CN110362728A - Information-pushing method, device, equipment and storage medium based on big data analysis - Google Patents
Information-pushing method, device, equipment and storage medium based on big data analysis Download PDFInfo
- Publication number
- CN110362728A CN110362728A CN201910539816.4A CN201910539816A CN110362728A CN 110362728 A CN110362728 A CN 110362728A CN 201910539816 A CN201910539816 A CN 201910539816A CN 110362728 A CN110362728 A CN 110362728A
- Authority
- CN
- China
- Prior art keywords
- hot spot
- training
- information
- network data
- big data
- 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
- 238000007405 data analysis Methods 0.000 title claims abstract description 98
- 238000000034 method Methods 0.000 title claims abstract description 68
- 230000008859 change Effects 0.000 claims abstract description 22
- 238000012549 training Methods 0.000 claims description 120
- 238000010801 machine learning Methods 0.000 claims description 20
- 238000004458 analytical method Methods 0.000 claims description 18
- 230000004044 response Effects 0.000 claims description 17
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 5
- 238000004519 manufacturing process Methods 0.000 claims 1
- 230000008569 process Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 7
- 239000000203 mixture Substances 0.000 description 7
- 238000012546 transfer Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 241001269238 Data Species 0.000 description 5
- 238000009472 formulation Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 244000046052 Phaseolus vulgaris Species 0.000 description 1
- 235000010627 Phaseolus vulgaris Nutrition 0.000 description 1
- 244000097202 Rathbunia alamosensis Species 0.000 description 1
- 235000009776 Rathbunia alamosensis Nutrition 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000005194 fractionation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003116 impacting effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to big data analysis technical field, a kind of information-pushing method based on big data analysis, device, equipment and storage medium are disclosed.This method comprises: acquiring the network data to be monitored issued from media account at times；The network data of day part is analyzed using the big data analysis model constructed in advance, obtains the change rate of the corresponding hot spot of network data；According to change rate and preset information value judgment criteria, predict whether hot spot has push value；If prediction hot spot has push value, by network data transmitting to user, so that user formulates the operational program of fitting hot spot according to network data.The technical issues of identifying valuable information by the above-mentioned means, solving in the Multi net voting data that can not fast and accurately comform in the prior art, and valuable information be pushed to user.
Description
Technical field
The present invention relates to big data analysis technical field more particularly to a kind of information push sides based on big data analysis
Method, device, equipment and storage medium.
Background technique
With the arrival of big data era, can all generate a large amount of network data in network all the time, and how from this
Identifying in a little network datas is just particularly important the valuable information of user.
However, in practical applications, the judgement for valuable information be usually by user by virtue of experience with personal emotion
Determining, therefore fast and accurate from numerous network datas can not identify valuable information at all, this allows for using
Family cannot formulate suitable operational program according to valuable information in time.
So can comform it is urgent to provide one kind fast and accurate in Multi net voting data identifies that valuable information pushes away
The method for giving user.
Above content is only used to facilitate the understanding of the technical scheme, and is not represented and is recognized that above content is existing skill
Art.
Summary of the invention
The main purpose of the present invention is to provide a kind of information-pushing method based on big data analysis, device, equipment and
Storage medium, it is intended to solution can not fast and accurately comform identify valuable information in Multi net voting data in the prior art,
And the technical issues of valuable information is pushed to user.
To achieve the above object, the present invention provides a kind of information-pushing method based on big data analysis, the methods
The following steps are included:
The network data to be monitored issued from media account is acquired at times；
The network data of day part is analyzed using the big data analysis model constructed in advance, obtains the network number
According to the change rate of corresponding hot spot；
According to the change rate and preset information value judgment criteria, predict whether the hot spot has push value；
If predicting, the hot spot has push value, by the network data transmitting to user, so that user's root
The operational program for being bonded the hot spot is formulated according to the network data.
Preferably, before described the step of acquiring the network data to be monitored issued from media account at times, the side
Method further include:
It determines described to be monitored from media account；
Wherein, the determination it is described it is to be monitored from media account the step of, comprising:
According to business it needs to be determined that the network address to be monitored from media platform；
Web crawlers is configured according to the network address, it is corresponding from the network address using the web crawlers
Crawl network data to be processed from media platform；
Using keyword extraction techniques, keyword extraction is carried out to the history pushed information prestored, the history is obtained and pushes away
The keyword of the corresponding hot spot of breath of delivering letters；
According to the keyword, the network data to be processed is filtered, at least one is obtained and participates in the hot spot
From media account；
Participation hot spot number is filtered out from respective media account and meets preset threshold, and is impacted and met preset condition
From media account, will filter out from media account as described to be monitored from media account.
Preferably, the step that the network data of day part is analyzed using the big data analysis model constructed in advance
Before rapid, the method also includes:
Construct the big data analysis model；
Wherein, the step of building big data analysis model, comprising:
Data acquisition instructions are received, the network address of training data to be collected is extracted from the data acquisition instructions；
Web crawlers is configured according to the network address, it is corresponding from the network address using the web crawlers
Webpage in obtain the training data；
According to the training data and predetermined machine learning algorithm, learning path is planned；
According to the learning path and the training data, training pattern is constructed；
According to the corresponding business demand of preset big data analysis model, learning objective is determined；
Using the machine learning algorithm, training is iterated to the training pattern；
When match degree is greater than the preset threshold for the training result and the learning objective that training obtains, determine described in obtaining
Big data analysis model.
Preferably, the machine learning algorithm is convolutional neural networks algorithm, and the convolution kernel of the training pattern is 5 × 5；
It is described to use the machine learning algorithm, the training pattern is iterated before trained step, the side
Method further include:
To the training pattern carry out convolution kernel fractured operation, by the training pattern 5 × 5 convolution kernel be split as to
Few two 3 × 3 convolution kernels；
Wherein, described to use the machine learning algorithm, trained step is iterated to the training pattern, comprising:
Using convolutional neural networks algorithm, respectively at least two 3 × 3 convolution for splitting acquisition in the training pattern
Core is iterated training.
Preferably, described according to the learning path and the training data, it is described before the step of constructing training pattern
Method further include:
The training data is normalized, target training data is obtained；
Wherein, described according to the learning path and the training data, the step of constructing training pattern, comprising:
According to the learning path and the target training data, training pattern is constructed.
Preferably, described so that the user formulates the step for being bonded the operational program of the hot spot according to the network data
Suddenly, comprising:
Monitor whether the user triggers operational program generation instruction；
If monitoring, the user triggers operational program and generates instruction, obtains the product to be promoted that the user provides
Product information；
According to the corresponding hot spot of the network data, hot spot template is generated；
The product information is input to the designated position of the hot spot template, obtains the business side for being bonded the hot spot
Case.
Preferably, it is described obtain the step of being bonded the operational program of the hot spot after, the method also includes:
The operational program is published to preset from media platform；
The user from media platform is obtained to the response message of the operational program；
According to the response message, the operational program is adjusted.
In addition, to achieve the above object, the present invention also proposes a kind of information push-delivery apparatus based on big data analysis, described
Device includes:
Acquisition module, for acquiring the network data to be monitored issued from media account at times；
Analysis module, for being analyzed using the big data analysis model constructed in advance the network data of day part,
Obtain the change rate of the corresponding hot spot of the network data；
Prediction module, for whether predicting the hot spot according to the change rate and preset information value judgment criteria
Has push value；
Pushing module, for the hot spot have push value when, by the network data transmitting to user, so that institute
It states user and formulates the operational program for being bonded the hot spot according to the network data.
In addition, to achieve the above object, the present invention also proposes a kind of information pushing equipment based on big data analysis, described
Equipment include: memory, processor and be stored on the memory and can run on the processor based on big data
The information push products of analysis, the information push products based on big data analysis be arranged for carrying out it is as described above based on
The step of information-pushing method of big data analysis.
In addition, to achieve the above object, the present invention also proposes a kind of storage medium, it is stored with and is based on the storage medium
The information push products of big data analysis is realized such as when the information push products based on big data analysis is executed by processor
The step of information-pushing method based on big data analysis described above.
Information provided by the invention based on big data analysis pushes scheme, by acquire at times specify it is to be monitored from matchmaker
The network data of body account publication, and the network data of day part is analyzed, it determines described to be monitored from media account hair
The change rate of the corresponding hot spot of a certain network data of cloth, so as to become society in the corresponding content of the network data
Before hot spot, prejudge out the hot spot whether have push value, and then decide whether by the network data transmitting to
User, so that user formulates the operational program for being bonded the hot spot according to the business demand of oneself and the network data.This
Sample not only can blindly follow the wind to avoid user, and can effectively be promoted using business of the hot spot to oneself.
Further, since the network data acquired in the present embodiment is to be monitored from media account from specifying, thus in fact
The controllable of network data is showed, to substantially reduce the system resource of the equipment for network data.
Detailed description of the invention
Fig. 1 is the information pushing equipment based on big data analysis for the hardware running environment that the embodiment of the present invention is related to
Structural schematic diagram；
Fig. 2 is that the present invention is based on the flow diagrams of the information-pushing method first embodiment of big data analysis；
Fig. 3 is that the present invention is based on the flow diagrams of the information-pushing method second embodiment of big data analysis；
Fig. 4 is that the present invention is based on the structural block diagrams of the information push-delivery apparatus first embodiment of big data analysis.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that described herein, specific examples are only used to explain the present invention, is not intended to limit the present invention.
Referring to Fig.1, Fig. 1 is the information based on big data analysis for the hardware running environment that the embodiment of the present invention is related to
Pushing equipment structural schematic diagram.
As shown in Figure 1, being somebody's turn to do the information pushing equipment based on big data analysis may include: processor 1001, such as center
Processor (Central Processing Unit, CPU), communication bus 1002, user interface 1003, network interface 1004 are deposited
Reservoir 1005.Wherein, communication bus 1002 is for realizing the connection communication between these components.User interface 1003 may include
Display screen (Display), input unit such as keyboard (Keyboard), optional user interface 1003 can also include having for standard
Line interface, wireless interface.Network interface 1004 optionally may include standard wireline interface and wireless interface (such as Wireless Fidelity
(WIreless-FIdelity, WI-FI) interface).Memory 1005 can be the random access memory (Random of high speed
Access Memory, RAM) memory, be also possible to stable nonvolatile memory (Non-Volatile Memory,
), such as magnetic disk storage NVM.Memory 1005 optionally can also be the storage device independently of aforementioned processor 1001.
It will be understood by those skilled in the art that structure shown in Fig. 1 is not constituted to the information based on big data analysis
The restriction of pushing equipment may include perhaps combining certain components or different components than illustrating more or fewer components
Arrangement.
As shown in Figure 1, as may include operating system, network communication mould in a kind of memory 1005 of storage medium
Block, Subscriber Interface Module SIM and the information push products based on big data analysis.
In information pushing equipment based on big data analysis shown in Fig. 1, network interface 1004 is mainly used for and network
Server carries out data communication；User interface 1003 is mainly used for carrying out data interaction with user；The present invention is based on big datas point
Processor 1001, memory 1005 in the information pushing equipment of analysis can be set to be set in the information push based on big data analysis
In standby, the information pushing equipment based on big data analysis called by processor 1001 stored in memory 1005 based on
The information push products of big data analysis, and execute the information push side provided in an embodiment of the present invention based on big data analysis
Method.
The embodiment of the invention provides a kind of information-pushing methods based on big data analysis, are this hair referring to Fig. 2, Fig. 2
A kind of flow diagram of bright information-pushing method first embodiment based on big data analysis.
In the present embodiment, the information-pushing method based on big data analysis the following steps are included:
Step S10 acquires the network data to be monitored issued from media account at times.
Specifically, the executing subject of the present embodiment is server, for example traditional physical server (occupies actual physics
The server in space) or virtual Cloud Server.
In addition, in order to guarantee that the information-pushing method based on big data analysis provided in the present embodiment can smoothly be held
Row, the server need to pre-establish communication connection from media platform from media account is corresponding with to be monitored.
It should be understood that described from media, i.e., usually said We Media, also known as " citizen matchmaker in the present embodiment
Body " or " individual media ".Specifically refer to the disseminator of privatization, popular, generalization, autonomy-oriented, with modernize, electronization
Means transmit the general name of normative and non-standard information new media to not specific most of or specific single people.
Correspondingly, the network platform for being used to propagate for the normative and non-standard information from media platform.
Specifically, currently, user's usage amount is more mainly has from media platform: blog, microblogging, wechat, Baidu official
The Web Communities such as square discussion bar, forum/BBS, will not enumerate herein, any restrictions are not also done to this.
Correspondingly, described from media account is above-mentioned to be arbitrarily supplied to the user account that user uses from media platform.
In addition, it is noted that number of users is huge due to low using threshold from media platform, if to from matchmaker
The network data of all user accounts publication of body platform is all monitored, it is clear that workload is excessively huge, and exists a large amount of
Interference information.Thus, in order to not only guarantee that determining hot spot has push value, but also server can be reduced as far as possible and need to locate
The network data of reason.In the present embodiment it is described it is to be monitored from media account specifically refer to meet certain specified conditions from media
Account.
That is, being needed before executing the operation for acquiring the network data to be monitored issued from media account at times
It first to determine described to be monitored from media account.
In order to make it easy to understand, the present embodiment provide it is a kind of determine the specific implementation to be monitored from media account,
Its determine process approximately as:
(1) according to business it needs to be determined that the network address to be monitored from media platform.
It should be understood that above-mentioned described network address, the unified resource specifically to be monitored from media platform are fixed
Position symbol (Uniform Resource Locator, URL).
(2) web crawlers is configured according to the network address, using the web crawlers from the network address
It is corresponding to crawl network data to be processed from media platform.
Specifically, in the present embodiment, for obtaining the web crawlers of network data to be processed, it can be universal network
In numerous web crawlers such as crawler, focused web crawler, increment type web crawlers, Deep Web Crawler any one or it is several
Kind, in a particular application, those skilled in the art can according to need selection, and the present invention does not do any restrictions to this.
In addition, it is noted that in practical applications, in order to avoid a large amount of network data heaps to be processed got
Product, causes system thread to block, influences treatment effect, can be first by described wait locate after getting network data to be processed
Reason network data is added in the network data buffer pool to be processed constructed in advance, such as Kafka message queue.
It should be understood that since Kafka has persistence, stability, the high pass amount of spitting, support server and consumption cluster
Carry out subregion message and support the characteristic of distributed system parallel data load, therefore selects Kafka message queue to cache
Network data to be processed is stated, a large amount of network data products to be processed can be avoided as far as possible, to effectively prevent thread block.
Further, since Kafka is an open source stream process platform of Apache Software Foundation exploitation, about its use
Mode have been relatively mature, and those skilled in the art in the concrete realization, can voluntarily realize by searching for relevant documentation,
Details are not described herein again.
(3) keyword extraction techniques are utilized, keyword extraction is carried out to the history pushed information prestored, obtains the history
The keyword of the corresponding hot spot of pushed information.
In order to make it easy to understand, marketing program needed for promoting product by enterprise of the operational program of formulation in the present embodiment is
Example.
Correspondingly, history marketing case relevant to the product that enterprise promotes that the history pushed information prestored is then.
It should be understood that in practical applications, the above-mentioned described history marketing preferred promotion effect of case is preferably sought
It closes a case example, i.e., the described history marketing case has attracted a large number of users concern, reached expected effect in certain time after popularization
Fruit.
Further, since the usage mode of keyword extraction techniques have been relatively mature, those skilled in the art is specific
In realization, it can voluntarily be realized, details are not described herein again by searching for relevant documentation.
(4) according to the keyword, the network data to be processed is filtered, at least one is obtained and participates in the heat
Point from media account.
The mode from media account that the hot spot is participated in about filtering, specifically can be, to the network number to be processed
According to attention traversal is carried out, then using the keyword extracted as index, searched in each network data to be processed,
Filtering, filters out the network data to be processed comprising the keyword.Then, reverse according to the network data to be processed filtered out
Obtain once issued the network data to be processed from media account.
(5) filtered out from respective media account participate in hot spot number meet preset threshold, and impact meet it is default
Condition from media account, will filter out from media account as described to be monitored from media account.
Specifically, due in practical applications, participate in the corresponding network data of a certain hot spot publication operation from matchmaker
Body account often more than one or even large number of.Therefore, how from a large amount of filtering out from media account for heat spot is participated in
Current embodiment require that carry out the to be monitored of data acquisition is particularly important from media account.
In this example, by be arranged two screening conditions, one be participate in hot spot number, the other is caused by shadow
It rings.Then by filter out it is each compared from the corresponding person's two values of media account with preset threshold value and condition, from
And using simultaneously meet above-mentioned two condition from media account as to be monitored from media account, not only reduce subsequent acquisition and arrive
Network data data volume, also ensure the corresponding hot spot value of collected network data.
In order to make it easy to understand, being illustrated below:
Such as, it is thus necessary to determine that it is to be monitored from media account be by real-name authentication, from media platform liveness compared with
Height, and have the advanced account of a large amount of beans vermicelli, i.e., usually said big V account, such as the big V account of Sina weibo.
Correspondingly, the pre-set threshold value for participating in hot spot number can be a probability value, such as 70%, i.e., in basis
When the quantity for the hot spot that the history marketing case prestored obtains is 10 times, the big V account for needing to filter out participates in the number of hot spot
At least 7 times.
Correspondingly, the pre-set preset condition impacted can be in a certain preset time period, and such as 1 hour
It is interior, it should be more than a certain numerical value by the amount of checking or transfer amount from the internet message about the hot spot that media account is issued, such as 10,000
It is secondary.
(quantity of the hot spot obtained according to the history marketing case prestored is 10 times) in this case, if according to institute
Keyword is stated, the network data to be processed is filtered, what is obtained there are 3 from media account, for ease of description, below
Referred to as from media account A, from media account B and from media account C.
Wherein, from the corresponding participation hot spot number of media account A be 5 times, impact degree be 1 hour in, publication
Internet message about the hot spot has been more than 10,000 times by the amount of checking or transfer amount；From the corresponding participation hot spot of media account B
Number is 8 times, and impacting degree is in 1 hour, and the internet message about the hot spot of publication is surpassed by the amount of checking or transfer amount
It has crossed 1.5 ten thousand times；It is 7 times from the corresponding participation hot spot number of media account C, the degree that impacts is the pass of publication in 1 hour
In the internet message of the hot spot by the amount of checking or transfer amount be more than 0.8 ten thousand times.
By foregoing description it is not difficult to find that it is final it is qualified from media account only from media account B, that is,
Say, finally but it is to be monitored from media account be from media account B.
It should be understood that having the above is only for example, not constituting any restriction to technical solution of the present invention
In body application, those skilled in the art, which can according to need, to be configured, and the present invention is without limitation.
Step S20 analyzes the network data of day part using the big data analysis model constructed in advance, obtains institute
State the change rate of the corresponding hot spot of network data.
Specifically, in practical applications, using the big data analysis model constructed in advance to the network data of day part
It is analyzed, obtains the operation of the change rate of the corresponding hot spot of the network data, be exactly substantially by collected day part
Network data as input parameter, the input layer of the big data analysis model is sequentially inputted to, then by the big data
Analysis model carries out Automatic analysis to the network data of input, finally will directly export the change rate of corresponding hot spot.
In addition, it is noted that in practical applications, in order to guarantee the smooth execution of aforesaid operations, needing first to construct
The big data analysis model.
About the mode for building the big data analysis model, can substantially be realized according to following process:
(1) data acquisition instructions are received, the network of training data to be collected is extracted from the data acquisition instructions
Location.
It should be understood that above-mentioned described network address, in addition to can be the webpage where training data to be collected
Uniform resource locator (Uniform Resource Locator, URL), can also be in any big data platform, it is described
The database storage address of training data, will not enumerate herein, and any restrictions are not also done to this.
In addition, it is noted that the accuracy of the change rate of the hot spot in order to guarantee subsequent analysis acquisition, the training
Data should be the determining historical network data to be monitored issued from media account, and the use for the historical network data issued
Information is paid close attention at family, such as user's transmitting active degree, forwarding time, the user's characteristic information etc. for forwarding institute's historical network data, herein
It will not enumerate, any restrictions are not also done to this.
(2) web crawlers is configured according to the network address, using the web crawlers from the network address
The training data is obtained in corresponding webpage.
About the selection of the web crawlers, the above-mentioned determination web crawlers to be monitored from media account can be referred to
Selection process, details are not described herein again.
In addition, it is noted that in practical applications, in order to avoid the accumulation of a large amount of training datas, leading to system thread
Obstruction, influences treatment effect, after getting training data, equally the training data first can be added to preparatory building
Training data buffer pool in, such as Kafka message queue.
About the use of Kafka, equally can with reference to the above-mentioned determination scheme to be monitored provided from media account with
And the existing relevant documentation about Kafka voluntarily realizes that details are not described herein again.
(3) according to the training data and predetermined machine learning algorithm, learning path is planned.
Specifically, in the present embodiment, predetermined machine learning algorithm is convolutional neural networks algorithm.
Correspondingly, the learning path of planning can be supervised learning mode and unsupervised learning mode.
About above-mentioned described supervised learning mode and unsupervised learning mode, during specific implementation, this field
Technical staff can check relevant documentation, voluntarily realize, details are not described herein again.
(4) according to the learning path and the training data, training pattern is constructed.
Specifically, since predetermined machine learning algorithm is convolutional neural networks algorithm, and convolution is used at present
The convolution kernel for the training pattern that neural network algorithm is trained is mostly 5 × 5.This results in the network depth of training pattern
Deficiency, and then the big data analysis model for causing training to obtain is inadequate to the accuracy of the analysis result of the network data.Cause
This, for the network depth of training for promotion model so that the big data analysis model that training obtains to the network number
According to analysis result accuracy, before executing above-mentioned steps (4), can first to the training pattern carry out convolution kernel fractionation
In the training pattern 5 × 5 convolution kernel, is split as at least two 3 × 3 convolution kernel, to increase training pattern by operation
Network depth.
Correspondingly, described to use the machine learning algorithm, it is specific that trained operation is iterated to the training pattern
Become: using convolutional neural networks algorithm, respectively at least two 3 × 3 convolution kernel for splitting acquisition in the training pattern
It is iterated training.
In addition, in practical applications, for the generalization ability (machine learning for the big data analysis model that training for promotion obtains
Adaptability of the algorithm to fresh sample), according to the learning path and the training data, before constructing training pattern,
First the training data can also be normalized, to obtain target training data.
Correspondingly, described according to the learning path and the training data, the operation for constructing training pattern specifically becomes:
According to the learning path and the target training data, training pattern is constructed.
(5) according to the corresponding business demand of preset big data analysis model, learning objective is determined.
Specifically, above-mentioned described learning objective, in subsequent training process, be for detect training result whether pole
The earth approaching to reality data, i.e. training pattern are after completing certain primary training, after training data is inputted training pattern, output
Training result and the learning objective it is close.
(6) machine learning algorithm is used, training is iterated to the training pattern.
(7) when match degree is greater than the preset threshold for the training result and the learning objective that training obtains, determination is obtained
The big data analysis model.
It should be understood that only a kind of concrete mode for constructing big data analysis model is given above, to the present invention
Technical solution do not constitute any restriction, in a particular application, those skilled in the art, which can according to need, to be configured,
The present invention is without limitation.
Step S30 predicts whether the hot spot has and pushes away according to the change rate and preset information value judgment criteria
Send value.
Specifically, information value judgment criteria mentioned here, it is as preset, any item met in change rate
When part, it will be considered that the corresponding hot spot of current network data has push value.
It is still by taking the operational program finally formulated is marketing program as an example, then above-mentioned for judging that the value information of change rate is sentenced
Disconnected standard is value judgement standard of marketing.
Correspondingly, it finally predicts whether the hot spot has the operation of push value, as predicts whether the hot spot has
Standby marketing value.
That is, in the application scenarios of product marketing, if the hot spot of prediction has marketing value, then it is assumed that
The corresponding network data of the hot spot has push value.
In order to make it easy to understand, whether marketing value judgement standard and determining hot spot have marketing value, lifted below
Example explanation:
Such as during continuous time tn, user's transfer amount of network data described in the t1 moment is n1, t2 moment institute
The user's transfer amount for stating network data is n2, and user's transfer amount of network data described in the t3 moment is n3；The marketing of setting is worth
Judgment criteria are as follows: tn- > tn+1- > tn+2 each time point is incremented more than 20%, then it is assumed that the hot spot has marketing value.
It should be understood that having the above is only for example, not constituting any restriction to technical solution of the present invention
In body application, those skilled in the art, which can according to need, to be configured, and the present invention is without limitation.
Step S40, if predicting, the hot spot has push value, by the network data transmitting to user, so that institute
It states user and formulates the operational program for being bonded the hot spot according to the network data.
Specifically, the described hot spot for having push value can be and will generate very high topic degree in the recent period in the present embodiment
Hot spot.
In addition, described in the present embodiment, value is pushed determining that the hot spot has, the network data transmitting is given
The operation of user is substantially such as personal computer, plate by the terminal device of the network data transmitting to the user
Computer, smart phone etc., will not enumerate herein, also with no restrictions to this.
However, it should be understood that above-mentioned described user, is not limited to individual natural person in practical applications,
It is also possible to be responsible for the staff of a certain business in enterprise or enterprise.
Still by taking the operational program finally formulated is marketing program as an example, then the user is to be responsible for product promotion in enterprise
The marketing personnel of work.
In addition, it is noted that in practical applications, in order to preferably assist user to formulate suitable business side
Case, after giving the network data transmitting to the user, the relevant information that can be provided by server according to user, automatically
The operational program of a fitting hot spot is generated, for user reference.
The behaviour of the above-mentioned described operational program that the fitting hot spot is formulated according to the network data in order to facilitate understanding
Make, the present embodiment is illustrated so that the operational program formulated is marketing program as an example:
Firstly, by the network data transmitting to the user marketing personnel of product promotion (specially be responsible for) it
Afterwards, monitor whether the user triggers operational program generation instruction (specially marketing program generates instruction).
Correspondingly, if monitoring, the user triggers operational program and generates instruction, obtain that the user provides to
Promote the product information of product.
Then, according to the corresponding hot spot of the network data, hot spot template is generated.
Finally, the product information to be input to the designated position of the hot spot template, the industry for being bonded the hot spot is obtained
Business scheme.
In order to make it easy to understand, being illustrated below:
Such as in the format of the network data are as follows: official declares+one heart (symbol)+a certain star photo, then generates
Hot spot template may is that official declare+one heart (symbol)+picture/information Adding Area；
Correspondingly, the marketing program of the fitting hot spot obtained, as+one heart (symbol) of official a surname+described wait promote
Product picture/information of product.
Also such as, in the format of the network data are as follows: XX is my XX, then the hot spot template generated may is that " to
Popularization name of product " is my XX+ picture/information Adding Area；
Correspondingly, the marketing program of the fitting hot spot obtained, as " name of product to be promoted " is described in my XX+
Product picture/information of product to be promoted.
It should be understood that above-mentioned " XX ", need to only fit into practical applications in relevant to the product to be promoted
Appearance, herein with no restrictions.
However, it should be understood that the above is only for example, not constituting any limit to technical solution of the present invention
Fixed, in a particular application, those skilled in the art, which can according to need, to be configured, and the present invention is without limitation.
By foregoing description it is not difficult to find that the information-pushing method based on big data analysis provided in the present embodiment, leads to
The network data to be monitored issued from media account is specified after acquisition at times, and the network data of day part is analyzed,
The change rate of a certain network data corresponding hot spot to be monitored issued from media account is determined, so as to described
Before the corresponding content of network data becomes social hotspots, prejudge out whether the hot spot has push value, and then certainly
It is fixed whether to carry out " taking advantage of other's power to market ", it not only can avoid blindly following the wind, and can effectively " borrow using hot spot progress
Gesture marketing ", and then promote marketing effectiveness.
In addition, in the information-pushing method provided in this embodiment based on big data analysis, the network data of acquisition is
It is to be monitored from media account from specifying, it is thus achieved that network data is controllable, to substantially reduce for handling net
The system resource of the equipment of network data.
With reference to Fig. 3, Fig. 3 is that a kind of process of the information-pushing method second embodiment based on big data analysis of the present invention is shown
It is intended to.
Based on above-mentioned first embodiment, the present embodiment is based on the information-pushing method of big data analysis in the step S40
Later, further includes:
The operational program is published to preset from media platform by step S50.
Specifically, above-mentioned described preset from media platform, it can be to provide described to be monitored from media account
From media platform, it is also possible to other from media platform, in practical applications, those skilled in the art can be according to wait promote
Product and the cooperative relationship from media platform and the universal range Rational choice from media platform.
Correspondingly, it is above-mentioned it is described the operational program is published to the preset operation from media platform, it is specifically sharp
Operational program publication operation is carried out from media account with pre-registered described preset from media platform.
Step S60 obtains the user from media platform to the response message of the operational program.
Still by taking the operational program of formulation is marketing program as an example, above-mentioned described response message may include described from media
The user of platform to the forwarding of the marketing program, the numbers of operations such as check, and forwarding crowd user's characteristic information, mention
The comment information etc. of friendship.
Step S70 is adjusted the operational program according to the response message.
Still by taking the operational program of formulation is marketing program as an example, according to the response message, to the marketing program into
When row adjustment, it specifically can use big data analysis technology, the response message analyzed, extract user to the battalion
The approval content of pin scheme and dissatisfied part, then according to the content extracted, it is reasonable to carry out to the marketing program.
By foregoing description it is not difficult to find that the information-pushing method based on big data analysis provided in the present embodiment,
The marketing program of the fitting hot spot of formulation be published to it is preset from after media platform, it is described from media platform by obtaining
User is adjusted the response message of the marketing program then according to the response message to the marketing program, so that
Marketing program can be adjusted in real time according to the actual situation, preferably fitting marketing hot spot.
In addition, the embodiment of the present invention also proposes a kind of storage medium, it is stored on the storage medium based on big data point
The information push products of analysis is realized as described above when the information push products based on big data analysis is executed by processor
The information-pushing method based on big data analysis the step of.
It is that the present invention is based on the structural block diagrams of the information push-delivery apparatus first embodiment of big data analysis referring to Fig. 4, Fig. 4.
As shown in figure 4, the information push-delivery apparatus based on big data analysis that the embodiment of the present invention proposes includes: acquisition module
4001, analysis module 4002, prediction module 4003 and pushing module 4004.
Wherein, the acquisition module 4001, for acquiring the network data to be monitored issued from media account at times；Institute
Analysis module 4002 is stated, for being analyzed using the big data analysis model constructed in advance the network data of day part, is obtained
To the change rate of the corresponding hot spot of the network data；The prediction module 4003, for according to the change rate and preset
Information value judgment criteria, predicts whether the hot spot has push value；The pushing module 4004, in the hot spot
When having push value, by the network data transmitting to user, it is bonded so that the user formulates according to the network data
The operational program of the hot spot.
In addition, it is noted that in order to guarantee that the network data to be monitored issued from media account is to have push valence
The information of value.Therefore, the information push-delivery apparatus provided in this embodiment based on big data analysis further include: to be monitored from media account
Number determining module.
Correspondingly, described to be monitored from media account determining module, for being acquired at times in the acquisition module 4001
It is to be monitored from media account issue network data before, determine described to be monitored from media account.
About described to be monitored from media account determining module, the mode to be monitored from media account is determined, substantially
It can be realized according to following process:
Firstly, according to business it needs to be determined that the network address to be monitored from media platform；
Then, web crawlers is configured according to the network address, from the network using the web crawlers
Location is corresponding to crawl network data to be processed from media platform；
Then, using keyword extraction techniques, keyword extraction is carried out to the history pushed information prestored, obtains described go through
The keyword of the corresponding hot spot of history pushed information；
Then, according to the keyword, the network data to be processed is filtered, is obtained described at least one participation
Hot spot from media account；
Finally, filtered out from respective media account participate in hot spot number meet preset threshold, and impact meet it is pre-
If condition from media account, will filter out from media account as described to be monitored from media account.
It should be understood that be given above it is only a kind of determine the concrete mode to be monitored from media account, to this hair
Bright technical solution does not constitute any restriction, and in a particular application, those skilled in the art, which can according to need, to be set
It sets, the present invention is without limitation.
However, it should be understood that in practical applications, in order to guarantee that the analysis module 4002 can be executed smoothly
Analysis operation.Information push-delivery apparatus provided in this embodiment based on big data analysis further include: big data analysis model construction
Module.
Correspondingly, the big data analysis model construction module, for utilizing building in advance in the analysis module 4002
Big data analysis model the network data of day part is analyzed before, construct the big data analysis model.
About the big data analysis model construction module, the mode of the big data analysis model is constructed, it substantially can be with
It is realized according to following process:
Firstly, receiving data acquisition instructions, the network of training data to be collected is extracted from the data acquisition instructions
Address；
Then, web crawlers is configured according to the network address, from the network using the web crawlers
The training data is obtained in the corresponding webpage in location；
Then, according to the training data and predetermined machine learning algorithm, learning path is planned；
Then, according to the learning path and the training data, training pattern is constructed；
Then, according to the corresponding business demand of preset big data analysis model, learning objective is determined；
Then, using the machine learning algorithm, training is iterated to the training pattern；
Finally, when match degree is greater than the preset threshold for the training result and the learning objective that training obtains, determining
To the big data analysis model.
In order to make it easy to understand, the present embodiment provides a kind of specific machine learning algorithm, specially convolutional neural networks are calculated
Method.
It correspondingly, is being specially 5 according to the convolution kernel of the learning path and the training pattern of training data building
× 5.
Therefore, for the network depth of training for promotion model, the big data analysis model that training is obtained is more
Accurately the network data of day part is analyzed, obtains more accurate analysis result.Using the convolutional Neural net
Network algorithm before being iterated training to the training pattern, first can carry out convolution kernel fractured operation to the training pattern,
To which in the training pattern 5 × 5 convolution kernel to be split as at least two 3 × 3 convolution kernel.
Correspondingly, described to use the machine learning algorithm, it is specific that trained operation is iterated to the training pattern
Become: using convolutional neural networks algorithm, respectively at least two 3 × 3 convolution kernel for splitting acquisition in the training pattern
It is iterated training.
In addition, in practical applications, for the generalization ability for the big data analysis model that training for promotion obtains, according to institute
Learning path and the training data are stated, before constructing training pattern, place first can also be normalized to the training data
Reason, to obtain target training data.
Correspondingly, described according to the learning path and the training data, the operation for constructing training pattern specifically becomes:
According to the learning path and the target training data, training pattern is constructed.
It should be understood that only a kind of concrete mode for constructing big data analysis model is given above, to the present invention
Technical solution do not constitute any restriction, in a particular application, those skilled in the art, which can according to need, to be configured,
The present invention is without limitation.
In addition, it is noted that the pushing module 4004 by the network data transmitting to user after, this reality
It applies in example described so that the user formulates the operation for being bonded the operational program of the hot spot according to the network data, substantially
It can be such that
Instruction is generated firstly, monitoring the user and whether triggering operational program；
Correspondingly, if monitoring, the user triggers operational program and generates instruction, obtain that the user provides to
Promote the product information of product；
Then, according to the corresponding hot spot of the network data, hot spot template is generated；
Finally, the product information to be input to the designated position of the hot spot template, the industry for being bonded the hot spot is obtained
Business scheme.
It should be understood that it is given above only a kind of concrete mode for the marketing program for formulating the fitting hot spot,
Any restriction is not constituted to technical solution of the present invention, in a particular application, those skilled in the art can according to need
It is configured, the present invention is without limitation.
By foregoing description it is not difficult to find that the information push-delivery apparatus based on big data analysis provided in the present embodiment, leads to
The network data to be monitored issued from media account is specified after acquisition at times, and the network data of day part is analyzed,
The change rate of a certain network data corresponding hot spot to be monitored issued from media account is determined, so as to described
Before the corresponding content of network data becomes social hotspots, prejudge out whether the hot spot has push value, and then certainly
It is fixed whether by the network data transmitting to user so that business demand and the network data system of the user according to oneself
Surely it is bonded the operational program of the hot spot.User not only can be avoided blindly to follow the wind, and can effectively utilize the hot spot
The business of oneself is promoted.
In addition, in the information push-delivery apparatus provided in this embodiment based on big data analysis, the network data of acquisition is
It is to be monitored from media account from specifying, it is thus achieved that network data is controllable, to substantially reduce for handling net
The system resource of the equipment of network data.
It should be noted that workflow described above is only schematical, not to protection model of the invention
Enclose composition limit, in practical applications, those skilled in the art can select according to the actual needs part therein or
It all achieves the purpose of the solution of this embodiment, herein with no restrictions.
In addition, the not technical detail of detailed description in the present embodiment, reference can be made to provided by any embodiment of the invention
Information-pushing method based on big data analysis, details are not described herein again.
Based on the first embodiment of the above-mentioned information push-delivery apparatus based on big data analysis, propose that the present invention is based on big datas
The information push-delivery apparatus second embodiment of analysis.
In the present embodiment, the information push-delivery apparatus based on big data analysis further include operational program release module,
Response information acquisition module and operational program adjust module.
Wherein, the operational program release module, it is preset from media platform for the operational program to be published to.
The response information acquisition module, for obtaining the response from the user of media platform to the operational program
Information.
The operational program adjusts module, for being adjusted to the operational program according to the response message.
It should be understood that having the above is only for example, not constituting any restriction to technical solution of the present invention
In body application, those skilled in the art, which can according to need, to be configured, and the present invention is without limitation.
By foregoing description it is not difficult to find that the information push-delivery apparatus based on big data analysis provided in the present embodiment,
The operational program of the fitting hot spot of formulation be published to it is preset from after media platform, it is described from media platform by obtaining
User is adjusted the response message of the operational program then according to the response message to the operational program, so that
Operational program can be adjusted in real time according to the actual situation, preferably be bonded hot spot.
It should be noted that workflow described above is only schematical, not to protection model of the invention
Enclose composition limit, in practical applications, those skilled in the art can select according to the actual needs part therein or
It all achieves the purpose of the solution of this embodiment, herein with no restrictions.
In addition, the not technical detail of detailed description in the present embodiment, reference can be made to provided by any embodiment of the invention
Information-pushing method based on big data analysis, details are not described herein again.
In addition, it should be noted that, herein, the terms "include", "comprise" or its any other variant are intended to contain
Lid non-exclusive inclusion, so that process, method, article or system including a series of elements are not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or system
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or system including the element.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
In (such as read-only memory (Read Only Memory, ROM)/RAM, magnetic disk, CD), including some instructions are used so that one
Terminal device (can be mobile phone, computer, server or the network equipment etc.) executes side described in each embodiment of the present invention
Method.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of information-pushing method based on big data analysis, which is characterized in that the described method includes:
The network data to be monitored issued from media account is acquired at times；
The network data of day part is analyzed using the big data analysis model constructed in advance, obtains the network data pair
The change rate for the hot spot answered；
According to the change rate and preset information value judgment criteria, predict whether the hot spot has push value；
If predicting, the hot spot has push value, by the network data transmitting to user, so that the user is according to institute
It states network data and formulates the operational program for being bonded the hot spot.
2. the method as described in claim 1, which is characterized in that described to acquire the net to be monitored issued from media account at times
Before the step of network data, the method also includes:
It determines described to be monitored from media account；
Wherein, the determination it is described it is to be monitored from media account the step of, comprising:
According to business it needs to be determined that the network address to be monitored from media platform；
Web crawlers is configured according to the network address, it is corresponding certainly from the network address using the web crawlers
Media platform crawls network data to be processed；
Using keyword extraction techniques, keyword extraction is carried out to the history pushed information prestored, obtains the history push letter
Cease the keyword of corresponding hot spot；
According to the keyword, the network data to be processed is filtered, at least one is obtained and participates in oneself of the hot spot
Media account；
Participation hot spot number is filtered out from respective media account and meets preset threshold, and impacts oneself for meeting preset condition
Media account will be filtered out from media account as described to be monitored from media account.
3. the method as described in claim 1, which is characterized in that it is described using the big data analysis model that constructs in advance to it is each when
Before the step of network data of section is analyzed, the method also includes:
Construct the big data analysis model；
Wherein, the step of building big data analysis model, comprising:
Data acquisition instructions are received, the network address of training data to be collected is extracted from the data acquisition instructions；
Web crawlers is configured according to the network address, using the web crawlers from the corresponding net of the network address
The training data is obtained in page；
According to the training data and predetermined machine learning algorithm, learning path is planned；
According to the learning path and the training data, training pattern is constructed；
According to the corresponding business demand of preset big data analysis model, learning objective is determined；
Using the machine learning algorithm, training is iterated to the training pattern；
When match degree is greater than the preset threshold for the training result and the learning objective that training obtains, determination obtains the big number
According to analysis model.
4. method as claimed in claim 3, which is characterized in that the machine learning algorithm is convolutional neural networks algorithm, institute
The convolution kernel for stating training pattern is 5 × 5；
It is described to use the machine learning algorithm, the training pattern is iterated before trained step, the method is also
Include:
Convolution kernel fractured operation is carried out to the training pattern, in the training pattern 5 × 5 convolution kernel is split as at least two
A 3 × 3 convolution kernel；
Wherein, described to use the machine learning algorithm, trained step is iterated to the training pattern, comprising:
Using convolutional neural networks algorithm, respectively to split in the training pattern at least two 3 × 3 convolution kernel of acquisition into
Row iteration training.
5. method as claimed in claim 3, which is characterized in that described according to the learning path and the training data, structure
Before the step of building training pattern, the method also includes:
The training data is normalized, target training data is obtained；
Wherein, described according to the learning path and the training data, the step of constructing training pattern, comprising:
According to the learning path and the target training data, training pattern is constructed.
6. such as method described in any one of claim 1 to 5, which is characterized in that described so that the user is according to the network
Data formulate the step of operational program for being bonded the hot spot, comprising:
Monitor whether the user triggers operational program generation instruction；
If monitoring, the user triggers operational program and generates instruction, obtains the production for the product to be promoted that the user provides
Product information；
According to the corresponding hot spot of the network data, hot spot template is generated；
The product information is input to the designated position of the hot spot template, obtains the operational program for being bonded the hot spot.
7. method as claimed in claim 6, which is characterized in that it is described obtain the step of being bonded the operational program of the hot spot it
Afterwards, the method also includes:
The operational program is published to preset from media platform；
The user from media platform is obtained to the response message of the operational program；
According to the response message, the operational program is adjusted.
8. a kind of information push-delivery apparatus based on big data analysis, which is characterized in that described device includes:
Acquisition module, for acquiring the network data to be monitored issued from media account at times；
Analysis module is obtained for being analyzed using the big data analysis model constructed in advance the network data of day part
The change rate of the corresponding hot spot of the network data；
Prediction module, for predicting whether the hot spot has according to the change rate and preset information value judgment criteria
Push value；
Pushing module, for the hot spot have push value when, by the network data transmitting to user, so that the use
The operational program for being bonded the hot spot is formulated according to the network data in family.
9. a kind of information pushing equipment based on big data analysis, which is characterized in that the equipment includes: memory, processor
And the information push products based on big data analysis that is stored on the memory and can run on the processor, it is described
Information push products based on big data analysis be arranged for carrying out as described in any one of claims 1 to 7 based on big data
The step of information-pushing method of analysis.
10. a kind of storage medium, which is characterized in that be stored with the information push journey based on big data analysis on the storage medium
Sequence is realized as described in any one of claim 1 to 7 when the information push products based on big data analysis is executed by processor
The information-pushing method based on big data analysis the step of.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910539816.4A CN110362728A (en) | 2019-06-19 | 2019-06-19 | Information-pushing method, device, equipment and storage medium based on big data analysis |
| PCT/CN2020/086169 WO2020253364A1 (en) | 2019-06-19 | 2020-04-22 | Big data analytics-based information pushing method, apparatus, and device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910539816.4A CN110362728A (en) | 2019-06-19 | 2019-06-19 | Information-pushing method, device, equipment and storage medium based on big data analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110362728A true CN110362728A (en) | 2019-10-22 |
Family
ID=68216543
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910539816.4A Pending CN110362728A (en) | 2019-06-19 | 2019-06-19 | Information-pushing method, device, equipment and storage medium based on big data analysis |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110362728A (en) |
| WO (1) | WO2020253364A1 (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110852792A (en) * | 2019-10-28 | 2020-02-28 | 海南太美航空股份有限公司 | Big data analysis-based airline value evaluation method and related products |
| CN111177552A (en) * | 2019-12-27 | 2020-05-19 | 绍兴市上虞区理工高等研究院 | Scientific and technological achievement pushing method and device based on user requirements |
| WO2020253364A1 (en) * | 2019-06-19 | 2020-12-24 | 深圳壹账通智能科技有限公司 | Big data analytics-based information pushing method, apparatus, and device, and storage medium |
| CN112749324A (en) * | 2019-10-31 | 2021-05-04 | 北京达佳互联信息技术有限公司 | Network medium information delivery control method and device, electronic equipment and storage medium |
| CN114897176A (en) * | 2022-03-11 | 2022-08-12 | 南京鼎傲科技有限公司 | Internet big data processing system and method based on artificial intelligence |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010076780A1 (en) * | 2009-01-01 | 2010-07-08 | Orca Interactive Ltd. | Adaptive blending of recommendation engines |
| CN106909637A (en) * | 2017-02-14 | 2017-06-30 | 国家计算机网络与信息安全管理中心 | The influence power analysis method and system of wechat public number |
| CN109191183A (en) * | 2018-08-10 | 2019-01-11 | 宜人恒业科技发展（北京）有限公司 | A kind of advertisement dispensing dynamic debugging system based on big data |
| CN109670104A (en) * | 2018-11-12 | 2019-04-23 | 深圳壹账通智能科技有限公司 | Information-pushing method, unit and storage medium based on machine learning |
| CN109711872A (en) * | 2018-12-14 | 2019-05-03 | 中国平安人寿保险股份有限公司 | Advertisement placement method and device based on big data analysis |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110362728A (en) * | 2019-06-19 | 2019-10-22 | 深圳壹账通智能科技有限公司 | Information-pushing method, device, equipment and storage medium based on big data analysis |
-
2019
- 2019-06-19 CN CN201910539816.4A patent/CN110362728A/en active Pending
-
2020
- 2020-04-22 WO PCT/CN2020/086169 patent/WO2020253364A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010076780A1 (en) * | 2009-01-01 | 2010-07-08 | Orca Interactive Ltd. | Adaptive blending of recommendation engines |
| CN106909637A (en) * | 2017-02-14 | 2017-06-30 | 国家计算机网络与信息安全管理中心 | The influence power analysis method and system of wechat public number |
| CN109191183A (en) * | 2018-08-10 | 2019-01-11 | 宜人恒业科技发展（北京）有限公司 | A kind of advertisement dispensing dynamic debugging system based on big data |
| CN109670104A (en) * | 2018-11-12 | 2019-04-23 | 深圳壹账通智能科技有限公司 | Information-pushing method, unit and storage medium based on machine learning |
| CN109711872A (en) * | 2018-12-14 | 2019-05-03 | 中国平安人寿保险股份有限公司 | Advertisement placement method and device based on big data analysis |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020253364A1 (en) * | 2019-06-19 | 2020-12-24 | 深圳壹账通智能科技有限公司 | Big data analytics-based information pushing method, apparatus, and device, and storage medium |
| CN110852792A (en) * | 2019-10-28 | 2020-02-28 | 海南太美航空股份有限公司 | Big data analysis-based airline value evaluation method and related products |
| CN110852792B (en) * | 2019-10-28 | 2023-10-03 | 海南太美航空股份有限公司 | Route value evaluation method based on big data analysis and related products |
| CN112749324A (en) * | 2019-10-31 | 2021-05-04 | 北京达佳互联信息技术有限公司 | Network medium information delivery control method and device, electronic equipment and storage medium |
| CN112749324B (en) * | 2019-10-31 | 2024-03-12 | 北京达佳互联信息技术有限公司 | Network medium information delivery control method and device, electronic equipment and storage medium |
| CN111177552A (en) * | 2019-12-27 | 2020-05-19 | 绍兴市上虞区理工高等研究院 | Scientific and technological achievement pushing method and device based on user requirements |
| CN114897176A (en) * | 2022-03-11 | 2022-08-12 | 南京鼎傲科技有限公司 | Internet big data processing system and method based on artificial intelligence |
| CN114897176B (en) * | 2022-03-11 | 2023-11-07 | 内蒙古塞上明珠科技成果推广服务有限公司 | Internet big data processing system and method based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020253364A1 (en) | 2020-12-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110362728A (en) | Information-pushing method, device, equipment and storage medium based on big data analysis | |
| US11100411B2 (en) | Predicting influence in social networks | |
| CN107798027B (en) | Information popularity prediction method, information recommendation method and device | |
| CN104753985B (en) | Session list display methods and device | |
| Dittus et al. | Analysing volunteer engagement in humanitarian mapping: building contributor communities at large scale | |
| US20160307131A1 (en) | Method, apparatus, and system for controlling delivery task in social networking platform | |
| US20090248852A1 (en) | Evaluating Entities Associations with their Respective Environments | |
| Eshtehardian et al. | Time–cost optimization: using GA and fuzzy sets theory for uncertainties in cost | |
| CN106992994A (en) | A kind of automatically-monitored method and system of cloud service | |
| CN105677845A (en) | Pushing method and device for electronic books | |
| CN108334575A (en) | A kind of recommendation results sequence modification method and device, electronic equipment | |
| CN108776844A (en) | Social network user behavior prediction method based on context-aware tensor resolution | |
| CN105426502A (en) | Social network based person information search and relational network drawing method | |
| Addison et al. | Setting conservation management thresholds using a novel participatory modeling approach | |
| Pollard | Applying the theory of planned behavior to individual computer energy saving behavioral intention and use at work | |
| Li et al. | Automated influence maintenance in social networks: an agent-based approach | |
| Holden et al. | Human judgment vs. quantitative models for the management of ecological resources | |
| Mosco | Marx in the Cloud | |
| CN107370659A (en) | Health control public number extension system and method based on wechat group | |
| Zhang et al. | Event organization 101: Understanding latent factors of event popularity | |
| Bentley et al. | Collective behaviour, uncertainty and environmental change | |
| KR101256652B1 (en) | System and method for predicting tour behaviour pattern of tourists | |
| Selvam et al. | Genetic algorithm based optimization for resource leveling problem with precedence constrained scheduling | |
| CN113569162A (en) | Data processing method, device, equipment and storage medium | |
| CN117252564A (en) | Resource scheduling method, device, computer equipment and storage medium |
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: 20191022 |
|
| WD01 | Invention patent application deemed withdrawn after publication |