CN109242359A - A kind of method and apparatus obtaining net recommendation - Google Patents
A kind of method and apparatus obtaining net recommendation Download PDFInfo
- Publication number
- CN109242359A CN109242359A CN201811259259.2A CN201811259259A CN109242359A CN 109242359 A CN109242359 A CN 109242359A CN 201811259259 A CN201811259259 A CN 201811259259A CN 109242359 A CN109242359 A CN 109242359A
- Authority
- CN
- China
- Prior art keywords
- user
- recommendation
- access
- access user
- daily
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The object of the present invention is to provide a kind of method and apparatus for obtaining net recommendation, this method comprises: obtaining the recommendation number for accessing user and daily access user in preset time range daily；Determine that daily access user recommends the criterion score of number according to the recommendation number of daily access user described in the preset time range and the daily access user；The criterion score of number is recommended to reject daily abnormal user according to daily access user described in the preset time range, to update the recommendation number of the daily access user and the daily access user；The recommendation value of access user is determined based on the recommendation number of the updated daily access user and the daily access user；Recommendation value based on the access user sets up threshold value and user is divided into the person of disparaging user, passive person user, nominator user's three classes；The access user's percentage of full dose in preset time range is accounted for based on the nominator user and the person of the disparaging user accounts for the difference of full dose access user's percentage in preset time range and determines net recommendation.
Description
Technical field
The present invention relates to computer field more particularly to a kind of method and apparatus for obtaining net recommendation.
Background technique
Customer loyalty is the key that enterprise's profit increases, and enterprise needs to quantify the loyalty of client.Shellfish grace consulting in 2003
Company Frederick Taylor Lei Hede proposes Net Promoter Score (NPS), net recommendation, Frederick Taylor Lei Hede
Think that net recommendation is the number that can be dedicated to enterprise's growth.Recommend some enterprise to other people by measuring some client
Industry or the index for servicing possibility increase to help the impression and attitude of enterprise's measuring customer to seek sustainable business
Point.
Existing net recommendation NPS model mainly understands user to the loyalty of enterprise by way of questionnaire investigation, passes through
User investigates feedback and obtains the net recommendation NPS for measuring customer loyalty.Net recommendation model is made of two parts, first part
Much product/service/brand may be recommended friend or colleague by inquiring that user has? in 0-10/give a mark,
10 points of expressions are ready to recommend very much, and 0 point of expression is unwilling to recommend very much.User is divided into nominator, quilt according to the marking of user
Dynamic person, the person's of disparaging three classes, wherein giving a mark 9-10 points is the loyal user nominator of product, and 7-8 points of marking are satisfied but not earnest
Passive person, marking 0-6 point is to the dissatisfied person of disparaging for even product being prevented to increase of product.Net recommendation NPS is exactly to recommend
The difference of person's percentage and the person's of disparaging percentage.Is second part by inquiring the reason of user provides score? according to
The answer of user carries out subsequent product improvement, improves customer satisfaction.The meaning of net recommendation NPS, which is to establish with user, is
The culture of the heart is reflected the loyalty of user by net recommendation NPS, measures the benign profit and bad profit of enterprise, help to look forward to
The promotion of industry realization public praise and customer loyalty.But there are samples to recycle limited amount for questionnaire investigation；Investigate time, investigation words art
Etc. factors influence lead to not guarantee sample recycling quality；The problems such as investigation recycling is time-consuming, these disadvantages lead to net recommendation
NPS can not reflection consumer loyalty degree promptly and accurately.
Summary of the invention
It is an object of the present invention to provide a kind of method and apparatus for obtaining net recommendation, to solve investigation sample recycling
Limited amount, sample recycling quality not can guarantee and investigate the time-consuming problem of recycling.
The method provided by the invention for obtaining net recommendation, comprising:
Obtain the recommendation number for accessing user and daily access user in preset time range daily；
According to the recommendation number of daily access user described in the preset time range and the daily access user
Determine that daily access user recommends the criterion score of number；
The criterion score of number is recommended to reject daily exception according to daily access user described in the preset time range
User, to update the recommendation number of the daily access user and the daily access user；
Visit is determined based on the recommendation number of the updated daily access user and the daily access user
Ask the recommendation value of user；
Recommendation value based on the access user sets up threshold value and user is divided into the person of disparaging user, passive person user, is pushed away
The person's of recommending user's three classes；
Full dose access user's percentage and the person of the disparaging user in preset time range are accounted for based on the nominator user
The difference for accounting for full dose access user's percentage in preset time range determines net recommendation.
Further, method of the present invention, according to daily access user described in the preset time range and institute
The recommendation number for stating daily access user determines that the step of daily access user recommends the criterion score of number includes:
The criterion score that the daily access user recommends number is calculated according to the following formula:
Wherein, zijIndicate the criterion score for recommending number corresponding to the access user i of access day j access, xijIt indicates
Access recommendation number corresponding to the access user i of day j access, μjIndicate the recommendation in the average each access user of access day j
Number, σjIndicate that all users in access day j access recommend the standard deviation in population of number.
Further, method of the present invention, according to daily access user referrer described in the preset time range
Several criterion score rejects the step of daily abnormal user and includes:
Work as zij> when, the recommendation number for accessing user and the access user is rejected as the daily abnormal user；
Work as zijWhen≤a, retain the recommendation number of access user and the access user；
Wherein, a indicates default screening threshold value.
Further, method of the present invention, based on the updated daily access user and it is described daily
The recommendation number of access user determines that the step of recommendation value of access user includes:
When the recommendation number of daily access user described in the preset time range is zero, then the access user
Recommendation be worth Fi=0；
When the recommendation total number of persons for accessing user in the preset time range is not zero and there is only when primary recommend, according to
The recommendation value of the access user is calculated in following formula:
Wherein, FiIndicate the recommendation value of access user i, αiIt indicates to reject in the preset time range described daily different
The recommendation number of user i, β are accessed behind common familyiIndicate the recommendation date of access user i, tmaxIndicate the preset time range
Interior date maximum value；
When the recommendation total number of persons for accessing user in the preset time range is not zero and number is recommended to be greater than one time, root
The recommendation value of the access user is calculated according to following formula:
Wherein, FiIndicate the recommendation value of access user i, αijIt indicates to reject in the preset time range described daily different
Recommendation number of the access user i in jth time, β behind common familyijThe recommendation date that expression access user i recommends in jth time, j=1,
2 ..., n, n are natural number and n >=2；βinIndicate that the last time, that is, n-th of the access user i in the preset time range pushes away
The recommendation date recommended；
Wherein, secondary recommendation is denoted as primary recommendation more than a day.
Further, method of the present invention, the recommendation value based on the access user set up threshold value and are divided into user
The step of person of disparaging user, passive person user, nominator user's three classes includes:
If the recommendation value of the access user is more than or equal to first threshold, it is determined that the user is nominator user；
If the recommendation value of the access user is less than the first threshold and is more than or equal to second threshold, it is determined that the use
Family is passive person user；
If the recommendation value of the access user is less than the second threshold, it is determined that the user is the person of disparaging user.
The device provided by the invention for obtaining net recommendation, comprising:
Module is obtained, for obtaining the referrer for accessing user and daily access user in preset time range daily
Number；
Criterion score module is used according to daily access user described in the preset time range and the daily access
The recommendation number at family determines that daily access user recommends the criterion score of number；
Update module, for recommending the criterion score of number according to daily access user described in the preset time range
Daily abnormal user is rejected, to update the recommendation number of the daily access user and the daily access user；
Recommend value module, for being based on the updated daily access user and the daily access user
Recommendation number determine access user recommendation value；
Categorization module, for based on it is described access user recommendation value set up threshold value by user be divided into the person of disparaging user,
Passive person user, nominator user's three classes；
Net recommendation module accesses user's percentage for accounting for full dose in preset time range based on the nominator user
The difference for accounting for full dose access user's percentage in preset time range with the person of the disparaging user determines net recommendation.
Further, device of the present invention, the criterion score module are specifically used for:
The criterion score that the daily access user recommends number is calculated according to the following formula:
Wherein, zijIndicate the criterion score for recommending number corresponding to the access user i of access day j access, xijIt indicates
Access recommendation number corresponding to the access user i of day j access, μjIndicate the recommendation in the average each access user of access day j
Number, σjIndicate that all users in access day j access recommend the standard deviation in population of number.
Further, device of the present invention, the update module are specifically used for:
Work as zij> when, the recommendation number for accessing user and the access user is rejected as the daily abnormal user；
Work as zijWhen≤a, retain the recommendation number of access user and the access user；
Wherein, a indicates default screening threshold value.
Further, device of the present invention, the recommendation value module are specifically used for:
When the recommendation number of daily access user described in the preset time range is zero, then the access user
Recommendation be worth Fi=0；
When the recommendation total number of persons for accessing user in the preset time range is not zero and there is only when primary recommend, according to
The recommendation value of the access user is calculated in following formula:
Wherein, FiIndicate the recommendation value of access user i, αiIt indicates to reject in the preset time range described daily different
The recommendation number of user i, β are accessed behind common familyiIndicate the recommendation date of access user i, tmaxIndicate the preset time range
Interior date maximum value；
When the recommendation total number of persons for accessing user in the preset time range is not zero and number is recommended to be greater than one time, root
The recommendation value of the access user is calculated according to following formula:
Wherein, FiIndicate the recommendation value of access user i, αijIt indicates to reject in the preset time range described daily different
Recommendation number of the access user i in jth time, β behind common familyijThe recommendation date that expression access user i recommends in jth time, j=1,
2 ..., n, n are natural number and n >=2；βinIndicate that the last time, that is, n-th of the access user i in the preset time range pushes away
The recommendation date recommended；
Wherein, secondary recommendation is denoted as primary recommendation more than a day.
Further, device of the present invention, the categorization module are specifically used for:
If the recommendation value of the access user is more than or equal to first threshold, it is determined that the user is nominator user；
If the recommendation value of the access user is less than the first threshold and is more than or equal to second threshold, it is determined that the use
Family is passive person user；
If the recommendation value of the access user is less than the second threshold, it is determined that the user is the person of disparaging user.
The present invention also provides a kind of computer readable storage medium, the computer-readable recording medium storage instruction, institute
Instruction method according to the present invention is stated to be executed.
The present invention also provides a kind of calculating equipment, comprising:
Processor；And
It is arranged to the memory of storage computer executable instructions, the executable instruction makes the place when executed
Reason device executes the operation of method as described herein.
A kind of method and apparatus obtaining net recommendation provided by the invention, by product full dose user in the product
Net recommendation NPS is calculated in actual recommendation behavior, overcomes investigation sample recycling limited amount, sample recycling quality can not protect
The problem of card and investigation recycling time-consuming.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, of the invention other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is the flow diagram of the method for the net recommendation of acquisition of the embodiment of the present invention one；
Fig. 2 is in the embodiment of the present invention to daily access user and the flow diagram for recommending number to be updated；
Fig. 3 is to recommend number according to user in the embodiment of the present invention and the time is recommended to calculate the process that user recommends value
Schematic diagram；
Fig. 4 is to recommend value that user is divided into nominator, passive person, the person of disparaging according to user in the embodiment of the present invention
Flow diagram；
Fig. 5 is the structural schematic diagram of the device of the net recommendation of acquisition of the embodiment of the present invention two.
The same or similar appended drawing reference represents the same or similar component in attached drawing.
Specific embodiment
Present invention is further described in detail with reference to the accompanying drawing.
Fig. 1 is the flow diagram of the method for the net recommendation of acquisition of the embodiment of the present invention one, as shown in Figure 1, of the invention
The method of the net recommendation of acquisition of embodiment one, comprising:
Step S101 obtains the recommendation number for accessing user and daily access user in preset time range daily.
Wherein, it identifies and its visits by the User ID that application program (APP, Application) obtains daily access user
Ask data.The data that daily access user is recommended to other users are obtained by APP, such as circle of friends is shared, user pushes away
Equal behavioral datas are recommended, and therefrom extract recommendation number.
Step S102, according to the daily access user described in the preset time range and the daily access user
Recommendation number determines that daily access user recommends the criterion score of number.
Wherein, the criterion score that the daily access user recommends number is calculated according to the following formula:
Wherein, zijIndicate the criterion score for recommending number corresponding to the access user i of access day j access, xijIt indicates
Access recommendation number corresponding to the access user i of day j access, μjIndicate the recommendation in the average each access user of access day j
Number, σjIndicate that all users in access day j access recommend the standard deviation in population of number.
Specifically, μjIndicate that the access user in jth day access APP recommends the average value of number, μjIt is based on daily access
What user obtained, the value can overall performance access daily user recommend number central tendency；σjIt indicates to access APP in jth day
Access user recommend number standard deviation in population, σjTo be obtained based on daily access user, the value can overall performance it is every
Day access user recommends the dispersion degree of number.
Step S103 recommends the criterion score of number to reject according to daily access user described in the preset time range
Daily abnormal user, to update the recommendation number of the daily access user and the daily access user.
Wherein, the step of rejecting daily abnormal user include:
Work as zij> when, the recommendation number for accessing user and the access user is rejected as the daily abnormal user；
Work as zijWhen≤a, retain the recommendation number of access user and the access user；
Wherein, a indicates default screening threshold value.
For example, Fig. 2 is to illustrate in the embodiment of the present invention to daily access user and the process for recommending number to be updated
Figure determines that daily access user recommends the criterion score of number as shown in Fig. 2, obtaining daily access user and its recommending number.
If screening threshold value a=2.As criterion score zijWhen > 2, illustrate data exception, pushing away for user data and access user will be accessed
Recommend number rejecting；As criterion score zijWhen≤2, illustrate that accessing user recommends number normal, retained business data, and then complete number
According to update.
Step S104, the referrer based on the updated daily access user and the daily access user
Number determines the recommendation value of access user.
Fig. 3 is to recommend number according to user in the embodiment of the present invention and the time is recommended to calculate the process that user recommends value
Schematic diagram, as shown in figure 3, based on accessing user after the update daily and its recommending number, it is contemplated that user is one or many
The recommendation of recommendation behavior is worth difference, and value is recommended to be influenced by recommendation time factor, therefore by user by recommendation behavior point
For nominator, passive person, the person's of disparaging three classes, the recommendation value of nominator, passive person, the person of disparaging three classes user are defined respectively.
Specifically, when the recommendation number of daily access user described in the preset time range is zero, then described
The recommendation for accessing user is worth Fi=0.
Specifically, when the recommendation total number of persons for accessing user in the preset time range is not zero and recommends there is only primary
When, secondary recommendation it will be denoted as primary recommendation more than a day, the recommendation value of the access user is calculated according to the following formula:
Wherein, FiIndicate the recommendation value of access user i, αiIt indicates to reject in the preset time range described daily different
The recommendation number of user i, β are accessed behind common familyiIndicate the recommendation date of access user i, tmaxIndicate the preset time range
Interior date maximum value.
Specifically, when the recommendation total number of persons for accessing user in the preset time range is not zero and number is recommended to be greater than one
When secondary, wherein primary recommendation will be denoted as secondary recommendation more than a day, recommend number to be greater than and once shows there is recommendation behavior in several days,
The recommendation value of the access user is calculated according to the following formula:
Wherein, FiIndicate the recommendation value of access user i, αijIt indicates to reject in the preset time range described daily different
Recommendation number of the access user i in jth time, β behind common familyijThe recommendation date that expression access user i recommends in jth time, j=1,
2 ..., n, n are natural number and n >=2；βinIndicate that the last time, that is, n-th of the access user i in the preset time range pushes away
The recommendation date recommended.
Step S105, the recommendation value based on the access user set up threshold value and user are divided into the person of disparaging user, passive
Person user, nominator user's three classes.
Fig. 4 is to recommend value that user is divided into nominator, passive person, the person of disparaging according to user in the embodiment of the present invention
Flow diagram, as shown in figure 4, determining that the user is the person of disparaging user when the recommendation value for accessing user is zero.
When the recommendation value for accessing user is greater than zero, classify according to following three kinds of situations:
If the recommendation value of the access user is more than or equal to first threshold, it is determined that the user is nominator user；
If the recommendation value of the access user is less than the first threshold and is more than or equal to second threshold, it is determined that the use
Family is passive person user；
If the recommendation value of the access user is less than the second threshold, it is determined that the user is the person of disparaging user.
Step S106 accounts in preset time range full dose access user's percentage based on the nominator user and described demotes
The difference that damage person user accounts for full dose access user's percentage in preset time range determines net recommendation.
The method of the net recommendation of acquisition of the embodiment of the present invention one, can obtain the recommendation behavioral data of user in time, lead to
The recommendation behavioral data of user is crossed to measure customer loyalty, daily observation NPS index is customized, timely feedbacks consumer products experience
And follow-up carries out product optimization in time, saves time cost, quickly pushes product optimization；It can be by recommending to go to full dose user
To be analyzed, Massive Sample can be statisticallyd analyze, compares existing NPS calculation method, analysis stability is high；It solves existing
For net recommendation by investigation sample size, investigation sample recycles quality, and investigation recovery time influence can not timely feedback user behavior,
To user, there are the potential influences for bothering factor for investigation, provide one kind in time, stability is high, is suitable for the analysis of big data magnanimity
The net recommendation of acquisition method.
Fig. 5 is the structural schematic diagram of the device of the net recommendation of acquisition of the embodiment of the present invention two, as shown in figure 5, of the invention
The device of the net recommendation of acquisition of embodiment two includes: to obtain module 51, criterion score module 52, update module 53, recommendation valence
It is worth module 54, categorization module 55 and net recommendation module 56.
Module 51 is obtained, for obtaining the referrer for accessing user and daily access user in preset time range daily
Number.
Criterion score module 52, according to daily access user described in the preset time range and the daily access
The recommendation number of user determines that daily access user recommends the criterion score of number.
Wherein, the criterion score module is specifically used for that the daily access user recommendation is calculated according to the following formula
The criterion score of number:
Wherein, zijIndicate the criterion score for recommending number corresponding to the access user i of access day j access, xijIt indicates
Access recommendation number corresponding to the access user i of day j access, μjIndicate the recommendation in the average each access user of access day j
Number, σjIndicate that all users in access day j access recommend the standard deviation in population of number.
Update module 53, for recommending the standard scores of number according to daily access user described in the preset time range
Number rejects daily abnormal user, to update the recommendation number of the daily access user and the daily access user.
Wherein, the update module is specifically used for:
Work as zij> when, the recommendation number for accessing user and the access user is rejected as the daily abnormal user；
Work as zijWhen≤a, retain the recommendation number of access user and the access user；
Wherein, a indicates default screening threshold value.
Recommend value module 54, for using based on the updated daily access user and the daily access
The recommendation number at family determines the recommendation value of access user.
Wherein, the recommendation value module is specifically used for:
When the recommendation number of daily access user described in the preset time range is zero, then the access user
Recommendation be worth Fi=0；
When the recommendation total number of persons for accessing user in the preset time range is not zero and there is only when primary recommend, according to
The recommendation value of the access user is calculated in following formula:
Wherein, FiIndicate the recommendation value of access user i, αiIt indicates to reject in the preset time range described daily different
The recommendation number of user i, β are accessed behind common familyiIndicate the recommendation date of access user i, tmaxIndicate the preset time range
Interior date maximum value；
When the recommendation total number of persons for accessing user in the preset time range is not zero and number is recommended to be greater than one time, root
The recommendation value of the access user is calculated according to following formula:
Wherein, FiIndicate the recommendation value of access user i, αijIt indicates to reject in the preset time range described daily different
Recommendation number of the access user i in jth time, β behind common familyijThe recommendation date that expression access user i recommends in jth time, j=1,
2 ..., n, n are natural number and n >=2；βinIndicate that the last time, that is, n-th of the access user i in the preset time range pushes away
The recommendation date recommended；
Wherein, secondary recommendation is denoted as primary recommendation more than a day.
Categorization module 55 sets up threshold value for the recommendation value based on the access user and user is divided into the person's of disparaging use
Family, passive person user, nominator user's three classes.
Wherein, the categorization module is specifically used for:
If the recommendation value of the access user is more than or equal to first threshold, it is determined that the user is nominator user；
If the recommendation value of the access user is less than the first threshold and is more than or equal to second threshold, it is determined that the use
Family is passive person user；
If the recommendation value of the access user is less than the second threshold, it is determined that the user is the person of disparaging user.
Net recommendation module 56 accesses user's percentage for accounting for full dose in preset time range based on the nominator user
Difference than accounting for full dose access user's percentage in preset time range with the person of the disparaging user determines net recommendation.
The device of the embodiment of the present invention two is the realization device for the method that the present invention implements one, and concrete principle is with reference to this
Inventive embodiments one, details are not described herein again.
The present invention also provides a kind of computer readable storage medium, the computer-readable recording medium storage instruction, institute
The method for stating instruction according to embodiments of the present invention one is executed.
The present invention also provides a kind of calculating equipment, comprising:
Processor；And
It is arranged to the memory of storage computer executable instructions, the executable instruction makes the place when executed
Manage the operation for the method that device is executed such as the embodiment of the present invention one.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
It should be noted that the present invention can be carried out in the assembly of software and/or software and hardware, for example, can adopt
With specific integrated circuit (ASIC), general purpose computer or any other realized similar to hardware device.In one embodiment
In, software program of the invention can be executed to implement the above steps or functions by processor.Similarly, of the invention
Software program (including relevant data structure) can be stored in computer readable recording medium, for example, RAM memory,
Magnetic or optical driver or floppy disc and similar devices.In addition, some of the steps or functions of the present invention may be implemented in hardware, example
Such as, as the circuit cooperated with processor thereby executing each step or function.
In addition, a part of the invention can be applied to computer program product, such as computer program instructions, when its quilt
When computer executes, by the operation of the computer, it can call or provide according to the method for the present invention and/or technical solution.
And the program instruction of method of the invention is called, it is possibly stored in fixed or moveable recording medium, and/or pass through
Broadcast or the data flow in other signal-bearing mediums and transmitted, and/or be stored according to described program instruction operation
In the working storage of computer equipment.Here, according to one embodiment of present invention including a device, which includes using
Memory in storage computer program instructions and processor for executing program instructions, wherein when the computer program refers to
When enabling by processor execution, method and/or skill of the device operation based on aforementioned multiple embodiments according to the present invention are triggered
Art scheme.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included in the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.This
Outside, it is clear that one word of " comprising " does not exclude other units or steps, and odd number is not excluded for plural number.That states in device claim is multiple
Unit or device can also be implemented through software or hardware by a unit or device.The first, the second equal words are used to table
Show title, and does not indicate any particular order.
Claims (12)
1. a kind of method for obtaining net recommendation characterized by comprising
Obtain the recommendation number for accessing user and daily access user in preset time range daily；
It is determined according to the recommendation number of daily access user described in the preset time range and the daily access user
Daily access user recommends the criterion score of number；
The criterion score of number is recommended to reject daily abnormal user according to daily access user described in the preset time range,
To update the recommendation number of the daily access user and the daily access user；
Determine that access is used based on the recommendation number of the updated daily access user and the daily access user
The recommendation at family is worth；
Recommendation value based on the access user sets up threshold value and user is divided into the person of disparaging user, passive person user, nominator
User's three classes；
Account in preset time range full dose access user's percentage based on the nominator user and the person of the disparaging user account for it is pre-
If the difference of full dose access user's percentage determines net recommendation in time range.
2. the method according to claim 1, wherein being used according to daily access described in the preset time range
The recommendation number of family and the daily access user determine that the step of daily access user recommends the criterion score of number includes:
The criterion score that the daily access user recommends number is calculated according to the following formula:
Wherein, zijIndicate the criterion score for recommending number corresponding to the access user i of access day j access, xijExpression is accessing
Recommendation number corresponding to the access user i of day j access, μjIndicate the recommendation number in the average each access user of access day j,
σjIndicate that all users in access day j access recommend the standard deviation in population of number.
3. according to the method described in claim 2, it is characterized in that, being used according to daily access described in the preset time range
Family recommend number criterion score reject daily abnormal user the step of include:
Work as zijWhen > a, the recommendation number for accessing user and the access user is rejected as the daily abnormal user；
Work as zijWhen≤a, retain the recommendation number of access user and the access user；
Wherein, a indicates default screening threshold value.
4. according to the method described in claim 3, it is characterized in that, based on the updated daily access user and
The recommendation number of the daily access user determines that the step of recommendation of access user is worth includes:
It is when the recommendation number of daily access user described in the preset time range is zero, then described to access pushing away for user
Recommend value Fi=0；
When the recommendation total number of persons for accessing user in the preset time range is not zero and there is only when primary recommend, according to as follows
The recommendation value of the access user is calculated in formula:
Wherein, FiIndicate the recommendation value of access user i, αiIt indicates to reject the daily abnormal use in the preset time range
The recommendation number of user i, β are accessed behind familyiIndicate the recommendation date of access user i, tmaxIt indicates in the preset time range
Date maximum value；
When the recommendation total number of persons for accessing user in the preset time range is not zero and number is recommended to be greater than one time, according to such as
The recommendation value of the access user is calculated in lower formula:
Wherein, FiIndicate the recommendation value of access user i, αijIt indicates to reject the daily abnormal use in the preset time range
User i is accessed behind family in the recommendation number of jth time, βijThe recommendation date that expression access user i recommends in jth time, j=1,
2 ..., n, n are natural number and n >=2；βinIndicate that the last time, that is, n-th of the access user i in the preset time range pushes away
The recommendation date recommended；
Wherein, secondary recommendation is denoted as primary recommendation more than a day.
5. according to the method described in claim 4, it is characterized in that, the recommendation value based on the access user is set up threshold value and is incited somebody to action
User is divided into the step of person of disparaging user, passive person user, nominator user's three classes and includes:
If the recommendation value of the access user is more than or equal to first threshold, it is determined that the user is nominator user；
If the recommendation value of the access user is less than the first threshold and is more than or equal to second threshold, it is determined that the user is
Passive person user；
If the recommendation value of the access user is less than the second threshold, it is determined that the user is the person of disparaging user.
6. a kind of device for obtaining net recommendation characterized by comprising
Module is obtained, for obtaining the recommendation number for accessing user and daily access user in preset time range daily；
Criterion score module, according to the daily access user described in the preset time range and the daily access user
Recommendation number determines that daily access user recommends the criterion score of number；
Update module, for recommending the criterion score of number to reject according to daily access user described in the preset time range
Daily abnormal user, to update the recommendation number of the daily access user and the daily access user；
Recommend value module, for pushing away based on the updated daily access user and the daily access user
Recommend the recommendation value that number determines access user；
Categorization module sets up threshold value for the recommendation value based on the access user and user is divided into the person of disparaging user, passive
Person user, nominator user's three classes；
Net recommendation module, for accounting for full dose access user's percentage and institute in preset time range based on the nominator user
It states the person of disparaging user and accounts for the difference of the access user's percentage of full dose in preset time range and determine net recommendation.
7. device according to claim 6, which is characterized in that the criterion score module is specifically used for:
The criterion score that the daily access user recommends number is calculated according to the following formula:
Wherein, zijIndicate the criterion score for recommending number corresponding to the access user i of access day j access, xijExpression is accessing
Recommendation number corresponding to the access user i of day j access, μjIndicate the recommendation number in the average each access user of access day j,
σjIndicate that all users in access day j access recommend the standard deviation in population of number.
8. device according to claim 7, which is characterized in that the update module is specifically used for:
Work as zijWhen > a, the recommendation number for accessing user and the access user is rejected as the daily abnormal user；
Work as zijWhen≤a, retain the recommendation number of access user and the access user；
Wherein, a indicates default screening threshold value.
9. device according to claim 8, which is characterized in that the recommendation value module is specifically used for:
It is when the recommendation number of daily access user described in the preset time range is zero, then described to access pushing away for user
Recommend value Fi=0；
When the recommendation total number of persons for accessing user in the preset time range is not zero and there is only when primary recommend, according to as follows
The recommendation value of the access user is calculated in formula:
Wherein, FiIndicate the recommendation value of access user i, αiIt indicates to reject the daily abnormal use in the preset time range
The recommendation number of user i, β are accessed behind familyiIndicate the recommendation date of access user i, tmaxIt indicates in the preset time range
Date maximum value；
When the recommendation total number of persons for accessing user in the preset time range is not zero and number is recommended to be greater than one time, according to such as
The recommendation value of the access user is calculated in lower formula:
Wherein, FiIndicate the recommendation value of access user i, αijIt indicates to reject the daily abnormal use in the preset time range
User i is accessed behind family in the recommendation number of jth time, βijThe recommendation date that expression access user i recommends in jth time, j=1,
2 ..., n, n are natural number and n >=2；βinIndicate that the last time, that is, n-th of the access user i in the preset time range pushes away
The recommendation date recommended；
Wherein, secondary recommendation is denoted as primary recommendation more than a day.
10. device according to claim 9, which is characterized in that the categorization module is specifically used for:
If the recommendation value of the access user is more than or equal to first threshold, it is determined that the user is nominator user；
If the recommendation value of the access user is less than the first threshold and is more than or equal to second threshold, it is determined that the user is
Passive person user；
If the recommendation value of the access user is less than the second threshold, it is determined that the user is the person of disparaging user.
11. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage instruction, it is described
Instruction the method according to any one of claims 1 to 5 is executed.
12. a kind of calculating equipment characterized by comprising
Processor；And
It is arranged to the memory of storage computer executable instructions, the executable instruction makes the processor when executed
Execute the operation such as any one of claims 1 to 5 the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811259259.2A CN109242359A (en) | 2018-10-26 | 2018-10-26 | A kind of method and apparatus obtaining net recommendation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811259259.2A CN109242359A (en) | 2018-10-26 | 2018-10-26 | A kind of method and apparatus obtaining net recommendation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109242359A true CN109242359A (en) | 2019-01-18 |
Family
ID=65078540
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811259259.2A Pending CN109242359A (en) | 2018-10-26 | 2018-10-26 | A kind of method and apparatus obtaining net recommendation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109242359A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113468394A (en) * | 2021-07-06 | 2021-10-01 | 北京有竹居网络技术有限公司 | Data processing method and device, electronic equipment and storage medium |
-
2018
- 2018-10-26 CN CN201811259259.2A patent/CN109242359A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113468394A (en) * | 2021-07-06 | 2021-10-01 | 北京有竹居网络技术有限公司 | Data processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8620718B2 (en) | Industry specific brand benchmarking system based on social media strength of a brand | |
| Hendren | Private information and insurance rejections | |
| Merchant et al. | Performance measurement and incentive compensation: an empirical analysis and comparison of Chinese and Western firms' practices | |
| Lee et al. | Estimation for volunteer panel web surveys using propensity score adjustment and calibration adjustment | |
| Brunetto et al. | Comparing the impact of management on public and private sector nurses in the UK, Italy, and Australia | |
| US9787838B1 (en) | System and method for analysis of interactions with a customer service center | |
| US11068743B2 (en) | Feature selection impact analysis for statistical models | |
| DE112012005177T5 (en) | Generating a natural language processing model for an information area | |
| CN107391692A (en) | The appraisal procedure and device of a kind of recommendation effect | |
| US20220343433A1 (en) | System and method that rank businesses in environmental, social and governance (esg) | |
| CA3020921A1 (en) | Query optimizer for combined structured and unstructured data records | |
| US20190236718A1 (en) | Skills-based characterization and comparison of entities | |
| Weinschenk et al. | Political trust in the American states | |
| US20150248501A1 (en) | Content analytics | |
| Su et al. | ESG Performance, Demographic Trend, and Labour Investment Efficiency in China | |
| Salisu et al. | The influence of marketing capability on firm performance: An empirical evidence from Nigeria | |
| CN109242359A (en) | A kind of method and apparatus obtaining net recommendation | |
| US20180373723A1 (en) | Method and system for applying a machine learning approach to ranking webpages' performance relative to their nearby peers | |
| Luo et al. | Individual differences and analyst forecast accuracy | |
| Scholta | Semi-automatic inductive derivation of reference process models that represent best practices in public administrations | |
| CN111316259A (en) | System and method for dynamic synthesis and transient clustering of semantic attributes for feedback and adjudication | |
| Thekkat et al. | Luxury shopping websites: The impact of ‘hygiene’design factors on trust and distrust | |
| Ahmad et al. | An integrated framework on service recovery performance: the mediating role of organizational commitment | |
| JP6605683B1 (en) | Estimating method, billing method, computer, and program | |
| Nandi et al. | Towards a Sustainable Future: The Interaction of Corporate Governance and Sustainable Policies with Corporate Social Responsibility |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190118 |
|
| RJ01 | Rejection of invention patent application after publication |