CN103854206A - Method and device for analyzing group characteristics - Google Patents
Method and device for analyzing group characteristics Download PDFInfo
- Publication number
- CN103854206A CN103854206A CN201410081661.1A CN201410081661A CN103854206A CN 103854206 A CN103854206 A CN 103854206A CN 201410081661 A CN201410081661 A CN 201410081661A CN 103854206 A CN103854206 A CN 103854206A
- Authority
- CN
- China
- Prior art keywords
- crowd
- attribute
- characteristic
- information
- distributed 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.)
- Granted
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention aims at providing a method and device for analyzing group characteristics. A library establishing device is used for collecting group attribute information and establishing a group attribute library. A modeling device is used for establishing a group characteristic distribution model based on the group attribute library. An analyzing device is used for analyzing the characteristic information of a target group based on the analyzing model. Compared with the prior art, the method has the advantage that characteristic analyzing can be effectively carried out on any selected target group by establishing the group attribute library and the group characteristic distribution model.
Description
Technical field
The present invention relates to internet arena, relate in particular to a kind of method and apparatus of analyst's group character.
Background technology
At existing internet arena, in order to diffuse information better, need to obtain corresponding with it target group, thus, the analysis demand of crowd characteristic continues to increase.Such as, automobile vendor thirsts for understanding to feature distributions such as the interested crowd's sex of automobile, age, income, hobbies very much, and cosmetics company wants that the feature of understanding its potential user distributes very much.Traditional crowd characteristic analytical approach, such as by Field Research or propagate the mode of questionnaire on the net, is analyzed crowd's feature.Typically, by transferring the sales data of automobile vendor, analyze and obtain, to the interested crowd characteristic of automobile, comprising sex ratio, age distribution, hobby; By planned network questionnaire, questionnaire is thrown on the website of often accessing target group, collect the questionnaire information of target group's feedback, analyze the feature that obtains target group.
But conventionally there is following defect in traditional crowd characteristic analytical approach: mode underaction, the analytical characteristic dimension of Field Research are few, the cycle of obtaining information is long, narrow range; The online higher data of the more difficult acquisition confidence level of mode of propagating questionnaire, affect the accuracy that crowd characteristic is analyzed.
Summary of the invention
The object of this invention is to provide a kind of method and apparatus of analyst's group character.
According to an aspect of the present invention, provide a kind of method of analyst's group character, the method comprises the following steps:
Collection crowd attribute information, sets up crowd's attribute library;
Based on described crowd's attribute library, set up crowd characteristic distributed model;
Based on described distributed model, evaluating objects crowd's characteristic information.
Wherein, described attribute information at least comprises the ascribed characteristics of population, personal preference, purchase intention and Regional Property.
Further, described based on described distributed model, the step of evaluating objects crowd's characteristic information specifically comprises:
Response user treats evaluating objects crowd's selection operation;
Based on described distributed model, evaluating objects crowd's characteristic information;
The characteristic information that described analysis is obtained is back to the terminal page in real time.
According to another aspect of the present invention, also provide a kind of equipment of analyst's group character, this equipment comprises:
Be used for gathering crowd's attribute information, set up the device (being called for short " building storehouse device ") of crowd's attribute library;
Based on described crowd's attribute library, set up the device (being called for short " model building device ") of crowd characteristic distributed model;
Based on described distributed model, the device of evaluating objects crowd's characteristic information (being called for short " analytical equipment ").
Wherein, described attribute information at least comprises the ascribed characteristics of population, personal preference, purchase intention and Regional Property.
Further, described analytical equipment specifically comprises with lower module:
Treat for responding user the module (being called for short " selection respond module ") that evaluating objects crowd selects operation;
Be used for based on described distribution module the module of evaluating objects crowd's characteristic information (being called for short " analysis module ");
Be back in real time the module (being called for short " returning to module ") of the terminal page for the characteristic information that described analysis is obtained.
Compared with prior art, the present invention has the following advantages: the instrument that the invention provides a self-service analysis internet specific crowd feature, crowd characteristic that can any colony of real-time analysis distributes, can save a large amount of investigation in early stage and analysis time, throw in good Data support is provided for the network information.Particularly the present invention carries out batch quantity analysis rather than only can carry out signature analysis to unique user, effectively lifting feature analysis efficiency crowd characteristic.And the diversity ratio that the present invention also provides all user characteristicses in the feature of special group and database, is thrown in good Data support is provided for information.
Accompanying drawing explanation
By reading the detailed description that non-limiting example is done of doing with reference to the following drawings, it is more obvious that other features, objects and advantages of the present invention will become:
Fig. 1 illustrates the equipment schematic diagram of analyst's group character in accordance with a preferred embodiment of the present invention;
Fig. 2 illustrates the interface schematic diagram of analyst's group character in accordance with a preferred embodiment of the present invention;
Fig. 3 illustrates according to the method flow diagram of analyst's group character of another preferred embodiment of the present invention;
In accompanying drawing, same or analogous Reference numeral represents same or analogous parts.
Embodiment
Below in conjunction with accompanying drawing, the present invention is described in further detail.
Fig. 1 illustrates the equipment schematic diagram of analyst's group character in accordance with a preferred embodiment of the present invention; Wherein, this equipment comprises: for gathering crowd's attribute information, set up the device 101 (being called for short " building storehouse device ") of crowd's attribute library; Based on described crowd's attribute library, set up the device 102 (being called for short " model building device ") of crowd characteristic distributed model; Based on described distributed model, the device 103 of evaluating objects crowd's characteristic information (being called for short " analytical equipment ").At this, described equipment includes but not limited to any electronic product that can carry out with user man-machine interaction by keyboard, telepilot, touch pad or voice-operated device, such as computing machine, smart mobile phone, PAD etc.Those skilled in the art will be understood that other equipment is equally applicable to the present invention, also should be included in protection domain of the present invention, and be contained in this at this with way of reference.
Between above-mentioned each device, be constant work, at this, it will be understood by those skilled in the art that " continuing " refers to above-mentioned each device respectively in real time, or according to the mode of operation requirement of setting or adjust in real time, carry out work.
Build storehouse device 101 and gather crowd's attribute information, set up crowd's attribute library.Wherein, described attribute information at least comprises the ascribed characteristics of population, personal preference, purchase intention and Regional Property.
Particularly, crowd herein mainly refers to, according to certain classification, the network user is carried out to colony's division.The described storehouse device of building can gather crowd's attribute information by the webserver, comprises crowd's self attributes, such as the ascribed characteristics of population, personal preference, purchase intention and Regional Property etc.; Can also comprise the relevant information that crowd conducts interviews to the particular content on specific website or webpage, for example access times to website URL in section sometime, pageview to certain particular content on website, visit capacity, click volume, clicking rate etc.At this, the content that crowd's attribute information is specifically comprised is not construed as limiting.Wherein, the webserver is accessed the platform of internet as user, on the webserver, can comprise the device of the various customer attribute informations for record access website or web site contents, as data acquisition unit, counter, registers etc., for gathering and add up the customer attribute information of access internet.The described webserver can be traditional server mode, can be also the form such as base station, website.
The described storehouse device of building, after the crowd of collection attribute information, is set up crowd's attribute library.In this crowd's attribute library, according to different attribute classifications, crowd's attribute is carried out to modularization classification.Particularly, described while building the relevant information that storehouse device conducts interviews to website or web site contents the crowd that obtains, the for example number of times to a certain class website or web site contents in certain a period of time, or when the visit data to inhomogeneity website or web site contents etc. cannot directly carry out modularization classification, by data analysis, formation crowd attribute library is easy to the data type of further processing, and realizes the modularization classification of crowd's attribute.For example, be categorized as at least with lower module according to crowd's self attributes:
1) including user's sex, age, income or/and the ascribed characteristics of population module the dimensions such as identity occupation;
2) user is in the hobby module in each field;
3) user is in the purchase intention module in each field;
4) user's Regional Property module.
And for example, carry out modularization classification according to the relevant information of user's access websites or web site contents, for example, the crowd who pays close attention to automotive-type website or web site contents can be divided to automotive-type module.
At this, dimension or the attribute of modularization classification institute foundation are not limited, can carry out module classification according to various attribute informations if desired.
Wherein, described in, build storehouse device include but not limited to subscriber equipment, the network equipment or the network equipment with subscriber equipment by the mutually integrated equipment forming of network; The described network equipment includes but not limited to the cloud that computing machine, network host, single network server, multiple webserver collection or multiple server form; Described network equipment end includes but not limited to website service end or network monitoring end, and described network service end and network monitoring end can be one end, also can separate independent.
Particularly, described model building device 102 is based on described crowd's attribute library of building storehouse device foundation, and by data analysis, the step of setting up crowd characteristic distributed model mainly comprises:
-a analyzes the feature of all users in described crowd's attribute library, comprises such as Sex distribution, age distribution, every profession and trade interest crowd distribution etc., obtain the feature distributed intelligence of all groups in crowd's attribute library.
-b samples and special format processing to the data in described crowd's attribute library, is loaded into memory database or other databases according to specific data structure., obtain crowd's attribute sample information based on this step, and form corresponding crowd's attribute sample information storehouse.
-c sets up crowd characteristic distributed model.Particularly, according to all users' feature distribution situation and described crowd's attribute sample information storehouse, utilize and carry out model training such as Classification Algorithms in Data Mining, obtain crowd characteristic distributed model.At this, the algorithm of model training is not construed as limiting.
Particularly, the crowd characteristic distributed model that described analytical equipment 103 is set up based on described model building device 102, analyzes specific objective crowd's characteristic information.Typically, described analytical equipment, for arbitrarily selected crowd, can analyze its corresponding crowd characteristic, such as the ascribed characteristics of population such as age, sex feature and this crowd's hobby feature, purchase intention feature etc.
Further, described analytical equipment specifically comprises with lower module:
M treats for responding user the module (being called for short " selection respond module ") that evaluating objects crowd selects operation;
N is used for based on described distribution module, the module of evaluating objects crowd's characteristic information (being called for short " analysis module ");
O is back to the module (being called for short " returning to module ") of the terminal page in real time for the characteristic information that described analysis is obtained.
Further, the crowd characteristic distributed model that above-mentioned model building device 102 is set up is the feature distributed intelligence based on described all users and crowd's attribute sample information storehouse mainly, calculates the attributive character distribution of specific crowd and specific crowd and the whole network crowd's feature difference.Such as, in the time that user selects target group and " has the purchase intention of BMW ", described analytical equipment is analyzed audient's feature of this target group based on described crowd characteristic distributed model, obtains in this target group 40% people and has the features such as distribution characteristics " has the purchase intention of Adui " simultaneously and distribute.By described feature distributed data, can clearly embody the correlativity of BMW crowd with the crowd of Audi.
According to the equipment of analyst's group character provided by the invention, the feature of all users in the feature of special group and described crowd's attribute library can be carried out to otherness comparison, for example, based on described crowd's attribute library, it is total user's 60% that described analysis module obtains masculinity proportion by analysis, simultaneously, obtaining masculinity proportion in target group is 90% of target group's sum, according to described two ratios, can learn that in target group, audient more lays particular stress on the male sex, and, in conjunction with other multiattribute dimensions more, described analysis module can further analyze the feature difference of all users in target group and described crowd's attribute library, thereby audience selection and the analysis etc. of carrying out information input for client provide good data analysis support.
In order better the technical program to be described, please refer to Fig. 2, Fig. 2 shows the interface schematic diagram of analyst's group character in accordance with a preferred embodiment of the present invention.In Fig. 2, left side shows crowd's attributive classification tree (being the crowd's attributive classification in demographic database), and described classification tree carries out labeling based on internet mass information, web site contents, network user's own characteristic etc. to crowd's attribute information.For example, can carry out editor's refinement of labeling from " individual concern, the ascribed characteristics of population, Regional Distribution, purchase intention " these four angles.Wherein, under the label of " ascribed characteristics of population ", be divided into multiple subtabs such as sex, age, identity occupation; " individual pays close attention to " label magnanimity information Network Based produces, and is divided into multiple different point of interest subtabs under it; Under " purchase intention ", be divided into user has purchase intention subtab to different product or service; Under " Regional Distribution " label, be divided into the subtab of multiple different cities.In the present embodiment, in described classification tree, each classification label can be distinguished different crowds.In classification tree, different classification labels shines upon mutually with corresponding crowd's attribute data.Comparatively speaking, the classification label in classification tree is fixed, and can construct different user property classification by different permutation and combination.
Wherein, described classification tree can be built storehouse device 101 and described model building device 102 is set up based on described, and is presented in interface.
In Fig. 2, center section shows the object that can analyze based on classification tree and alternative target analysis colony.Wherein, the form of the retrieval type that the content of described analysis purpose can be by obtaining user input obtains, and also can obtain such as the form of selecting the sub-option in drop-down list by response user, in this no limit.For example, in Fig. 2, shown analysis purpose content is " crowd characteristic of analyzing Beijing area concern automobile ".Wherein, the form that alternative target analysis colony can be drawn to the classification label in left side in specific webpage region by response user is determined.Certainly, described selection is not limited to this form that pulls, also can comprise operations such as double-click, slip, can also from drop-down list, select or receive the retrieval type of user's input, such as by page technology such as ASP, JSP or PHP, obtain the retrieval type of user in the input of the inputting interface such as search box, query frame; Or mutual by with the third party device such as search engine, obtains the retrieval type of this user's input.At this, the mode of selecting is not limited.For example, in Fig. 2, by response user, the classification label in left side " sex: man " and " individual pays close attention to: automobile " are drawn in a virtual box, to determine target group to be analyzed.
In Fig. 2, right side shows according to above-mentioned analysis purpose and target group, analyzes the feature distribution results obtaining.Take purchase intention as example, show the crowd of Beijing area concern automobile, product corresponding to its purchase intention mainly comprises automobile, finance and economics finance, 3C Product, service for life etc.Wherein, shown Count can represent the pass fluence of this user to specific products or service or website, also can represent the click volume of this user to specific products or service or website, can also represent other indexes, in this no limit, only for example, in like manner, shown Final Percent (final number percent) and Index are also only for example, and the content that actual analysis obtains includes but not limited to the analysis result shown in Fig. 2.Also, the displaying at described interface is example, is not the restriction to technical solution of the present invention.
Fig. 3 illustrates according to the method flow diagram of analyst's group character of another preferred embodiment of the present invention.Particularly, in step s1, build storehouse device collection crowd attribute information, set up crowd's attribute library; In step s2, model building device, based on described crowd's attribute library, is set up crowd characteristic distributed model; In step s3, analytical equipment is based on described analytical model, evaluating objects crowd's characteristic information.At this, described equipment includes but not limited to any electronic product that can carry out with user man-machine interaction by keyboard, telepilot, touch pad or voice-operated device, such as computing machine, smart mobile phone, PAD etc.Those skilled in the art will be understood that other equipment is equally applicable to the present invention, also should be included in protection domain of the present invention, and be contained in this at this with way of reference.
Between above steps, be constant work, at this, it will be understood by those skilled in the art that " continuing " refers to above steps difference in real time or according to the mode of operation requirement of setting or adjust in real time, carry out above steps.
Wherein, in step s1, build storehouse device collection crowd attribute information, set up crowd's attribute library.Wherein, described attribute information at least comprises the ascribed characteristics of population, personal preference, purchase intention and Regional Property.
Particularly, crowd herein mainly refers to, according to certain classification, the network user is carried out to colony's division.The described storehouse device of building can gather crowd's attribute information by the webserver, comprises crowd's self attributes, such as the ascribed characteristics of population, personal preference, purchase intention and Regional Property etc.; Can also comprise the relevant information that crowd conducts interviews to the particular content on specific website or webpage, for example access times to website URL in section sometime, pageview to certain particular content on website, visit capacity, click volume, clicking rate etc.At this, the content that crowd's attribute information is specifically comprised is not construed as limiting.Wherein, the webserver is accessed the platform of internet as user, on the webserver, can comprise the device of the various customer attribute informations for record access website or web site contents, as data acquisition unit, counter, registers etc., for gathering and add up the customer attribute information of access internet.The described webserver can be traditional server mode, can be also the form such as base station, website.
The described storehouse device of building, after the crowd of collection attribute information, is set up crowd's attribute library.In this crowd's attribute library, according to different attribute classifications, crowd's attribute is carried out to modularization classification.Particularly, described while building the relevant information that storehouse device conducts interviews to website or web site contents the crowd that obtains, the for example number of times to a certain class website or web site contents in certain a period of time, or when the visit data to inhomogeneity website or web site contents etc. cannot directly carry out modularization classification, by data analysis, formation crowd attribute library is easy to the data type of further processing, and realizes the modularization classification of crowd's attribute.For example, be categorized as at least with lower module according to crowd's self attributes:
1) including user's sex, age, income or/and the ascribed characteristics of population module the dimensions such as identity occupation;
2) user is in the hobby module in each field;
3) user is in the purchase intention module in each field;
4) user's Regional Property module.
And for example, carry out modularization classification according to the relevant information of user's access websites or web site contents, for example, the crowd who pays close attention to automotive-type website or web site contents can be divided to automotive-type module.
At this, dimension or the attribute of modularization classification institute foundation are not limited, can carry out module classification according to various attribute informations if desired.
In step s2, model building device, based on described crowd's attribute library, is set up crowd characteristic distributed model.Particularly, described model building device is based on described crowd's attribute library of building storehouse device foundation, and by data analysis, the step of setting up crowd characteristic distributed model mainly comprises:
-a analyzes the feature of all users in described crowd's attribute library, comprises such as Sex distribution, age distribution, every profession and trade interest crowd distribution etc., obtain the feature distributed intelligence of all groups in crowd's attribute library.
-b samples and special format processing to the data in described crowd's attribute library, is loaded into memory database or other databases according to specific data structure., obtain crowd's attribute sample information based on this step, and form corresponding crowd's attribute sample information storehouse.
-c sets up crowd characteristic distributed model.Particularly, according to all users' feature distribution situation and described crowd's attribute sample information storehouse, utilize and carry out model training such as Classification Algorithms in Data Mining, obtain crowd characteristic distributed model.At this, the algorithm of model training is not construed as limiting.
In step s3, analytical equipment is based on described distributed model, evaluating objects crowd's characteristic information.Particularly, the crowd characteristic distributed model that described analytical equipment is set up based on described model building device, analyzes specific objective crowd's characteristic information.Typically, described analytical equipment, for arbitrarily selected crowd, can analyze its corresponding crowd characteristic, such as the ascribed characteristics of population such as age, sex feature and this crowd's hobby feature, purchase intention feature etc.
Further, described step s3 specifically comprises the following steps:
R response user treats the operation that evaluating objects crowd selects.Typically, the form by response user, the classification label in classification tree being drawn in specific webpage region is determined target group.
S is based on described distribution module, evaluating objects crowd's characteristic information.Wherein, the analysis dimension of described characteristic information is in this no limit, includes but not limited to index and the number percents etc. such as visit capacity, click volume, clicking rate.
The characteristic information that t obtains described analysis is back to the terminal page in real time.Typically, the characteristic information by the page technology such as such as JSP, ASP, PHP, analysis being obtained is back to the terminal page in real time.
Further, the crowd characteristic distributed model that above-mentioned model building device is set up is the feature distributed intelligence based on described all users and crowd's attribute sample information storehouse mainly, calculates the attributive character distribution of specific crowd and specific crowd and the whole network crowd's feature difference.Such as, in the time that user selects target group and " has the purchase intention of BMW ", described analytical equipment is analyzed audient's feature of this target group based on described crowd characteristic distributed model, obtains in this target group 40% people and has the features such as distribution characteristics " has the purchase intention of Adui " simultaneously and distribute.By described feature distributed data, can clearly embody the correlation information of BMW crowd with the crowd of Audi.
According to the method for analyst's group character provided by the invention, the feature of all users in the feature of special group and described crowd's attribute library can be carried out to otherness comparison, for example, based on described crowd's attribute library, it is total user's 60% that described analysis module obtains masculinity proportion by analysis, simultaneously, obtaining masculinity proportion in target group is 90% of target group's sum, according to described two ratios, can learn that in target group, audient more lays particular stress on the male sex, and, in conjunction with other multiattribute dimensions more, described analysis module can further analyze the feature difference of all users in target group and described crowd's attribute library, thereby audience selection and the analysis etc. of carrying out information input for client provide good data analysis support.
To those skilled in the art, obviously the invention is not restricted to the details of above-mentioned one exemplary embodiment, and in the situation that not deviating from spirit of the present invention or essential characteristic, can realize the present invention with other concrete form.Therefore, no matter from which point, all should regard embodiment as exemplary, and be nonrestrictive, scope of the present invention is limited by claims rather than above-mentioned explanation, is therefore intended to all changes that drop in the implication and the scope that are equal to important document of claim to include in the present invention.Any Reference numeral in claim should be considered as limiting related claim.
Claims (8)
1. a method for analyst's group character, the method comprises the following steps:
Collection crowd attribute information, sets up crowd's attribute library;
Based on described crowd's attribute library, set up crowd characteristic distributed model;
Based on described distributed model, evaluating objects crowd's characteristic information.
2. method according to claim 1, wherein, described attribute information at least comprises the ascribed characteristics of population, personal preference, purchase intention and Regional Property.
3. method according to claim 1 and 2, wherein, described based on described distributed model, the step of evaluating objects crowd's characteristic information specifically comprises:
The operation that response user selects target group to be analyzed;
Based on described distributed model, analyze described target group's characteristic information;
The characteristic information that described analysis is obtained is back to the terminal page in real time.
4. method according to claim 1 and 2, wherein, the described step of setting up crowd characteristic distributed model mainly comprises:
Obtain the feature distributed intelligence of all groups in crowd's attribute library;
Described feature distributed intelligence is sampled and formatd processing, obtain crowd's attribute sample information, and form corresponding crowd's attribute sample information storehouse;
Set up crowd characteristic distributed model.
5. an equipment for analyst's group character, this equipment comprises:
Be used for gathering crowd's attribute information, set up the device of crowd's attribute library;
Based on described crowd's attribute library, set up the device of crowd characteristic distributed model;
Based on described distributed model, the device of evaluating objects crowd's characteristic information.
6. equipment according to claim 5, wherein, described attribute information at least comprises the ascribed characteristics of population, personal preference, purchase intention and Regional Property.
7. according to the equipment described in claim 5 or 6, wherein, described based on described distributed model, the device of evaluating objects crowd's characteristic information specifically comprises:
For responding user, target group to be analyzed is selected the module of operation;
Be used for based on described distribution module the module of evaluating objects crowd's characteristic information;
Be back in real time the module of the terminal page for the characteristic information that described analysis is obtained.
8. according to the equipment described in claim 5 or 6, wherein, the described concrete execution step of device of setting up crowd characteristic distributed model mainly comprises:
Obtain the feature distributed intelligence of all groups in crowd's attribute library;
Described feature distributed intelligence is sampled and formatd processing, obtain crowd's attribute sample information, and form corresponding crowd's attribute sample information storehouse;
Set up crowd characteristic distributed model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410081661.1A CN103854206B (en) | 2014-03-06 | 2014-03-06 | A kind of method and apparatus of analysis crowd characteristic |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410081661.1A CN103854206B (en) | 2014-03-06 | 2014-03-06 | A kind of method and apparatus of analysis crowd characteristic |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103854206A true CN103854206A (en) | 2014-06-11 |
CN103854206B CN103854206B (en) | 2018-10-02 |
Family
ID=50861828
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410081661.1A Active CN103854206B (en) | 2014-03-06 | 2014-03-06 | A kind of method and apparatus of analysis crowd characteristic |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103854206B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104050394A (en) * | 2014-07-04 | 2014-09-17 | 北京师范大学 | Modeling method and topological attribute analytical method for group brain network |
CN105323601A (en) * | 2014-07-18 | 2016-02-10 | 上海星红桉数据科技有限公司 | Personnel attribute identification method based on multi-screen user behavior data |
CN106056407A (en) * | 2016-06-03 | 2016-10-26 | 北京网智天元科技股份有限公司 | Online banking user portrait drawing method and equipment based on user behavior analysis |
CN108241989A (en) * | 2016-12-26 | 2018-07-03 | 北京国双科技有限公司 | Otherness data capture method and device |
CN109815987A (en) * | 2018-12-27 | 2019-05-28 | 北京卓思天成数据咨询股份有限公司 | A kind of listener clustering method and categorizing system |
CN110427546A (en) * | 2018-04-28 | 2019-11-08 | 北京京东尚科信息技术有限公司 | A kind of information displaying method and device |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102103603A (en) * | 2009-12-18 | 2011-06-22 | 百度在线网络技术(北京)有限公司 | User behavior data analysis method and device |
CN102592236A (en) * | 2011-12-28 | 2012-07-18 | 北京品友互动信息技术有限公司 | Internet advertising crowd analysis system and analysis method |
-
2014
- 2014-03-06 CN CN201410081661.1A patent/CN103854206B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102103603A (en) * | 2009-12-18 | 2011-06-22 | 百度在线网络技术(北京)有限公司 | User behavior data analysis method and device |
CN102592236A (en) * | 2011-12-28 | 2012-07-18 | 北京品友互动信息技术有限公司 | Internet advertising crowd analysis system and analysis method |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104050394A (en) * | 2014-07-04 | 2014-09-17 | 北京师范大学 | Modeling method and topological attribute analytical method for group brain network |
CN104050394B (en) * | 2014-07-04 | 2017-10-17 | 北京师范大学 | The modeling method and its topological attribute analysis method of colony's brain network |
CN105323601A (en) * | 2014-07-18 | 2016-02-10 | 上海星红桉数据科技有限公司 | Personnel attribute identification method based on multi-screen user behavior data |
CN106056407A (en) * | 2016-06-03 | 2016-10-26 | 北京网智天元科技股份有限公司 | Online banking user portrait drawing method and equipment based on user behavior analysis |
CN108241989A (en) * | 2016-12-26 | 2018-07-03 | 北京国双科技有限公司 | Otherness data capture method and device |
CN110427546A (en) * | 2018-04-28 | 2019-11-08 | 北京京东尚科信息技术有限公司 | A kind of information displaying method and device |
CN109815987A (en) * | 2018-12-27 | 2019-05-28 | 北京卓思天成数据咨询股份有限公司 | A kind of listener clustering method and categorizing system |
CN109815987B (en) * | 2018-12-27 | 2020-12-01 | 北京卓思天成数据咨询股份有限公司 | Crowd classification method and system |
Also Published As
Publication number | Publication date |
---|---|
CN103854206B (en) | 2018-10-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9881042B2 (en) | Internet based method and system for ranking individuals using a popularity profile | |
CN104090919B (en) | Advertisement recommending method and advertisement recommending server | |
CN107871244B (en) | Method and device for detecting advertising effect | |
CN108550068B (en) | Personalized commodity recommendation method and system based on user behavior analysis | |
JP5596152B2 (en) | Information matching method and system on electronic commerce website | |
Lu et al. | BizSeeker: a hybrid semantic recommendation system for personalized government‐to‐business e‐services | |
CN107862022B (en) | Culture resource recommendation system | |
US8341101B1 (en) | Determining relationships between data items and individuals, and dynamically calculating a metric score based on groups of characteristics | |
CN106682686A (en) | User gender prediction method based on mobile phone Internet-surfing behavior | |
CN103854206A (en) | Method and device for analyzing group characteristics | |
Ridge et al. | The use of big data analytics in the retail industries in South Africa | |
KR101566616B1 (en) | Advertisement decision supporting system using big data-processing and method thereof | |
CN105023165A (en) | Method, device and system for controlling release tasks in social networking platform | |
CN108885624A (en) | Information recommendation system and method | |
US10565627B2 (en) | Systems and methods for automatically generating remarketing lists | |
US20140195303A1 (en) | Method of automated group identification based on social and behavioral information | |
CN111967914A (en) | User portrait based recommendation method and device, computer equipment and storage medium | |
CN107077498A (en) | The presentation-entity relation in online advertisement | |
Azcorra et al. | Unsupervised scalable statistical method for identifying influential users in online social networks | |
KR20200025431A (en) | Total management system and method about open market | |
Dias et al. | Automating the extraction of static content and dynamic behaviour from e-commerce websites | |
US9508087B1 (en) | Identifying similar display items for potential placement of content items therein | |
Guarita et al. | Monitoring drug trends in the digital environment–new methods, challenges and the opportunities provided by automated approaches | |
KR100901782B1 (en) | Method and System for Generating Marketing Information | |
CN107357847B (en) | Data processing method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CP03 | Change of name, title or address | ||
CP03 | Change of name, title or address |
Address after: Unit 01, 9th Floor, Building 20, Dongsanhuan Middle Road, Chaoyang District, Beijing 100022 Patentee after: Beijing Shenyan Intelligent Technology Co., Ltd. Address before: 100025 Room 2101, Block A, Building 2000,1, Eastern District, Xili 100, Balizhuang, Chaoyang District, Beijing Patentee before: Beijing Pinyou Interactive Information Technology Co., Ltd. |