CN107256231A - A kind of Team Member's identification equipment, method and system - Google Patents
A kind of Team Member's identification equipment, method and system Download PDFInfo
- Publication number
- CN107256231A CN107256231A CN201710309342.5A CN201710309342A CN107256231A CN 107256231 A CN107256231 A CN 107256231A CN 201710309342 A CN201710309342 A CN 201710309342A CN 107256231 A CN107256231 A CN 107256231A
- Authority
- CN
- China
- Prior art keywords
- team
- user
- identified
- specified
- geographic area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 239000013598 vector Substances 0.000 claims description 46
- 238000004422 calculation algorithm Methods 0.000 claims description 24
- 238000007635 classification algorithm Methods 0.000 claims description 11
- 238000007477 logistic regression Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 238000004590 computer program Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 238000011478 gradient descent method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000007115 recruitment Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000012706 support-vector machine 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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of Team Member's identification equipment, method and system, and this method includes：According to the focused data for being used to characterize the specified team of user's concern to be identified of acquisition, determine that the user to be identified is directed to the attention rate of the specified team；According to the default geographic area of acquisition and the geographic position data of the user to be identified, determine the degree of association of the user to be identified and default geographic area, wherein, the default geographic area includes the geographical position where the specified team, and the degree of association is used to characterize the situation that the user to be identified appears in the default geographic area；According to the attention rate and the degree of association, two disaggregated models of the specified team obtained using training in advance, recognize the user to be identified whether be the specified team member.The present invention can improve the accuracy of the affiliated team's recognition result of user.
Description
Technical field
The present invention relates to technical field of data processing, more particularly to a kind of Team Member's identification equipment, method and system.
Background technology
Many users can fill in personal data in website or application at present, and personal data include the group that user is added
The data such as team, name and hobby.The data for its team added filled in based on user, conventional Team Member's recognition methods
For：
Using crawler technology the network data that user produces in certain period of time is crawled from network side；From network data
The data for the team that the user that extraction user fills in website and application is added；If the team that the user is added
Data include specifying team, it is determined that the user is the member for specifying team；If in the data for the team that the user is added
Do not include specifying team, it is determined that the user is not the member for specifying team.
Inventor has found that the data of above-mentioned Team Member's recognition methods institute foundation are artificially filled in for user, deposit and user is added
The possibility that the team entered artificially fakes, in addition, user may add or depart from before the above-mentioned period specifies team, but is used
Family is not upgraded in time its team for being added in website and application, and the user in the now acquired above-mentioned period is added
The data of team there is hysteresis quality, therefore, the data of above-mentioned Team Member's recognition methods institute foundation it is unreliable, so as to cause
The problem of recognition result accuracy is poor.
The content of the invention
The present invention provides a kind of Team Member's recognition methods, equipment and system, for improving the affiliated team's identification knot of user
The accuracy of fruit.
In a first aspect, the embodiment of the present invention provides a kind of Team Member's identification equipment, including：
Processor, for according to the pass for being used to characterize the specified team of user's concern to be identified obtained from database server
Data are noted, determine that the user to be identified is directed to the attention rate of the specified team；Obtained according to from the database server
Default geographic area and the user to be identified geographic position data, determine the user to be identified with it is described defaultly
The degree of association in region is managed, wherein, the default geographic area includes the geographical position where the specified team, the degree of association
The situation of the default geographic area is appeared in for characterizing the user to be identified；According to the attention rate and the association
Degree, two disaggregated models of the specified team obtained using training in advance recognize whether the user to be identified is the finger
Determine the member of team；
Transmitter, for recognition result to be sent to the database server, so that the database server is to institute
Recognition result is stated to be stored.
Second aspect, the embodiment of the present invention provides a kind of Team Member's recognition methods, including：
According to the focused data for being used to characterize the specified team of user's concern to be identified of acquisition, the user to be identified is determined
For the attention rate of the specified team；
According to the default geographic area of acquisition and the geographic position data of the user to be identified, determine described to be identified
User and the degree of association of the default geographic area, wherein, the default geographic area includes the ground where the specified team
Position is managed, the degree of association is used to characterize the situation that the user to be identified appears in the default geographic area；
According to the attention rate and the degree of association, two classification moulds of the specified team obtained using training in advance
Type, recognize the user to be identified whether be the specified team member.
Alternatively, in methods described, the focused data includes at least one of following：
The number, the number of concern specified team's microblogging, download for paying close attention to specified team's wechat public number are described
Specify the number of the application program of team's exploitation and the amount of reading of specified team's related news, log in the specified team
Related web site number of times.
Alternatively, in methods described, determine that the user to be identified is directed to the attention rate of the specified team, specific bag
Include：
If the focused data includes at least two, it is determined that the user to be identified is directed to the concern of the specified team
Spend at least two corresponding numerical value sums.
Alternatively, in methods described, the degree of association of the user to be identified and default geographic area is determined, is specifically included：
For every position data of the user to be identified in first time period of acquisition, if this position data pair
The geographical position answered belongs to the default geographic area, then preserves this position data to position data set；
By the ratio of the total number of the position data included in position data set duration corresponding with the first time period
Value, is used as the user to be identified and the degree of association of default geographic area.
Alternatively, in methods described, training in advance obtains two disaggregated models of the specified team, specifically includes：
According to the classification collection of the set of eigenvectors of sample of users and sample of users, obtained using default classification algorithm training
Two disaggregated models of the specified team；Wherein, the set of eigenvectors is used for the characteristic vector for preserving each sample of users, institute
Stating characteristic vector includes correspondence sample of users for the attention rate and correspondence sample of users of specifying team and default geographic area
The degree of association, it is not to specify Team Member and sample of users to be to specify the member two of team that the classification collection, which includes sample of users,
Plant classification.
Alternatively, in methods described, the default sorting algorithm is Naive Bayes Classification Algorithm or logistic regression point
Class algorithm.
The third aspect, the embodiment of the present invention provides a kind of Team Member's identifying device, including：
First determining module, for the focused data for being used to characterize the specified team of user's concern to be identified according to acquisition,
Determine that the user to be identified is directed to the attention rate of the specified team；
Second determining module, for the default geographic area according to acquisition and the geographical position number of the user to be identified
According to, the degree of association of the user to be identified and the default geographic area are determined, wherein, the default geographic area is comprising described
The geographical position where team is specified, the degree of association appears in the default geographic area for characterizing the user to be identified
Situation；
3rd determining module, for according to the attention rate and the degree of association, obtained using training in advance described in
Specify two disaggregated models of team, recognize the user to be identified whether be the specified team member.
Fourth aspect, the embodiment of the present invention provides a kind of Team Member's identifying system, including：
Database server, for storing the focused data, the default ground that are used for characterizing the specified team of user's concern to be identified
The recognition result that region, the geographic position data of the user to be identified and computer server are sent is managed, wherein, it is described pre-
If geographic area includes the geographical position where the specified team, the degree of association is used to characterize user's appearance to be identified
Situation in the default geographic area；
Calculation server, for obtaining the focused data, default geographic area and institute from the database server
State the geographic position data of user to be identified；According to the focused data, determine that the user to be identified is directed to the specified group
The attention rate of team；According to the default geographic area and the geographic position data of the user to be identified, it is determined that described wait to know
Other user and the degree of association of the default geographic area；According to the attention rate and the degree of association, obtained using training in advance
Two disaggregated models of the specified team arrived, recognize whether the user to be identified is the member of the specified team, and incite somebody to action
Recognition result is sent to the database server.
5th aspect, the embodiments of the invention provide a kind of nonvolatile computer storage media, the computer storage
Media storage has computer executable instructions, and the computer executable instructions can perform above-mentioned Team Member's recognition methods.
Using Team Member's identification equipment provided in an embodiment of the present invention, method and system, have the advantages that：
Compared to the mode for the affiliated team of data identification user filled in the prior art only in accordance with user, the present invention is implemented
Example determines that concern used in attention rate specifies the focused data of team and determines user institute to be identified used in the degree of association
The confidence level and real-time of both user data of the geographical position at place preferably, therefore, knowledge are treated using both user data
Other user carries out affiliated team's identification, can improve the accuracy of recognition result.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of Team Member's recognition methods provided in an embodiment of the present invention；
Fig. 2 determines user to be identified and the method flow of the degree of association of default geographic area to be provided in an embodiment of the present invention
Schematic diagram；
Fig. 3 is the hardware architecture diagram of Team Member's identification equipment provided in an embodiment of the present invention；
Fig. 4 is the structural representation of Team Member's identifying device provided in an embodiment of the present invention；
Fig. 5 is the structural representation of Team Member's identifying system provided in an embodiment of the present invention.
Embodiment
It is possible to the present invention below in conjunction with accompanying drawing to make the object, technical solutions and advantages of the present invention clearer
Embodiment is further described.
Embodiment one
The embodiment of the present invention provides a kind of Team Member's recognition methods, as shown in figure 1, including：
Step 101, according to the focused data for being used to characterize the specified team of user's concern to be identified of acquisition, it is determined that described treat
Recognize that user is directed to the attention rate of the specified team.
When it is implemented, using web crawlers technology, the user couple to be identified can be obtained according to the mark of user to be identified
The network data answered.From the corresponding network data of user to be identified of acquisition, count and extract the user to be identified to specifying
The focused data of team, to embody degree of concern of the user to be identified to specified team.The mark of user can exist for the user
The register account number in team is specified, such as, the mark of user can be QQ accounts, microblog account etc., and user to be identified can be
Any user, is not limited here.Preferably, by for characterize user to be identified pay close attention to specify team focused data store to
Database server.
Wherein, team is a community by basic staff and management level composition of personnel, and it is single that team can include office
Position, public institution, enterprise, corporations, organization for public benefit etc., such as enterprise can be Tencent or Siemens Company etc..
As a kind of possible embodiment, user to be identified includes following at least one to the focused data for specifying team
：
The number, the number of concern specified team's microblogging, download for paying close attention to specified team's wechat public number are described
Specify the number of the application program of team's exploitation and the amount of reading of specified team's related news, log in the specified team
Related web site number of times.
Specifically, team would generally open it is some there is the not public number of same-action, microblogging etc., by taking Tencent as an example,
The wechat public number of the said firm can include administration class wechat public number, the issue Tengxun official information used inside Tengxun
Official's wechat public number and Tengxun's product related wechat public number etc..
Wherein, paying close attention to the number of specified team's wechat public number can determine in such a way：
Produced network data is operated in wechat client using user to be identified, statistics is located in second time period
In the wechat public number number for the specified team that state is paid close attention to by user to be identified, concern specified team's wechat public is used as
Number number.
Wherein, paying close attention to the number of specified team's microblogging can determine in such a way：
Produced network data is operated in wechat wins client using user to be identified, is counted in certain period of time
Microblogging number in the specified team that state is paid close attention to by user to be identified, is used as the number for paying close attention to specified team's microblogging.
Wherein, downloading the number of the application program of specified team's exploitation can determine in such a way：
Using the corresponding network data of user to be identified, the application downloaded in certain period of time and specify team's exploitation is counted
The number of program, is used as the number for the application program for downloading specified team's exploitation.
Wherein, the amount of reading with specified team's related news is determined in such a way：
From the corresponding network data of user to be identified, extract the user to be identified and read in certain period of time with specifying
The reading data of team's related news；Statistics reads the bar number of data, is used as the amount of reading with specified team's relevant information.
Wherein, the number of times for logging in the related web site of the specified team is determined in such a way：
From the corresponding network data of user to be identified, extract the user to be identified and the group of specifying is logged in certain period of time
The logon data of the related web site of team；The bar number of logon data is counted, time for the related web site for logging in the specified team is used as
Number.
It should be noted that the end time point of above-mentioned second time period can be current point in time, second time period pair
The duration answered can be set according to practical application scene, not limited here, such as second time period can be on April 28th, 2017
8:00 to 2017 on April 29,8:00, wherein, 28 days 8 April in 2017:00 is sart point in time, 29 days 8 April in 2017:00
For current point in time, a length of 1 day when second time period is corresponding.
If specifying the focused data of team to include at least two when it is implemented, specifying user to be directed to, it is determined that described to treat
It is at least two corresponding numerical value sums for the attention rate of the specified team to recognize user.Such as focused data includes
Pay close attention to the number M of specified team's wechat public number and pay close attention to the number N of specified team's microblogging, then by M and N's and value
The attention rate of the specified team is directed to as user to be identified.Or, it is that each focused data sets weights, by multinomial concern
The weighted sum result of data is defined as user to be identified and is directed to the attention rate for specifying team, such as：Focused data includes concern
The number M of the specified team's wechat public number and number N for paying close attention to specified team's microblogging, wherein, pay close attention to described specify
The corresponding weights of number of team's wechat public number are a, and the corresponding weights of number for paying close attention to specified team's microblogging are b, then
AM+bN is directed to the attention rate of the specified team as user to be identified.
The focused data of team is specified only to include one if specifying user to be directed to, it is determined that the user to be identified is directed to institute
The attention rate for stating specified team is the corresponding numerical value of this, such as attention rate is individual for concern specified team's wechat public number
Number M.
Step 102, according to the default geographic area of acquisition and the geographic position data of the user to be identified, institute is determined
The degree of association of user to be identified and the default geographic area are stated, wherein, the default geographic area includes the specified team
The geographical position at place, the degree of association is used to characterize the situation that the user to be identified appears in the default geographic area.
When it is implemented, from the corresponding network data of user to be identified of acquisition, extracting user to be identified at first
Between the geographic position data of network side is reported in section；Wherein, one geographical position of a position data correspondence, a geographical position
A plurality of position data may be corresponded to by putting.Position data is that user to be identified passes through LBS (Location Based Service, base
Service in position) etc. the location information that reports of positioning service, or, position data be user to be identified when accessing network on
Report to public network IP (Internet Protocol, procotol) address of network side, wherein, can be by belonging to the public network IP ground
Region is defined as the geographical position of user to be identified.Further, extract user to be identified and report to net during the working time
The geographic position data of network side, wherein working time section are the sub- period of first time period, and working time section belongs to the group of specifying
Its member as defined in team need to specify the period that team site is handled official business or other are movable.Such as, the very first time
Section is 15 days, then working time section is the working time section in working day for including in this 15 days, for example morning 9 every workday
5 points to afternoon of point is working time section.
Specifically, the degree of association is used to characterize the situation that the user to be identified appears in the default geographic area,
The degree of association in geographical position and default geographic area residing for i.e. described user to be identified.User to be identified is in first time period
What is occurred in default geographic area is more frequent, represents that user to be identified and the degree of association of the default geographic area are higher.It can pass through
The subordinate relation of the corresponding geographical position of the geographic position data and default geographic area obtained is analyzed, the use to be identified is determined
The degree of association at family and default geographic area.
The start time point of first time period and end time point can be set according to practical application scene, first time period pair
The duration answered can also be set according to practical application scene, not limited here, such as the end time point of first time period can be with
For current point in time, the corresponding duration of first time period can be 30 days or 15 days.
Geographical position where specifying team potentially includes multiple, now, presets geographic area to be multiple, wherein, one
Predeterminable area includes a geographical position where the specified team, such as Tengxun sets first office in Shanghai,
One the second office is set in Beijing, then presetting geographic area includes two, i.e., comprising geographical where the first office
The geographic area of position, and include the geographic area of the second office geographic location.Therefore, in the embodiment of the present invention
Default geographic area at least include one, when default geographic area includes multiple, it is necessary to default geographical according at least one
Region and the geographic position data of the user to be identified, determine the pass of the user to be identified and all default geographic areas
Connection degree.
Included in default geographic area on the premise of specifying team geographic location, preset the size of geographic area and cover
Lid scope can be set according to practical application scene, such as it to be a circular geographic area, the circle that geographic area is preset in region
The longitude and latitude in the geographical position where team is is specified in the center of circle of shape geographic area, and the radius of the circular geographic area can be according to reality
Border application scenarios setting, is not limited here.
It should be noted that not being defined here to the execution sequence of step 101 and step 102, it can also first carry out
Step 102, then step 101 is performed, or the two is performed simultaneously.
Preferably, the geographic position data of default geographic area and the user to be identified is stored to database service
Device.
Step 103, according to the attention rate and the degree of association, the specified team obtained using training in advance
Two disaggregated models, recognize the user to be identified whether be the specified team member.
When it is implemented, the sample set of the sample of users previously according to specified team, training obtains specifying two points of team
Class model, training obtains specifying the mode of two disaggregated models of team to be introduced below.
The embodiment of the present invention, user to be identified is directed to the attention rate for specifying team and user to be identified and default geography
The degree of association in region, constitutes the corresponding characteristic vector of user to be identified, regard this feature vector as the two classification moulds for specifying team
The input of type, determines whether user to be identified is the member that specifies team according to the output of two disaggregated models, such as, specifies team
For Tencent, then using the corresponding characteristic vector of user to be identified as two disaggregated models of Tencent input, according to rising
The output of two disaggregated models of news company determine user to be identified whether be Tencent employee.
It should be noted that same user to be identified can correspond to multiple characteristic vectors, such as the user to be identified is right respectively
The characteristic vector and the characteristic vector for the second team of the first team should be directed to, now, is directed to according to the user to be identified
The characteristic vector of first team and two disaggregated models of the first team, determine the user to be identified whether be the first team into
Member, accordingly, according to the user to be identified for the characteristic vector of the second team and two disaggregated models of the second team, it is determined that
The user to be identified whether be the second team member.
The embodiment of the present invention, using acquisition user to be identified pay close attention to specify team focused data and preservation wait know
Other user determines that user to be identified is directed to the attention rate for specifying team respectively in both user data of described geographical position
And the degree of association, the attention rate and the degree of association for specifying team are directed to further according to user to be identified, two classification moulds of specified team are utilized
Type, self-adapting estimation goes out whether the user to be identified is the member for specifying team, i.e. by analyzing user to be identified for specifying
The attention rate and the degree of association of team are classified to user, and whether determine user to be identified is the member for specifying team.Compared to
The mode of the affiliated team of user is recognized only in accordance with the data that user fills in the prior art, the embodiment of the present invention determines attention rate institute
The concern used specify the focused data of team and determine geographical position used in the degree of association residing for user to be identified this
The confidence level and real-time of two kinds of user data preferably, using both user data carry out affiliated team to user to be identified and known
Not, the accuracy of recognition result can be improved.
Team in embodiments of the present invention for enterprise scene under, prior art by crawl user future it is carefree,
The data of the enterprise added in the resume data filled in talent's recruitment websites such as neck English (LinkedIn), to recognize the use
Whether the tenure enterprise of family currently is to specify enterprise's (recognizing whether the user is the employee for specifying enterprise), but used in it
Resume data artificially filled in by user, there is artificial to the possibility of the data fabrication of enterprise added, therefore letter
Count the poor reliability of evidence one by one, and user is after specified enterprise is left, enterprise that may not again to being added in resume data
It is updated, therefore, resume data have more serious hysteresis quality.In the embodiment of the present invention, user couple determines that attention rate is made
Concern specify the focused data of enterprise and determine geographical position used in the degree of association residing for user to be identified this two
The difficulty height that user data is artificially faked is planted, also, is updated manually without user.
As a kind of possible embodiment, the content that can be provided according to Fig. 2 determines the user to be identified and default ground
Manage the degree of association in region：
Step 201, for every position data of the user to be identified in first time period of acquisition, if this position
Put the corresponding geographical position of data and belong to the default geographic area, then preserve this position data to position data set.
When it is implemented, reporting to every positional number of network side in first time period for the user to be identified of acquisition
According to performing after following operate, so that it is determined that position data set, the operation is：Judge the corresponding geographical position of the position data
Whether default geographic area is belonged to, if it is, this position data is preserved into most position data set, should if not, abandoning
Bar position data.
Step 202, it is the total number of the position data included in position data set is corresponding with the first time period
The ratio of duration, is used as the user to be identified and the degree of association of default geographic area.
When it is implemented, the total number of the position data included in statistics position data set, by the total number and the
The ratio of one period corresponding duration, is used as user to be identified and the degree of association of default geographic area.
The embodiment that Fig. 2 is provided is only a kind of possible embodiment, and user to be identified can be also determined according to other manner
With the degree of association of default geographic area, do not limit here, such as：Count user to be identified and net is reported in first time period
The total number L of the position data of network side, and in position data set position data total number Q, using Q and L ratio as
The degree of association of user to be identified and default geographic area, or, using the total number of position data in position data set as treating
Recognize user and the degree of association of default geographic area.
In the case of being the member for specifying team based on user to be identified, the user appears in finger in certain period of time
Determine the consideration of the geographic area where team, the embodiment of the present invention appears in default ground using user to be identified in first time period
The number of times in region is managed, the degree of association of user to be identified and the default geographic area comprising specified team geographical position is determined, from
And when user to be identified is identified, using the degree of association as one of reference factor, the accuracy of recognition result can be improved.
When it is implemented, can in the following way training in advance obtain specify team two disaggregated models：
According to the classification collection of the set of eigenvectors of sample of users and sample of users, obtained using default classification algorithm training
Two disaggregated models of the specified team；Wherein, the set of eigenvectors is used for the characteristic vector for preserving each sample of users, institute
Stating characteristic vector includes correspondence sample of users for the attention rate and correspondence sample of users of specifying team and default geographic area
The degree of association, it is not to specify Team Member and sample of users to be to specify the member two of team that the classification collection, which includes sample of users,
Plant classification.
When it is implemented, using the set of eigenvectors and the classification collection of sample of users of the sample of users for specifying team, it is right
Unknown parameter in default sorting algorithm is trained, to determine the specific value of unknown parameter, after unknown parameter is determined
The default corresponding mathematical modeling of sorting algorithm is defined as specifying two disaggregated models of team.
As a kind of possible embodiment, the default sorting algorithm is that Naive Bayes Classification Algorithm or logic are returned
Return sorting algorithm, or other sorting algorithms, do not limit here, such as can also be SVMs, decision tree, K
The sorting algorithms such as neighbour, neutral net.
In the case where default sorting algorithm is logistic regression algorithm, it can in such a way train and obtain the specified group
Two disaggregated models of team：
According to the classification collection of the set of eigenvectors of sample of users and sample of users, patrolled using gradient descent method training
The unknown parameter in regression forecasting function is collected, the logistic regression anticipation function after being determined according to unknown parameter and predetermined probabilities threshold
Value, it is determined that specifying two disaggregated models of team.Wherein, logistic regression anticipation function is：
Wherein, xiRepresent any feature vector that characteristic vector is concentrated, hθ(xi) represent characteristic vector xiCorresponding sample of users is specified
The probability of Team Member, xi1Represent characteristic vector xiIn attention rate, xi2Represent characteristic vector xiIn the degree of association, θ0、θ1、θ2
It is unknown parameter, after gradient descent method, the unknown parameter in logistic regression Prediction Parameters is that can determine that, specific implementation process
For prior art, do not repeat here.
It should be noted that the characteristic vector input logic regression forecasting function h of sample of usersθ(xi) before, preferred pair sample
Attention rate and the degree of association in this user characteristics vector are normalized, to improve the precision of two disaggregated models trained
And two disaggregated model the speed of unknown parameter, two classification that reduction training is obtained are asked using gradient descent method in the training process
Model can not convergent risk.
Specifically, two disaggregated models of the specified team determined are：
If hθ(xj) >=H, the classification belonging to user to be identified is 1；If hθ(xj) ＜ H, the classification belonging to user to be identified is
0；Wherein, when classification is 1, it is the member for specifying team to represent user to be identified, when classification is 0, represents that user to be identified is not
Perform the member of team, hθ(xj) for unknown parameter determine after logistic regression anticipation function, for representing that user to be identified refers to
Determine the probability of the member of team, xjThe corresponding characteristic vector of user to be identified is represented, H represents predetermined probabilities threshold value, H big I
Set, do not limited here according to practical application scene, such as H=0.5.
It should be noted that two disaggregated models trained using the sample of users characteristic vector based on normalized,
Carry out before Team Member's identification, place preferably is normalized in the attention rate and the degree of association in the characteristic vector of user to be identified
Reason.
When it is implemented, user to be identified to be directed to the attention rate x for specifying teamj1And user to be identified and default geography
The degree of association x in regionj2Substitute intoObtain hθ(xj), then by obtained hθ(xj) compared with H, if hθ(xj)≥
H, it is the member for specifying team to determine user to be identified, if hθ(xj) ＜ H, it is not the member for specifying team to determine user to be identified.
Illustrate, it is assumed that train the θ come0=0.8, θ1=2, θ2=1, feature after user to be identified normalization to
Measure as [0.5,0.2], wherein, xj1=0.5, xj2=0.2, H=0.5 are by xj1And xj2Substitute into formulaAfterwards,
Obtain hθ(xj)=0.845, more than 0.5, it is determined that the user to be identified is the employee for specifying team.
In the case where default sorting algorithm is NB Algorithm, it can in such a way train and obtain described specify
Two disaggregated models of team：
According to the classification collection of the set of eigenvectors of sample of users, and sample of users, NB Algorithm, training are utilized
Obtain two disaggregated models of the specified team；Wherein, the set of eigenvectors be used to preserving the feature of each sample of users to
Measure xj, the characteristic vector xjThe attention rate x for specifying team is directed to including correspondence sample of usersj1And correspond to sample of users and pre-
If the degree of association x of geographic areaj2, it is not to specify Team Member and sample of users to refer to that the classification collection y, which includes sample of users,
Determine two kinds of classifications of member of team；
Where it is assumed that each feature (attention rate or the degree of association) that characteristic vector is concentrated is successive value and assumes each feature
Gaussian distributed, then the corresponding formula of NB Algorithm is as follows：
Wherein,
Wherein,
In naive Bayesian formula, yiRepresent any classification in the classification collection y, xjRepresent in the set of eigenvectors x
Any feature vector, P (yi|xj) expression characteristic vector be xjClassification belonging to corresponding sample of users is yiProbability, P (xj) be
Characteristic vector xjThe probability occurred in the set of eigenvectors x, P (yi) it is classification yiWhat is occurred in the classification collection y is general
Rate, σ 'yiIt is y for affiliated classificationiThe corresponding characteristic vector of sample of users in, feature xj1Standard deviation, η 'yiTo be affiliated
Classification is yiThe corresponding characteristic vector of sample of users in, feature xj1Average, σ "yiIt is y for affiliated classificationiSample of users
In corresponding characteristic vector, feature xj2Standard deviation, η "yiIt is y for affiliated classificationiThe corresponding characteristic vector of sample of users
In, feature xj2Average, σ ' be the corresponding characteristic vector of all sample of users in, feature xj1Standard deviation, η ' be all samples
In the corresponding characteristic vector of user, feature xj1Average, σ " be the corresponding characteristic vector of all sample of users in, feature xj2's
Standard deviation, η " be the corresponding characteristic vector of all sample of users in, feature xj2Average, xj1It is characterized vector xjIn concern
Degree, xj2It is characterized vector xjIn the degree of association.Wherein, the calculation of standard deviation and average is existing calculation, here not
Repeat.
Specific implementation, can make classification collection y={ y1=0, y2=1 }, wherein, 0 expression user is not the member for specifying team,
1 expression user is the member for specifying team.
In the case where default sorting algorithm is NB Algorithm, two disaggregated models of obtained specified team are trained
For：If P (1 | xt) ＞ P (0 | xt), user's generic to be identified is 1；If P (1 | xt)≤P(0|xt), belonging to user to be identified
Classification is 0.Wherein, xtFor the corresponding characteristic vector of user to be identified.
Embodiment two
Based on the inventive concept same with above-described embodiment one, the embodiment of the present invention provides a kind of Team Member's identification and set
It is standby, for performing above-mentioned Team Member's recognition methods, as shown in figure 3, knowing for the Team Member described in the embodiment of the present invention two
The hardware architecture diagram of other equipment.Team Member's identification equipment is specifically as follows desktop computer, portable computer, intelligence
Energy mobile phone, tablet personal computer etc..Specifically, the equipment described in the embodiment of the present invention two can include processor 301, transmitter
302, wherein, processor 301, for specifying team for characterizing user's concern to be identified according to what is obtained from database server
Focused data, determine the user to be identified be directed to the specified team attention rate；According to from the database server
Obtain default geographic area and the user to be identified geographic position data, determine the user to be identified with it is described pre-
If the degree of association of geographic area, wherein, the default geographic area includes the geographical position where the specified team, the pass
Connection degree is used to characterize the situation that the user to be identified appears in the default geographic area；According to the attention rate and described
The degree of association, two disaggregated models of the specified team obtained using training in advance recognize whether the user to be identified is institute
State the member of specified team.Transmitter 302, for recognition result to be sent to the database server, so that the data
Storehouse server is stored to the recognition result.Further, the equipment described in the embodiment of the present invention two can also include
Memory 303, input unit 304 and output device 305 etc..Wherein, memory 303 can include read-only storage (ROM)
With random access memory (RAM), and the programmed instruction that stores and data in memory 303 are provided to processor 301, in this hair
In bright embodiment, memory 303 can be used for the corresponding program of storage Team Member recognition methods；Input unit 304 can be wrapped
Include keyboard, mouse, touch-screen etc.；Output device 305 can include display device, such as liquid crystal display (Liquid Crystal
Display, LCD), cathode-ray tube (Cathode Ray Tube, CRT) etc..Processor 301, transmitter 302, memory
303rd, input unit 304 and output device 305 can be connected by bus or other modes, to be connected by bus in Fig. 3
Exemplified by.
Processor 301 calls the programmed instruction of the storage of memory 303 and performs embodiment one according to the programmed instruction of acquisition
Team Member's recognition methods of offer.
Alternatively, the focused data includes at least one of following：
The number, the number of concern specified team's microblogging, download for paying close attention to specified team's wechat public number are described
Specify the number of the application program of team's exploitation and the amount of reading of specified team's related news, log in the specified team
Related web site number of times.
Alternatively, the processor 301 is when it is determined that the user to be identified is directed to the attention rate of the specified team, tool
Body is used for：If the focused data includes at least two, it is determined that the user to be identified is directed to the concern of the specified team
Spend at least two corresponding numerical value sums.
Alternatively, the processor 301 it is determined that the user to be identified and the default geographic area the degree of association when,
Specifically for：
For every position data of the user to be identified in first time period of acquisition, if this position data pair
The geographical position answered belongs to the default geographic area, then preserves this position data to position data set；By positional number
According to the ratio of the total number of the position data included in set duration corresponding with the first time period, as described to be identified
User and the degree of association of default geographic area.
Alternatively, the processor 301, is additionally operable to：Training in advance obtains the two of the specified team in such a way
Disaggregated model：
According to the classification collection of the set of eigenvectors of sample of users and sample of users, obtained using default classification algorithm training
Two disaggregated models of the specified team；Wherein, the set of eigenvectors is used for the characteristic vector for preserving each sample of users, institute
Stating characteristic vector includes correspondence sample of users for the attention rate and correspondence sample of users of specifying team and default geographic area
The degree of association, it is not to specify Team Member and sample of users to be to specify the member two of team that the classification collection, which includes sample of users,
Plant classification.
Alternatively, the default sorting algorithm is Naive Bayes Classification Algorithm or logistic regression sorting algorithm.
Embodiment three
Based on the inventive concept same with above-described embodiment one, the embodiment of the present invention provides a kind of Team Member's identification dress
Put, as shown in figure 4, including：
First determining module 401, for the concern number for being used to characterize the specified team of user's concern to be identified according to acquisition
According to, determine the user to be identified be directed to the specified team attention rate；
Second determining module 402, for the default geographic area according to acquisition and the geographical position of the user to be identified
Data are put, the degree of association of the user to be identified and the default geographic area is determined, wherein, the default geographic area is included
Geographical position where the specified team, the degree of association appears in the default geography for characterizing the user to be identified
The situation in region；
3rd determining module 403, for according to the attention rate and the degree of association, the institute obtained using training in advance
State two disaggregated models of specified team, recognize the user to be identified whether be the specified team member.
Alternatively, in described device, the focused data includes at least one of following：
The number, the number of concern specified team's microblogging, download for paying close attention to specified team's wechat public number are described
Specify the number of the application program of team's exploitation and the amount of reading of specified team's related news, log in the specified team
Related web site number of times.
Alternatively, in described device, first determining module, specifically for：
If the focused data includes at least two, it is determined that the user to be identified is directed to the concern of the specified team
Spend at least two corresponding numerical value sums.
Alternatively, in described device, second determining module is specifically included：
Storage unit, for every position data of the user to be identified for acquisition in first time period, if
The corresponding geographical position of this position data belongs to the default geographic area, then preserves this position data to position data
Set；
Determining unit, for the total number of position data and the first time period pair that will be included in position data set
The ratio for the duration answered, is used as the user to be identified and the degree of association of default geographic area.
Alternatively, described device, in addition to：
Training module 404, two disaggregated models of the specified team are obtained for training in advance in such a way
According to the classification collection of the set of eigenvectors of sample of users and sample of users, obtained using default classification algorithm training
Two disaggregated models of the specified team；Wherein, the set of eigenvectors is used for the characteristic vector for preserving each sample of users, institute
Stating characteristic vector includes correspondence sample of users for the attention rate and correspondence sample of users of specifying team and default geographic area
The degree of association, it is not to specify Team Member and sample of users to be to specify the member two of team that the classification collection, which includes sample of users,
Plant classification.
Alternatively, in described device, the default sorting algorithm is Naive Bayes Classification Algorithm or logistic regression point
Class algorithm.
Example IV
The embodiment of the present invention also provides a kind of Team Member's identifying system, as shown in figure 5, including：
Database server 501, pays close attention to the focused data of specified team for characterizing user to be identified for storing, presets
The recognition result that geographic area, the geographic position data of the user to be identified and computer server are sent, wherein, it is described
Default geographic area includes the geographical position where the specified team, and the degree of association goes out for characterizing the user to be identified
The situation of the present default geographic area；
Calculation server 502, for from the database server obtain the focused data, default geographic area and
The geographic position data of the user to be identified；According to the focused data, determine that the user to be identified specifies for described
The attention rate of team；According to the default geographic area and the geographic position data of the user to be identified, it is determined that described treat
Recognize user and the degree of association of the default geographic area；According to the attention rate and the degree of association, training in advance is utilized
Two disaggregated models of the obtained specified team, recognize the user to be identified whether be the specified team member, and
Recognition result is sent to the database server.
Wherein, calculation server 502 is Team Member's identification equipment in embodiment two.
Embodiment five
The embodiment of the present application provides a kind of nonvolatile computer storage media, and the computer-readable storage medium is stored with
Computer executable instructions, the computer executable instructions can perform the identification side of any Team Member in above-described embodiment one
Method.
Using Team Member's identification equipment provided in an embodiment of the present invention, method and system, have the advantages that：
Compared to the mode for the affiliated team of data identification user filled in the prior art only in accordance with user, the present invention is implemented
Example determines that concern used in attention rate specifies the focused data of team and determines user institute to be identified used in the degree of association
Both user data confidence levels of the geographical position at place and real-time are preferable, therefore, using both user data to be identified
User carries out affiliated team's identification, can improve the accuracy of recognition result.
Although it should be noted that be referred to some modules of Team Member's identifying device in above-detailed, this
It is not enforceable that kind division is merely exemplary.In fact, according to the embodiment of the present invention, above-described two or
The feature and function of more multimode can embody in a module.Conversely, the feature and work(of an above-described module
It can be further divided into being embodied by multiple modules.
The present invention is the flow with reference to method according to embodiments of the present invention, equipment (system) and computer program product
Figure and/or block diagram are described.It should be understood that can be by every first-class in computer program instructions implementation process figure and/or block diagram
Journey and/or the flow in square frame and flow chart and/or block diagram and/or the combination of square frame.These computer programs can be provided
The processor of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that produced by the instruction of computer or the computing device of other programmable data processing devices for real
The device for the function of being specified in present one flow of flow chart or one square frame of multiple flows and/or block diagram or multiple square frames.
These computer program instructions, which may be alternatively stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory, which is produced, to be included referring to
Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one square frame of block diagram or
The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that in meter
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented processing, thus in computer or
The instruction performed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in individual square frame or multiple square frames.
, but those skilled in the art once know basic creation although preferred embodiments of the present invention have been described
Property concept, then can make other change and modification to these embodiments.So, appended claims are intended to be construed to include excellent
Select embodiment and fall into having altered and changing for the scope of the invention.
Obviously, those skilled in the art can carry out the essence of various changes and modification without departing from the present invention to the present invention
God and scope.So, if these modifications and variations of the present invention belong to the scope of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to comprising including these changes and modification.
Claims (13)
1. a kind of Team Member's identification equipment, it is characterised in that including：
Processor, for according to the concern number for being used to characterize the specified team of user's concern to be identified obtained from database server
According to, determine the user to be identified be directed to the specified team attention rate；According to from the database server obtain it is pre-
If geographic area and the geographic position data of the user to be identified, determine the user to be identified and the default geographic region
The degree of association in domain, wherein, the default geographic area includes the geographical position where the specified team, and the degree of association is used for
Characterize the situation that the user to be identified appears in the default geographic area；According to the attention rate and the degree of association,
Two disaggregated models of the specified team obtained using training in advance, recognize whether the user to be identified is the specified group
The member of team；
Transmitter, for recognition result to be sent to the database server, so that the database server is known to described
Other result is stored.
2. equipment according to claim 1, it is characterised in that the focused data includes at least one of following：
The number, the number of concern specified team's microblogging, download for paying close attention to specified team's wechat public number are described specified
Number, the amount of reading with specified team's related news, the phase for logging in the specified team of the application program of team's exploitation
Close the number of times of website.
3. equipment according to claim 2, it is characterised in that the processor, specifically for：
If the focused data includes at least two, it is determined that the user to be identified is for the attention rate of the specified team
At least two corresponding numerical value sums.
4. equipment according to claim 1, it is characterised in that processor, specifically for：
For every position data of the user to be identified in first time period of acquisition, if this position data is corresponding
Geographical position belongs to the default geographic area, then preserves this position data to position data set；
By the ratio of the total number of the position data included in position data set duration corresponding with the first time period, make
For the user to be identified and the degree of association of default geographic area.
5. equipment according to claim 1, it is characterised in that the processor, is additionally operable to：
Training in advance obtains two disaggregated models of the specified team in such a way：
According to the classification collection of the set of eigenvectors of sample of users and sample of users, obtain described using default classification algorithm training
Specify two disaggregated models of team；Wherein, the set of eigenvectors is used for the characteristic vector for preserving each sample of users, the spy
Levying vector includes attention rate and correspondence sample of users and the pass of default geographic area that correspondence sample of users is directed to specified team
Connection degree, it is not to specify Team Member and sample of users to be the species of member two for specifying team that the classification collection, which includes sample of users,
Not.
6. equipment according to claim 5, it is characterised in that the default sorting algorithm is Naive Bayes Classification Algorithm
Or logistic regression sorting algorithm.
7. a kind of Team Member's recognition methods, it is characterised in that including：
According to the focused data for being used to characterize the specified team of user's concern to be identified of acquisition, determine that the user to be identified is directed to
The attention rate of the specified team；
According to the default geographic area of acquisition and the geographic position data of the user to be identified, the user to be identified is determined
With the degree of association of the default geographic area, wherein, the default geographic area include the specified team where geographical position
Put, the degree of association is used to characterize the situation that the user to be identified appears in the default geographic area；
According to the attention rate and the degree of association, two disaggregated models of the specified team obtained using training in advance,
Recognize the user to be identified whether be the specified team member.
8. method according to claim 7, it is characterised in that the focused data includes at least one of following：
The number, the number of concern specified team's microblogging, download for paying close attention to specified team's wechat public number are described specified
Number, the amount of reading with specified team's related news, the phase for logging in the specified team of the application program of team's exploitation
Close the number of times of website.
9. method according to claim 8, it is characterised in that determine the user to be identified for the specified team
Attention rate, is specifically included：
If the focused data includes at least two, it is determined that the user to be identified is for the attention rate of the specified team
At least two corresponding numerical value sums.
10. method according to claim 7, it is characterised in that determine the user to be identified and default geographic area
The degree of association, is specifically included：
For every position data of the user to be identified in first time period of acquisition, if this position data is corresponding
Geographical position belongs to the default geographic area, then preserves this position data to position data set；
By the ratio of the total number of the position data included in position data set duration corresponding with the first time period, make
For the user to be identified and the degree of association of default geographic area.
11. method according to claim 7, it is characterised in that training in advance obtains two classification moulds of the specified team
Type, is specifically included：
According to the classification collection of the set of eigenvectors of sample of users and sample of users, obtain described using default classification algorithm training
Specify two disaggregated models of team；Wherein, the set of eigenvectors is used for the characteristic vector for preserving each sample of users, the spy
Levying vector includes attention rate and correspondence sample of users and the pass of default geographic area that correspondence sample of users is directed to specified team
Connection degree, it is not to specify Team Member and sample of users to be the species of member two for specifying team that the classification collection, which includes sample of users,
Not.
12. method according to claim 11, it is characterised in that the default sorting algorithm is calculated for Naive Bayes Classification
Method or logistic regression sorting algorithm.
13. a kind of Team Member's identifying system, it is characterised in that including：
Database server, for storing the focused data, the default geographic region that are used for characterizing the specified team of user's concern to be identified
The recognition result that domain, the geographic position data of the user to be identified and computer server are sent, wherein, it is described defaultly
Manage region and include the geographical position where the specified team, the degree of association appears in institute for characterizing the user to be identified
State the situation of default geographic area；
Calculation server, for obtaining the focused data, default geographic area from the database server and described treating
Recognize the geographic position data of user；According to the focused data, determine the user to be identified for the specified team
Attention rate；According to the default geographic area and the geographic position data of the user to be identified, the use to be identified is determined
The degree of association at family and the default geographic area；According to the attention rate and the degree of association, obtained using training in advance
Two disaggregated models of the specified team, recognize whether the user to be identified is the member of the specified team, and will recognize
As a result send to the database server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710309342.5A CN107256231B (en) | 2017-05-04 | 2017-05-04 | Team member identification device, method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710309342.5A CN107256231B (en) | 2017-05-04 | 2017-05-04 | Team member identification device, method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107256231A true CN107256231A (en) | 2017-10-17 |
| CN107256231B CN107256231B (en) | 2022-04-22 |
Family
ID=60027911
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710309342.5A Active CN107256231B (en) | 2017-05-04 | 2017-05-04 | Team member identification device, method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107256231B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108989992A (en) * | 2018-08-03 | 2018-12-11 | 四川民工加网络科技有限公司 | Migrant worker's dynamic realtime method for tracing and device |
| CN110147923A (en) * | 2019-04-04 | 2019-08-20 | 阿里巴巴集团控股有限公司 | The method and device of risk subscribers for identification |
| CN112307075A (en) * | 2019-08-01 | 2021-02-02 | 中国移动通信集团广东有限公司 | User relationship identification method and device |
| CN113034157A (en) * | 2019-12-24 | 2021-06-25 | 中国移动通信集团浙江有限公司 | Group member identification method and device and computing equipment |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070106780A1 (en) * | 2002-02-20 | 2007-05-10 | Microsoft Corporation | Social mapping of contacts from computer communication information |
| US20110115699A1 (en) * | 2009-11-17 | 2011-05-19 | Sony Corporation | Display control system, display control device, and display control method |
| CN103377262A (en) * | 2012-04-28 | 2013-10-30 | 国际商业机器公司 | Method and device for grouping users |
| US8694413B1 (en) * | 2011-09-29 | 2014-04-08 | Morgan Stanley & Co. Llc | Computer-based systems and methods for determining interest levels of consumers in research work product produced by a research department |
| WO2014150073A2 (en) * | 2013-03-15 | 2014-09-25 | Ad-Vantage Networks, Inc. | Methods and systems for requesting, processing, and displaying content |
| CN104462448A (en) * | 2014-12-15 | 2015-03-25 | 微梦创科网络科技（中国）有限公司 | Group name classification method and device |
| CN104573109A (en) * | 2015-01-30 | 2015-04-29 | 深圳市中兴移动通信有限公司 | System, terminal and method for automatic recommendation based on group relation |
| CN105488211A (en) * | 2015-12-11 | 2016-04-13 | 成都陌云科技有限公司 | Method for determining user group based on feature analysis |
| CN105512301A (en) * | 2015-12-11 | 2016-04-20 | 成都陌云科技有限公司 | User grouping method based on social content |
| CN106227835A (en) * | 2016-07-25 | 2016-12-14 | 中南大学 | Team's research direction method for digging based on two subnetwork figure hierarchical clusterings |
| WO2017041651A1 (en) * | 2015-09-09 | 2017-03-16 | 阿里巴巴集团控股有限公司 | User data classification method and device |
-
2017
- 2017-05-04 CN CN201710309342.5A patent/CN107256231B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070106780A1 (en) * | 2002-02-20 | 2007-05-10 | Microsoft Corporation | Social mapping of contacts from computer communication information |
| US20110115699A1 (en) * | 2009-11-17 | 2011-05-19 | Sony Corporation | Display control system, display control device, and display control method |
| US8694413B1 (en) * | 2011-09-29 | 2014-04-08 | Morgan Stanley & Co. Llc | Computer-based systems and methods for determining interest levels of consumers in research work product produced by a research department |
| CN103377262A (en) * | 2012-04-28 | 2013-10-30 | 国际商业机器公司 | Method and device for grouping users |
| WO2014150073A2 (en) * | 2013-03-15 | 2014-09-25 | Ad-Vantage Networks, Inc. | Methods and systems for requesting, processing, and displaying content |
| CN104462448A (en) * | 2014-12-15 | 2015-03-25 | 微梦创科网络科技（中国）有限公司 | Group name classification method and device |
| CN104573109A (en) * | 2015-01-30 | 2015-04-29 | 深圳市中兴移动通信有限公司 | System, terminal and method for automatic recommendation based on group relation |
| WO2017041651A1 (en) * | 2015-09-09 | 2017-03-16 | 阿里巴巴集团控股有限公司 | User data classification method and device |
| CN105488211A (en) * | 2015-12-11 | 2016-04-13 | 成都陌云科技有限公司 | Method for determining user group based on feature analysis |
| CN105512301A (en) * | 2015-12-11 | 2016-04-20 | 成都陌云科技有限公司 | User grouping method based on social content |
| CN106227835A (en) * | 2016-07-25 | 2016-12-14 | 中南大学 | Team's research direction method for digging based on two subnetwork figure hierarchical clusterings |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108989992A (en) * | 2018-08-03 | 2018-12-11 | 四川民工加网络科技有限公司 | Migrant worker's dynamic realtime method for tracing and device |
| CN110147923A (en) * | 2019-04-04 | 2019-08-20 | 阿里巴巴集团控股有限公司 | The method and device of risk subscribers for identification |
| CN112307075A (en) * | 2019-08-01 | 2021-02-02 | 中国移动通信集团广东有限公司 | User relationship identification method and device |
| CN112307075B (en) * | 2019-08-01 | 2023-09-19 | 中国移动通信集团广东有限公司 | User relationship identification method and device |
| CN113034157A (en) * | 2019-12-24 | 2021-06-25 | 中国移动通信集团浙江有限公司 | Group member identification method and device and computing equipment |
| CN113034157B (en) * | 2019-12-24 | 2023-12-26 | 中国移动通信集团浙江有限公司 | Group member identification method and device and computing equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107256231B (en) | 2022-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103796183B (en) | A kind of refuse messages recognition methods and device | |
| CN107612893A (en) | The auditing system and method and structure short message examination ＆ verification model method of short message | |
| CN107256231A (en) | A kind of Team Member's identification equipment, method and system | |
| CN108629413A (en) | Neural network model training, trading activity Risk Identification Method and device | |
| CN109074553A (en) | It is handled using the spam of continuous model training | |
| CN107908566A (en) | Automatic test management method, device, terminal device and storage medium | |
| CN108229963A (en) | The Risk Identification Method and device of user's operation behavior | |
| Ballin et al. | Joint determination of optimal stratification and sample allocation using genetic algorithm | |
| CN110442712A (en) | Determination method, apparatus, server and the text of risk try system | |
| CN107193974A (en) | Localized information based on artificial intelligence determines method and apparatus | |
| CN110308946A (en) | Race batch processing method, equipment, storage medium and device based on artificial intelligence | |
| CN110162292A (en) | Voice broadcast method and device | |
| CN105894028A (en) | User identification method and device | |
| CN114187036B (en) | Internet advertisement intelligent recommendation management system based on behavior characteristic recognition | |
| CN109840778A (en) | The recognition methods of fraudulent user and device, readable storage medium storing program for executing | |
| CN108241867A (en) | A kind of sorting technique and device | |
| CN109284500A (en) | Information transmission system and method based on merchants inviting work process and reading preference | |
| CN111061948A (en) | User label recommendation method and device, computer equipment and storage medium | |
| CN114493686A (en) | Operation content generation and pushing method and device | |
| CN111882113B (en) | Enterprise mobile banking user prediction method and device | |
| CN113191681A (en) | Site selection method and device for network points, electronic equipment and readable storage medium | |
| CN110215703A (en) | The selection method of game application, apparatus and system | |
| CN115545088B (en) | Model construction method, classification method, device and electronic equipment | |
| CN106407212A (en) | Network account category determination method and apparatus, and object clustering method and apparatus | |
| CN110533454A (en) | A kind of method and system identifying business object group |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |