CN115375037A - Demand prediction method and device - Google Patents
Demand prediction method and device Download PDFInfo
- Publication number
- CN115375037A CN115375037A CN202211117183.6A CN202211117183A CN115375037A CN 115375037 A CN115375037 A CN 115375037A CN 202211117183 A CN202211117183 A CN 202211117183A CN 115375037 A CN115375037 A CN 115375037A
- Authority
- CN
- China
- Prior art keywords
- sequence
- demand
- seasonal
- zero
- demands
- 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 50
- 230000001932 seasonal effect Effects 0.000 claims abstract description 186
- 238000009499 grossing Methods 0.000 claims description 16
- 238000001914 filtration Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 5
- 238000013277 forecasting method Methods 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 235000019580 granularity Nutrition 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 230000000306 recurrent effect Effects 0.000 description 3
- 238000013068 supply chain management Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000008929 regeneration Effects 0.000 description 2
- 238000011069 regeneration method Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012384 transportation and delivery 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the disclosure discloses a demand forecasting method and device. One embodiment of the method comprises: acquiring a predicted demand quantity sequence of a target object in a target time period, wherein the predicted demand quantity sequence comprises a seasonal demand quantity sequence and a non-seasonal demand quantity sequence, and the seasonal demand quantity sequence represents demand quantity generated by seasonal influence of the target time period; updating the non-seasonal demand sequence to obtain an updated non-seasonal demand sequence, wherein the updated non-seasonal demand sequence represents the influence of the intermittency of the demand of the target object on the non-seasonal demand sequence; and updating the forecast demand sequence according to the seasonal demand sequence and the updated non-seasonal demand sequence. The embodiment contributes to improving the accuracy of demand amount prediction of the target object.
Description
Technical Field
The embodiment of the disclosure relates to the technical field of computers, in particular to a demand forecasting method and device.
Background
In the engineering machinery industry and the like, the demand of various products is generally required to be predicted in advance, so as to manufacture, distribute or allocate resources and the like according to the needs. The existing product prediction methods include a conventional prediction method and a prediction method based on deep learning. Conventional prediction methods include, for example, exponential smoothing, croston, ARIMA (automated Integrated Moving Average Model), prophet algorithm, etc. The prediction method based on deep learning and the like include, for example, a prediction method based on RNN (Recurrent Neural Network) and TCN time convolution Network, and the like.
The demand for a large amount of products in the industries such as construction machinery and the like usually presents a strong intermittency. The existing prediction methods generally focus on considering the seasonal characteristics of the product demand, and cannot well consider the seasonal characteristics and the indirect characteristics of the product demand at the same time.
Disclosure of Invention
The embodiment of the disclosure provides a demand forecasting method and device.
In a first aspect, an embodiment of the present disclosure provides a demand prediction method, including: acquiring a predicted demand sequence of a target object in a target time period, wherein the predicted demand sequence comprises a seasonal demand sequence and a non-seasonal demand sequence, and the seasonal demand sequence represents the demand generated by the seasonal influence of the target time period; updating the non-seasonal demand sequence to obtain an updated non-seasonal demand sequence, wherein the updated non-seasonal demand sequence represents the influence of the intermittency of the demand of the target object on the non-seasonal demand sequence; and updating the forecast demand sequence according to the seasonal demand sequence and the updated non-seasonal demand sequence.
In a second aspect, an embodiment of the present disclosure provides a demand prediction apparatus, including: an acquisition unit configured to acquire a sequence of predicted demand amounts of a target object over a target time period, wherein the sequence of predicted demand amounts includes a sequence of seasonal demand amounts and a sequence of non-seasonal demand amounts, the sequence of seasonal demand amounts representing demand amounts resulting from seasonal influences of the target time period; a first updating unit configured to update a sequence of non-seasonal demands, resulting in an updated sequence of non-seasonal demands, wherein the updated sequence of non-seasonal demands represents an effect of an intermittency of a demand of a target object on the sequence of non-seasonal demands; a second updating unit configured to update the sequence of predicted demand amounts based on the sequence of seasonal demand amounts and the updated sequence of non-seasonal demand amounts.
In a third aspect, an embodiment of the present disclosure provides an electronic device, including: one or more processors; storage means for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method as described in any implementation of the first aspect.
In a fourth aspect, embodiments of the present disclosure provide a computer-readable medium on which a computer program is stored, which computer program, when executed by a processor, implements the method as described in any of the implementations of the first aspect.
According to the demand forecasting method and device provided by the embodiment of the disclosure, the seasonal demand sequence generated by seasonal influence of the target object in the target time period and the non-seasonal demand sequence excluding the seasonal influence are forecasted, then the non-seasonal demand sequence is updated according to the intermittence of the demand of the target object, and the forecasted demand sequence of the target object in the target time period is obtained according to the seasonal demand sequence and the updated non-seasonal demand sequence, so that the influence of the seasonality, the intermittence and the like on the demand of the target object is considered at the same time, and the accuracy of forecasting the demand of the target object is improved.
Drawings
Other features, objects and advantages of the disclosure will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is an exemplary system architecture diagram in which one embodiment of the present disclosure may be applied;
FIG. 2 is a flow diagram of one embodiment of a demand prediction method according to the present disclosure;
FIG. 3 is a schematic diagram of an application scenario of a demand forecasting method according to an embodiment of the present disclosure;
FIG. 4 is a flow diagram of yet another embodiment of a demand prediction method according to the present disclosure;
FIG. 5 is a schematic block diagram of one embodiment of a demand prediction apparatus according to the present disclosure;
FIG. 6 is a schematic structural diagram of an electronic device suitable for use in implementing embodiments of the present disclosure.
Detailed Description
The present disclosure is described in further detail below with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that, in the present disclosure, the embodiments and features of the embodiments may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
FIG. 1 illustrates an exemplary architecture 100 to which embodiments of the demand forecasting method or apparatus of the present disclosure may be applied.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. Network 104 is the medium used to provide communication links between terminal devices 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The terminal devices 101, 102, 103 interact with a server 105 via a network 104 to receive or send messages or the like. Various client applications may be installed on the terminal devices 101, 102, 103. Such as browser-type applications, search-type applications, shopping-type applications, database-type applications, and so forth.
The terminal devices 101, 102, 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be various electronic devices including, but not limited to, smart phones, tablet computers, e-book readers, laptop portable computers, desktop computers, and the like. When the terminal apparatuses 101, 102, 103 are software, they can be installed in the electronic apparatuses listed above. It may be implemented as multiple pieces of software or software modules (e.g., multiple pieces of software or software modules to provide distributed services) or as a single piece of software or software module. And is not particularly limited herein.
The server 105 may be a server that provides various services, such as a backend server that provides support for client applications installed on the terminal devices 101, 102, 103. The server 105 may obtain a predicted demand sequence of the target object in the target time period from the terminal devices 101, 102, 103, where the predicted demand sequence may include a seasonal demand sequence and a non-seasonal demand sequence, and may update the non-seasonal demand sequence to obtain an updated non-seasonal demand sequence, and then update the predicted demand sequence according to the seasonal demand sequence and the updated non-seasonal demand sequence.
It should be noted that the sequence of the predicted demand amounts of the target objects in the target time period may also be directly stored locally in the server 105, and the server 105 may directly extract and process the sequence of the predicted demand amounts of the target objects in the target time period, in which case, the terminal devices 101, 102, and 103 and the network 104 may not be present.
It should be noted that the demand forecasting method provided by the embodiment of the present disclosure is generally executed by the server 105, and accordingly, the demand forecasting device is generally disposed in the server 105.
It should be further noted that the terminal devices 101, 102, and 103 may also have demand forecasting applications installed therein, and the terminal devices 101, 102, and 103 may also obtain a sequence of forecasted demand of the target object in the target time period based on the demand forecasting applications, where the sequence of forecasted demand may include a seasonal demand sequence and a non-seasonal demand sequence, and then may update the non-seasonal demand sequence to obtain an updated non-seasonal demand sequence, and then update the sequence of forecasted demand according to the seasonal demand sequence and the updated non-seasonal demand sequence.
In this case, the demand prediction method may be executed by the terminal devices 101, 102, and 103, and accordingly, the demand prediction apparatus may be provided in the terminal devices 101, 102, and 103. At this point, the exemplary system architecture 100 may not have the server 105 and the network 104.
The server 105 may be hardware or software. When the server 105 is hardware, it may be implemented as a distributed server cluster composed of a plurality of servers, or may be implemented as a single server. When the server 105 is software, it may be implemented as multiple pieces of software or software modules (e.g., multiple pieces of software or software modules used to provide distributed services), or as a single piece of software or software module. And is not particularly limited herein.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow 200 of one embodiment of a demand prediction method according to the present disclosure is shown. The demand prediction method includes the steps of:
In this embodiment, the object may be various things with or without entities. For example, the object may be various items (e.g., a work machine, etc.). For example, the object may be a virtual product such as various services. The target object may be any object to be subjected to the demand pre-storage. The target time period may be any time period specified according to actual application requirements.
The demand sequence may consist of several chronologically ordered demands. The predicted demand may refer to a predicted value of the demand. As an example, the target object is a robotic arm. The target time period is the next quarter. The sequence of forecasted demand may consist of the forecasted demand for the target object for each month or week in the next quarter. In other words, each element in the sequence of the predicted demand amounts corresponds to one time point.
The sequence of forecasted demand may include a sequence of seasonal demands and a sequence of non-seasonal demands. Wherein the seasonal demand in the sequence of seasonal demands may represent a demand for the target object due to an influence of the season of the target time period. Correspondingly, the non-seasonal demand in the non-seasonal demand sequence may represent a demand for the target object excluding the influence of the season of the target time period. That is, the predicted demand amount of the target object at each time point in the target time period is decomposed into a seasonal demand amount and a non-seasonal demand amount according to seasonality.
The execution subject of the demand prediction method (such as the server 105 shown in fig. 1 or the like) may acquire the predicted demand sequence of the target object for the target time period from a local or other storage device or the like. The sequence of the predicted demand amount of the target object in the target time period can be determined in advance by adopting various methods. For example, the sequence of predicted demand amounts for the target object over the target time period may be determined by a technician based on historical experience. For another example, various existing demand prediction methods may be employed to determine a sequence of predicted demands of the target object over the target time period. The predicted demand amount sequence of the target object in the target time period may be determined by the execution subject, or may be determined by other electronic devices.
Step 202, updating the non-seasonal demand sequence to obtain an updated non-seasonal demand sequence.
In this embodiment, the updated non-seasonal demand sequence may represent an effect or variation on the non-seasonal demand sequence caused by the intermittency of the demand of the target object. Since the demand of many objects usually has a certain intermittency, i.e. a temporal characteristic, the non-seasonal demand sequence can be represented more accurately by taking into account the intermittency of the demand of the target object to update the non-seasonal demand sequence.
In particular, various methods may be employed to update the non-seasonal demand sequence based on the intermittency of the demand of the target object. For example, characteristic changes of the historical demand of the target object in time can be counted, and then the influence of the intermittence of the demand of the target object on the non-seasonal demand sequence is determined according to the counting result, so that shadow updating of the non-seasonal demand sequence is achieved.
And step 203, updating the forecast demand sequence according to the seasonal demand sequence and the updated non-seasonal demand sequence.
In this embodiment, after obtaining the updated non-seasonal demand sequence, the sequence of seasonal demands obtained in step 201 may be combined with the sequence of seasonal demands to update the sequence of predicted demands of the target object in the target time period. In general, the elements in the seasonal demand sequence, the non-seasonal demand sequence, and the updated non-seasonal demand sequence are in one-to-one correspondence according to time points. Thus, the updated sequence of non-seasonal demands may be determined by calculating a sum of corresponding elements in the updated sequence of non-seasonal demands and the sequence of seasonal demands, and determining the sequence of demands calculated by the sum as the updated sequence of forecasted demands.
In some optional implementation manners of this embodiment, the pre-stored demand sequence of the target object in the target time period may be obtained by the following steps:
step one, obtaining a historical demand sequence of a target object.
In this step, the history demand amount sequence of the target object may include the demand amount of the target object at several time points before the target time period. Specifically, the actual demand of the target object at each time point can be recorded in time along with the time change, so as to form a historical demand sequence of the target object.
And step two, obtaining the predicted demand by using an exponential smoothing algorithm according to the historical demand sequence.
In the step, the exponential smoothing algorithm increases the weight of the recent observed value by giving different weights to the observed values at different times, so that the predicted value can quickly reflect the actual change. Specifically, the predicted demand amount may be obtained by a technician by using different smoothing times according to actual application requirements, such as a first exponential smoothing method, a second exponential smoothing method, a third exponential smoothing method, and the like.
As an example, the predicted required amount may be obtained by the following formula:
s t ＝β(y t -r t )+(1-β)s t-1
r t ＝α(y t -s t )+(1-α)r t-1
wherein the content of the first and second substances,
indicating the predicted demand. "y" represents the actual demand. "s" represents "seasonal demand. "r" represents non-seasonal demand. "t" and "t-1" respectively represent two different time points adjacent to each other in front and rear. "α" and "β" are smoothing coefficients. Generally, the smoothing coefficient is not less than "0" and not more than "1".
At this time, smoothing coefficients "α" and "β" may be calculated by using an iterative method and minimizing a prediction error according to the historical demand sequence, and then the calculated smoothing coefficients "α" and "β" may be used to obtain a predicted demand sequence, which specifically includes a seasonal demand sequence and a non-seasonal demand sequence.
The demand of the target object can be accurately decomposed into seasonal demand and non-seasonal demand by using an exponential smoothing algorithm, so that the influence of seasonality on the demand of the target object can be accurately described.
In some optional implementation manners of this embodiment, after the historical demand sequence of the target object is obtained, the historical demand sequence may be further preprocessed to obtain a preprocessed historical demand, and then the historical demand sequence may be replaced with the preprocessed historical demand for subsequent predicted demand update.
The preprocessing can include operations such as data filtering and/or data summarization, and can be flexibly set according to actual application requirements. For example, in a scenario where the historical demand sequence for a target object is determined by statistics on orders that include the target object, data filtering may include, but is not limited to, order filtering, promotion filtering, and large order culling, among others. Data summaries may include, but are not limited to, warehouse layer level summaries, alternate chains, order summary requirements, and the like.
The order filtering may refer to filtering special orders and orders that are older. The live-marketing filtering may refer to filtering dimensions for which no sales records exist for a long time, and the dimensions may refer to various attributes of the target object, and the like. The big order rejection can refer to the rejection of orders with abnormal requirements according to a preset rule. Some abnormal data can be eliminated through data filtering, so that the interference of the abnormal data on the prediction demand is avoided.
The warehouse network level summarization can refer to summarization of orders in various warehouses according to a hierarchical structure among the warehouses, and a specific summarization mode can be flexibly set according to an actual application scene. The replacement chain may refer to an update replacement of an old target object after the target object is upgraded. The order summarizing requirement can mean that orders with the same time granularity are summarized according to the time granularity, and the time granularity can be flexibly set according to an actual application scene. The statistical category of the historical demand sequence of the target object can be flexibly set through data summarization, so that demand prediction of the target object on different data granularities is realized.
With continued reference to fig. 3, fig. 3 is an exemplary application scenario 300 of the demand prediction method according to the present embodiment. In the application scenario of fig. 3, taking the target object as an example of the robot arm, the demand of the robot arm in each previous quarter may be first obtained from the database to form a history demand sequence 301. Then, an exponential smoothing algorithm or the like may be used to predict the demand of the robot arm in the next quarter from the historical demand sequence 301 to form a predicted demand sequence 302. Specifically, the predicted demand sequence includes a seasonal demand sequence 3021 and a non-seasonal demand sequence 3022, and then the non-seasonal demand sequence 3022 may be updated in consideration of the intermittent characteristics of the robot demand, so as to obtain an updated non-seasonal demand sequence 3023, and further, the updated predicted demand sequence 303 may be obtained based on the seasonal demand sequence 3021, so as to implement more accurate robot demand prediction.
After the demand of the robot arm is predicted, more rational robot arm supply chain management may be further performed based on the prediction result, i.e., the updated predicted demand sequence 303. As indicated by reference numeral 304, supply chain management may specifically include, but is not limited to: inventory management, production management, transportation management, pricing management, and the like.
For example, the stock quantity of the robot arm is controlled according to the prediction result, and the situations such as stock shortage or overstock are avoided. For another example, production, delivery date, transportation mode and the like are reasonably arranged according to the prediction result, and the user requirements are met in time. By feeding back the prediction results to supply chain management, it helps to reduce inventory, ensure production continuity, reduce costs, improve quality of service, maintain a balance between supply chain reaction capacity and costs.
In consideration of seasonal and intermittent characteristics of a target object, the existing traditional demand forecasting method can only focus on the characteristics of a single demand sequence generally, and the deep learning-based demand forecasting method is poor in interpretability generally. According to the method provided by the embodiment of the disclosure, seasonal characteristics of the target object are considered by using an exponential smoothing algorithm and the like, then the non-seasonal partial data is further processed by considering intermittent characteristics of the target object in a deep regeneration process, and then the demand data is predicted by combining the demand data considering the seasonal characteristics and the intermittent characteristics of the target object, so that the prediction result can meet the seasonal characteristics and the intermittent characteristics of the target object. And by analyzing by using the historical demand data of the target object, the information among the historical demand data of the target objects with different dimensions can be fully utilized, and simultaneously, the interpretability of seasonal and intermittent influences on demand can be better provided by using a deep regeneration process.
With further reference to FIG. 4, a flow 400 of yet another embodiment of a demand prediction method is illustrated. The flow 400 of the demand prediction method includes the following steps:
In this embodiment, the non-seasonal demand sequence is split into a non-zero demand sequence and a time interval sequence. And the non-zero demand sequence is obtained by sequentially removing zero elements in the non-seasonal demand sequence. The sequence of time intervals is obtained by sequentially calculating the time intervals between adjacent non-zero demands (i.e. non-zero elements) in the sequence of non-seasonal demands.
As an example, the formation of the sequence of non-zero demands and the sequence of time intervals may be expressed as follows:
{r t |t＝1，2，…}
{d t |d t ＝r σ(t) ；t＝1，2，…}
{p t |p t ＝σ(t)-σ(t-1)；t＝1，2，…}
where "r" represents a non-seasonal demand sequence. "t" represents each time point in the target time period. "d" represents a non-zero demand sequence. "p" represents a sequence of time intervals. "σ (i)" represents the time at which the "i" th non-zero demand amount is present. The value of "I" is "0" or "1", specifically "r m If "greater than" 0", then" I "takes the value of" 1", if" r "is greater than m If "equal to" 0", then" I "takes the value of" 0". "m" and "n" are positive integers.
And 403, updating the non-seasonal demand sequence according to the non-zero demand sequence and the time interval sequence to obtain an updated non-seasonal demand sequence.
In this embodiment, the use of a non-zero demand sequence and a time interval sequence may characterize the intermittent nature of the non-seasonal demand sequence, as the intermittent nature is that the demand is zero at several points in time. Therefore, after the non-zero demand sequence and the time interval sequence are obtained, the non-seasonal demand sequence is updated by the non-zero demand sequence and the time interval sequence, and the updated non-seasonal demand sequence can meet the intermittent characteristics of the target object.
In particular, various update methods may be employed to update the non-seasonal demand sequence based on a non-zero demand sequence and a time interval sequence. For example, a recurrent neural network may be used to jointly model the non-zero demand time series data and the non-zero demand time interval time series data to train the recurrent neural network to represent the correspondence between the non-zero demand sequence and the time interval sequence and the updated non-seasonal demand sequence.
For another example, for a non-zero demand in the sequence of non-zero demands, a quotient of the non-zero demand and its corresponding time interval in the sequence of time intervals may be determined, and then the non-zero demand in the sequence of non-seasonal demands may be updated to its corresponding quotient, thereby implementing the updating of the sequence of non-seasonal demands.
Step 404, updating the sequence of forecasted demand based on the sequence of seasonal demands and the updated sequence of non-seasonal demands.
In this embodiment, after the updated non-seasonal demand sequence is obtained, the obtained predicted demand sequence of the target object in the target time period may be further updated according to the seasonal demand sequence and the updated non-seasonal demand sequence, so that the updated predicted demand sequence not only can meet seasonal characteristics, but also can meet intermittent characteristics.
According to the method provided by the embodiment of the disclosure, the non-seasonal demand sequence is split into the non-zero demand sequence and the time interval sequence, and the non-zero demand sequence and the time interval sequence are used for conveniently representing the intermittent characteristics of the demand of the target object, so that the non-seasonal demand sequence can be conveniently updated according to the non-zero demand sequence and the time interval sequence, and the demand prediction efficiency is favorably improved.
With further reference to fig. 5, as an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a demand forecasting apparatus, which corresponds to the embodiment of the method shown in fig. 2, and which can be applied to various electronic devices.
As shown in fig. 5, the demand amount prediction apparatus 500 provided by the present embodiment includes an acquisition unit 501, a first update unit 502, and a second update unit 503. Wherein the obtaining unit 501 is configured to obtain a sequence of predicted demands of the target object over the target time period, wherein the sequence of predicted demands includes a seasonal demand sequence and a non-seasonal demand sequence, the seasonal demand sequence representing demands resulting from seasonal influence of the target time period; the first updating unit 502 is configured to update the sequence of non-seasonal demands, resulting in an updated sequence of non-seasonal demands, wherein the updated sequence of non-seasonal demands represents an effect of the intermittency of the demand of the target object on the sequence of non-seasonal demands; the second updating unit 503 is configured to update the sequence of predicted demand amounts based on the sequence of seasonal demand amounts and the updated sequence of non-seasonal demand amounts.
In the present embodiment, the demand amount prediction device 500: the specific processing of the obtaining unit 501, the first updating unit 502, and the second updating unit 503 and the technical effects thereof can refer to the related descriptions of step 201, step 202, and step 203 in the corresponding embodiment of fig. 2, which are not repeated herein.
In some optional implementations of the present embodiment, the first updating unit 502 is further configured to: selecting non-zero demand from the non-seasonal demand sequence to form a non-zero demand sequence, and determining a time interval between adjacent non-zero demands in the non-zero demand sequence to form a time interval sequence; and updating the non-seasonal demand sequence according to the non-zero demand sequence and the time interval sequence to obtain the updated non-seasonal demand sequence.
In some optional implementations of this embodiment, the obtaining unit 501 is further configured to: acquiring a historical demand sequence of a target object; and obtaining a prediction demand sequence by using an exponential smoothing algorithm according to the historical demand sequence.
In some optional implementations of the present embodiment, the demand prediction apparatus 500 further includes: the pre-processing unit (not shown in the figure) is configured to: preprocessing the historical demand sequence, and replacing the historical demand sequence with the obtained preprocessed historical demand, wherein the preprocessing comprises data filtering and/or data summarization.
In some optional implementations of the present embodiment, the first updating unit 502 is further configured to: for the non-zero demand in the non-zero demand sequence, determining the quotient of the non-zero demand and the time interval corresponding to the non-zero demand in the time interval sequence; the non-zero demand in the sequence of non-seasonal demands is updated to its corresponding quotient.
The apparatus provided by the above-mentioned embodiment of the present disclosure acquires, by the acquisition unit, a sequence of predicted demands of the target object over the target time period, wherein the sequence of predicted demands includes a seasonal demand sequence and a non-seasonal demand sequence, the seasonal demand sequence representing demands resulting from seasonal influence of the target time period; the first updating unit updates the non-seasonal demand sequence to obtain an updated non-seasonal demand sequence, wherein the updated non-seasonal demand sequence represents the influence of the intermittence of the demand of the target object on the non-seasonal demand sequence; the second updating unit updates the predicted demand sequence according to the seasonal demand sequence and the updated non-seasonal demand sequence, and contributes to improving the accuracy of the demand prediction result of the target object by considering the influence of seasonality, intermittency and the like on the demand of the target object.
Referring now to FIG. 6, a schematic diagram of an electronic device (e.g., the server of FIG. 1) 600 suitable for use in implementing embodiments of the present disclosure is shown. The terminal device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the use range of the embodiments of the present disclosure.
As shown in fig. 6, the electronic device 600 may include a processing means (e.g., central processing unit, graphics processor, etc.) 601 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
Generally, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While fig. 6 illustrates an electronic device 600 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may be alternatively implemented or provided. Each block shown in fig. 6 may represent one device or may represent multiple devices as desired.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 609, or may be installed from the storage means 608, or may be installed from the ROM 602. The computer program, when executed by the processing device 601, performs the above-described functions defined in the methods of embodiments of the present disclosure.
It should be noted that the computer readable medium described in the embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In embodiments of the present disclosure, however, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring a predicted demand sequence of a target object in a target time period, wherein the predicted demand sequence comprises a seasonal demand sequence and a non-seasonal demand sequence, and the seasonal demand sequence represents the demand generated by the seasonal influence of the target time period; updating the non-seasonal demand sequence to obtain an updated non-seasonal demand sequence, wherein the updated non-seasonal demand sequence represents the influence of the intermittency of the demand of the target object on the non-seasonal demand sequence; and updating the forecast demand sequence according to the seasonal demand sequence and the updated non-seasonal demand sequence.
Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present disclosure may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes an acquisition unit, a first update unit, and a second update unit. Where the names of these units do not in some cases constitute a limitation on the unit itself, for example, the second updating unit may also be described as a "unit that updates the sequence of predicted demand amounts from the sequence of seasonal demand amounts and the updated sequence of non-seasonal demand amounts".
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.
Claims (10)
1. A demand prediction method comprising:
acquiring a predicted demand sequence of a target object in a target time period, wherein the predicted demand sequence comprises a seasonal demand sequence and a non-seasonal demand sequence, and the seasonal demand sequence represents demand caused by seasonal influence of the target time period;
updating the non-seasonal demand sequence to obtain an updated non-seasonal demand sequence, wherein the updated non-seasonal demand sequence represents the influence of the intermittence of the demand of the target object on the non-seasonal demand sequence;
and updating the forecast demand sequence according to the seasonal demand sequence and the updated non-seasonal demand sequence.
2. The method of claim 1, wherein the updating the sequence of non-seasonal demands to obtain an updated sequence of non-seasonal demands comprises:
selecting non-zero demand from the non-seasonal demand sequence to form a non-zero demand sequence, and determining a time interval between adjacent non-zero demands in the non-zero demand sequence to form a time interval sequence;
and updating the non-seasonal demand sequence according to the non-zero demand sequence and the time interval sequence to obtain an updated non-seasonal demand sequence.
3. The method of claim 1, wherein the obtaining the sequence of predicted demand amounts for the target object over the target time period comprises:
acquiring a historical demand sequence of the target object;
and obtaining a prediction demand sequence by utilizing an exponential smoothing algorithm according to the historical demand sequence.
4. The method of claim 3, wherein after said obtaining the sequence of historical demand quantities for the target object, the method further comprises:
preprocessing the historical demand sequence, and replacing the historical demand sequence with the obtained preprocessed historical demand, wherein the preprocessing comprises data filtering and/or data summarization.
5. The method of claim 2, wherein the updating the sequence of non-seasonal demands based on the sequence of non-zero demands and the sequence of time intervals to obtain an updated sequence of non-seasonal demands comprises:
for a non-zero demand in the sequence of non-zero demands, determining a quotient of the non-zero demand and a time interval corresponding to the sequence of time intervals;
updating the non-zero demand in the sequence of non-seasonal demands to their corresponding quotients.
6. A demand prediction apparatus comprising:
an acquisition unit configured to acquire a sequence of predicted demands of a target object over a target time period, wherein the sequence of predicted demands includes a seasonal demand sequence and a non-seasonal demand sequence, the seasonal demand sequence representing a demand resulting from a seasonal influence of the target time period;
a first updating unit configured to update the non-seasonal demand sequence to obtain an updated non-seasonal demand sequence, wherein the updated non-seasonal demand sequence represents an effect of the intermittency of the demand of the target object on the non-seasonal demand sequence;
a second updating unit configured to update the sequence of predicted demand amounts based on the sequence of seasonal demand amounts and the updated sequence of non-seasonal demand amounts.
7. The apparatus of claim 6, wherein the first updating unit is further configured to:
selecting non-zero demand from the non-seasonal demand sequence to form a non-zero demand sequence, and determining a time interval between adjacent non-zero demands in the non-zero demand sequence to form a time interval sequence;
and updating the non-seasonal demand sequence according to the non-zero demand sequence and the time interval sequence to obtain an updated non-seasonal demand sequence.
8. The apparatus of claim 7, wherein the first updating unit is further configured to:
for a non-zero demand in the sequence of non-zero demands, determining a quotient of the non-zero demand and a time interval corresponding to the sequence of time intervals;
updating the non-zero demand in the sequence of non-seasonal demands to its corresponding quotient.
9. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon;
when executed by the one or more processors, cause the one or more processors to perform the method recited in any one of claims 1-5.
10. A computer-readable medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211117183.6A CN115375037A (en) | 2022-09-14 | 2022-09-14 | Demand prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211117183.6A CN115375037A (en) | 2022-09-14 | 2022-09-14 | Demand prediction method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115375037A true CN115375037A (en) | 2022-11-22 |
Family
ID=84070721
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211117183.6A Pending CN115375037A (en) | 2022-09-14 | 2022-09-14 | Demand prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115375037A (en) |
-
2022
- 2022-09-14 CN CN202211117183.6A patent/CN115375037A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230351323A1 (en) | Systems and methods for inventory management and optimization | |
| CN109961198B (en) | Associated information generation method and device | |
| CN110555578A (en) | sales prediction method and device | |
| CN111325587A (en) | Method and apparatus for generating information | |
| US20230011954A1 (en) | Device, method, and system for business plan management | |
| CN110766184A (en) | Order quantity prediction method and device | |
| CN110650170A (en) | Method and device for pushing information | |
| CN114663015A (en) | Replenishment method and device | |
| CN112102043B (en) | Item recommendation page generation method and device, electronic equipment and readable medium | |
| CN114049072A (en) | Index determination method and device, electronic equipment and computer readable medium | |
| CN109978421B (en) | Information output method and device | |
| CN112085442B (en) | Device operation method, apparatus, electronic device, and computer-readable medium | |
| CN113435632A (en) | Information generation method and device, electronic equipment and computer readable medium | |
| CN112308378A (en) | Scheduling device control method, scheduling device control device, electronic device and computer readable medium | |
| CN115018106A (en) | Anomaly analysis method, device, equipment and computer-readable storage medium | |
| CN111915340B (en) | Method, device, equipment and storage medium for identifying merchant type | |
| CN113780912A (en) | Method and device for determining safety stock | |
| CN110033292B (en) | Information output method and device | |
| CN116562772A (en) | Method, apparatus, device, medium and program product for generating article replenishment information | |
| CN113837694B (en) | Article display method, apparatus, electronic device, and readable medium | |
| CN112862415B (en) | Transportation vehicle scheduling method and device, electronic equipment and computer readable medium | |
| CN112287208A (en) | User portrait generation method and device, electronic equipment and storage medium | |
| CN115375037A (en) | Demand prediction method and device | |
| CN110837907A (en) | Method and device for predicting wave order quantity | |
| CN113780611A (en) | Inventory management 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 |