CN109829758A - Sales Volume of Commodity prediction technique and system towards more duration of insurances - Google Patents
Sales Volume of Commodity prediction technique and system towards more duration of insurances Download PDFInfo
- Publication number
- CN109829758A CN109829758A CN201910072180.7A CN201910072180A CN109829758A CN 109829758 A CN109829758 A CN 109829758A CN 201910072180 A CN201910072180 A CN 201910072180A CN 109829758 A CN109829758 A CN 109829758A
- Authority
- CN
- China
- Prior art keywords
- commodity
- sales volume
- sales
- information
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of Sales Volume of Commodity prediction techniques and system towards more duration of insurances, this method comprises: obtaining the order information of storage device within a preset period of time；Predicted to obtain storage device in the theoretical blanket order amount of preset time point using one-dimensional temporal model according to order information；It obtains commodity historical sales information and commodity stores information；It is trained to obtain storage device in the prediction blanket order amount of preset time point using deep neural network model according to commodity historical sales information and commodity storage information；By theoretical blanket order amount and prediction blanket order amount, merchandise sales ratio corresponding with storage unit each in storage device obtains first sales volume and second sales volume of the commodity in each storage unit respectively；Sales Volume of Commodity prediction result is obtained using machine learning integrated model according to the first sales volume and the second sales volume.The present invention has the advantage that the commodity of different duration of insurances can be directed to, the following sales volume is precisely predicted.
Description
Technical field
The present invention relates to technical field of electronic commerce, and in particular to a kind of Sales Volume of Commodity prediction technique towards more duration of insurances and
System.
Background technique
The supply system that big multi-platform electric business uses at present and is protected, inventory both for the commodity of long duration of insurance towards brachymedial
The fresh commodity industry for being easy to sell out does not have a set of fairly perfect supply guarantee system also.Wherein commodity projection algorithm is supply
The core of system, current predictive method are established mostly on simple Time series forecasting model, for example, using average, exponential smoothing or
ARIMA model etc., and when these naive models apply the effect when brachymedial is protected on commodity generally poor.
Summary of the invention
The present invention is directed at least solve one of above-mentioned technical problem.
It, can be with for this purpose, the first purpose of this invention is to propose a kind of Sales Volume of Commodity prediction technique towards more duration of insurances
For the commodity of different duration of insurances, the following sales volume is precisely predicted.
To achieve the goals above, embodiment of the invention discloses a kind of Sales Volume of Commodity prediction sides towards more duration of insurances
Method, comprising the following steps: obtain the order information of storage device within a preset period of time；It is used according to the order information one-dimensional
Temporal model is predicted to obtain the storage device in the theoretical blanket order amount of preset time point；Obtain commodity historical sales letter
Breath and commodity store information；Deep neural network mould is used according to the commodity historical sales information and commodity storage information
Type obtains the storage device in the prediction blanket order amount of the preset time point；According to the theoretical blanket order amount and described deposit
The corresponding merchandise sales ratio of each storage unit obtains first sales volume of the commodity in each storage unit, and root in storage device
Commodity are obtained according to corresponding merchandise sales ratio in the prediction blanket order amount and each storage unit of the storage device to exist
The second sales volume in each storage unit；It is obtained according to first sales volume and second sales volume using machine learning integrated model
To Sales Volume of Commodity prediction result.
Sales Volume of Commodity prediction technique according to an embodiment of the present invention towards more duration of insurances, combines one-dimensional time series forecasting mould
Type and deep neural network model, while the history feature information of different duration of insurances is added, the commodity of different duration of insurances can be established
The model of different parameters, therefore can be realized the accurate prediction to the Sales Volume of Commodity of different duration of insurances.
In addition, the Sales Volume of Commodity prediction technique according to the above embodiment of the present invention towards more duration of insurances can also have it is as follows
Additional technical characteristic:
Optionally, described according to the corresponding commodity of storage unit each in the theoretical blanket order amount and the storage device
Sale ratio obtains the first sales volume of commodity in the memory unit, specifically includes: according to the theoretical blanket order amount and described depositing
The corresponding merchandise sales ratio of each storage unit obtains first sales volume by smooth average computation in storage device.
Optionally, described that deep neural network is used according to the commodity historical sales information and commodity storage information
Model obtains the storage device in the prediction blanket order amount of the preset time point, specifically includes: by the commodity history pin
It sells information and the commodity stores and fill up, standardize to model progress outlier exclusion, missing values before information is inputted as feature
After processing, normalized, Regularization, label coding processing and one-hot coding processing, the deep neural network is inputted
Model obtains the prediction blanket order amount.
Optionally, the one-dimensional temporal model is that autoregression integrates moving average model.
Optionally, the deep neural network model is shot and long term memory network model.
Optionally, the machine learning integrated model is that gradient promotes tree-model or Xgboost model.
It, can be with for this purpose, second object of the present invention is to propose a kind of Sales Volume of Commodity forecasting system towards more duration of insurances
For the commodity of different duration of insurances, the following sales volume is precisely predicted.
To achieve the goals above, embodiment of the invention discloses a kind of, and the Sales Volume of Commodity towards more duration of insurances predicts system
System, comprising: data acquisition module, for obtaining storage device order information within a preset period of time, commodity historical sales letter
Breath and commodity store information；One-dimensional temporal model, for obtaining the storage device in preset time according to the order information
The theoretical blanket order amount of point；Deep neural network model, for being stored according to the commodity historical sales information and the commodity
Information is trained to obtain the storage device in the prediction blanket order amount of the preset time point；Method for Sales Forecast module, is used for
Commodity are obtained according to the corresponding merchandise sales ratio of storage unit each in the theoretical blanket order amount and the storage device to exist
The first sales volume in each storage unit, and according to each storage unit pair in the prediction blanket order amount and the storage device
The merchandise sales ratio answered obtains second sales volume of the commodity in each storage unit；Machine learning integrated model is used for basis
First sales volume and second sales volume obtain Sales Volume of Commodity prediction result.
Sales Volume of Commodity forecasting system according to an embodiment of the present invention towards more duration of insurances, combines one-dimensional time series forecasting mould
Type and deep neural network model, while the history feature information of different duration of insurances is added, the commodity of different duration of insurances can be established
The model of different parameters, therefore can be realized the accurate prediction to the Sales Volume of Commodity of different duration of insurances.
In addition, the Sales Volume of Commodity prediction technique according to the above embodiment of the present invention towards more duration of insurances can also have it is as follows
Additional technical characteristic:
Optionally, the Method for Sales Forecast module is single according to storage each in the theoretical blanket order amount and the storage device
The corresponding merchandise sales ratio of member obtains first sales volume by smooth average computation.
Optionally, further includes: it is preceding to model, for the commodity historical sales information and commodity storage information to be made
It is characterized input progress outlier exclusion, missing values are filled up, standardization, normalized, Regularization, label coding
After processing and one-hot coding processing, the deep neural network model being inputted, being obtained with will pass through the deep neural network model
To the prediction blanket order amount.
Optionally, the one-dimensional temporal model is that autoregression integrates moving average model.
Optionally, the deep neural network model is shot and long term memory network model.
Optionally, the machine learning integrated model is that gradient promotes tree-model or Xgboost model.
Additional aspect and advantage of the invention will be set forth in part in the description, and will partially become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
Above-mentioned and/or additional aspect of the invention and advantage will become from the description of the embodiment in conjunction with the following figures
Obviously and it is readily appreciated that, in which:
Fig. 1 is the flow chart of the Sales Volume of Commodity prediction technique towards more duration of insurances of one embodiment of the invention；
Fig. 2 is the calculation method flow chart that theoretical sales volume is calculated in one embodiment of the invention；
Fig. 3 is the schematic diagram of the database based on distributed document storage in one embodiment of the invention；
Fig. 4 is the structural block diagram of the Sales Volume of Commodity forecasting system towards more duration of insurances of one embodiment of the invention.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and for explaining only the invention, and is not considered as limiting the invention.
In the description of the present invention, it is to be understood that, term " first ", " second " are used for description purposes only, and cannot
It is interpreted as indication or suggestion relative importance.
Referring to following description and drawings, it will be clear that these and other aspects of the embodiment of the present invention.In these descriptions
In attached drawing, some particular implementations in the embodiment of the present invention are specifically disclosed, to indicate to implement implementation of the invention
Some modes of the principle of example, but it is to be understood that the scope of embodiments of the invention is not limited.On the contrary, of the invention
Embodiment includes all changes, modification and the equivalent fallen within the scope of the spirit and intension of attached claims.
The Sales Volume of Commodity prediction technique and system of the invention towards more duration of insurances is described below in conjunction with attached drawing.
Fig. 1 is the flow chart of the Sales Volume of Commodity prediction technique towards more duration of insurances of one embodiment of the invention.Such as Fig. 1 institute
Show, the Sales Volume of Commodity prediction technique towards more duration of insurances of the embodiment of the present invention, comprising the following steps:
Obtain the order information of storage device within a preset period of time.
Predicted to obtain storage device default using one-dimensional temporal model according to order information within a preset time
The theoretical blanket order amount at time point (such as in such a month, and on such a day).In one embodiment of the invention, one-dimensional temporal model is to return certainly
Return integral moving average model, i.e. Arima model.Firstly, the data to theoretical blanket order amount carry out tranquilization processing, method is
Difference is done to time series.Assuming that initial data is X=(X1,X2,X3..., Xn), then first-order difference sequence is (X1-X2,X2-
X3,X3-X4,...,Xn-1- Xn), second differnce is to do difference to first-order difference sequence, and by parity of reasoning.Second step, when checking steady
Between sequence autocorrelogram and partial autocorrelation figure, obtain suitable q (rolling average item number) and p (autoregression item).With ARIMA mould
Type removes fitting data, judges whether residual sequence is white noise sequence.Judging result indicates that residual sequence is white noise sequence, because
This ARIMA model is the model of a suitable sample, can be used for carrying out the prediction of theoretical blanket order amount.
It obtains commodity historical sales information and commodity stores information.Wherein, commodity historical sales information and commodity storage letter
Breath may include the week information of History Order amount, sales promotion information, the Weather information of history, history, can also include commodity valence
Lattice transition information, duration of insurance information.Wherein, History Order information can be the History Order information in big storehouse.One big storehouse includes more
A small storehouse, such as one big storehouse can give 100 small storehouses with distribution of goods.
It is trained and is deposited using deep neural network model according to commodity historical sales information and commodity storage information
Storage device preset time point prediction blanket order amount, i.e., using commodity historical sales information and commodity storage information as feature,
Outlier exclusion is carried out to model before input, missing values are filled up, standardization, normalized, Regularization, label volume
After code processing and one-hot coding processing, inputs and be trained to obtain prediction blanket order amount into deep neural network model.
Commodity are obtained according to the corresponding merchandise sales ratio of storage unit each in theoretical blanket order amount and storage device to exist
The first sales volume in each storage unit.In some instances, storage device is big storehouse, and storage unit is small storehouse, and big storehouse can
It, i.e., can be with according to the sale ratio of corresponding goods in the theoretical blanket order amount in big storehouse and each small storehouse to include multiple small storehouses
Obtain first sales volume of the commodity in small storehouse.In addition, according to each storage unit pair in prediction blanket order amount and storage device
The merchandise sales ratio answered obtains second sales volume of the commodity in each storage unit.Wherein it is possible to according to theoretical blanket order amount
Merchandise sales ratio corresponding with storage unit each in storage device is by smooth average computation or passes through other computation models
The first sales volume is calculated.It is logical according to the corresponding merchandise sales ratio of storage unit each in prediction blanket order amount and storage device
It crosses smooth average computation and obtains second sales volume of the commodity in each storage unit.
Sales Volume of Commodity prediction result is obtained using machine learning integrated model according to the first sales volume and the second sales volume.Wherein,
Machine learning integrated model is gradient boosted tree GBDT model or Xgboost model.Made according to the first sales volume and the second sales volume
Method for Sales Forecast, which is carried out, with GBDT or Xgboost model exports final Sales Volume of Commodity prediction result.
Sales Volume of Commodity prediction technique according to an embodiment of the present invention towards more duration of insurances, combines one-dimensional time series forecasting mould
Type and deep neural network model, while the history feature information of different duration of insurances is added, the commodity of different duration of insurances can be established
The model of different parameters, therefore can be realized the accurate prediction to the Sales Volume of Commodity of different duration of insurances.
Fig. 2 is to calculate the calculation method flow chart of theoretical sales volume in one embodiment of the present of invention.Brachymedial phase shelf-life quotient
Product inventory's phase long quality guarantee period commodity are more prone to produce report damage, and selling out probability also if therefore reducing turnover will increase.By right
The calculating of History Order information theory sales volume is most probable when can not sold out with simulating the same day to estimate sales volume value, after being
Continuous model training is utilized.
Fig. 3 is the schematic diagram of the database based on distributed document storage in one embodiment of the invention.As shown in figure 3,
History Order/sales volume letter of commodity is obtained from MySQL (Relational DBMS) and Hive (Tool for Data Warehouse)
Breath and other characteristic informations carry out entering Method for Sales Forecast link after ETL (data warehouse technology) cleaning.To commodity projection
The mode of sales volume are as follows: carry out the rule-based filtering (such as lipuid goods rule etc.) of part first, and multiply related coefficient and (such as promote
Coefficient and the number of days that replenishes etc.) application amount of the commodity in micro- storehouse is obtained, these rules or coefficient need related operation personnel pre-
First set in system MySQL database.The small storehouse commodity Ying Youliang being calculated is subtracted into showing for small storehouse commodity
It (is obtained from the databases such as MongoDB) in stock, then judges whether calculated value is more than to preset to replenish the upper limit of the number (according to micro-
Holding capacity of bin is set by staff), overage is cast out, finally carries out pushing away list by the replenishment quantity result of acquisition.
Fig. 4 is the structural block diagram of the Sales Volume of Commodity forecasting system towards more duration of insurances of one embodiment of the invention.Such as Fig. 4 institute
Show, the Sales Volume of Commodity forecasting system towards more duration of insurances of the embodiment of the present invention, including data acquisition module, one-dimensional temporal model,
Deep neural network model, Method for Sales Forecast module and machine learning integrated model.
Wherein, data acquisition module is used to obtain storage device order information within a preset period of time, commodity history pin
Sell information and commodity storage information.One-dimensional temporal model is used to obtain storage device in the reason of preset time point according to order information
By blanket order amount.Deep neural network model is used to be trained to obtain according to commodity historical sales information and commodity storage information
Prediction blanket order amount of the storage device in preset time point.Method for Sales Forecast module is used for according to theoretical blanket order amount and storage device
In the corresponding merchandise sales ratio of each storage unit obtain first sales volume of the commodity in each storage unit, and according to prediction
The corresponding merchandise sales ratio of each storage unit obtains commodity in each storage unit in blanket order amount and storage device
Second sales volume.Machine learning integrated model is used to obtain Sales Volume of Commodity prediction result according to the first sales volume and the second sales volume.
Sales Volume of Commodity forecasting system according to an embodiment of the present invention towards more duration of insurances, combines one-dimensional time series forecasting mould
Type and deep neural network model, while the history feature information of different duration of insurances is added, the commodity of different duration of insurances can be established
The model of different parameters, therefore can be realized the accurate prediction to the Sales Volume of Commodity of different duration of insurances.
In one embodiment of the invention, Method for Sales Forecast module is each deposited according in theoretical blanket order amount and storage device
The corresponding merchandise sales ratio of storage unit obtains the first sales volume by smooth average computation.
In one embodiment of the invention, preceding that model is used for commodity historical sales information to model before further including
It is filled up with commodity storage information as feature input progress outlier exclusion, missing values, standardization, normalized, just
After then changing processing, label coding processing and one-hot coding processing, deep neural network model is inputted, will pass through depth nerve net
Network model obtains prediction blanket order amount.
In one embodiment of the invention, one-dimensional temporal model is that autoregression integrates moving average model.
In one embodiment of the invention, deep neural network model is shot and long term memory network model.
In one embodiment of the invention, machine learning integrated model is that gradient promotes tree-model or Xgboost model.
It should be noted that the specific embodiment of the Sales Volume of Commodity forecasting system towards more duration of insurances of the embodiment of the present invention
It is similar with the specific embodiment of Sales Volume of Commodity prediction technique towards more duration of insurances of the embodiment of the present invention, referring specifically to towards more
The description of the Sales Volume of Commodity prediction technique part of duration of insurance does not repeat them here to reduce redundancy.
In addition, the Sales Volume of Commodity forecasting system towards more duration of insurances of the embodiment of the present invention other compositions and effect for
All be for those skilled in the art it is known, in order to reduce redundancy, do not repeat them here.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
One or more embodiment or examples in can be combined in any suitable manner.
Although an embodiment of the present invention has been shown and described, it will be understood by those skilled in the art that: not
A variety of change, modification, replacement and modification can be carried out to these embodiments in the case where being detached from the principle of the present invention and objective, this
The range of invention is by claim and its equivalent limits.
Claims (10)
1. a kind of Sales Volume of Commodity prediction technique towards more duration of insurances, which comprises the following steps:
Obtain the order information of storage device within a preset period of time；
Predicted to obtain the storage device in the reason of preset time point using one-dimensional temporal model according to the order information
By blanket order amount；
It obtains commodity historical sales information and commodity stores information；
Described deposit is obtained using deep neural network model according to the commodity historical sales information and commodity storage information
Prediction blanket order amount of the storage device in the preset time point；
Quotient is obtained according to the corresponding merchandise sales ratio of storage unit each in the theoretical blanket order amount and the storage device
First sales volume of the product in each storage unit, and according to each storage list of prediction the blanket order amount and the storage device
Corresponding merchandise sales ratio obtains second sales volume of the commodity in each storage unit in member；
Sales Volume of Commodity prediction result is obtained using machine learning integrated model according to first sales volume and second sales volume.
2. the Sales Volume of Commodity prediction technique according to claim 1 towards more duration of insurances, which is characterized in that described according to
The corresponding merchandise sales ratio of each storage unit obtains commodity in storage unit in theoretical blanket order amount and the storage device
In the first sales volume, specifically include:
Passed through according to the corresponding merchandise sales ratio of storage unit each in the theoretical blanket order amount and the storage device flat
Sliding average computation obtains first sales volume.
3. the Sales Volume of Commodity prediction technique according to claim 1 towards more duration of insurances, which is characterized in that described according to
Commodity historical sales information and the commodity store information and obtain the storage device described using deep neural network model
The prediction blanket order amount of preset time point, specifically includes:
The commodity historical sales information and commodity storage information is preceding to model progress exceptional value row as feature input
Remove, missing values are filled up, standardization, normalized, Regularization, label coding processing and one-hot coding processing after,
It inputs the deep neural network model and obtains the prediction blanket order amount.
4. the Sales Volume of Commodity prediction technique according to claim 1 towards more duration of insurances, which is characterized in that the one-dimensional timing
Model is that autoregression integrates moving average model.
5. the Sales Volume of Commodity prediction technique according to claim 1 towards more duration of insurances, which is characterized in that the machine learning
Integrated model is that gradient promotes tree-model or Xgboost model.
6. a kind of Sales Volume of Commodity forecasting system towards more duration of insurances characterized by comprising
Data acquisition module, for obtain storage device order information within a preset period of time, commodity historical sales information and
Commodity store information；
One-dimensional temporal model, for obtaining the storage device in the theoretical blanket order of preset time point according to the order information
Amount；
Deep neural network model, for being trained according to the commodity historical sales information and commodity storage information
To the storage device the preset time point prediction blanket order amount；
Method for Sales Forecast module, for according to the corresponding quotient of storage unit each in the theoretical blanket order amount and the storage device
Product sale ratio obtains first sales volume of the commodity in each storage unit, and according to the prediction blanket order amount and the storage
The corresponding merchandise sales ratio of each storage unit obtains second sales volume of the commodity in each storage unit in device；
Machine learning integrated model, for obtaining Sales Volume of Commodity prediction result according to first sales volume and second sales volume.
7. the Sales Volume of Commodity forecasting system according to claim 6 towards more duration of insurances, which is characterized in that the Method for Sales Forecast
Module passes through flat according to the corresponding merchandise sales ratio of storage unit each in the theoretical blanket order amount and the storage device
Sliding average computation obtains first sales volume.
8. the Sales Volume of Commodity forecasting system according to claim 6 towards more duration of insurances, which is characterized in that further include:
It is preceding to model, for carrying out exception using the commodity historical sales information and commodity storage information as feature input
Value excludes, missing values are filled up, standardization, normalized, Regularization, label coding handles and one-hot coding processing
Afterwards, the deep neural network model is inputted, obtains the prediction blanket order amount will pass through the deep neural network model.
9. the Sales Volume of Commodity forecasting system according to claim 6 towards more duration of insurances, which is characterized in that the one-dimensional timing
Model is that autoregression integrates moving average model.
10. the Sales Volume of Commodity forecasting system according to claim 6 towards more duration of insurances, which is characterized in that the engineering
Practising integrated model is that gradient promotes tree-model or Xgboost model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910072180.7A CN109829758A (en) | 2019-01-25 | 2019-01-25 | Sales Volume of Commodity prediction technique and system towards more duration of insurances |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910072180.7A CN109829758A (en) | 2019-01-25 | 2019-01-25 | Sales Volume of Commodity prediction technique and system towards more duration of insurances |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109829758A true CN109829758A (en) | 2019-05-31 |
Family
ID=66862520
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910072180.7A Pending CN109829758A (en) | 2019-01-25 | 2019-01-25 | Sales Volume of Commodity prediction technique and system towards more duration of insurances |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109829758A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111062669A (en) * | 2019-12-20 | 2020-04-24 | 北京每日优鲜电子商务有限公司 | Service processing method, device, storage medium and server |
| CN112308351A (en) * | 2019-07-26 | 2021-02-02 | 上海漕泾热电有限责任公司 | Heat supply balance prediction system and method for cogeneration power plant |
| CN112488600A (en) * | 2019-09-11 | 2021-03-12 | 英业达科技有限公司 | Order prediction method |
| CN113095745A (en) * | 2020-01-09 | 2021-07-09 | 北京沃东天骏信息技术有限公司 | Replenishment decision model training and replenishment decision method, system, equipment and medium |
| CN114723474A (en) * | 2022-02-21 | 2022-07-08 | 浪潮卓数大数据产业发展有限公司 | Method and system for calculating sales volume based on E-commerce commodity inventory |
| CN115034523A (en) * | 2022-08-10 | 2022-09-09 | 深圳市感恩网络科技有限公司 | Enterprise ERP integrated management system and method based on big data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102385724A (en) * | 2010-08-27 | 2012-03-21 | 上海财经大学 | Spare part assembling demand forecasting information processing method applied to inventory management |
| CN106204086A (en) * | 2015-05-06 | 2016-12-07 | 阿里巴巴集团控股有限公司 | The method for early warning of Sales Volume of Commodity and device |
| CN107038190A (en) * | 2016-10-28 | 2017-08-11 | 厦门大学 | A kind of intelligent promotion plan modeling method applied to Taobao |
| CN109214601A (en) * | 2018-10-31 | 2019-01-15 | 四川长虹电器股份有限公司 | Household electric appliances big data Method for Sales Forecast method |
-
2019
- 2019-01-25 CN CN201910072180.7A patent/CN109829758A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102385724A (en) * | 2010-08-27 | 2012-03-21 | 上海财经大学 | Spare part assembling demand forecasting information processing method applied to inventory management |
| CN106204086A (en) * | 2015-05-06 | 2016-12-07 | 阿里巴巴集团控股有限公司 | The method for early warning of Sales Volume of Commodity and device |
| CN107038190A (en) * | 2016-10-28 | 2017-08-11 | 厦门大学 | A kind of intelligent promotion plan modeling method applied to Taobao |
| CN109214601A (en) * | 2018-10-31 | 2019-01-15 | 四川长虹电器股份有限公司 | Household electric appliances big data Method for Sales Forecast method |
Non-Patent Citations (2)
| Title |
|---|
| 彭喜元 彭宇 刘大同著: "《数据驱动的故障预测》", 31 March 2016 * |
| 黄培根: "连锁超市保质期商品配货模型集应用", 《吉首大学学报（自然科学版）》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112308351A (en) * | 2019-07-26 | 2021-02-02 | 上海漕泾热电有限责任公司 | Heat supply balance prediction system and method for cogeneration power plant |
| CN112308351B (en) * | 2019-07-26 | 2022-09-09 | 上海漕泾热电有限责任公司 | Heat supply balance prediction system and method for cogeneration power plant |
| CN112488600A (en) * | 2019-09-11 | 2021-03-12 | 英业达科技有限公司 | Order prediction method |
| CN111062669A (en) * | 2019-12-20 | 2020-04-24 | 北京每日优鲜电子商务有限公司 | Service processing method, device, storage medium and server |
| CN113095745A (en) * | 2020-01-09 | 2021-07-09 | 北京沃东天骏信息技术有限公司 | Replenishment decision model training and replenishment decision method, system, equipment and medium |
| CN114723474A (en) * | 2022-02-21 | 2022-07-08 | 浪潮卓数大数据产业发展有限公司 | Method and system for calculating sales volume based on E-commerce commodity inventory |
| CN115034523A (en) * | 2022-08-10 | 2022-09-09 | 深圳市感恩网络科技有限公司 | Enterprise ERP integrated management system and method based on big data |
| CN115034523B (en) * | 2022-08-10 | 2022-11-01 | 深圳市感恩网络科技有限公司 | Enterprise ERP (enterprise resource planning) comprehensive management system and method based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109829758A (en) | Sales Volume of Commodity prediction technique and system towards more duration of insurances | |
| Abolghasemi et al. | Demand forecasting in supply chain: The impact of demand volatility in the presence of promotion | |
| CN109740793B (en) | Inventory optimization method based on probability demand distribution | |
| Xia et al. | A seasonal discrete grey forecasting model for fashion retailing | |
| Chen et al. | Production scheduling and vehicle routing with time windows for perishable food products | |
| WO2019001120A1 (en) | Method and system for processing dynamic pricing data of commodity | |
| CN111340421A (en) | Purchasing method | |
| US20030126103A1 (en) | Agent using detailed predictive model | |
| Vahdani et al. | A hybrid multi-stage predictive model for supply chain network collapse recovery analysis: a practical framework for effective supply chain network continuity management | |
| CN106991548A (en) | A kind of warehouse goods yard planing method, device and electronic installation | |
| CN109493151A (en) | Method for Sales Forecast method and system | |
| US20080177599A1 (en) | Method Of Determining Safety Stock Levels | |
| CN113487359B (en) | Commodity sales predicting method and device based on multi-mode characteristics and related equipment | |
| Leung et al. | Prediction of B2C e-commerce order arrival using hybrid autoregressive-adaptive neuro-fuzzy inference system (AR-ANFIS) for managing fluctuation of throughput in e-fulfilment centres | |
| CN110751524A (en) | Intelligent coupon dispatching method based on reinforcement learning | |
| CN115689451A (en) | Method, device, terminal and medium for determining replenishment quantity of off-line retail store | |
| CN113656691A (en) | Data prediction method, device and storage medium | |
| CN114239989A (en) | Method, system, equipment and storage medium for calculating material demand plan | |
| CN113657667A (en) | Data processing method, device, equipment and storage medium | |
| CN112712251B (en) | Ship intelligent scheduling method applied to barge management system | |
| CN114881694A (en) | Automatic replenishment method, system, electronic device, storage medium, and program product | |
| Baniwal et al. | An imitation learning approach for computing anticipatory picking decisions in retail distribution centres | |
| JP2001243401A (en) | Order receipt prediction system | |
| Hui et al. | A fuzzy association Rule Mining framework for variables selection concerning the storage time of packaged food | |
| US20030204468A1 (en) | Stock planning method |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190531 |
|
| RJ01 | Rejection of invention patent application after publication |