CN105654311A - User information providing method and device - Google Patents
User information providing method and device Download PDFInfo
- Publication number
- CN105654311A CN105654311A CN201510990663.7A CN201510990663A CN105654311A CN 105654311 A CN105654311 A CN 105654311A CN 201510990663 A CN201510990663 A CN 201510990663A CN 105654311 A CN105654311 A CN 105654311A
- Authority
- CN
- China
- Prior art keywords
- user
- user data
- described user
- predetermined threshold
- threshold value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/01—Customer relationship services
- G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
- G06Q30/016—After-sales
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- Finance (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides a user information providing method and device. Reference to the indexes of multiple aspects is performed so that user importance can be more accurately measured and presented to customer service personnel, and thus advantages of comprehensive consideration and wide applicability can be realized. The method comprises the steps that user data corresponding to each user are acquired, and the user data include multiple preset types of indexes; a user comprehensive value is determined according to the user data; the user comprehensive value is stored; and the user comprehensive value corresponding to the designated user is outputted under the condition that a request of scheduling the designated user data is received.
Description
Technical field
The present invention relates to field of computer technology, particularly a kind of method that user profile is provided and device.
Background technology
In electricity business's customer service system, contact staff has a lot of business scenario processing user's request, consulting, complaint based on user's comprehensive value, needs the function realizing in system that user's comprehensive value is judged in these scenes.
In existing electricity business's customer service system, usual calling and obtaining user this index of history spending amount is for contact staff's reference. User's history spending amount numerical value height then shows that this user is high-quality user, and contact staff can provided better service. The program uses SQL query table data in data base, and collects the order amount of money with sum function. The prior art has and considers unilateral, shortcoming that reference index is single, can only simple rule in fulfillment database and logic, it is impossible to realize the program function of complicated algorithm.
Summary of the invention
In view of this, the present invention provides a kind of method and apparatus providing user profile, with reference to the index of many aspects, it is possible to weighs user's importance more exactly and presents to contact staff, has consideration comprehensively, the advantages such as the suitability is wide.
For achieving the above object, according to an aspect of the invention, it is provided a kind of method providing user profile.
The method of the offer user profile of the present invention includes: gather the user data that each user is corresponding, and described user data includes multiple preset kind index; User's comprehensive value is determined according to described user data; Described user's comprehensive value is stored; When receive transfer appointment user data requests, export and described specify described user's comprehensive value corresponding to user.
Alternatively, described user data include buying in the recent period natural law, recent order total amount, the recent actual delivery amount of money, recent order volume, in the recent period single all amount of money, whether blacklist, finally buy Days from present time, your the order amount of money, the quantity that buys luxuries, user's login times, cancellation of order number of times, reject single amount, compensate in applications at least one.
Alternatively, determine that the step of user's comprehensive value includes according to described user data: screen out incomplete described user data; Complete described user data is carried out pretreatment; Adopt analytic hierarchy process (AHP) that pre-processed results is calculated, obtain described user's comprehensive value.
Alternatively, the step that complete described user data carries out pretreatment includes: the preset kind index of the logical type in complete described user data is remained unchanged;The preset kind index of the numeric type in complete described user data is done following process: after arc tangent process is first carried out more than the preset kind index of the first predetermined threshold value for average, carry out extreme difference standardization; Extreme difference standardization is made directly less than or equal to the first predetermined threshold value and be more than or equal to the preset kind index of the second predetermined threshold value for average; Carrying out extreme difference standardization after first carrying out totalling process for average less than the preset kind index of the second predetermined threshold value, wherein the first predetermined threshold value is more than the second predetermined threshold value.
Alternatively, adopting analytic hierarchy process (AHP), pre-processed results is calculated, after obtaining the step of described user's comprehensive value, also include: judge whether described user's comprehensive value of all users meets normal distribution, if meeting, enter downstream, if not meeting, revising the weight parameter in described analytic hierarchy process (AHP), again adopting analytic hierarchy process (AHP) that described pre-processed results is calculated.
According to a further aspect in the invention, it is provided that a kind of device that user profile is provided.
The device of the offer information of the present invention includes: acquisition module, and for gathering the user data that each user is corresponding, described user data includes multiple preset kind index; Determine module, for determining user's comprehensive value according to described user data; Memory module, for storing described user's comprehensive value; Output module, when receive transfer appointment user data requests, export and described specify described user's comprehensive value corresponding to user.
Alternatively, described user data include buying in the recent period natural law, recent order total amount, the recent actual delivery amount of money, recent order volume, in the recent period single all amount of money, whether blacklist, finally buy Days from present time, your the order amount of money, the quantity that buys luxuries, user's login times, cancellation of order number of times, reject single amount, compensate in applications at least one.
Alternatively, described determine that module is additionally operable to: screen out incomplete described user data; Complete described user data is carried out pretreatment; Adopt analytic hierarchy process (AHP) that pre-processed results is calculated, obtain described user's comprehensive value.
Alternatively, described determine that module is additionally operable to: the preset kind index of the logical type in complete described user data is remained unchanged; The preset kind index of the numeric type in complete described user data is done following process: after arc tangent process is first carried out more than the preset kind index of the first predetermined threshold value for average, carry out extreme difference standardization; Extreme difference standardization is made directly less than or equal to the first predetermined threshold value and be more than or equal to the preset kind index of the second predetermined threshold value for average; Carrying out extreme difference standardization after first carrying out totalling process for average less than the preset kind index of the second predetermined threshold value, wherein the first predetermined threshold value is more than the second predetermined threshold value.
Alternatively, described determine that module is additionally operable to: judge whether described user's comprehensive value of all users meets normal distribution, if meeting, enter downstream, if not meeting, revising the weight parameter in described analytic hierarchy process (AHP), again adopting analytic hierarchy process (AHP) that described pre-processed results is calculated.
According to technical scheme, with reference to the index of many aspects, it is possible to weigh user's importance more exactly and present to contact staff, there is consideration comprehensively, the advantages such as the suitability is wide.
Accompanying drawing explanation
Accompanying drawing is used for being more fully understood that the present invention, does not constitute inappropriate limitation of the present invention.Wherein:
Fig. 1 is the schematic diagram of the basic step of the method for the offer user profile according to embodiment of the present invention;
Fig. 2 is the schematic diagram of the main modular of the device of the offer user profile according to embodiment of the present invention;
Fig. 3 is the target layers structural representation of user's comprehensive value of embodiment of the present invention.
Detailed description of the invention
Below in conjunction with accompanying drawing, the exemplary embodiment of the present invention is explained, including the various details of embodiment of the present invention to help understanding, it should it is only exemplary that they are thought. Therefore, those of ordinary skill in the art will be appreciated that, it is possible to embodiment described herein is made various change and amendment, without departing from scope and spirit of the present invention. Equally, for clarity and conciseness, description below eliminates the description to known function and structure.
Fig. 1 is the schematic diagram of the basic step of the method for the offer user profile according to embodiment of the present invention. As it is shown in figure 1, the method for the offer user profile of embodiment of the present invention includes steps A to step D. The executive agent of method is the device of the offer user profile of embodiment of the present invention.
Step A: gather the user data that each user is corresponding, user data includes multiple preset kind index. Collection action can be periodically subject to according to predetermined period. User data can include buying in the recent period natural law, recent order total amount, the recent actual delivery amount of money, recent order volume, in the recent period single all amount of money, whether blacklist, finally buy Days from present time, your the order amount of money, the quantity that buys luxuries, user's login times, cancellation of order number of times, reject single amount, compensate in applications at least one.
Step B: determine user's comprehensive value according to user data. Determine that according to user data the specific algorithm of user's comprehensive value will do concrete introduction below.
Step C: user's comprehensive value is stored. It should be noted that storage can regularly carry out in bulk, it is also possible to immediately carry out one by one.
Step D: when receive transfer appointment user data requests, user's comprehensive value corresponding to user is specified in output.
From the foregoing, it will be observed that the method for the offer user profile of embodiment of the present invention, with reference to the index of many aspects, it is possible to weigh user's importance more exactly and present to contact staff, there is consideration comprehensively, the advantages such as the suitability is wide.
In embodiments of the present invention, step B may further include steps B1 to step B3.
Step B1: screen out incomplete user data. In other words, judge for sky, the data of each bar user data whether indices are not for Null, then do not mean that data are complete seriatim. Complete user data is retained when, and incomplete user data is then rejected.
Step B2: complete user data is carried out pretreatment. The detailed process of step B2 can be such that (1) the preset kind index of the logical type in complete user data is remained unchanged (2) preset kind index to the numeric type in complete user data does following process: carries out extreme difference standardization after 1. first carrying out arc tangent process for average more than the preset kind index of the first predetermined threshold value; 2. extreme difference standardization is made directly less than or equal to the first predetermined threshold value and be more than or equal to the preset kind index of the second predetermined threshold value for average; 3. extreme difference standardization is carried out after totalling process first being carried out less than the preset kind index of the second predetermined threshold value for average.It should be noted that the first predetermined threshold value is more than the second predetermined threshold value.
Step B3: adopt analytic hierarchy process (AHP) that pre-processed results is calculated, obtain user's comprehensive value. Analytic hierarchy process AHP (AnalyticHierarchyProcess) is that the element always relevant with decision-making is resolved into the levels such as target, criterion, scheme, carries out the decision method of qualitative and quantitative analysis on this basis. The basic step of analytic hierarchy process (AHP) is roughly divided into " Judgement Matricies, calculate weight vector coefficient, carry out consistency check, be formally weighted " four steps.
Alternatively, after step B3, step B4 is also included: judge whether user's comprehensive value of all users meets normal distribution. If meeting normal distribution, enter downstream, if not meeting normal distribution, the weight parameter in modifying layer fractional analysis, again adopt analytic hierarchy process (AHP) that pre-processed results is calculated. In other words, if meeting normal distribution, entering step C, if not meeting, re-executing step B3.
As in figure 2 it is shown, the device 20 of the offer information of embodiments of the present invention includes: acquisition module 21, determine module 22, memory module 23 and output module 24.
Acquisition module 21 is for gathering the user data that each user is corresponding, and user data includes multiple preset kind index. Determine that module 22 is for determining user's comprehensive value according to user data. Memory module 23 is for storing user's comprehensive value; Output module 24 when receive transfer appointment user data requests, user's comprehensive value corresponding to user is specified in output.
From the foregoing, it will be observed that the device of the offer user profile of embodiment of the present invention, with reference to the index of many aspects, it is possible to weigh user's importance more exactly and present to contact staff, there is consideration comprehensively, the advantages such as the suitability is wide.
Alternatively, user data can include buying in the recent period natural law, recent order total amount, the recent actual delivery amount of money, recent order volume, in the recent period single all amount of money, whether blacklist, finally buy Days from present time, your the order amount of money, the quantity that buys luxuries, user's login times, cancellation of order number of times, reject single amount, compensate in applications at least one.
Optionally it is determined that module 22 is additionally operable to: screen out incomplete user data; Complete user data is carried out pretreatment; Adopt analytic hierarchy process (AHP) that pre-processed results is calculated, obtain user's comprehensive value.
Optionally it is determined that module 22 is additionally operable to: the preset kind index of the logical type in complete user data is remained unchanged; The preset kind index of the numeric type in complete user data is done following process: after arc tangent process is first carried out more than the preset kind index of the first predetermined threshold value for average, carry out extreme difference standardization; Extreme difference standardization is made directly less than or equal to the first predetermined threshold value and be more than or equal to the preset kind index of the second predetermined threshold value for average; Carrying out extreme difference standardization after first carrying out totalling process for average less than the preset kind index of the second predetermined threshold value, wherein the first predetermined threshold value is more than the second predetermined threshold value.
Alternatively, determine that module 22 is additionally operable to: judge whether user's comprehensive value of all users meets normal distribution, if meeting, enter downstream, if not meeting, the weight parameter in modifying layer fractional analysis, again adopt analytic hierarchy process (AHP) that pre-processed results is calculated.
From the foregoing, it will be observed that the device of the offer user profile of embodiment of the present invention, with reference to the index of many aspects, it is possible to weigh user's importance more exactly and present to contact staff, there is consideration comprehensively, the advantages such as the suitability is wide.
For making those skilled in the art be more fully understood that, specific embodiment is set forth below and illustrates.
1st step: gather user data.
Obtain the data such as the order detailed data of user, user basic information, USI user service information, collect table sample by user as shown in table 1.
Table 1 user data summary sheet
2nd step: integrity verifies.
Use sql to judge the field of verification every record, if not being Null, then check tag is designated as 1 (" 1 " expression is upchecked), is otherwise designated as 0.
3rd step: data prediction.
When level when between each index differs greatly, for avoiding being analyzed the prominent high numerical indication that the causes weakening effect to low numerical indication by original index value, it is therefore desirable to original index data are carried out pretreatment. The logic of Preprocessing Algorithm all uses sql+python script to encapsulate in a program. Preprocessor specifically includes following steps:
(1) logical type index is not processed, retain former state. Whether the index processed includes: " blacklist ".
(2) the high unit magnitude achievement data of numerical value relatively big (such as numerical value typically over 1000) in logarithm value type index, carries out extreme difference standardization after first carrying out arc tangent process.
The index processed includes: the nearly order total amount (after_prefr_amount) in March, user's actual delivery amount of money (user_actual_pay_amount) in nearly March, nearly March the single all amount of money (avg_ord_amount), the most expensive list the amount of money (max_p_after_prefr_amount).
Wherein, arctan function refers to function: y=arctanx, and its codomain is (-pi/2, pi/2).
Extreme difference standardization is also known as min-max standardization, and processing formula is:
New data=(former data-minimum)/(maximum-minimum), codomain interval [0,1]
(3) the middle unit magnitude achievement data that in logarithm value type index, numerical value is placed in the middle, is made directly extreme difference standardization. The index name processed and objective result are in Table 2.
Unit magnitude achievement data list in table 2
(4) the low unit magnitude achievement data of numerical value less (such as numerical value is usually less than 10) in logarithm value type index, carries out extreme difference standardization after first carrying out totalling process.
The index processed includes: cancellation of order number of times (cancel_ord_num), the single amount (reject_ord_num) of rejection, compensation applications (recoup_apply_num).
Wherein adding up operation is: ana_badman_num=
cancel_ord_num+reject_ord_num+recoup_apply_num
4th step: Judgement Matricies, calculate weight vector coefficient and carry out consistency check.
The purpose of this step is that each factor to level compares between two. According to calculating each factor of each judgment matrix for the relative weight coefficient of its criterion, finally by consistency check, could illustrate that judgment matrix is logically rational.
Wherein, consistency check formula is: CR=CI/RI.
CR (consistencyratio) represents consistency ration, when CR is < when 0.10, it is believed that the concordance of judgment matrix is acceptable. CI (consistencyindex) represents coincident indicator, is calculated as follows: CI=(�� max-n)/(n-1), and �� max represents the Maximum characteristic root of judgment matrix; N represents the number of the paired comparison factor.RI (randomindex) represents random index, and it can be tabled look-up and determine.
The target layers structure of the user's comprehensive value shown in Fig. 3, carries out judgment matrix proportion, calculates weight vectors and consistency detection, if Table 3 below is to shown in table 7:
Table 3 user contributes step analysis
Table 4 user's purchasing power step analysis
Table 5 user contributes step analysis
Table 6 user's liveness step analysis
Table 7 user services unfavorable ratings step analysis
| Evaluation index | Weight wi |
| Cancellation of order number of times+rejection number+compensation amount | Wi_51=0.5 |
| Blacklist | Wi_52=0.5 |
5th step: calculate sublayer index index.
Application level analytic process adds up by the weight of each straton index factor and calculates, and obtains user's contribution index, user's buying power index, consumer loyalty degree index, user's liveness index and user and services unfavorable ratings index. The logic of the algorithm of this step all uses sql+python script to encapsulate in a program. Operate as follows:
M1_value (user's contribution index)=0.088*scale_ord_num+0.2426*scale_after_prefr_amount+0.66 94*scale_user_actual_pay_amount
M2_buy (user's buying power index)=0.637*scale_max_p_after_prefr_amount+0.2583*scale_after_ prefr_amount+0.1047*scale_y_sale_qtty
M3_loyt (consumer loyalty degree index)=0.7306*scale_avg_ord_amount+0.1884*scale_cnt_ord_dt+0.08 1*scale_ord_num
M4_acti (user's liveness index)=0.637*scale_last_ord_days+
0.2583*scale_cnt_ord_dt+0.1047*scale_user_login_times
M5_goodrate (user services unfavorable ratings index)=10-(0.5*scale_ana_badman_num+0.5*black_user_flag*10)
6th step: calculate user's comprehensive value.
The result of calculation of previous step is calculated arithmetic average, as the final appraisal results of user's comprehensive value. Algorithm is as follows:
Avg_per_user=(m1_value+m2_buy+m3_loyt+m4_acti+m5_goodrate)/5
Illustrate with user data above, obtain result as shown in table 8. Data in table 8 carry out retaining 2 decimals and process, and numerical value this user's comprehensive value of more big expression is more high.
Table 8 user's comprehensive value summary sheet
7th step: data test collection data distribution checking.
Sample of users evaluation result is carried out distribution tests, meets normal distribution and be just considered verification and pass through.
Method of calibration: use verification function shapiro.test () in R language
Operational approach: shapiro.test (data)
The logic of algorithm above all uses R+sql+python script to be encapsulated in this subprogram.
8th step: storage data.
By database link user's comprehensive value of user imported in the object library of customer service system, wait call request.
9th step: be applied to customer service system.
Contact staff can obtain user's comprehensive value result by retrieval and inquisition data base. When caller client or online tool consulting, complaint or other problems, contact staff takes different business games to service user according to the user's comprehensive value inquired. Such as:
Case A: incoming call client is high score client (vip top-tier customer), its counseling problem is that the dispensing of certain order postpones, contact staff checks score, send work order immediately and carry out reminder, and the contact method of the delivery service personnel of order dispensing station is informed client, feedback client's arrival time and dispensing person, improve CSAT as early as possible.
Case B: incoming call client is low point of client (low value client), its counseling problem is also that the dispensing of certain order postpones, and contact staff checks score, does not do reminder, inform that client bears with, save entreprise cost in normal timeliness.
As seen from the above, by considering that many factors calculates user's comprehensive value of electricity business's customer service system, break away from over only by the simple evaluation standard of the customer consumption amount of money. Above-described embodiment adopts various dimensions multi objective and increases the negative value of services factor, thus the evaluation of user's comprehensive value is more comprehensive; On the other hand, the present invention adopts R+sql+python script synthetical development technology, replaces using in the past sql simple statistics technology, therefore can increase complex logic, merge multiple data mining algorithm so that system extension and application effect are obviously improved.
In service application value, contact staff is in the service process of client, by the acquisition to user's comprehensive value information, customer service can be helped to improve the service level to core customer, final realization is increased customer satisfaction degree, and maintains customer loyalty, promotes client's consumption in electricity business website to promote.
Above-mentioned detailed description of the invention, is not intended that limiting the scope of the invention. Those skilled in the art are it is to be understood that depend on designing requirement and other factors, it is possible to various amendment, combination, sub-portfolio and replacement occur. Any amendment, equivalent replacement and improvement etc. made within the spirit and principles in the present invention, should be included within scope.
Claims (10)
1. the method that user profile is provided, it is characterised in that including:
Gathering the user data of each user, described user data includes multiple preset kind index;
User's comprehensive value is determined according to described user data;
Described user's comprehensive value is stored;
When receive transfer appointment user data requests, export and described specify described user's comprehensive value corresponding to user.
2. the method for offer user profile according to claim 1, it is characterized in that, described user data include buying in the recent period natural law, recent order total amount, the recent actual delivery amount of money, recent order volume, in the recent period single all amount of money, whether blacklist, finally buy Days from present time, your the order amount of money, the quantity that buys luxuries, user's login times, cancellation of order number of times, reject single amount, compensate in applications at least one.
3. the method for offer user profile according to claim 1, it is characterised in that determine that according to described user data the step of user's comprehensive value includes:
Screen out incomplete described user data;
Complete described user data is carried out pretreatment;
Adopt analytic hierarchy process (AHP) that pre-processed results is calculated, obtain described user's comprehensive value.
4. the method for offer user profile according to claim 3, it is characterised in that the step that complete described user data carries out pretreatment includes:
The preset kind index of the logical type in complete described user data is remained unchanged;
The preset kind index of the numeric type in complete described user data is done following process: after arc tangent process is first carried out more than the preset kind index of the first predetermined threshold value for average, carry out extreme difference standardization; Extreme difference standardization is made directly less than or equal to the first predetermined threshold value and be more than or equal to the preset kind index of the second predetermined threshold value for average; Carrying out extreme difference standardization after first carrying out totalling process for average less than the preset kind index of the second predetermined threshold value, wherein the first predetermined threshold value is more than the second predetermined threshold value.
5. the method for offer user profile according to claim 3, it is characterised in that adopting analytic hierarchy process (AHP) that pre-processed results is calculated, after obtaining the step of described user's comprehensive value, also including:
Judging whether described user's comprehensive value of all users meets normal distribution, if meeting, entering downstream, if not meeting, revising the weight parameter in described analytic hierarchy process (AHP), again adopt analytic hierarchy process (AHP) that described pre-processed results is calculated.
6. the device of the offer user profile that user profile is provided, it is characterised in that including:
Acquisition module, for gathering the user data of each user, described user data includes multiple preset kind index;
Determine module, for determining user's comprehensive value according to described user data;
Memory module, for storing described user's comprehensive value;
Output module, when receive transfer appointment user data requests, export and described specify described user's comprehensive value corresponding to user.
7. the device of offer user profile according to claim 6, it is characterized in that, described user data include buying in the recent period natural law, recent order total amount, the recent actual delivery amount of money, recent order volume, in the recent period single all amount of money, whether blacklist, finally buy Days from present time, your the order amount of money, the quantity that buys luxuries, user's login times, cancellation of order number of times, reject single amount, compensate in applications at least one.
8. the device of offer user profile according to claim 6, it is characterised in that described determine that module is additionally operable to:
Screen out incomplete described user data;
Complete described user data is carried out pretreatment;
Adopt analytic hierarchy process (AHP) that pre-processed results is calculated, obtain described user's comprehensive value.
9. the device of offer user profile according to claim 8, it is characterised in that described determine that module is additionally operable to:
The preset kind index of the logical type in complete described user data is remained unchanged;
The preset kind index of the numeric type in complete described user data is done following process: after arc tangent process is first carried out more than the preset kind index of the first predetermined threshold value for average, carry out extreme difference standardization; Extreme difference standardization is made directly less than or equal to the first predetermined threshold value and be more than or equal to the preset kind index of the second predetermined threshold value for average; Carrying out extreme difference standardization after first carrying out totalling process for average less than the preset kind index of the second predetermined threshold value, wherein the first predetermined threshold value is more than the second predetermined threshold value.
10. the device of offer user profile according to claim 8, it is characterised in that described determine that module is additionally operable to:
Judging whether described user's comprehensive value of all users meets normal distribution, if meeting, entering downstream, if not meeting, revising the weight parameter in described analytic hierarchy process (AHP), again adopt analytic hierarchy process (AHP) that described pre-processed results is calculated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510990663.7A CN105654311A (en) | 2015-12-24 | 2015-12-24 | User information providing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510990663.7A CN105654311A (en) | 2015-12-24 | 2015-12-24 | User information providing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105654311A true CN105654311A (en) | 2016-06-08 |
Family
ID=56477607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510990663.7A Pending CN105654311A (en) | 2015-12-24 | 2015-12-24 | User information providing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105654311A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106447404A (en) * | 2016-10-21 | 2017-02-22 | 青岛海信移动通信技术股份有限公司 | Method and device for determining user type |
| CN107968893A (en) * | 2016-10-19 | 2018-04-27 | 阿里巴巴集团控股有限公司 | A kind of means of communication and device |
| CN108076237A (en) * | 2016-11-18 | 2018-05-25 | 腾讯科技（深圳）有限公司 | A kind of phone customer service data processing method and device |
| CN108269118A (en) * | 2017-01-03 | 2018-07-10 | 中兴通讯股份有限公司 | A kind of method and apparatus of data analysis |
| CN110222028A (en) * | 2019-04-30 | 2019-09-10 | 重庆小雨点小额贷款有限公司 | A kind of data managing method, device, equipment and storage medium |
| CN111275523A (en) * | 2020-01-17 | 2020-06-12 | 青梧桐有限责任公司 | Method and system for calculating recommended amount based on irregular data |
-
2015
- 2015-12-24 CN CN201510990663.7A patent/CN105654311A/en active Pending
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107968893A (en) * | 2016-10-19 | 2018-04-27 | 阿里巴巴集团控股有限公司 | A kind of means of communication and device |
| CN106447404A (en) * | 2016-10-21 | 2017-02-22 | 青岛海信移动通信技术股份有限公司 | Method and device for determining user type |
| CN108076237A (en) * | 2016-11-18 | 2018-05-25 | 腾讯科技（深圳）有限公司 | A kind of phone customer service data processing method and device |
| CN108076237B (en) * | 2016-11-18 | 2020-06-05 | 腾讯科技（深圳）有限公司 | Telephone customer service data processing method and device |
| CN108269118A (en) * | 2017-01-03 | 2018-07-10 | 中兴通讯股份有限公司 | A kind of method and apparatus of data analysis |
| CN108269118B (en) * | 2017-01-03 | 2023-11-17 | 中兴通讯股份有限公司 | Data analysis method and device |
| CN108269118B9 (en) * | 2017-01-03 | 2024-01-02 | 中兴通讯股份有限公司 | Data analysis method and device |
| CN110222028A (en) * | 2019-04-30 | 2019-09-10 | 重庆小雨点小额贷款有限公司 | A kind of data managing method, device, equipment and storage medium |
| CN111275523A (en) * | 2020-01-17 | 2020-06-12 | 青梧桐有限责任公司 | Method and system for calculating recommended amount based on irregular data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105654311A (en) | User information providing method and device | |
| EP3043447B1 (en) | Distribution transformer heavy loading and overloading mid-term and short-term pre-warning analytics model | |
| Zhang et al. | An application of the AHP in 3PL vendor selection of a 4PL system | |
| Tung | Customer satisfaction, perceived value and customer loyalty: the mobile services industry in China | |
| US20130275176A1 (en) | Risk assessment of a supplier of an organization | |
| US20170372389A1 (en) | Adaptive and tunable risk processing system and method | |
| CN108712279B (en) | User off-network prediction method and device | |
| Lim et al. | Cost-of-quality optimization via zero-one polynomial programming | |
| CN107153985A (en) | A kind of excavation of user side multi-energy data and analysis method | |
| CN113408114A (en) | Method and system for evaluating vulnerability threat degree of power monitoring system equipment | |
| KR100974342B1 (en) | The system for company credit rating using the recommendation of professional group | |
| CN115689752A (en) | Method, device and equipment for adjusting wind control rule and storage medium | |
| CN114782123A (en) | Credit assessment method and system | |
| CN108428108A (en) | Government affairs information dissemination method, device and terminal device | |
| CN114331735A (en) | Financial risk model training method and device and financial risk prediction method and device | |
| CN112950359B (en) | User identification method and device | |
| Samson et al. | Linear models as aids in insurance decision making: the estimation of automobile insurance claims | |
| Ma et al. | Supplier selection analysis under the green supply chain | |
| US20190066115A1 (en) | Calculation of benchmark dispute overage and rejection data with redress options | |
| CN113643061A (en) | Intelligent delivery system based on big data machine learning | |
| CN114266485A (en) | Construction method and construction system of power information communication data quality detection model | |
| US20220351112A1 (en) | System and method for obtaining audit evidence | |
| CN112668842A (en) | Vehicle insurance claim settlement risk factor evaluation method and device, electronic equipment and medium | |
| Yuyang et al. | Establishing information valuing characteristics for engineering design information | |
| CN108073632B (en) | Method, device and system for information processing of terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160608 |
|
| RJ01 | Rejection of invention patent application after publication |