CN108629627A - A kind of automatic dispensing control method of moving advertising - Google Patents
A kind of automatic dispensing control method of moving advertising Download PDFInfo
- Publication number
- CN108629627A CN108629627A CN201810429774.4A CN201810429774A CN108629627A CN 108629627 A CN108629627 A CN 108629627A CN 201810429774 A CN201810429774 A CN 201810429774A CN 108629627 A CN108629627 A CN 108629627A
- Authority
- CN
- China
- Prior art keywords
- data
- advertisement
- prioritization scheme
- module
- moving advertising
- 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
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
- G06Q30/0244—Optimization
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0273—Determination of fees for advertising
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0273—Determination of fees for advertising
- G06Q30/0275—Auctions
Abstract
The invention belongs to the technical fields that moving advertising is launched, and in particular to a kind of automatic dispensing control method of moving advertising；The technical issues of solution is：There is provided a kind of the degree of automation it is higher, launch the higher moving advertising of efficiency automatic dispensing control method；The technical solution used for：A kind of automatic dispensing control method of moving advertising, including：S10, the advertisement for obtaining multiple platforms are launched data and are stored；S20, sub-module load configuration data；S30 obtains current dispensing ad data；S40, the history for calculating same type advertisement launch data, obtain prioritization scheme；S50 executes prioritization scheme.
Description
Technical field
The invention belongs to the technical fields that moving advertising is launched, and in particular to a kind of automatic dispensing controlling party of moving advertising
Method.
Background technology
With the continuous development of mobile Internet, moving advertising is increasingly becoming the advertisement form of mainstream；Moving advertising is logical
It crosses mobile device and accesses the advertisement shown when mobile application or mobile webpage.
The putting person of moving advertising would generally use foundation, dispensing and the management of the progress advertisement of advertisement delivery tool, still
At present due to being that control is launched in artificial progress advertisement, there are the odjective causes such as the time difference, network and human operational error, strategy to judge
The problems such as error, causes advertisement to fail to reach good dispensing effect.
It is wide to solve accurately carry out how therefore, it is necessary to introduce the technical solution of automation and sequencing
The problem of accusing control and launching decision.
Invention content
The present invention overcomes the shortcomings of the prior art, technical problem to be solved to be：A kind of the degree of automation is provided
Automatic dispensing control method that is higher, launching the higher moving advertising of efficiency.
In order to solve the above-mentioned technical problem, the technical solution adopted by the present invention is：
A kind of automatic dispensing control method of moving advertising, including：S10, the advertisement for obtaining multiple platforms launch data simultaneously
Storage；S20, sub-module load configuration data；S30 obtains current dispensing ad data；S40 calculates the history of same type advertisement
Data are launched, prioritization scheme is obtained；S50 executes prioritization scheme.
Preferably, the history impression information for calculating same type advertisement, including：It filters out and currently launches ad data
Data are launched in similar history advertisement；Calculating benchmark data behavior；Feature Selection is carried out to historical data variable；It is calculated by mapping
Method and screening model obtain auxiliary prioritization scheme.
Preferably, the analysis obtains in prioritization scheme：The prioritization scheme includes：The parameter of bidding of regulation and control advertisement,
Magnitude parameter, budget parameters, waiting parameter and audience.
Correspondingly, the automatic putting control system of a kind of moving advertising, including：Acquisition module, for obtaining multiple platforms
Advertisement launch and data and store；Load-on module loads configuration data for sub-module；Acquisition module, for obtaining current throwing
Put ad data；Computing module, the history for calculating same type advertisement launch data, obtain prioritization scheme；Execution module is used
In execution prioritization scheme.
Preferably, the computing module includes：Preliminary screening module, it is similar to ad data is currently launched for filtering out
History advertisement launch data；Benchmark behavior computing module is used for calculating benchmark data behavior；Feature Selection module, for pair
Historical data variable carries out Feature Selection；Prioritization scheme computing module, for by mapping algorithm and screening model, being optimized
Scheme.
Preferably, in the analysis module：The prioritization scheme includes：The parameter of bidding of regulation and control advertisement, magnitude parameter,
Budget parameters, waiting parameter and audience.
The present invention has the advantages that compared with prior art：
A kind of automatic dispensing control method of moving advertising of the present invention, realizes the key link in advertisement release process
The automation control management of (such as advertisement start and stop, advertisement intelligent bid, dynamic control advertising budget) and optimization, solve due to when
Difference, network, artificial adjustment error etc. control error caused by reasons, make the dispensing of moving advertising and management from pure manual control to
The transition of automation greatly improves the efficiency of advertising management.
Description of the drawings
The present invention will be further described in detail below in conjunction with the accompanying drawings；
Fig. 1 is a kind of automatic flow diagram for launching control method for moving advertising that the embodiment of the present invention one provides；
Fig. 2 is a kind of structural schematic diagram of the automatic putting control system for moving advertising that the embodiment of the present invention one provides；
Fig. 3 is a kind of structural schematic diagram of the automatic putting control system of moving advertising provided by Embodiment 2 of the present invention；
In figure：10 be acquisition module, and 20 be load-on module, and 30 be acquisition module, and 40 be computing module, and 50 be analysis mould
Block, 60 be execution module；
401 be preliminary screening module, behavior computing module on the basis of 402, and 403 are characterized screening module, and 404 be optimization side
Case computing module.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments；Based on the embodiments of the present invention, ordinary skill people
The every other embodiment that member is obtained without creative efforts, shall fall within the protection scope of the present invention.
Fig. 1 is a kind of automatic flow diagram for launching control method for moving advertising that the embodiment of the present invention one provides；
As shown in Figure 1, a kind of automatic dispensing control method of moving advertising, including：Data are launched in S10, the advertisement for obtaining multiple platforms
And it stores；S20, sub-module load configuration data；S30 obtains current dispensing ad data；S40 calculates going through for same type advertisement
History launches data；S50 is analyzed and is obtained prioritization scheme；S60 executes prioritization scheme；In the present invention, added by different modules
Different configuration datas is carried, the history that can be used for calculating same type advertisement launches data.
Specifically, the history impression information for calculating same type advertisement, including：It filters out and currently launches ad data
Data are launched in similar history advertisement；Calculating benchmark data behavior；Feature Selection is carried out to historical data variable；It is calculated by mapping
Method and screening model obtain auxiliary prioritization scheme；In the present embodiment, described filtering out is similar with ad data is currently launched
Data are launched in history advertisement, can be screened by collaborative filtering module；In the present embodiment, the collaborative filtering module can
For：
The current similarity launched between ad data and history advertisement dispensing data is calculated with cosine similarity formula, is led to
Cosine similarity is crossed to be screened：Its cosine calculating formula of similarity is：If N (u) is the current set for launching ad data, N
(v) set of data is launched for history advertisement；It preselects similarity formula：
It is described by mapping algorithm and screening model, obtain in auxiliary prioritization scheme, the screening model can be linear
Recurrence, Stochastic Decision-making forest, deep-neural-network, own coding machine are composed.
Wherein：It is returned using Stochastic Decision-making forest, which is calculated the prediction optimal solution for launching parameter,
Its detailed process is as follows
1, as follows using the modeling process of random forest：
(1) random forest is made of more decision trees；If the quantity of the decision tree used is t, each node makes
The feature quantity used is f；If given test data set is combined into S, intrinsic dimensionality F；End condition is：Minimum sample on node
Number；The 1-t is set, i=1-t：
(2) from there is data set S (i) of the extraction size put back to as S in S, as the sample of root node, from root node
Start to train；
(3) if reaching end condition on present node, it is leaf node that present node, which is arranged, and prediction output is current
The average value of each sample value of node sample set then proceedes to train other nodes；If present node does not reach termination item
Part then randomly selects f dimensional features from F dimensional features without what is put back to；Using this f dimensional feature, best one-dimensional of classifying quality is found
Feature k and its threshold value th, sample of the sample kth dimensional feature less than th is divided into left sibling on present node, remaining is drawn
Assign to right node；Continue to train other nodes.
(4) (2) (3) are repeated until leaf node is all trained or be marked as to all nodes；
(5) (2) are repeated, (3), (4) were all trained to until all decision trees.
2, as follows using the prediction process of random forest：
The 1-t is set, i=1-t：
(1) since the root node of present tree, according to the threshold value th of present node, judgement be enter left sibling (<Th) also
Be enter right node (>=th), until reaching, some leaf node, and export predicted value.
(2) (1) is repeated until all t trees all output predicted value, for regression model, predicted value, that is, all trees
Output average value.
(3) using formula argmax (Var-VarLeft-VarRight) prosthomere is worked as to the judgment criteria of prediction result
The variance Var of point training set subtracts the variance VarLeft of left child node and the variance VarRight value maximums of right child node.
Before data are calculated by regression model, needs to carry out Feature Conversion to the data of input, i.e., first compile data
Code is another form, then carries out a series of operations on this basis.It finally needs to utilize self-editing ink recorder, by the number after coding
Initial data is reverted to according to by decoding, and can preferably retain the main feature of initial data.Self-editing ink recorder is by three layers
Neural network forms,
(1) original input signal is set as x, and s is nonlinear function, and W is weight matrix, and b is deviation value；X passes through first layer
Input layer reaches second layer middle layer, and signal becomes y；Wherein：Y=s (Wx+b)；
(2) y reaches second layer middle layer by first layer input layer, and signal becomes z.W ' is the transposition of W：W '=WT；Its
In：Z=s (W ' y+b ')；
(3) adjust s parameter, make the z and the signal x being originally inputted of final output as possible approach.Utilize square error
Formula calculates error amount：L (xz)=| | x-z | |2。
Further, described to analyze and obtain in prioritization scheme, it can be by assisting process control more and being based on state machine pattern
Module carry out analysis calculating.
When launching the rule control of data setting automation to advertisement, there are the same times to have multiple rules to be performed simultaneously
The case where.We realize the parallel processing of multiple processor active tasks of same time using more association's process controls.Multiple conditions are controlled
The case where same advertisement is launched, it is possible that a variety of operation intermediate state.So system designs adoption status machine pattern, can
It reduces system structure caused by the increase due to state and changes cost, i.e., when receiving new input value every time, it is only necessary to hand over
It goes to handle to current state, chain processing is carried out without a series of states before dependence.
Further, the analysis obtains in prioritization scheme；The prioritization scheme includes：The ginseng of bidding of regulation and control advertisement
Number, magnitude parameter, budget parameters, waiting parameter and audience.
A kind of automatic dispensing control method of moving advertising of the present invention, realizes the key link in advertisement release process
The automation control management of (such as advertisement start and stop, advertisement intelligent bid, dynamic control advertising budget) and optimization, solve due to when
Difference, network, artificial adjustment error etc. control error caused by reasons, make the dispensing of moving advertising and management from pure manual control to
The transition of automation greatly improves the efficiency of advertising management.
The automatic trustship advertisement start and stop of system and adjustment budget are realized through the invention, are saved advertiser and are put into effect management
90% or more time, advertising input output ratio are up to 50% (generally 30%), improve advertisement dispensing whole efficiency and reach
85%.
Fig. 2 is a kind of structural schematic diagram of the automatic putting control system for moving advertising that the embodiment of the present invention one provides,
As shown in Fig. 2, a kind of automatic putting control system of moving advertising, including：Acquisition module 10, for obtaining the wide of multiple platforms
It accuses and launches data and store；Load-on module 20 loads configuration data for sub-module；Acquisition module 30, for obtaining current throwing
Put ad data；Computing module 40, the history for calculating same type advertisement launch data；Analysis module 50, for analyzing simultaneously
Obtain prioritization scheme；Execution module 60, for executing prioritization scheme.
Fig. 3 is a kind of structural schematic diagram of the automatic putting control system of moving advertising provided by Embodiment 2 of the present invention,
As shown in figure 3, on the basis of embodiment one, the computing module 40 includes：Preliminary screening module 401, for filter out with
It is current to launch the similar history advertisement dispensing data of ad data；Benchmark behavior computing module 402 is used for calculating benchmark data line
For；Feature Selection module 403, for carrying out Feature Selection to historical data variable；Prioritization scheme computing module 404, for leading to
Mapping algorithm and screening model are crossed, auxiliary prioritization scheme is obtained.
Specifically, in the analysis module 50：The prioritization scheme includes：Parameter of bidding, the magnitude ginseng of regulation and control advertisement
Number, budget parameters, waiting parameter and audience.
The present invention, can be (logical to the particular advertisement stereotactic conditions of different advertisement types according to the account of the history for launching advertisement
Cross calculating benchmark data behavior acquisition) result estimate is made, to recommend optimal advertisement dropping apparatus, while the system meeting
The impression information and effect data for extracting advertisement, realize the comprehensive descision decision of a variety of policy conditions.
When the effect of some advertisement reaches the specified specified conditions of configuration, the setting that will be set out under conditions present is grasped
Make, such as increase and launch budget, increase advertisement bid, pause advertisement etc. passes through continuous adjusting and optimizing scheme (tactful condition threshold
Value), verify the correctness of advertising strategy so that system configuration can be selected with the dispensing of The Gift of Being the Best You Can Be, realize that advertisement is launched complete
Whole Process.
Finally it should be noted that：The above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Present invention has been described in detail with reference to the aforementioned embodiments for pipe, it will be understood by those of ordinary skill in the art that：Its according to
So can with technical scheme described in the above embodiments is modified, either to which part or all technical features into
Row equivalent replacement；And these modifications or replacements, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (6)
1. a kind of automatic dispensing control method of moving advertising, it is characterised in that：Including：
S10, the advertisement for obtaining multiple platforms are launched data and are stored；
S20, sub-module load configuration data；
S30 obtains current dispensing ad data；
S40, the history for calculating same type advertisement launch data, obtain prioritization scheme；
S50 executes prioritization scheme.
2. a kind of automatic dispensing control method of moving advertising according to claim 1, it is characterised in that：It is described to calculate together
The history impression information of type advertisements, including：
It filters out history advertisement similar with ad data is currently launched and launches data；
Calculating benchmark data behavior；
Feature Selection is carried out to historical data variable；
By mapping algorithm and screening model, auxiliary prioritization scheme is obtained.
3. a kind of automatic dispensing control method of moving advertising according to claim 1, it is characterised in that：It is described to analyze
Into prioritization scheme；
The prioritization scheme includes：Parameter of bidding, magnitude parameter, budget parameters, waiting parameter and the audient group of regulation and control advertisement
Body.
4. a kind of automatic putting control system of moving advertising, it is characterised in that：Including：
Acquisition module (10), the advertisement for obtaining multiple platforms are launched data and are stored；
Load-on module (20) loads configuration data for sub-module；
Acquisition module (30), for obtaining current dispensing ad data；
Computing module (40), the history for calculating same type advertisement launch data, obtain prioritization scheme；
Execution module (50), for executing prioritization scheme.
5. a kind of automatic putting control system of moving advertising according to claim 4, it is characterised in that：The calculating mould
Block (40) includes：
Preliminary screening module (401) launches data for filtering out history advertisement similar with ad data is currently launched；
Benchmark behavior computing module (402) is used for calculating benchmark data behavior；
Feature Selection module (403), for carrying out Feature Selection to historical data variable；
Prioritization scheme computing module (404), for by mapping algorithm and screening model, obtaining prioritization scheme.
6. a kind of automatic putting control system of moving advertising according to claim 4, it is characterised in that：The analysis mould
In block (50)：
The prioritization scheme includes：Parameter of bidding, magnitude parameter, budget parameters, waiting parameter and the audient group of regulation and control advertisement
Body.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810429774.4A CN108629627A (en) | 2018-05-08 | 2018-05-08 | A kind of automatic dispensing control method of moving advertising |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810429774.4A CN108629627A (en) | 2018-05-08 | 2018-05-08 | A kind of automatic dispensing control method of moving advertising |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108629627A true CN108629627A (en) | 2018-10-09 |
Family
ID=63695815
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810429774.4A Pending CN108629627A (en) | 2018-05-08 | 2018-05-08 | A kind of automatic dispensing control method of moving advertising |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108629627A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636488A (en) * | 2019-01-17 | 2019-04-16 | 珠海天燕科技有限公司 | Advertisement placement method and device |
| CN111178960A (en) * | 2019-12-26 | 2020-05-19 | 浙江致梦大数据有限公司 | Advertisement resource integration platform |
| CN112396471A (en) * | 2020-12-10 | 2021-02-23 | 杭州次元岛科技有限公司 | Advertisement putting optimization method and device based on big data |
| CN112749997A (en) * | 2018-10-11 | 2021-05-04 | 广东聚宝屋传媒有限公司 | Express package-based advertisement delivery management method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102665118A (en) * | 2012-05-15 | 2012-09-12 | 合一网络技术(北京)有限公司 | Method and system for controlling releasing frequency and priority of network video advertisement |
| CN104299151A (en) * | 2014-09-28 | 2015-01-21 | 新浪网技术(中国)有限公司 | Online advertising flow distribution system and method |
| CN105741133A (en) * | 2016-01-26 | 2016-07-06 | 电子科技大学 | Stepping management method for online advertisement delivery |
| CN106412644A (en) * | 2016-09-19 | 2017-02-15 | 北京喂呦科技有限公司 | Accurate advertising method and system based on smart TV player |
| CN107153970A (en) * | 2017-04-24 | 2017-09-12 | 郑州埃文计算机科技有限公司 | A kind of bid and budget method of estimation towards real time bid advertisement |
-
2018
- 2018-05-08 CN CN201810429774.4A patent/CN108629627A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102665118A (en) * | 2012-05-15 | 2012-09-12 | 合一网络技术(北京)有限公司 | Method and system for controlling releasing frequency and priority of network video advertisement |
| CN104299151A (en) * | 2014-09-28 | 2015-01-21 | 新浪网技术(中国)有限公司 | Online advertising flow distribution system and method |
| CN105741133A (en) * | 2016-01-26 | 2016-07-06 | 电子科技大学 | Stepping management method for online advertisement delivery |
| CN106412644A (en) * | 2016-09-19 | 2017-02-15 | 北京喂呦科技有限公司 | Accurate advertising method and system based on smart TV player |
| CN107153970A (en) * | 2017-04-24 | 2017-09-12 | 郑州埃文计算机科技有限公司 | A kind of bid and budget method of estimation towards real time bid advertisement |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112749997A (en) * | 2018-10-11 | 2021-05-04 | 广东聚宝屋传媒有限公司 | Express package-based advertisement delivery management method and device |
| CN112749997B (en) * | 2018-10-11 | 2023-10-20 | 广东聚宝屋传媒有限公司 | Advertisement delivery management method and device based on express package |
| CN109636488A (en) * | 2019-01-17 | 2019-04-16 | 珠海天燕科技有限公司 | Advertisement placement method and device |
| CN111178960A (en) * | 2019-12-26 | 2020-05-19 | 浙江致梦大数据有限公司 | Advertisement resource integration platform |
| CN111178960B (en) * | 2019-12-26 | 2023-05-23 | 浙江致梦大数据有限公司 | Advertisement resource integration platform |
| CN112396471A (en) * | 2020-12-10 | 2021-02-23 | 杭州次元岛科技有限公司 | Advertisement putting optimization method and device based on big data |
| CN112396471B (en) * | 2020-12-10 | 2021-05-11 | 杭州次元岛科技有限公司 | Advertisement putting optimization method and device based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108629627A (en) | A kind of automatic dispensing control method of moving advertising | |
| CN107423442A (en) | Method and system, storage medium and computer equipment are recommended in application based on user's portrait behavioural analysis | |
| CN109492774A (en) | A kind of cloud resource dispatching method based on deep learning | |
| CN108154430A (en) | A kind of credit scoring construction method based on machine learning and big data technology | |
| CN110110887A (en) | To the prediction technique of low-voltage platform area line loss per unit | |
| CN109271374A (en) | A kind of database health scoring method and scoring system based on machine learning | |
| CN109636213A (en) | Order splitting, evaluation method and device, electronic equipment and storage medium | |
| CN104842564B (en) | A kind of 3 D-printing multitask Optimization Scheduling based on NSGA II | |
| CN104636801A (en) | Transmission line audible noise prediction method based on BP neural network optimization | |
| CN106802553A (en) | A kind of railway locomotive operation control system hybrid tasks scheduling method based on intensified learning | |
| CN106934497A (en) | Wisdom cell power consumption real-time predicting method and device based on deep learning | |
| CN105719045A (en) | Retention risk determiner | |
| CN110147389A (en) | Account number treating method and apparatus, storage medium and electronic device | |
| CN110059887A (en) | BP neural network Risk Identification Method and system based on self-adapted genetic algorithm | |
| CN109872052A (en) | A kind of law court's case intelligence division householder method and system | |
| CN108170531A (en) | A kind of cloud data center request stream scheduling method based on depth belief network | |
| CN104217255B (en) | A kind of power system multiple target optimized maintenance method under market environment | |
| CN109978268A (en) | A kind of short-term load forecasting method, system and relevant apparatus | |
| CN110070228A (en) | BP neural network wind speed prediction method for neuron branch evolution | |
| CN108122166A (en) | The method sorted out to stock and scored using intelligent quantization financial technology | |
| CN104657390B (en) | A kind of answer platform method and system | |
| CN108648087A (en) | Risk analysis method, device and equipment about fund product-specific investments management | |
| CN105005501B (en) | A kind of second order optimizing and scheduling task method towards cloud data center | |
| CN108428061A (en) | Intelligent Tenders Decision system based on DEA-GA-BP and tender Evaluation Method | |
| CN104392317A (en) | Project scheduling method based on genetic culture gene 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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181009 |
|
| WD01 | Invention patent application deemed withdrawn after publication |