CN109902859A - Queuing peak period predictor method based on big data and machine learning algorithm - Google Patents
Queuing peak period predictor method based on big data and machine learning algorithm Download PDFInfo
- Publication number
- CN109902859A CN109902859A CN201910076184.2A CN201910076184A CN109902859A CN 109902859 A CN109902859 A CN 109902859A CN 201910076184 A CN201910076184 A CN 201910076184A CN 109902859 A CN109902859 A CN 109902859A
- Authority
- CN
- China
- Prior art keywords
- taking
- data
- time
- machine learning
- learning algorithm
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000010801 machine learning Methods 0.000 title claims abstract description 21
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 19
- 238000012549 training Methods 0.000 claims abstract description 24
- 210000004899 c-terminal region Anatomy 0.000 claims abstract description 8
- 238000003066 decision tree Methods 0.000 claims description 18
- 238000007637 random forest analysis Methods 0.000 claims description 9
- 238000004140 cleaning Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 7
- 238000012935 Averaging Methods 0.000 claims description 4
- 230000002123 temporal effect Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 4
- 239000002699 waste material Substances 0.000 abstract description 4
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Queuing peak period predictor method based on big data and machine learning algorithm, it is related to being lined up peak period pre-estimating technology field.Queuing peak period predictor method based on big data and machine learning algorithm effectively cleans data specifically includes the following steps: based on the practical dining sequence between the adjacent number of taking；In conjunction with machine learning algorithm, model training is carried out to the relationship on waiting time and the number of taking time, the number of taking date etc., obtains the physical relationship between waiting time and these parameters；For the estimated specific number of the taking period of C-terminal user and date parameter, corresponding queue waiting time is estimated；The time point normally done business in the period for whole day is scanned, the relation curve at each of obtain normally doing business in one day in the period number of taking moment and the queue waiting time estimated.After adopting the above technical scheme, the time for reducing user wastes the invention has the benefit that improving the accuracy of estimated time, the dining efficiency of entire catering industry is improved.
Description
Technical field
The present invention relates to be lined up peak period pre-estimating technology field, and in particular to based on big data and machine learning algorithm
It is lined up peak period predictor method.
Background technique
Queuing has dinner and has become the normality in the hot dining room of major business circles, in order to which specification queuing order is generally using according to taking
Number sequence orderly had dinner, while in order to C-terminal user bring preferably be lined up experience, generally indicated on its number of taking list
The table number that front also needs to wait for.With the development of the universal and mobile Internet of smart phone, based on eating under the number of taking line on line
New model become mainstream step by step, user without reach dining room scene can the number of taking on line, and wait table number to close according to current
Reason arranges the stroke of oneself.Based on " a kind of CCP118040081: method and device for estimating dining waiting time " patented technology
The required waiting time can also be calculated, the queuing experience of C-terminal user is further improved.However these applications are all based on
Under the premise of the number of getting list, when at present still cannot the number of taking list when, when can not provide the waiting with reference significance for C-terminal client
Between.For example, do not send out today estimate 11 points of numbers of taking of tomorrow noon need to be lined up how long, can not also know 12 points of tomorrow noon it is rigid
It has dinner well and needs how far ahead of time the number of taking (is had dinner, mainly for big table even this height of box although part dining table is only reserved
End service, this for middle teapoy peak period of having dinner do not support that reservation has dinner when general).In recent years, with big data and
Therefore the high speed development of machine learning algorithm, more and more fields are changed.Currently, in dining queuing field, due to moving
The extensive use of dynamic interconnection, has had accumulated a large amount of latency data, when so that estimating the queuing of future time period on line
Length becomes practical.In order under the premise of not changing existing dining room management mode, meet C-terminal client to certain following a period of time
The quarter number of taking is estimated wait how long, and the following a certain moment have dinner need how far ahead of time the better experience requirements for the number of taking, this hair
Bright scheme proposes a kind of queuing peak period predictor method based on big data and machine learning algorithm.But the prior art with
Regular time length makees simple and crude division to whole day, and simple averaging is done in section at the same time, causes: 1,
Have lost the information of the fluctuation within the same period；2, it is difficult to that " waiting time and the number of taking time Relationship song is accurately positioned
Turning point in line "；3, mutually indepedent between the two neighboring period, have lost the correlation between certain time adjacent segments
Property；4, without efficiently using the features such as different seasons in month.It is larger to eventually lead to the error that the waiting time is estimated, and stability compared with
It is low.
Summary of the invention
In view of the defects and deficiencies of the prior art, the present invention intends to provide one kind to be based on big data and machine learning
The queuing peak period predictor method of algorithm, improves the accuracy of estimated time, and user is more reasonably arranged certainly
Oneself stroke, and then the time waste of user is reduced, help to improve the dining efficiency of entire catering industry.
To achieve the above object, the present invention is using following technical scheme: the row based on big data and machine learning algorithm
Team peak period predictor method specifically includes the following steps: one, based between the adjacent number of taking practical dining sequence, to data into
Row effectively cleaning；Two, based on the historical data after cleaning, in conjunction with machine learning algorithm, to waiting time and the number of taking time, the number of taking
The relationship on date (what day, several months, if festivals or holidays) etc. carries out model training, obtains between waiting time and these parameters
Physical relationship, and save as prediction model；Three, it is based on prediction model, for the estimated specific number of the taking period of C-terminal user and date
Parameter estimates corresponding queue waiting time；Four, the time point normally done business in the period for whole day is scanned, and obtains one
It each of normally does business in the period in it relation curve at the number of taking moment and the queue waiting time estimated；Five, it is based on step
Four obtained curves, the following a certain moment number of taking of prediction is estimated wait how long, and needs of having dinner of the following a certain moment shift to an earlier date
How long the number of taking.
In the step one to data it is effective cleaning specifically include following method: one, based on the waiting time be T1 into
The training of row prediction model, rather than the original record of waiting time (T1+T2)；If two, historgraphic data recording is not marked on line
Remember the T1 corresponding time, but only have recorded T1+T2 total time, such historical data should be dropped, and be not involved in prediction model instruction
Practice.
Prediction model in the step three specifically includes following principle: one, determining that the feature for training pattern becomes
Amount and target variable；Two, based on random forest (Random Forest) regression model to the pass between (X1, X2, X3, X4) and Y
System is fitted；Three, it is tested based on performance of the test set data to prediction model.
Characteristic variable in the principle one is four temporal characteristics of user's number of taking: several points, what day, several months
Whether festivals or holidays.
The fitting specifically includes following procedure: one, based on put back to rule from training data concentration randomly select one
Fixed training data, and (X1, X2, X3, X4) randomly selects a feature combination, such as (X1, X2, X4) from characteristic set,
A sub- training set is collectively formed；Two, the sub- training set extracted based on (a), establishes a decision tree (Decision Tree)
Regression model Ti；Three, (a) (b) process n times are repeated, N number of decision tree regression model T1:N is generated；It four, will in data to be predicted
All features (X1, X2, X3, X4) of test data are input to T1:N, are averaging to the output of N number of decision tree regression model, and
It is exported the average value as prediction result.
After adopting the above technical scheme, the invention has the following beneficial effects: the accuracy of estimated time is improved, so that user can be with
The stroke of oneself is more reasonably arranged, and then reduces the time waste of user, helps to improve the dining of entire catering industry
Efficiency.
Specific embodiment
Present embodiment the technical solution adopted is that: the queuing peak period based on big data and machine learning algorithm
Predictor method specifically includes the following steps: one, based between the adjacent number of taking practical dining sequence, data are effectively cleaned
(with reference to the patent " CCP118040081, a kind of method and device for estimating dining waiting time " having been filed on)；Two, based on cleaning
Historical data afterwards, in conjunction with machine learning algorithm, to waiting time and the number of taking time, the number of the taking date (what day, several months, if
Festivals or holidays) etc. relationship carry out model training, obtain the physical relationship between waiting time and these parameters, and save as and estimate
Model；Three, it is based on prediction model, for the estimated specific number of the taking period of C-terminal user and date parameter, estimates corresponding queuing etc.
To the time；Four, the time point normally done business in the period for whole day is scanned, and obtains normally doing business in one day every in the period
The relation curve at a number of taking moment and the queue waiting time estimated；Five, it is based on the obtained curve of step 4, predicts future
The a certain moment number of taking is estimated wait how long, and the following a certain moment have dinner need how far ahead of time the number of taking.
In the step one to data it is effective cleaning specifically include following method: one, based on the waiting time be T1 into
The training of row prediction model, rather than the original record of waiting time (T1+T2)；If two, historgraphic data recording is not marked on line
Remember the T1 corresponding time, but only have recorded T1+T2 total time, such historical data should be dropped, and be not involved in prediction model instruction
Practice.The time be lined up have dinner in existed number after dining situation again, for example, user's U number of taking is An, after waiting time T1, dining room
No. An is called, but a number situation had occurred not in dining room in user U at that time.Then user U does not cancel and having dinner, but in mistake again
It has dinner again after time T2.Therefore, on line in data record, the user U practical waiting time is T1+T2, but therein
Time T2 is partly due to that the reason of user U oneself causes, and is not due to be lined up required objective time itself, the time is lined up
The required time is T1.So on line record waiting time T1+T2 disturb to the training of prediction model, need into
Row cleaning.
Prediction model in the step three specifically includes following principle: one, determining that the feature for training pattern becomes
Amount and target variable；The above training is a kind of table type based on a specific dining room, such as: the teapoy of western Bei Zhongshangongyuandian.
If all queuings (teapoy, middle table and big table etc.) to the dining room Duo Jia are estimated, need to the every of wherein each dining room
A kind of table type is individually trained.In feature what day and be all made of within several months one-hot encoding (one-hot) coding mode.Two, it is based on
Random forest (Random Forest) regression model is fitted the relationship between (X1, X2, X3, X4) and Y；Three, based on survey
Examination collection data test the performance of prediction model.Based on the characteristic variable in test set data { Y:(X1, X2, X3, X4) }
(X1, X2, X3, X4) calculates corresponding queuing time discreet value according to the random forest regression model T1:N 2) trained
YHAT, according to the error between YHAT and Y: sum (Y-YHAT) 2, as the performance indicator of prediction model H, error is smaller, says
Bright model H performance is better, by continuous adjusting and optimizing model parameter N, maximum decision tree depth and minimum extraction feature quantity
Deng so that minimizing the error between YHAT and Y.
Random forest establishes multiple decision trees, and by bagging technology is merged them more quasi- to obtain
True and stable prediction.The big advantage of the one of random forest is that it can be not only used for classifying, it can also be used to which regression problem, these two types are asked
Topic constitutes just to be faced required for current most of machine learning systems.
One-hot coding, that is, One-Hot coding, also known as an efficient coding, method are come using N bit status register
N number of state is encoded, each state has its independent register-bit, and when any, wherein only one has
Effect.Such as encode to six states: natural order code is 000,001,010,011,100,101；One-hot coding is then:
000001,000010,000100,001000,010000,100000。
Characteristic variable in the principle one is four temporal characteristics of user's number of taking: several points, what day, several months
Whether festivals or holidays.
The fitting specifically includes following procedure: one, based on put back to rule from training data concentration randomly select one
Fixed training data, and (X1, X2, X3, X4) randomly selects a feature combination, such as (X1, X2, X4) from characteristic set,
A sub- training set is collectively formed；Two, the sub- training set extracted based on (a), establishes a decision tree (Decision Tree)
Regression model Ti；Three, (a) (b) process n times are repeated, N number of decision tree regression model T1:N is generated；It four, will in data to be predicted
All features (X1, X2, X3, X4) of test data are input to T1:N, are averaging to the output of N number of decision tree regression model, and
It is exported the average value as prediction result.
Decision tree be it is known it is various happen probability on the basis of, seek phase of net present value (NPV) by constituting decision tree
Prestige value is more than or equal to zero probability, and assessment item risk judges the method for decision analysis of its feasibility, is intuitively with probability point
A kind of graphical method of analysis.Since this decision branch is drawn as figure like the limb of one tree, therefore claim decision tree.In machine learning
In, decision tree is a prediction model, and what he represented is a kind of mapping relations between object properties and object value.
After adopting the above technical scheme, the invention has the following beneficial effects: the accuracy of estimated time is improved, so that user can be with
The stroke of oneself is more reasonably arranged, and then reduces the time waste of user, helps to improve the dining of entire catering industry
Efficiency.
The above is only used to illustrate the technical scheme of the present invention and not to limit it, and those of ordinary skill in the art are to this hair
The other modifications or equivalent replacement that bright technical solution is made, as long as it does not depart from the spirit and scope of the technical scheme of the present invention,
It is intended to be within the scope of the claims of the invention.
Claims (5)
1. the queuing peak period predictor method based on big data and machine learning algorithm, it is characterised in that: it specifically include with
Lower step: one, based on practical dining sequence adjacent take number between, data are effectively cleaned；Two, based on going through after cleaning
History data, in conjunction with machine learning algorithm, to waiting time and the number of taking time, the number of taking date (what day, several months, if festivals or holidays)
Deng relationship carry out model training, obtain the physical relationship between waiting time and these parameters, and save as prediction model；
Three, it is based on prediction model, for the estimated specific number of the taking period of C-terminal user and date parameter, when estimating corresponding wait in line
Between；Four, the time point normally done business in the period for whole day is scanned, and each of obtaining normally doing business in one day in the period taking
The relation curve at number moment and the queue waiting time estimated；Five, it is based on the obtained curve of step 4, prediction is following a certain
The moment number of taking is estimated wait how long, and the following a certain moment have dinner need how far ahead of time the number of taking.
2. the queuing peak period predictor method according to claim 1 based on big data and machine learning algorithm,
Be characterized in that: in the step one to data it is effective cleaning specifically include following method: one, based on the waiting time be T1 into
The training of row prediction model, rather than the original record of waiting time (T1+T2)；If two, historgraphic data recording is not marked on line
Remember the T1 corresponding time, but only have recorded T1+T2 total time, such historical data should be dropped, and be not involved in prediction model instruction
Practice.
3. the queuing peak period predictor method according to claim 1 based on big data and machine learning algorithm,
Be characterized in that: the prediction model in the step three specifically includes following principle: one, determining that the feature for training pattern becomes
Amount and target variable；Two, based on random forest (Random Forest) regression model to the pass between (X1, X2, X3, X4) and Y
System is fitted；Three, it is tested based on performance of the test set data to prediction model.
4. the queuing peak period predictor method according to claim 3 based on big data and machine learning algorithm,
Be characterized in that: characteristic variable in the principle one is four temporal characteristics of user's number of taking: several points, what day, it is several
Month and whether festivals or holidays.
5. the queuing peak period predictor method according to claim 3 based on big data and machine learning algorithm,
Be characterized in that: the fitting specifically includes following procedure: one, based on put back to rule from training data concentration randomly select one
Fixed training data, and (X1, X2, X3, X4) randomly selects a feature combination, such as (X1, X2, X4) from characteristic set,
A sub- training set is collectively formed；Two, the sub- training set extracted based on (a), establishes a decision tree (Decision Tree)
Regression model Ti；Three, (a) (b) process n times are repeated, N number of decision tree regression model T1:N is generated；It four, will in data to be predicted
All features (X1, X2, X3, X4) of test data are input to T1:N, are averaging to the output of N number of decision tree regression model, and
It is exported the average value as prediction result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910076184.2A CN109902859B (en) | 2019-01-26 | 2019-01-26 | Queuing peak period estimation method based on big data and machine learning algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910076184.2A CN109902859B (en) | 2019-01-26 | 2019-01-26 | Queuing peak period estimation method based on big data and machine learning algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109902859A true CN109902859A (en) | 2019-06-18 |
| CN109902859B CN109902859B (en) | 2023-03-24 |
Family
ID=66944272
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910076184.2A Active CN109902859B (en) | 2019-01-26 | 2019-01-26 | Queuing peak period estimation method based on big data and machine learning algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109902859B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110490356A (en) * | 2019-07-02 | 2019-11-22 | 北京星选科技有限公司 | Interface display method, device, electronic equipment |
| CN110490357A (en) * | 2019-07-02 | 2019-11-22 | 北京星选科技有限公司 | Confirmation method, device, server, the electronic equipment of waiting time |
| CN111062749A (en) * | 2019-12-12 | 2020-04-24 | 北京爱奇艺科技有限公司 | Growth amount estimation method, growth amount estimation device, electronic apparatus, and storage medium |
| CN112633567A (en) * | 2020-12-16 | 2021-04-09 | 深圳前海微众银行股份有限公司 | Method and device for predicting waiting duration and storage medium |
| CN113592183A (en) * | 2021-08-05 | 2021-11-02 | 杭州企智互联科技有限公司 | Dining peak prediction method and device |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101110136A (en) * | 2007-04-24 | 2008-01-23 | 暨南大学 | Intelligent queuing system |
| CN101739745A (en) * | 2009-12-01 | 2010-06-16 | 中国建设银行股份有限公司 | Queuing processing device and processing method thereof and queuing machine |
| CN103985186A (en) * | 2014-05-28 | 2014-08-13 | 南京亿栋信息科技有限公司 | Waiting time predicting method for queuing machine |
| CN107169891A (en) * | 2017-07-13 | 2017-09-15 | 成都人人互动网络科技有限公司 | It is a kind of to reduce client and order the method for stand-by period |
| CN107392334A (en) * | 2017-07-13 | 2017-11-24 | 成都人人互动网络科技有限公司 | One kind row number meal ordering system |
| CN107767521A (en) * | 2017-09-30 | 2018-03-06 | 深圳春沐源控股有限公司 | Dining room queuing number-taking method and system |
| CN107832884A (en) * | 2017-11-06 | 2018-03-23 | 北京戴纳实验科技有限公司 | A kind of method for recommending time for eating meals |
| CN107943861A (en) * | 2017-11-09 | 2018-04-20 | 北京众荟信息技术股份有限公司 | A kind of missing data compensation process and system based on time series |
| CN108230527A (en) * | 2017-12-29 | 2018-06-29 | 深圳市爱号网络科技有限公司 | A kind of novel intelligent cloud is lined up measuring and calculating and the method and system of automatic shunt |
| JP2018185591A (en) * | 2017-04-24 | 2018-11-22 | 清水建設株式会社 | Demand predicting system and demand predicting method |
-
2019
- 2019-01-26 CN CN201910076184.2A patent/CN109902859B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101110136A (en) * | 2007-04-24 | 2008-01-23 | 暨南大学 | Intelligent queuing system |
| CN101739745A (en) * | 2009-12-01 | 2010-06-16 | 中国建设银行股份有限公司 | Queuing processing device and processing method thereof and queuing machine |
| CN103985186A (en) * | 2014-05-28 | 2014-08-13 | 南京亿栋信息科技有限公司 | Waiting time predicting method for queuing machine |
| JP2018185591A (en) * | 2017-04-24 | 2018-11-22 | 清水建設株式会社 | Demand predicting system and demand predicting method |
| CN107169891A (en) * | 2017-07-13 | 2017-09-15 | 成都人人互动网络科技有限公司 | It is a kind of to reduce client and order the method for stand-by period |
| CN107392334A (en) * | 2017-07-13 | 2017-11-24 | 成都人人互动网络科技有限公司 | One kind row number meal ordering system |
| CN107767521A (en) * | 2017-09-30 | 2018-03-06 | 深圳春沐源控股有限公司 | Dining room queuing number-taking method and system |
| CN107832884A (en) * | 2017-11-06 | 2018-03-23 | 北京戴纳实验科技有限公司 | A kind of method for recommending time for eating meals |
| CN107943861A (en) * | 2017-11-09 | 2018-04-20 | 北京众荟信息技术股份有限公司 | A kind of missing data compensation process and system based on time series |
| CN108230527A (en) * | 2017-12-29 | 2018-06-29 | 深圳市爱号网络科技有限公司 | A kind of novel intelligent cloud is lined up measuring and calculating and the method and system of automatic shunt |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110490356A (en) * | 2019-07-02 | 2019-11-22 | 北京星选科技有限公司 | Interface display method, device, electronic equipment |
| CN110490357A (en) * | 2019-07-02 | 2019-11-22 | 北京星选科技有限公司 | Confirmation method, device, server, the electronic equipment of waiting time |
| CN111062749A (en) * | 2019-12-12 | 2020-04-24 | 北京爱奇艺科技有限公司 | Growth amount estimation method, growth amount estimation device, electronic apparatus, and storage medium |
| CN112633567A (en) * | 2020-12-16 | 2021-04-09 | 深圳前海微众银行股份有限公司 | Method and device for predicting waiting duration and storage medium |
| CN113592183A (en) * | 2021-08-05 | 2021-11-02 | 杭州企智互联科技有限公司 | Dining peak prediction method and device |
| CN113592183B (en) * | 2021-08-05 | 2022-04-19 | 杭州企智互联科技有限公司 | Dining peak prediction method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109902859B (en) | 2023-03-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109902859A (en) | Queuing peak period predictor method based on big data and machine learning algorithm | |
| CN106549772B (en) | Resource prediction method, system and capacity management device | |
| CN106020715B (en) | Storage pool capacity management | |
| EP3804226A1 (en) | Telecommunications network traffic metrics evaluation and prediction | |
| CN106777703A (en) | A kind of bus passenger real-time analyzer and its construction method | |
| CN107220263B (en) | Optimization method, evaluation method, processing method and device for data migration | |
| CN109993428A (en) | Resource allocation methods and device | |
| CN107193967A (en) | A kind of multi-source heterogeneous industry field big data handles full link solution | |
| CN105960790B (en) | Method for cache | |
| CN103150245B (en) | Determine method and the storage controller of the access characteristics of data entity | |
| CN110245782A (en) | Prediction model training method, device and equipment | |
| KR101435096B1 (en) | Apparatus and method for prediction of merchandise demand using social network service data | |
| CN109376218B (en) | Thesis influence assessment method based on cascade | |
| Zhou et al. | Key time steps selection for large‐scale time‐varying volume datasets using an information‐theoretic storyboard | |
| CN108470261A (en) | Ordering method and device | |
| CN113469462B (en) | Order heat prediction and order allocation method and equipment | |
| CN113420165B (en) | Training of classification model and classification method and device of multimedia data | |
| TWI662809B (en) | Obstacle location system and maintenance method for image streaming service | |
| KR20220052200A (en) | Machine learning based load prrdiction model cmparative verification system and mthod | |
| CN112954066A (en) | Information pushing method and device, electronic equipment and readable storage medium | |
| CN111861397A (en) | Intelligent scheduling platform for client visit | |
| KR20140146437A (en) | Apparatus and method for forecasting business performance based on patent information | |
| CN114520773A (en) | Service request response method, device, server and storage medium | |
| CN110517009A (en) | Real-time common layer building method, device and server | |
| CN106897728B (en) | Sample selection method, device and system based on business monitoring system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231214 Address after: 200331, Room 515, No. 788 Zhenbei Road, Putuo District, Shanghai Patentee after: Meizhiwei (Shanghai) Information Technology Co.,Ltd. Address before: 200120 Room 302, Building 88, Lane 887, Zuchongzhi Road, Free Trade Experimental Zone, Pudong New Area, Shanghai Patentee before: DELICIOUS NOWAIT (SHANGHAI) INFORMATION TECHNOLOGY CO.,LTD. |