CN112488377A - Method and device for predicting daily order quantity of express delivery, storage medium and electronic equipment - Google Patents
Method and device for predicting daily order quantity of express delivery, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN112488377A CN112488377A CN202011339140.3A CN202011339140A CN112488377A CN 112488377 A CN112488377 A CN 112488377A CN 202011339140 A CN202011339140 A CN 202011339140A CN 112488377 A CN112488377 A CN 112488377A
- Authority
- CN
- China
- Prior art keywords
- day
- order quantity
- time point
- data
- prediction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000004364 calculation method Methods 0.000 claims abstract description 16
- 230000002354 daily effect Effects 0.000 claims description 21
- 230000014509 gene expression Effects 0.000 claims description 10
- 230000003203 everyday effect Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 2
- 238000013277 forecasting method Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 230000006399 behavior Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000001186 cumulative effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 241001123248 Arma Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06Q10/04—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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Mathematical Physics (AREA)
- Operations Research (AREA)
- Mathematical Analysis (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Computational Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Mathematical Optimization (AREA)
- Tourism & Hospitality (AREA)
- Pure & Applied Mathematics (AREA)
- Algebra (AREA)
- Game Theory and Decision Science (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a method and a device for predicting daily order quantity of express delivery, a storage medium and electronic equipment, belonging to the technical field of logistics, wherein the prediction method comprises the steps of acquiring historical data of daily order quantity of express delivery before the current day; according to the historical data, historical ratio data of the order quantity of the adjacent time points in each day is calculated; determining the prediction ratio data of each time point in a day according to the historical ratio data; and performing prediction calculation based on the order quantity data of the previous time point of the current time point and the prediction ratio data of the corresponding time point so as to predict the order quantity of the current day. The method and the device are beneficial to effectively realizing the real-time prediction of the express order quantity on the same day.
Description
Technical Field
The application belongs to the technical field of logistics, and particularly relates to a method and device for predicting daily order quantity of express delivery, a storage medium and electronic equipment.
Background
For express companies with scales above (orders per day above ten million), it is necessary to predict the orders more accurately so as to improve efficiency in operation management (e.g., reasonably arrange sorting and dispatch resources according to prediction).
The order quantity prediction in the related art mainly comprises the steps of predicting the order quantity of a certain day in advance for several days, and performing real-time prediction and updating by using real-time data of the day (the updating frequency is generally once per hour). The two different time requirements correspond to two different requirements, the forecast of days in advance is that an express company needs to know about the business of a certain day or a certain period of time in advance, and the real-time forecast of the day is to obtain a more accurate forecast of the order quantity of the day by using the existing order data information of the day.
For predicting the updated scene in real time on the day, an easily conceivable method is to use yesterday's order distribution to deduce today's total. Specifically, assuming that r (t) is the proportion of the cumulative order quantity due to yesterday till t to yesterday all day, after knowing the cumulative order quantity q (t) due to today till t, q (t)/r (t) can be used as the prediction of today's all day order quantity. However, in practical implementation, this method has a great disadvantage that when one day is a holiday or a short day (such as 11, 618) and the other day is a normal day, r (t) has a great difference between the two adjacent days, so that the prediction method cannot realize effective prediction.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
In order to overcome the problems in the related art at least to a certain extent, the method, the device, the storage medium and the electronic equipment for predicting the daily order quantity of the express are provided, and the method, the device, the storage medium and the electronic equipment are beneficial to effectively realizing the real-time daily prediction of the daily order quantity of the express.
In order to achieve the purpose, the following technical scheme is adopted in the application:
in a first aspect,
the application provides a method for predicting daily order quantity of express delivery, which comprises the following steps:
acquiring historical data of the order quantity of express days before the current day;
according to the historical data, historical ratio data of the order quantity of the adjacent time points in each day is calculated;
determining the prediction ratio data of each time point in a day according to the historical ratio data;
and performing prediction calculation based on the order quantity data of the previous time point of the current time point and the prediction ratio data of the corresponding time point so as to predict the order quantity of the current day.
Optionally, the historical data is order quantity data of a day before the current day;
the determining of the prediction ratio data of each time point in a day is specifically to determine the historical ratio data of each time point in the previous day as the prediction ratio data of the corresponding time point in the day.
Optionally, the historical data is specifically order quantity data of a preset time period before the current day; the determining the predictive ratio data for each time point of the day may include,
and carrying out average value calculation based on historical ratio data of the same time point every day in the preset time period, and determining the obtained average value data as the predicted ratio data of the corresponding time point in the day.
Optionally, the preset time period is a continuous time period immediately adjacent to the current day.
Optionally, the continuous period of time is from 2 to 5 days.
Optionally, the step of predicting the order quantity of the current day includes calculating the order quantity q (t) of the current time point according to the following expression,
Q(t)＝Q(t-1)*r(t)，
where t represents the current time point, Q (t-1) represents order quantity data of a time point previous to the time point t, and r (t) represents prediction ratio data corresponding to the time point t.
Optionally, the predicting the order quantity of the current day includes calculating a total order quantity S of the current day according to the following expression,
S＝S(0:t-1)+S(t:23)，
S(t:23)＝Q(t)+Q(t)*r(t+1)+…+Q(t)*r(t+1)(t+2)…*r(23)，
wherein S (0: t-1) represents the known order quantity from the current day to the time point of t-1, and S (t:23) represents the predicted order quantity from the time point of t to the time point of 23.
In a second aspect of the present invention,
the application provides a prediction device of express delivery day order volume, the device includes:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring historical data of orders on express days before the current day;
the first calculation module is used for calculating historical ratio data of the order quantity of adjacent time points in each day according to the historical data;
the determining module is used for determining the prediction ratio data of each time point in a day according to the historical ratio data;
and the second calculation module is used for performing prediction calculation based on the order quantity data of the previous time point of the current time point and the prediction ratio data of the corresponding time point so as to predict the order quantity of the current day.
In a third aspect,
the present application provides a readable storage medium having stored thereon an executable program which, when executed by a processor, performs the steps of the method described above.
In a fourth aspect of the present invention,
the application provides an electronic device, including:
a memory having an executable program stored thereon;
a processor for executing the executable program in the memory to implement the steps of the method described above.
This application adopts above technical scheme, possesses following beneficial effect at least:
according to the technical scheme, the prediction ratio data used for prediction calculation are determined from the fact that the ordering behavior habit of the user is stable, and the express daily order quantity is predicted based on the prediction ratio data. The prediction method is simple and convenient to implement, and can effectively achieve the real-time prediction of the express order quantity on the same day.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The accompanying drawings are included to provide a further understanding of the technology or prior art of the present application and are incorporated in and constitute a part of this specification. The drawings expressing the embodiments of the present application are used for explaining the technical solutions of the present application, and should not be construed as limiting the technical solutions of the present application.
Fig. 1 is a schematic flow chart of a method for predicting daily orders of express delivery according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of an apparatus for predicting a daily order quantity of express delivery according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail below. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without making any creative effort, shall fall within the protection scope of the present application.
As described in the background, for express companies with scales above, express order volumes need to be predicted. The order quantity prediction in the related technology mainly comprises the steps of predicting the order quantity of a certain day in advance for several days, and performing real-time prediction and updating by using real-time data of the day.
In a scene needing prediction for several days in advance, two methods are available, namely a model fitting method is used, and a ratio method is used. As the former, a time series model of ARMA series or a linear regression model or the like can be selected. For the latter, historical data of a similar time day of the previous year needs to be found, then, a mean value avg (t) (wherein t represents the t-th year) of the time day dt needing to be predicted in the previous 7 days is calculated, then, a mean value avg (t-1) of a time period corresponding to the seven days of the previous year is calculated, the order quantity Q (dt) of the same day of the previous year corresponding to the time day needing to be predicted is divided by the avg (t-1), so that a proportion r is obtained, and then, the avg (t) is multiplied by r to obtain the prediction of the order quantity dt.
The two methods for forecasting days in advance face an embarrassment that the order quantity of express companies in normal time days is greatly different from that in special time days when modeling is carried out by using a model, for example, the order quantity in the double eleven days is far away from that in No. 11 and 6 months. The time of twenty-one can be called special time day, and the time of 11 month 6 can be called ordinary time day. It is readily understood that the special time days may also include holidays and 618, twenty-two and so on businessy days.
It is clear that it is difficult to predict these particular times of day. Because the volume of orders for these special days is very different from the usual days, separate predictions are needed. But the single prediction also faces the shortage of historical data. This is because modelers need to take out data from history for these special times and days for modeling, but we know that true popularity of twenty-one is only about the last 5 years, and that for the twenty-two and 618 shopping festival is about 3 years. Thus, there are few historical data for these particular days, which are not well modeled.
Thus, there is a second method of predicting a few days ahead-the method of passing a ratio. Specific ideas have been mentioned above, and the disadvantage here is that the ratio in the foregoing is very unstable. The prediction results obtained may have large errors if used directly. An improvement is to observe the variation trend of the ratio for years, and the ratio taking the variation trend into account is used for predicting the order quantity of the time required to predict the current year, so that a better result is obtained. The identification of this trend alone is again a difficult and error-prone place.
Furthermore, neither of these two methods of prediction ahead of time allow corrections to be made on the current day based on current data of that day that is already in real time. There is a need for a method of predicting the amount of orders on the day that are updated in real time. By observing the daily order quantity change of the express company, one easily obtained conclusion is that the order quantity of two adjacent days generally does not change much. Thus, as described in the background, one solution is to assume that the prior day's order size behaves at a different hour than the current day's order size. Assuming that the cumulative amount of orders due to a certain time t on the previous day is Q (t) and the amount of orders over the day on the previous day is Q, Q (t)/Q is the proportion of orders due to the time t on the previous day to the total orders on the previous day, and r (t) is Q (t)/Q. In view of this assumption, it can be considered that Q (t)/Q is also a proportion of orders ending up to time t on the day to the total order on the day. Therefore, the accumulated order quantity D (t) at the time of the deadline t is obtained after the time t of the day, and the prediction of the order quantity of the whole day of the day is obtained by using the accumulated order quantity D (t)/r (t).
However, the applicant has found that this method has major disadvantages after considering the daily order quantity of the courier company in the hour dimension. First, even if the order quantities on two adjacent days are not very different, the distribution of the order quantities on two days in 0-23 hours is different, especially the distribution change in 0-10 hours is relatively large, so the above-mentioned assumption is not particularly true in this time period; secondly, when one of the two adjacent days is a holiday or a short day and the other day is a normal day, the two adjacent days have a great difference in the order quantity, and the distribution of the order quantity in different hours is also different, that is, r (t) has a great difference in the two adjacent days, which means that the first type of prediction method has the problem.
To design a new method for alleviating an error in predicting the order quantity on the current day using the order quantity distribution on the previous day. The applicant has found, through a further study on the distribution of daily orders over different hours, a law that the ordering behavior of the user, starting from 8:00 o' clock to 23:00, exhibits: when the order quantity Q (t) at time t is divided by the order quantity Q (t-1) at previous time, the change of r (t) ═ Q (t)/Q (t-1) on two adjacent days is small.
Based on the law, the applicant provides a method for predicting the daily order quantity of the express delivery based on the law reflecting the ordering behavior habit of the user. As shown in fig. 1, in one embodiment, the prediction method includes the following steps:
step S110 is performed to obtain historical data of the order amount of the express day before the current day, for example, the historical data is obtained from a historical database of a fast forwarding company; specifically, in this embodiment, the history data is order amount data of the day before the current day.
Then, step S120 is carried out, and historical ratio data of the order quantity of the adjacent time points in each day is calculated according to the historical data;
in this embodiment, the ratio of the order quantity at the time point adjacent to the current day is calculated on the basis of the express order quantity data of the day before the current day, which is referred to as historical ratio data in this application, for example, historical ratio data r (t) q (t)/q (t-1), where q (t) represents the order quantity at the time point t in the day, and q (t-1) represents the order quantity at the time point adjacent to the time point t in the day.
After the step S120, continuing to step S130, determining the predicted ratio data of each time point in the day according to the historical ratio data;
in this embodiment, based on the above assumptions, it is obvious that the historical ratio data r (t) of each time point in the previous day is determined as the predicted ratio data r (t) of the corresponding time point in the day.
Finally, step S140 is performed, and a prediction calculation is performed based on the order quantity data of the previous time point of the current time point and the prediction ratio data of the corresponding time point, so as to predict the order quantity of the current day.
Specifically, in this embodiment, the order quantity prediction on the current day includes calculating the order quantity q (t) predicted at the current time point according to the following expression,
Q(t)＝Q(t-1)*r(t) (1)
expression (1), t denotes the current time point, Q (t-1) denotes the order amount data at the time point immediately before the time point t, and r (t) denotes the prediction ratio data corresponding to the time point t.
And further, in this embodiment, the order quantity prediction of the current day is performed, and the method further includes calculating the total predicted order quantity S of the current day according to the following expression,
S＝S(0:t-1)+S(t:23) (2)
S(t:23)＝Q(t)+Q(t)*r(t+1)+…+Q(t)*r(t+1)(t+2)…*r(23) (3)
in expressions (2) and (3), S (0: t-1) represents the known order quantity from the current day up to the time point of t-1, and S (t:23) represents the predicted order quantity from the time point of t up to the time point of 23 on the current day.
As explained below for the meaning of the above expression, according to the above assumptions, if we already know that the order quantity at the previous time t-1 is a × Q (t-1), then it is obvious that we can find that the order quantity at the current time t is a × r (t), so that the time t +1 is a (r) (t +1), the time t +2 is a (r) (t +1) × r (t +2), and so on, the order quantity at the time t + n is a (r) (t +1) × r (t +2) × … (t + n), and the time t + n is the current time 23, so that a (r) (t +1) × r (t +2) × … (t + n) is the predicted value at the time a (r (t + 23). Thus, the order quantity of each hour from the time t to the end of the day has a predicted value, and the sum of the predicted values is S (t:23) ═ A (t) + A (r) (t) + r (t +1) + r (t +2) + … + A (r) (t +1) + r (t +2) + … r (23) which is the sum of the predicted order quantities after the time t-1.
Since the order quantity is known at each time from time 0 to time t-1 (for example, we need to predict 7:20 of the day, then the order at time 0-6 is known and does not need to predict), it is assumed that S (0: t-1) is used, and then the predicted order quantity (total order quantity) S ═ S (0: t-1) + S (t:23) is obtained all day.
By adopting the prediction mode, the updating is carried out at each time t, so that a new predicted value of the daily order quantity exists every hour, and as the time t approaches to the time 23, the predicted value of the daily order quantity is closer to an actual value due to less and less time needing prediction and more stable user behavior habits.
In addition, the applicant has also found that the above assumption that r (t) is the same on two consecutive days is not entirely true in practice. In practice, r (t) will vary greatly between two consecutive days before 9:00 a day, and from 9:00 the ratio will stabilize between two consecutive days. Based on this, as a specific implementation manner, in this embodiment, t in the expressions (2) and (3) is greater than or equal to 9 points, that is, in practice, the real-time prediction starts from 8 points, so as to realize more accurate and effective prediction.
By verifying actual data for more than 100 days from 3 months to 6 months, it was found that the prediction error obtained using the new method was significantly reduced by more than 5% starting from 8:00 (the prediction error is defined as abs (the amount of actual orders on the day-the amount of orders predicted all day at a certain time)/the amount of actual orders on the day, where abs is an absolute value function).
According to the technical scheme, the prediction ratio data used for prediction calculation are determined from the fact that the ordering behavior habit of the user is stable, and the express daily order quantity is predicted based on the prediction ratio data. The prediction method is simple and convenient to implement, and can effectively achieve the real-time prediction of the express order quantity on the same day.
To facilitate understanding of the technical solutions of the present application, the technical solutions of the present application will be described below with reference to another embodiment.
As an improvement of the foregoing embodiment, the history data in this embodiment is specifically: order quantity data of a preset time period before the current day; for example, the preset time period is a continuous time period next to the current day, for example, the continuous time period is 2 to 5 days.
Further, in step S120 of this embodiment, historical ratio data of order amounts at adjacent time points in each day in a preset time period is calculated; in the following step S130, an average value calculation is performed based on the historical ratio data of the same time point every day in a predetermined time period, and the obtained average value data is determined as the predicted ratio data r (t) of the corresponding time point in the day.
The prediction in step S140 is performed based on the prediction ratio data obtained in this manner, and the prediction effect can be further improved to some extent.
In addition, the applicant should emphasize that the technical solution of the present application can be effectively implemented in the case that the daily order quantity may be required to be more than ten million orders and the order quantity may show certain laws when an express company predicts the order quantity because the daily order quantity changes are difficult to be perceived.
Fig. 2 is a schematic structural diagram of an apparatus for predicting a daily order quantity of express delivery according to an embodiment of the present application, and as shown in fig. 2, the apparatus 200 includes:
an obtaining module 201, configured to obtain historical data of an order amount of an express day before a current day;
the first calculating module 202 is configured to calculate historical ratio data of order amounts of adjacent time points in each day according to historical data;
a determining module 203, configured to determine, according to the historical ratio data, prediction ratio data of each time point in a day;
the second calculating module 204 is configured to perform a prediction calculation based on order quantity data at a time point before the current time point and prediction ratio data at the corresponding time point, so as to predict an order quantity on the current day.
With respect to the prediction apparatus 200 in the above related embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
In one embodiment, the present application also provides a readable storage medium having stored thereon an executable program, which when executed by a processor, performs the steps of the above-described method.
With regard to the readable storage medium in the above-mentioned embodiments, the specific manner of executing the operation by the stored program has been described in detail in the embodiments related to the method, and will not be elaborated herein.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application, and as shown in fig. 3, the electronic device 300 includes:
a memory 301 having an executable program stored thereon;
a processor 302 for executing the executable program in the memory 301 to implement the steps of the above method.
With respect to the electronic device 300 in the above embodiment, the specific manner of executing the program in the memory 301 by the processor 302 thereof has been described in detail in the embodiment related to the method, and will not be elaborated herein.
The above description is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method for predicting daily order quantity of express delivery is characterized by comprising the following steps:
acquiring historical data of the order quantity of express days before the current day;
according to the historical data, historical ratio data of the order quantity of the adjacent time points in each day is calculated;
determining the prediction ratio data of each time point in a day according to the historical ratio data;
and performing prediction calculation based on the order quantity data of the previous time point of the current time point and the prediction ratio data of the corresponding time point so as to predict the order quantity of the current day.
2. The prediction method according to claim 1, wherein the history data is, specifically, order amount data of a day before a current day;
the determining of the prediction ratio data of each time point in a day is specifically to determine the historical ratio data of each time point in the previous day as the prediction ratio data of the corresponding time point in the day.
3. The prediction method according to claim 1, wherein the historical data is specifically order quantity data of a preset time period before a current day; the determining the predictive ratio data for each time point of the day may include,
and carrying out average value calculation based on historical ratio data of the same time point every day in the preset time period, and determining the obtained average value data as the predicted ratio data of the corresponding time point in the day.
4. The prediction method according to claim 3, wherein the preset time period is a continuous time period immediately adjacent to a current day.
5. The prediction method according to claim 4, wherein the continuous period of time is 2 to 5 days.
6. The prediction method according to claim 1, wherein the predicting the order quantity on the current day comprises calculating the order quantity Q (t) of the predicted current time point according to the following expression,
Q(t)＝Q(t-1)*r(t)，
where t represents the current time point, Q (t-1) represents order quantity data of a time point previous to the time point t, and r (t) represents prediction ratio data corresponding to the time point t.
7. The forecasting method according to claim 6, wherein the forecasting of the order quantity for the current day includes calculating a total order quantity S for the forecasting current day according to the following expression,
S＝S(0:t-1)+S(t:23)，
S(t:23)＝Q(t)+Q(t)*r(t+1)+…+Q(t)*r(t+1)(t+2)…*r(23)，
wherein S (0: t-1) represents the known order quantity from the current day to the time point of t-1, and S (t:23) represents the predicted order quantity from the time point of t to the time point of 23.
8. An express daily order amount prediction device, comprising:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring historical data of orders on express days before the current day;
the first calculation module is used for calculating historical ratio data of the order quantity of adjacent time points in each day according to the historical data;
the determining module is used for determining the prediction ratio data of each time point in a day according to the historical ratio data;
and the second calculation module is used for performing prediction calculation based on the order quantity data of the previous time point of the current time point and the prediction ratio data of the corresponding time point so as to predict the order quantity of the current day.
9. A readable storage medium having stored thereon an executable program, wherein the executable program, when executed by a processor, performs the steps of the method of any one of claims 1-7.
10. An electronic device, comprising:
a memory having an executable program stored thereon;
a processor for executing the executable program in the memory to implement the steps of the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011339140.3A CN112488377A (en) | 2020-11-25 | 2020-11-25 | Method and device for predicting daily order quantity of express delivery, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011339140.3A CN112488377A (en) | 2020-11-25 | 2020-11-25 | Method and device for predicting daily order quantity of express delivery, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112488377A true CN112488377A (en) | 2021-03-12 |
Family
ID=74934720
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011339140.3A Pending CN112488377A (en) | 2020-11-25 | 2020-11-25 | Method and device for predicting daily order quantity of express delivery, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112488377A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114091755A (en) * | 2021-11-23 | 2022-02-25 | 北京奇艺世纪科技有限公司 | Method and device for predicting daily active user, electronic equipment and medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120143652A1 (en) * | 2010-12-06 | 2012-06-07 | Stefan Resag | Sales volume monitoring |
| CN104766144A (en) * | 2015-04-22 | 2015-07-08 | 携程计算机技术（上海）有限公司 | Order forecasting method and system |
| CN106779230A (en) * | 2016-12-27 | 2017-05-31 | 北京三快在线科技有限公司 | Order volume predictor method and device, electronic equipment |
| CN107292649A (en) * | 2016-04-01 | 2017-10-24 | 阿里巴巴集团控股有限公司 | The method and apparatus of traffic forecast Data correction |
| CN108053242A (en) * | 2017-12-12 | 2018-05-18 | 携程旅游信息技术（上海）有限公司 | Sight spot admission ticket ticket amount Forecasting Methodology, system, equipment and storage medium |
| CN108764559A (en) * | 2018-05-22 | 2018-11-06 | 四川众之金科技有限公司 | The same day withdraws deposit total value prediction technique and device |
| KR101915416B1 (en) * | 2017-12-26 | 2019-01-07 | 벽산파워 주식회사 | A peak demand control system using energy storage system |
-
2020
- 2020-11-25 CN CN202011339140.3A patent/CN112488377A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120143652A1 (en) * | 2010-12-06 | 2012-06-07 | Stefan Resag | Sales volume monitoring |
| CN104766144A (en) * | 2015-04-22 | 2015-07-08 | 携程计算机技术（上海）有限公司 | Order forecasting method and system |
| CN107292649A (en) * | 2016-04-01 | 2017-10-24 | 阿里巴巴集团控股有限公司 | The method and apparatus of traffic forecast Data correction |
| CN106779230A (en) * | 2016-12-27 | 2017-05-31 | 北京三快在线科技有限公司 | Order volume predictor method and device, electronic equipment |
| CN108053242A (en) * | 2017-12-12 | 2018-05-18 | 携程旅游信息技术（上海）有限公司 | Sight spot admission ticket ticket amount Forecasting Methodology, system, equipment and storage medium |
| KR101915416B1 (en) * | 2017-12-26 | 2019-01-07 | 벽산파워 주식회사 | A peak demand control system using energy storage system |
| WO2019132054A1 (en) * | 2017-12-26 | 2019-07-04 | 벽산파워 주식회사 | Peak demand control system using energy storage device |
| CN108764559A (en) * | 2018-05-22 | 2018-11-06 | 四川众之金科技有限公司 | The same day withdraws deposit total value prediction technique and device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114091755A (en) * | 2021-11-23 | 2022-02-25 | 北京奇艺世纪科技有限公司 | Method and device for predicting daily active user, electronic equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9356846B2 (en) | Automated upgrading method for capacity of IT system resources | |
| JP3581094B2 (en) | Residual value prediction system and method, and recording medium recording residual value prediction program operating on computer | |
| US10345770B2 (en) | Power demand estimating apparatus, method, program, and demand suppressing schedule planning apparatus | |
| US7987106B1 (en) | System and methods for forecasting time series with multiple seasonal patterns | |
| JP6079215B2 (en) | Power demand forecasting device, program | |
| CN105205297B (en) | Service prediction method and system based on time sequence | |
| CN109615226A (en) | A kind of operation indicator method for monitoring abnormality | |
| CN104471573A (en) | Updating cached database query results | |
| CN111210056A (en) | Electricity price scheme determination method and device, computer equipment and storage medium | |
| CN111242602A (en) | Control method and device of payment equipment, computer readable storage medium and equipment | |
| US20160036272A1 (en) | Predicting and optimizing energy storage lifetime performance with adaptive automation control software | |
| CN112613637A (en) | Method and device for processing charging load | |
| CN109886737A (en) | Needing forecasting method, device, electronic equipment and readable storage medium storing program for executing | |
| CN113919655A (en) | Law enforcement personnel scheduling method, system, computer device and storage medium | |
| WO2024001045A1 (en) | Carbon quota surplus and deficit prediction method, apparatus, and electronic device, and storage medium | |
| CN112488377A (en) | Method and device for predicting daily order quantity of express delivery, storage medium and electronic equipment | |
| CN111210260A (en) | Electricity price data processing method and device, computer equipment and storage medium | |
| CN116050866A (en) | Combined user missing electric quantity fitting method and system based on typical load curve | |
| CN109146134A (en) | Part amount prediction technique, system, equipment and storage medium are pulled in a kind of peak | |
| Hau | A Hicksian approach to cost-benefit analysis with discrete-choice models | |
| CN114416891A (en) | Method, system, apparatus and medium for data processing in a knowledge graph | |
| JP2004023114A (en) | Method and system for predicting communication traffic | |
| CN110532319A (en) | A kind of distribution meteorological data timing processing system | |
| KR20130044765A (en) | Appratus and method for estimation of weekly power load to improve processing time using neural network and revision factor | |
| CN115564152A (en) | Carbon emission prediction method and device based on STIRPAT model |
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 |