CN109408735B - Stranger social user portrait generation method and system - Google Patents
Stranger social user portrait generation method and system Download PDFInfo
- Publication number
- CN109408735B CN109408735B CN201811182324.6A CN201811182324A CN109408735B CN 109408735 B CN109408735 B CN 109408735B CN 201811182324 A CN201811182324 A CN 201811182324A CN 109408735 B CN109408735 B CN 109408735B
- Authority
- CN
- China
- Prior art keywords
- activity
- current user
- feature vector
- user
- information
- 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.)
- Active
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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Abstract
The embodiment of the application provides a method and a system for generating a stranger social user portrait, wherein the method comprises the following steps: acquiring big data information of a current user, wherein the big data information comprises registration information, personal interest tag information and personal social activity information of the current user; extracting interest preference of the current user from the big data information, and generating a corresponding feature vector according to the interest preference; correcting the characteristic vector according to the type of the historical activities pushed to the current user to generate a corrected characteristic vector; and pushing the activity information of the current activity related to the interest preference in the corrected feature vector to the current user according to a preset condition. According to the method for generating the stranger social user portrait, activities can be pushed to the user according to multiple interests of the user, the single activity type of the activities pushed to the user is avoided, the interest of the user in participating in the activities is improved, and the development of stranger social is facilitated.
Description
Technical Field
The application relates to the technical field of internet, in particular to a stranger social user portrait generation method and system.
Background
Social interaction refers to the interpersonal communication between people in the society, and is the consciousness that people transmit information and communicate ideas in a certain mode (tool) so as to achieve various social activities with a certain purpose. In the modern times, changes in economic and social environments make interpersonal communication more important. With the development of scientific technology and the application of internet resources in life, the communication between people is realized by means of the internet, and strangers can also realize social contact through the internet, so that the purposes of further developing and expanding the strangers are realized.
In the prior art, in the process of realizing social contact among strangers, users usually use an intelligent terminal to initiate or register to participate in social activities in an APP of the intelligent terminal so as to realize the social contact among the strangers. The APP of the intelligent terminal invites other users to participate in social activities by pushing activity information of the social activities initiated by the other users to the user. However, in the prior art, the activity type of the activity pushed to the user by the APP of the intelligent terminal is too single, so that the pushed activity is not the type in which the user is interested, and meanwhile, the interest of the user in other aspects is ignored, the interest of the user in participating in the activity is reduced, the user experience is influenced, and the development of strangers in social contact is not facilitated.
Disclosure of Invention
In view of this, an object of the present application is to provide a method and a system for generating a stranger social user portrait, so as to solve the technical problems that in the prior art, the activity type of the activity pushed to the user by the APP of the intelligent terminal is too single, so that the pushed activity is not the type of interest of the user, and meanwhile, the interest of the user in other aspects is ignored, the interest of the user in participating in the activity is reduced, and the experience of the user is affected.
In view of the above, in a first aspect of the present application, a method for generating a stranger social user representation is provided, including:
acquiring big data information of a current user, wherein the big data information comprises registration information, personal interest tag information and personal social activity information of the current user;
extracting interest preference of the current user from the big data information, and generating a corresponding feature vector according to the interest preference;
correcting the characteristic vector according to the type of the historical activities pushed to the current user to generate a corrected characteristic vector;
and pushing the activity information of the current activity related to the interest preference in the corrected feature vector to the current user according to a preset condition.
In some embodiments, the method of claim 1, wherein the personal social activity information comprises:
the activity information of the social activity initiated by the current user and/or the activity information of the social activity in which the current user participates and/or the activity information of the social activity in which the current user focuses attention.
In some embodiments, the modifying the feature vector with the weight vector to generate a modified feature vector includes:
using weight vectors (alpha)1，α2，α3，……，αk) For the feature vector (x)1，x2，x3，……，xk) Correction is performed to generate a corrected feature vector (alpha)1x1，α2x2，α3x3，……，αkxk) In which α is1+α2+α3+……+αk=1，α1，α2，α3，……，αkIs inversely related to the cumulative number of each type of historical activity pushed to the current user.
In some embodiments, further comprising:
and storing the activity information of the current activity pushed to the current user, and updating the pre-stored accumulated quantity of each type of historical activity pushed to the current user according to the activity information.
In some embodiments, the pushing, according to a preset condition, activity information of a current activity related to interest preference in the modified feature vector to the current user includes:
and pushing the activity information of the current activity related to the interest preference with the largest specific gravity value in the corrected feature vector to the current user.
In some embodiments, the utilization weight vector (α)1，α2，α3，……，αk) For the feature vector (x)1，x2，x3，……，xk) Correction is performed to generate a corrected feature vector (alpha)1x1，α2x2，α3x3，……，αkxk) The method comprises the following steps:
reducing the modified feature vector (alpha)1x1，α2x2，α3x3，……，αkxk) Middle dimension alpha with the largest specific gravity valuenxnCorrection parameter α innThe values of the other correction parameters are increased averagely to generate the correction characteristics after the correction parameters are changedVector, where n =1,2,3.. k.
In some embodiments, the utilization weight vector (α)1，α2，α3，……，αk) For the feature vector (x)1，x2，x3，……，xk) Correction is performed to generate a corrected feature vector (alpha)1x1，α2x2，α3x3，……，αkxk) The method comprises the following steps:
reducing the modified feature vector (alpha)1x1，α2x2，α3x3，……，αkxk) Increasing the value of the correction parameter alpha n in the dimension alpha nxn with the maximum specific gravity value to increase the correction characteristic vector alpha n1x1，α2x2，α3x3，……，αkxk) The value of the correction parameter in the dimension with the second largest value of the medium specific gravity generates a corrected feature vector after the correction parameter is changed, wherein n =1,2,3.. k.
In some embodiments, the utilization weight vector (α)1，α2，α3，……，αk) For the feature vector (x)1，x2，x3，……，xk) Correction is performed to generate a corrected feature vector (alpha)1x1，α2x2，α3x3，……，αkxk) The method comprises the following steps:
reducing the modified feature vector (alpha)1x1，α2x2，α3x3，……，αkxk) Middle dimension alpha with the largest specific gravity valuenxnCorrection parameter α innAnd increasing the value of the correction parameter of the corresponding dimension in the correction feature vector according to the activity of the user to participate or pay attention to, and generating the correction feature vector after the correction parameter is changed, wherein n =1,2,3.
In another aspect of the present application, a system for generating a stranger social user representation is further provided, including:
the big data information acquisition module is used for acquiring big data information of a current user, wherein the big data information comprises registration information, personal interest tag information and personal social activity information of the current user;
the characteristic vector generation module is used for extracting interest preference of the current user from the big data information and generating a corresponding characteristic vector according to the interest preference;
the corrected feature vector generating module is used for correcting the feature vector according to the type of the historical activities pushed to the current user to generate a corrected feature vector;
and the activity information pushing module is used for pushing the activity information of the current activity related to the interest preference in the corrected feature vector to the current user according to a preset condition.
In some embodiments, further comprising:
and the storage module is used for storing the activity information of the current activity pushed to the current user and updating the pre-stored accumulated quantity of each type of historical activity pushed to the current user according to the activity information.
The embodiment of the application provides a method and a system for generating a stranger social user portrait, wherein the method comprises the following steps: acquiring big data information of a current user, wherein the big data information comprises registration information, personal interest tag information and personal social activity information of the current user; extracting interest preference of the current user from the big data information, and generating a corresponding feature vector according to the interest preference; correcting the characteristic vector according to the type of the historical activities pushed to the current user to generate a corrected characteristic vector; and pushing the activity information of the current activity related to the interest preference in the corrected feature vector to the current user according to a preset condition. According to the method for generating the stranger social user portrait, activities can be pushed to the user according to multiple interests of the user, the situation that the types of the activities pushed to the user are too single is avoided, the interest of the user in participating in the activities is improved, the user experience is improved, and the development of stranger social is facilitated.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is a flowchart of a stranger social user representation generation method according to a first embodiment of the present application;
FIG. 2 is a flowchart of a stranger social user representation generation method according to a second embodiment of the present application;
fig. 3 is a schematic structural diagram of a system for generating a stranger social user representation according to a third embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
The user representation integrates registered personal information of the user, user interest tags, historical social activities in which the user participates (such as social activities initiated or participated by the user, and social activities concerned or favored by the user) into a feature vector with multiple dimensions according to historical big data of each user. The feature vector can be used for judging interest preference of the user for participating in stranger social activities, and further recommending social activities suitable for the user. For example, if the user representation indicates that the user is a sports fan, he may be given more recommendations for social activities of sports type.
However, such a drawback may lead to a gradual simplification of the types of social activities pushed to the user, for example, the user is considered to like sports according to the user portrait analysis, so that more sports activities are pushed to the user, and the number of sports activities selected by the user to participate or like increases, so that the score of the dimension representing the sports in the user portrait is higher, and more sports activities are pushed, and so on, and finally, the activities received by the user are focused on the sports, and the interests of the user in other aspects are ignored, so that the user feels single, and the interest of participating in the activities is reduced.
In order to overcome the problems, the application provides a method and a system for generating a stranger social user portrait. Fig. 1 shows a flowchart of a method for generating a stranger social user representation according to an embodiment of the present application. As can be seen from fig. 1, the method for generating a stranger social user portrait according to the present embodiment may include the following steps:
s101: big data information of a current user is obtained, and the big data information comprises registration information, personal interest tag information and personal social activity information of the current user.
The method for generating the stranger social user portrait is mainly applied to a background server, the background server can be in communication connection with a plurality of intelligent terminals, and after the background server prefers the interest of the user, corresponding activities are pushed to the user through the intelligent terminals, so that the user participates in the pushed activities, and the social contact among the strangers is further achieved. The intelligent terminal in this embodiment may be, for example, a common smart phone, a tablet computer, a portable computer, and the like, an APP (application software) may be installed in the intelligent terminal, and a user may realize stranger social contact by registering an APP account. Specifically, the user can initiate an activity through the APP, and publish activity information, so that other users can obtain the activity information and further participate in the activity to realize social contact among strangers, and the user can also participate in activities initiated by other users to realize social contact among strangers. And after other users release the activity information, the background server acquires the corresponding activity type according to the activity information and pushes the activity to the user with the interest preference conforming to the activity type.
Firstly, a background server needs to acquire big data information of a current user, wherein the big data information comprises registration information, personal interest tag information and personal social activity information of the current user, so that interest preference of the current user is determined according to the acquired big data information of the current user. In this embodiment, the main source of the big data information of the current user acquired by the background server and the APP installed in the intelligent terminal of the current user, where the background server is a background server corresponding to the APP. The big data information includes registration information of the current user, such as a user name, a gender, a birth year and month, a residence and personal hobbies, personal interest tag information, such as sports, food, music, and the like, the personal interest tag information in this embodiment may be an evaluation tag of another user to the current user, or an evaluation tag for the current user that is automatically generated by a background server according to an activity type of an activity in which the current user participates, and personal social activity information, and the personal social activity information in this embodiment may be activity information of a social activity initiated by the current user and/or activity information of a social activity in which the current user participates and/or activity information of a social activity in which the current user pays attention.
S102: and extracting interest preference of the current user from the big data information, and generating a corresponding feature vector according to the interest preference.
In this embodiment, after the big data information of the current user is obtained, the registration information, the personal interest tag information, and the personal social activity information of the current user, which are included in the big data information, may be analyzed, and the types of the interest preferences of the current user and the statistics of each type, which are represented by the information, may be determined. For example, if the personal preference in the registration information of the current user is sports, the user may determine that the type of the interest preference of the current user includes sports, and the statistic of sports is 1, and if the personal interest tag information includes "sports, food, music, sports, music", then the type of the interest preference of the current user may also include food and music, the statistic of food is 1, the statistic of music is 2, and the personal social activity information is: "the number of times of initiating and participating in sports-like social activities is 3", "the number of times of initiating and participating in gourmet-like social activities is 5", "the number of times of initiating and participating in music-like social activities is 2", "the number of times of regarding favorite sports-like social activities is 5", "the number of times of regarding favorite gourmet-like social activities is 7", "the number of times of regarding favorite music-like social activities is 3", the big data information may be integrated into the feature vector of the interest preference of the current user, and the detailed description is given on how to integrate into the feature vector by taking the above example as an example, in the above example, the types of interest preference of the current user include three types of sports, gourmet, and music, and it can be determined statistically that the statistic of sports is 11, the statistic of gourmet is 14, the statistic of music is 7, the generated feature vector is (sports 11, gourmet 14, music 7). The embodiment is only an exemplary illustration of how to generate the feature vector, and should not be understood as a limitation of the technical solution of the present application. In addition, the types of the interest preferences of the current user may also include other types, which are not listed one by one, and when determining the types of the interest preferences of the current user represented by the information, because the interest preferences of the same type have different expression modes in the information, the method of the embodiment of the application may classify the data information of the same type having different expression modes into one type when determining the interest preferences of the current user.
S103: and correcting the characteristic vector according to the type of the historical activities pushed to the current user to generate a corrected characteristic vector.
After generating the feature vector corresponding to the interest preference of the current user, in order to avoid that the activity type of the activity pushed to the user is too single due to pushing the activity information to the current user directly according to the feature vector, this embodiment corrects the feature vector according to the type of the historical activity pushed to the current user, and specifically, uses a weight vector (α)1，α2，α3，……，αk) For the feature vector (x)1，x2，x3，……，xk) Correction is performed to generate a corrected feature vector (alpha)1x1，α2x2，α3x3，……，αkxk) In which α is1+α2+α3+……+αk=1，α1，α2，α3，……，αkThe value of (a) is inversely related to the accumulated number of each type of historical activities pushed to the current user, i.e. the more the accumulated number of the corresponding type of historical activities pushed to the current user is, the corresponding alpha isnThe smaller the value of (a), so as to avoid too single an activity type of the activity pushed to the user, where n =1,2,3.
S104: and pushing the activity information of the current activity related to the interest preference in the corrected feature vector to the current user according to a preset condition.
After generating the modified feature vector corresponding to the interest preference of the current user, the activity information of the current activity related to the interest preference in the modified feature vector may be pushed to the current user according to a preset condition, for example, the activity information of the current activity related to the interest preference with the largest specific gravity value in the modified feature vector is pushed to the current user. I.e. the largest mean value of the correction vectorsnxnAnd pushing the current activity related to the corresponding interest preference to the current user.
According to the method for generating the stranger social user portrait, activities can be pushed to the user according to multiple interests of the user, the situation that the types of the activities pushed to the user are too single is avoided, the interest of the user in participating in the activities is improved, the user experience is improved, and the development of stranger social is facilitated.
Fig. 2 is a flowchart of a method for generating a stranger social user representation according to a second embodiment of the present application. As can be seen from fig. 2, the method for generating a stranger social user profile of the present embodiment may include the following steps:
s201: big data information of a current user is obtained, and the big data information comprises registration information, personal interest tag information and personal social activity information of the current user.
In this embodiment, the background server needs to acquire big data information of the current user, where the big data information includes registration information of the current user, personal interest tag information, and personal social activity information, so as to analyze and determine interest preference of the current user according to the acquired big data information of the current user. In this embodiment, the main source of the big data information of the current user acquired by the background server and the APP installed in the intelligent terminal of the current user, where the background server is a background server corresponding to the APP. The big data information includes registration information of the current user, such as a user name, a gender, a birth year and month, a residence and personal hobbies, personal interest tag information, such as sports, food, music, and the like, the personal interest tag information in this embodiment may be an evaluation tag of another user to the current user, or an evaluation tag for the current user that is automatically generated by a background server according to an activity type of an activity in which the current user participates, and personal social activity information, and the personal social activity information in this embodiment may be activity information of a social activity initiated by the current user and/or activity information of a social activity in which the current user participates and/or activity information of a social activity in which the current user pays attention.
S202: and extracting interest preference of the current user from the big data information, and generating a corresponding feature vector according to the interest preference.
In this embodiment, after the big data information of the current user is obtained, the registration information, the personal interest tag information, and the personal social activity information of the current user, which are included in the big data information, may be analyzed, and the types of the interest preferences of the current user and the statistics of each type, which are represented by the information, may be determined.
S203: using weight vectors (alpha)1，α2，α3，……，αk) For the feature vector (x)1，x2，x3，……，xk) Correction is performed to generate a corrected feature vector (alpha)1x1，α2x2，α3x3，……，αkxk）。
After generating the feature vector corresponding to the interest preference of the current user, in order to avoid that the activity type of the activity pushed to the user is too single due to pushing the activity information to the current user directly according to the feature vector, this embodiment corrects the feature vector according to the type of the historical activity pushed to the current user, and specifically, uses a weight vector (α)1，α2，α3，……，αk) For the feature vector (x)1，x2，x3，……，xk) Correction is performed to generate a corrected feature vector (alpha)1x1，α2x2，α3x3，……，αkxk) In which α is1+α2+α3+……+αk=1，α1，α2，α3，……，αkThe value of (a) is inversely related to the accumulated number of each type of historical activities pushed to the current user, i.e. the more the accumulated number of the corresponding type of historical activities pushed to the current user is, the corresponding alpha isnThe smaller the value of (a), so as to avoid too single an activity type of the activity pushed to the user, where n =1,2,3.
S204: and pushing the activity information of the current activity related to the interest preference in the corrected feature vector to the current user according to a preset condition.
S205: and storing the activity information of the current activity pushed to the current user, and updating the pre-stored accumulated quantity of each type of historical activity pushed to the current user according to the activity information.
In this embodiment, after the background server obtains the big data information of the current user and generates the corresponding correction vector, the pre-stored push may be further pushed to the post according to the activity informationAnd updating the accumulated quantity of each type of historical activities of the current user. Classifying the pushed activity information of the current activity into the accumulated number of the historical activities, and weighting the vector (alpha)1，α2，α3，……，αk) Correction parameter α innAn update is made, where n =1,2,3.
According to the method for generating the stranger social user portrait, activities can be pushed to the user according to multiple interests of the user, the situation that the types of the activities pushed to the user are too single is avoided, the interest of the user in participating in the activities is improved, the user experience is improved, and the development of stranger social is facilitated.
As an alternative embodiment of the present application, in the above embodiment, the utilization weight vector (α) is1，α2，α3，……，αk) For the feature vector (x)1，x2，x3，……，xk) Correction is performed to generate a corrected feature vector (alpha)1x1，α2x2，α3x3，……，αkxk) The method comprises the following steps:
reducing the modified feature vector (alpha)1x1，α2x2，α3x3，……，αkxk) Middle dimension alpha with the largest specific gravity valuenxnCorrection parameter α innAnd (3) averaging the values of the other correction parameters to generate a corrected feature vector after the correction parameters are changed, wherein n =1,2,3.. k.
As another alternative embodiment of the present application, in the above embodiment, the use of the weight vector (α)1，α2，α3，……，αk) For the feature vector (x)1，x2，x3，……，xk) Correction is performed to generate a corrected feature vector (alpha)1x1，α2x2，α3x3，……，αkxk) The method also comprises the following steps:
reducing the modified feature vector (alpha)1x1，α2x2，α3x3，……，αkxk) Middle dimension alpha with the largest specific gravity valuenxnCorrection parameter α innIncreasing the modified feature vector (α)1x1，α2x2，α3x3，……，αkxk) The value of the correction parameter in the dimension with the second largest value of the medium specific gravity generates a corrected feature vector after the correction parameter is changed, wherein n =1,2,3.. k.
As a further alternative embodiment of the present application, in the above embodiment, the utilization weight vector (α) is1，α2，α3，……，αk) For the feature vector (x)1，x2，x3，……，xk) Correction is performed to generate a corrected feature vector (alpha)1x1，α2x2，α3x3，……，αkxk) The method comprises the following steps:
reducing the modified feature vector (alpha)1x1，α2x2，α3x3，……，αkxk) Middle dimension alpha with the largest specific gravity valuenxnCorrection parameter α innAnd increasing the value of the correction parameter of the corresponding dimension in the correction feature vector according to the activity of the user to participate or pay attention to, and generating the correction feature vector after the correction parameter is changed, wherein n =1,2,3.
Fig. 3 is a schematic structural diagram of a system for generating a stranger social user representation according to a third embodiment of the present application. The system for generating the stranger social user portrait comprises the following steps:
the big data information obtaining module 301 is configured to obtain big data information of a current user, where the big data information includes registration information of the current user, personal interest tag information, and personal social activity information.
A feature vector generation module 302, configured to extract interest preferences of the current user from the big data information, and generate a corresponding feature vector according to the interest preferences.
A modified feature vector generation module 303, configured to modify the feature vector according to the type of the historical activity pushed to the current user, and generate a modified feature vector.
Specifically, the modified feature vector generation module 303 is configured to modify the feature vector (x 1, x2, x3, … …, xk) by using a weight vector (α 1, α 2, α 03, … …, α 1 k) to generate a modified feature vector (α 21x1, α 32x2, α 43x3, … …, α 5 kxk), where a value of α 61+ α 2+ α 3+ … … + α k =1, α 1, α 2, α 3, … …, α k is inversely related to the cumulative number of each type of historical activities pushed to the current user. Optionally, reducing the modified feature vector (α)1x1，α2x2，α3x3，……，αkxk) Middle dimension alpha with the largest specific gravity valuenxnCorrection parameter α innAnd (3) averaging the values of the other correction parameters to generate a corrected feature vector after the correction parameters are changed, wherein n =1,2,3.. k. Or, reducing the modified feature vector (α)1x1，α2x2，α3x3，……，αkxk) Correction parameter alpha in dimension alpha nxn with maximum specific gravity valuenIncreasing the modified feature vector (α)1x1，α2x2，α3x3，……，αkxk) The value of the correction parameter in the dimension with the second largest value of the medium specific gravity generates a corrected feature vector after the correction parameter is changed, wherein n =1,2,3.. k. Or reducing the modified feature vector (alpha)1x1，α2x2，α3x3，……，αkxk) Middle dimension alpha with the largest specific gravity valuenxnCorrection parameter α innAccording to user selection to participate or shut offNote that the positive activity increases the value of the correction parameter of the corresponding dimension in the correction feature vector, and generates a correction feature vector after the correction parameter is changed, where n =1,2,3.. k.
And the activity information pushing module 304 is configured to push, according to a preset condition, activity information of a current activity related to the interest preference in the modified feature vector to the current user.
In addition, the system for generating a stranger social user representation according to the embodiment may further include:
and the storage module is used for storing the activity information of the current activity pushed to the current user and updating the pre-stored accumulated quantity of each type of historical activity pushed to the current user according to the activity information.
The system for generating the stranger social user portrait in the embodiment of the application can achieve the technical effects similar to those of the method embodiment, and the details are not repeated here.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the invention. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.
Claims (5)
1. A stranger social user portrait generation method is characterized by comprising the following steps:
acquiring big data information of a current user through a stranger social APP installed and registered by the current user, wherein the big data information comprises registration information of the current user, personal interest tag information and personal social activity information; the registration information of the current user comprises a user name, gender, birth year and month, residence and personal hobbies; the personal interest label information is an evaluation label of other users for the current user, and the evaluation label aiming at the current user is automatically generated by the background server according to the activity type of the activity in which the current user participates; the personal social activity information is activity information of a social activity initiated by the current user and/or activity information of a social activity in which the current user participates and/or activity information of a social activity in which the current user is interested in liking;
extracting interest preference of the current user from the big data information, and generating a corresponding feature vector according to the interest preference;
correcting the characteristic vector according to the type of the historical activities pushed to the current user to generate a corrected characteristic vector;
pushing the activity information of the current activity related to the interest preference in the corrected feature vector to the current user according to a preset condition;
wherein, the modifying the feature vector by using the weight vector to generate a modified feature vector comprises:
using weight vectors (alpha)1，α2，α3，……，αk) For the feature vector (x)1，x2，x3，……，xk) Correction is performed to generate a corrected feature vector (alpha)1x1，α2x2，α3x3，……，αkxk) In which α is1+α2+α3+……+αk=1，α1，α2，α3，……，αkIs inversely related to the cumulative number of each type of historical activity pushed to the current user; wherein, the more the accumulated number of the historical activities of the corresponding class pushed to the current user is, the corresponding alpha isnThe smaller the value of (c);
the utilization weight vector (alpha)1，α2，α3，……，αk) For the feature vector (x)1，x2，x3，……，xk) Correction is performed to generate a corrected feature vector (alpha)1x1，α2x2，α3x3，……，αkxk) The method specifically comprises the following steps:
reducing the modified feature vector (alpha)1x1，α2x2，α3x3，……，αkxk) Middle dimension alpha with the largest specific gravity valuenxnCorrection parameter α innThe values of other correction parameters are averagely increased to generate a correction feature vector after the correction parameters are changed, wherein n =1,2,3.. k; or, reducing the modified feature vector (α)1x1，α2x2，α3x3，……，αkxk) Middle dimension alpha with the largest specific gravity valuenxnCorrection parameter α innIncreasing the modified feature vector (α)1x1，α2x2，α3x3，……，αkxk) Generating a modified feature vector after modification of the modification parameters by using the values of the modification parameters in the dimension with the second largest medium specific gravity value, wherein n =1,2,3.. k; or, reducing the modified feature vector (α)1x1，α2x2，α3x3，……，αkxk) Middle dimension alpha with the largest specific gravity valuenxnCorrection parameter α innAnd increasing the value of the correction parameter of the corresponding dimension in the correction feature vector according to the activity of the user to participate or pay attention to, and generating the correction feature vector after the correction parameter is changed, wherein n =1,2,3.
2. The method of claim 1, further comprising:
and storing the activity information of the current activity pushed to the current user, and updating the pre-stored accumulated quantity of each type of historical activity pushed to the current user according to the activity information.
3. The method according to claim 2, wherein the pushing, according to a preset condition, activity information of a current activity related to interest preference in the modified feature vector to the current user comprises:
and pushing the activity information of the current activity related to the interest preference with the largest specific gravity value in the corrected feature vector to the current user.
4. A system for generating a stranger social user representation, comprising:
the big data information acquisition module is used for acquiring big data information of a current user through a stranger social APP installed and registered by the current user, wherein the big data information comprises registration information of the current user, personal interest tag information and personal social activity information; the registration information of the current user comprises a user name, gender, birth year and month, residence and personal hobbies; the personal interest label information is an evaluation label of other users for the current user, and the evaluation label aiming at the current user is automatically generated by the background server according to the activity type of the activity in which the current user participates; the personal social activity information is activity information of a social activity initiated by the current user and/or activity information of a social activity in which the current user participates and/or activity information of a social activity in which the current user is interested in liking;
the characteristic vector generation module is used for extracting interest preference of the current user from the big data information and generating a corresponding characteristic vector according to the interest preference;
the corrected feature vector generating module is used for correcting the feature vector according to the type of the historical activities pushed to the current user to generate a corrected feature vector;
the activity information pushing module is used for pushing the activity information of the current activity related to the interest preference in the corrected feature vector to the current user according to a preset condition;
the modified feature vector generation module is used for utilizing a weight vector (alpha)1，α2，α3，……，αk) For the feature vector (x)1，x2，x3，……，xk) Correction is performed to generate a corrected feature vector (alpha)1x1，α2x2，α3x3，……，αkxk) In which α is1+α2+α3+……+αk=1，α1，α2，α3，……，αkIs inversely related to the cumulative number of each type of historical activity pushed to the current user; wherein, the more the accumulated number of the historical activities of the corresponding class pushed to the current user is, the corresponding alpha isnThe smaller the value of (c); wherein the modified feature vector (α) is reduced1x1，α2x2，α3x3，……，αkxk) Middle dimension alpha with the largest specific gravity valuenxnCorrection parameter α innThe values of other correction parameters are averagely increased to generate a correction feature vector after the correction parameters are changed, wherein n =1,2,3.. k; or, reducing the modified feature vector (α)1x1，α2x2，α3x3，……，αkxk) Correction parameter alpha in dimension alpha nxn with maximum specific gravity valuenIncreasing the modified feature vector (α)1x1，α2x2，α3x3，……，αkxk) Generating a modified feature vector after modification of the modification parameters by using the values of the modification parameters in the dimension with the second largest medium specific gravity value, wherein n =1,2,3.. k; or, reducing the modified feature vector (α)1x1，α2x2，α3x3，……，αkxk) Middle dimension alpha with the largest specific gravity valuenxnCorrection parameter α innAnd increasing the value of the correction parameter of the corresponding dimension in the correction feature vector according to the activity of the user to participate or pay attention to, and generating the correction feature vector after the correction parameter is changed, wherein n =1,2,3.
5. The system of claim 4, further comprising:
and the storage module is used for storing the activity information of the current activity pushed to the current user and updating the pre-stored accumulated quantity of each type of historical activity pushed to the current user according to the activity information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811182324.6A CN109408735B (en) | 2018-10-11 | 2018-10-11 | Stranger social user portrait generation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811182324.6A CN109408735B (en) | 2018-10-11 | 2018-10-11 | Stranger social user portrait generation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109408735A CN109408735A (en) | 2019-03-01 |
| CN109408735B true CN109408735B (en) | 2021-06-25 |
Family
ID=65466982
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811182324.6A Active CN109408735B (en) | 2018-10-11 | 2018-10-11 | Stranger social user portrait generation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109408735B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111552865A (en) * | 2020-03-31 | 2020-08-18 | 深圳壹账通智能科技有限公司 | User interest portrait method and related equipment |
| CN111931107B (en) * | 2020-07-31 | 2024-03-22 | 博泰车联网科技(上海)股份有限公司 | Digital citizen system construction method, system and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104036038A (en) * | 2014-06-30 | 2014-09-10 | 北京奇虎科技有限公司 | News recommendation method and system |
| CN104731861A (en) * | 2015-02-05 | 2015-06-24 | 腾讯科技（深圳）有限公司 | Method and device for pushing multimedia data |
| CN105005587A (en) * | 2015-06-26 | 2015-10-28 | 深圳市腾讯计算机系统有限公司 | User portrait updating method, apparatus and system |
| CN107729569A (en) * | 2017-11-17 | 2018-02-23 | 杭州师范大学 | A kind of social networks Forecasting Methodology of UNE structure and text message |
| CN107885889A (en) * | 2017-12-13 | 2018-04-06 | 聚好看科技股份有限公司 | Feedback method, methods of exhibiting and the device of search result |
| CN108256093A (en) * | 2018-01-29 | 2018-07-06 | 华南理工大学 | A kind of Collaborative Filtering Recommendation Algorithm based on the more interest of user and interests change |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102831234B (en) * | 2012-08-31 | 2015-04-22 | 北京邮电大学 | Personalized news recommendation device and method based on news content and theme feature |
| JP2018170568A (en) * | 2017-03-29 | 2018-11-01 | ブラザー工業株式会社 | Image processing apparatus, control program, and communication system |
-
2018
- 2018-10-11 CN CN201811182324.6A patent/CN109408735B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104036038A (en) * | 2014-06-30 | 2014-09-10 | 北京奇虎科技有限公司 | News recommendation method and system |
| CN104731861A (en) * | 2015-02-05 | 2015-06-24 | 腾讯科技（深圳）有限公司 | Method and device for pushing multimedia data |
| CN105005587A (en) * | 2015-06-26 | 2015-10-28 | 深圳市腾讯计算机系统有限公司 | User portrait updating method, apparatus and system |
| CN107729569A (en) * | 2017-11-17 | 2018-02-23 | 杭州师范大学 | A kind of social networks Forecasting Methodology of UNE structure and text message |
| CN107885889A (en) * | 2017-12-13 | 2018-04-06 | 聚好看科技股份有限公司 | Feedback method, methods of exhibiting and the device of search result |
| CN108256093A (en) * | 2018-01-29 | 2018-07-06 | 华南理工大学 | A kind of Collaborative Filtering Recommendation Algorithm based on the more interest of user and interests change |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109408735A (en) | 2019-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8965828B2 (en) | Inferring user mood based on user and group characteristic data | |
| US8631122B2 (en) | Determining demographics based on user interaction | |
| US20170186045A1 (en) | Content ranking and serving on a multi-user device or interface | |
| US11538051B2 (en) | Machine learning-based generation of target segments | |
| US20190068526A1 (en) | Methods and systems for helper bot platform assistance | |
| US9253282B2 (en) | Method and apparatus for generating, using, or updating an enriched user profile | |
| Bilogrevic et al. | A machine-learning based approach to privacy-aware information-sharing in mobile social networks | |
| US20160063560A1 (en) | Accelerating engagement of potential buyers based on big data analytics | |
| AU2017204022A1 (en) | Cognitive relevance targeting in a social networking system | |
| US9582811B2 (en) | Active time spent optimization and reporting | |
| US20150324857A1 (en) | Cross-platform advertising systems and methods | |
| US20130138514A1 (en) | Advertisements with multiple targeting criteria bids | |
| US20190095868A1 (en) | Methods and systems for converting unstructured text into structured job postings | |
| US20160275533A1 (en) | Segment Membership Determination for Content Provisioning | |
| CN108900924A (en) | The method and apparatus of commending friends in direct broadcasting room | |
| JP2018120461A (en) | Extraction equipment, extraction method and extraction program | |
| US20160277538A1 (en) | Method and system for matching profile records | |
| US20170352044A1 (en) | Method and system for evaluating reliability based on analysis of user activities on social medium | |
| US10991013B2 (en) | Presentation of media content based on computing device context | |
| CN109408735B (en) | Stranger social user portrait generation method and system | |
| JPWO2016002133A1 (en) | Prediction system and prediction method | |
| US20150066652A1 (en) | System and method for dynamic cross-platform allocation of third-party content | |
| CN113454669A (en) | Characterizing a place by user visited features | |
| CN113127723B (en) | User portrait processing method, device, server and storage medium | |
| CN109241202B (en) | Stranger social user matching method and system based on clustering |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |