CN114925265A - User portrait group acquisition method, system, equipment and computer readable storage medium based on group behaviors - Google Patents
User portrait group acquisition method, system, equipment and computer readable storage medium based on group behaviors Download PDFInfo
- Publication number
- CN114925265A CN114925265A CN202210300173.XA CN202210300173A CN114925265A CN 114925265 A CN114925265 A CN 114925265A CN 202210300173 A CN202210300173 A CN 202210300173A CN 114925265 A CN114925265 A CN 114925265A
- Authority
- CN
- China
- Prior art keywords
- user
- group
- behavior
- users
- portrait
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a user portrait group acquisition method, a system, equipment and a computer readable storage medium based on group behaviors. The user portrait group obtaining method obtains a similar group corresponding to each user based on the operation behavior portrait of the user, and further obtains the corresponding user portrait group according to the similar group with different precision thresholds. Through the technical scheme that this application provided, can carry out the accurate drawing and portrait group's acquirement through the crowd action to the user action, this technical scheme has all established a similar user group for every user, and then realize the automatic classification and the acquisition of user drawing group through setting up different aggregate precision thresholds, it is accurate to have the drawing, aggregate precision adjustable advantage, can obtain all kinds of user drawings that the precision is different according to the precision demand of difference, agree with the user drawing demand in fields such as product design, content recommendation, but have spreading value.
Description
Technical Field
The invention relates to the technical field of big data analysis, and particularly discloses a user portrait group acquisition method, a system and equipment based on group behaviors and a computer readable storage medium.
Background
User portrayal is a link which is crucial to product development. With accurate user portrayal, the service can be provided for the user in a targeted way. The user portrait of the traditional software product is that a product manager self-establishes a plurality of user types, and classifies users into one user type according to the data filled by the users and the behaviors of the users. The user portrait created by a traditional product manager is often too rough in type. Therefore, thousands of user figures are developed, and personalized content recommendation is realized by adopting behavior data of the user and model reasoning. The completely individualized user portrait of thousands of people is often difficult to carry out corresponding product design for a single new user, and only the related content can be searched for and recommended to the user aiming at the user behavior which has already occurred to the user, and the content recommended to the user is often too high in homogeneity and uneven in quality, so that the user sinks deeply into the information cocoon house.
Disclosure of Invention
In order to solve the above problems in the prior art, the present invention provides a user portrait group acquisition method, system, device and computer readable storage medium based on group behaviors.
In a first aspect of the present application, a method for obtaining a user portrait group based on group behaviors is provided, which specifically includes the following steps:
acquiring an operation behavior portrait of a user according to a historical operation behavior log of the user;
acquiring a similar group corresponding to each user according to the operation behavior portrait of all users;
sequencing the similar groups in sequence from at least one according to the number of users contained in the similar groups;
performing cyclic operation on the similar groups according to the sorting to obtain a plurality of user portrait groups corresponding to all users, wherein:
setting similar groups corresponding to groups containing n users as G1, G2, … … and Gn respectively, and corresponding user portrait groups as R1, R2, … … and Rm, wherein n and m are non-zero natural numbers and m is less than or equal to n, then the acquisition process of the user portrait groups R1, R2 and … … specifically comprises the following steps:
step S1, setting constant value i equal to 1, j equal to 2;
step S2, let R1 be G1;
step S3, acquiring behavior deviation degrees D1, D2, … … and Di of R1, R2 and Gj;
step S4, acquiring the minimum value in the behavior deviation degrees and setting the behavior deviation degree corresponding to the minimum value as Dx;
step S5, obtaining a user portrait group Rx corresponding to the behavior deviation degree Dx, and determining whether the number of users in the user portrait group Rx is greater than a first preset threshold: if yes, go to step S6, otherwise go to step S7;
step S6, if j is less than or equal to n, making i equal to i +1, j equal to j +1, Ri equal to Gj, and then returning to step S3;
in step S7, when j is smaller than or equal to n, let the user image group Rx be the union of the user image group Rx and the similar group Gj, and let j be j +1, and then return to step S3.
In a possible implementation of the first aspect, in obtaining the operation behavior representation according to the historical operation behavior log, the method further includes:
presetting a plurality of function points, wherein each function point corresponds to one function operation;
acquiring the operation times of a user on the function point;
and taking a user behavior vector formed by the operation times corresponding to all the functional points as an operation behavior portrait.
In a possible implementation of the first aspect, in the process of obtaining the similar group corresponding to each user according to the operation behavior representation of all users, the method further includes:
aiming at the selected user, acquiring the standard deviation of the user behavior vectors of the selected user and the rest users in the whole users;
obtaining the remaining users with the standard deviation smaller than a second preset threshold value as similar groups corresponding to the selected users;
and repeating the steps until the traversal of all the users is completed.
In a possible implementation of the first aspect, in the process of sequentially ranking the similar groups by at least according to the number of users included in the similar groups, the similar groups are randomly ranked in the case that there is a coincidence in the number of users included in the similar groups.
In a possible implementation of the first aspect, the first preset threshold is positively correlated with a blur degree of the user image group;
the larger the value of the first preset threshold is, the more the number of users contained in a single user portrait group is, and the more fuzzy the user portrait corresponding to the user portrait group is.
A second aspect of the present application provides a user portrait group acquisition system based on group behaviors, which is applied to the user portrait group acquisition method based on group behaviors provided by the first aspect, and includes:
the behavior acquisition unit is used for acquiring an operation behavior portrait of the user according to a historical operation behavior log of the user;
the clustering unit is used for acquiring a similar cluster corresponding to each user according to the operation behavior portrait of all users;
the sequencing unit is used for sequencing the similar groups in sequence from at least one to more according to the number of users contained in the similar groups;
and the user portrait unit is used for performing cyclic operation on the similar groups according to the sorting to obtain a plurality of user portrait groups corresponding to all the users, wherein:
setting similar groups corresponding to groups containing n users as G1, G2, … … and Gn respectively, and corresponding user portrait groups as R1, R2, … … and Rm, wherein n and m are non-zero natural numbers and m is less than or equal to n, the acquisition process of the user portrait groups R1, R2, … … and Rm specifically comprises the following steps:
step S1, setting constant value i equal to 1, j equal to 2;
step S2, let R1 be G1;
step S3, acquiring behavior deviation degrees D1, D2, … … and Di of R1, R2.
Step S4, acquiring the minimum value in the behavior deviation degrees and setting the behavior deviation degree corresponding to the minimum value as Dx;
step S5, obtaining a user portrait group Rx corresponding to the behavior deviation degree Dx, and determining whether the number of users in the user portrait group Rx is greater than a first preset threshold: if yes, go to step S6, otherwise go to step S7;
step S6, if j is less than or equal to n, making i equal to i +1, j equal to j +1, Ri equal to Gj, and then returning to step S3;
in step S7, when j is smaller than or equal to n, let the user image group Rx be the union of the user image group Rx and the similar group Gj, and let j be j +1, and then return to step S3.
In a possible implementation of the second aspect, in the behavior acquisition unit, the method further includes:
the setting module is used for presetting a plurality of function points, and each function point corresponds to one function operation;
the acquisition module is used for acquiring the operation times of the user on the function points;
a generation module for using the user behavior vector composed of the operation times corresponding to all the function points as the operation behavior portrait
In a possible implementation of the second aspect, in the clustering unit, the method further includes:
the calculation module is used for acquiring the standard deviation of the user behavior vectors of the selected user and the rest users in the whole users aiming at the selected user;
and the judging module is used for acquiring the remaining users corresponding to the standard deviation smaller than the second preset threshold value as the similar group corresponding to the selected user.
A third aspect of the present application provides a user portrait group acquisition apparatus based on group behaviors, including:
a memory for storing a computer program;
a processor, configured to implement the group behavior-based user representation group acquisition method provided in the foregoing first aspect when executing the computer program.
A fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method for obtaining a user portrait group based on group behaviors, as provided in the first aspect, is implemented.
Compared with the prior art, the method has the following beneficial effects:
through the technical scheme that this application provided, can carry out the acquirement of accurate portrayal and portrait group through the group action to user's action, this technical scheme has all established a similar user group for every user, and then realize the automatic classification and the acquisition of user portrayal group through setting up different polymerization precision thresholds, it is accurate to have portrayal, the advantage of polymerization precision adjustable, can obtain all kinds of user portrayals that the precision is different according to the precision demand of difference, agree with the user portrayal demand in fields such as product design, content recommendation, but have spreading value.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a schematic flow chart diagram illustrating a method for capturing a user portrait group based on group behaviors according to an embodiment of the present application;
FIG. 2 is a schematic flow chart illustrating a process for obtaining a user image population according to an embodiment of the present application;
FIG. 3 is a schematic diagram illustrating a process of obtaining an operation behavior representation from a historical operation behavior log according to an embodiment of the present application;
FIG. 4 is a schematic flow chart illustrating a process of obtaining similar groups corresponding to each user according to the operation behavior portraits of all users according to an embodiment of the present application;
FIG. 5 is a schematic diagram illustrating a user representation group capture system based on group behaviors, according to an embodiment of the present application;
FIG. 6 is a schematic diagram illustrating an exemplary architecture of a user representation group capture device based on group behaviors, according to an embodiment of the present disclosure;
fig. 7 shows a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present application.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that it would be obvious to those skilled in the art that various changes and modifications can be made without departing from the spirit of the invention. All falling within the scope of the present invention.
The term "include" and variations thereof as used herein is meant to be inclusive in an open-ended manner, i.e., "including but not limited to". The term "or" means "and/or" unless specifically stated otherwise. The term "based on" means "based at least regionally. The terms "one example embodiment" and "one embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first," "second," and the like may refer to different or the same objects. Other explicit and implicit definitions are also possible below.
Aiming at the practical problems that the precision of a user portrait cannot be freely regulated and controlled and the precision is low in the prior art, the application provides a user portrait group acquisition method, a system, equipment and a computer readable storage medium based on group behaviors. Through the technical scheme provided by the application, various user figures with different precisions are obtained according to different precision requirements, the user figure requirements in the fields of product design, content recommendation and the like are met, and the method and the device have popularization value. The technical solutions provided in the present application will be illustrated and described below with reference to examples.
In some embodiments of the present application, fig. 1 shows a flow chart of a user portrait group acquisition method based on group behaviors, and specifically, the measuring method specifically includes the following steps:
step 101: and acquiring the operation behavior portrait of the user according to the historical operation behavior log of the user.
Step 102: and acquiring a similar group corresponding to each user according to the operation behavior portrait of the whole users.
Step 103: the similar groups are ordered in turn by at least according to the number of users contained in the similar groups.
Step 104: and performing cyclic operation on the similar groups according to the sequence to obtain a plurality of user portrait groups corresponding to all the users.
Specifically, fig. 2 shows a schematic flow chart of acquiring user image populations, where the similar populations corresponding to the population containing n users are set as G1, G2, … …, Gn, and the corresponding user image populations are set as R1, R2, … …, Rm, where n, m are non-zero natural numbers and m is less than or equal to n, the acquiring process of the user image populations R1, R2, … …, Rm may include as shown in fig. 2:
in step S104a, a constant value i is set to 1 and j is set to 2.
In step S104b, R1 is G1.
Step S104c, obtaining behavior deviation degrees D1, D2, … … and Di of R1, R2.
In step S104d, the minimum value of the behavior deviation degrees is acquired and the behavior deviation degree corresponding to the minimum value is set to Dx.
Step S104e, obtaining a user portrait group Rx corresponding to the behavior deviation degree Dx, and determining whether the number of users in the user portrait group Rx is greater than a first preset threshold: if so, the process goes to step S6, otherwise, the process goes to step S7.
In step S104f, if j is smaller than or equal to n, i is equal to i +1, j is equal to j +1, and Ri is equal to Gj, and then the process returns to step S104 c.
In step S104g, when j is less than or equal to n, the user image group Rx is made to be a union of the user image group Rx and the similar group Gj, and j is made to be j +1, and then the process returns to step S104 c.
Through the steps 101 to 104, accurate acquisition of a user portrait group can be realized, which will be described below
In some embodiments of the present application, fig. 3 shows a schematic flowchart of obtaining an operation behavior representation according to a historical operation behavior log, which may specifically include:
step 301: a plurality of function points are preset, and each function point corresponds to one function operation.
Step 302: and acquiring the operation times of the user on the function point.
Step 303: and using the user behavior vector formed by the operation times corresponding to all the functional points as an operation behavior portrait.
In the above embodiment, various behaviors of the user using the software may be collected to serve as the operation behavior portrait of the user, and specifically, some function points may be set in the software product, when the user operates a certain function of the software product, the background may collect corresponding data information, and further, the user behavior vector may be obtained by counting the operation times of each user on each function point. For example, for three statistical function points, if a user operates 100 times on the first function point, 50 times on the second function point, and 200 times on the third function point, the user behavior vector of the user may be (100, 50, 200).
In some embodiments of the present application, fig. 4 is a schematic flowchart illustrating a process of obtaining a similar group corresponding to each user according to an operation behavior representation of all users, which may specifically include:
step 401: and aiming at the selected user, acquiring the standard deviation of the user behavior vectors of the selected user and the rest users in the whole users.
Step 402: and acquiring the remaining users corresponding to the standard deviation smaller than the second preset threshold value as the similar groups corresponding to the selected users.
Step 403: and repeating the steps until the traversal of all the users is completed.
In some embodiments of the present application, based on the setting of the user behavior vector, for a similar group, an average behavior vector corresponding to the similar group may be obtained in a weighted average manner. For example, for a similar group G ═ user a, user B, and user C, where the behavior vector of user a is (101,201,301), the behavior vector of user B is (100,200,300), and the behavior vector of user C is (99,199,299), then the average behavior vector of the similar group can be represented as ((101+100+99)/3, (201+200+199)/3, (301+300+299)/3) ═ 100,200, 300).
In the aforementioned step S3, the degrees of deviation D1, D2, … … and Di of behavior may be obtained by expressing the standard deviation values associated with the average behavior vector between the similar group and the group of user images to be confirmed, so as to obtain the degrees of deviation D1, D2, … … and Di of behavior.
In some embodiments of the present application, in the process of sequentially ranking similar groups by at least according to the number of users included in the similar groups, in the case that there is a consistency in the number of users included in several similar groups, several similar groups are arbitrarily ranked.
For example, in some embodiments of the present application, the total users may include three users, namely, user a, user B, and user C, where the similar group G1 of user a is { user B }, the similar group of user B is G2 is { user a, user C }, and the similar group of user C is G3 is { user B }, so that since the similar group G2 includes 2 users and the similar groups G1 and G3 both include 1 user, the final obtained ranking may be G2\ G1\ G3 or G2\ G3\ G1.
In some embodiments of the present application, in the step 104, the first predetermined threshold may be dynamically adjustable, and a value of the first predetermined threshold is positively correlated to a blur degree of the user portrait group. That is, the larger the value of the first preset threshold is, the larger the number of users included in a single user portrait group is, and the more blurred the user portrait corresponding to the user portrait group is.
It is understood that the user portrait groups R1, R2, … …, Rm are constructed according to a first preset threshold, and the degree of accuracy of the user portrait groups can be adjusted by adjusting the value of the first preset threshold. When the first preset threshold is obtained to be larger, the number of users contained in the obtained user portrait group is larger, and the corresponding user portrait is fuzzy; when the first preset threshold value is large enough, all users can be contained in one user portrait group, and m is 1, namely only one user portrait group; when the first preset threshold is sufficiently small, a case where m is equal to n, that is, one independent user corresponds to one user portrait, can be obtained.
In some embodiments of the present application, fig. 5 provides a user portrait group acquisition system based on group behaviors, which is applied in the user portrait group acquisition method based on group behaviors provided in the foregoing embodiments. Specifically, as shown in fig. 5, the user representation group acquiring system may include:
the behavior acquisition unit 001 is used for acquiring an operation behavior portrait of the user according to a historical operation behavior log of the user;
the clustering unit 002 is used for acquiring a similar cluster corresponding to each user according to the operation behavior portrait of the whole users;
a sorting unit 003 for sorting the similar groups in order by at least according to the number of users included in the similar groups;
a user portrait unit 004 for performing a cyclic operation on the similar groups according to the sorting to obtain a plurality of user portrait groups corresponding to all users, wherein: setting similar groups corresponding to groups containing n users as G1, G2, … … and Gn respectively, and corresponding user portrait groups as R1, R2, … … and Rm, wherein n and m are non-zero natural numbers and m is less than or equal to n, and then obtaining processes of the user portrait groups R1, R2, … … and Rm are shown in FIG. 2 specifically, and are not described herein.
In some embodiments of the application, further, in the behavior acquisition unit 001, the behavior acquisition unit further includes:
the setting module is used for presetting a plurality of function points, and each function point corresponds to one function operation;
the acquisition module is used for acquiring the operation times of the user on the function points;
a generation module for using the user behavior vector composed of the operation times corresponding to all the function points as the operation behavior portrait
In some embodiments of the present application, the clustering unit 002 further includes:
the calculation module is used for acquiring the standard deviation of the user behavior vectors of the selected user and the rest users in the whole users aiming at the selected user;
and the judging module is used for acquiring the remaining users corresponding to the standard deviation smaller than the second preset threshold value as the similar groups corresponding to the selected users.
It is understood that, in the above embodiment, the functions performed by the behavior acquisition unit 001 to the user image unit 004 are the same as the operations performed in steps 101 to 104 in the above embodiment, and are not repeated herein.
In some embodiments of the present application, there is also provided a user representation group acquisition device based on group behaviors, the device comprising:
a memory for storing a computer program;
and the processor is used for realizing the steps of the image correction method explained in the technical scheme of the application when executing the computer program.
It should be understood that aspects of the subject technology can be implemented as a system, method or program product. Accordingly, aspects of the present technology may be embodied in the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" platform.
FIG. 6 illustrates a block diagram of a user representation group capture device based on group behavior according to some embodiments of the present application. An electronic device 600 implemented according to an embodiment in the present embodiment is described in detail below with reference to fig. 6. The electronic device 600 shown in fig. 6 is only an example, and should not bring any limitation to the function and the application scope of any embodiment of the technical solution of the present application.
As shown in fig. 6, the electronic device 600 is embodied in the form of a general purpose computing device. The set-up of the electronic device 600 may include, but is not limited to: at least one processing unit 610, at least one memory unit 620, a bus 630 connecting the different platform components (including the memory unit 620 and the processing unit 610), a display unit 640, and the like.
Wherein the storage unit stores a program code, which can be executed by the processing unit 610, so that the processing unit 610 performs the implementation steps according to the present embodiment described in the above-mentioned image stitching method area in the present embodiment. For example, the processing unit 610 may perform the steps as shown in fig. 1 to 5.
The storage unit 620 may include readable media in the form of volatile memory units, such as a random access unit (RAM)6201 and/or a cache memory unit 6202, which may further include a read-only memory unit (ROM) 6203.
The memory unit 620 may also include a program/utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may comprise an implementation of a network environment.
The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 600, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 650. Also, the electronic device 600 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via the network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via the bus 630. It should be appreciated that although not shown in FIG. 6, other hardware and/or software modules may be used in conjunction with electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, to name a few.
In some embodiments of the present application, a computer-readable storage medium is further provided, where a computer program is stored on the computer-readable storage medium, and when executed by a processor, the computer program can implement the relevant steps of the group behavior-based user representation group obtaining method provided in the foregoing embodiments.
Although this embodiment does not exhaustively list other specific embodiments, in some possible embodiments, the aspects described in the present technical solution can also be implemented in the form of a program product, which includes program code for causing a terminal device to execute the steps according to the embodiments described in the various embodiments of the present technical solution in the area of the image stitching method in the present technical solution when the program product runs on the terminal device.
FIG. 7 illustrates a schematic structural diagram of a computer-readable storage medium according to some embodiments of the present application. As shown in fig. 7, a program product 800 for implementing the method according to the embodiment of the present disclosure is described, which may employ a portable compact disc read only memory (CD-ROM) and include program codes, and may be executed on a terminal device, such as a personal computer. Of course, the program product generated according to the embodiment is not limited thereto, and in the technical solution of the present application, the readable storage medium may be any tangible medium containing or storing the program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
A computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the C language or similar programming languages. The program code may execute entirely on the user's computing device, locally on the user's device, as a stand-alone software package, locally on the user's computing device, locally on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
In conclusion, according to the technical scheme provided by the application, the user behaviors can be accurately portrayed and portrayed through the group behaviors, a similar user group is established for each user, automatic classification and acquisition of the user portrayal group are further realized by setting different aggregation precision thresholds, the method has the advantages of portrayal precision and adjustable aggregation precision, various user portrayals with different precisions can be acquired according to different precision requirements, user portrayal requirements in the fields of product design, content recommendation and the like are met, and the method has popularization value.
The above description is only for describing the preferred embodiments of the present invention, and is not intended to limit the scope of the present invention, and any variations and modifications made by those skilled in the art based on the above disclosure are within the scope of the appended claims.
Claims (10)
1. A user portrait group obtaining method based on group behaviors is characterized by comprising the following steps:
acquiring an operation behavior portrait of a user according to a historical operation behavior log of the user;
acquiring a similar group corresponding to each user according to the operation behavior portrait of all users;
sequencing the similar groups in sequence from at least one according to the number of users contained in the similar groups;
performing cyclic operation on the similar groups according to the sorting to obtain a plurality of user portrait groups corresponding to all users, wherein:
setting similar groups corresponding to groups containing n users as G1, G2, … … and Gn respectively, and corresponding user portrait groups as R1, R2, … … and Rm, wherein n and m are non-zero natural numbers and m is less than or equal to n, then the acquisition process of the user portrait groups as R1, R2 and … … and Rm specifically comprises the following steps:
step S1, setting constant value i equal to 1, j equal to 2;
step S2, let R1 be G1;
step S3, acquiring behavior deviation degrees D1, D2, … … and Di of R1, R2 and Gj;
step S4, acquiring a minimum value of the behavior deviation degrees and setting the behavior deviation degree corresponding to the minimum value as Dx;
step S5, obtaining a user portrait group Rx corresponding to the behavior deviation degree Dx, and determining whether the number of users in the user portrait group Rx is greater than a first preset threshold: if yes, go to step S6, otherwise go to step S7;
a step S6, in case j is less than or equal to n, making i ═ i +1, j ═ j +1, Ri ═ Gj, and then returning to the step S3;
step S7, when j is less than or equal to n, let the user portrait group Rx be the union of the user portrait group Rx and the similar group Gj, and let j be j +1, and then return to step S3.
2. The group behavior-based user representation group acquisition method as claimed in claim 1, wherein in the process of acquiring the operation behavior representation according to the historical operation behavior log, the method further comprises:
presetting a plurality of function points, wherein each function point corresponds to one function operation;
acquiring the operation times of the user on the function point;
and taking a user behavior vector formed by the operation times corresponding to all the function points as the operation behavior portrait.
3. The method for capturing user representation group based on group behaviors as claimed in claim 2, wherein in the process of capturing similar group corresponding to each user according to the operation behavior representation of all users, further comprising:
for a selected user, obtaining a standard deviation of the user behavior vectors of the selected user and the remaining users in the total of users;
obtaining the remaining users corresponding to the standard deviation smaller than a second preset threshold value as the similar groups corresponding to the selected users;
and repeating the steps until the traversal of all the users is completed.
4. The method as claimed in claim 1, wherein in the process of sequentially ranking the similar groups by at least according to the number of users included in the similar groups, the similar groups are randomly ranked in the case that the number of users included in the similar groups is consistent.
5. The method of claim 1, wherein the first predetermined threshold is positively correlated to the blur level of the user representation group;
the larger the value of the first preset threshold is, the larger the number of the users contained in a single user portrait group is, and the more fuzzy the user portrait corresponding to the user portrait group is.
6. A user portrait group acquisition system based on group behaviors, which is applied to the user portrait group acquisition method based on group behaviors of any one of claims 1 to 7, and comprises:
the behavior acquisition unit is used for acquiring an operation behavior portrait of the user according to a historical operation behavior log of the user;
the clustering unit is used for acquiring a similar cluster corresponding to each user according to the operation behavior portrait of all users;
the sequencing unit is used for sequencing the similar groups in sequence from at least one to more according to the number of users contained in the similar groups;
the user portrait unit is used for performing cyclic operation on the similar groups according to the sorting to obtain a plurality of user portrait groups corresponding to all users, wherein:
setting similar groups corresponding to groups containing n users as G1, G2, … … and Gn respectively, and corresponding user portrait groups as R1, R2, … … and Rm, wherein n and m are non-zero natural numbers and m is less than or equal to n, the acquisition process of the user portrait groups R1, R2, … … and Rm specifically comprises the following steps:
step S1, setting constant value i equal to 1, j equal to 2;
step S2, let R1 be G1;
step S3, acquiring behavior deviation degrees D1, D2, … … and Di of R1, R2.
Step S4, acquiring the minimum value in the behavior deviation degrees and setting the behavior deviation degree corresponding to the minimum value as Dx;
step S5, obtaining a user portrait group Rx corresponding to the behavior deviation degree Dx, and determining whether the number of users in the user portrait group Rx is greater than a first preset threshold: if yes, go to step S6, otherwise go to step S7;
step S6, if j is less than or equal to n, making i equal to i +1, j equal to j +1, Ri equal to Gj, and then returning to step S3;
step S7, when j is less than or equal to n, let the user portrait group Rx be the union of the user portrait group Rx and the similar group Gj, and let j be j +1, and then return to step S3.
7. The population behavior based user representation population capture system of claim 6, wherein the behavior capture unit further comprises:
the setting module is used for presetting a plurality of function points, and each function point corresponds to one function operation;
the acquisition module is used for acquiring the operation times of the user on the function points;
and the generating module is used for taking a user behavior vector formed by the operation times corresponding to all the function points as the operation behavior portrait.
8. The group behavior-based user representation group capture system of claim 7, further comprising in the clustering unit:
a calculation module, configured to, for a selected user, obtain a standard deviation of the user behavior vectors of the selected user and remaining users in the entire users;
and the judging module is used for acquiring the remaining users corresponding to the standard deviation smaller than a second preset threshold value to serve as the similar group corresponding to the selected user.
9. A user portrait group acquisition device based on group behaviors, comprising:
a memory for storing a computer program;
a processor for implementing the group behavior based user representation group acquisition method as claimed in any one of claims 1 to 5 when executing the computer program.
10. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, implements the group behavior-based user representation group capture method as recited in any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210300173.XA CN114925265A (en) | 2022-03-25 | 2022-03-25 | User portrait group acquisition method, system, equipment and computer readable storage medium based on group behaviors |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210300173.XA CN114925265A (en) | 2022-03-25 | 2022-03-25 | User portrait group acquisition method, system, equipment and computer readable storage medium based on group behaviors |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114925265A true CN114925265A (en) | 2022-08-19 |
Family
ID=82805412
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210300173.XA Pending CN114925265A (en) | 2022-03-25 | 2022-03-25 | User portrait group acquisition method, system, equipment and computer readable storage medium based on group behaviors |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114925265A (en) |
-
2022
- 2022-03-25 CN CN202210300173.XA patent/CN114925265A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108280477B (en) | Method and apparatus for clustering images | |
CN108197652B (en) | Method and apparatus for generating information | |
CN112380859A (en) | Public opinion information recommendation method and device, electronic equipment and computer storage medium | |
US11748452B2 (en) | Method for data processing by performing different non-linear combination processing | |
CN113128419B (en) | Obstacle recognition method and device, electronic equipment and storage medium | |
WO2022126961A1 (en) | Method for target object behavior prediction of data offset and related device thereof | |
CN114494784A (en) | Deep learning model training method, image processing method and object recognition method | |
CN114821140A (en) | Image clustering method based on Manhattan distance, terminal device and storage medium | |
CN113011210A (en) | Video processing method and device | |
CN113742069A (en) | Capacity prediction method and device based on artificial intelligence and storage medium | |
CN111652282B (en) | Big data-based user preference analysis method and device and electronic equipment | |
CN110347973B (en) | Method and device for generating information | |
CN113705686B (en) | Image classification method, device, electronic equipment and readable storage medium | |
CN114330929B (en) | Content contribution evaluation method, device, electronic equipment and readable storage medium | |
CN113762421B (en) | Classification model training method, flow analysis method, device and equipment | |
CN114925265A (en) | User portrait group acquisition method, system, equipment and computer readable storage medium based on group behaviors | |
CN113780666B (en) | Missing value prediction method and device and readable storage medium | |
CN113961962A (en) | Model training method and system based on privacy protection and computer equipment | |
CN114385714A (en) | Feedback-based multi-row-order fusion method, device and equipment and readable storage medium | |
CN113779116A (en) | Object sorting method, related equipment and medium | |
CN109885504B (en) | Recommendation system test method, device, medium and electronic equipment | |
CN113515701A (en) | Information recommendation method and device | |
CN107623863B (en) | Algorithm testing method and device and server | |
CN111897910A (en) | Information pushing method and device | |
CN116501993B (en) | House source data recommendation method and device |
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 |