CN107292672A - System and method for is realized in a kind of catering industry sales forecast - Google Patents
System and method for is realized in a kind of catering industry sales forecast Download PDFInfo
- Publication number
- CN107292672A CN107292672A CN201710543595.9A CN201710543595A CN107292672A CN 107292672 A CN107292672 A CN 107292672A CN 201710543595 A CN201710543595 A CN 201710543595A CN 107292672 A CN107292672 A CN 107292672A
- Authority
- CN
- China
- Prior art keywords
- information
- data
- shops
- model
- market
- 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 36
- 235000013311 vegetables Nutrition 0.000 claims abstract description 37
- 238000005516 engineering process Methods 0.000 claims abstract description 19
- 238000013135 deep learning Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 9
- 230000000694 effects Effects 0.000 claims description 19
- 230000008859 change Effects 0.000 claims description 18
- 230000008451 emotion Effects 0.000 claims description 15
- 230000007613 environmental effect Effects 0.000 claims description 14
- 238000011156 evaluation Methods 0.000 claims description 14
- 230000010354 integration Effects 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 7
- 230000007774 longterm Effects 0.000 claims description 7
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims description 7
- 238000007637 random forest analysis Methods 0.000 claims description 7
- 238000009795 derivation Methods 0.000 claims description 6
- 230000036651 mood Effects 0.000 claims description 6
- 230000007704 transition Effects 0.000 claims description 6
- 235000013305 food Nutrition 0.000 claims description 4
- 238000012098 association analyses Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 241001269238 Data Species 0.000 abstract description 3
- 238000004422 calculation algorithm Methods 0.000 abstract description 3
- 230000009471 action Effects 0.000 abstract description 2
- 230000004927 fusion Effects 0.000 abstract description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 1
- 235000013361 beverage Nutrition 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 125000001475 halogen functional group Chemical group 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- 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
- G06Q50/10—Services
- G06Q50/12—Hotels or restaurants
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Tourism & Hospitality (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Human Resources & Organizations (AREA)
- Game Theory and Decision Science (AREA)
- General Health & Medical Sciences (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
System and method is realized the invention discloses a kind of catering industry sales forecast, using crawler technology, image recognition technology, text analysis technique and deep learning algorithm are to comment platform data, geographical location information data, Weather information, the external datas such as market information and pos data, shops's information, dish information, the internal datas such as houses market action message are acquired processing and information excavating, set up the forecast model of fusion, according to interior external information instantly, provide the vegetable sales data by week in following three months, and combine vegetable BOM, shops stock, central warehouse is deposited and safety inventory MRP etc., provide the Order Scheduling in future.Compared to other existing Forecasting Methodologies, MAPE (average absolute percent error) can be by 30% 40% liftings to 10% 15%.
Description
Technical field
The present invention relates to sales forecasting system and method, more particularly to a kind of catering industry sales forecast realize system with
Method, belongs to web crawlers, image recognition, text analyzing, deep learning field.
Background technology
Crawler technology is a kind of program of " automation browse network ", and it is according to certain rule, automatically on the world wide web (www
Capture the information that user needs.With the development of internet, network turns into the carrier of bulk information.Crawler technology also turns into data
The important component of collection, is a step the most basic during big data is analyzed.
Text analysis technique refers to the expression to text and its selection of characteristic item, in being text mining, information retrieval
Basic problem.The information that the computer that structureless urtext is converted into structuring can be recognized and handled by it, so as to build
Vertical mathematical modeling describes and replaced text, finally realizes the purpose that effective information is excavated from a large amount of texts.Text semantic point
Analysis is the process for recognizing the semantic information such as text subject, classification and meaning, natural language processing, information filtering, information classification,
The fields such as information retrieval, semantic excavation are all commonly used.Online various word public sentiment can be converted into by text analyzing
Useful information is aided in following Method for Sales Forecast model.
Image recognition technology, refers to handle image using computer, analyzed and understood, to recognize various different moulds
The target of formula and the technology to picture.Structureless image recognition can be recognized and handled into the computer of concrete structure by it
Information.Menu information easily can be easily converted into by structured message by image recognition technology, can also be by carriages such as comments
Obtain useful structure data submodel by the vegetable in information and the progress image recognition of the vegetable of rival and be predicted.
Deep learning has distributed nature expression, Automatic Feature Extraction, end-to-end machine learning and good extensive energy
The advantages such as power, the successful application attracted people's attention in many fields such as speech recognition, image recognition and natural language processing.
Among LSTM models based on time series, deep learning is proved to the analysis and prediction that can be very good to carry out time series.
Instantly food and drink forecast model, on the one hand without market information and external information is utilized well, causes to sales volume
Fluctuation situation can not effectively understand, cause when the marketing activity changes, it is impossible to effectively future is predicted;
On the other hand do not effectively integrate, lack in the listing of new vegetable or other vegetables for the substitution effect and Halo effect in vegetable
When the activity of goods promotion causes the sales volume to fluctuate, the sales volume of related vegetable impacted can also be fluctuated, and this partial information is not
When including model, related product Method for Sales Forecast is forbidden, so overall prediction accuracy is not high.
It is directed to food and beverage enterprise, inventory problem problem in the urgent need to address always.On the one hand stock is excessively easily caused
Stock, occupied fund;On the other hand very few easily cause of getting ready the goods is run out of goods and profit and brand is impacted.It is how smart
Preparing goods turns into paying close attention to for enterprise, and inside and outside information resources are fully integrated in this invention, utilize forward position deep learning model
Based on merge a variety of models, provide accurately Method for Sales Forecast, so that power-assisted enterprise precisely gets ready the goods, improving inventory turnover ratio
Meanwhile, supply shortage phenomenon is reduced, enterprise profit and brand image is ensured.
The content of the invention
The present invention is to realize System and method for there is provided a kind of catering industry sales forecast to solve above-mentioned deficiency,
To improve the accuracy of vegetable prediction, power-assisted enterprise precisely gets ready the goods, and improves profit.
The above-mentioned purpose of the present invention is realized by following technical scheme:A kind of realization system of catering industry sales forecast
System, it is characterised in that:Commented including data acquisition with pretreatment unit, menu image recognition unit, public sentiment semantic analysis and emotion
Subdivision, shops's spatial autocorrelation explore unit, automation modeling and updating block and MRP units;
The data acquisition is used for data acquisition, data cleansing and data feature extraction with pretreatment unit;Specifically:
Data acquisition, it is basic using environment, exterior market and rivals such as public opinion, the weather such as crawler technology collection evaluation
Information is simultaneously stored;
Data cleansing, carries out data by the environmental informations such as weather, shops's information, corporate history marketing activity information and locates in advance
Reason, forms structuring time serial message and stores;
Data characteristics is extracted, and using Arima model thoughts, shops's POS data is carried out into history dimension, Long-term change trend, season
The derivation informations such as degree change are simultaneously stored;
The menu image recognition unit is used to recognize menu transition information, by history menu temporally typing, passes through figure
As identification, the history of menu is changed into structuring and stored;
The public sentiment semantic analysis is used to excavate the scoring of vegetable emotion and excavates overall catering market with emotion scoring unit
Mood, specifically:
The scoring of vegetable emotion is excavated, using participle technique, mutual information model, topic model etc., to public opinions such as basic evaluations
Information carries out text analyzing, comprising semantic analysis and sentiment analysis, obtains the market public opinion information of the structuring of each vegetable, example
Such as the scoring of market emotion, refer to the information such as frequency and store;
Overall catering market mood is excavated, using participle technique, mutual information model, topic model etc., to all dining places
Comment and analyzed, obtain the information such as whole catering market and the hot spot of public opinions segmented market and store;
Shops's spatial autocorrelation, which explores unit, is used to exploring high degree of correlation rival in region, and utilization space is from phase
Close model, be associated analysis to the rival in shops region, rival's list of the high degree of association of formation and
The history number change of opponent is simultaneously stored;
The automation modeling is used to build forecast model automatically with updating block, and the information of storage is included into depth automatically
Learn among LSTM models, predict following three months by week by vegetable sales volume, while be predicted using RandomForest,
Both are predicted the outcome and is weighted according to confidence level, final Method for Sales Forecast result is obtained.Simultaneously model can set it is regular from
It is dynamic to update, to make fast reaction to environmental changes such as markets, finally realize the sales forecast needed for enterprise;
The MRP units be used for after sales forecast is drawn, deposited using the existing shops stock of enterprise, central warehouse,
Way and safety inventory are set etc., are called ripe MRP systems, are drawn the procurement plan needed for supply chain department and delivery meter
Draw.
A kind of implementation method of catering industry sales forecast, including:
Using environment, exterior market and rival's essential informations such as public opinion, the weather such as crawler technology collection evaluation, formed
Fundamental external data;
Using image recognition technology, the menu information of catering companies is subjected to structuring, identification draws the difference that menu changes
It is different;And image recognition technology is utilized, the picture in public opinion information is identified and is converted into word auxiliary text analyzing;
Using participle technique, mutual information model, topic model etc., text analyzing is carried out to the public opinion such as basic evaluation information,
Comprising semantic analysis and sentiment analysis, the market public opinion information of the structuring of each vegetable is obtained, and rival and whole
The structuring public opinion information of catering market;
Utilization space autocorrelation model, analysis is associated to the rival in shops region, forms high association
The history quantity of the rival of degree;
The environmental informations such as weather, shops's information, corporate history marketing activity information are subjected to data prediction, structure is formed
Change time serial message;
Using Arima model thoughts, shops's POS data is subjected to the derivative letters such as history dimension, Long-term change trend, season change
Breath;
Using the associated effect model of promotion, incidence coefficient between different vegetables, and the association effect that promotion is brought are analyzed
Answer coefficient;
Above- mentioned information is included into deep learning LSTM models, following three months of prediction by week by vegetable sales volume, together
Shi Liyong RandomForest are predicted, and both are predicted the outcome and is weighted according to confidence level, obtain final Method for Sales Forecast
As a result;
And then, sales forecast and shops stock, central warehouse are deposited using MRP models, included in information integrations such as ways, is drawn
Following amount of purchase and delivering amount from total storehouse to shops.
Specifically:
The implementation method of the catering industry sales forecast of the present invention, comprises the following steps:
Step 1:Data acquisition:
Utilize environment, exterior market and rival's essential informations such as public opinion, the weather such as crawler technology collection evaluation;
Step 2:External data and internal data are spliced and integrated:
External information and internal information are subjected to splicing integration as keyword according to vegetable and shops;
Step 3:Text analyzing:
Using participle technique, mutual information model, topic model etc., text analyzing is carried out to the public opinion such as basic evaluation information,
Comprising semantic analysis and sentiment analysis, the market public opinion information of the structuring of each vegetable is obtained, and rival and whole
The structuring public opinion information of catering market;
Step 4:Association analysis:
Using the associated effect model of promotion, incidence coefficient between different vegetables, and the association effect that promotion is brought are analyzed
Answer coefficient;
Step 5:Image recognition:
Menu transition information is recognized, by history menu temporally typing, by image recognition, the history of menu is changed and tied
Structure is simultaneously stored;
Step 6:Sales data derives:
Data characteristics is extracted, and using Arima model thoughts, shops's POS data is carried out into history dimension, Long-term change trend, season
The derivation informations such as degree change are simultaneously stored;
Step 7:Spatial autocorrelation analysis:
Utilization space autocorrelation model, analysis is associated to the rival in shops region, forms high association
The history quantity of the rival of degree;
Step 8:Data structured processing:
The environmental informations such as weather, shops's information, corporate history marketing activity information are subjected to data prediction, data are entered
Row feature extraction, carries out labeling processing, forms structuring time serial message and stores;
Step 9:Automation modeling:
It is automatic to build forecast model, the information of storage is included into deep learning LSTM models, prediction future three automatically
, while being predicted using RandomForest, both are predicted the outcome according to confidence level to enter by vegetable sales volume by week within individual month
Row weighting, obtains final Method for Sales Forecast result.Model, which can be set, simultaneously periodically automatically updates, to be done to environmental changes such as markets
Go out fast reaction, finally realize the sales forecast needed for enterprise;
Step 10:MRP model integrations:
Sales forecast and shops stock, central warehouse are deposited using MRP models, included in information integrations such as ways, future is drawn
Amount of purchase and delivering amount from total storehouse to shops.
Present invention advantage compared with prior art is:The present invention is based on cloud platform service architecture, using text analyzing skill
Art and deep learning algorithm, the variation of research menu, exterior market information, environmental information, internal promotion information, public feelings information, dish
The influence to following sales volume such as product substitutional relation, history sales volume, with model based on deep learning LSTM, merges other its
His forecast model finally realizes the prediction to following sales volume as auxiliary information.Compared to other existing Forecasting Methodologies, MAPE
(average absolute percent error) can be by 30%-40% liftings to 10%-15%.
Brief description of the drawings
Fig. 1 is workflow diagram of the invention.
Embodiment
The present invention is described in further detail with reference to embodiment.
As shown in figure 1, system is realized in a kind of catering industry sales forecast, it is characterised in that:Including data acquisition and in advance
Processing unit, menu image recognition unit, public sentiment semantic analysis and emotion scoring unit, shops spatial autocorrelation explore unit,
Automation modeling and updating block and MRP units;
The data acquisition is used for data acquisition, data cleansing and data feature extraction with pretreatment unit;Specifically:
Data acquisition, it is basic using environment, exterior market and rivals such as public opinion, the weather such as crawler technology collection evaluation
Information is simultaneously stored;
Data cleansing, carries out data by the environmental informations such as weather, shops's information, corporate history marketing activity information and locates in advance
Reason, forms structuring time serial message and stores;
Data characteristics is extracted, and using Arima model thoughts, shops's POS data is carried out into history dimension, Long-term change trend, season
The derivation informations such as degree change are simultaneously stored;
The menu image recognition unit is used to recognize menu transition information, by history menu temporally typing, passes through figure
As identification, the history of menu is changed into structuring and stored;
The public sentiment semantic analysis is used to excavate the scoring of vegetable emotion and excavates overall catering market with emotion scoring unit
Mood, specifically:
The scoring of vegetable emotion is excavated, using participle technique, mutual information model, topic model etc., to public opinions such as basic evaluations
Information carries out text analyzing, comprising semantic analysis and sentiment analysis, obtains the market public opinion information of the structuring of each vegetable, example
Such as the scoring of market emotion, refer to the information such as frequency and store;
Overall catering market mood is excavated, using participle technique, mutual information model, topic model etc., to all dining places
Comment and analyzed, obtain the information such as whole catering market and the hot spot of public opinions segmented market and store;
Shops's spatial autocorrelation, which explores unit, is used to exploring high degree of correlation rival in region, and utilization space is from phase
Close model, be associated analysis to the rival in shops region, rival's list of the high degree of association of formation and
The history number change of opponent is simultaneously stored;
The automation modeling is used to build forecast model automatically with updating block, and the information of storage is included into depth automatically
Learn among LSTM models, predict following three months by week by vegetable sales volume, while be predicted using RandomForest,
Both are predicted the outcome and is weighted according to confidence level, final Method for Sales Forecast result is obtained.Simultaneously model can set it is regular from
It is dynamic to update, to make fast reaction to environmental changes such as markets, finally realize the sales forecast needed for enterprise;
The MRP units be used for after sales forecast is drawn, deposited using the existing shops stock of enterprise, central warehouse,
Way and safety inventory are set etc., are called ripe MRP systems, are drawn the procurement plan needed for supply chain department and delivery meter
Draw.
The implementation method of the catering industry sales forecast of the present invention, comprises the following steps:
Step 1:Data acquisition:
Utilize environment, exterior market and rival's essential informations such as public opinion, the weather such as crawler technology collection evaluation;
Step 2:External data and internal data are spliced and integrated:
External information and internal information are subjected to splicing integration as keyword according to vegetable and shops;
Step 3:Text analyzing:
Using participle technique, mutual information model, topic model etc., text analyzing is carried out to the public opinion such as basic evaluation information,
Comprising semantic analysis and sentiment analysis, the market public opinion information of the structuring of each vegetable is obtained, and rival and whole
The structuring public opinion information of catering market;
Step 4:Association analysis:
Using the associated effect model of promotion, incidence coefficient between different vegetables, and the association effect that promotion is brought are analyzed
Answer coefficient;
Step 5:Image recognition:
Menu transition information is recognized, by history menu temporally typing, by image recognition, the history of menu is changed and tied
Structure is simultaneously stored;
Step 6:Sales data derives:
Data characteristics is extracted, and using Arima model thoughts, shops's POS data is carried out into history dimension, Long-term change trend, season
The derivation informations such as degree change are simultaneously stored;
Step 7:Spatial autocorrelation analysis:
Utilization space autocorrelation model, analysis is associated to the rival in shops region, forms high association
The history quantity of the rival of degree;
Step 8:Data structured processing:
The environmental informations such as weather, shops's information, corporate history marketing activity information are subjected to data prediction, data are entered
Row feature extraction, carries out labeling processing, forms structuring time serial message and stores;
Step 9:Automation modeling:
It is automatic to build forecast model, the information of storage is included into deep learning LSTM models, prediction future three automatically
, while being predicted using RandomForest, both are predicted the outcome according to confidence level to enter by vegetable sales volume by week within individual month
Row weighting, obtains final Method for Sales Forecast result.Model, which can be set, simultaneously periodically automatically updates, to be done to environmental changes such as markets
Go out fast reaction, finally realize the sales forecast needed for enterprise;
Step 10:MRP model integrations:
Sales forecast and shops stock, central warehouse are deposited using MRP models, included in information integrations such as ways, future is drawn
Amount of purchase and delivering amount from total storehouse to shops.
The system of the present invention is based on cloud service framework, using crawler technology, image recognition technology, text analysis technique and depth
Learning algorithm is spent to external data and pos such as comment platform data, geographical location information data, Weather information, market informations
The internal datas such as data, shops's information, dish information, houses market action message are acquired processing and information excavating, set up
The forecast model of fusion, according to interior external information instantly, provides the vegetable sales data by week in following three months, and combine dish
Product BOM, shops stock, central warehouse are deposited and safety inventory MRP etc., provide the Order Scheduling in future.
Embodiments of the invention are the foregoing is only, are not intended to limit the scope of the invention, it is every to utilize this hair
Equivalent structure or equivalent flow conversion that bright specification and embodiment content are made, or directly or indirectly it is used in other correlations
Technical field, is included within the scope of the present invention.
Claims (2)
1. system is realized in a kind of catering industry sales forecast, it is characterised in that:Including data acquisition and pretreatment unit, menu
Image identification unit, public sentiment semantic analysis and emotion scoring unit, shops spatial autocorrelation explore unit, automation modeling with more
New unit and MRP units;
The data acquisition is used for data acquisition, data cleansing and data feature extraction with pretreatment unit;Specifically:
Data acquisition, utilizes environment, exterior market and rival's essential informations such as public opinion, the weather such as crawler technology collection evaluation
And store;
Data cleansing, data prediction, shape are carried out by the environmental informations such as weather, shops's information, corporate history marketing activity information
Into structuring time serial message and store;
Data characteristics is extracted, and using Arima model thoughts, shops's POS data is carried out into history dimension, Long-term change trend, become in season
The derivation informations such as change are simultaneously stored;
The menu image recognition unit is used to recognize menu transition information, and history menu temporally typing is known by image
Not, the history of menu is changed into structuring and stored;
The public sentiment semantic analysis is used to excavate the scoring of vegetable emotion and excavates overall catering market mood with emotion scoring unit,
Specifically:
The scoring of vegetable emotion is excavated, using participle technique, mutual information model, topic model etc., to the public opinion information such as basic evaluation
Text analyzing is carried out, comprising semantic analysis and sentiment analysis, the market public opinion information of the structuring of each vegetable, such as city is obtained
Field emotion scoring, refers to the information such as frequency and stores;
Excavate overall catering market mood, using participle technique, mutual information model, topic model etc., all food and drink are commented on into
Row analysis, obtains the information such as whole catering market and the hot spot of public opinions segmented market and stores;
Shops's spatial autocorrelation, which explores unit, to be used to explore high degree of correlation rival in region, utilization space auto-correlation mould
Type, analysis is associated to the rival in shops region, forms rival's list and the opponent of the high degree of association
History number change and store;
The automation modeling is used to build forecast model automatically with updating block, and the information of storage is included into deep learning automatically
Among LSTM models, following three months are predicted by week by vegetable sales volume, while being predicted using RandomForest, by two
Person predicts the outcome to be weighted according to confidence level, obtains final Method for Sales Forecast result.Simultaneously model can set it is periodically automatic more
Newly, to make fast reaction to environmental changes such as markets, the sales forecast needed for enterprise is finally realized;
The MRP units be used for after sales forecast is drawn, deposited using the existing shops stock of enterprise, central warehouse, way with
And safety inventory is set etc., ripe MRP systems are called, the procurement plan needed for supply chain department and shipment schedule is drawn.
2. a kind of implementation method of catering industry sales forecast, it is characterised in that:Comprise the following steps:
Step 1:Data acquisition:
Utilize environment, exterior market and rival's essential informations such as public opinion, the weather such as crawler technology collection evaluation;
Step 2:External data and internal data are spliced and integrated:
External information and internal information are subjected to splicing integration as keyword according to vegetable and shops;
Step 3:Text analyzing:
Using participle technique, mutual information model, topic model etc., text analyzing is carried out to the public opinion such as basic evaluation information, comprising
Semantic analysis and sentiment analysis, obtain the market public opinion information of the structuring of each vegetable, and rival and whole food and drink
The structuring public opinion information in market;
Step 4:Association analysis:
Using the associated effect model of promotion, incidence coefficient between different vegetables, and the associated effect system that promotion is brought are analyzed
Number;
Step 5:Image recognition:
Menu transition information is recognized, by history menu temporally typing, by image recognition, the history of menu is changed into structuring
And store;
Step 6:Sales data derives:
Data characteristics is extracted, and using Arima model thoughts, shops's POS data is carried out into history dimension, Long-term change trend, become in season
The derivation informations such as change are simultaneously stored;
Step 7:Spatial autocorrelation analysis:
Utilization space autocorrelation model, analysis is associated to the rival in shops region, forms the high degree of association
The history quantity of rival;
Step 8:Data structured processing:
The environmental informations such as weather, shops's information, corporate history marketing activity information are subjected to data prediction, data carried out special
Extraction is levied, labeling processing is carried out, structuring time serial message is formed and stores;
Step 9:Automation modeling:
It is automatic to build forecast model, the information of storage is included into deep learning LSTM models automatically, prediction is following three months
By week by vegetable sales volume, while being predicted using RandomForest, both are predicted the outcome and added according to confidence level
Power, obtains final Method for Sales Forecast result.Model, which can be set, simultaneously periodically automatically updates, to be made soon to environmental changes such as markets
Speed reaction, finally realizes the sales forecast needed for enterprise;
Step 10:MRP model integrations:
Sales forecast and shops stock, central warehouse are deposited using MRP models, included in information integrations such as ways, adopting for future is drawn
Purchase amount and delivering amount from total storehouse to shops.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710543595.9A CN107292672A (en) | 2017-07-05 | 2017-07-05 | System and method for is realized in a kind of catering industry sales forecast |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710543595.9A CN107292672A (en) | 2017-07-05 | 2017-07-05 | System and method for is realized in a kind of catering industry sales forecast |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107292672A true CN107292672A (en) | 2017-10-24 |
Family
ID=60100278
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710543595.9A Pending CN107292672A (en) | 2017-07-05 | 2017-07-05 | System and method for is realized in a kind of catering industry sales forecast |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107292672A (en) |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107886272A (en) * | 2017-11-06 | 2018-04-06 | 北京戴纳实验科技有限公司 | A kind of food management method |
CN108038216A (en) * | 2017-12-22 | 2018-05-15 | 联想(北京)有限公司 | Information processing method, device and server cluster |
CN109871403A (en) * | 2019-02-26 | 2019-06-11 | 扬州制汇互联信息技术有限公司 | Industrial big data analysis method based on industry supply chain |
CN109886747A (en) * | 2019-02-22 | 2019-06-14 | 网易(杭州)网络有限公司 | Method for Sales Forecast method, medium, device and calculating equipment |
CN109934385A (en) * | 2019-01-29 | 2019-06-25 | 跨越速运集团有限公司 | Goods amount prediction technique and system based on length Memory Neural Networks |
CN109978612A (en) * | 2019-03-18 | 2019-07-05 | 北京工业大学 | A kind of convenience store's Method for Sales Forecast method based on deep learning |
CN110135876A (en) * | 2018-02-09 | 2019-08-16 | 北京京东尚科信息技术有限公司 | The method and device of Method for Sales Forecast |
CN110490635A (en) * | 2019-07-12 | 2019-11-22 | 阿里巴巴集团控股有限公司 | Trade company's vegetable transaction prediction and method and device of preparing for a meal |
CN110599234A (en) * | 2019-08-13 | 2019-12-20 | 广东工业大学 | Product sales prediction method |
CN110633401A (en) * | 2019-07-26 | 2019-12-31 | 苏宁云计算有限公司 | Prediction model of store data and establishment method thereof |
CN110737643A (en) * | 2019-09-29 | 2020-01-31 | 广州餐道信息科技有限公司 | big data analysis, processing and management center station based on catering information management system |
CN110807692A (en) * | 2019-11-04 | 2020-02-18 | 济南大学 | Intelligent sale system of restaurant |
CN110969467A (en) * | 2018-09-30 | 2020-04-07 | 北京国双科技有限公司 | Product sales prediction method and related device |
CN112633594A (en) * | 2020-12-30 | 2021-04-09 | 北京高思博乐教育科技股份有限公司 | Automatic prediction method, device and system for multi-target time sequence |
CN113610657A (en) * | 2021-10-10 | 2021-11-05 | 江苏四方精密钢管有限公司 | Method and system for popularizing and selling steel pipe products |
CN113780611A (en) * | 2020-12-10 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Inventory management method and device |
CN116843378A (en) * | 2023-09-01 | 2023-10-03 | 阳信东泰精密金属有限公司 | Hardware fitting supply prediction method and system based on deep learning |
KR20230137774A (en) | 2022-03-22 | 2023-10-05 | 한병엽 | Method for extracting order information |
CN117557289A (en) * | 2023-11-20 | 2024-02-13 | 大头(广州)软件技术有限公司 | Restaurant data modeling method and system based on intelligent marketing scene |
CN117934124A (en) * | 2024-03-25 | 2024-04-26 | 邯郸鉴晨网络科技有限公司 | Big data-based electronic commerce order information intelligent processing system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104281623A (en) * | 2013-07-12 | 2015-01-14 | 武汉好味道科技有限公司 | Method and system for predicting hot dishes and recommending personalized dishes on internet |
CN105205769A (en) * | 2015-09-28 | 2015-12-30 | 廖健伟 | Data mining method based on intelligent canteen catering system |
CN105976199A (en) * | 2016-04-26 | 2016-09-28 | 重庆大学 | Medicine sales prediction method and medicine sales prediction system based on hybrid model |
CN106408341A (en) * | 2016-09-21 | 2017-02-15 | 北京小米移动软件有限公司 | Goods sales volume prediction method and device, and electronic equipment |
-
2017
- 2017-07-05 CN CN201710543595.9A patent/CN107292672A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104281623A (en) * | 2013-07-12 | 2015-01-14 | 武汉好味道科技有限公司 | Method and system for predicting hot dishes and recommending personalized dishes on internet |
CN105205769A (en) * | 2015-09-28 | 2015-12-30 | 廖健伟 | Data mining method based on intelligent canteen catering system |
CN105976199A (en) * | 2016-04-26 | 2016-09-28 | 重庆大学 | Medicine sales prediction method and medicine sales prediction system based on hybrid model |
CN106408341A (en) * | 2016-09-21 | 2017-02-15 | 北京小米移动软件有限公司 | Goods sales volume prediction method and device, and electronic equipment |
Non-Patent Citations (3)
Title |
---|
张膂: "基于餐饮评论的情感倾向性分析", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
柴军: "餐饮业菜品销售量预测研究", 《中国优秀硕士学位论文全文数据库经济与管理科学辑》 * |
陈亮 等: "深度学习框架下LSTM网络在短期电力负荷预测中的应用", 《电力信息与通信技术》 * |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107886272B (en) * | 2017-11-06 | 2021-08-31 | 北京戴纳实验科技有限公司 | Food material management method |
CN107886272A (en) * | 2017-11-06 | 2018-04-06 | 北京戴纳实验科技有限公司 | A kind of food management method |
CN108038216A (en) * | 2017-12-22 | 2018-05-15 | 联想(北京)有限公司 | Information processing method, device and server cluster |
CN110135876A (en) * | 2018-02-09 | 2019-08-16 | 北京京东尚科信息技术有限公司 | The method and device of Method for Sales Forecast |
CN110969467A (en) * | 2018-09-30 | 2020-04-07 | 北京国双科技有限公司 | Product sales prediction method and related device |
CN110969467B (en) * | 2018-09-30 | 2023-12-26 | 北京国双科技有限公司 | Product sales prediction method and related device |
CN109934385A (en) * | 2019-01-29 | 2019-06-25 | 跨越速运集团有限公司 | Goods amount prediction technique and system based on length Memory Neural Networks |
CN109886747A (en) * | 2019-02-22 | 2019-06-14 | 网易(杭州)网络有限公司 | Method for Sales Forecast method, medium, device and calculating equipment |
CN109871403A (en) * | 2019-02-26 | 2019-06-11 | 扬州制汇互联信息技术有限公司 | Industrial big data analysis method based on industry supply chain |
CN109978612A (en) * | 2019-03-18 | 2019-07-05 | 北京工业大学 | A kind of convenience store's Method for Sales Forecast method based on deep learning |
CN110490635A (en) * | 2019-07-12 | 2019-11-22 | 阿里巴巴集团控股有限公司 | Trade company's vegetable transaction prediction and method and device of preparing for a meal |
CN110633401A (en) * | 2019-07-26 | 2019-12-31 | 苏宁云计算有限公司 | Prediction model of store data and establishment method thereof |
CN110599234A (en) * | 2019-08-13 | 2019-12-20 | 广东工业大学 | Product sales prediction method |
CN110737643B (en) * | 2019-09-29 | 2022-11-15 | 餐道信息科技有限公司 | Big data analysis processing management middle platform based on catering information management system |
CN110737643A (en) * | 2019-09-29 | 2020-01-31 | 广州餐道信息科技有限公司 | big data analysis, processing and management center station based on catering information management system |
CN110807692A (en) * | 2019-11-04 | 2020-02-18 | 济南大学 | Intelligent sale system of restaurant |
CN113780611A (en) * | 2020-12-10 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Inventory management method and device |
CN112633594A (en) * | 2020-12-30 | 2021-04-09 | 北京高思博乐教育科技股份有限公司 | Automatic prediction method, device and system for multi-target time sequence |
CN113610657A (en) * | 2021-10-10 | 2021-11-05 | 江苏四方精密钢管有限公司 | Method and system for popularizing and selling steel pipe products |
KR20230137774A (en) | 2022-03-22 | 2023-10-05 | 한병엽 | Method for extracting order information |
CN116843378A (en) * | 2023-09-01 | 2023-10-03 | 阳信东泰精密金属有限公司 | Hardware fitting supply prediction method and system based on deep learning |
CN117557289A (en) * | 2023-11-20 | 2024-02-13 | 大头(广州)软件技术有限公司 | Restaurant data modeling method and system based on intelligent marketing scene |
CN117557289B (en) * | 2023-11-20 | 2024-04-16 | 大头(广州)软件技术有限公司 | Restaurant data modeling method and system based on intelligent marketing scene |
CN117934124A (en) * | 2024-03-25 | 2024-04-26 | 邯郸鉴晨网络科技有限公司 | Big data-based electronic commerce order information intelligent processing system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107292672A (en) | System and method for is realized in a kind of catering industry sales forecast | |
Núñez-Merino et al. | Information and digital technologies of Industry 4.0 and Lean supply chain management: a systematic literature review | |
He et al. | Evolutionary food quality and location strategies for restaurants in competitive online-to-offline food ordering and delivery markets: An agent-based approach | |
Rane | Enhancing customer loyalty through Artificial Intelligence (AI), Internet of Things (IoT), and Big Data technologies: improving customer satisfaction, engagement, relationship, and experience | |
Kumar et al. | si 3-Industry: A sustainable, intelligent, innovative, internet-of-things industry | |
Sheffi | Balancing green: When to embrace sustainability in a business (and when not to) | |
Shukla et al. | Agri‐fresh produce supply chain management: a state‐of‐the‐art literature review | |
Xue et al. | Social media user behavior analysis applied to the fashion and apparel industry in the big data era | |
Jin et al. | Sustainable digital marketing under big data: an AI random forest model approach | |
Alizadeh et al. | Suitable delivery system in small e-commerce companies | |
CN110288423A (en) | A kind of business model of S2B2C | |
Yerragudipadu et al. | An Efficient Novel Approach on Machine Learning Paradigmsfor Food Delivery Company through Demand Forecastıng in societal community | |
Ouro‐Salim et al. | The use of Big Data to mitigate waste in agri‐food supply chains | |
Fuchs et al. | Business intelligence for destinations: Creating knowledge from social media | |
Frohmann | Digital pricing: A guide to strategic pricing for the digital economy | |
Nguyen et al. | Artificial intelligence (AI)-driven services | |
Nadeem et al. | Probec: A Product hunting tool | |
Ranjekar et al. | Rise of quick commerce in India: business models and infrastructure requirements | |
Crandall et al. | How Management Programs Can Improve Organization Performance: Selecting and Implementing the Best Program for Your Organization | |
Huang et al. | Comparison of E-Commerce Retail Between China and Japan | |
Kim | Implementing a sustainable decision-making environment-cases for GIS, BIM, and big data utilization | |
Liu | Method to Facilitate E-Commerce Buying Power by Using Machine Learning Techniques | |
Ghanbari | Presenting the smart-sustainable supply chain model based on artificial intelligence | |
Quayson et al. | Machine Learning and Supply Chain Management | |
Holmér et al. | Development of a data-driven marketing strategy for an online pharmacy |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171024 |