount.For example, being 100 for the demand in the October 1 of prediction, if 8 a.m., real-time sales volume has reached 80, then can incite somebody to action
The demand of this day is turned up.
In addition, can suitably turn down demand if sales volume is too low in real time.For example, the demand in the October 1 for prediction
It is 100, if 2 pm, real-time sales volume is 10, then can turn down the demand of this day.
Embodiment of the disclosure can accurately adjust demand according to real-time sale situation, especially for time granularity compared with
Big demand (such as moon) avoids demand caused by emergency situations inaccurate.
In conclusion embodiment of the disclosure provides a kind of needing forecasting method, which comprises determine the mesh
Mark the history sales volume in hotel;The target hotel is determined according to the reference history sales volume in the target hotel and with reference to the room time is closed
Sales volume Reduction parameter, it is described with reference to history sales volume, with reference to the room time is closed be respectively that the target hotel is corresponding with reference to hotel
History sales volume closes the room time;It is adjusted according to history sales volume of the sales volume Reduction parameter to the target hotel;According to tune
The demand of target hotel at the appointed time described in history Method for Sales Forecast after whole.It can be according to the history pin in reference hotel
Amount, pass room time are adjusted the history sales volume in target hotel, help to improve demand using more accurate history sales volume
Prediction accuracy.
Embodiment three
Referring to Fig. 3, it illustrates the structure charts of the demand-prediction device in another embodiment of the disclosure, specifically such as
Under.
History sales volume determining module 301, for determining the history sales volume in target hotel.
Sales volume Reduction parameter determining module 302, for the reference history sales volume according to the target hotel and with reference to pass room
Time determines the sales volume Reduction parameter in the target hotel, it is described with reference to history sales volume, with reference to the room time is closed be respectively the mesh
Mark the corresponding history sales volume with reference to hotel in hotel, pass room time.
History sales volume adjusts module 303, for the history sales volume according to the sales volume Reduction parameter to the target hotel
It is adjusted.
Demand Forecast module 304, for the target hotel according to the history Method for Sales Forecast after adjustment when specified
Between demand.
In conclusion embodiment of the disclosure provides a kind of demand-prediction device, described device includes: that history sales volume is true
Cover half block, for determining the history sales volume in target hotel;Sales volume Reduction parameter determining module, for according to the target hotel
The sales volume Reduction parameter in the target hotel is determined with reference to history sales volume and with reference to the pass room time, it is described with reference to history sales volume, ginseng
Examining the pass room time is respectively the corresponding history sales volume with reference to hotel in the target hotel, pass room time;History sales volume adjusts module,
For being adjusted according to history sales volume of the sales volume Reduction parameter to the target hotel;Demand Forecast module, is used for
According to the demand of target hotel at the appointed time described in the history Method for Sales Forecast after adjustment.It can going through according to reference hotel
History sales volume, pass room time are adjusted the history sales volume in target hotel, and being helped to improve using more accurate history sales volume is needed
The prediction accuracy for the amount of asking.
Embodiment three is the corresponding Installation practice of embodiment one, and detailed description is referred to embodiment one, herein no longer
It repeats.
Example IV
Referring to Fig. 4, it illustrates the structure charts of the demand-prediction device in a kind of embodiment of the disclosure, specifically such as
Under.
History sales volume determining module 401, for determining the history sales volume in target hotel.
Sales volume Reduction parameter determining module 402, for the reference history sales volume according to the target hotel and with reference to pass room
Time determines the sales volume Reduction parameter in the target hotel, it is described with reference to history sales volume, with reference to the room time is closed be respectively the mesh
The corresponding history sales volume with reference to hotel in hotel, pass room time are marked, optionally, in the embodiments of the present disclosure, above-mentioned sales volume reduction ginseng
Counting determining module 402 includes:
Average reference history sales volume computational submodule 4021, for calculate the target hotel reference history sales volume it is flat
Mean value obtains average reference history sales volume.
Average reference closes room time computational submodule 4022, and the flat of room time is closed in the reference for calculating the target hotel
Mean value obtains average reference and closes the room time.
Sales volume Reduction parameter computational submodule 4023, for according to the average reference history sales volume and the average reference
Close room time calculating sales volume Reduction parameter.
History sales volume adjusts module 403, for the history sales volume according to the sales volume Reduction parameter to the target hotel
It is adjusted, optionally, in the embodiments of the present disclosure, above-mentioned history sales volume adjusts module 403, comprising:
History sales volume adjusting submodule 4031, for calculating the history pin of the sales volume Reduction parameter Yu the target hotel
The product of amount, the history sales volume after being adjusted.
Demand Forecast module 404, for the target hotel according to the history Method for Sales Forecast after adjustment when specified
Between demand.Optionally, in the embodiments of the present disclosure, the demand amount prediction module 404, comprising:
Barrel type is divided to determine submodule 4041, for true according to the history sales volume and data degree of saturation in the target hotel
Fixed corresponding point of target hotel barrel type.
Prediction model chooses submodule 4042, for dividing barrel type corresponding Demand Forecast model described in determination.
Demand Forecast submodule 4043, for using the Demand Forecast model according to the history after the adjustment
The demand in target hotel described in Method for Sales Forecast.
Optionally, in another embodiment of the disclosure, the demand amount predicts submodule 4043, comprising:
Fixed reference feature acquiring unit, for obtaining fixed reference feature, the fixed reference feature is included at least: the target hotel
Predetermined number, the pricing information in the target hotel, the target hotel user browse information, the static state in the target hotel
Label information, holiday information, Weather information and the traffic information in the target hotel are one such.
Demand Forecast unit, for history sales volume, the fixed reference feature after adjustment to be input to the Demand Forecast
In model, the demand in the target hotel is obtained.
Demand splits module 405, for determining target hotel according to the demand of the target hotel at the appointed time
The demand of product at the appointed time.
Optionally, in another embodiment of the disclosure, the demand amount splits module 405, comprising:
History sales statistics submodule, for counting the history sales volume of the target Hotel Products.
First demand split submodule, for according to the history sales volume of the target Hotel Products in total sales volume
Accounting, the demand of the target hotel at the appointed time determine the demand of the target Hotel Products at the appointed time, institute
State the sum of the history sales volume that total sales volume is each target Hotel Products.
Optionally, in another embodiment of the disclosure, the demand amount splits module 405, comprising:
Second demand splits submodule, for being referred to according to the pricing information of target Hotel Products, the target hotel
The demand fixed time determines the demand of the target Hotel Products at the appointed time.
Demand deviation computing module 406, for calculating true for the second designated time period before the specified time
The difference of real demand and predicted required amount.
First demand adjusts module 407, for the demand according to the difference to the target hotel at the appointed time
Amount is adjusted.
Second demand adjusts module 408, for adjusting the target hotel according to the real-time sales volume of the specified time
Demand at the appointed time.
In conclusion embodiment of the disclosure provides a kind of demand-prediction device, described device includes: that history sales volume is true
Cover half block, for determining the history sales volume in target hotel;Sales volume Reduction parameter determining module, for according to the target hotel
The sales volume Reduction parameter in the target hotel is determined with reference to history sales volume and with reference to the pass room time, it is described with reference to history sales volume, ginseng
Examining the pass room time is respectively the corresponding history sales volume with reference to hotel in the target hotel, pass room time;History sales volume adjusts module,
For being adjusted according to history sales volume of the sales volume Reduction parameter to the target hotel;Demand Forecast module, is used for
According to the demand of target hotel at the appointed time described in the history Method for Sales Forecast after adjustment.It can going through according to reference hotel
History sales volume, pass room time are adjusted the history sales volume in target hotel, and being helped to improve using more accurate history sales volume is needed
The prediction accuracy for the amount of asking.
Example IV is the corresponding Installation practice of embodiment two, and detailed description is referred to embodiment two, herein no longer
It repeats.
Embodiment of the disclosure additionally provides a kind of electronic equipment, referring to Fig. 5, comprising: processor 501, memory 502 with
And it is stored in the computer program 5021 that can be run on the memory 502 and on the processor, the processor 501 is held
The needing forecasting method of previous embodiment is realized when row described program.
Embodiment of the disclosure additionally provides a kind of readable storage medium storing program for executing, when the instruction in the storage medium is set by electronics
When standby processor executes, so that electronic equipment is able to carry out the needing forecasting method of previous embodiment.
For device embodiment, since it is basically similar to the method embodiment, related so being described relatively simple
Place illustrates referring to the part of embodiment of the method.
Algorithm and display are not inherently related to any particular computer, virtual system, or other device provided herein.
Various general-purpose systems can also be used together with teachings based herein.As described above, it constructs required by this kind of system
Structure be obvious.In addition, embodiment of the disclosure is also not for any particular programming language.It should be understood that can be with
The content of embodiment of the disclosure described herein is realized using various programming languages, and is retouched above to what language-specific was done
Stating is preferred forms in order to disclose embodiment of the disclosure.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the disclosure
The embodiment of example can be practiced without these specific details.In some instances, it is not been shown in detail well known
Methods, structures and technologies, so as not to obscure the understanding of this specification.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of the various inventive aspects,
Above in the description of the exemplary embodiment of embodiment of the disclosure, each feature of embodiment of the disclosure is sometimes by together
It is grouped into single embodiment, figure or descriptions thereof.However, it is as follows that the method for the disclosure should not be construed to reflection
Be intended to: embodiment of the disclosure i.e. claimed requires more more than feature expressly recited in each claim
Feature.More precisely, as reflected in the following claims, inventive aspect is single less than disclosed above
All features of embodiment.Therefore, it then follows thus claims of specific embodiment are expressly incorporated in the specific embodiment party
Formula, wherein separate embodiments of each claim as embodiment of the disclosure itself.
Those skilled in the art will understand that can be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more devices different from this embodiment.It can be the module or list in embodiment
Member or component are combined into a module or unit or component, and furthermore they can be divided into multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it can use any
Combination is to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so disclosed
All process or units of what method or apparatus are combined.Unless expressly stated otherwise, this specification is (including adjoint power
Benefit require, abstract and attached drawing) disclosed in each feature can carry out generation with an alternative feature that provides the same, equivalent, or similar purpose
It replaces.
The various component embodiments of embodiment of the disclosure can be implemented in hardware, or in one or more processing
The software module run on device is realized, or is implemented in a combination thereof.It will be understood by those of skill in the art that can be in reality
It tramples and middle realizes requirement forecasting equipment according to an embodiment of the present disclosure using microprocessor or digital signal processor (DSP)
In some or all components some or all functions.Embodiment of the disclosure is also implemented as executing here
Some or all device or device programs of described method.Such program for realizing embodiment of the disclosure
It can store on a computer-readable medium, or may be in the form of one or more signals.Such signal can be with
It downloads from internet website, is perhaps provided on the carrier signal or is provided in any other form.
It should be noted that above-described embodiment illustrates rather than to embodiment of the disclosure embodiment of the disclosure
It is limited, and those skilled in the art can be designed replacement without departing from the scope of the appended claims and implement
Example.In the claims, any reference symbol between parentheses should not be configured to limitations on claims.Word
"comprising" does not exclude the presence of element or step not listed in the claims.Word "a" or "an" located in front of the element is not
There are multiple such elements for exclusion.Embodiment of the disclosure can be by means of including the hardware of several different elements and borrowing
Help properly programmed computer to realize.In the unit claims listing several devices, several in these devices
A can be is embodied by the same item of hardware.The use of word first, second, and third does not indicate any suitable
Sequence.These words can be construed to title.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
The foregoing is merely the preferred embodiments of embodiment of the disclosure, not to limit the implementation of the disclosure
Example, all made any modifications, equivalent replacements, and improvements etc. within the spirit and principle of embodiment of the disclosure should all include
Within the protection scope of embodiment of the disclosure.
The above, the only specific embodiment of embodiment of the disclosure, but the protection scope of embodiment of the disclosure
It is not limited thereto, anyone skilled in the art, can in the technical scope that embodiment of the disclosure discloses
Change or replacement are readily occurred in, should all be covered within the protection scope of embodiment of the disclosure.Therefore, embodiment of the disclosure
Protection scope should be subject to the protection scope in claims.
Claims (13)
1. a kind of needing forecasting method, which is characterized in that the described method includes:
Determine the history sales volume in target hotel;
Determine that the sales volume reduction in the target hotel is joined according to the reference history sales volume in the target hotel and with reference to the room time is closed
Number, described is respectively the corresponding history sales volume with reference to hotel in the target hotel, pass room with reference to history sales volume, with reference to the pass room time
Time;
It is adjusted according to history sales volume of the sales volume Reduction parameter to the target hotel;
According to the demand of target hotel at the appointed time described in the history Method for Sales Forecast after adjustment.
2. the method according to claim 1, wherein it is described according to the sales volume Reduction parameter to the target wine
The step of history sales volume in shop is adjusted, comprising:
Calculate the product of the history sales volume in the sales volume Reduction parameter and the target hotel, the history pin after being adjusted
Amount.
3. the method according to claim 1, wherein the reference history sales volume according to the target hotel and
The step of determining the sales volume Reduction parameter in the target hotel with reference to the pass room time, comprising:
The average value for calculating the reference history sales volume in the target hotel, obtains average reference history sales volume;
The average value of room time is closed in the reference for calculating the target hotel, obtains average reference and closes the room time;
Room time calculating sales volume Reduction parameter is closed according to the average reference history sales volume and the average reference.
4. the method according to claim 1, wherein the mesh according to the history Method for Sales Forecast after adjustment
The step of marking the demand of hotel at the appointed time, comprising:
Corresponding point of target hotel barrel type is determined according to the history sales volume in the target hotel and data degree of saturation;
Divide barrel type corresponding Demand Forecast model described in determination;
Using the demand in Demand Forecast model target hotel according to the history Method for Sales Forecast after the adjustment.
5. according to the method described in claim 4, it is characterized in that, described use the Demand Forecast model according to the tune
The step of demand in target hotel described in the history Method for Sales Forecast after whole, comprising:
Obtain fixed reference feature, the fixed reference feature includes at least: the predetermined number in the target hotel, the target hotel valence
Lattice information, user the browsing information, the static labels information in the target hotel, holiday information, weather in the target hotel
The traffic information in information and the target hotel is one such;
History sales volume, fixed reference feature after adjustment is input in the Demand Forecast model, the target hotel is obtained
Demand.
6. the method according to claim 1, wherein described according to the history Method for Sales Forecast after adjustment
After the step of target hotel demand at the appointed time, further includes:
The demand of target Hotel Products at the appointed time is determined according to the demand of the target hotel at the appointed time.
7. according to the method described in claim 6, it is characterized in that, the demand according to the target hotel at the appointed time
The step of measuring the demand of determining target Hotel Products at the appointed time, comprising:
Count the history sales volume of the target Hotel Products;
At the appointed time according to accounting of the history sales volume of the target Hotel Products in total sales volume, the target hotel
Demand determines that the demand of the target Hotel Products at the appointed time, the total sales volume are going through for each target Hotel Products
The sum of history sales volume.
8. according to the method described in claim 6, it is characterized in that, the demand according to the target hotel at the appointed time
The step of measuring the demand of determining target Hotel Products at the appointed time, comprising:
The target hotel is determined according to the pricing information of target Hotel Products, the demand of the target hotel at the appointed time
The demand of product at the appointed time.
9. the method according to claim 1, wherein the method also includes:
For the second designated time period before the specified time, the difference of real demand amount and predicted required amount is calculated;
The demand of the target hotel at the appointed time is adjusted according to the difference.
10. the method according to claim 1, wherein the method also includes:
The demand of the target hotel at the appointed time is adjusted according to the real-time sales volume of the specified time.
11. a kind of demand-prediction device, which is characterized in that described device includes:
History sales volume determining module, for determining the history sales volume in target hotel;
Sales volume Reduction parameter determining module is determined for the reference history sales volume according to the target hotel and with reference to the room time is closed
The sales volume Reduction parameter in the target hotel, it is described with reference to history sales volume, with reference to close the room time be respectively the target hotel pair
The history sales volume in hotel should be referred to, close the room time;
History sales volume adjusts module, for being adjusted according to history sales volume of the sales volume Reduction parameter to the target hotel
It is whole;
Demand Forecast module, for the demand of target hotel at the appointed time according to the history Method for Sales Forecast after adjustment
Amount.
12. a kind of electronic equipment characterized by comprising
Processor, memory and it is stored in the computer program that can be run on the memory and on the processor,
It is characterized in that, the processor realizes the requirement forecasting as described in one or more in claim 1-10 when executing described program
Method.
13. a kind of readable storage medium storing program for executing, which is characterized in that when the instruction in the storage medium is held by the processor of electronic equipment
When row, so that electronic equipment is able to carry out the needing forecasting method as described in one or more in claim to a method 1-10.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910082390.4A CN109886737A (en) | 2019-01-28 | 2019-01-28 | Needing forecasting method, device, electronic equipment and readable storage medium storing program for executing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910082390.4A CN109886737A (en) | 2019-01-28 | 2019-01-28 | Needing forecasting method, device, electronic equipment and readable storage medium storing program for executing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109886737A true CN109886737A (en) | 2019-06-14 |
Family
ID=66927197
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910082390.4A Pending CN109886737A (en) | 2019-01-28 | 2019-01-28 | Needing forecasting method, device, electronic equipment and readable storage medium storing program for executing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109886737A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110689170A (en) * | 2019-09-04 | 2020-01-14 | 北京三快在线科技有限公司 | Object parameter determination method and device, electronic equipment and storage medium |
CN112258224A (en) * | 2020-10-19 | 2021-01-22 | 北京沃东天骏信息技术有限公司 | Information generation method, device, terminal, system and storage medium |
CN112308587A (en) * | 2019-07-31 | 2021-02-02 | 中国石油天然气股份有限公司 | Method and device for determining natural gas peak-valley-month sales volume and storage medium |
CN113592532A (en) * | 2021-06-25 | 2021-11-02 | 杉数科技(北京)有限公司 | Method and device for restoring historical demand of commodity |
CN118096243A (en) * | 2024-04-28 | 2024-05-28 | 国网山东省电力公司淄博供电公司 | New energy automobile sales prediction method, system and medium based on fusion model |
-
2019
- 2019-01-28 CN CN201910082390.4A patent/CN109886737A/en active Pending
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112308587A (en) * | 2019-07-31 | 2021-02-02 | 中国石油天然气股份有限公司 | Method and device for determining natural gas peak-valley-month sales volume and storage medium |
CN112308587B (en) * | 2019-07-31 | 2024-03-05 | 中国石油天然气股份有限公司 | Natural gas peak valley month sales quantity determining method, device and storage medium |
CN110689170A (en) * | 2019-09-04 | 2020-01-14 | 北京三快在线科技有限公司 | Object parameter determination method and device, electronic equipment and storage medium |
CN112258224A (en) * | 2020-10-19 | 2021-01-22 | 北京沃东天骏信息技术有限公司 | Information generation method, device, terminal, system and storage medium |
CN113592532A (en) * | 2021-06-25 | 2021-11-02 | 杉数科技(北京)有限公司 | Method and device for restoring historical demand of commodity |
CN118096243A (en) * | 2024-04-28 | 2024-05-28 | 国网山东省电力公司淄博供电公司 | New energy automobile sales prediction method, system and medium based on fusion model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11281969B1 (en) | Artificial intelligence system combining state space models and neural networks for time series forecasting | |
CN109886737A (en) | Needing forecasting method, device, electronic equipment and readable storage medium storing program for executing | |
US20200057918A1 (en) | Systems and methods for training artificial intelligence to predict utilization of resources | |
US20230018311A1 (en) | Systems and methods for quantity determinations without predicting out of stock events | |
US10748072B1 (en) | Intermittent demand forecasting for large inventories | |
US11010798B2 (en) | System and method for integrating retail price optimization for revenue and profit with business rules | |
CN109657831A (en) | A kind of Traffic prediction method, apparatus, equipment, storage medium | |
US11301794B2 (en) | Machine for labor optimization for efficient shipping | |
Temur | A novel multi attribute decision making approach for location decision under high uncertainty | |
Tiemessen et al. | Dynamic demand fulfillment in spare parts networks with multiple customer classes | |
Xiao et al. | MIP-based fix-and-optimise algorithms for the parallel machine capacitated lot-sizing and scheduling problem | |
US20110279469A1 (en) | Performing time slice-based visual prediction | |
CN108460631A (en) | The mixing method for pushing and device of diversification information | |
CN109445884A (en) | A kind of functional label methods of exhibiting and terminal device | |
CN110019420A (en) | A kind of data sequence prediction technique and calculate equipment | |
CN113204712A (en) | Information pushing method, device, medium and program product based on community service | |
CN109615414A (en) | House property predictor method, device and storage medium | |
CN110751359B (en) | Automatic route network evaluation method, electronic equipment and storage medium | |
US20170178221A1 (en) | Method and system for inventory availability prediction | |
CN114693351A (en) | Information prediction method and device and electronic equipment | |
CN111464337A (en) | Resource allocation method and device and electronic equipment | |
CN115759926A (en) | Article scheduling method, device, equipment and computer readable medium | |
CN110008970A (en) | A kind of address information generation method and device | |
CN104040548A (en) | Automatic demand parameter estimation | |
CN114782129A (en) | Information recommendation method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |