CN106779859A - A kind of real-time Method for Sales Forecast method of mobile terminal product - Google Patents
A kind of real-time Method for Sales Forecast method of mobile terminal product Download PDFInfo
- Publication number
- CN106779859A CN106779859A CN201611222987.7A CN201611222987A CN106779859A CN 106779859 A CN106779859 A CN 106779859A CN 201611222987 A CN201611222987 A CN 201611222987A CN 106779859 A CN106779859 A CN 106779859A
- Authority
- CN
- China
- Prior art keywords
- mobile terminal
- target model
- sales volume
- days
- model mobile
- 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
- 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
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of real-time Method for Sales Forecast method of mobile terminal product, the historical record data that target model mobile terminal history sales volume data, the history sales volume data of contrast model mobile terminal, user's access search engine historical record data and user access e-commerce website is collected first；Three kinds of modes that linear regression method, autoregression integration moving average method and contrast predicted method is respectively adopted set up the Method for Sales Forecast model of target model mobile terminal and respectively obtain different results；Corresponding weighted value is assigned to result respectively, then using weighted sum method, the tentative prediction result of the mobile terminal product sales volume is drawn；Target model mobile terminal is estimated in following temperature variation tendency, then tentative prediction result is modified, obtain revised final result.Based on the present invention can provide a kind of big data by multidimensional, can real-time estimate, can self-correction, the degree of accuracy real-time Method for Sales Forecast method of mobile terminal product high.
Description
Technical field
The present invention relates to areas of information technology, more particularly to a kind of real-time Method for Sales Forecast method of mobile terminal product.
Background technology
The fast development of human information technology, interpersonal information interchange is more and more easier, and this be unable to do without various shiftings
The development and application of dynamic end product, popularity rate more and more higher of the mobile terminal in its people, with the arrival in big data epoch,
If can on commercial field maintenance data digging technology, to the mobile terminal of certain specific model in following certain hour
Sales volume makes Accurate Prediction in units of day, it is possible to walk in the market for helping manufacturer preferably to hold the model mobile terminal
Gesture, helps to be made rational planning for accordingly and precision marketing, will provide huge to the production of end product, logistics, storage
Help, greatly improve the efficiency for producing and selling enterprise.
Existing traditional terminal sales Forecasting Methodology is generally divided into two kinds：One kind is to combine itself from already by expert system
Test, qualitative forecasting is carried out to sales volume；Another kind is to collect the history sales volume data in units of day, using regression analysis or sequential
Following daily terminal sales are predicted by analysis, but not only the degree of accuracy is low, lack dynamic for the result of above method prediction
Response and shortage real-time；And changing factor of the customer group to terminal requirements degree is have ignored, because it also can be in following shadow
Ring the sales volume of terminal；Furthermore, only focus on the historical data of a certain particular brand and model terminal, lack to same brand other
The reference and utilization of model terminal historical data.
The content of the invention
There is provided the invention aims to overcome the deficiencies in the prior art one kind based on multidimensional big data, can be real-time
Prediction, can self-correction, the degree of accuracy real-time Method for Sales Forecast method of mobile terminal product high.
To reach above-mentioned purpose, present invention employs following technical scheme.
A kind of real-time Method for Sales Forecast method of mobile terminal product, comprises the following steps：
Step one：The history sales volume data of target model mobile terminal and contrast model mobile terminal are collected, and user accesses
The historical record data of search engine and e-commerce website；
Step 2：Using the historical data being collected into step one, linear regression method, autoregression integration moving average is respectively adopted
Three kinds of modes of method and contrast predicted method set up the Method for Sales Forecast model of target model mobile terminal；
Step 3：With reference to different forecast models in step 2, a weighted value is assigned respectively to each forecast model, then carry out
Weighted sum is calculated, and draws the tentative prediction result of the mobile terminal product sales volume；
Step 4：It is every using the daily number of times data that target model mobile terminal is searched on e-commerce website of user and user
Day searches for the frequency data of target model mobile terminal on a search engine, estimates target model mobile terminal in following temperature
Variation tendency, the tentative prediction result to being obtained in step 3 is modified, and obtains revised final result.
The data collected in the step one include following：
（1）The accumulative sales volume of target model mobile terminal in M days in the past is obtained from database, is obtained in units of day, by
The accumulative sales volume of target model mobile terminal untill the same day.
（2）For the mobile terminal of target model, a kind of brand of searching is identical, sell day 1 to two year more early than current time
Mobile terminal model, the model mobile terminal is obtained from database and sells accumulative sales volume daily in latter N days, wherein numerical value
N is much larger than numerical value M, for being contrasted.
（3）Arranged in the past in M days from web search daily record, Internet user searches on some popular e-commerce websites
The number of times of rope target model mobile terminal.
（4）Arranged in the past in M days from web search daily record, Internet user searches for object type on popular search engine
The number of times of number mobile terminal accounts for the ratio of whole searching times.
Forecast model in the step 2, specifically includes：
Assuming that on the premise of known target model mobile terminal goes over the accumulative sales volume of M days, target is every in predicting X days future
It accumulative sales volume.Including following three kinds：
Model one：Using the accumulative sales volume of target model mobile terminal in past M days, with the linear regression based on least square method
Method is analyzed, and historical data is fitted, and obtains the straight line that a strips are Si=a*Di+b, daily for representing
Accumulative sales volume and number of days contact.
Model two：Using the accumulative sales volume of target model mobile terminal in past M days, moving average mould is integrated with autoregression
Type（That is ARIMA models）Time-Series analysis is carried out, by observing autocorrelogram and inclined phase of the historical data under different rank difference
Guan Tu, determines the parameter of ARIMA models, obtains the matched curve of historical data, then just can further obtain in following X days
Corresponding Method for Sales Forecast.
Model three：Accumulative sales volume daily in latter N days is sold using model mobile terminal is contrasted, is obtained and target model is moved
The sales volume of dynamic terminal is estimated.
Amendment in the step 4, specifically includes：
（1）Moving average model, i.e. ARIMA models are integrated with autoregression, mesh is searched on e-commerce website daily to user
Mark the number of times data of model mobile terminal<D1, T1>, <D2, T2>, <D3, T3>……<DM, TM>Carry out Time-Series analysis,
User searches for number of times TM+1, TM+2, TM+3 ... the TM+X of the terminal on e-commerce website in prediction is following X days.
（2）Moving average model, i.e. ARIMA models are integrated with autoregression, mesh is searched on a search engine daily to user
Mark the number of times data of model mobile terminal<D1, R1>, <D2, R2>, <D3, R3>……<DM, RM>Carry out Time-Series analysis,
User searches for number of times RM+1, RM+2, RM+3 ... the RM+X of the terminal on e-commerce website in prediction is following X days.
（3）Temperature trend of the target model mobile terminal at the X days is calculated using following formula：
Wherein：trendxIt is temperature Trend value, the value has reacted target model mobile terminal near between 0.95~1.05 scope
The general morphologictrend of phase pouplarity.
（4）The prediction sales volume of the jth day using following formula to obtaining is modified, and obtains final predicting the outcome：
Wherein：SjFor step 3 is predicted the outcome；Sj_finalThe final result that step 4 is obtained；trendjIt is the temperature of jth day
Trend value.
Due to the beneficial technique effect that the utilization of above-mentioned technical proposal, the present invention have：
（1）The technical program with existing conventional solution using the qualitative forecasting of expert system and Heuristics compared with, this
Based on technical scheme is using big datas such as history sales volume data, fully determined with Time-Series analysis and machine learning algorithm
Amount prediction, and using regression analysis by distinct methods to Different Results merged, so as to get result have more
Convincingness.
（2）The technical program not only with reference to the history pin of the model terminal when the sales volume of target model terminal is predicted
Amount data, have also introduced the history sales volume data with the contrast model mobile terminal of the same brand of the terminal as reference, increase
The confidence level of result.
（3）The technical program not only with reference to the history sales volume data of target model mobile terminal, also with user in electricity
The frequency data of target model mobile terminal are searched on sub- business web site and search engine, analysis target model mobile terminal is not
The temperature variation tendency come, and the following Method for Sales Forecast value of target model mobile terminal is corrected on this basis, further increase
The confidence level of result.
Brief description of the drawings
Technical solution of the present invention is described further below in conjunction with the accompanying drawings.
Accompanying drawing 1 is schematic process flow diagram of the invention.
Accompanying drawing 2 is the graph of a relation of the time and sales volume predicted using linear regression method.
Accompanying drawing 3 is using the time of autoregression integration moving average method prediction and the graph of a relation of sales volume.
In figure：1. target model mobile terminal history sales volume data；2. the history sales volume data of model mobile terminal are contrasted；
3. linear regression method；4. autoregression integrates moving average method；5. predicted method is contrasted；6. the first result；7. the second result；8. the 3rd
As a result；9. the first weighted value；10. the second weighted value；11. the 3rd weighted values；12. weighted sum methods；13. tentative prediction results；
14. users access search engine historical record data；15. users access e-commerce website historical record data；16. temperatures become
Gesture value；17. modified results；18. final results.
Specific embodiment
Below in conjunction with the accompanying drawings and specific embodiment the present invention is described in further detail.
As shown in Figure 1, a kind of real-time Method for Sales Forecast method of mobile terminal product, collects target model mobile terminal first
History sales volume data 1, the history sales volume data 2, user of contrast model mobile terminal access search engine historical record data 14
E-commerce website historical record data 15 is accessed with user；Linear regression method 3, autoregression integration moving average method is respectively adopted
4 set up the Method for Sales Forecast model of target model mobile terminal and respectively obtain the first result with three kinds of modes of contrast predicted method 5
6th, the second result 7 and the 3rd result 8；Combining target model mobile terminal history sales volume data 1 and contrast model mobile terminal
History sales volume data 2 are distinguished corresponding first weighted value 9, second that assigns and are weighed to the first result 6, the second result 7 and the 3rd result 8
The weighted value 11 of weight values 10 and the 3rd, then using weighted sum method 12, draws the tentative prediction knot of the mobile terminal product sales volume
Really 13；Search engine historical record data 14 is accessed using the daily user of user and user accesses the history note of e-commerce website
Record data 15, estimate target model mobile terminal in following temperature variation tendency, obtain the heat of the target model mobile terminal
Degree Trend value 16, then carries out modified result 17 to tentative prediction, obtains revised final result 18.
It is as shown in Figure 2 the example that following sales volume is predicted using linear regression method, wherein abscissa is the time, and unit is
Number of days, ordinate is sales volume, and unit is ten thousand；It is as shown in Figure 3 using the autoregression integration following sales volume of moving average method prediction
Example, wherein abscissa be the time, unit is number of days, and ordinate is sales volume, and unit is ten thousand.
The above is only concrete application example of the invention, protection scope of the present invention is not limited in any way.All uses
Equivalents or equivalence replacement and the technical scheme that is formed, all fall within rights protection scope of the present invention.
Claims (4)
1. a kind of real-time Method for Sales Forecast method of mobile terminal product, it is characterised in that comprise the following steps：
Step one：The history sales volume data of target model mobile terminal and contrast model mobile terminal are collected, and user accesses
The historical record data of search engine and e-commerce website；
Step 2：Using the historical data being collected into step one, linear regression method, autoregression integration moving average is respectively adopted
Three kinds of modes of method and contrast predicted method set up the Method for Sales Forecast model of target model mobile terminal；
Step 3：With reference to different forecast models in step 2, a weighted value is assigned respectively to each forecast model, then carry out
Weighted sum is calculated, and draws the tentative prediction result of the mobile terminal product sales volume；
Step 4：It is every using the daily number of times data that target model mobile terminal is searched on e-commerce website of user and user
Day searches for the frequency data of target model mobile terminal on a search engine, estimates target model mobile terminal in following temperature
Variation tendency, the tentative prediction result to being obtained in step 3 is modified, and obtains revised final result.
2. a kind of real-time Method for Sales Forecast method of mobile terminal product according to claim 1, it is characterised in that：The step
The data collected in one include following：
（Ⅰ）The accumulative sales volume of target model mobile terminal in M days in the past is obtained from database, is obtained in units of day, by
The accumulative sales volume of target model mobile terminal untill the same day；
（Ⅱ）For the mobile terminal of target model, find that a kind of brand is identical, sell day than early 1 to two year of current time
Mobile terminal model, the model mobile terminal is obtained from database and sells accumulative sales volume daily in latter N days, wherein numerical value of N
Much larger than numerical value M, for being contrasted；
（Ⅲ）Arranged in the past in M days from web search daily record, Internet user searches on some popular e-commerce websites
The number of times of target model mobile terminal；
（Ⅳ）Arranged in the past in M days from web search daily record, Internet user searches for target model on popular search engine
The number of times of mobile terminal accounts for the ratio of whole searching times.
3. a kind of real-time Method for Sales Forecast method of mobile terminal product according to claim 1, it is characterised in that：The step
Forecast model in two, specifically includes：
Assuming that on the premise of known target model mobile terminal goes over the accumulative sales volume of M days, target is every in predicting X days future
It accumulative sales volume；
Including following three kinds：
Model one：Using the accumulative sales volume of target model mobile terminal in past M days, with the linear regression based on least square method
Method is analyzed, and historical data is fitted and obtains straight line, for representing the connection of daily accumulative sales volume and number of days
System；
Model two：Using the accumulative sales volume of target model mobile terminal in past M days, moving average model is integrated with autoregression,
I.e. ARIMA models, carry out Time-Series analysis, by observing autocorrelogram and partial correlation of the historical data under different rank difference
Figure, determines the parameter of ARIMA models, obtains the matched curve of historical data, then just can further obtain right in following X days
The Method for Sales Forecast answered；
Model three：Accumulative sales volume daily in latter N days is sold using model mobile terminal is contrasted, is obtained and target model is moved eventually
The sales volume at end is estimated.
4. a kind of real-time Method for Sales Forecast method of mobile terminal product according to claim 1, it is characterised in that：The step
Modified result in four, specifically includes：
（Ⅰ）The moving average model search target model mobile terminal on e-commerce website daily to user is integrated with autoregression
Number of times data<D1, T1>, <D2, T2>, <D3, T3>……<DM, TM>Time-Series analysis is carried out, in X days future of prediction
User searches for number of times TM+1, TM+2, TM+3 ... the TM+X of the terminal on e-commerce website；
（Ⅱ）Moving average model being integrated with autoregression, target model mobile terminal is searched on a search engine daily to user
Number of times data<D1, R1>, <D2, R2>, <D3, R3>……<DM, RM>Carry out Time-Series analysis, following X days interior use of prediction
Number of times RM+1, RM+2, RM+3 ... the RM+X of the terminal are searched in family on e-commerce website；
（Ⅲ）Temperature trend of the target model mobile terminal at the X days is calculated using following formula：
Wherein：trendxIt is temperature Trend value, the value has reacted target model mobile terminal near between 0.95~1.05 scope
The general morphologictrend of phase pouplarity；
（Ⅳ）The prediction sales volume of the jth day using following formula to obtaining is modified, and obtains final predicting the outcome：
Wherein：SjIt is step（Three）Predicted the outcome；Sj_finalStep（Four）The final result for obtaining；trendjIt is jth day
Temperature Trend value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611222987.7A CN106779859A (en) | 2016-12-27 | 2016-12-27 | A kind of real-time Method for Sales Forecast method of mobile terminal product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611222987.7A CN106779859A (en) | 2016-12-27 | 2016-12-27 | A kind of real-time Method for Sales Forecast method of mobile terminal product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106779859A true CN106779859A (en) | 2017-05-31 |
Family
ID=58927111
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611222987.7A Pending CN106779859A (en) | 2016-12-27 | 2016-12-27 | A kind of real-time Method for Sales Forecast method of mobile terminal product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106779859A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107346502A (en) * | 2017-08-24 | 2017-11-14 | 四川长虹电器股份有限公司 | A kind of iteration product marketing forecast method based on big data |
| CN108520324A (en) * | 2018-04-13 | 2018-09-11 | 北京京东金融科技控股有限公司 | Method and apparatus for generating information |
| CN108960884A (en) * | 2018-05-02 | 2018-12-07 | 网易无尾熊（杭州）科技有限公司 | Information processing method, model building method and device, medium and calculating equipment |
| CN109034905A (en) * | 2018-08-03 | 2018-12-18 | 四川长虹电器股份有限公司 | The method for promoting sales volume prediction result robustness |
| 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 |
| CN109559138A (en) * | 2017-09-25 | 2019-04-02 | 北京京东尚科信息技术有限公司 | Dodge purchase activity sales volume prediction technique and device, storage medium, electronic equipment |
| CN109961315A (en) * | 2019-01-29 | 2019-07-02 | 河南中烟工业有限责任公司 | A kind of monthly Method for Sales Forecast method of cigarette based on nonlinear combination model |
| CN110033292A (en) * | 2018-01-12 | 2019-07-19 | 北京京东尚科信息技术有限公司 | Information output method and device |
| 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 |
| CN110826949A (en) * | 2018-08-08 | 2020-02-21 | 北京京东振世信息技术有限公司 | Capacity control implementation method and device |
| CN110858346A (en) * | 2018-08-22 | 2020-03-03 | 阿里巴巴集团控股有限公司 | Data processing method, device and machine readable medium |
| CN111210272A (en) * | 2020-01-03 | 2020-05-29 | 北京小米移动软件有限公司 | Method and device for measuring and calculating product sales and storage medium |
| CN111724188A (en) * | 2019-03-22 | 2020-09-29 | 北京沃东天骏信息技术有限公司 | Method, apparatus, device and storage medium for optimizing commodity display position |
| CN111882039A (en) * | 2020-07-28 | 2020-11-03 | 平安科技（深圳）有限公司 | Physical machine sales data prediction method and device, computer equipment and storage medium |
| CN112785229A (en) * | 2021-01-22 | 2021-05-11 | 上海爱钢国际贸易有限公司 | Electronic commerce transaction system for metal materials based on big data |
| CN113554473A (en) * | 2021-08-11 | 2021-10-26 | 上海明略人工智能(集团)有限公司 | Information search amount prediction method and device, electronic equipment and readable storage medium |
| CN114023447A (en) * | 2021-12-06 | 2022-02-08 | 清华大学 | Training method and device for rare patient number prediction model |
| CN116796772A (en) * | 2023-08-25 | 2023-09-22 | 北京思谨科技有限公司 | Intelligent file cabinet control system of dynamic RFID |
Citations (6)
| 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 |
| CN102968670A (en) * | 2012-10-23 | 2013-03-13 | 北京京东世纪贸易有限公司 | Method and device for predicting data |
| CN104123377A (en) * | 2014-07-30 | 2014-10-29 | 福州大学 | Microblog topic popularity prediction system and method |
| CN104700152A (en) * | 2014-10-22 | 2015-06-10 | 浙江中烟工业有限责任公司 | Method for predicting tobacco sales volumes by means of fusing seasonal sales information with search behavior information |
| CN105894113A (en) * | 2016-03-31 | 2016-08-24 | 中国石油天然气股份有限公司规划总院 | Natural gas short-period demand prediction method |
| 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 |
-
2016
- 2016-12-27 CN CN201611222987.7A patent/CN106779859A/en active Pending
Patent Citations (6)
| 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 |
| CN102968670A (en) * | 2012-10-23 | 2013-03-13 | 北京京东世纪贸易有限公司 | Method and device for predicting data |
| CN104123377A (en) * | 2014-07-30 | 2014-10-29 | 福州大学 | Microblog topic popularity prediction system and method |
| CN104700152A (en) * | 2014-10-22 | 2015-06-10 | 浙江中烟工业有限责任公司 | Method for predicting tobacco sales volumes by means of fusing seasonal sales information with search behavior information |
| 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 |
| CN105894113A (en) * | 2016-03-31 | 2016-08-24 | 中国石油天然气股份有限公司规划总院 | Natural gas short-period demand prediction method |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107346502A (en) * | 2017-08-24 | 2017-11-14 | 四川长虹电器股份有限公司 | A kind of iteration product marketing forecast method based on big data |
| CN109559138A (en) * | 2017-09-25 | 2019-04-02 | 北京京东尚科信息技术有限公司 | Dodge purchase activity sales volume prediction technique and device, storage medium, electronic equipment |
| CN110033292B (en) * | 2018-01-12 | 2024-05-17 | 北京京东尚科信息技术有限公司 | Information output method and device |
| CN110033292A (en) * | 2018-01-12 | 2019-07-19 | 北京京东尚科信息技术有限公司 | Information output method and device |
| 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 |
| CN108520324A (en) * | 2018-04-13 | 2018-09-11 | 北京京东金融科技控股有限公司 | Method and apparatus for generating information |
| CN108960884A (en) * | 2018-05-02 | 2018-12-07 | 网易无尾熊（杭州）科技有限公司 | Information processing method, model building method and device, medium and calculating equipment |
| CN109034905A (en) * | 2018-08-03 | 2018-12-18 | 四川长虹电器股份有限公司 | The method for promoting sales volume prediction result robustness |
| CN110826949A (en) * | 2018-08-08 | 2020-02-21 | 北京京东振世信息技术有限公司 | Capacity control implementation method and device |
| CN110858346A (en) * | 2018-08-22 | 2020-03-03 | 阿里巴巴集团控股有限公司 | Data processing method, device and machine readable medium |
| CN110858346B (en) * | 2018-08-22 | 2023-05-02 | 阿里巴巴集团控股有限公司 | Data processing method, apparatus and machine readable medium |
| 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 |
| CN109961315A (en) * | 2019-01-29 | 2019-07-02 | 河南中烟工业有限责任公司 | A kind of monthly Method for Sales Forecast method of cigarette based on nonlinear combination model |
| CN111724188A (en) * | 2019-03-22 | 2020-09-29 | 北京沃东天骏信息技术有限公司 | Method, apparatus, device and storage medium for optimizing commodity display position |
| CN111724188B (en) * | 2019-03-22 | 2024-04-19 | 北京沃东天骏信息技术有限公司 | Method, apparatus, device and storage medium for optimizing commodity display position |
| CN111210272A (en) * | 2020-01-03 | 2020-05-29 | 北京小米移动软件有限公司 | Method and device for measuring and calculating product sales and storage medium |
| CN111210272B (en) * | 2020-01-03 | 2023-08-29 | 北京小米移动软件有限公司 | Product sales measurement method and device and storage medium |
| CN111882039A (en) * | 2020-07-28 | 2020-11-03 | 平安科技（深圳）有限公司 | Physical machine sales data prediction method and device, computer equipment and storage medium |
| CN112785229A (en) * | 2021-01-22 | 2021-05-11 | 上海爱钢国际贸易有限公司 | Electronic commerce transaction system for metal materials based on big data |
| CN113554473A (en) * | 2021-08-11 | 2021-10-26 | 上海明略人工智能(集团)有限公司 | Information search amount prediction method and device, electronic equipment and readable storage medium |
| CN114023447A (en) * | 2021-12-06 | 2022-02-08 | 清华大学 | Training method and device for rare patient number prediction model |
| CN116796772A (en) * | 2023-08-25 | 2023-09-22 | 北京思谨科技有限公司 | Intelligent file cabinet control system of dynamic RFID |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106779859A (en) | A kind of real-time Method for Sales Forecast method of mobile terminal product | |
| Li et al. | Demand prediction and regulation zoning of urban-industrial land: Evidence from Beijing-Tianjin-Hebei Urban Agglomeration, China | |
| CN105260803B (en) | A kind of system power consumption prediction technique | |
| CN109858728B (en) | Load prediction method based on industry-divided electricity utilization characteristic analysis | |
| TWI603273B (en) | Method and device for placing information search | |
| CN101329683A (en) | Recommendation system and method | |
| CN105335524B (en) | A kind of graph search method applied to extensive irregular eutectic data | |
| CN108256093A (en) | A kind of Collaborative Filtering Recommendation Algorithm based on the more interest of user and interests change | |
| CN106875090A (en) | A kind of multirobot distributed task scheduling towards dynamic task distributes forming method | |
| CN109685290A (en) | A kind of electricity demand forecasting method, device and equipment based on deep learning | |
| CN105488216A (en) | Recommendation system and method based on implicit feedback collaborative filtering algorithm | |
| CN101694652A (en) | Network resource personalized recommended method based on ultrafast neural network | |
| CN104239496B (en) | A kind of method of combination fuzzy weighted values similarity measurement and cluster collaborative filtering | |
| CN106096047B (en) | User partition preference calculation method and system based on Information Entropy | |
| CN103309894B (en) | Based on search implementation method and the system of user property | |
| CN103235822B (en) | The generation of database and querying method | |
| CN107305501A (en) | A kind of processing method and system of multithread stream data | |
| CN109492076A (en) | A kind of network-based community's question and answer website answer credible evaluation method | |
| Li et al. | Grey relational decision making model of three-parameter interval grey number based on AHP and DEA | |
| Ramesh et al. | Station-level demand prediction for bike-sharing system | |
| Li et al. | Daily streamflow forecasting based on flow pattern recognition | |
| CN117291655A (en) | Consumer life cycle operation analysis method based on entity and network collaborative mapping | |
| CN104657429B (en) | Technology-driven type Product Innovation Method based on complex network | |
| Onile et al. | A comparative study on graph-based ranking algorithms for consumer-oriented demand side management | |
| CN109583763A (en) | Branch trade custom power load growth feature mining algorithm |
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 |