CN102436506A - Mass data processing method and device for network server - Google Patents
Mass data processing method and device for network server Download PDFInfo
- Publication number
- CN102436506A CN102436506A CN201110447888XA CN201110447888A CN102436506A CN 102436506 A CN102436506 A CN 102436506A CN 201110447888X A CN201110447888X A CN 201110447888XA CN 201110447888 A CN201110447888 A CN 201110447888A CN 102436506 A CN102436506 A CN 102436506A
- Authority
- CN
- China
- Prior art keywords
- data
- user
- result
- network server
- mining model
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention is applicable to the field of computer data processing and provides a mass data processing method and a mass data processing device for a network server. The method comprises the following steps of: clearing up stored basic information data of a user and data generated by using service of the user by using the network server, and establishing a corresponding data warehouse; establishing a corresponding data mining model according to a predetermined mining target; and analyzing data warehouse data of the established mining model to obtain a mining result by a data mining algorithm. By the method, valuable information in recording data used by the user can be acquired, and the information can help a service provider better make a corresponding business decision; therefore, a better and more humanized using service is brought to the user.
Description
Technical field
The invention belongs to field of computer data processing, relate in particular to a kind of disposal route and device of network server end mass data.
Background technology
The Internet era people be unable to do without the network equipment; We carry out the Online Video program request through intelligent television or computer or Online Music is listened to through regular meeting; And before using this similar service, all need carry out user's registration usually, just can use these services after succeeding in registration; Need fill in some user-dependent individual essential informations simultaneously or after succeeding in registration in registration, such as age, sex, occupation or the like.And; The user also can produce a large amount of use data in the process of using various services; For example the user browses the Video service that this website provides behind a video website registered user, in browsing video, can produce such as having watched which video, having watched and how long, when to begin to watch or the like these to use data.These use the essential information data of data and user's registration all to exist in the webserver on backstage; And the provider of these present services does not utilize these data resources well; Just carry out some database manipulations commonly used with these data; Click ranking list etc. such as only having generated video with these data; Therefore prior art only is through simple statistical treatment for this mass data that is stored in the network server, does not bring more value information for service provider and user.
Summary of the invention
The present invention provides a kind of disposal route of mass data of network server end, be intended to solve prior art and do not make full use of the mass data that these users produce, can't for service provider and user bring more more than the technical matters of more valuable information.
The present invention is achieved in that a kind of disposal route of mass data of network server end, and said method comprises the steps:
The webserver is put the user's of storage essential information data and the data that the user uses service to produce in order, sets up corresponding data warehouse;
Excavation target according to confirming is in advance set up corresponding data mining model;
Adopt data mining algorithm to analyze the data warehouse data to the data mining model of setting up and obtain excavating the result.
Further,, said data mining model employing data mining algorithm analysis data warehouse data to foundation also comprise the steps: after obtaining excavating result step
Use the said excavation result's of data verification accuracy through new user; Preserve wherein the excavation result and the data mining model that produces these excavations result of high accuracy; Obtain new excavation result according to the data mining model of said generation and the mining algorithm of employing again, so circulation obtains best excavation result and mining model.
Another object of the present invention is to provide a kind of treating apparatus of mass data of network server end, described device comprises:
The data warehouse construction unit is used for the user's of webserver stores essential information data and the data that the user uses service to produce are put in order, sets up corresponding data warehouse;
Mining model is confirmed the unit, is used for setting up corresponding data mining model according to definite good excavation target;
Excavate generation unit as a result, be used for adopting data mining algorithm to analyze the data warehouse data and obtain excavating the result the data mining model of setting up.
Further, this device also comprises:
The results model authentication unit; Use the said excavation result's of data verification accuracy through new user; Preserve wherein the excavation result and the data mining model that produces these excavations result of high accuracy; Obtain new excavation result according to the data mining model of said generation and the mining algorithm of employing again, so circulation obtains best excavation result and mining model.
The invention has the beneficial effects as follows: the disposal route that the invention provides a kind of mass data of network server end; The essential information data load of this method through the data the user being used service and produce and user is in data warehouse; Excavate target and data mining model according to established data then; Adopt data mining algorithm to obtain containing the excavation result of information of forecasting; These excavate the result can helping service provider better make corresponding business decision, thus to the user brought better, the use service of hommization more.
Another beneficial effect of the present invention is: the treating apparatus that the invention provides a kind of mass data of network server end; The essential information data load of this device through the data the user being used service and produce and user is in data warehouse; Excavate target and data mining model according to established data then; Adopt data mining algorithm to obtain containing the excavation result of information of forecasting; These excavate the result can helping service provider better make corresponding business decision, thus to the user brought better, the use service of hommization more.
Description of drawings
Fig. 1 is the process flow diagram of the disposal route of the network server end mass data that provides of the embodiment of the invention;
Fig. 2 is the topology example figure of the decision tree that provides of the embodiment of the invention;
Fig. 3 is the structural drawing of the treating apparatus of the network server end mass data that provides of the embodiment of the invention.
Embodiment
In order to make the object of the invention, technical scheme and advantage clearer,, the present invention is further elaborated below in conjunction with accompanying drawing and embodiment.Should be appreciated that specific embodiment described herein only in order to explanation the present invention, and be not used in qualification the present invention.
Fig. 1 shows the treatment scheme of the mass data of the network server end that the embodiment of the invention provides, and only shows the part relevant with the embodiment of the invention for the ease of explanation.
In step S1, the use data that user basic information data of preserving when the webserver receives user's registration service and user are produced when using service.
In embodiments of the present invention; This step is the preposition step that is used for preserving user data; Described mass data is exactly a large amount of record data that customer group generates; Comprise the use data that the user uses certain service and produced (for example the user browses the Video service that this website provides behind a video website registered user, in browsing video, can produce such as watched which video, watched how long, when to begin to watch or the like these to use data) and user's essential information data itself.The network terminal (like computer, intelligent television etc.) that the user uses is connected with the webserver on backstage, and the above-mentioned record data that generate just are kept in the webserver.Usually the user needs the registered user before in the service of using service provider to provide (for example watch video, online tin of song, see e-book etc.); The back system that succeeds in registration distributes unique ID of this user identity of sign can for each user; Default password was logined network server when the user can and register through this ID; Perhaps logining successfully during registration, the back user also need fill in individual essential information and save as user basic information data (the individual essential information of the age of for example filling in, sex, occupation or the like); Registration and login back user just can use service provider to provide some to serve, and the use data of user's generation after this all are associated with this ID.
In step S2, the webserver is put the user's of storage essential information data and the data that the user uses this service to produce in order, to set up corresponding data warehouse.
In embodiments of the present invention; Described data warehouse is the basis of carrying out data analysis; Its groundwork is that the raw data in the database is carried out induction-arrangement; Be gathered into a data acquisition that can supply data mining, its purpose is to merge and organize these data, so that can analyze and be used for the supporting business decision-making to it.The essential information data that described user uses data that service produces and user possibly be chaotic as the information source of data mining; So the above-mentioned user that the webserver needs to receive uses data that service produces and user's essential information data to put in order; For example extract useful data message; Simultaneously these useful data messages are carried out data type conversion according to actual demand, generate the data type that is suitable for data mining, to set up corresponding data warehouse.Age data such as being stored in the user in the database all exists with digital form, makes up data warehouse for ease, can concrete age data be divided according to age bracket at this; Such as belonging to young below 30; 30 to 60 belong to the middle age, belong to old more than 60, when concrete the realization; Described age chopping rule can be self-defined according to actual needs, and the conversion of this data type can realize through SQL statement.These data after type conversion are arranged grouping according to field, finally be built into the data warehouse that is used for data mining.
In step S3, set up corresponding data mining model according to the excavation target of confirming in advance.
In embodiments of the present invention; Described excavation target is exactly according to the conceivable predictive content of Data Warehouse; Has good program request rate such as prediction swordsman type film; The content of this prediction is exactly determined excavation target so, and data mining model is exactly according to the content of this prediction and the corresponding a kind of prediction rule that generates.
In step S4, adopt data mining algorithm to analyze the data warehouse data to the data mining model of setting up and obtain excavating the result.
In embodiments of the present invention, the choosing of data mining algorithm determined the quality that predicts the outcome, and present embodiment is partial to sorting algorithm; Can select decision Tree algorithms for use at this; Decision tree is the structure of the tree of a similar process flow diagram, and top layer is a root node, below each inner node represent a test on the attribute; Each branch represents the output of a test; The distribution of each leaf node representation class or class, it can generate understandable rule, can show clearly that which field is important.
The elementary tactics of decision Tree algorithms is following:
Decision tree begins from the individual node of training sample;
If all at same type, node becomes leaf to training sample so, and uses such mark;
Otherwise, continue to select field to continue classification to training sample as node;
To each known property value of field, create a branch, and divide sample in view of the above;
Decision Tree algorithms uses same process recurrence to form the sample decision tree that each is divided, in case an attribute appears on the node, just needn't consider that attribute can appear on the offspring of this node.
When satisfying following three kinds of situation, the division of decision tree finishes:
(1) stops when all training samples of given node all belong to same time-like, and come this leaf of mark with such;
(2) stop when field can be used for further dividing training sample when not remaining, and come this leaf of mark with the class of the majority of training sample;
(3) when branch has training sample, do not stop, and come this leaf of mark with the class of the majority in the training sample.
In order to improve the efficient of decision Tree algorithms; The node of decision tree is selected very important; Adopt the mode of comparison information degree of gain to select each node in embodiments of the present invention, calculate the information gain degree of each attribute, by sequential build decision tree from small to large; Maximum as root node, and the like.
Enumerate the implementation procedure of this algorithm of example explanation below.
At first be ready to the data in the data warehouse, form is following:
| Sex | Age | Job specification | Films types | Attribute 4 | |
... | Attribute n | Predict the outcome |
| The man | Middle age | White collar | Terrified | ?... | ?... | ... | ... | Love is seen |
Above-mentioned data are that information source data to be excavated obtain after type conversion by actual demand; Convert the data type that helps data mining to; Here identical with precedent, can concrete age data be divided into three types of " youth ", " middle ages " and " old age " according to pre-defined rule.Because several kinds of attribute fields shown in possibly as above showing incessantly in the user record data for example can also comprise " video playback time point ", " video playback duration " or the like, these required attribute fields are omitted with n at this and are represented.And this attribute that predicts the outcome is the property value that just has in the sample data of excavating, and it mainly is the classification of paying close attention in certain bar data, and whether the user likes seeing this type of film, that is our predictive content.
The information gain degree that then calculates each field attribute is also confirmed the node location of decision tree in view of the above.With the age field attribute is example, at first calculates the mathematical expectation of " age " this attribute:
I (the S middle age, S is young, S is old)=-(log
2(P middle age)+log
2(P is young)+log
2(P is old))
" age " attribute is the probability that occurs in " middle age " in " P middle age " expression sample;
" age " attribute is the probability that " youth " occurs in " P is young " expression sample;
" age " attribute is the probability that occurs in " old age " in " P is old " expression sample;
Because " age " attribute has three different values, therefore can use " age " attribute to be divided into 3 sub-set to sample; Wherein " S middle age " expression age is the number in whole sample in " middle age "; Certainly in the middle of " S middle age " this sub-set, other some attributes are also arranged, such as comprising " sex " attribute: " S man ", " S woman " etc.According to dividing the entropy that three sub-set of coming out calculate them:
E(A)＝{(S11+S21+....Sm1)*I(S11，S21，....Sm1)/S}+{(S12+S22+....Sm2)*I(S12，S22，....Sm2)/S}+{(S13+S23+....Sm3)*I(S13，S23，....Sm3)/S}
Sx1 (x=1 wherein; 2...m) in " 1 " representation attribute be " middle age ", " x " expression " age " other attribute in addition is " man " such as " sex "; Therefore Sx1 is illustrated in the age property value in the sample set in " middle age "; Number with sample of other certain property value because also have much other attributes, therefore adopts m here and representes; Sx2 (x=1 in like manner; 2...m) be illustrated in the age property value in the sample set of " youth ", have the number of the sample of other certain property value, Sx3 (x=1; 2...m) be illustrated in the age property value in the sample set in " old age ", have the number of the sample of other certain property value.
Obtaining attribute at last for the information gain degree at " age " is:
Δ age=I (the S middle age, S is young, S is old)-E (A)
Because be " age " to be example only here with attribute field, if therefore the property value of other attribute has y state, promptly can be divided into the y sub-set, the normal formula for any one its entropy of attribute is so:
E(A)＝{(S11+S21+....Sm1)*I(S11，S21，....Sm1)/S}+{(S12+S22+....Sm2)*I(S12，S22，....Sm2)/S}+....+{(S1y+S2y+....Smy)*I(S1y，S2y，....Smy)/S}
In like manner can calculate the corresponding information gain degree of other attribute, again with all information gain degree by ordering from big to small, maximum as root node, and the like, finally obtain optimum decision tree.
For the ease of understanding,, provided the topology example of decision tree with reference to Fig. 2.
In diagram, provided the position of each attribute node according to the size of information gain degree, obvious " sex " attribute＞" age " attribute＞" films types " attribute here also has certainly that other attribute diagram is unlisted comes.
At first all sample datas are classified according to sexes; Be divided into " man ", " woman " two sub-set; In " man " subclass, be divided into " old age ", " youth " and " middle age " three sub-set according to the age again, the sample in the diagram in " old age " and " youth " subclass can't be classified, and becomes the leaf node in the decision tree; And " middle age " subclass is divided into a plurality of subclass according to films types; Comprising " terror ", " describing love affairs " or the like, at " terror " subclass and a series of other attributive classification of " describing love affairs " subclass process, finally can be predicting the outcome of " liking " or " disliking " on earth.
In the present embodiment, each predicts the outcome and can represent with an ID, and this ID has also represented corresponding data mining model simultaneously, predicts the outcome through the ID sign, is convenient to the later stage it is handled.
In step S5; Use the said excavation result's of data verification accuracy through new user; Preserve wherein the excavation result and the data mining model that produces these excavations result of high accuracy; Obtain new excavation result according to the data mining model of said generation and the mining algorithm of employing again, so circulation obtains best excavation result and mining model.
In embodiments of the present invention; After obtaining data mining results (promptly predicting the outcome); Excavate result and data mining model in order further to revise; Can verify described excavation result through the new use data that the user uses service to produce, preserve the higher excavation result of accuracy wherein in knowledge base, preserve corresponding data mining model simultaneously.Subsequently new data mining model and described mining algorithm are obtained excavating the result once more, just can obtain best excavation result and mining model through circulation several times like this.
In step S6, the said best excavation result who obtains is sent to service provider and/or user.
In embodiments of the present invention, after the excavation result sent to the service provider, the difference use hobby of different user colony can be known by service provider, and the service provider can make better business decision in view of the above.To excavate the result send to can help behind the user (for example can pass through short message mode) user better, the use service of hommization more.
In step S7, the said best excavation result who obtains is sent to the user, in interactive information that webserver reception user sends and the database that is saved in the storage user basic information.
In embodiments of the present invention; The user can carry out information interaction with the service provider after receiving and excavating the result; Interactive information is sent to the essential information of improving the user in the database; These information datas as the data source of excavating, can further be revised the excavation result like this and improved the accuracy rate of excavation.
Fig. 3 shows the structure of treating apparatus of the mass data of network server end, and said device comprises:
Data warehouse construction unit 10 is used for user with webserver stores and uses data that service produces and user's essential information data to put in order, sets up corresponding data warehouse, specifically like above-mentioned step S1 and the said content of S2, repeats no more at this.
Mining model is confirmed unit 20, is used for setting up corresponding data mining model according to the excavation target of confirming in advance, specifically like the said content of above-mentioned step S3, repeats no more at this.
Excavate generation unit 30 as a result, be used for adopting data mining algorithm to analyze the data warehouse data and obtain excavating the result, specifically, repeat no more at this like the said content of above-mentioned step S4 to the data mining model of setting up.
Further as preferred embodiment, this device also comprises:
Results model authentication unit 40; Use the said excavation result's of data verification accuracy through new user; Preserve wherein the excavation result and the data mining model that produces these excavations result of high accuracy, obtain new excavation result according to the data mining model of said generation and the mining algorithm of employing again, so circulation obtains best excavation result and mining model; Specifically, repeat no more at this like the said content of above-mentioned step S5.
Further as preferred embodiment, this device also comprises:
Excavate transmitting element 50 as a result, be used for the said best excavation result who obtains is sent to service provider and/or user, specifically, repeat no more at this like above-mentioned step S6 and the said content of S7.
In embodiments of the present invention; User record data through on the webserver are set up data warehouse, confirmed data mining target and data mining model after, adopt data mining algorithm to obtain corresponding data mining and predict the outcome; In repeated validation through follow-up excavation result; Obtain best excavation result, the service provider obtains can making better business decision after these excavate the result, has also brought better service for the user.
The above is merely preferred embodiment of the present invention, not in order to restriction the present invention, all any modifications of within spirit of the present invention and principle, being done, is equal to and replaces and improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. the disposal route of a network server end mass data is characterized in that, said method comprises the steps:
The webserver is put the user's of storage essential information data and the data that the user uses service to produce in order, sets up corresponding data warehouse;
Excavation target according to confirming is in advance set up corresponding data mining model;
Adopt data mining algorithm to analyze the data warehouse data to the data mining model of setting up to obtain excavating the result.
2. the disposal route of a kind of network server end mass data as claimed in claim 1 is characterized in that, after said data mining model employing data mining algorithm analysis data warehouse data to foundation obtain excavating result step, also comprises the steps:
Use the said excavation result's of data verification accuracy through new user; Preserve wherein the excavation result and the data mining model that produces these excavations result of high accuracy; Obtain new excavation result according to the data mining model of said generation and the mining algorithm of employing again, so circulation obtains best excavation result and mining model.
3. the disposal route of a kind of network server end mass data as claimed in claim 2 is characterized in that, after obtaining best excavation result and mining model, this method also comprises the steps:
The said best excavation result who obtains is sent to service provider and/or user.
4. the disposal route of a kind of network server end mass data as claimed in claim 2 is characterized in that, after obtaining best excavation result and mining model, this method also comprises the steps:
The said best excavation result who obtains is sent to the user, in interactive information that webserver reception user sends and the database that is saved in the storage user basic information.
5. like the disposal route of described any network server end mass data of claim 1 to 4; It is characterized in that; At the webserver user's of storage essential information data and the data that the user uses service to produce are put in order, set up corresponding data warehouse step and also comprise the steps: before
The use data that user basic information data of preserving when the webserver receives user's registration service and user are produced when using this service.
6. like the disposal route of described any network server end mass data of claim 1 to 4, it is characterized in that described data mining algorithm is a decision Tree algorithms.
7. the disposal route of a kind of network server end mass data as claimed in claim 6 is characterized in that, the decision tree that said decision Tree algorithms adopted is that the mode through the comparison information degree of gain makes up.
8. the treating apparatus of a network server end mass data is characterized in that, described device comprises:
The data warehouse construction unit is used for the user's of webserver stores essential information data and the data that the user uses service to produce are put in order, sets up corresponding data warehouse;
Mining model is confirmed the unit, is used for setting up corresponding data mining model according to the excavation target of confirming in advance;
Excavate generation unit as a result, be used for adopting data mining algorithm to analyze the data warehouse data and obtain excavating the result the data mining model of setting up.
9. the treating apparatus of a kind of network server end mass data as claimed in claim 8 is characterized in that, this device also comprises:
The results model authentication unit; Use the said excavation result's of data verification accuracy through new user; Preserve wherein the excavation result and the data mining model that produces these excavations result of high accuracy; Obtain new excavation result according to the data mining model of said generation and the mining algorithm of employing again, so circulation obtains best excavation result and mining model.
10. like the treating apparatus of the described a kind of network server end mass data of right, it is characterized in that this device also comprises:
Excavate transmitting element as a result, be used for the said best excavation result who obtains is sent to service provider and/or user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110447888XA CN102436506A (en) | 2011-12-27 | 2011-12-27 | Mass data processing method and device for network server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110447888XA CN102436506A (en) | 2011-12-27 | 2011-12-27 | Mass data processing method and device for network server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102436506A true CN102436506A (en) | 2012-05-02 |
Family
ID=45984568
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110447888XA Pending CN102436506A (en) | 2011-12-27 | 2011-12-27 | Mass data processing method and device for network server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102436506A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103425707A (en) * | 2012-05-25 | 2013-12-04 | 中兴通讯股份有限公司 | Data analyzing method and data analyzing device |
| CN104636954A (en) * | 2014-12-08 | 2015-05-20 | 北京掌阔技术有限公司 | Data mining method and data mining device for advertising media putting quantity |
| CN105243515A (en) * | 2015-11-09 | 2016-01-13 | 浙江中之杰软件技术有限公司 | Enterprise condition management system |
| CN105589896A (en) * | 2014-11-14 | 2016-05-18 | 北大方正集团有限公司 | Data mining method and device |
| CN105787010A (en) * | 2016-02-23 | 2016-07-20 | 北京凯行同创科技有限公司 | Acquisition processing and pushing method and system based on personal data |
| CN106156127A (en) * | 2015-04-08 | 2016-11-23 | 深圳市腾讯计算机系统有限公司 | Select the method and device that data content pushes to terminal |
| CN107046480A (en) * | 2017-04-17 | 2017-08-15 | 广东经纬天地科技股份有限公司 | A kind of user's perception evaluating method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101110115A (en) * | 2006-07-20 | 2008-01-23 | 阿里巴巴公司 | Method for processing merchandise information in internet and system thereof |
| CN101639842A (en) * | 2008-07-29 | 2010-02-03 | 阿里巴巴集团控股有限公司 | Characteristics data statistic method and system of members |
| CN102054002A (en) * | 2009-10-28 | 2011-05-11 | 中国移动通信集团公司 | Method and device for generating decision tree in data mining system |
| CN102073960A (en) * | 2010-09-15 | 2011-05-25 | 江苏仕德伟网络科技股份有限公司 | Method for assessing operation effect in website marketing process |
-
2011
- 2011-12-27 CN CN201110447888XA patent/CN102436506A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101110115A (en) * | 2006-07-20 | 2008-01-23 | 阿里巴巴公司 | Method for processing merchandise information in internet and system thereof |
| CN101639842A (en) * | 2008-07-29 | 2010-02-03 | 阿里巴巴集团控股有限公司 | Characteristics data statistic method and system of members |
| CN102054002A (en) * | 2009-10-28 | 2011-05-11 | 中国移动通信集团公司 | Method and device for generating decision tree in data mining system |
| CN102073960A (en) * | 2010-09-15 | 2011-05-25 | 江苏仕德伟网络科技股份有限公司 | Method for assessing operation effect in website marketing process |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103425707A (en) * | 2012-05-25 | 2013-12-04 | 中兴通讯股份有限公司 | Data analyzing method and data analyzing device |
| CN105589896A (en) * | 2014-11-14 | 2016-05-18 | 北大方正集团有限公司 | Data mining method and device |
| CN105589896B (en) * | 2014-11-14 | 2019-03-12 | 北大方正集团有限公司 | Data digging method and device |
| CN104636954A (en) * | 2014-12-08 | 2015-05-20 | 北京掌阔技术有限公司 | Data mining method and data mining device for advertising media putting quantity |
| CN106156127A (en) * | 2015-04-08 | 2016-11-23 | 深圳市腾讯计算机系统有限公司 | Select the method and device that data content pushes to terminal |
| CN106156127B (en) * | 2015-04-08 | 2020-06-16 | 深圳市腾讯计算机系统有限公司 | Method and device for selecting data content to push to terminal |
| US10789311B2 (en) | 2015-04-08 | 2020-09-29 | Tencent Technology (Shenzhen) Company Limited | Method and device for selecting data content to be pushed to terminal, and non-transitory computer storage medium |
| CN105243515A (en) * | 2015-11-09 | 2016-01-13 | 浙江中之杰软件技术有限公司 | Enterprise condition management system |
| CN105243515B (en) * | 2015-11-09 | 2022-01-18 | 浙江中之杰软件技术有限公司 | Enterprise condition management system |
| CN105787010A (en) * | 2016-02-23 | 2016-07-20 | 北京凯行同创科技有限公司 | Acquisition processing and pushing method and system based on personal data |
| CN105787010B (en) * | 2016-02-23 | 2019-08-16 | 北京凯行同创科技有限公司 | Acquisition process and method for pushing and system based on personal data |
| CN107046480A (en) * | 2017-04-17 | 2017-08-15 | 广东经纬天地科技股份有限公司 | A kind of user's perception evaluating method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111428881B (en) | Recognition model training method, device, equipment and readable storage medium | |
| US11538064B2 (en) | System and method of providing a platform for managing data content campaign on social networks | |
| CN102436506A (en) | Mass data processing method and device for network server | |
| CN108574706B (en) | Media file pushing method and device | |
| CN108536650B (en) | Method and device for generating gradient lifting tree model | |
| CN108205766A (en) | Information-pushing method, apparatus and system | |
| KR20160058896A (en) | System and method for analyzing and transmitting social communication data | |
| CN103069413A (en) | Customizing content displayed for a user based on user preferences of another user | |
| CN104054055A (en) | Identifying and tracking user activity when using networked devices based on associations between identifiers for physical devices or software applications | |
| US20190147500A1 (en) | Media Planning System | |
| CN104657372A (en) | Page operation data processing method and device | |
| CN109446171B (en) | Data processing method and device | |
| CN102880688A (en) | Method, device and equipment for evaluating webpage | |
| CN106534902A (en) | Behavior analysis method and system | |
| US9866454B2 (en) | Generating anonymous data from web data | |
| US10936601B2 (en) | Combined predictions methodology | |
| CN106850406B (en) | Content sharing method and device | |
| US20180204248A1 (en) | Web page viewership prediction | |
| JP2013105213A (en) | Information recommending device and method, and device and program | |
| Kolar et al. | People in motion: Spatio-temporal analytics on call detail records | |
| CN109614521A (en) | A kind of efficient secret protection subgraph inquiry processing method | |
| CN110196949A (en) | Information-pushing method, device, electronic equipment and computer-readable medium | |
| US20150200905A1 (en) | Systems and methods for improving efficiency of electronic transmission of messages | |
| CN115345635A (en) | Processing method and device for recommended content, computer equipment and storage medium | |
| CA2967572A1 (en) | Media planning system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20120502 |