CN111815197A - Influence index calculation method, device, equipment and storage medium - Google Patents

Influence index calculation method, device, equipment and storage medium Download PDF

Info

Publication number
CN111815197A
CN111815197A CN202010728591.XA CN202010728591A CN111815197A CN 111815197 A CN111815197 A CN 111815197A CN 202010728591 A CN202010728591 A CN 202010728591A CN 111815197 A CN111815197 A CN 111815197A
Authority
CN
China
Prior art keywords
user
propagation
participating
index
participating user
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
Application number
CN202010728591.XA
Other languages
Chinese (zh)
Inventor
吴明平
梁新敏
陈羲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Fengzhi Technology Co ltd
Original Assignee
Shanghai Fengzhi Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Fengzhi Technology Co ltd filed Critical Shanghai Fengzhi Technology Co ltd
Priority to CN202010728591.XA priority Critical patent/CN111815197A/en
Publication of CN111815197A publication Critical patent/CN111815197A/en
Pending legal-status Critical Current

Links

Images

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
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • 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
    • 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
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Human Resources & Organizations (AREA)
  • Finance (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Game Theory and Decision Science (AREA)
  • Educational Administration (AREA)
  • Data Mining & Analysis (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

The application provides an influence index calculation method, an influence index calculation device, influence index calculation equipment and a storage medium, and relates to the technical field of internet. The method comprises the following steps: acquiring participation behavior information of a plurality of participant users in a private domain of an object to be launched aiming at the object to be launched; calculating the activity index of each participating user according to the participation behavior information of each participating user; constructing a user propagation network of the object to be launched according to the sharing propagation relationship of a plurality of participating users aiming at the object to be launched; and calculating the influence index of each participating user for the object to be delivered according to the activity index and the propagation network. In the scheme of the invention, the obtained activity index and the propagation network are combined to calculate the influence index of each participating user aiming at the object to be launched, so that the accuracy of obtaining the influence index is improved, the accuracy and the intelligence of launching the object to be launched are improved, and the maximum propagation coverage is obtained.

Description

Influence index calculation method, device, equipment and storage medium
Technical Field
The invention relates to the technical field of internet, in particular to a method, a device, equipment and a storage medium for calculating an influence index.
Background
In the internet era, with the increasing perfection of e-commerce platforms and network content products, e-commerce shopping is no longer a simple network ordering and offline goods receiving mode, and consumers are no longer satisfied with purchasing evaluation and seller show under looking over commodities, and with the coming of the 5G era, the network speed can enable people to release works such as words, pictures, videos and the like at any time and any place. Therefore, more and more companies pay attention to private marketing and social e-commerce, and compared with the large V and star effect in the microblog, some KOCs (Key Opinion leaders, i.e. buyers with strong transmission power) existing in the social e-commerce bring greater transmission and promotion capability of exclusive in the field to the brand.
At present, in social e-commerce, some service providers can provide a fission mode to promote customers for brand parties, can design some customized business logics, and put the customized business logics in a social platform to achieve a propaganda target, and further guide the customized business logics to a corresponding e-commerce platform to achieve the purpose of final transformation and retention.
However, the popularization method has the defects of low delivery accuracy, poor intelligence and the like due to uncontrollable active quality of the community.
Disclosure of Invention
The present invention aims to provide a method, an apparatus, a device and a storage medium for calculating an influence index, so as to improve the accuracy of obtaining the influence index, and further improve the accuracy and intelligence of delivering an object to be delivered, thereby obtaining the maximum propagation coverage.
In order to achieve the above purpose, the technical solutions adopted in the embodiments of the present application are as follows:
in a first aspect, an embodiment of the present application provides an influence index calculation method, where the method includes:
acquiring participation behavior information of a plurality of participant users in a private domain of an object to be launched aiming at the object to be launched;
calculating the activity index of each participating user according to the participation behavior information of each participating user;
constructing a user propagation network of the object to be launched according to the sharing propagation relationship of the plurality of participating users aiming at the object to be launched; the user propagation network is used for indicating a sharing propagation relationship of the plurality of participating users aiming at the information of the object to be delivered;
and calculating the influence index of each participating user for the object to be delivered according to the activity index and the propagation network.
Optionally, the participation behavior information includes: various behavior data of each participating user in a preset time period; the calculating the activity index of each participating user according to the participation behavior information of each participating user comprises the following steps:
calculating the activity index of each participating user according to each behavior data of each participating user in the preset time period and the sum of each behavior data of the plurality of participating users in the preset time period.
Optionally, the calculating the activity indicator of each participating user according to each behavior data of each participating user in the preset time period and a sum of each behavior data of the plurality of participating users in the preset time period includes:
calculating a behavior index of each participating user according to each behavior data of each participating user in the preset time period and the sum of each behavior data of the plurality of participating users in the preset time period;
and weighting according to the plurality of behavior indexes of each participating user, and calculating the activity index of each participating user.
Optionally, the plurality of behavior data includes at least one of: click times, browsing duration, sharing times, transaction quantity of the object to be delivered and transaction consumption resources of the object to be delivered.
Optionally, the calculating, according to the activity index and the propagation network, an influence index of each participating user on the object to be delivered includes:
determining a propagation capacity index of each participating user for the object to be launched according to the sharing propagation relation of each participating user indicated by the user propagation network;
and weighting according to the activity index and the propagation capacity index, and calculating the influence index of each participating user.
Optionally, the determining, according to the sharing propagation relationship of each participating user indicated by the user propagation network, a propagation capability index of each participating user for the object to be delivered includes:
and calculating the propagation capacity index of each participating user by adopting a webpage ranking algorithm according to the sharing propagation relation of each participating user indicated by the user propagation network.
Optionally, before calculating the propagation capability index of each participating user by using a web page ranking algorithm according to the sharing propagation relationship of each participating user indicated by the user propagation network, the method further includes:
determining a degree index of each user node in the user propagation network according to the sharing propagation relationship of each participating user indicated by the user propagation network, wherein the degree index is used for indicating the connection capacity of each user node with other user connection nodes in the user propagation network;
determining super user nodes with the number of the propagation user nodes being larger than or equal to a preset threshold value according to the degree index;
deleting the connection points with the preset times of transmission of the super user node as empty and the free nodes with the number of the transmission nodes lower than the number of the preset connection points from the user transmission network to obtain an updated user transmission network;
correspondingly, the calculating the propagation capacity index of each participating user by using a web page ranking algorithm according to the sharing propagation relationship of each participating user indicated by the user propagation network includes:
and calculating the propagation capacity index of each participating user by adopting a webpage ranking algorithm according to the updated sharing propagation relation of each participating user indicated by the user propagation network.
In a second aspect, an embodiment of the present application further provides an influence index calculation apparatus, where the apparatus includes: the system comprises an acquisition module, a calculation module and a construction module;
the acquisition module is used for acquiring participation behavior information of a plurality of participating users in a private domain of an object to be launched aiming at the object to be launched;
the computing module is used for computing the activity degree index of each participating user according to the participation behavior information of each participating user;
the building module is used for building a user propagation network of the object to be launched according to the sharing propagation relationship of the plurality of participating users for the object to be launched; the user propagation network is used for indicating a sharing propagation relationship of the plurality of participating users aiming at the information of the object to be delivered;
the calculation module is further configured to calculate an influence index of each participating user on the object to be delivered according to the activity index and the propagation network.
Optionally, the participation behavior information includes: various behavior data of each participating user in a preset time period; the calculation module is specifically configured to:
calculating the activity index of each participating user according to each behavior data of each participating user in the preset time period and the sum of each behavior data of the plurality of participating users in the preset time period.
Optionally, the computing module is further specifically configured to:
calculating a behavior index of each participating user according to each behavior data of each participating user in the preset time period and the sum of each behavior data of the plurality of participating users in the preset time period;
and weighting according to the plurality of behavior indexes of each participating user, and calculating the activity index of each participating user.
Optionally, the plurality of behavior data includes at least one of: click times, browsing duration, sharing times, transaction quantity of the object to be delivered and transaction consumption resources of the object to be delivered.
Optionally, the computing module is further configured to:
determining a propagation capacity index of each participating user for the object to be launched according to the sharing propagation relation of each participating user indicated by the user propagation network;
and weighting according to the activity index and the propagation capacity index, and calculating the influence index of each participating user.
Optionally, the computing module is further specifically configured to:
and calculating the propagation capacity index of each participating user by adopting a webpage ranking algorithm according to the sharing propagation relation of each participating user indicated by the user propagation network.
Optionally, the building module is specifically configured to:
determining a degree index of each user node in the user propagation network according to the sharing propagation relationship of each participating user indicated by the user propagation network, wherein the degree index is used for indicating the connection capacity of each user node with other user connection nodes in the user propagation network;
determining super user nodes with the number of the propagation user nodes being larger than or equal to a preset threshold value according to the degree index;
deleting the connection points with the preset times of transmission of the super user node as empty and the free nodes with the number of the transmission nodes lower than the number of the preset connection points from the user transmission network to obtain an updated user transmission network;
correspondingly, the calculating the propagation capacity index of each participating user by using a web page ranking algorithm according to the sharing propagation relationship of each participating user indicated by the user propagation network includes:
and calculating the propagation capacity index of each participating user by adopting a webpage ranking algorithm according to the updated sharing propagation relation of each participating user indicated by the user propagation network.
In a third aspect, an embodiment of the present application further provides an influence index calculation device, including: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating via the bus when the impact metric calculation device is run, the processor executing the machine-readable instructions to perform the steps of the impact metric calculation method as provided by the first aspect.
In a fourth aspect, the present application further provides a computer-readable storage medium, where the storage medium stores a computer program, and the computer program is executed by a processor to perform the steps of the influence index calculation method according to the first aspect.
The beneficial effect of this application is:
the method, the device, the equipment and the storage medium for calculating the influence indexes provided by the application comprise the following steps: acquiring participation behavior information of a plurality of participant users in a private domain of an object to be launched aiming at the object to be launched; calculating the activity index of each participating user according to the participation behavior information of each participating user; constructing a user propagation network of the object to be launched according to the sharing propagation relationship of a plurality of participating users aiming at the object to be launched; the user propagation network is used for indicating the sharing propagation relationship of a plurality of participating users aiming at the information of the object to be launched; and calculating the influence index of each participating user for the object to be delivered according to the activity index and the propagation network. According to the scheme, the activity index of each participating user is calculated according to the participation behavior information of each participating user, the user propagation network of the object to be launched is constructed according to the sharing propagation relation of a plurality of participating users for the object to be launched, finally, the influence index of each participating user for the object to be launched is calculated by combining the activity index and the propagation network obtained through calculation, the calculation accuracy of the influence index is improved, the KOC in social electronic commerce is accurately determined, the launching popularization operation corresponding to the object to be launched by the KOC is conveniently executed, the accuracy and the intelligence of launching the object to be launched are improved, and the maximum propagation coverage is obtained.
Additionally, the plurality of behavioral data for each participating user may include at least one of: the method has the advantages that the click times, the browsing duration, the sharing times, the transaction quantity of the objects to be released and the transaction consumption resources of the objects to be released can be calculated from multiple angles, so that the activity index of each participating user can be calculated, and the accuracy and the comprehensiveness of the activity are effectively improved.
Secondly, determining the propagation capacity index of each participating user aiming at the object to be launched according to the sharing propagation relation of each participating user indicated by the user propagation network, weighting according to the activity index and the propagation capacity index, and calculating the influence index of each participating user, so that the influence index of the participating user depends on the activity index and the propagation capacity index of the user, and the accuracy of obtaining the influence index is improved.
Finally, determining the degree index of each user node in the user transmission network according to the sharing transmission relationship of each participating user indicated by the user transmission network, determining the super user node with the number of the transmission user nodes being more than or equal to a preset threshold value according to the degree index, and deleting the connection points which are propagated to be empty by the super user node for the preset times from the user propagation network, and free nodes with the number of the propagation nodes lower than the number of the preset nodes to obtain an updated user propagation network, and finally, according to the sharing propagation relation of each participated user indicated by the updated user propagation network, the propagation capacity index of each participated user is calculated by adopting a webpage ranking algorithm, so that the influence of the propagation capacity of other user nodes on the super user node with small propagation capacity is effectively avoided, and the practicability and the accuracy of calculating the influence index are improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic flowchart of a method for calculating an influence index according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of a user propagation network of an object to be delivered according to an embodiment of the present application;
fig. 3 is a schematic flowchart of another method for calculating an influence index according to an embodiment of the present disclosure;
fig. 4 is a schematic flowchart of another method for calculating an influence index according to an embodiment of the present disclosure;
fig. 5 is a schematic flowchart of another method for calculating an influence index according to an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of an influence index calculation apparatus according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an influence index calculation device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention.
The technical solution of the present invention is explained below by means of possible implementations.
Fig. 1 is a schematic flowchart of a method for calculating an influence index according to an embodiment of the present disclosure; the execution subject of the propagation capability index calculation method provided by the application can be a computer or any other electronic equipment with a processing function. As shown in fig. 1, the method may include:
s101, acquiring participation behavior information of a plurality of participation users in the private domain of the object to be launched aiming at the object to be launched.
The to-be-released object private domain may be, for example, a commodity private domain of a preset brand, or a private domain of other to-be-released object types, and the like. The participating users refer to users who have participated in the online promotion activity corresponding to the object to be delivered, such as users who have clicked on the activity page corresponding to the object to be delivered and browsed the activity page.
Generally, if a user participates in the activities of a certain type of objects to be launched, behavior information of the user is generated according to the participation behavior of the user and stored in a corresponding database. Therefore, the participation behavior information of the participating users can be obtained by querying the database to obtain the participation behavior information of the participating users in the private domain of the object to be delivered with respect to the object to be delivered, where the participation behavior information may include behavior information based on an activity page corresponding to the object to be delivered, and may include, for example, at least one of the following behavior information: the number of times of clicking the corresponding active page of the object to be launched, the average browsing time, the number of sharing times and the like.
And S102, calculating the activity index of each participating user according to the participation behavior information of each participating user.
In some embodiments, after obtaining the participation behavior information of a plurality of participating users in the private domain of the object to be delivered for the object to be delivered, the activity index of each participating user may be calculated and determined according to the participation behavior information of each participating user.
For example, the activity index of each user can be calculated and determined according to the comparison between the participation behavior information of each participating user and the preset behavior information of the corresponding type. For example, the activity indicators may be classified as super-active, moderate-active, and general-active, wherein the super-active, moderate-active, and general-active indicators are, within a preset time period: number of clicks on the object to be delivered 10, 5 and 2. For example, the user a may be determined to be super-active by clicking the number of times 15 that the user a clicks the object to be delivered within a preset time period.
The activity index of each participating user can be calculated and determined according to the actual service requirement without detailed description, and the activity index of each participating user can be calculated and determined according to the actual service requirement without specific limitation, and is not limited to the two methods for obtaining the activity index of each participating user.
S103, establishing a user propagation network of the object to be launched according to the sharing propagation relation of the plurality of participating users to the object to be launched.
The user propagation network is used for indicating the sharing propagation relationship of a plurality of participating users aiming at the information of the object to be launched. The sharing propagation relationship of each participating user for the object to be delivered may be, for example, an operation behavior of each participating user on a respective social platform for an activity page corresponding to the object to be delivered, which includes but is not limited to: sharing operation, praise operation, or text comment operation.
Specifically, after acquiring participation behavior information of a plurality of participating users in a private domain of the object to be launched, the participation behavior information of the plurality of participating users may be analyzed to determine a sharing propagation relationship of the plurality of participating users with respect to the object to be launched. For example, after participating in an object to be delivered, the user a shares the object to be delivered to the user B, the user C, the user D, and the like, wherein the user B shares the object to be delivered to the user F, the user G, the user H, and the like, and then the user propagation network of the object to be delivered can be further constructed through the sharing propagation relationship among the plurality of users.
Optionally, for example, fig. 2 is a schematic structural diagram of a user propagation network of an object to be delivered according to an embodiment of the present application; as shown in fig. 2, in the propagation network, each user is a node in the propagation network, edges between users represent activity sharing relationships, and the propagation relationship behavior between users may include: and based on the praise behavior and the share behavior of the activity page corresponding to the object to be launched, and the weight taking the behavior times among the users as the side, the construction of the user propagation network of the object to be launched can be completed. For example, a user a shares objects to be delivered to a user e, a user d and a user d respectively, and the sharing times are as follows: 1. 3, 2, which will not be described herein.
And S104, calculating the influence index of each participating user for the object to be launched according to the activity index and the propagation network.
In some embodiments, after the activity index of each participating user is obtained through calculation and the user propagation network of the object to be delivered is constructed, the activity index of each participating user and the propagation network can be combined, so that the accuracy of calculating the influence index of each participating user on the object to be delivered is improved.
In summary, the present application provides a method for calculating an influence index, including: acquiring participation behavior information of a plurality of participant users in a private domain of an object to be launched aiming at the object to be launched; calculating the activity index of each participating user according to the participation behavior information of each participating user; constructing a user propagation network of the object to be launched according to the sharing propagation relationship of a plurality of participating users aiming at the object to be launched; the user propagation network is used for indicating the sharing propagation relationship of a plurality of users aiming at the information of the object to be launched; and calculating the influence index of each participating user for the object to be delivered according to the activity index and the propagation network. According to the scheme, the activity index of each participating user is calculated according to the participation behavior information of each participating user, the user propagation network of the object to be launched is constructed according to the sharing propagation relation of a plurality of participating users for the object to be launched, and finally the influence index of each participating user for the object to be launched is calculated by combining the activity index obtained through calculation and the propagation network, so that the accuracy and the intelligence of calculating the influence index are improved, and the maximum propagation coverage is obtained.
Optionally, the participation behavior information includes: various behavior data of each participating user in a preset time period; calculating the activity index of each participating user according to the participation behavior information of each participating user, wherein the activity index comprises the following steps:
and calculating the activity index of each participating user according to each behavior data of each participating user in a preset time period and the sum of each behavior data of a plurality of participating users in the preset time period.
In some embodiments, for example, the engagement behavior information may include: the number of times of clicking the object to be delivered, the average browsing time, the number of sharing times and the like.
For example, all participating users are 20 people, and the participating behavior information of the participating user a in a preset time period in one day is respectively: the number of times of clicking the object to be released is 10, the average browsing time is 4 hours, and the number of sharing times is 20, all the participating users are 20, and the sum of each behavior data of the 20 users in one day in the preset time period is respectively: the number of times of clicking on the object to be delivered is 100, the average browsing time is 40 hours, and the number of sharing times is 100, and the activity index of each participating user can be further determined by calculating the ratio of each behavior data of each participating user to the sum of each behavior data of all participating users in a preset time period, so that the activity index activity (a) of the user a (10/100+ 4/40+ 20/100) can be determined to be 0.4.
Fig. 3 is a schematic flowchart of another method for calculating an influence index according to an embodiment of the present disclosure; optionally, as shown in fig. 3, calculating the activity indicator of each participating user according to each behavior data of each participating user in a preset time period and a sum of each behavior data of a plurality of participating users in the preset time period includes:
s301, calculating a behavior index of each participating user according to each behavior data of each participating user in a preset time period and the sum of each behavior data of a plurality of participating users in the preset time period.
Alternatively, on the basis of the above embodiment, after acquiring each behavior data of each participating user within a preset time period and a sum of each behavior data of a plurality of participating users, one behavior index of each participating user may be calculated respectively. For example, an activity index for determining the number of times that the participating user a clicks the object to be delivered may be calculated, the activity index for the number of times that a certain user i clicks the object to be delivered may be denoted by cn (i), and cn (a) ═ 10/100 ═ 0.1, that is, the activity index for the number of times that the participating user a clicks the object to be delivered may be determined to be 0.1, or other behavior indexes of the participating user a may be obtained by continuous calculation, which is not listed here.
S302, weighting is carried out according to the plurality of behavior indexes of each participating user, and the activity index of each participating user is calculated.
For example, on the basis of the above embodiment, different weights may be set for each behavior data to perform weighting processing on each behavior data, so as to obtain an activity index of each participating user. For example, on the basis of the above embodiment, the weight set for each kind of behavior data included in the above participation behavior information is: 1. 2 and 3, the activity indexes of the multiple behaviors of the participating user i can be marked as activity (i), and then activity (a) ═ (1/6) × (10/100+2 × (4/40) +3 × (20/100)) ═ 0.15 can be determined, wherein the weight set by each behavior data can be adjusted according to actual requirements, so that the obtained activity index of each participating user is closer to reality, and the accuracy of activity evaluation is effectively improved.
Optionally, the activity index of each participating user on a current day may also be calculated based on time sequence, for example, the activity index on the current day 1, it can be understood that the activity index of each participating user on the current day 1 is influenced by the behavior of the participating user on the first day together with the behavior of the participating user in the previous period, and there is a time decay, so according to newton's law of cooling, a time controlled decay function is provided as follows:
N(t)＝Noe-α(t+l)
wherein N (t) is an activity index of each participating user on the t-th day before the current first day, N0Is the liveness index of each participating user on the current first day, N (t) and N0The control activity index is controlled to start to decay from which day. Suppose that, the decay starts from the current first day, i.e. the activity index of the first day is 1, and the decay reaches 0.1 after 10 days, i.e.:
Noe-αl＝1
Noe-α(10+l)＝0.1
α, l are obtained as follows:
Figure BDA0002601723310000111
Figure BDA0002601723310000112
then the activity level indicator for each participating user on the current first day may be calculated based on the time sequence t days before the first day as:
Figure BDA0002601723310000113
optionally, the plurality of behavioral data includes at least one of: the method has the advantages that the click times, the browsing duration, the sharing times, the transaction quantity of the objects to be released and the transaction consumption resources of the objects to be released can be calculated from multiple angles, so that the activity index of each participating user can be calculated, and the accuracy and the comprehensiveness of the activity are effectively improved.
For example, the plurality of behavior activity indicators of a participating user i may be activity (i) ═ 1/13 × (cn (i)/cn _ all +2 × rt (i)/rt _ all +3 sn (i)/sn _ all +4 bn (i)/bn _ all +4 bm (i)/bm _ all), where cn (i), rt (i), sn (i), bn (i), and bm (i) are the number of clicks, the browsing duration, the sharing duration, the number of transactions of objects to be dropped, the transaction consumption resources of objects to be dropped, (cn _ all), (rt _ all), (sn _ all), (bn _ all), and (bm _ all) of all users in a period of time, respectively, the total number of times of clicks, the total number of clicks, and the total number of transactions of objects to be dropped, and the sum of transaction consumption resources of the objects to be delivered, and the like.
Fig. 4 is a schematic flowchart of another method for calculating an influence index according to an embodiment of the present disclosure; optionally, as shown in fig. 4, calculating an influence index of each participating user on the object to be delivered according to the activity index and the propagation network includes:
s401, determining the propagation capacity index of each participating user for the object to be launched according to the sharing propagation relation of each participating user indicated by the user propagation network.
It should be noted that, for determining the propagation capability index of each participating user for the object to be delivered, it is assumed that no "wool party" exists in the obtained data, and the data are all users that propagate naturally, so that the propagation capability index of each participating user for the object to be delivered can be further calculated and determined according to the sharing propagation relationship of each participating user indicated by the user propagation network, and the accuracy of obtaining the propagation capability index is improved.
S402, weighting is carried out according to the activity index and the propagation capacity index, and the influence index of each participating user is calculated.
Optionally, after obtaining the liveness index and the propagation capability index, the liveness index and the propagation capability index may be weighted based on the weight of the liveness index and the weight of the propagation capability index to obtain the influence index of each participating user. Wherein the sum of the weight of the activity index and the weight of the propagation capacity index is 1.
For example, if a user of the multiple participating users may be denoted by i, the activity index may be denoted as activity (i), the propagation capability index may also be denoted as pagerank (i), and the influence index may be denoted as influnce (i), and then influnce (i) ═ activity (i) + b × pagerank (i) may be obtained, where a and b are weight parameters, and may be adjusted according to an actual service network, and it may be understood that a + b ═ 1.
In this embodiment, the influence index of each participating user is calculated by weighting according to the activity index and the propagation capacity index, so that the influence index of the participating user depends on the activity index and the propagation capacity index of the user, the accuracy of obtaining the influence index is improved, the calculated influence index of each participating user can be introduced into a recommendation system to process targeted promotion activities, and the maximum propagation coverage is obtained with the minimum initial cost.
Optionally, determining, according to the sharing propagation relationship of each participating user indicated by the user propagation network, a propagation capability index of each participating user for the object to be delivered, including:
and calculating the propagation capacity index of each participating user by adopting a webpage ranking algorithm according to the sharing propagation relation of each participating user indicated by the user propagation network.
In other embodiments, after determining the sharing propagation relationship of each participating user, a propagation capability index of each participating user may be calculated using pagarank (web page ranking algorithm). For example, pr (u) represents the propagation capability index of user u, and pr (u) may be the sum of the weighted influence of all participating users, and the formula is:
Figure BDA0002601723310000131
the influence that the participating user v can bring to the participating user u is the influence of the participating user v on the participating user u by PR (v) multiplied by the weight w (v) between u and v, and divided by the sharing quantity L (v) of the participating user v, all the participating users v which can bring to the participating user u in sharing and propagation are counted, and the obtained sum is the influence of the user node u.
It should be noted that pr (v) is assumed to be known in advance, and w (v) is the number of times users u and v share.
Fig. 5 is a schematic flowchart of another method for calculating an influence index according to an embodiment of the present disclosure; optionally, as shown in fig. 5, before calculating the propagation capability index of each participating user by using a web page ranking algorithm according to the sharing propagation relationship of each participating user indicated by the user propagation network, the method further includes:
s501, determining the degree index of each user node in the user propagation network according to the sharing propagation relation of each participating user indicated by the user propagation network.
The degree index is used for indicating the connection capacity of each user node with other user connection nodes in the user propagation network.
It can be understood that the degree index of the graph can display the connection capability of each user node. For example, in a certain user propagation network, it may be determined that 50 users are connected through the user node a according to the sharing propagation relationship of the user node a, and the degree index of the user node a is 50.
S502, according to the degree index, determining the super user nodes with the number of the propagation user nodes being larger than or equal to a preset threshold value.
Specifically, after determining the degree index of each user node in the user propagation network, the degree index of each user node may be compared with a preset threshold. For example, a super user node may be defined as a user node whose degree index of the user node is greater than or equal to a preset threshold 100, for example, if the degree index of the user node b is 150, the user node b is greater than the preset threshold 100, that is, 150>100, the user node b may be called a super user node, and it may be understood that 150 participating users are connected through the user node b, that is, the user node b shares and propagates 150 users.
S503, deleting the connection points with the preset number of times of super user node transmission as empty and the free nodes with the number of the transmission nodes lower than the preset number of the connection points from the user transmission network to obtain the updated user transmission network.
Generally, degree is taken as a statistical index, and only whether the next node to which the current node is connected has the propagation capability cannot be evaluated; however, pagerank is a better way to find nodes with a propagation capability. Therefore, the degree index of each user node in the user propagation network can be calculated by adopting the degree index of the graph.
However, in an actual propagation network, there is a case where one user node has multiple connection points, but the propagation capability of the multiple connection points of the user node is poor, in this case, after one user node a with propagation capability is associated with the multiple connection points, the propagation capability of the user node a calculated by the pagerank algorithm is increased, and in an actual service, the calculation result is not in accordance with the conventional knowledge, because once the activity of the nodes is low, the probability of propagation network collapse is increased, and therefore, the pagerank algorithm needs to be optimized.
Optionally, in some embodiments, after determining the super user node, the connection point where the super user node propagates to be empty for the preset number of times and the free node where the number of propagation nodes is lower than the preset number of connection points may be selected to be deleted, so as to obtain the updated user propagation network.
Specifically, for example, if the preset number is set to 2, the connection point that the super node propagates to be empty in two degrees may be deleted. For example, on the basis of the above embodiment, after determining that the user node b is a super user, according to the sharing propagation relationship between 150 user nodes connected to the user node b, a user node without a connection point in the 150 user nodes is determined, for example, if it is determined through analysis of the propagation network that 25 user nodes in the 150 user nodes do not have a connection point, the 25 user nodes are deleted from the user propagation network to obtain an updated user propagation network, so that the stability of the user propagation network is improved.
And, in order to improve the actual effectiveness of the user propagation network, free nodes with the number of propagation nodes lower than the number of preset connection points can be further used, for example, if the number of the preset connection points is 100, the user nodes with the number of the propagation nodes lower than 100 of the user nodes can be deleted, and the updated user propagation network is obtained.
Optionally, the updated user propagation network described above can also be extended to more complex scenarios including, for example, temporal information, user node base attribute information or information about the activity hierarchy.
Correspondingly, calculating the propagation capacity index of each participating user by adopting a webpage ranking algorithm according to the sharing propagation relationship of each participating user indicated by the user propagation network, including the following step S404:
and S504, calculating the propagation capacity index of each participating user by adopting a webpage ranking algorithm according to the sharing propagation relation of each participating user indicated by the updated user propagation network.
In some embodiments, weighted pagerank (weighted web ranking algorithm) may be used to calculate the propagation capacity of each user in the modified propagation network, which improves the practicability and accuracy of calculating the propagation capacity index.
The following describes apparatuses, devices, and storage media for performing the calculation of the propagation performance index provided in the present application, and specific implementation procedures and technical effects thereof are referred to above, and will not be described again below.
Fig. 6 is a schematic structural diagram of an influence index calculation apparatus according to an embodiment of the present application; as shown in fig. 6, the propagation capability index calculation means 600 includes: an acquisition module 601, a calculation module 602, and a construction module 603.
An obtaining module 601, configured to obtain participation behavior information of a plurality of participating users in a private domain of an object to be launched, for the object to be launched;
a calculating module 602, configured to calculate an activity index of each participating user according to the participation behavior information of each participating user;
the building module 603 is configured to build a user propagation network of the object to be launched according to the sharing propagation relationship of the plurality of participating users for the object to be launched; the user propagation network is used for indicating the sharing propagation relationship of a plurality of participating users aiming at the information of the object to be launched;
the calculating module 602 is further configured to calculate an influence index of each participating user on the object to be delivered according to the activity index and the propagation network.
Optionally, the participation behavior information includes: various behavior data of each participating user in a preset time period; the calculating module 602 is specifically configured to:
and calculating the activity index of each participating user according to each behavior data of each participating user in a preset time period and the sum of each behavior data of a plurality of participating users in the preset time period.
Optionally, the calculating module 602 is further specifically configured to:
calculating a behavior index of each participating user according to each behavior data of each participating user in a preset time period and the sum of each behavior data of a plurality of participating users in the preset time period;
and weighting according to the plurality of behavior indexes of each participating user, and calculating the activity index of each participating user.
Optionally, the plurality of behavioral data includes at least one of: click times, browsing duration, sharing times, transaction quantity of the object to be released and transaction consumption resources of the object to be released.
Optionally, the calculating module 602 is further configured to:
determining a propagation capacity index of each participating user for an object to be launched according to the sharing propagation relation of each participating user indicated by the user propagation network;
and weighting according to the activity index and the propagation capacity index, and calculating the influence index of each participating user.
Optionally, the calculating module 602 is further specifically configured to:
and calculating the propagation capacity index of each participating user by adopting a webpage ranking algorithm according to the sharing propagation relation of each participating user indicated by the user propagation network.
Optionally, the building module 603 is specifically configured to:
determining a degree index of each user node in the user propagation network according to the sharing propagation relationship of each participating user indicated by the user propagation network, wherein the degree index is used for indicating the connection capacity of each user node with other user connection nodes in the user propagation network;
determining super user nodes with the number of the propagation user nodes being larger than or equal to a preset threshold value according to the degree index;
deleting the connection points with the preset times of super user node transmission as empty and the free nodes with the number of the transmission nodes lower than the preset number of the connection points from the user transmission network to obtain an updated user transmission network;
correspondingly, the calculating module 602 is further specifically configured to:
and calculating the propagation capacity index of each participating user by adopting a webpage ranking algorithm according to the sharing propagation relation of each participating user indicated by the updated user propagation network.
The above-mentioned apparatus is used for executing the method provided by the foregoing embodiment, and the implementation principle and technical effect are similar, which are not described herein again.
These above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), among others. For another example, when one of the above modules is implemented in the form of a processing element scheduler code, the processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).
Fig. 7 is a schematic structural diagram of an influence index calculation device according to an embodiment of the present application; as shown in fig. 7, the influence index calculation device may be integrated into a terminal device or a chip of the terminal device, and the terminal device may be a calculation device having a data processing function, or may be a server or a chip of the server.
The apparatus comprises: a processor 701, a memory 702.
The memory 702 is used for storing programs, and the processor 701 calls the programs stored in the memory 702 to execute the above method embodiments. The specific implementation and technical effects are similar, and are not described herein again.
Optionally, the invention also provides a program product, for example a computer-readable storage medium, comprising a program which, when being executed by a processor, is adapted to carry out the above-mentioned method embodiments.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

Claims (10)

1. An influence index calculation method, characterized by comprising:
acquiring participation behavior information of a plurality of participant users in a private domain of an object to be launched aiming at the object to be launched;
calculating the activity index of each participating user according to the participation behavior information of each participating user;
constructing a user propagation network of the object to be launched according to the sharing propagation relationship of the plurality of participating users aiming at the object to be launched; the user propagation network is used for indicating a sharing propagation relationship of the plurality of participating users aiming at the information of the object to be delivered;
and calculating the influence index of each participating user for the object to be delivered according to the activity index and the propagation network.
2. The method of claim 1, wherein the engagement behavior information comprises: various behavior data of each participating user in a preset time period; the calculating the activity index of each participating user according to the participation behavior information of each participating user comprises the following steps:
calculating the activity index of each participating user according to each behavior data of each participating user in the preset time period and the sum of each behavior data of the plurality of participating users in the preset time period.
3. The method according to claim 2, wherein the calculating the activity indicator of each participating user according to each behavior data of each participating user in the preset time period and the sum of each behavior data of the plurality of participating users in the preset time period comprises:
calculating a behavior index of each participating user according to each behavior data of each participating user in the preset time period and the sum of each behavior data of the plurality of participating users in the preset time period;
and weighting according to the plurality of behavior indexes of each participating user, and calculating the activity index of each participating user.
4. The method of claim 2, wherein the plurality of behavior data comprises at least one of: click times, browsing duration, sharing times, transaction quantity of the object to be delivered and transaction consumption resources of the object to be delivered.
5. The method according to claim 1, wherein said calculating an influence metric of each of said participating users with respect to said object to be delivered according to said liveness metric and said propagation network comprises:
determining a propagation capacity index of each participating user for the object to be launched according to the sharing propagation relation of each participating user indicated by the user propagation network;
and weighting according to the activity index and the propagation capacity index, and calculating the influence index of each participating user.
6. The method according to claim 5, wherein the determining, according to the sharing propagation relationship of the participating users indicated by the user propagation network, a propagation capability index of each participating user for the object to be delivered includes:
and calculating the propagation capacity index of each participating user by adopting a webpage ranking algorithm according to the sharing propagation relation of each participating user indicated by the user propagation network.
7. The method according to claim 6, wherein before calculating the propagation capability indicator of each participating user by using a web page ranking algorithm according to the sharing propagation relationship of each participating user indicated by the user propagation network, the method further comprises:
determining a degree index of each user node in the user propagation network according to the sharing propagation relationship of each participating user indicated by the user propagation network, wherein the degree index is used for indicating the connection capacity of each user node with other user connection nodes in the user propagation network;
determining super user nodes with the number of the propagation user nodes being larger than or equal to a preset threshold value according to the degree index;
deleting the connection points with the preset times of transmission of the super user node as empty and the free nodes with the number of the transmission nodes lower than the number of the preset connection points from the user transmission network to obtain an updated user transmission network;
correspondingly, the calculating the propagation capacity index of each participating user by using a web page ranking algorithm according to the sharing propagation relationship of each participating user indicated by the user propagation network includes:
and calculating the propagation capacity index of each participating user by adopting a webpage ranking algorithm according to the updated sharing propagation relation of each participating user indicated by the user propagation network.
8. An influence index calculation apparatus, characterized in that the apparatus comprises: the system comprises an acquisition module, a calculation module and a construction module;
the acquisition module is used for acquiring participation behavior information of a plurality of participating users in a private domain of an object to be launched aiming at the object to be launched;
the computing module is used for computing the activity degree index of each participating user according to the participation behavior information of each participating user;
the building module is used for building a user propagation network of the object to be launched according to the sharing propagation relationship of the plurality of participating users for the object to be launched; the user propagation network is used for indicating a sharing propagation relationship of the plurality of participating users aiming at the information of the object to be delivered;
the calculation module is further configured to calculate an influence index of each participating user on the object to be delivered according to the activity index and the propagation network.
9. An influence index calculation device, comprising: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating via the bus when the impact metric calculation device is operating, the processor executing the machine-readable instructions to perform the steps of the impact metric calculation method according to any of claims 1-7.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the impact indicator calculation method according to any one of claims 1 to 7.
CN202010728591.XA 2020-07-24 2020-07-24 Influence index calculation method, device, equipment and storage medium Pending CN111815197A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010728591.XA CN111815197A (en) 2020-07-24 2020-07-24 Influence index calculation method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010728591.XA CN111815197A (en) 2020-07-24 2020-07-24 Influence index calculation method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN111815197A true CN111815197A (en) 2020-10-23

Family

ID=72861189

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010728591.XA Pending CN111815197A (en) 2020-07-24 2020-07-24 Influence index calculation method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN111815197A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102663101A (en) * 2012-04-13 2012-09-12 北京交通大学 Sina microblog-based user grade sequencing algorithm
CN104123352A (en) * 2014-07-10 2014-10-29 西安理工大学 Method for measuring influence of users on topic hierarchy for MicroBlog
CN105095267A (en) * 2014-05-09 2015-11-25 阿里巴巴集团控股有限公司 User involving project recommendation method and apparatus
CN105956925A (en) * 2016-04-23 2016-09-21 时趣互动（北京）科技有限公司 Method and device for discovering important users on the basis of spreading networks
CN106875205A (en) * 2016-07-11 2017-06-20 阿里巴巴集团控股有限公司 A kind of object selection method and device
CN109410078A (en) * 2018-09-12 2019-03-01 河南理工大学 A kind of information propagation prediction method for the mobile social networking shared suitable for object oriented file

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102663101A (en) * 2012-04-13 2012-09-12 北京交通大学 Sina microblog-based user grade sequencing algorithm
CN105095267A (en) * 2014-05-09 2015-11-25 阿里巴巴集团控股有限公司 User involving project recommendation method and apparatus
CN104123352A (en) * 2014-07-10 2014-10-29 西安理工大学 Method for measuring influence of users on topic hierarchy for MicroBlog
CN105956925A (en) * 2016-04-23 2016-09-21 时趣互动（北京）科技有限公司 Method and device for discovering important users on the basis of spreading networks
CN106875205A (en) * 2016-07-11 2017-06-20 阿里巴巴集团控股有限公司 A kind of object selection method and device
CN109410078A (en) * 2018-09-12 2019-03-01 河南理工大学 A kind of information propagation prediction method for the mobile social networking shared suitable for object oriented file

Similar Documents

Publication Publication Date Title
US10868888B1 (en) Method and apparatus for real-time personalization
JP6788667B2 (en) Advertising lift measurement
US10649818B2 (en) Multi-touch attribution model for valuing impressions and other online activities
US9455891B2 (en) Methods, apparatus, and articles of manufacture to determine a network efficacy
KR101923065B1 (en) User-initiated boosting of social networking objects
US8655949B2 (en) Correlated information recommendation
US9413557B2 (en) Pricing in social advertising
AU2017202596A1 (en) Querying features based on user actions in online systems
US11394810B2 (en) Method and system for segmentation as a service
US20140358694A1 (en) Social media pricing engine
US20110320284A1 (en) Market for Social Promotion of Digital Goods
US10621641B2 (en) Method and device for pushing information
US11188846B1 (en) Determining a sequential order of types of events based on user actions associated with a third party system
JP6810184B2 (en) Calculation device, calculation method and calculation program
CN111815197A (en) Influence index calculation method, device, equipment and storage medium
JP7010870B2 (en) Decision device, decision method and decision program
JP6007300B1 (en) Calculation device, calculation method, and calculation program
JP7253410B2 (en) Information processing device, information processing method and program
CN117972096B (en) Method and system for processing interaction message of social platform
US12003598B2 (en) Method and system for segmentation as a service
JP7287926B2 (en) Decision device, decision method and decision program
JP2012063803A (en) Advertisement distribution device and method
Al-Dulaimi Image content based topological analysis for friend recommendation on Twitter
CN110866192A (en) Promotion efficiency evaluation method, promotion mode determination method and device
CN113360756A (en) Resource recommendation method and device, electronic equipment and medium

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: 20201023

RJ01 Rejection of invention patent application after publication