A profile determination method

Abstract

The present invention relates to a profile determination method, the method comprising: step S1: obtaining a second user profile of each user in a user set; step S2: screening key users based on the second user profile. The present invention can consider the uploaded user profile while obtaining the user profile in real time, and determine the key users in a quantitative manner by uniformly considering the user profiles obtained from various channels, thereby achieving a focus on the key users, thereby greatly improving the user experience.

Description

[Technical field]

[0001] The invention belongs to the field of user management, and in particular relates to a profile determination method. [Background technology]

[0002] With the development of Internet technology, Web2.0 type websites continue to emerge, including many social network service (SNS) websites. SNS refers to Internet application services designed to help people build social networks; another explanation of SNS is Social Network Site, that is, social networking sites or social networks. However, the user data of each SNS website cannot be reused on multiple SNS websites, that is, the user data of the same user cannot be shared between different SNS websites. Each SNS website that the user has registered with needs to analyze the user data of the user in isolation, which may cause some SNS websites to have too little user data, so that they cannot provide users with better services, and users can only log in to each SNS website in turn to use the services provided by different SNS websites. For example: for newly registered users, a single SNS website cannot obtain enough data for analysis within a period of time, which will affect the accuracy of user data analysis, and then affect the provision of services, and reduce user experience. Based on the above problems, a new profile determination method is urgently needed. The present invention can consider the uploaded user profile while obtaining the user profile in real time. By uniformly considering the user profiles obtained from various channels, key users are determined in a quantitative manner, and key users are focused on, thereby greatly improving the user experience. [Summary of the invention]

[0003] In order to solve the above problems in the prior art, the present invention proposes a profile determination method, which comprises the following steps:

[0004] Step S1: obtaining a second user profile of each user in the user set;

[0005] Step S2: Filter key users based on the second user profile.

[0006] Furthermore, the step S1 is specifically to create an uploaded data area for each user, store the uploaded data set by the user and obtained by big data analysis in the uploaded data area; obtain the uploaded data from the uploaded data area, set a weight level for the uploaded data, and use the uploaded data as the second user profile.

[0007] Furthermore, creating an upload data area for each user specifically includes: creating an independent upload area for each user and obtaining an index based on the user identifier, so that the upload data area can be quickly located through the index when the upload data needs to be accessed.

[0008] Furthermore, the index is obtained by performing a hash calculation on the user identifier.

[0009] Furthermore, the upload data area is located in a cloud area or in an independent physical area.

[0010] Furthermore, the uploading data set by the user and obtained by big data analysis is stored in the uploading data area, specifically: the uploading data area is divided into a first area and a second area, and the uploading data is stored in the first or second manner.

[0011] Further, method 1: storing fixed uploaded data in the first area and storing newly uploaded data in the second area; wherein the fixed uploaded data is uploaded data having an existence time exceeding a first time threshold; and the newly uploaded data is uploaded data having an existence time lower than the first time threshold.

[0012] Further, method 2: placing the data set by the user in the first area; placing the uploaded data obtained by big data analysis with high similarity to the user settings in the first area, and placing the uploaded data with low similarity in the second area.

[0013] The beneficial effects of the present invention include: being able to consider uploading acquired user profiles while acquiring user profiles in real time, uniformly considering user profiles acquired from various channels, determining key users in a quantitative manner, and focusing on key users, thereby greatly improving user experience.

Brief Description of the Drawings

[0014] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present application, but do not constitute an improper limitation of the present invention. In the drawings:

[0015] Figure 1 is a flow chart of the profile determination method of the present invention. [Specific implementation method]

[0016] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments, wherein the illustrative embodiments and descriptions are only used to explain the present invention but are not intended to limit the present invention.

[0017] A profile determination method used in the present invention is described in detail, and the method comprises the following steps:

[0018] Step S1: acquiring a first user profile in real time, specifically: setting a real-time acquisition device for each user in the user set, acquiring real-time data based on a real-time period associated with the real-time acquisition device, the real-time data being associated with each user, acquiring a weight level of the real-time data based on a weight level of the real-time acquisition device; and using the real-time data as the first user profile;

[0019] Preferably: the real-time period is a preset value set according to the parameters of the real-time acquisition device;

[0020] Preferably: each real-time acquisition device is used to acquire real-time data for one or more users;

[0021] The step of acquiring the weight level of the real-time data based on the weight level of the real-time acquisition device specifically comprises: acquiring parameters of the real-time acquisition device, and acquiring the weight level of the real-time acquisition device based on the parameters of the real-time acquisition device; and acquiring the weight level of the real-time data based on the weight level of the real-time acquisition device.

[0022] Preferably: the parameters of the real-time acquisition device include: implementation mode, real-time cycle, real-time granularity, and accuracy;

[0023] The weight level of the real-time acquisition device is obtained based on the parameter of the real-time acquisition device, specifically: obtaining the parameter value of the parameter of the real-time acquisition device, and calculating the weight level of the real-time acquisition device based on the following formula;

[0024]

[0025] Where: PRA is the weight level of the real-time acquisition device, HS is the implementation method, FR is the real-time cycle, GR is the real-time granularity, AC is the accuracy, and BS_AC is the accuracy adjustment value;

[0026] Preferably: when a hardware implementation is adopted, the implementation parameter value is higher, and when a software implementation is adopted, the implementation parameter value is lower;

[0027] Preferably: when the hardware implementation is adopted, HS=1, and when the software implementation is adopted, HS=0.1;

[0028] The step of acquiring the weight level of the real-time data based on the weight level of the real-time acquisition device specifically comprises: using the weight level of the real-time acquisition device as the weight level of the real-time data;

[0029] Dynamically adjusting the weight level based on the adjustment value, so as to dynamically balance the weight of the device and the user itself;

[0030] Step S2: obtaining a second user profile of each user in the user set, specifically: creating an uploaded data area for each user, storing the uploaded data set by the user and obtained by big data analysis in the uploaded data area; obtaining the uploaded data from the uploaded data area, setting a weight level for the uploaded data, and using the uploaded data as the second user profile;

[0031] The creating of an upload data area for each user specifically includes: creating an independent upload area for each user and obtaining an index based on the user identifier, so that the upload data area can be quickly located through the index when the upload data needs to be accessed;

[0032] Preferably: the index is obtained by performing a hash calculation on the user identifier;

[0033] Preferably: the data upload area is located in a cloud area or in an independent physical area;

[0034] Preferably: the data upload area is set at a location close to the user's physical location; specifically: the location close to the user is the user's mobile phone storage area;

[0035] The storing of the uploaded data set by the user and obtained by the big data analysis in the uploaded data area specifically comprises: dividing the uploaded data area into a first area and a second area, and adopting the first method or the second method to store the uploaded data;

[0036] Method 1: storing fixed uploaded data in the first area and storing newly uploaded data in the second area; wherein fixed uploaded data refers to uploaded data whose existence time exceeds the first time threshold; newly uploaded data refers to uploaded data whose existence time is lower than the first time threshold; the first time threshold can be used to distinguish uploaded data, and the deposited data and the data to be examined can be distinguished and considered;

[0037] Method 2: placing the data set by the user in the first area; placing the uploaded data obtained by big data analysis and having a high similarity with the user setting in the first area, and placing the uploaded data with a low similarity in the second area; the high similarity specifically means that the similarity is greater than a first similarity threshold;

[0038] Preferably: the first similarity threshold is dynamically set based on the size of the first area, and the first similarity threshold is reduced as the size of the first area increases until a minimum similarity threshold is reached, and vice versa, until a maximum similarity threshold is reached; wherein the minimum similarity threshold and the maximum similarity threshold are both fixed values; the minimum similarity threshold is 80%, and the maximum similarity threshold is 100%;

[0039] Preferably, the setting of weight levels for the uploaded data is specifically: setting the uploaded data in the first area to a high weight level, and setting the uploaded data in the second area to a low weight level;

[0040] Step S3: filtering key users based on the first user profile and the second user profile; specifically: if the weight level of the first user profile or the weight level of the second user profile of the user has a weight level higher than the weight level threshold, the user is set as a key user;

[0041] Pay special attention to key users;

[0042] When a user is a key user, specialized services can be provided to the user, thereby improving the user experience of the key user;

[0043] The above description is only a preferred embodiment of the present invention, so all equivalent changes or modifications made according to the structure, characteristics and principles described in the scope of the patent application of the present invention are included in the scope of the patent application of the present invention.

Claims

1. A profile determination method, characterized in that: The method comprises the following steps: Step S1: Obtain a second user profile of each user in the user set; Step S2: screening key users based on the second user profile; The step S1 specifically includes creating an uploaded data area for each user, storing the uploaded data set by the user and obtained by big data analysis in the uploaded data area; obtaining the uploaded data from the uploaded data area, setting a weight level for the uploaded data, and using the uploaded data as the second user profile; The creating of the upload data area for each user specifically includes: creating an independent upload area for each user and obtaining an index based on the user identifier, so that the upload data area can be quickly located through the index when the upload data needs to be accessed; The index is obtained by performing hash calculation on the user identifier; The upload data area is located in a cloud area or in an independent physical area; Where: PRA is the weight level of the real-time acquisition device, HS is the implementation method, FR is the real-time cycle, GR is the real-time granularity, AC is the accuracy, and BS_AC is the accuracy adjustment value; Acquiring the first user profile in real time, specifically: setting a real-time acquisition device for each user in the user set, acquiring real-time data based on a real-time period associated with the real-time acquisition device, the real-time data being associated with each user, acquiring a weight level of the real-time data based on a weight level of the real-time acquisition device; and using the real-time data as the first user profile; The key user is screened based on the first user profile and the second user profile; specifically: if the weight level of the first user profile or the second user profile of the user has a weight level higher than the weight level threshold, the user is set as the key user.

2. The profile determination method according to claim 1, characterized in that: The method of storing the uploaded data set by the user and obtained by the big data analysis in the uploaded data area specifically includes: dividing the uploaded data area into a first area and a second area, and adopting method one or method two to store the uploaded data.

3. The profile determination method according to claim 2, characterized in that: Method 1: storing fixed uploaded data in the first area and storing newly uploaded data in the second area; wherein the fixed uploaded data is uploaded data whose existence time exceeds the first time threshold; and the newly uploaded data is uploaded data whose existence time is lower than the first time threshold.

4. The profile determination method according to claim 3, characterized in that: Method 2: placing the data set by the user in the first area; placing the uploaded data obtained through big data analysis that is highly similar to the user settings in the first area, and placing the uploaded data that is less similar in the second area.

Images