CN110210907A - A kind of data analysis replenishment system of automatic vending - Google Patents
A kind of data analysis replenishment system of automatic vending Download PDFInfo
- Publication number
- CN110210907A CN110210907A CN201910497088.5A CN201910497088A CN110210907A CN 110210907 A CN110210907 A CN 110210907A CN 201910497088 A CN201910497088 A CN 201910497088A CN 110210907 A CN110210907 A CN 110210907A
- Authority
- CN
- China
- Prior art keywords
- sales
- vending machine
- article
- vending
- cycle
- 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
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
Abstract
A kind of data analysis replenishment system of automatic vending, is made of memory, arithmetic element and display；So that Vending Machine solves Vending Machine in different location, Various Seasonal, the article demand of different time and reasonable replenishment quantity according to the replenishment need of the analyses and each article of automatic Prediction such as the machine sales figure, single machine article inventory record；The introducing of the vending machine profitable assessment models of deep neural network, by reasonable input feature value, make its to the Weather information outside historic sales data and inventory data also can fine comprehensive assessment, solve the problems, such as part objects Dependent Demand weather condition；The machine themselves capture storing data is all made of to the prediction of the profitable of each article of vending machine simultaneously, is not required to set up unified central service and communicate with, so that the limitation of Vending Machine installation and deployment is less, have bigger survival ability.
Description
Technical field
A kind of information analysis field of the present invention, and in particular to data analysis replenishment system of automatic vending.
Background technique
In daily life, the Shopping Behaviors of people are not occurring all the time, are convenience-for-people and save the cost, improve efficiency,
Take up an area it is smaller, come into being without the Vending Machine of shop assistant.The article demand of different location Various Seasonal different time is not
Equally, i.e. the replenishment quantity of article is different, it is more it is less there is drawback, influence Vending Machine profitability；Reasonably replenish
Amount needs exceptionally experienced staff that could complete, and there are biggish human factor errors；I.e. demand largely has
The staff of corresponding experience and knowledge, considerably increases the utilization cost of Vending Machine；Secondly, difference sells article by it
His influence of factor such as synoptic climate is not also identical, and the difficulty of artificial reasonable prediction further increases, and does not have portability,
Reduce Vending Machine expansion force.
Summary of the invention
The purpose of the present invention is to provide a kind of data of automatic vending to analyze replenishment system, by only selling to the machine history
The analysis of data is sold, realizes and reasonable, Accurate Prediction is carried out to replenishment quantity；And pass through the rational design of input feature value, metering
Weather conditions respectively sell Vending Machine the influence of article.
The object of the invention is realized by following technical solution:
A kind of data analysis replenishment system of automatic vending, is made of memory, arithmetic element and display；
The memory storage vending machine sales figure and single machine article inventory record；
The sales figure includes on-sale date, sells listing details list；
It is described sell listing details list include goods categories, item price and article metering；
The single machine article inventory record saves vending machine and sells article different moments quantity in stock；
The arithmetic element obtains vending machine sales figure in memory, and single machine article inventory record calculates next sell
Replenishment quantity needed for period each article；
The display show single machine article inventory record and it is next sell period each article needed for replenishment quantity；
It is described it is next sell the period be next twenty four hours in；
The arithmetic element calculates next replenishment quantity needed for selling period each article, and specific step is as follows:
S001, classification classify to vending machine sales figure according to type of goods；
S002, merging, the vending machine sales figure to having classified, are subject to current time, are unit according to the period is sold
Merge each article of vending machine and respectively sells cyclical sales record；
S003, replenishment quantity predictor formula calculate that article is next sells replenishment quantity needed for the period；
The replenishment quantity predictor formula is as follows:
In formula,It is subject to the sales volume for selling period article for i-th of article of jth class at current time, sjFor jth class object
The quantity in stock at product current time, r > 0 are the factor that replenishes, and are suitable for articles-selling amount and there is fluctuation,It is under jth class article one
A period forecasting sales volume, i.e. vending machine sales figure are to vending machine profitable assessed value, djFor the next all arteries and veins of jth class article
Replenishment quantity needed for period；
More preferably, a kind of data of automatic vending analyze replenishment system, and the factor that replenishes is related to type of goods, perishable easy
Rotten article, r=0.2, shelf-life longer articles r=0.4.
More preferably, a kind of data of automatic vending analyze replenishment system, are sold using vending machine sales figure to vending machine
The sales figure of force estimation, different sales cycles influences difference to vending machine sales force, is characterized using multinomial:
In formula, for jth class article,For next sales cycle Scheduled sales quantity, i.e. vending machine profitable；For with next
A sales cycle is the sales figure of i-th of sales cycle of starting；For the impact factor to vending machine sales force；It is described
Impact factorIt is obtained for vending machine sales figure optimization.
More preferably, a kind of data of automatic vending analyze replenishment system, are sold using vending machine sales figure to vending machine
Force estimation, be not sales cycle sales figure vending machine sales force is influenced it is different, in closer sales cycle time
Sales volume influence is bigger, is characterized as below using multinomial:
In formula, e-i·λ·tIntroduce time factor, the sales volume for characterizing in closer sales cycle time influence it is bigger,
T is sales cycle duration, and λ is sales cycle duration zoom factor, is changed over time for adjusting different sales cycles to sale
The change rate that machine sales force influences, value range meet λ > 0, the impact factorFor vending machine sales figure optimization
Solution obtains.
More preferably, a kind of data of automatic vending analyze replenishment system, and sales cycle duration zoom factor λ=1.5 make
The influence that the sales figure of the time longer sales cycle of prediction sales cycle must be separated by becomes smaller.
More preferably, a kind of data of automatic vending analyze replenishment system, are sold using vending machine sales figure to vending machine
Force estimation considers that weather, temperature etc. have a certain impact to items for merchandising tool, increases weather data unit, and networking is completed current
Climatic data record and the climatic prediction data record of next sales cycle in sales cycle, vending machine is sold and is remembered
Record, single machine article inventory record and corresponding climatic data record, climatic prediction data record input vending machine sell force estimation
Model obtains predicted value；
The climatic data record includes be averaged in the vending machine location present sales period outdoor temperature, Average indoor temperature
Degree, weather digital label；
The climatic prediction data record includes be averaged vending machine location next sales cycle outdoor temperature, average room
Interior temperature, weather digital label；
The weather digital label carries out unified calibration according to 0,1,2 ... for for example fine, the negative, rain by weather classification；
The vending machine profitable assessment models, input by vending machine sales figure and corresponding climatic data record,
Climatic prediction data record composition, inputs as follows:
Indicate the input of jth class articles-selling machine profitable assessment models, wherein viIndicate the i-th of range prediction sales cycle
The sales figure of a sales cycle, piFor growth ratesiFor growth rate piGrowing direction,ti,mi,liThe Average indoor temperature of respectively i-th sales cycle, average outdoor temperature and day destiny
Word label,Respectively i-th of sales cycle is to the Average indoor temperature of i-1 sales cycle, averagely outdoor temp
The predicted value of degree and weather digital label；The input of vending machine profitable assessment models introduces time variable and weather correlation ginseng
Number such as Average indoor temperature, average outdoor temperature and weather, so that vending machine profitable assessment models fully take into account weather
Etc. influence of the factors to commercial articles vending power；
The vending machine profitable assessment models are deep neural network model, by full link module and 5 convolution modules
Serial link exports feature vector, then links two full linking layers respectively as output；
The full link module is made of full linking layer and reshape layers；
The convolution module can be made of convolutional layer, BN layers and activation primitive；
The assorted linking two full linking layers link full linking layer 1 as output, specially feature vector, export two
Value, as v0Relative to v1Growing directionClassification prediction result, feature vector links full linking layer 2, exports 1
Value, as v0Relative to v1The sizes values of growthEstimation；
The vending machine sales figure is to vending machine profitable assessed value are as follows:
The vending machine profitable assessment models parameter is that training is completed under line.
The invention has the following beneficial effects:
The present invention provides a kind of data of automatic vending to analyze replenishment system, according to the machine sales figure, single machine article
The replenishment need of the analyses such as inventory record and each article of automatic Prediction, solve Vending Machine different location, Various Seasonal,
The problem of article demand of different time and reasonable replenishment quantity, substitution have the employee work of professional standing and experience, greatly save
Human cost；
The present invention sells force estimation mould using the vending machine of deep neural network to the sale force estimation of automatic vending article
Type makes it also can be comprehensive very well to the Weather information outside historic sales data and inventory data by reasonable input feature value
Assessment is closed, solves the problems, such as part objects Dependent Demand weather condition；
The present invention is all made of the machine themselves capture storing data to the prediction of the profitable of each article of vending machine, is not required to set up
Unified central service simultaneously communicates with, so that the limitation of Vending Machine installation and deployment is less, has bigger survival ability.
Detailed description of the invention
A kind of Fig. 1: vending machine profitable assessment models structural schematic diagram.
The full link module structural schematic diagram of Fig. 2: vending machine profitable assessment models.
The convolution module structural schematic diagram of Fig. 3: vending machine profitable assessment models.
Specific embodiment
The present invention is specifically described below by embodiment, it is necessary to which indicated herein is that following embodiment is only used
In invention is further explained, it should not be understood as limiting the scope of the invention, person skilled in art can
To make some nonessential modifications and adaptations to the present invention according to aforementioned present invention content.
Embodiment 1
A kind of data analysis replenishment system of automatic vending, is made of memory, arithmetic element and display；
Wherein memory storage vending machine sales figure and single machine article inventory record, including on-sale date, sell article
Detail list；Selling listing details list includes goods categories, item price and article metering；
Single machine article inventory record saves vending machine and sells article different moments quantity in stock, occurs when selling article inventory amount
Single machine article inventory record is updated when variation, i.e., with vending machine sales figure synchronized update simultaneously；
Arithmetic element obtains vending machine sales figure in memory, and the record calculating of single machine article inventory is next to sell the period
Replenishment quantity needed for each article；
Display show single machine article inventory record and it is next sell period each article needed for replenishment quantity；
It is above-mentioned it is next sell the period be next twenty four hours in；
Vending machine sales figure and single machine article inventory record in memory are obtained for arithmetic element and calculate next sell
Replenishment quantity needed for selling period each article carries out as follows:
S001, classification classify to vending machine sales figure according to type of goods；
S002, merging, the vending machine sales figure to having classified, are subject to current time, are unit according to the period is sold
Merge each article of vending machine and respectively sells cyclical sales record；
S003, replenishment quantity predictor formula calculate that article is next sells replenishment quantity needed for the period；
The replenishment quantity predictor formula is as follows:
In formula,It is subject to the sales volume for selling period article for i-th of article of jth class at current time, sjFor jth class object
The quantity in stock at product current time, r > 0 are the factor that replenishes, and are suitable for articles-selling amount and there is fluctuation,It is under jth class article one
A period forecasting sales volume, i.e. vending machine sales figure are to vending machine profitable assessed value, djFor the next all arteries and veins of jth class article
Replenishment quantity needed for period, while introducing time factor e-i·λ·t, for characterizing the sales volume shadow in closer sales cycle time
Sound is bigger, and t is sales cycle duration, and λ is sales cycle duration zoom factor, changes over time for adjusting different sales cycles
On the change rate that machine for selling sales force influences, value range meets λ > 0,For the impact factor to vending machine sales force,
The sales figure of different sales cycles influences different, the impact factor on vending machine sales forceFor vending machine sales figure
Optimization obtains；
The factor that wherein replenishes r is related to type of goods, for perishable perishable, r=0.2, shelf-life longer articles r=
0.4；
Sales cycle duration zoom factor λ=1.5, so that be separated by the time longer sales cycle of prediction sales cycle
The influence of sales figure becomes smaller.
Embodiment 2
A kind of data analysis replenishment system of automatic vending, sells force estimation to vending machine using vending machine sales figure,
Consider that weather, temperature etc. have a certain impact to items for merchandising tool, increase weather data unit, the present sales period is completed in networking
Interior climatic data record and the climatic prediction data record of next sales cycle, by vending machine sales figure, single machine object
Product inventory record and corresponding climatic data record, climatic prediction data record input vending machine profitable assessment models, obtain
Predicted value；
Climatic data record includes be averaged in the vending machine location present sales period outdoor temperature, Average indoor temperature, day
Gas digital label；
Climatic prediction data record includes be averaged vending machine location next sales cycle outdoor temperature, Average indoor temperature
Degree, weather digital label；
Weather digital label carries out unified calibration according to 0,1,2 ... for for example fine, the negative, rain by weather classification；
Vending machine profitable assessment models, input is by vending machine sales figure and corresponding climatic data record, weather
Prediction data record composition, inputs as follows:
Indicate the input of jth class articles-selling machine profitable assessment models, wherein viIndicate the i-th of range prediction sales cycle
The sales figure of a sales cycle, piFor growth ratesiFor growth rate piGrowing direction,ti,mi,liThe Average indoor temperature of respectively i-th sales cycle, average outdoor temperature and day destiny
Word label,Respectively i-th of sales cycle is to the Average indoor temperature of i-1 sales cycle, averagely outdoor temp
The predicted value of degree and weather digital label；The input of vending machine profitable assessment models introduces time variable and weather correlation ginseng
Number such as Average indoor temperature, average outdoor temperature and weather, so that vending machine profitable assessment models fully take into account weather
Etc. influence of the factors to commercial articles vending power；
Above-mentioned vending machine profitable assessment models are deep neural network model, as shown in Figure 1 by full link module and 5
Convolution module serial link exports feature vector, then links two full linking layers respectively as output；Network model first uses entirely
Link model carries out linear combination to input data, fully considers the form of mode input data,
To meet the requirement of network subsequent input as shown in Fig. 2, link module is by full linking layer and reshape layers of group entirely
At；
Convolution module as shown in Figure 3 is made of convolutional layer, BN layers and activation primitive；
The assorted linking two full linking layers link full linking layer 1 as output, specially feature vector, export two
Value, as v0Relative to v1Growing directionClassification prediction result, feature vector links full linking layer 2, exports 1
Value, as v0Relative to v1The sizes values of growthEstimation；
The vending machine sales figure is to vending machine profitable assessed value are as follows:
The vending machine profitable assessment models parameter is that training is completed under line.
Embodiment 3
A kind of vending machine profitable assessment models training method of the data analysis replenishment system of automatic vending, including input
Sample generating method and model parameter update method；
The input of vending machine profitable assessment models is by vending machine sales figure, single machine article inventory record, climatic data
Parameter generates in record and climatic prediction data record；Specifically it is made of input feature vector and label；
Input feature value:
The corresponding label of above-mentioned input feature value are as follows:
For vending machine profitable assessment models as shown in Figure 1 by full link module and 5 convolution module serial links, output is special
Vector is levied, then links two full linking layers respectively as output；
To meet the requirement of network subsequent input as shown in Fig. 2, link module is by full linking layer and reshape layers of group entirely
At；
Convolution module as shown in Figure 3 is made of convolutional layer, BN layers and activation primitive；
Assorted linking two full linking layers link full linking layer 1 as output, specially feature vector, export two values,
And two values and label s will be exportedkInput softmax loss function calculates Classification Loss value loss togethersoftmax；Feature vector
Full linking layer 2 is linked, a value is exported, with label pkInput mean square error loss function, which calculates, together returns penalty values
lossMSE；
Total loss function value are as follows:
Loss=(lossMSE+losssoftmax)·0.5
In vending machine profitable assessment models parameter renewal process, input feature value and its corresponding label are inputted
Model, feature vector of the input feature value Jing Guo full link module sequentially input again 5 convolution modules obtain convolution feature to
Amount；
Convolution feature vector passes through full linking layer 1, two values is exported, with label skSoftmax loss function is inputted together
Calculate Classification Loss value losssoftmax；
Convolution property vector passes through full linking layer 2, a value is exported, with label pkMean square error loss function is inputted together
It calculates and returns penalty values lossMSE；
Calculate total loss function value are as follows:
Loss=(lossMSE+losssoftmax)·0.5
Vending machine profitable assessment models according to total reversed gradient transmitting of loss function value and update mould according to gradient value
Shape parameter；
Appeal model parameter renewal process is repeated, until model training is completed.
Claims (6)
1. a kind of data of automatic vending analyze replenishment system, it is made of memory, arithmetic element and display；
The memory storage vending machine sales figure and single machine article inventory record；
The sales figure includes on-sale date, sells listing details list；
It is described sell listing details list include goods categories, item price and article metering；
The single machine article inventory record saves vending machine and sells article different moments quantity in stock；
The arithmetic element obtains vending machine sales figure in memory, and the record calculating of single machine article inventory is next to sell the period
Replenishment quantity needed for each article；
The display show single machine article inventory record and it is next sell period each article needed for replenishment quantity；
It is described it is next sell the period be next twenty four hours in；
The arithmetic element calculates next replenishment quantity needed for selling period each article, and specific step is as follows:
S001, classification classify to vending machine sales figure according to type of goods；
S002, merging, the vending machine sales figure to having classified, are subject to current time, merge according to the period is sold for unit
Each article of vending machine respectively sells cyclical sales record；
S003, replenishment quantity predictor formula calculate that article is next sells replenishment quantity needed for the period；
The replenishment quantity predictor formula is as follows:
In formula,It is subject to the sales volume for selling period article for i-th of article of jth class at current time, sjWork as jth class article
The quantity in stock at preceding moment, r > 0 are the factor that replenishes, and are suitable for articles-selling amount and there is fluctuation,For jth class article next week
Phase predicts sales volume, i.e., vending machine sales figure is to vending machine profitable assessed value, djFor jth class article next all arteries and veins periods
Required replenishment quantity.
2. a kind of data of automatic vending analyze replenishment system as described in claim 1, it is characterised in that: it is described replenish the factor with
Type of goods is related, perishable perishable, r=0.2, shelf-life longer articles r=0.4.
3. a kind of data of automatic vending analyze replenishment system as claimed in claim 2, it is characterised in that: the vending machine sale
Record sells force estimation to vending machine, and the sales figure of different sales cycles influences difference to vending machine sales force, using more
Item formula is characterized:
In formula, for jth class article,For next sales cycle Scheduled sales quantity, i.e. vending machine profitable；For with next pin
Sell the sales figure for i-th of sales cycle that the period is starting；For the impact factor to vending machine sales force；The influence
The factorIt is obtained for vending machine sales figure optimization.
4. a kind of data of automatic vending analyze replenishment system as claimed in claim 2, it is characterised in that: the vending machine sale
Record sells force estimation to vending machine, is not that the sales figure of sales cycle influences difference to vending machine sales force, the time gets over
Sales volume influence in close sales cycle is bigger, is characterized as below using multinomial:
In formula, e-i·λ·tTime factor is introduced, the sales volume for characterizing in closer sales cycle time influences bigger, and t is pin
Cycle duration is sold, λ is sales cycle duration zoom factor, is changed over time for adjusting different sales cycles to machine for selling sale
The change rate of capacity, value range meet λ > 0, the impact factorIt is obtained for vending machine sales figure optimization
It arrives.
5. a kind of data of automatic vending analyze replenishment system as claimed in claim 4, it is characterised in that: when the sales cycle
Long zoom factor λ=1.5, so that the influence for being separated by the sales figure of the time longer sales cycle of prediction sales cycle becomes
It is small.
6. a kind of data of automatic vending analyze replenishment system as claimed in claim 2, it is characterised in that: the vending machine sale
Record to vending machine sell force estimation, increase weather data unit, networking complete sales cycle in climatic data record and
The climatic prediction data record of next sales cycle；
Vending machine sales figure, single machine article inventory record and corresponding climatic data record, climatic prediction data record is defeated
Enter vending machine profitable assessment models, obtains predicted value；
The climatic data record includes be averaged in the vending machine location present sales period outdoor temperature, Average indoor temperature, day
Gas digital label；
The climatic prediction data record includes be averaged vending machine location next sales cycle outdoor temperature, Average indoor temperature
Degree, weather digital label；
The weather digital label carries out unified calibration according to 0,1,2 ... for for example fine, the negative, rain by weather classification；
The vending machine profitable assessment models, input is by vending machine sales figure and corresponding climatic data record, weather
Prediction data record composition, inputs as follows:
Indicate the input of jth class articles-selling machine profitable assessment models, wherein viIndicate i-th of pin of range prediction sales cycle
Sell the sales figure in period, piFor growth ratesiFor growth rate piGrowing direction,
ti,mi,liThe Average indoor temperature of respectively i-th sales cycle, average outdoor temperature and weather digital label,Average indoor temperature, average outdoor temperature and day of respectively i-th of the sales cycle to i-1 sales cycle
The predicted value of gas digital label.
The vending machine profitable assessment models are deep neural network model, serial by full link module and 5 convolution modules
Link exports feature vector, then links two full linking layers respectively as output；
The full link module is made of full linking layer and reshape layers；
The convolution module can be made of convolutional layer, BN layers and activation primitive；
The assorted linking two full linking layers link full linking layer 1 as output, specially feature vector, export two values,
As v0Relative to v1Growing directionClassification prediction result, feature vector links full linking layer 2, exports 1 value,
As v0Relative to v1The sizes values of growthEstimation；
The vending machine sales figure is to vending machine profitable assessed value are as follows:
The vending machine profitable assessment models parameter is that training is completed under line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910497088.5A CN110210907A (en) | 2019-06-10 | 2019-06-10 | A kind of data analysis replenishment system of automatic vending |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910497088.5A CN110210907A (en) | 2019-06-10 | 2019-06-10 | A kind of data analysis replenishment system of automatic vending |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110210907A true CN110210907A (en) | 2019-09-06 |
Family
ID=67791727
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910497088.5A Pending CN110210907A (en) | 2019-06-10 | 2019-06-10 | A kind of data analysis replenishment system of automatic vending |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110210907A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110852675A (en) * | 2019-11-06 | 2020-02-28 | 秒针信息技术有限公司 | Method, device, computer storage medium and terminal for realizing distribution management |
| CN112634519A (en) * | 2020-12-11 | 2021-04-09 | 珠海格力电器股份有限公司 | Control method and device for display cabinet and display cabinet |
| CN116739301A (en) * | 2023-07-11 | 2023-09-12 | 上海朗晖慧科技术有限公司 | Big data-based supply and demand balance management system and method |
| CN116957471A (en) * | 2023-07-29 | 2023-10-27 | 京品高科信息科技（北京）有限公司 | Intelligent retail service method, system, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010128816A (en) * | 2008-11-27 | 2010-06-10 | Canon It Solutions Inc | Apparatus and method for supporting operation of vending machine, and program |
| CN108961542A (en) * | 2018-05-23 | 2018-12-07 | 李鹰 | Unmanned intelligent sell goods unit and system |
| CN109509037A (en) * | 2018-12-26 | 2019-03-22 | 广州联业商用机器人科技股份有限公司 | A kind of sales data statistical analysis technique, system and the storage medium of vending machine |
| CN109558991A (en) * | 2018-12-17 | 2019-04-02 | 广州甘来信息科技有限公司 | Based on cargo path amount recommended method, device, equipment and the storage medium from the machine of dealer |
-
2019
- 2019-06-10 CN CN201910497088.5A patent/CN110210907A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010128816A (en) * | 2008-11-27 | 2010-06-10 | Canon It Solutions Inc | Apparatus and method for supporting operation of vending machine, and program |
| CN108961542A (en) * | 2018-05-23 | 2018-12-07 | 李鹰 | Unmanned intelligent sell goods unit and system |
| CN109558991A (en) * | 2018-12-17 | 2019-04-02 | 广州甘来信息科技有限公司 | Based on cargo path amount recommended method, device, equipment and the storage medium from the machine of dealer |
| CN109509037A (en) * | 2018-12-26 | 2019-03-22 | 广州联业商用机器人科技股份有限公司 | A kind of sales data statistical analysis technique, system and the storage medium of vending machine |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110852675A (en) * | 2019-11-06 | 2020-02-28 | 秒针信息技术有限公司 | Method, device, computer storage medium and terminal for realizing distribution management |
| CN112634519A (en) * | 2020-12-11 | 2021-04-09 | 珠海格力电器股份有限公司 | Control method and device for display cabinet and display cabinet |
| CN116739301A (en) * | 2023-07-11 | 2023-09-12 | 上海朗晖慧科技术有限公司 | Big data-based supply and demand balance management system and method |
| CN116957471A (en) * | 2023-07-29 | 2023-10-27 | 京品高科信息科技（北京）有限公司 | Intelligent retail service method, system, electronic equipment and storage medium |
| CN116957471B (en) * | 2023-07-29 | 2024-03-19 | 京品高科信息科技（北京）有限公司 | Intelligent retail service method, system, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110210907A (en) | A kind of data analysis replenishment system of automatic vending | |
| Meissner et al. | Approximate dynamic programming for lateral transshipment problems in multi-location inventory systems | |
| CN107563705A (en) | Household electrical appliances product safety stock and the system and method ordered goods again are analyzed using big data | |
| CN110378528A (en) | Workshop scheduled production method and system based on genetic algorithm | |
| CN109741083B (en) | Material demand weighted prediction method based on enterprise MRP | |
| CN109034495A (en) | Electric Load Prediction System based on edge calculations | |
| CN107506845A (en) | A kind of electricity sales amount Forecasting Methodology and its system based on multi-model fusion | |
| CN114663008B (en) | Intelligent replenishment system based on fresh food of store | |
| CN114548871B (en) | Big data driven supply chain AI intelligent replenishment system | |
| CN112613719A (en) | Intelligent ordering system and method for cooked food store | |
| Bodur et al. | A short-term load demand forecasting based on the method of LSTM | |
| Zhang et al. | A back propagation neural network-based method for intelligent decision-making | |
| KR20210014432A (en) | Method for accurate estimating demand of Raw Materials Using System for estimating demand of Raw Materials | |
| CN111680837B (en) | Multi-scene multi-commodity chain convenience store site selection optimization method under competitive environment | |
| Afrah et al. | The Utilization of Deep Learning in Forecasting The Inflation Rate of Education Costs in Malang | |
| Wang | Analysis of bullwhip effects in perishable product supply chain based on system dynamics model | |
| Islam et al. | Novel AI-Powered Dynamic Inventory Management Algorithm in the USA: Machine Learning Dimension | |
| Cao et al. | A multiobjective multiperiod mixed-integer programming optimization model for integrated scheduling of supply chain under demand uncertainty | |
| TW202113698A (en) | Predicting sale system and method | |
| Kharkyanen et al. | Development of information technology for supporting the process of adjustment of the food enterprise assortment | |
| Zhu et al. | Vegetable Pricing and Restocking with Markov Models | |
| Cheng et al. | Inventory demand forecast based on gray correlation analysis and time series neural network hybrid model | |
| Seifbarghy et al. | Single-vendor multi-buyer vendor managed inventory with discrete demand and stockout | |
| Hong et al. | Automated grocery ordering systems for smart home | |
| Wang et al. | Order Schedule on Multi-mixed-model Assembly Lines in Assemble-to-Order Environments |
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: 20190906 |
|
| RJ01 | Rejection of invention patent application after publication |