CN108537358B

CN108537358B - Community data processing method and device, storage medium and electronic device

Info

Publication number: CN108537358B
Application number: CN201810160163.4A
Authority: CN
Inventors: 石杨; 王常伦; 陈征
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2018-02-26
Filing date: 2018-02-26
Publication date: 2021-04-09
Anticipated expiration: 2038-02-26
Also published as: CN108537358A

Abstract

The invention discloses a community data processing method and device, a storage medium and an electronic device. Wherein, the method comprises the following steps: determining the type of each first user in a first user set which has accessed the community, wherein the type of each first user is a target type under a target dimension; searching a second user matched with the type of the first user from a set of second users who never access the community; acquiring a first index of the first user in the target dimension, and acquiring a second index of the second user in the target dimension; and optimizing the data of the community according to the first index and the second index, wherein the community after optimization is used for improving the behavior index of the first user in the target dimension. The invention solves the technical problem that the community content can not be optimized according to the user behavior to precipitate the user.

Description

Community data processing method and device, storage medium and electronic device

Technical Field

The invention relates to the field of data processing, in particular to a community data processing method and device, a storage medium and an electronic device.

Background

The rapid development of the internet and the mobile internet in the last 10 years has the advantages that the penetration rate of netizens is continuously increased, the population dividend gradually disappears, and the internet is gradually changed into an inventory market from an incremental market. The education of users by internet products makes users more critical in selecting products and obtaining content information. Premium products and premium content change from being in short supply to being in excess. Large flows of traditional portal-type media are being broken down and split up step by step.

For the above two reasons, the difficulty of internet products in acquiring users and depositing users is increasing. With the rise of content marketing, the operation strategy of internet products under new situation attracts and precipitates users more with high-quality content to aggregate high-quality traffic. For example, combining products with a community platform, precipitating more users to use the products through premium community content.

However, there is no method for measuring the quality of the community, so that the community content cannot be optimized to precipitate more users.

In view of the above problems, no effective solution has been proposed.

Disclosure of Invention

The embodiment of the invention provides a community data processing method, a community data processing device, a storage medium and an electronic device, and at least solves the technical problem that community contents cannot be optimized according to user behaviors to precipitate users.

According to an aspect of the embodiments of the present invention, there is provided a method for processing community data, including: determining the type of each first user in a first user set which has accessed a community, wherein the type of each first user is a target type in a target dimension; searching a second user matched with the type of the first user from a set of second users who never visit the community; obtaining a first index of the first user in the target dimension and a second index of the second user in the target dimension, wherein the first index is used for indicating behavior change of the first user in a first time period before the first user accesses the community and a second time period after the first user accesses the community, and the second index is used for indicating behavior change of the second user in the first time period and the second time period; and optimizing the data of the community according to the first index and the second index, wherein the optimized community is used for improving the behavior index of the first user in the target dimension.

According to another aspect of the embodiments of the present invention, there is also provided a device for processing community data, including: the determining unit is used for determining the type of each first user in a first user set which has accessed the community, wherein the type of each first user is a target type under a target dimension; the searching unit is used for searching a second user matched with the type of the first user from a set of second users who never visit the community; a first obtaining unit, configured to obtain a first index of the first user in the target dimension, where the first index is used to indicate a behavior change of the first user in a first time period before accessing the community and a second time period after accessing the community; a second obtaining unit, configured to obtain a second index of the second user in the target dimension, where the second index is used to indicate a behavior change of the second user in the first time period and the second time period; and the processing unit is used for optimizing the data of the community according to the first index and the second index, wherein the community after optimization is used for improving the behavior index of the first user in the target dimension.

Optionally, the processing unit comprises: a fourth determining module, configured to determine, by using a ratio of the first index and the second index, a degree of influence of the community on behavior of the first user in the target dimension; and the updating module is used for updating the content displayed by the community according to the behavior influence degree.

According to another aspect of the embodiments of the present invention, there is also provided a storage medium having a computer program stored therein, wherein the computer program is configured to perform the above method when executed.

According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including a memory and a processor, wherein the memory stores therein a computer program, and the processor is configured to execute the above method through the computer program.

The influence of the community on the user behavior is determined through the first index and the second index which measure the change of the user behavior under the target dimensionality, and accordingly, the data of the community is optimized, so that the technical problem that the community content cannot be optimized according to the user behavior to precipitate the user in the prior art can be solved, and the technical effect of optimizing the community content according to the user behavior is achieved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:

FIG. 1 is a schematic diagram of a hardware architecture according to an embodiment of the present invention;

FIG. 2 is a flowchart of a method of processing community data according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of various types according to an embodiment of the invention;

FIG. 4 is a flow chart for obtaining a first index and a second index according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of obtaining a first index and a second index according to an embodiment of the invention;

FIG. 6 is a histogram of TGI index according to an embodiment of the present invention;

FIG. 7 is a schematic diagram of a community data processing apparatus according to an embodiment of the present invention;

fig. 8 is a schematic diagram of a terminal according to an embodiment of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, 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 only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

The noun explains:

TGI: target Group Index, Target population Index

DAU, Daily Active User, Active Daily population

ARPU: average Revenue Per User Per Average User

According to an aspect of an embodiment of the present invention, a method for processing community data is provided. In this embodiment, the above-mentioned community data processing method may be applied to a hardware environment formed by the terminal 102 and the server 104 shown in fig. 1. As shown in fig. 1, a terminal 102 is connected to a server 104 via a network including, but not limited to: the terminal 102 may be a mobile phone terminal, a PC terminal, a notebook terminal, or a tablet terminal.

The community data processing method of the present embodiment may be executed on the terminal 102, or may be executed in the server 104. The terminal 102 may provide a community interface 106, collect user data, report the user data to the server 104 for storage, and process the data by the server 104. Alternatively, the collected data of the user is processed by the terminal 102.

The data processing of the embodiment can analyze the communities in two aspects, so as to optimize the communities according to the analysis result. These two aspects include: and analyzing the community aggregation user quality and analyzing the promotion of the community on the user quality. The analysis of community aggregated user quality is used to illustrate which features users logged into the community have, at what level in a dimension, among all users the users with those features are. Topic analysis of user quality by a community is used to illustrate that data changes in a dimension before and after a user accesses the community. According to at least one of the analysis of the community aggregated user quality and the promotion analysis of the community on the user quality, the pushing effect of the community on the product can be measured, and then the community is optimized. The optimization includes selection of the content of the community, improvement and upgrading of the content of the community, and the like. For example, for a game product, the contents of strategies, plays, teaching, events and the like related to the user can be pushed according to the first index and the second index, so that the pushed contents are more in line with the requirements of the user. For video playing products, top comments and discussions of related communities can be screened out according to the first index and the second index, and a display mode, a recommendation mode and the like of video resources can be set. For the map product, the map updating frequency, the introduction of the surrounding area, the navigation prompting lamp and the like of the related community can be adjusted according to the first index and the second index. The optimized content includes not limited to the sections, not limited to the content of each section, the display form of the community and the like. The optimization process can be automatically adjusted according to the corresponding relation between the first index and the second index and the corresponding data.

Fig. 2 is a flowchart of a community data processing method according to an embodiment of the present invention. As shown in fig. 2, the method for processing community data includes:

s202, determining the type of each first user in a first user set which has accessed the community, wherein the type of each first user is a target type under a target dimension;

the first user is a user who has accessed the community, and the first user set comprises a plurality of first users. The type of the first user may be obtained by clustering. Target dimensions can be determined through user clustering, and the target dimensions are divided into multiple types. Each first user corresponds to one of the pair types. Wherein the target dimension may comprise one or more dimensions.

Optionally, determining the type of each first user in the set of first users who have accessed the community comprises: acquiring multiple types under a target dimension; determining the value range of the target parameter in the target dimension according to various types; classifying each first user in the first user set according to the value range and the target parameter value of each first user; the type of the first user is determined to be a target type of the multiple types.

Each target dimension may include multiple types, and the type may be determined in the target dimension based on target parameters in the target dimension. For example, under the dimension of user activity, 3 types including high activity, medium activity and low activity are included. For example, 2 types of the high-level rating and the normal rating may be included in the dimension of the user rating. Combinations of liveness and user ratings may also be provided as a type, for example, high liveness and high rating, low liveness and high rating, medium liveness and normal rating. The high activity, the medium activity and the low activity can be used as a target parameter in the activity dimension, and the common grade and the high grade can also be used as a target parameter in the grade dimension. Both the activity and the level can be divided by adopting values in a certain range. The type of the first user may be determined using the partition criteria. For example, when the user's score is greater than or equal to the value a, the user is determined to be a high level; and when the user integral is less than the value A, determining that the user is in the normal grade.

The target dimension may include a first dimension and a second dimension, and acquiring the plurality of types under the target dimension includes: and clustering the first user set into multiple types on the first dimension and the second dimension by adopting a user clustering mode, wherein each type comprises a parameter value range of the first dimension and a parameter value range of the second dimension.

Each dimension comprises a plurality of types, and the types on the first dimension and the second dimension are arranged and combined to obtain the plurality of types. For example, the first dimension is the user's liveness and the second dimension is the user's payment situation. Wherein, the liveness comprises 3 types, namely high liveness, medium liveness and low liveness; the payment case includes type 3, high payment, medium payment and low payment, respectively. The two dimensions of the activity and the payment situation result in 9 types shown in fig. 3, namely low payment high activity, medium payment high activity, high payment high activity, low payment medium activity, medium payment medium activity, low payment low activity, medium payment low activity and high payment low activity. When the activity is divided into high, medium and low levels and the payment is divided into high, medium and low levels, the division can be carried out according to the value range of each type. For example, when the activity value is [0, m ], the activity type is determined to be a low activity type; when the activity value is (m, n), determining the activity type as the medium activity type; and when the activity value is larger than n, determining the activity type as a high activity type. Similarly, when the payment value is [0, g ], determining the payment type as a low payment type; when the payment value is in (g, h), determining the payment type as the medium payment type; and when the payment value is larger than h, determining the payment type as a high payment type.

After the multiple types are clustered by utilizing a user clustering mode, classifying each first user in the first user set which has access to the community. And determining the type of each first user according to the activity value and the payment value of each first user. And when the liveness value and the payment value of the first user are required to meet the value range of any one of the types in the 9, determining the type of the first user.

For example, if the activity of the first user is in the value range of [0, m ] and the payment is in the value range of (g, h), the type of the first user is determined to be the type of payment in low activity. Each first user in the set of first users is classified in this manner, determining the type of each first user.

S204, searching a second user matched with the type of the first user from a set of second users who never access the community;

optionally, the similar users are diffused among the second users for each type of first users in a look-like manner, and users of the same type and who have not accessed the micro-community are found. Searching a second user with the difference value between the target parameter value of the second user and the target parameter value of the first user within a preset range from a set of second users who never access the community; and configuring the type of the searched second user as the type of the corresponding first user.

The first user and the second user with the difference value within the preset range are similar. Having determined the type of the first user in the above step, the type of the second user similar to the first user is the same as the type of the first user.

Step S206, acquiring a first index of the first user in the target dimension, wherein the first index is used for indicating behavior change of the first user in a first time period before the first user accesses the community and a second time period after the first user accesses the community;

step S208, obtaining a second index of the second user in the target dimension, where the second index is used to indicate behavior changes of the second user in the first time period and the second time period;

optionally, the obtaining a first index of the first user in the target dimension and a second index of the second user in the target dimension includes: taking the ratio of a first parameter of the first user in the first time period after the first user accesses the community to a second parameter of the first user in the second time period before the first user accesses the community as a first index; and taking the ratio of the first parameter of the second user in the first time period to the second parameter of the second user in the second time period as a second index.

The first parameter and the second parameter are parameters in a target dimension, such as weekly liveness in a liveness dimension, or a weekly payment average in a payment dimension. The first parameter and the second parameter are both parameters in the same dimension, and the difference is that the first parameter is a parameter after the first user accesses the community, and the second parameter is a parameter before the first user accesses the community. The behavior influence of the community on the first user can be obtained by using the parameters before and after the community is accessed. For example, the first parameter is a payment value after the community is accessed, the second parameter is a payment value before the community is accessed, and the change of the payment value of the first user before and after the community is accessed can be determined according to the second parameter and the first parameter, so that the influence of the community on the payment behavior of the first user is determined. To avoid the problem that the single data of the first user is relatively inaccurate, the variation of the parameter of the first user in the target dimension before and after the community is visited can be counted for a period of time, and the period of time can be different time granularities of days, a week, a month, a quarter and the like.

The second user is of the same type as the first user. The first parameter of the second user and the first parameter of the first user are parameters in the same dimension in the same time period, and the second parameter of the second user and the second parameter of the first user are parameters in the same dimension in the same time period. For example: the first parameter of the first user is the average value of the week activity of the first week of the 10 months, and the first parameter of the second user is also the average value of the week activity of the first week of the 10 months. That is, the average value of the weekly activity means the average value of the weekly activity in the same period. For example, the second parameter of the first user is the average monthly payment for 1 month, and the second parameter of the second user is also the average monthly payment for 1 month. The difference is that the first parameter of the first user is data after the first user accesses the community, and the second parameter is data before the first user accesses the community. The first parameter and the second parameter of the second user are data of the contemporaneously unaccessed community.

The first parameter and the second parameter of the first user are used for obtaining a first index, and the first parameter and the second parameter of the second user are used for obtaining a second index. The first index is a ratio of a first parameter to a second parameter of the first user, and reflects the difference of the first user in the parameters after accessing the community, so that the behavior influence of the community on the first user is obtained. The second index is a ratio of the first parameter to the second parameter of the second user, and represents behavior changes of the second user in the first time period and the second time period.

And S210, optimizing the data of the community according to the first index and the second index. Wherein the community after optimization processing is used for improving the behavior index of the first user in the target dimension.

For example, a first index and a second index before the push content is updated are detected, the push content of the community is updated, the first index and the second index are detected again after the push content is updated, and if the ratio of the first index to the second index detected after the push content is updated is higher than the ratio of the first index to the second index detected before the push content is updated, the updated push content is indicated to make the user more willing to browse the community, or the user more willing to use a product corresponding to the community. And if the ratio of the first index to the second index detected after the push content is updated is lower than the ratio of the first index to the second index detected before the push content is updated, the updated push content does not improve the willingness of the user to browse the community, and the push content needs to be updated again. The content pushed by the update in this example may also be the arrangement of the updated layout, the display mode of the comment, the content set in the layout, and the like.

The first parameter and the second parameter of the second user are mainly used as reference functions, and in order to eliminate the influence of factors such as operation activities and time periods of communities, data processing is more accurate. And optimizing the data of the community by using the ratio of the first index to the second index. Namely, the optimization processing of the data of the community according to the first index and the second index comprises: determining the degree of influence of the community on the behavior of the first user under the target dimension by using the ratio of the first index to the second index; and updating the content displayed by the community according to the behavior influence degree.

The degree of the influence of the behavior is how much the community has an influence on the behavior of the first user. For example, in the dimension of the activity, before the first user accesses the community, the first user logs in the community or a product corresponding to the community once a week, and after the first user accesses the community, the first user logs in the community or a product corresponding to the community once a day, which indicates that the community affects the login behavior of the first user. For example, if the user a logs in the community or a product corresponding to the community 2 times a day after accessing the community, and the user B logs in the community or a product corresponding to the community 1 time a day after accessing the community, the community affects the behavior of the user a to a higher degree than the behavior of the user B. For example, after the community content is updated for the first time, the user a logs in the community or a product corresponding to the community 2 times a day after accessing the community, and after the community content is updated for the second time, the user a logs in the community or a product corresponding to the community 3 times a day after accessing the community, so that the degree of influence of the community updated for the second time on the behavior of the user a is higher than that of the community updated for the first time.

In the dimension of liveness, an active elevation index can be calculated: M-M1/M2 100

The first index M1 is the average value of the activity of the first user in the week (first parameter) after accessing the community (first time period)/the average value of the activity of the first user in the week (second parameter) before accessing the community (second time period)

Second index M2 is the average of the weekly activity of the second user over the first time period/average of the weekly activity of the second user over the second time period

In the dimension of payment, a payment promotion index may be calculated: N-N1/N2 100

First index N1 is the average weekly charge (first parameter) after a first user accesses the community (first time period)/the average weekly charge (second parameter) before the first user accesses the community (second time period)

Second index N2 is the average of the weekly payment of the second user over the first time period/the average of the weekly payment of the second user over the second time period

And comparing the parameter change of the first user in the target dimension before and after the first user accesses the community, and simultaneously comparing the parameter change of the second user in the target dimension in the same time period, thereby determining the influence of the community on the user behavior, namely the influence of the community on the parameter in the target dimension, and optimizing the content displayed by the community. For example, updating the layout, updating the contents of the layout, updating the page layout, etc.

According to the embodiment, the influence of the community on the user behavior is determined by the first index and the second index which measure the change of the user behavior under the target dimension, and accordingly, the data of the community is optimized, so that the technical problem that the community content cannot be optimized according to the user behavior to deposit the user in the prior art can be solved, the technical effect of optimizing the community content according to the user behavior is achieved, and the use experience of the community in the use of the product by the user is improved.

The embodiment will be described below with reference to fig. 4, which illustrates a micro community as an example.

S401, selecting users who visit the community on a certain day to obtain a first user set.

S402, clustering the users into 9 quadrants. As shown in fig. 3, the 9 quadrants are of the 9-quadrant type.

And S403, diffusing users corresponding to the 9 quadrants from the users who do not access the community through a look-like method to obtain a set of second users.

S404, calculating the changes of the liveness indexes and the payment indexes of the first user and the second user before and after the first user and the second user visit the community respectively.

S405, calculating an active promotion index M and a paid promotion index N.

As shown in fig. 5, the user in the designated quadrant before accessing the micro community determines the type of the first user before accessing the micro community, and obtains the average value M of the liveness of the first user of the type₁₁And a paid mean N₁₁Accessing the first user, namely the user in the designated quadrant after the micro community accesses the average value M of the activity of the first user after the community accesses₁₂And a paid mean N₁₂Thereby obtaining M₁＝M₁₂/M₁₁,N₁＝N₁₂/N₁₁。

The type of a second user corresponding to a first user before accessing the micro community is determined by similar users clustered in time periods corresponding to the previous 2 weeks and the previous 1 week, and the activity mean value M of the second user of the type is obtained₂₁And a paid mean N₂₁And acquiring the average value M of the activity degrees of the second user in the later 1 week and the later 2 weeks by the user in the designated quadrant of the later 1 week and the later 2 weeks, namely the second user₂₂And a paid mean N₂₂Thereby obtaining M₂＝M₂₂/M₂₁,N₁＝N₂₂/N₂₁。

Wherein M is₁₁、M₁₂、M₁₂、M₂₂、N₁₁、N₁₂、N₂₁、N₂₂The values of (A) are shown in Table 1.

TABLE 1

Index (I)	Degree of cyclic activity	Weekly payment mean
			Before accessing micro-communities	M₁₁＝3.80	N₁₁＝36.0
After accessing micro-communities	M₁₂＝4.00	N₁₂＝38.1
			Clustering reference user (front)	M₂₁＝3.90	N₂₁＝36.4
Clustering reference user (rear)	M₂₂＝3.80	N₂₂＝37.1

The calculated active boost index M and paid boost index N are shown in table 2:

TABLE 2

M₁	M₂	M
			1.05	0.97	108
N₁	N₂	N
			1.06	1.02	104

From the results in table 2, M and N are values greater than 100, and when the values are larger, the improvement effect of the micro-community on the user is larger. From the liveness promoting index and the payment promoting index, the micro community can promote the user behavior, and the liveness promoting index indicates that the user is more active after accessing the micro community, namely more products corresponding to the micro community are used; the payment degree promotion index indicates that the user pays more after accessing the micro community, that is, the user uses more payment functions when using the product.

The micro-community of the present embodiment may be a community associated with a product, which may be a community embedded in the product. For example, communities in game applications, communities in map applications, communities in instant messaging applications, etc., have the main characteristic of paying more attention to and showing the content of the product. For example, communities in game applications show game related content, communities in map applications show road condition related content, and communities in instant messaging applications show social related content.

The embodiment describes behavior changes of the user in the activity dimension and the payment dimension within a period of time, and it should be noted that the embodiment may analyze the behavior changes of the user after accessing the community in multiple dimensions, and may also analyze the behavior changes of the user after accessing the community in multiple periods of time, thereby determining a trend change of the influence of the community on the behavior of the user, and further updating and adjusting the community.

In order to more specifically update and optimize the content of the community, it may be determined what quality the population frequently accessing the community belongs to in the large population (all users of the product related to the community, including all users accessing the community and those not accessing the community), and the quality may be measured by two dimensions of liveness and payment of the users, that is, before determining the type of each first user in the set of first users accessing the community, the method further includes: acquiring a third index of the set of the first users in the target dimension, wherein the third index is used for indicating the proportion of the first users with the target characteristics in the set of the first users; acquiring a fourth index of the reference set in the target dimension, wherein the reference set comprises a first user set and a second user set, and the fourth index is used for indicating the proportion of the reference with the target characteristics in the reference set; and obtaining a target group index according to the third index and the fourth index, wherein the target group index is used for indicating the strength degree of the first user with the target characteristics relative to the reference with the target characteristics in the reference set on the target dimension.

Taking the game community as an example, the game community attracts the access of game users with its unique content and specific functions. For example, the game micro-community integrates various functions such as a personal center, latest information, hero teaching, boutique strategy, game video, game circle of friends, and the like. The quality of community aggregated users is an important aspect for judging community value, and communities capable of precipitating and aggregating high-quality users can become an important channel for high-quality users in game operation. The selection of two dimensions, active and paid, among a plurality of metrics defines the quality of the game user. In the active aspect, three-day retention, seven-day retention and fourteen-day retention of an active user are selected as index judgment of an active dimension, and in the payment aspect, payment permeability, payment ARPU and active user ARPU are selected as judgment of the user payment aspect.

In this embodiment, a method similar to the Target Group Index (TGI) is adopted to analyze and judge the quality of the community aggregated users. The target population index is a "tendency index" which is a value obtained by multiplying a ratio of a certain subgroup and a certain index to a ratio of the same index in the total group by the number of criteria of 100. The target population index reflects the strength of the target population in the dimension of the index to be analyzed in the analyzed field. The brute force program may be a degree of dominance in a target dimension of a target population relative to a reference population, the reference population being a cardinal number, the target population being a portion of the reference population. For example, a portion of the persons in a class have joined the math boosting class by election, and this portion of the students who entered the math boosting class by election will perform somewhat better in math than other students who did not enter the math boosting class. The target population can be well characterized by the index. And effective data basis is provided for strategy formulation and value judgment.

The calculation method of the target population index comprises the following steps:

TGI index [ proportion of population having a certain characteristic in the target population/proportion of population having the same characteristic in the population ]. times.100. The TGI index can be used to characterize the difference of the attention of different users, wherein the TGI index is equal to 100 and represents the average level, and is higher than 100, which represents that the attention of the users in the category is higher than the overall level. Wherein, the proportion of the group with a certain characteristic in the target group is the third index, and the proportion of the group with the same characteristic in the population is the fourth index. Target population index (third index/fourth index) 100.

The data in table 3 are used as an example to illustrate the analytical calculation of TGI index:

TABLE 3

The TGI index is visually reflected by the histogram of fig. 6. The microcommunity user of table 3 is the first set of users and the large disk user is the reference set. In this embodiment, the two indexes of paid ARPU and active ARPU are different from the above ratio, and the concept of intermediate parameters (trade paid ARPU and trade active ARPU) is used, and assuming that trade paid ARPU is a and trade active ARPU is B, the achievement rate of micro-community paid ARPU is 26.5/a, the achievement rate of large-disk paid ARPU is 20.4/a, TGI (26.5/a)/(20.4/a) is 130, and active ARPU can be calculated to be 238 in the same manner. When the TGI index is larger than 100, the larger the data is, the more obvious the index characteristic is in the user group of the micro-community. From table 3 above, it can be seen that the active and paid TGI indexes of the microcommunity users are both greater than 100, and the paid penetration rate and the active ARPU are more significant, which indicates that the microcommunity aggregates core users with good quality in the reference set, and the paid capacity is significantly higher than that of the reference set.

By the method, the quality condition of the first users in the aggregation first user set in the community can be judged, the TGI index can be calculated according to days or weeks in the time dimension, so that the quality change condition of the content community users can be followed in real time, and the content such as the content displayed by the community or the operation strategy can be adjusted according to the quality change of the users.

It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.

Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.

According to still another aspect of the embodiments of the present invention, there is also provided a processing apparatus of community data for implementing the above processing method of community data, as shown in fig. 7, the apparatus includes:

a determining unit 70, configured to determine a type of each first user in a first user set accessing a community, where the type of each first user is a target type in a target dimension;

the first user is accessed community, and the first user set comprises a plurality of first users. The type of the first user may be obtained by clustering. Target dimensions can be determined through user clustering, and the target dimensions are divided into multiple types. Each first user corresponds to one of the pair types. Wherein the target dimension may comprise one or more dimensions.

Optionally, the determining unit includes: the acquisition module is used for acquiring multiple types under the target dimension; the value taking module is used for determining the value taking range of the target parameter in the target dimension according to the multiple types; a classification module, configured to classify each first user in the first user set according to the value range and a target parameter value of each first user; a third determining module, configured to determine that the type of the first user is the target type of the multiple types.

The target dimension includes a first dimension and a second dimension, and the obtaining module includes: and the clustering submodule is used for clustering the first user set into multiple types on the first dimension and the second dimension in a user clustering mode, wherein each type comprises a parameter value range of the first dimension and a parameter value range of the second dimension.

A searching unit 72, configured to search a second user matching the type of the first user from a set of second users who never visited the community;

optionally, the similar users are diffused among the second users for each type of first users in a look-like manner, and users of the same type and who have not accessed the micro-community are found. Namely, the search unit includes: the searching module is used for searching a second user of which the difference value between the target parameter value of the second user and the target parameter value of the first user is within a preset range from a set of second users who never visit the community; and the configuration module is used for configuring the type of the searched second user with the corresponding type of the first user.

A first obtaining unit 74, configured to obtain a first index of the first user in the target dimension, where the first index is used to indicate a behavior change of the first user in a first time period before accessing the community and a second time period after accessing the community;

a second obtaining unit 76, configured to obtain a second index of the second user in the target dimension, where the second index is used to indicate a behavior change of the second user in the first time period and the second time period.

Optionally, the first obtaining unit includes: a first determining module, configured to use a ratio of a first parameter of the first user in the first time period after accessing the community to a second parameter of the first user in the second time period before accessing the community as the first index; the second acquisition unit includes: a second determining module, configured to use a ratio of a first parameter of the second user in the first time period to a second parameter of the second user in the second time period as the second index.

A processing unit 78, configured to perform optimization processing on the data of the community according to the first index and the second index, where the community after the optimization processing is used to improve the behavior index of the first user in the target dimension.

The first parameter and the second parameter of the second user are mainly used as reference functions, and in order to eliminate the influence of factors such as operation activities and time periods of communities, data processing is more accurate. And optimizing the data of the community by using the ratio of the first index to the second index. That is, optionally, the processing unit comprises: a fourth determining module, configured to determine, by using a ratio of the first index and the second index, a degree of influence of the community on behavior of the first user in the target dimension; and the updating module is used for updating the content displayed by the community according to the behavior influence degree.

In order to more specifically update and optimize the content of the community, it can be determined what quality of the people who frequently visit the community belongs to in the large-disk population (all users of the products related to the community, including all users who visited the community and those who did not visit the community), and the quality can be measured by two dimensions of the liveness and the payment of the users, that is, the device further comprises: the first index unit is used for acquiring a third index of the set of first users in the target dimension before determining the type of each first user in the set of first users who visit the community, wherein the third index is used for indicating the proportion of the first users with target characteristics in the set of first users; a second index unit, configured to obtain a fourth index of a reference set in the target dimension, where the reference set includes the first user set and the second user set, and the fourth index is used to indicate a proportion of a reference with the target feature in the reference set; a third index unit, configured to obtain a target group index according to the third index and the fourth index, where the target group index is used to indicate how strong a first user with the target feature is in the target dimension relative to the reference with the target feature in the reference set.

In this embodiment, a method similar to the Target Group Index (TGI) is adopted to analyze and judge the quality of the community aggregated users. The target population index is a "tendency index" which is a value obtained by multiplying a ratio of a certain subgroup and a certain index to a ratio of the same index in the total group by the number of criteria of 100. The target population index reflects the strength of the target population in the dimension of the index to be analyzed in the analyzed field. The target population can be well characterized by the index. And effective data basis is provided for strategy formulation and value judgment.

According to another aspect of the embodiments of the present invention, there is also provided an electronic device for implementing the method for processing community data, as shown in fig. 8, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor is configured to execute the steps in any one of the method embodiments through the computer program.

Alternatively, fig. 8 is a block diagram of an electronic device according to an embodiment of the invention. As shown in fig. 8, the electronic device may include: one or more processors 801 (only one shown), at least one communication bus 802, a user interface 803, at least one transmitting device 804, and memory 805. Wherein a communication bus 802 is used to enable connective communication between these components. The user interface 803 may include, among other things, a display 806 and a keyboard 807. The transmission means 804 may optionally include standard wired and wireless interfaces.

Optionally, in this embodiment, the electronic apparatus may be located in at least one network device of a plurality of network devices of a computer network.

Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:

s1, determining the type of each first user in a first user set which has accessed the community, wherein the type of each first user is a target type under a target dimension;

s2, searching a second user matched with the type of the first user from a set of second users who never visit the community;

s3, acquiring a first index of the first user in the target dimension and a second index of the second user in the target dimension, wherein the first index is used for indicating behavior change of the first user in a first time period before the community is accessed and a second time period after the community is accessed, and the second index is used for indicating behavior change of the second user in the first time period and the second time period;

and S4, optimizing the data of the community according to the first index and the second index, wherein the community after optimization is used for improving the behavior index of the first user in the target dimension.

Alternatively, it can be understood by those skilled in the art that the structure shown in fig. 8 is only an illustration, and the electronic device may also be a terminal device such as a smart phone (e.g., an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, a Mobile Internet Device (MID), a PAD, and the like. Fig. 8 is a diagram illustrating a structure of the electronic device. For example, the electronic device may also include more or fewer components (e.g., network interfaces, display devices, etc.) than shown in FIG. 8, or have a different configuration than shown in FIG. 8.

The memory 805 may be used to store software programs and modules, such as program instructions/modules corresponding to the method and apparatus for processing community data in the embodiment of the present invention, and the processor 801 executes various functional applications and data processing by running the software programs and modules stored in the memory 805, that is, implements the above-described method for processing community data. The memory 805 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 805 may further include memory located remotely from the processor 801, which may be connected to the terminal through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission device 804 is used for receiving or transmitting data via a network. Examples of the network may include a wired network and a wireless network. In one example, the transmission device 804 includes a Network adapter (NIC) that can be connected to a router via a Network cable and other Network devices to communicate with the internet or a local area Network. In one example, the transmission device 804 is a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.

Specifically, the memory 805 is used for storing preset action conditions, information of a preset authorized user, and an application program.

Embodiments of the present invention also provide a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the above method embodiments when executed.

Alternatively, in the present embodiment, the storage medium may be configured to store a computer program for executing the steps of:

Optionally, the storage medium is further arranged to store a computer program for performing the steps of: taking a ratio of a first parameter of the first user within the first time period after accessing the community to a second parameter of the first user within the second time period before accessing the community as the first index; and taking the ratio of the first parameter of the second user in the first time period to the second parameter of the second user in the second time period as the second index.

Optionally, the storage medium is further arranged to store a computer program for performing the steps of: acquiring multiple types under the target dimension; determining the value range of the target parameter in the target dimension according to the multiple types; classifying each first user in the first user set according to the value range and the target parameter value of each first user; determining the type of the first user as the target type of the multiple types.

Optionally, the storage medium is further arranged to store a computer program for performing the steps of: and clustering the first user set into the multiple types on the first dimension and the second dimension in a user clustering mode, wherein each type comprises a parameter value range of the first dimension and a parameter value range of the second dimension.

Optionally, the storage medium is further arranged to store a computer program for performing the steps of: searching a second user with a difference value between the target parameter value of the second user and the target parameter value of the first user within a preset range from a set of second users who never visit the community; and configuring the type of the searched second user with the corresponding type of the first user.

Optionally, the storage medium is further arranged to store a computer program for performing the steps of: acquiring a third index of the set of first users in the target dimension, wherein the third index is used for indicating the proportion of the first users with target characteristics in the set of first users; obtaining a fourth index of a reference set in the target dimension, wherein the reference set comprises the first user set and the second user set, and the fourth index is used for indicating the proportion of a reference with the target feature in the reference set; and obtaining a target group index according to the third index and the fourth index, wherein the target group index is used for indicating the strength degree of the first user with the target feature on the target dimension relative to the reference with the target feature in the reference set.

Optionally, the storage medium is further configured to store a computer program for executing the steps included in the method in the foregoing embodiment, which is not described in detail in this embodiment.

Alternatively, in this embodiment, a person skilled in the art may understand that all or part of the steps in the methods of the foregoing embodiments may be implemented by a program instructing hardware associated with the terminal device, where the program may be stored in a computer-readable storage medium, and the storage medium may include: flash disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.

The integrated unit in the above embodiments, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in the above computer-readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing one or more computer devices (which may be personal computers, servers, network devices, etc.) to execute all or part of the steps of the method according to the embodiments of the present invention.

In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the several embodiments provided in the present application, it should be understood that the disclosed client may be implemented in other manners. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be 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, units or modules, and may be in an electrical 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, and can also be realized in a form of a software functional unit.

The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims

1. A method for processing community data is characterized by comprising the following steps:

acquiring multiple types under a target dimension;

determining the value range of the target parameter in the target dimension according to the multiple types;

classifying each first user in the first user set according to the value range and the target parameter value of each first user;

determining the type of the first user as a target type in the multiple types; the type of the first user is a target type under a target dimension;

searching a second user with a difference value between a target parameter value of the second user and a target parameter value of the first user within a preset range from a set of second users who never visit the community;

configuring the type of the searched second user with the type of the corresponding first user;

obtaining a first index of the first user in the target dimension, wherein the first index is used for indicating behavior change of the first user in a first time period before the first user accesses the community and a second time period after the first user accesses the community;

obtaining a second index of the second user in the target dimension, wherein the second index is used for indicating the behavior change of the second user in the first time period and the second time period;

optimizing the arrangement of the blocks of the community and the display mode of the comment according to the first index and the second index, specifically including detecting the first index and the second index before updating the arrangement of the blocks of the community and the display mode of the comment, and detecting the first index and the second index after updating the arrangement of the blocks of the community and the display mode of the comment, wherein when the ratio of the first index to the second index after updating the arrangement of the blocks of the community and the display mode of the comment is higher than the ratio of the first index to the second index before updating the arrangement of the blocks of the community and the display mode of the comment, the updated arrangement of the blocks of the community and the display mode of the comment are retained, and when the ratio of the first index to the second index after updating the arrangement of the blocks of the community and the display mode of the comment is lower than the updated arrangement of the blocks, Under the condition of the ratio of the first index to the second index before the display mode of the comments, updating the arrangement of the plates of the community and the display mode of the comments again, and pushing the arrangement of the plates of the community and the display mode of the comments after updating again.

2. The method of claim 1, wherein obtaining a first index of the first user in the target dimension and a second index of the second user in the target dimension comprises:

taking a ratio of a first parameter of the first user within the first time period after accessing the community to a second parameter of the first user within the second time period before accessing the community as the first index;

and taking the ratio of the first parameter of the second user in the first time period to the second parameter of the second user in the second time period as the second index.

3. The method of claim 1, wherein the target dimension comprises a first dimension and a second dimension, and wherein obtaining the plurality of types in the target dimension comprises:

and clustering the first user set into the multiple types on the first dimension and the second dimension in a user clustering mode, wherein each type comprises a parameter value range of the first dimension and a parameter value range of the second dimension.

4. The method of claim 1, wherein prior to determining the type of each first user in the set of first users who have accessed the community, the method further comprises:

acquiring a third index of the set of first users in the target dimension, wherein the third index is used for indicating the proportion of the first users with target characteristics in the set of first users;

obtaining a fourth index of a reference set in the target dimension, wherein the reference set comprises the first user set and the second user set, and the fourth index is used for indicating the proportion of a reference with the target feature in the reference set;

and obtaining a target group index according to the third index and the fourth index, wherein the target group index is used for indicating the strength degree of the first user with the target feature on the target dimension relative to the reference with the target feature in the reference set.

5. The method of claim 1, wherein optimizing the arrangement of the blocks and the display mode of the comments of the community according to the first index and the second index comprises:

determining the degree of influence of the community on the behavior of the first user in the target dimension by using the ratio of the first index to the second index;

and updating the arrangement of the community plates and the display mode of the comments according to the behavior influence degree.

6. An apparatus for processing community data, comprising:

the determining unit comprises an obtaining module, a determining module and a judging module, wherein the obtaining module is used for obtaining multiple types under the target dimension; the value taking module is used for determining the value taking range of the target parameter in the target dimension according to the multiple types; the classification module is used for classifying each first user in the first user set according to the value range and the target parameter value of each first user; a third determining module, configured to determine that the type of the first user is a target type in the multiple types, where each type of the first user is a target type in a target dimension;

the searching unit comprises a searching module, a searching module and a searching module, wherein the searching module is used for searching a second user of which the difference value between the target parameter value of the second user and the target parameter value of the first user is within a preset range from a set of second users who never visit the community; the configuration module is used for configuring the type of the searched second user with the corresponding type of the first user;

a first obtaining unit, configured to obtain a first index of the first user in the target dimension, where the first index is used to indicate a behavior change of the first user in a first time period before accessing the community and a second time period after accessing the community;

a second obtaining unit, configured to obtain a second index of the second user in the target dimension, where the second index is used to indicate a behavior change of the second user in the first time period and the second time period;

a processing unit, configured to perform optimization processing on the arrangement of the blocks of the community and the display manner of the comment according to the first index and the second index, specifically, detect the first index and the second index before the arrangement of the blocks of the community and the display manner of the comment are updated, and detect the first index and the second index after the arrangement of the blocks of the community and the display manner of the comment are updated, retain the updated arrangement of the blocks of the community and the display manner of the comment when a ratio of the first index and the second index after the arrangement of the blocks of the community and the display manner of the comment are updated is higher than a ratio of the first index and the second index before the arrangement of the blocks of the community and the display manner of the comment are updated, and maintain the updated arrangement of the blocks of the community and the display manner of the comment when the ratio of the first index and the second index after the arrangement of the blocks of the community and the display manner of the comment are updated is lower than the ratio of the updated arrangement of the blocks of the community and the display manner of Under the condition of the ratio of the first index to the second index before the plate arrangement and comment display mode, the plate arrangement and comment display mode of the community is updated again, and the updated plate arrangement and comment display mode of the community is pushed again.

7. The apparatus of claim 6,

the first acquisition unit includes: a first determining module, configured to use a ratio of a first parameter of the first user in the first time period after accessing the community to a second parameter of the first user in the second time period before accessing the community as the first index;

the second acquisition unit includes: a second determining module, configured to use a ratio of a first parameter of the second user in the first time period to a second parameter of the second user in the second time period as the second index.

8. The apparatus of claim 6, wherein the target dimensions comprise a first dimension and a second dimension, and wherein the obtaining module comprises:

and the clustering submodule is used for clustering the first user set into multiple types on the first dimension and the second dimension in a user clustering mode, wherein each type comprises a parameter value range of the first dimension and a parameter value range of the second dimension.

9. The apparatus of claim 6, further comprising:

the first index unit is used for acquiring a third index of the set of first users in the target dimension before determining the type of each first user in the set of first users who visit the community, wherein the third index is used for indicating the proportion of the first users with target characteristics in the set of first users;

a second index unit, configured to obtain a fourth index of a reference set in the target dimension, where the reference set includes the first user set and the second user set, and the fourth index is used to indicate a proportion of a reference with the target feature in the reference set;

a third index unit, configured to obtain a target group index according to the third index and the fourth index, where the target group index is used to indicate how strong a first user with the target feature is in the target dimension relative to the reference with the target feature in the reference set.

10. A storage medium, in which a computer program is stored, wherein the computer program is arranged to perform the method of any of claims 1 to 5 when executed.

11. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to execute the method of any of claims 1 to 5 by means of the computer program.