CN115098793B

CN115098793B - User portrait analysis method and system based on big data

Info

Publication number: CN115098793B
Application number: CN202210321101.3A
Authority: CN
Inventors: 陈应书; 郭从仁
Original assignee: Weimaikejian Group Co ltd
Current assignee: Weimai Technology Co ltd
Priority date: 2022-03-30
Filing date: 2022-03-30
Publication date: 2023-05-09
Anticipated expiration: 2042-03-30
Also published as: CN115098793A

Abstract

The invention provides a user portrait analysis method and a user portrait analysis system based on big data, and relates to the technical field of big data. In the invention, aiming at each user terminal device, user portrait information of a device user corresponding to the user terminal device is obtained; aiming at each equipment user in a plurality of equipment users corresponding to a plurality of user terminal equipment, obtaining the matching degree of the user portrait corresponding to the equipment user based on the matching degree between the user portrait information corresponding to the equipment user and the predetermined target user portrait information; and determining target equipment users from the plurality of equipment users based on the user portrait matching degree corresponding to each equipment user in the plurality of equipment users, wherein each determined target equipment user is used for constructing and forming a target user group. Based on the method, the problem of poor reliability of the user group formed based on the prior art construction can be solved.

Description

User portrait analysis method and system based on big data

Technical Field

The invention relates to the technical field of big data, in particular to a user portrait analysis method and system based on big data.

Background

With the continuous development of internet technology and computer technology, the network behaviors of users are becoming larger and larger, so that classifying users based on their network behavior data has become an important application, for example, different users may be classified based on similarity between their network behavior data to form different user groups. However, since the division of the groups is performed from the viewpoint of similarity between users, there may be a problem that the reliability of constructing the formed user group is not good for the application layer, such as mismatch with the application requirements.

Disclosure of Invention

In view of the above, the present invention aims to provide a user portrait analysis method and system based on big data, so as to solve the problem of poor reliability of a user group formed based on prior art construction.

In order to achieve the above purpose, the embodiment of the present invention adopts the following technical scheme:

the user portrait analysis method based on big data is applied to a user data analysis server, and comprises the following steps:

for each user terminal device in a plurality of user terminal devices in communication connection, obtaining user portrait information of a device user corresponding to the user terminal device, wherein the user portrait information is formed by constructing based on user characteristic information obtained by data acquisition of the corresponding device user;

Aiming at each equipment user in a plurality of equipment users corresponding to the plurality of user terminal equipment, obtaining the matching degree of the user portraits corresponding to the equipment user based on the matching degree between the user portraits information corresponding to the equipment user and the predetermined target user portraits information, wherein the target user portraits information is formed based on the user characteristic information of a target user group to be formed by building;

and determining target equipment users from the plurality of equipment users based on the user portrait matching degree corresponding to each equipment user, wherein each determined target equipment user is used for constructing and forming the target user group.

In some preferred embodiments, in the above big data based user portrait analysis method, the step of obtaining, for each of the plurality of user terminal devices, user portrait information of a device user corresponding to the user terminal device includes:

judging whether a user portrait analysis instruction is acquired or not, and generating user portrait analysis notification information after the user portrait analysis instruction is acquired;

Transmitting the user portrait analysis notification information to each of a plurality of user terminal devices in communication connection, wherein each of the user terminal devices is used for displaying the user portrait analysis notification information to a device user corresponding to the user terminal device after receiving the user portrait analysis notification information, responding to the operation that the device user agrees to perform user portrait analysis based on the user portrait analysis notification information to generate corresponding user portrait analysis confirmation information, and transmitting the user portrait analysis confirmation information to the user data analysis server;

and after acquiring the user portrait analysis confirmation information sent by each user terminal device in the plurality of user terminal devices, respectively acquiring the user portrait information of the device user corresponding to each user terminal device in the plurality of user terminal devices.

In some preferred embodiments, in the above big data based user portrait analysis method, the step of obtaining, for each device user of the plurality of device users corresponding to the plurality of user terminal devices, a user portrait matching degree corresponding to the device user based on a matching degree between user portrait information corresponding to the device user and predetermined target user portrait information includes:

Determining a fusion coefficient corresponding to each piece of user characteristic information contained in the predetermined target user portrait information;

for each equipment user in a plurality of equipment users corresponding to the plurality of user terminal equipment, respectively calculating the matching degree between each piece of user characteristic information included in the user portrait information corresponding to the equipment user and the corresponding user characteristic information included in the target user portrait information, and obtaining the characteristic matching degree corresponding to each piece of user characteristic information included in the user portrait information;

and aiming at each equipment user in a plurality of equipment users corresponding to the plurality of user terminal equipment, carrying out fusion processing on the feature matching degree corresponding to each piece of user feature information included in the user portrait information corresponding to the equipment user based on the fusion coefficient corresponding to each piece of user feature information to obtain the user portrait matching degree corresponding to the equipment user.

In some preferred embodiments, in the above big data based user portrait analysis method, the step of determining, for each piece of user feature information included in the predetermined target user portrait information, a fusion coefficient corresponding to the user feature information includes:

Obtaining each historical target user group formed through historical construction, and obtaining at least one historical target user group, wherein each historical target user group in the at least one historical target user group comprises at least one historical equipment user;

determining historical user portrait information corresponding to each historical target user group in the at least one historical target user group, and performing de-duplication screening on historical user feature information included in the historical user portrait information corresponding to each historical target user group in the at least one historical target user group to obtain a corresponding historical feature information set;

determining, for each piece of historical user feature information in the historical feature information set, a historical device user corresponding to the historical user feature information in the at least one historical target user group as a first historical device user corresponding to the historical user feature information, and determining a fusion coefficient corresponding to the historical user feature information based on the first historical device user;

for each piece of user characteristic information included in the predetermined target user portrait information, determining historical user characteristic information to which the user characteristic information belongs, and determining a fusion coefficient corresponding to the historical user characteristic information as a fusion coefficient corresponding to the user characteristic information.

In some preferred embodiments, in the above big data based user portrait analysis method, the step of determining, for each piece of historical user feature information in the set of historical feature information, a historical device user corresponding to the historical user feature information in the at least one historical target user group as a first historical device user corresponding to the historical user feature information, and determining, based on the first historical device user, a fusion coefficient corresponding to the historical user feature information includes:

determining, for each piece of historical user feature information in the historical feature information set, a historical device user corresponding to the historical user feature information in the at least one historical target user group as a first historical device user corresponding to the historical user feature information, counting the number of the first historical device users corresponding to the historical user feature information to obtain a first user counting number corresponding to the historical user feature information, and determining a first coefficient corresponding to the historical user feature information based on the first user counting number corresponding to the historical user feature information, wherein a positive correlation exists between the first coefficient and the first user counting number;

For each historical target user group in the at least one historical target user group, respectively determining the information attention degree of each historical equipment user in the historical target user group to the historical recommendation information corresponding to the historical target user group, and determining the group contribution coefficient of each historical equipment user in the historical target user group based on the information attention degree corresponding to each historical equipment user, wherein the group contribution coefficient has a positive correlation with the information attention degree;

for each group contribution coefficient, determining the historical formation time of a historical target user group corresponding to the group contribution coefficient, constructing and forming corresponding two-dimensional coordinates based on the group contribution coefficient and the historical formation time, and determining a coordinate vector corresponding to the two-dimensional coordinates;

for each piece of historical user characteristic information in the historical characteristic information set, sequentially connecting one coordinate vector corresponding to each first historical equipment user corresponding to the historical user characteristic information to obtain one connecting path corresponding to the historical user characteristic information, wherein the step of sequentially connecting one coordinate vector corresponding to each first historical equipment user corresponding to the historical user characteristic information to obtain one connecting path corresponding to the historical user characteristic information is carried out for a plurality of times to obtain a plurality of corresponding connecting paths, and each two connecting paths in the plurality of connecting paths are different;

For each piece of historical user characteristic information in the historical characteristic information set, calculating the vector distance between two adjacent coordinate vectors in each connecting path corresponding to the historical user characteristic information respectively, calculating the sum value of the vector distances between two adjacent coordinate vectors in each connecting path respectively to obtain the vector distance and the value corresponding to each connecting path, determining the connecting path corresponding to the vector distance and the value with the minimum value as a target connecting path corresponding to the historical user characteristic information, and fusing each group contribution coefficient corresponding to the target connecting path to obtain a contribution coefficient fusion value corresponding to the historical user characteristic information;

and determining a fusion coefficient corresponding to the historical user characteristic system information based on the contribution coefficient fusion value and the first coefficient corresponding to the historical user characteristic system information aiming at each piece of historical user characteristic information in the historical characteristic information set.

In some preferred embodiments, in the above big data based user profile analysis method, the step of determining a target device user from the plurality of device users based on a user profile matching degree corresponding to each of the plurality of device users includes:

For each device user in the plurality of device users, determining a relative magnitude relation between the user portrait matching degree corresponding to the device user and a pre-configured portrait matching degree threshold;

and for each equipment user in the plurality of equipment users, if the user portrait matching degree corresponding to the equipment user is greater than or equal to the portrait matching degree threshold value, determining the equipment user as a target equipment user, and if the user portrait matching degree corresponding to the equipment user is less than the portrait matching degree threshold value, determining the equipment user as a non-target equipment user.

based on the user portrait matching degree corresponding to each of the plurality of equipment users, sorting the equipment users to obtain a user sorting sequence corresponding to the plurality of equipment users, wherein when the equipment users are subjected to sorting, sorting is performed according to the order of the bigger before smaller or bigger before smaller before bigger of the user portrait matching degree corresponding to the equipment users;

And acquiring group quantity range information configured for the target user group in advance, and selecting the equipment user with the corresponding quantity range with the largest user portrait matching degree in the user sorting sequence as the target equipment user based on the group quantity range information.

The embodiment of the invention also provides a user portrait analysis system based on big data, which is applied to a user data analysis server and comprises:

the user portrait acquisition module is used for acquiring user portrait information of a device user corresponding to each user terminal device in a plurality of user terminal devices in communication connection, wherein the user portrait information is formed by constructing based on user characteristic information obtained by data acquisition of the corresponding device user;

the portrait matching degree determining module is used for obtaining the user portrait matching degree corresponding to each equipment user in a plurality of equipment users corresponding to the plurality of user terminal equipment based on the matching degree between the user portrait information corresponding to the equipment user and the predetermined target user portrait information, wherein the target user portrait information is formed based on the user characteristic information of a target user group to be formed by construction;

And the target user determining module is used for determining target equipment users from the plurality of equipment users based on the user portrait matching degree corresponding to each equipment user in the plurality of equipment users, wherein each determined target equipment user is used for constructing and forming the target user group.

In some preferred embodiments, in the above big data based user profile analysis system, the user profile acquisition module is specifically configured to:

In some preferred embodiments, in the above big data based user portrait analysis system, the portrait matching degree determining module is specifically configured to:

According to the user portrait analysis method and system based on big data, the user portrait information of the equipment user corresponding to each user terminal equipment can be obtained firstly, then, the reliability of the target user group constructed based on the determined target equipment user can be guaranteed for each equipment user of the equipment users corresponding to the user terminal equipment, and the problem of poor reliability of the user group constructed based on the prior art can be solved.

In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

Fig. 1 is an application block diagram of a user data analysis server according to an embodiment of the present invention.

Fig. 2 is a flowchart illustrating steps included in the big data-based user portrait analysis method according to an embodiment of the present invention.

FIG. 3 is a schematic diagram of each module included in the big data based user portrait analysis system according to an embodiment of the present invention.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.

Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

As shown in fig. 1, an embodiment of the present invention provides a user data analysis server. Wherein the user data analysis server may comprise a memory and a processor.

In detail, the memory and the processor are electrically connected directly or indirectly to realize transmission or interaction of data. For example, electrical connection may be made to each other via one or more communication buses or signal lines. The memory may store at least one software functional module (computer program) that may exist in the form of software or firmware. The processor may be configured to execute an executable computer program stored in the memory, thereby implementing the big data based user portrait analysis method provided by an embodiment of the present invention (as described later).

For example, in one possible implementation, the Memory may be, but is not limited to, random access Memory (Random Access Memory, RAM), read Only Memory (ROM), programmable Read Only Memory (Programmable Read-Only Memory, PROM), erasable Read Only Memory (Erasable Programmable Read-Only Memory, EPROM), electrically erasable Read Only Memory (Electric Erasable Programmable Read-Only Memory, EEPROM), and the like.

For example, in one possible implementation, the processor may be a general purpose processor including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), a System on Chip (SoC), etc.; but also Digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

Also, the structure shown in fig. 1 is only illustrative, and the user data analysis server may further include more or less components than those shown in fig. 1, or have a different configuration from that shown in fig. 1, for example, may include a communication unit for information interaction with other devices (such as a user terminal device, etc., where the user terminal device may include, but is not limited to, a mobile phone, a computer, etc.).

With reference to fig. 2, the embodiment of the invention also provides a user portrait analysis method based on big data, which can be applied to the user data analysis server. The method steps defined by the flow related to the user portrait analysis method based on big data can be realized by the user data analysis server. The specific flow shown in fig. 2 will be described in detail.

Step S110, for each user terminal device in a plurality of user terminal devices in communication connection, user portrait information of a device user corresponding to the user terminal device is obtained.

In the embodiment of the present invention, the user data analysis server may acquire, for each of a plurality of user terminal devices in communication connection, user portrait information of a device user corresponding to the user terminal device. The user portrait information is formed based on user characteristic information (such as gender, age, income and the like) obtained by data acquisition of corresponding equipment users.

Step S120, for each equipment user in a plurality of equipment users corresponding to the plurality of user terminal equipment, obtaining the matching degree of the user portrait corresponding to the equipment user based on the matching degree between the user portrait information corresponding to the equipment user and the predetermined target user portrait information.

In the embodiment of the invention, the user data analysis server can obtain the matching degree of the user portrait corresponding to each equipment user in the plurality of equipment users corresponding to the plurality of user terminal equipment based on the matching degree between the user portrait information corresponding to the equipment user and the predetermined target user portrait information. The target user portrait information is formed by constructing based on user characteristic information of a target user group to be formed by constructing.

And step S130, determining a target device user from the plurality of device users based on the user portrait matching degree corresponding to each device user in the plurality of device users.

In the embodiment of the invention, the user data analysis server may determine the target device user from the plurality of device users based on the user portrait matching degree corresponding to each of the plurality of device users. And each determined target device user is used for constructing and forming the target user group (so that the information to be recommended corresponding to the target user portrait information can be pushed to each target device user in the target user group).

According to the user portrait analysis method based on big data, the user portrait information of the equipment user corresponding to each user terminal equipment can be obtained firstly for each user terminal equipment, then, the user portrait matching degree corresponding to each equipment user can be obtained based on the matching degree between the user portrait information corresponding to the equipment user and the predetermined target user portrait information for each equipment user corresponding to the plurality of user terminal equipment, so that the target equipment user can be determined in the plurality of equipment users based on the user portrait matching degree corresponding to each equipment user in the plurality of equipment users, and therefore, the higher matching degree between the determined target equipment user and the target user portrait information (namely the required characteristics of the user) representing the application requirements can be ensured, and the reliability of the target user group constructed based on the determined target equipment user is ensured, so that the problem of poor reliability of the user group constructed based on the prior art is solved.

For example, in one possible implementation, step S110 in the above implementation may further include the following steps:

firstly, judging whether a user portrait analysis instruction is acquired (for example, the user portrait analysis instruction can be considered to be acquired after the information to be recommended is received) and generating user portrait analysis notification information after the user portrait analysis instruction is acquired;

secondly, sending the user portrait analysis notification information to each of a plurality of user terminal devices in communication connection, wherein each of the plurality of user terminal devices is used for displaying the user portrait analysis notification information to a device user corresponding to the user terminal device after receiving the user portrait analysis notification information, responding to the operation that the device user agrees to perform user portrait analysis based on the user portrait analysis notification information to generate corresponding user portrait analysis confirmation information, and sending the user portrait analysis confirmation information to the user data analysis server;

and then, after acquiring the user portrait analysis confirmation information sent by each of the plurality of user terminal devices, respectively acquiring the user portrait information of the device user corresponding to each of the plurality of user terminal devices.

For example, in one possible implementation, step S120 in the above implementation may further include the following steps:

firstly, determining a fusion coefficient corresponding to each piece of user characteristic information contained in predetermined target user portrait information;

secondly, for each equipment user in a plurality of equipment users corresponding to the plurality of user terminal equipment, calculating the matching degree between each piece of user characteristic information included in the user portrait information corresponding to the equipment user and the corresponding user characteristic information included in the target user portrait information respectively, and obtaining the characteristic matching degree corresponding to each piece of user characteristic information included in the user portrait information;

and then, for each equipment user in a plurality of equipment users corresponding to the plurality of user terminal equipment, carrying out fusion processing (such as weighted summation calculation and the like) on the feature matching degree corresponding to each piece of user feature information included in the user portrait information corresponding to the equipment user based on the fusion coefficient corresponding to each piece of user feature information, so as to obtain the user portrait matching degree corresponding to the equipment user.

For example, in one possible implementation manner, the step of determining, for each piece of user feature information included in the predetermined target user portrait information in the foregoing implementation manner, a fusion coefficient corresponding to the user feature information may further include the following steps:

Firstly, obtaining each historical target user group formed through historical construction to obtain at least one historical target user group, wherein each historical target user group in the at least one historical target user group comprises at least one historical equipment user;

secondly, determining historical user portrait information corresponding to each historical target user group in the at least one historical target user group, and performing de-duplication screening (namely, the same historical user feature information only keeps one piece of the same) on the historical user feature information included in the historical user portrait information corresponding to each historical target user group in the at least one historical target user group to obtain a corresponding historical feature information set;

then, determining, for each piece of historical user characteristic information in the historical characteristic information set, a historical equipment user corresponding to the historical user characteristic information in the at least one historical target user group as a first historical equipment user corresponding to the historical user characteristic information, and determining a fusion coefficient corresponding to the historical user characteristic information based on the first historical equipment user;

And finally, determining the historical user characteristic information of each piece of user characteristic information included in the predetermined target user portrait information (such as the same) and determining the fusion coefficient corresponding to the historical user characteristic information as the fusion coefficient corresponding to the user characteristic information.

For example, in one possible implementation manner, the step of determining, for each piece of historical user feature information in the set of historical feature information in the foregoing implementation manner, a historical device user corresponding to the historical user feature information in the at least one historical target user group as a first historical device user corresponding to the historical user feature information, and determining, based on the first historical device user, a fusion coefficient corresponding to the historical user feature information, further includes the steps of:

firstly, determining a corresponding historical equipment user of the historical user characteristic information in the at least one historical target user group as a first historical equipment user corresponding to the historical user characteristic information aiming at each piece of historical user characteristic information in the historical characteristic information set, counting the number of the first historical equipment users corresponding to the historical user characteristic information to obtain a first user counting number corresponding to the historical user characteristic information, and determining a first coefficient corresponding to the historical user characteristic information based on the first user counting number corresponding to the historical user characteristic information, wherein the first coefficient and the first user counting number have a positive correlation;

Secondly, for each historical target user group in the at least one historical target user group, respectively determining the information attention degree of each historical equipment user in the historical target user group to the historical recommendation information corresponding to the historical target user group, and determining the group contribution coefficient of each historical equipment user in the historical target user group based on the information attention degree corresponding to each historical equipment user, wherein the group contribution coefficient and the information attention degree have a positive correlation (for example, the information attention degree can be directly used as the group contribution coefficient);

then, for each group contribution coefficient, determining the history formation time of a history target user group corresponding to the group contribution coefficient, constructing and forming corresponding two-dimensional coordinates based on the group contribution coefficient and the history formation time, and determining a coordinate vector corresponding to the two-dimensional coordinates;

then, for each piece of historical user characteristic information in the historical characteristic information set, sequentially connecting one coordinate vector corresponding to each first historical equipment user corresponding to the historical user characteristic information to obtain one connecting path corresponding to the historical user characteristic information, wherein for each piece of historical user characteristic information in the historical characteristic information set, sequentially connecting one coordinate vector corresponding to each first historical equipment user corresponding to the historical user characteristic information to obtain one connecting path corresponding to the historical user characteristic information, and executing the step of obtaining a plurality of times to obtain a plurality of corresponding connecting paths, wherein each two connecting paths in the plurality of connecting paths are different;

Further, for each piece of historical user characteristic information in the historical characteristic information set, calculating the vector distance between two adjacent coordinate vectors in each connecting path corresponding to the historical user characteristic information respectively, calculating the sum value of the vector distances between two adjacent coordinate vectors in each connecting path respectively to obtain the vector distance and the value corresponding to each connecting path, determining the connecting path corresponding to the vector distance and the value with the minimum value as a target connecting path corresponding to the historical user characteristic information, and fusing each group contribution coefficient corresponding to the target connecting path to obtain a contribution coefficient fusion value corresponding to the historical user characteristic information;

and finally, determining a fusion coefficient corresponding to the historical user characteristic system information according to the contribution coefficient fusion value corresponding to the historical user characteristic system information and the first coefficient (such as a calculated product or average value) aiming at each piece of historical user characteristic information in the historical characteristic information set.

secondly, respectively determining the information attention degree of each historical equipment user in the historical target user group to the historical recommendation information corresponding to the historical target user group aiming at each historical target user group in the at least one historical target user group, and determining the group contribution coefficient of each historical equipment user in the historical target user group based on the information attention degree corresponding to each historical equipment user, wherein the group contribution coefficient and the information attention degree have a positive correlation relationship, and the historical target user groups are multiple;

Then, counting the number of group contribution coefficients corresponding to each historical equipment user, obtaining the coefficient statistical number used by the historical equipment for corresponding, determining the relative magnitude relation between the coefficient statistical number and a preset statistical number threshold, and determining the historical equipment user as a second historical equipment user when the coefficient statistical number is larger than the statistical number threshold, or determining the historical equipment user as a third historical equipment user when the coefficient statistical number is smaller than or equal to the statistical number threshold, wherein a plurality of group contribution coefficients corresponding to each historical equipment user are sequentially arranged based on the historical formation time of a historical target user group corresponding to each group contribution coefficient;

then, determining the coefficient statistical quantity with the minimum value in the coefficient statistical quantity corresponding to each second historical equipment user, taking the coefficient statistical quantity as a first quantity reference value, calculating the average value of the group contribution coefficient corresponding to the third historical equipment user aiming at each third historical equipment user, determining one second historical equipment user with a correlation based on the average value and the average value of the group contribution coefficient corresponding to each second historical equipment user, and carrying out interpolation processing on the group contribution coefficient corresponding to the third historical equipment user based on the group contribution coefficient corresponding to the second historical equipment user to obtain a new group contribution coefficient corresponding to the third historical equipment user, wherein the number of the new group contribution coefficient corresponding to each third historical equipment user is the same as the number of the group contribution coefficient corresponding to one second historical equipment user with the correlation;

Further, for each historical equipment user, based on the statistical quantity threshold, sliding window processing is performed on a plurality of group contribution coefficients currently owned by the historical equipment user to obtain a plurality of coefficient sliding window sequences corresponding to the historical equipment user, sequence similarity (such as calculating the coefficient similarity of group contribution coefficients at corresponding sequence positions and then calculating the average value of the coefficient similarity) between every two coefficient sliding window sequences in the plurality of coefficient sliding window sequences, and for each coefficient sliding window sequence corresponding to the historical equipment user, calculating the average value of the sequence similarity between the coefficient sliding window sequence and each other coefficient sliding window sequence to obtain a similarity average value corresponding to the coefficient sliding window sequence, and determining one coefficient sliding window sequence with the largest corresponding similarity average value in the plurality of coefficient sliding window sequences as a target coefficient sliding window sequence corresponding to the historical equipment user;

still further, for each historical equipment user, determining a target group contribution coefficient corresponding to the historical equipment user (for example, calculating an average value or a median value of a plurality of group contribution coefficients included in the target coefficient sliding window sequence, and taking the average value or the median value as the target group contribution coefficient) based on a plurality of group contribution coefficients included in the target coefficient sliding window sequence corresponding to the historical equipment user, and for each piece of historical user characteristic information in the historical characteristic information set, performing fusion processing on the target group contribution coefficient corresponding to each historical equipment user corresponding to the historical user characteristic information to obtain a contribution coefficient fusion value corresponding to the historical user characteristic system information;

And finally, determining a fusion coefficient corresponding to the historical user characteristic system information according to the contribution coefficient fusion value and the first coefficient corresponding to the historical user characteristic system information aiming at each piece of historical user characteristic information in the historical characteristic information set.

For example, in one possible implementation, step S130 in the above implementation may further include the following steps:

firstly, for each device user in the plurality of device users, determining a relative magnitude relation between a user portrait matching degree corresponding to the device user and a pre-configured portrait matching degree threshold (such as whether the user portrait matching degree is greater than or equal to the portrait matching degree threshold);

and secondly, aiming at each equipment user in the plurality of equipment users, if the user portrait matching degree corresponding to the equipment user is larger than or equal to the portrait matching degree threshold value, determining the equipment user as a target equipment user, and if the user portrait matching degree corresponding to the equipment user is smaller than the portrait matching degree threshold value, determining the equipment user as a non-target equipment user.

Firstly, based on the user portrait matching degree corresponding to each of the plurality of equipment users, carrying out sorting processing on the equipment users to obtain user sorting sequences corresponding to the plurality of equipment users, wherein when the equipment users are subjected to sorting processing, sorting is carried out according to the order of the bigger before smaller before bigger or bigger before bigger of the user portrait matching degree corresponding to the equipment users;

and secondly, acquiring group quantity range information configured for the target user group in advance, and selecting the equipment user with the corresponding quantity range with the largest user portrait matching degree from the user sorting sequence based on the group quantity range information as the target equipment user.

With reference to fig. 3, the embodiment of the invention further provides a user portrait analysis system based on big data, which can be applied to the user data analysis server. The user portrait analysis system can comprise a user portrait acquisition module, a portrait matching degree determination module and a target user determination module.

The user portrait acquisition module is used for acquiring user portrait information of a device user corresponding to each user terminal device in a plurality of user terminal devices in communication connection, wherein the user portrait information is formed based on user characteristic information obtained by data acquisition of the corresponding device user.

The portrait matching degree determining module is used for obtaining the user portrait matching degree corresponding to each equipment user in a plurality of equipment users corresponding to the plurality of user terminal equipment based on the matching degree between the user portrait information corresponding to the equipment user and the predetermined target user portrait information, wherein the target user portrait information is formed based on the user characteristic information of a target user group to be formed by building.

The target user determining module is configured to determine a target device user from the plurality of device users based on a user portrait matching degree corresponding to each device user in the plurality of device users, where each determined target device user is used to construct and form the target user group.

For example, in one possible implementation, the user portrait acquisition module is specifically configured (refer to the description related to step S110 above):

For example, in one possible implementation manner, the image matching degree determining module is specifically configured (refer to the related description of step S120 above):

In summary, the user portrait analysis method and system based on big data provided by the invention can acquire the user portrait information of the device user corresponding to each user terminal device, and then can acquire the user portrait matching degree corresponding to each device user based on the matching degree between the user portrait information corresponding to the device user and the predetermined target user portrait information for each device user corresponding to a plurality of user terminal devices, so that the target device user can be determined in a plurality of device users based on the user portrait matching degree corresponding to each device user, and thus, the higher matching degree between the determined target device user and the target user portrait information (i.e. the required characteristics of the user) representing the application requirements can be ensured, thereby ensuring the reliability of the target user group constructed based on the determined target device user, and further improving the problem of poor reliability of the user group constructed based on the prior art.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. The apparatus and method embodiments described above are merely illustrative, for example, flow diagrams and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In addition, functional modules in the embodiments of the present invention may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.

The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, an electronic device, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A big data based user portrayal analysis method, which is applied to a user data analysis server, comprising:

Determining target equipment users from the plurality of equipment users based on the user portrait matching degree corresponding to each of the plurality of equipment users, wherein each determined target equipment user is used for constructing and forming the target user group;

the step of obtaining the matching degree of the user portrait corresponding to each equipment user in the plurality of equipment users corresponding to the plurality of user terminal equipment based on the matching degree between the user portrait information corresponding to the equipment user and the predetermined target user portrait information comprises the following steps:

Aiming at each equipment user in a plurality of equipment users corresponding to the plurality of user terminal equipment, carrying out fusion processing on the feature matching degree corresponding to each piece of user feature information included in the user portrait information corresponding to the equipment user based on the fusion coefficient corresponding to each piece of user feature information to obtain the user portrait matching degree corresponding to the equipment user;

the step of determining the fusion coefficient corresponding to each piece of user characteristic information included in the predetermined target user portrait information includes:

for each piece of user characteristic information included in the predetermined target user portrait information, determining historical user characteristic information to which the user characteristic information belongs, and determining a fusion coefficient corresponding to the historical user characteristic information as a fusion coefficient corresponding to the user characteristic information;

the step of determining, for each piece of history user feature information in the history feature information set, a history device user corresponding to the history user feature information in the at least one history target user group as a first history device user corresponding to the history user feature information, and determining, based on the first history device user, a fusion coefficient corresponding to the history user feature information includes:

For each historical target user group in the at least one historical target user group, respectively determining the information attention degree of each historical equipment user in the historical target user group to the historical recommendation information corresponding to the historical target user group, and determining the group contribution coefficient of each historical equipment user in the historical target user group based on the information attention degree corresponding to each historical equipment user, wherein the group contribution coefficient has a positive correlation with the information attention degree, and the historical target user group is a plurality of;

counting the number of group contribution coefficients corresponding to each historical equipment user, obtaining the coefficient statistical number used by the historical equipment for corresponding, determining the relative magnitude relation between the coefficient statistical number and a preset statistical number threshold, and determining the historical equipment user as a second historical equipment user when the coefficient statistical number is larger than the statistical number threshold, or determining the historical equipment user as a third historical equipment user when the coefficient statistical number is smaller than or equal to the statistical number threshold, wherein a plurality of group contribution coefficients corresponding to each historical equipment user are sequentially arranged based on the historical formation time of a historical target user group corresponding to each group contribution coefficient;

Determining the coefficient statistical quantity with the minimum value from the coefficient statistical quantity corresponding to each second historical equipment user, taking the coefficient statistical quantity as a first quantity reference value, calculating the average value of the group contribution coefficient corresponding to each third historical equipment user aiming at each third historical equipment user, determining one second historical equipment user with a correlation relationship based on the average value and the average value of the group contribution coefficient corresponding to each second historical equipment user, and carrying out interpolation processing on the group contribution coefficient corresponding to the third historical equipment user based on the group contribution coefficient corresponding to the second historical equipment user to obtain a new group contribution coefficient corresponding to the third historical equipment user, wherein the number of the new group contribution coefficient corresponding to each third historical equipment user is the same as the number of the group contribution coefficient corresponding to one second historical equipment user with the correlation relationship;

performing sliding window processing on a plurality of group contribution coefficients of the historical equipment user according to the statistical quantity threshold value, obtaining a plurality of coefficient sliding window sequences corresponding to the historical equipment user, calculating sequence similarity between every two coefficient sliding window sequences in the plurality of coefficient sliding window sequences, calculating an average value of sequence similarity between the coefficient sliding window sequences and each other coefficient sliding window sequence according to each coefficient sliding window sequence corresponding to the historical equipment user, obtaining a similarity average value corresponding to the coefficient sliding window sequence, and determining one coefficient sliding window sequence with the largest corresponding similarity average value in the plurality of coefficient sliding window sequences to be used as a target coefficient sliding window sequence corresponding to the historical equipment user;

Determining a target group contribution coefficient corresponding to the historical equipment user according to a plurality of group contribution coefficients included in the target coefficient sliding window sequence corresponding to the historical equipment user, and carrying out fusion processing on the target group contribution coefficient corresponding to each historical equipment user corresponding to the historical user characteristic information according to each piece of historical user characteristic information in the historical characteristic information set to obtain a contribution coefficient fusion value corresponding to the historical user characteristic system information;

2. The big data based user portrayal analysis method according to claim 1, wherein the step of obtaining, for each of the plurality of user terminal devices, user portrayal information of a device user corresponding to the user terminal device includes:

3. The big data based user profile analysis method of claim 1 or 2, wherein the step of determining a target device user among the plurality of device users based on a user profile matching degree corresponding to each of the plurality of device users comprises:

4. The big data based user profile analysis method of claim 1 or 2, wherein the step of determining a target device user among the plurality of device users based on a user profile matching degree corresponding to each of the plurality of device users comprises:

5. A big data based user profile analysis system for use with a user data analysis server, the big data based user profile analysis system comprising:

The target user determining module is used for determining target device users from the plurality of device users based on the user portrait matching degree corresponding to each device user in the plurality of device users, wherein each determined target device user is used for constructing and forming the target user group;

the portrait matching degree determining module is specifically configured to:

Wherein, for each piece of user characteristic information included in the predetermined target user portrait information, determining a fusion coefficient corresponding to the user characteristic information includes:

the determining, for each piece of history user feature information in the history feature information set, a history device user corresponding to the history user feature information in the at least one history target user group, as a first history device user corresponding to the history user feature information, and determining, based on the first history device user, a fusion coefficient corresponding to the history user feature information, including:

6. The big data based user representation analysis system of claim 5, wherein the user representation acquisition module is specifically configured to: