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

Abstract

The user portrait analysis method and system based on big data provided by the present invention relate to the technical field of big data. In the present invention, for each user terminal device, the user portrait information of the device user corresponding to the user terminal device is obtained; for each device user among the multiple device users corresponding to multiple user terminal devices, based on the device user corresponding The matching degree between the user portrait information and the predetermined target user portrait information is obtained to obtain the user portrait matching degree corresponding to the device user; based on the user portrait matching degree corresponding to each device user among multiple device users, in multiple Target device users are determined from the device users, wherein each determined target device user is used to construct a target user group. Based on the above method, the problem of poor reliability of the user group formed based on the prior art can be improved.

Description

User portrait analysis method and system based on big data

technical field

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

Background technique

With the continuous development of Internet technology and computer technology, the user's network behavior is becoming more and more large. Therefore, it has become an important application to classify users based on the user's network behavior data. The similarity between behavioral data is used to classify different users and form different user groups. However, this is to divide groups from the perspective of similarity between users. Therefore, at the application level, there may be a problem of poor reliability of the constructed user groups, such as mismatching with application requirements.

Contents of the invention

In view of this, the purpose of the present invention is to provide a user profile analysis method and system based on big data, so as to improve the problem of poor reliability of user groups formed based on existing technologies.

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

A user portrait analysis method based on big data, applied to a user data analysis server, the user portrait analysis method based on big data includes:

For each user terminal device among the plurality of user terminal devices connected by communication, obtain user portrait information of a device user corresponding to the user terminal device, wherein the user portrait information is based on user profile information obtained from data collection of the corresponding device user. The formation of characteristic information;

For each of the multiple device users corresponding to the multiple user terminal devices, based on the matching degree between the user portrait information corresponding to the device user and the predetermined target user portrait information, the corresponding User portrait matching degree, wherein the target user portrait information is constructed and formed based on the user characteristic information of the target user group to be formed;

Based on the user portrait matching degree corresponding to each of the multiple device users, target device users are determined among the multiple device users, wherein each of the determined target device users is used to build a The target user group.

In some preferred embodiments, in the above-mentioned user portrait analysis method based on big data, for each of the plurality of user terminal devices, the user portrait of the device user corresponding to the user terminal device is acquired Information steps, including:

Judging whether the user portrait analysis instruction has been obtained, and after obtaining the user portrait analysis instruction, generating user portrait analysis notification information;

Send the user portrait analysis notification information to each user terminal device among the plurality of user terminal devices connected by communication, wherein each of the user terminal devices is configured to, after receiving the user portrait analysis notification information, send to The device user corresponding to the user terminal device displays the user portrait analysis notification information, and generates corresponding user portrait analysis confirmation information in response to the device user agreeing to perform user portrait analysis based on the user portrait analysis notification information, and The user portrait analysis confirmation information is sent to the user data analysis server;

After obtaining the user profile analysis confirmation information sent by each of the multiple user terminal devices, respectively obtain the user ID of the device user corresponding to each of the multiple user terminal devices portrait information.

In some preferred embodiments, in the above-mentioned user portrait analysis method based on big data, for each device user among the multiple device users corresponding to the multiple user terminal devices, based on the user corresponding to the device user The matching degree between the portrait information and the predetermined target user portrait information, and the steps of obtaining the matching degree of the user portrait corresponding to the device user include:

For each piece of user characteristic information included in the predetermined target user portrait information, determine the fusion coefficient corresponding to the user characteristic information;

For each device user among the multiple device users corresponding to the multiple user terminal devices, calculate each piece of user characteristic information included in the user portrait information corresponding to the device user and the corresponding user information included in the target user portrait information. The matching degree between the characteristic information is obtained to obtain the characteristic matching degree corresponding to each piece of user characteristic information included in the user portrait information;

For each device user in the plurality of device users corresponding to the plurality of user terminal devices, based on the fusion coefficient corresponding to each piece of user characteristic information, each piece of user characteristic information included in the user portrait information corresponding to the device user The corresponding feature matching degree is fused to obtain the user portrait matching degree corresponding to the device user.

In some preferred embodiments, in the above-mentioned user portrait analysis method based on big data, the step of determining the fusion coefficient corresponding to the user characteristic information for each piece of user characteristic information included in the predetermined target user portrait information, include:

Obtaining each historical target user group constructed in history to obtain at least one historical target user group, wherein each of the at least one historical target user group includes at least one historical device user;

For each historical target user group in the at least one historical target user group, determine historical user portrait information corresponding to the historical target user group, and correspond to each historical target user group in the at least one historical target user group The historical user profile information included in the historical user portrait information is deduplicated and filtered to obtain the corresponding historical feature information set;

For each piece of historical user characteristic information in the historical characteristic information set, determine the historical device user corresponding to the historical user characteristic information in the at least one historical target user group as the first historical device corresponding to the historical user characteristic information user, and determine the 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, determine the historical user characteristic information to which the user characteristic information belongs, and determine the fusion coefficient corresponding to the historical user characteristic information as the fusion coefficient corresponding to the user characteristic information.

In some preferred embodiments, in the above-mentioned user portrait analysis method based on big data, for each piece of historical user characteristic information in the historical characteristic information set, it is determined that the historical user characteristic information is included in the at least one history The corresponding historical device user in the target user group is used as the first historical device user corresponding to the historical user characteristic information, and the step of determining the fusion coefficient corresponding to the historical user characteristic information based on the first historical device user includes:

For each piece of historical user characteristic information in the historical characteristic information set, determine the historical device user corresponding to the historical user characteristic information in the at least one historical target user group as the first historical device corresponding to the historical user characteristic information users, and count the number of first historical device users corresponding to the historical user characteristic information, obtain the first user statistical quantity corresponding to the historical user characteristic information, and determine the first user statistical quantity corresponding to the historical user characteristic information. A first coefficient corresponding to historical user characteristic information, wherein there is a positive correlation between the first coefficient and the first user statistics;

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

For each of the group contribution coefficients, determine the historical formation time of the historical target user group corresponding to the group contribution coefficient, and construct and form corresponding two-dimensional coordinates based on the group contribution coefficient and the historical formation time, and determine the two-dimensional coordinates Corresponding coordinate vector;

For each piece of historical user characteristic information in the historical characteristic information set, a coordinate vector corresponding to each first historical device user corresponding to the historical user characteristic information is sequentially connected to obtain a connection corresponding to the historical user characteristic information path, wherein, for each piece of historical user characteristic information in the historical characteristic information set, a coordinate vector corresponding to each first historical device user corresponding to the historical user characteristic information is sequentially connected to obtain the historical user The step of one connection path corresponding to the feature information is executed multiple times to obtain corresponding multiple connection paths, wherein every two connection paths in the multiple connection paths are different;

For each piece of historical user feature information in the historical feature information set, calculate the vector distance between two adjacent coordinate vectors in each connection path corresponding to the historical user feature information, and calculate the vector distance between two adjacent coordinate vectors in each connection path respectively. The sum of the vector distances between two adjacent coordinate vectors is used to obtain the vector distance and value corresponding to each connection path, and the connection path corresponding to the vector distance and value with the minimum value is determined as the corresponding historical user characteristic information The target connection path of the target connection path is fused with each group contribution coefficient corresponding to the target connection path to obtain the fusion value of the contribution coefficient corresponding to the historical user characteristic information;

For each piece of historical user characteristic information in the historical characteristic information set, the fusion coefficient corresponding to the historical user characteristic information is determined based on the contribution coefficient fusion value and the first coefficient corresponding to the historical user characteristic information.

In some preferred embodiments, in the above-mentioned user portrait analysis method based on big data, based on the user portrait matching degree corresponding to each of the multiple device users, among the multiple device users Steps to identify target device users include:

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

For each device user among the plurality of device users, if the user portrait matching degree corresponding to the device user is greater than or equal to the portrait matching degree threshold, determine the device user as the target device user, and if the device user corresponds to If the matching degree of the user portrait is less than the threshold matching degree of the portrait, the device user is determined to be a non-target device user.

In some preferred embodiments, in the above-mentioned user portrait analysis method based on big data, based on the user portrait matching degree corresponding to each of the multiple device users, among the multiple device users Steps to identify target device users include:

Based on the user portrait matching degree corresponding to each of the multiple device users, sort the device users to obtain a user sorting sequence corresponding to the multiple device users, wherein the device users are sorted During the sorting process, sorting is performed in the order of first large and then small or first small and then large according to the matching degree of the user portrait corresponding to the device user;

Acquiring group number range information pre-configured for the target user group, and selecting device users in the corresponding number range with the highest matching degree of user portraits in the user sorting sequence as target device users based on the group number range information.

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

A user portrait acquisition module, configured to acquire user portrait information of a device user corresponding to the user terminal device for each user terminal device in a plurality of user terminal devices connected by communication, wherein the user portrait information is based on the corresponding device The user characteristic information is constructed and formed through data collection by the user;

The portrait matching degree determination module is configured to, for each of the multiple device users corresponding to the multiple user terminal devices, based on the matching between the user portrait information corresponding to the device user and the predetermined target user portrait information degree, to obtain the user portrait matching degree corresponding to the device user, wherein the target user portrait information is constructed and formed based on the user characteristic information of the target user group to be formed;

The target user determination module is configured to determine the target device user among the multiple device users based on the user portrait matching degree corresponding to each of the multiple device users, wherein each of the determined Target device users are used to construct and form the target user group.

In some preferred embodiments, in the above-mentioned user portrait analysis system based on big data, the user portrait acquisition module is specifically used for:

Judging whether the user portrait analysis instruction has been obtained, and after obtaining the user portrait analysis instruction, generating user portrait analysis notification information;

Send the user portrait analysis notification information to each user terminal device among the plurality of user terminal devices connected by communication, wherein each of the user terminal devices is configured to, after receiving the user portrait analysis notification information, send to The device user corresponding to the user terminal device displays the user portrait analysis notification information, and generates corresponding user portrait analysis confirmation information in response to the device user agreeing to perform user portrait analysis based on the user portrait analysis notification information, and The user portrait analysis confirmation information is sent to the user data analysis server;

After obtaining the user profile analysis confirmation information sent by each of the multiple user terminal devices, respectively obtain the user ID of the device user corresponding to each of the multiple user terminal devices portrait information.

In some preferred embodiments, in the above-mentioned user portrait analysis system based on big data, the portrait matching degree determination module is specifically used for:

For each piece of user characteristic information included in the predetermined target user portrait information, determine the fusion coefficient corresponding to the user characteristic information;

For each device user among the multiple device users corresponding to the multiple user terminal devices, calculate each piece of user characteristic information included in the user portrait information corresponding to the device user and the corresponding user information included in the target user portrait information. The matching degree between the characteristic information is obtained to obtain the characteristic matching degree corresponding to each piece of user characteristic information included in the user portrait information;

For each device user in the plurality of device users corresponding to the plurality of user terminal devices, based on the fusion coefficient corresponding to each piece of user characteristic information, each piece of user characteristic information included in the user portrait information corresponding to the device user The corresponding feature matching degree is fused to obtain the user portrait matching degree corresponding to the device user.

The user portrait analysis method and system based on big data provided by the embodiments of the present invention can first obtain the user portrait information of the device user corresponding to the user terminal device for each user terminal device, and then can correspond to multiple user terminal devices. For each device user among the multiple device users, based on the matching degree between the user portrait information corresponding to the device user and the predetermined target user portrait information, the user portrait matching degree corresponding to the device user is obtained, so that the user portrait matching degree corresponding to the device user can be obtained based on multiple The user portrait matching degree corresponding to each device user among multiple device users determines the target device user among multiple device users. In this way, it can be guaranteed that the determined target device user and the target user portrait information representing the application requirements (that is, the required There is a high degree of matching between the user's characteristics), so as to ensure the reliability of the target user group constructed based on the determined target device user, thereby improving the problem of poor reliability of the user group formed based on the existing technology .

In order to make the above-mentioned objects, features and advantages of the present invention more comprehensible, preferred embodiments will be described in detail below together with the accompanying drawings.

Description of drawings

FIG. 1 is an application block diagram of a user data analysis server provided by an embodiment of the present invention.

FIG. 2 is a schematic flowchart of steps included in the method for analyzing user portraits based on big data provided by an embodiment of the present invention.

Fig. 3 is a schematic diagram of various modules included in the user portrait analysis system based on big data provided by the embodiment of the present invention.

Detailed ways

In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is only a part of embodiments of the present invention, but not all embodiments. The components of the embodiments of the invention generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations.

Accordingly, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present 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 include a memory and a processor.

In detail, the memory and the processor are electrically connected directly or indirectly to realize data transmission or interaction. For example, they can be electrically connected to each other through one or more communication buses or signal lines. The memory may store at least one software function module (computer program) in the form of software or firmware (firmware). The processor can be used to execute the executable computer program stored in the memory, so as to realize the user profile analysis method based on big data provided by the embodiment of the present invention (as described later).

For example, in a possible implementation manner, the memory may be, but not limited to, random access memory (Random Access Memory, RAM), read only memory (Read Only Memory, ROM), programmable read-only Memory (Programmable Read-Only Memory, PROM), Erasable Programmable Read-Only Memory (EPROM), Electric Erasable Programmable Read-Only Memory (EEPROM), etc.

For example, in a possible implementation manner, 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 a chip ( System on Chip, SoC), etc.; it can also be digital signal processor (DSP), application specific integrated circuit (ASIC), field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

Moreover, the structure shown in FIG. 1 is only for illustration, and the user data analysis server may also include more or fewer components than those shown in FIG. 1, or have a configuration different from that shown in FIG. 1, for example, may include A communication unit for information interaction with other devices (such as user terminal equipment, etc., where the user terminal equipment may include, but not limited to, mobile phones, computers, etc.).

With reference to FIG. 2 , an embodiment of the present invention also provides a method for analyzing user portraits based on big data, which can be applied to the above-mentioned user data analysis server. Wherein, the method steps defined in the process related to the big data-based user portrait analysis method can be implemented by the user data analysis server. The specific process shown in FIG. 2 will be described in detail below.

Step S110, for each user terminal device among the plurality of user terminal devices connected by communication, acquire user portrait information of a device user corresponding to the user terminal device.

In the embodiment of the present invention, the user data analysis server may obtain user portrait information of a device user corresponding to the user terminal device for each user terminal device among a plurality of user terminal devices connected by communication. Wherein, the user portrait information is constructed based on user characteristic information (such as gender, age, income, etc.) obtained through data collection of corresponding device users.

Step S120, for each of the multiple device users corresponding to the multiple user terminal devices, based on the matching degree between the user portrait information corresponding to the device user and the predetermined target user portrait information, obtain the device User portrait matching degree corresponding to the user.

In the embodiment of the present invention, the user data analysis server may, for each device user among the multiple device users corresponding to the multiple user terminal devices, based on the user portrait information corresponding to the device user and the predetermined target user The matching degree between the portrait information is used to obtain the matching degree of the user portrait corresponding to the device user. Wherein, the target user profile information is constructed based on the user characteristic information of the target user group to be constructed.

Step S130, based on the user portrait matching degree corresponding to each of the multiple device users, determine a target device user among the multiple device users.

In the embodiment of the present invention, the user data analysis server may determine the target device user among the multiple device users based on the user profile matching degree corresponding to each of the multiple device users. Wherein, each determined target device user is used to construct and form the target user group (in this way, the information to be recommended corresponding to the target user portrait information can be pushed to each target device in the target user group user).

Based on the above-mentioned user portrait analysis method based on big data, the user portrait information of the device user corresponding to the user terminal device can be obtained for each user terminal device first, and then the multiple device users corresponding to multiple user terminal devices can be obtained For each device user in the device user, based on the matching degree between the user portrait information corresponding to the device user and the predetermined target user portrait information, the user portrait matching degree corresponding to the device user is obtained, so that it can be based on multiple device users. The user portrait matching degree corresponding to each device user determines the target device user among multiple device users, so that the determined target device user and the target user portrait information (that is, the required user characteristics) that represent the application requirements can be guaranteed. There is a high degree of matching between them, so as to ensure the reliability of the target user group constructed based on the determined target device users, thereby improving the problem of poor reliability of the user group formed based on the existing technology.

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

First, determine whether the user portrait analysis instruction has been obtained (for example, after receiving the above-mentioned information to be recommended, it can be considered that the user portrait analysis instruction has been obtained), and after obtaining the user portrait analysis instruction, generate a user portrait analyze notification information;

Secondly, the user portrait analysis notification information is sent to each user terminal device in a plurality of user terminal devices connected by communication, wherein each user terminal device in a plurality of user terminal devices is configured to receive the user After the portrait analysis notification information, display the user portrait analysis notification information to the device user corresponding to the user terminal device, and generate a corresponding user portrait in response to the operation of the device user agreeing to perform user portrait analysis based on the user portrait analysis notification information Analyzing the confirmation information, and sending the user portrait analysis confirmation information to the user data analysis server;

Then, after obtaining the user profile analysis confirmation information sent by each of the plurality of user terminal devices, respectively obtaining the device user corresponding to each of the plurality of user terminal devices user profile information.

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

First, for each piece of user characteristic information included in the predetermined target user portrait information, determine the fusion coefficient corresponding to the user characteristic information;

Secondly, for each of the multiple device users corresponding to the multiple user terminal devices, respectively calculate the correspondence between each piece of user characteristic information included in the user portrait information corresponding to the device user and the target user portrait information. The matching degree between the user characteristic information of the user profile information is obtained, and the characteristic matching degree corresponding to each piece of user characteristic information included in the user portrait information is obtained;

Then, for each of the multiple device users corresponding to the multiple user terminal devices, based on the fusion coefficient corresponding to each piece of user characteristic information, each piece of user information included in the user portrait information corresponding to the device user The feature matching degree corresponding to the feature information is fused (such as weighted sum calculation, etc.) to obtain the user portrait matching degree corresponding to the device user.

For example, in a possible implementation manner, the step of determining the fusion coefficient corresponding to the user characteristic information for each piece of user characteristic information included in the predetermined target user portrait information in the above implementation manner may be further Include the following steps:

Firstly, acquire each historical target user group formed historically, and obtain at least one historical target user group, wherein each of the historical target user groups in the at least one historical target user group includes at least one historical device user ;

Secondly, for each historical target user group in the at least one historical target user group, determine the historical user portrait information corresponding to the historical target user group, and for each historical target user group in the at least one historical target user group The historical user feature information included in the historical user portrait information corresponding to the group is deduplicated and filtered (that is, only one of the same historical user feature information is retained), and the corresponding historical feature information set is obtained;

Then, for each piece of historical user characteristic information in the historical characteristic information set, determine the historical device user corresponding to the historical user characteristic information in the at least one historical target user group as the first user corresponding to the historical user characteristic information. Historical device users, and determine the fusion coefficient corresponding to the historical user feature information based on the first historical device user;

Finally, for each piece of user characteristic information included in the predetermined target user portrait information, determine the historical user characteristic information to which the user characteristic information belongs (if the same), and determine the fusion coefficient corresponding to the historical user characteristic information as the user characteristic The fusion coefficient corresponding to the information.

For example, in a possible implementation manner, in the above implementation manner, for each piece of historical user characteristic information in the historical characteristic information set, it is determined that the historical user characteristic information is included in the at least one historical target user. The corresponding historical device user in the group is used as the first historical device user corresponding to the historical user characteristic information, and the step of determining the fusion coefficient corresponding to the historical user characteristic information based on the first historical device user further includes the following steps:

First, for each piece of historical user characteristic information in the historical characteristic information set, determine the historical device user corresponding to the historical user characteristic information in the at least one historical target user group as the first user corresponding to the historical user characteristic information. Historical device users, and count the number of first historical device users corresponding to the historical user characteristic information, obtain the first user statistical quantity corresponding to the historical user characteristic information, and, based on the first user statistical quantity corresponding to the historical user characteristic information determining a first coefficient corresponding to the historical user feature information, wherein there is a positive correlation between the first coefficient and the first user statistics;

Secondly, for each historical target user group in the at least one historical target user group, respectively determine the information attention of each historical device user in the historical target user group to the historical recommendation information corresponding to the historical target user group, And determine the group contribution coefficient of each historical device user in the historical target user group based on the information attention corresponding to each historical device user, wherein there is a positive correlation between the group contribution coefficient and the information attention ( For example, the information attention can be directly used as the group contribution coefficient);

Then, for each of the group contribution coefficients, determine the historical formation time of the historical target user group corresponding to the group contribution coefficient, and construct and form corresponding two-dimensional coordinates based on the group contribution coefficient and the historical formation time, and determine the two The coordinate vector corresponding to the dimension coordinate;

Afterwards, for each piece of historical user characteristic information in the historical characteristic information set, a coordinate vector corresponding to each first historical device user corresponding to the historical user characteristic information is sequentially connected to obtain the corresponding historical user characteristic information. A connection path, wherein, for each piece of historical user characteristic information in the historical characteristic information set, a coordinate vector corresponding to each first historical device user corresponding to the historical user characteristic information is sequentially connected to obtain the The step of one connection path corresponding to the historical user characteristic information is executed multiple times to obtain corresponding multiple connection paths, and every two connection paths in the multiple connection paths are different;

Further, for each piece of historical user feature information in the set of historical feature information, calculate the vector distance between two adjacent coordinate vectors in each connection path corresponding to the historical user feature information, and calculate the distance of each connection The sum of the vector distances between two adjacent coordinate vectors in the path obtains the vector distance and value corresponding to each connection path, and determines the connection path corresponding to the vector distance and value with the minimum value as the historical user feature The target connection path corresponding to the information is fused with each group contribution coefficient corresponding to the target connection path to obtain the fusion value of the contribution coefficient corresponding to the historical user characteristic information;

Finally, for each piece of historical user feature information in the historical feature information set, determine The fusion coefficient corresponding to the historical user characteristic information.

For example, in a possible implementation manner, in the above implementation manner, for each piece of historical user characteristic information in the historical characteristic information set, it is determined that the historical user characteristic information is included in the at least one historical target user. The corresponding historical device user in the group is used as the first historical device user corresponding to the historical user characteristic information, and the step of determining the fusion coefficient corresponding to the historical user characteristic information based on the first historical device user further includes the following steps:

First, for each piece of historical user characteristic information in the historical characteristic information set, determine the historical device user corresponding to the historical user characteristic information in the at least one historical target user group as the first user corresponding to the historical user characteristic information. Historical device users, and count the number of first historical device users corresponding to the historical user characteristic information, obtain the first user statistical quantity corresponding to the historical user characteristic information, and, based on the first user statistical quantity corresponding to the historical user characteristic information determining a first coefficient corresponding to the historical user characteristic information, wherein there is a positive correlation between the first coefficient and the first user statistics;

Secondly, for each historical target user group in the at least one historical target user group, respectively determine the information attention of each historical device user in the historical target user group to the historical recommendation information corresponding to the historical target user group, And determine the group contribution coefficient of each historical device user in the historical target user group based on the information attention corresponding to each historical device user, wherein there is a positive correlation between the group contribution coefficient and the information attention, There are multiple historical target user groups;

Then, for each historical device user, count the number of group contribution coefficients corresponding to the historical device user, obtain the statistical quantity of the coefficient corresponding to the historical device, and determine the difference between the coefficient statistical quantity and the pre-configured statistical quantity threshold The relative size relationship among them, and, when the statistical quantity of the coefficient is greater than the threshold of the statistical quantity, determine the historical equipment user as the second historical equipment user, or, when the statistical quantity of the coefficient is less than or equal to the threshold of the statistical quantity , determining the historical device user as a third historical device user, wherein the multiple group contribution coefficients corresponding to each historical device user are arranged in order based on the historical formation time of the historical target user group corresponding to each group contribution coefficient;

Afterwards, among the coefficient statistical quantities corresponding to each of the second historical device users, the coefficient statistical quantity with the smallest value is determined as the first quantity reference value, and for each of the third historical device users, the first statistical quantity is calculated. The average value of the group contribution coefficients corresponding to the three historical device users, and, based on the average value and the average value of the group contribution coefficients corresponding to each of the second historical device users, determine a second historical device user with a correlation , and based on the group contribution coefficient corresponding to the second historical device user, the group contribution coefficient corresponding to the third historical device user is interpolated to obtain a new group contribution coefficient corresponding to the third historical device user, wherein each The number of new group contribution coefficients corresponding to the third historical device user is the same as the number of group contribution coefficients corresponding to a second historical device user having a correlation;

Further, for each historical device user, based on the statistical quantity threshold, perform sliding window processing on the plurality of group contribution coefficients currently owned by the historical device user to obtain a plurality of coefficient sliding window sequences corresponding to the historical device user, And calculate the sequence similarity between every two coefficient sliding window sequences in the multiple coefficient sliding window sequences (such as calculating the coefficient similarity of the group contribution coefficient corresponding to the sequence position respectively, and then calculating the average value of the coefficient similarity, etc.) , and, for each coefficient sliding window sequence corresponding to the historical device user, calculate the average value of the sequence similarity between this coefficient sliding window sequence and every other coefficient sliding window sequence, and obtain the corresponding similarity of the coefficient sliding window sequence Degree mean value, and then determine a corresponding coefficient sliding window sequence with the largest similarity mean value in the plurality of coefficient sliding window sequences, as the target coefficient sliding window sequence corresponding to the historical device user;

Still further, for each historical device user, based on the plurality of group contribution coefficients included in the target coefficient sliding window sequence corresponding to the historical device user, determine the target group contribution coefficient corresponding to the historical device user (as calculated The average or median value of the multiple group contribution coefficients included in the target coefficient sliding window sequence, and then use the average or median value as the target group contribution coefficient), and for each piece of history in the historical feature information set For the user characteristic information, fusion processing is performed on the target group contribution coefficient corresponding to each historical device user corresponding to the historical user characteristic information, to obtain the fusion value of the contribution coefficient corresponding to the historical user characteristic information;

Finally, for each piece of historical user characteristic information in the historical characteristic information set, based on the fusion value of the contribution coefficient corresponding to the historical user characteristic information and the first coefficient, determine the fusion value corresponding to the historical user characteristic information. coefficient.

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

First, for each device user among the plurality of device users, determine the relative size relationship between the user portrait matching degree corresponding to the device user and a pre-configured portrait matching degree threshold (for example, whether the user portrait matching degree is greater than or equal to the portrait matching degree threshold);

Secondly, for each device user among the plurality of device users, if the user portrait matching degree corresponding to the device user is greater than or equal to the portrait matching degree threshold, the device user is determined as the target device user, and if the device user If the user portrait matching degree corresponding to the user is less than the portrait matching degree threshold, the device user is determined to be a non-target device user.

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

First, based on the matching degree of user portraits corresponding to each of the multiple device users, the device users are sorted to obtain a user sorting sequence corresponding to the multiple device users, wherein the device users When the user performs sorting processing, the user portrait matching degree corresponding to the device user is sorted in the order of first large and then small or first small and then large;

Secondly, obtain the group number range information pre-configured for the target user group, and select the device users in the corresponding number range with the highest matching degree of user portraits in the user ranking sequence as target device users based on the group number range information .

With reference to FIG. 3 , an embodiment of the present invention also provides a user profile analysis system based on big data, which can be applied to the above user data analysis server. Wherein, the user portrait analysis system may include a user portrait acquisition module, a portrait matching degree determination module, and a target user determination module.

The user portrait acquisition module is configured to acquire user portrait information of a device user corresponding to the user terminal equipment for each user terminal equipment among a plurality of user terminal equipment connected by communication, wherein the user portrait information is based on a corresponding The user characteristic information obtained from data collection by device users is constructed and formed.

The portrait matching degree determination module is configured to, for each of the multiple device users corresponding to the multiple user terminal devices, based on the difference between the user portrait information corresponding to the device user and the predetermined target user portrait information The matching degree of the user portrait corresponding to the device user is obtained, wherein the target user portrait information is constructed based on the user characteristic information of the target user group to be formed.

The target user determination module is configured to determine target device users among the multiple device users based on the matching degree of user portraits corresponding to each of the multiple device users, wherein each determined The target device users are used to construct and form the target user group.

For example, in a possible implementation manner, the user portrait acquisition module is specifically used for (refer to the relevant description of the above-mentioned step S110):

Judging whether the user portrait analysis instruction has been obtained, and after obtaining the user portrait analysis instruction, generating user portrait analysis notification information;

Send the user portrait analysis notification information to each user terminal device among the plurality of user terminal devices connected by communication, wherein each of the user terminal devices is configured to, after receiving the user portrait analysis notification information, send to The device user corresponding to the user terminal device displays the user portrait analysis notification information, and generates corresponding user portrait analysis confirmation information in response to the device user agreeing to perform user portrait analysis based on the user portrait analysis notification information, and The user portrait analysis confirmation information is sent to the user data analysis server;

After obtaining the user profile analysis confirmation information sent by each of the multiple user terminal devices, respectively obtain the user ID of the device user corresponding to each of the multiple user terminal devices portrait information.

For example, in a possible implementation manner, the portrait matching degree determination module is specifically used for (refer to the relevant description of the above-mentioned step S120):

For each piece of user characteristic information included in the predetermined target user portrait information, determine the fusion coefficient corresponding to the user characteristic information;

For each device user among the multiple device users corresponding to the multiple user terminal devices, calculate each piece of user characteristic information included in the user portrait information corresponding to the device user and the corresponding user information included in the target user portrait information. The matching degree between the characteristic information is obtained to obtain the characteristic matching degree corresponding to each piece of user characteristic information included in the user portrait information;

For each device user in the plurality of device users corresponding to the plurality of user terminal devices, based on the fusion coefficient corresponding to each piece of user characteristic information, each piece of user characteristic information included in the user portrait information corresponding to the device user The corresponding feature matching degree is fused to obtain the user portrait matching degree corresponding to the device user.

To sum up, the user portrait analysis method and system based on big data provided by the present invention can first obtain the user portrait information of the device user corresponding to the user terminal device for each user terminal device, and then can target multiple user For each of the multiple device users corresponding to the terminal device, based on the matching degree between the user portrait information corresponding to the device user and the predetermined target user portrait information, the matching degree of the user portrait corresponding to the device user is obtained, so that Based on the user profile matching degree corresponding to each device user, the target device user can be determined among multiple device users. In this way, it can be guaranteed that the determined target device user and the target user profile information representing the application requirements (that is, the required user profile information) Features) have a high matching degree, thereby ensuring the reliability of the target user group constructed based on the determined target device users, thereby improving the problem of poor reliability of the user group formed based on the existing technology.

In the several embodiments provided by the embodiments of the present invention, it should be understood that the disclosed devices and methods may also be implemented in other ways. The device and method embodiments described above are only illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show possible implementation architectures of devices, methods and computer program products according to multiple embodiments of the present invention, function and operation. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or part of code that includes one or more Executable instructions. 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 in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified function or action , or may be implemented by a combination of dedicated hardware and computer instructions.

In addition, each functional module in each embodiment of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, an electronic device, or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes. . It should be noted that, in this document, the terms "comprising", "comprising" or any other variation thereof are intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising said element.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims (6)

1. A user portrait analysis method based on big data, characterized in that it is applied to a user data analysis server, and the user portrait analysis method based on big data comprises: For each user terminal device among the plurality of user terminal devices connected by communication, obtain user portrait information of a device user corresponding to the user terminal device, wherein the user portrait information is based on user profile information obtained from data collection of the corresponding device user. The formation of characteristic information; For each of the multiple device users corresponding to the multiple user terminal devices, based on the matching degree between the user portrait information corresponding to the device user and the predetermined target user portrait information, the corresponding User portrait matching degree, wherein the target user portrait information is constructed and formed based on the user characteristic information of the target user group to be formed; Based on the user portrait matching degree corresponding to each of the multiple device users, target device users are determined among the multiple device users, wherein each of the determined target device users is used to build a the target user group; Wherein, for each of the multiple device users corresponding to the multiple user terminal devices, based on the matching degree between the user portrait information corresponding to the device user and the predetermined target user portrait information, the The steps of user profile matching degree corresponding to the device user include: For each piece of user characteristic information included in the predetermined target user portrait information, determine the fusion coefficient corresponding to the user characteristic information; For each device user among the multiple device users corresponding to the multiple user terminal devices, calculate each piece of user characteristic information included in the user portrait information corresponding to the device user and the corresponding user information included in the target user portrait information. The matching degree between the characteristic information is obtained to obtain the characteristic matching degree corresponding to each piece of user characteristic information included in the user portrait information; For each device user in the plurality of device users corresponding to the plurality of user terminal devices, based on the fusion coefficient corresponding to each piece of user characteristic information, each piece of user characteristic information included in the user portrait information corresponding to the device user The corresponding feature matching degree is fused to obtain the user portrait matching degree corresponding to the device user; Wherein, the step of determining the fusion coefficient corresponding to the user characteristic information for each piece of user characteristic information included in the predetermined target user portrait information includes: Obtaining each historical target user group constructed in history to obtain at least one historical target user group, wherein each of the at least one historical target user group includes at least one historical device user; For each historical target user group in the at least one historical target user group, determine historical user portrait information corresponding to the historical target user group, and correspond to each historical target user group in the at least one historical target user group The historical user profile information included in the historical user portrait information is deduplicated and filtered to obtain the corresponding historical feature information set; For each piece of historical user characteristic information in the historical characteristic information set, determine the historical device user corresponding to the historical user characteristic information in the at least one historical target user group as the first historical device corresponding to the historical user characteristic information user, and determine the 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, determine the historical user characteristic information to which the user characteristic information belongs, and determine the fusion coefficient corresponding to the historical user characteristic information as the fusion coefficient corresponding to the user characteristic information; Wherein, for each piece of historical user characteristic information in the historical characteristic information set, determine the historical device user corresponding to the historical user characteristic information in the at least one historical target user group, as the historical user characteristic information corresponding The first historical device user, and the step of determining the fusion coefficient corresponding to the historical user feature information based on the first historical device user includes: For each piece of historical user characteristic information in the historical characteristic information set, determine the historical device user corresponding to the historical user characteristic information in the at least one historical target user group as the first historical device corresponding to the historical user characteristic information users, and count the number of first historical device users corresponding to the historical user characteristic information, obtain the first user statistical quantity corresponding to the historical user characteristic information, and determine the first user statistical quantity corresponding to the historical user characteristic information. A first coefficient corresponding to historical user characteristic information, wherein there is a positive correlation between the first coefficient and the first user statistics; For each historical target user group in the at least one historical target user group, respectively determine the information attention of each historical device user in the historical target user group to the historical recommendation information corresponding to the historical target user group, and based on The information attention corresponding to each historical equipment user determines the group contribution coefficient of each historical equipment user in the historical target user group, wherein the group contribution coefficient has a positive correlation with the information attention, and the There are multiple historical target user groups; For each historical device user, count the number of group contribution coefficients corresponding to the historical device user, obtain the corresponding coefficient statistics for the historical device, and determine the coefficient between the coefficient statistics and the pre-configured statistical threshold Relative size relationship, and, when the statistical quantity of the coefficient is greater than the statistical quantity threshold, determine the historical device user as the second historical device user, or, when the statistical quantity of the coefficient is less than or equal to the statistical quantity threshold, determine The historical device user is determined as the third historical device user, wherein the multiple group contribution coefficients corresponding to each historical device user are arranged in order based on the historical formation time of the historical target user group corresponding to each group contribution coefficient; Determine the coefficient statistic quantity with the smallest value among the coefficient statistic quantities corresponding to each of the second historical device users as the first quantity reference value, and calculate the third history for each of the third historical device users The average value of the group contribution coefficient corresponding to the device user, and, based on the average value and the average value of the group contribution coefficient corresponding to each of the second historical device users, determine a second historical device user with a correlation, and Based on the group contribution coefficient corresponding to the second historical device user, the group contribution coefficient corresponding to the third historical device user is interpolated to obtain a new group contribution coefficient corresponding to the third historical device user, wherein each of the The number of new group contribution coefficients corresponding to the third historical device user is the same as the number of group contribution coefficients corresponding to a second historical device user with a correlation; For each historical device user, based on the statistical quantity threshold, perform sliding window processing on multiple group contribution coefficients currently owned by the historical device user, obtain a plurality of coefficient sliding window sequences corresponding to the historical device user, and calculate The sequence 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 device user, calculate the coefficient sliding window sequence and each other coefficient The average value of the sequence similarity between the sliding window sequences is obtained to obtain the corresponding similarity average value of the coefficient sliding window sequence, and then determine a coefficient sliding window sequence with the largest corresponding similarity average value in the plurality of coefficient sliding window sequences, As the target coefficient sliding window sequence corresponding to the historical device user; For each historical device user, based on the plurality of group contribution coefficients included in the target coefficient sliding window sequence corresponding to the historical device user, determine the target group contribution coefficient corresponding to the historical device user, and for the historical feature For each piece of historical user feature information in the information collection, the target group contribution coefficient corresponding to each historical device user corresponding to the historical user feature information is fused to obtain the contribution coefficient fusion value corresponding to the historical user feature system information; For each piece of historical user characteristic information in the historical characteristic information set, the fusion coefficient corresponding to the historical user characteristic information is determined based on the contribution coefficient fusion value and the first coefficient corresponding to the historical user characteristic information. 2. The user portrait analysis method based on big data as claimed in claim 1, wherein, for each user terminal device in the plurality of user terminal devices, the information of the device user corresponding to the user terminal device is obtained. The steps of user profile information include: Judging whether the user portrait analysis instruction has been obtained, and after obtaining the user portrait analysis instruction, generating user portrait analysis notification information; Send the user portrait analysis notification information to each user terminal device among the plurality of user terminal devices connected by communication, wherein each of the user terminal devices is configured to, after receiving the user portrait analysis notification information, send to The device user corresponding to the user terminal device displays the user portrait analysis notification information, and generates corresponding user portrait analysis confirmation information in response to the device user agreeing to perform user portrait analysis based on the user portrait analysis notification information, and The user portrait analysis confirmation information is sent to the user data analysis server; After obtaining the user profile analysis confirmation information sent by each of the multiple user terminal devices, respectively obtain the user ID of the device user corresponding to each of the multiple user terminal devices portrait information. 3. The user portrait analysis method based on big data as claimed in claim 1 or 2, wherein, based on the user portrait matching degree corresponding to each device user in the multiple device users, in the multiple The steps of determining the target device user among the device users include: For each device user in the plurality of device users, determine the relative size relationship between the user portrait matching degree corresponding to the device user and a pre-configured portrait matching degree threshold; For each device user among the plurality of device users, if the user portrait matching degree corresponding to the device user is greater than or equal to the portrait matching degree threshold, determine the device user as the target device user, and if the device user corresponds to If the matching degree of the user portrait is less than the threshold matching degree of the portrait, the device user is determined to be a non-target device user. 4. The user portrait analysis method based on big data as claimed in claim 1 or 2, wherein, based on the user portrait matching degree corresponding to each device user in the multiple device users, in the multiple The steps of determining the target device user among the device users include: Based on the user portrait matching degree corresponding to each of the multiple device users, sort the device users to obtain a user sorting sequence corresponding to the multiple device users, wherein the device users are sorted During the sorting process, sorting is performed in the order of first large and then small or first small and then large according to the matching degree of the user portrait corresponding to the device user; Acquiring group number range information pre-configured for the target user group, and selecting device users in the corresponding number range with the highest matching degree of user portraits in the user sorting sequence as target device users based on the group number range information. 5. A user portrait analysis system based on big data, characterized in that it is applied to a user data analysis server, and the user portrait analysis system based on big data includes: A user portrait acquisition module, configured to acquire user portrait information of a device user corresponding to the user terminal device for each user terminal device in a plurality of user terminal devices connected by communication, wherein the user portrait information is based on the corresponding device The user characteristic information is constructed and formed through data collection by the user; The portrait matching degree determination module is configured to, for each of the multiple device users corresponding to the multiple user terminal devices, based on the matching between the user portrait information corresponding to the device user and the predetermined target user portrait information degree, to obtain the user portrait matching degree corresponding to the device user, wherein the target user portrait information is constructed and formed based on the user characteristic information of the target user group to be formed; The target user determination module is configured to determine the target device user among the multiple device users based on the user portrait matching degree corresponding to each of the multiple device users, wherein each of the determined Target device users are used to construct and form the target user group; Wherein, the image matching degree determination module is specifically used for: For each piece of user characteristic information included in the predetermined target user portrait information, determine the fusion coefficient corresponding to the user characteristic information; For each device user among the multiple device users corresponding to the multiple user terminal devices, calculate each piece of user characteristic information included in the user portrait information corresponding to the device user and the corresponding user information included in the target user portrait information. The matching degree between the characteristic information is obtained to obtain the characteristic matching degree corresponding to each piece of user characteristic information included in the user portrait information; For each device user in the plurality of device users corresponding to the plurality of user terminal devices, based on the fusion coefficient corresponding to each piece of user characteristic information, each piece of user characteristic information included in the user portrait information corresponding to the device user The corresponding feature matching degree is fused to obtain the user portrait matching degree corresponding to the device user; Wherein, for each piece of user characteristic information included in the predetermined target user portrait information, determining the fusion coefficient corresponding to the user characteristic information includes: Obtaining each historical target user group constructed in history to obtain at least one historical target user group, wherein each of the at least one historical target user group includes at least one historical device user; For each historical target user group in the at least one historical target user group, determine historical user portrait information corresponding to the historical target user group, and correspond to each historical target user group in the at least one historical target user group The historical user profile information included in the historical user portrait information is deduplicated and filtered to obtain the corresponding historical feature information set; For each piece of historical user characteristic information in the historical characteristic information set, determine the historical device user corresponding to the historical user characteristic information in the at least one historical target user group as the first historical device corresponding to the historical user characteristic information user, and determine the 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, determine the historical user characteristic information to which the user characteristic information belongs, and determine the fusion coefficient corresponding to the historical user characteristic information as the fusion coefficient corresponding to the user characteristic information; Wherein, for each piece of historical user characteristic information in the historical characteristic information set, determine the historical device user corresponding to the historical user characteristic information in the at least one historical target user group, as the historical user characteristic information corresponding The first historical device user, and determining the fusion coefficient corresponding to the historical user feature information based on the first historical device user, including: For each piece of historical user characteristic information in the historical characteristic information set, determine the historical device user corresponding to the historical user characteristic information in the at least one historical target user group as the first historical device corresponding to the historical user characteristic information users, and count the number of first historical device users corresponding to the historical user characteristic information, obtain the first user statistical quantity corresponding to the historical user characteristic information, and determine the first user statistical quantity corresponding to the historical user characteristic information. A first coefficient corresponding to historical user characteristic information, wherein there is a positive correlation between the first coefficient and the first user statistics; For each historical target user group in the at least one historical target user group, respectively determine the information attention of each historical device user in the historical target user group to the historical recommendation information corresponding to the historical target user group, and based on The information attention corresponding to each historical equipment user determines the group contribution coefficient of each historical equipment user in the historical target user group, wherein the group contribution coefficient has a positive correlation with the information attention, and the There are multiple historical target user groups; For each historical device user, count the number of group contribution coefficients corresponding to the historical device user, obtain the corresponding coefficient statistics for the historical device, and determine the coefficient between the coefficient statistics and the pre-configured statistical threshold Relative size relationship, and, when the statistical quantity of the coefficient is greater than the statistical quantity threshold, determine the historical device user as the second historical device user, or, when the statistical quantity of the coefficient is less than or equal to the statistical quantity threshold, determine The historical device user is determined as the third historical device user, wherein the multiple group contribution coefficients corresponding to each historical device user are arranged in order based on the historical formation time of the historical target user group corresponding to each group contribution coefficient; Determine the coefficient statistic quantity with the smallest value among the coefficient statistic quantities corresponding to each of the second historical device users as the first quantity reference value, and calculate the third history for each of the third historical device users The average value of the group contribution coefficient corresponding to the device user, and, based on the average value and the average value of the group contribution coefficient corresponding to each of the second historical device users, determine a second historical device user with a correlation, and Based on the group contribution coefficient corresponding to the second historical device user, the group contribution coefficient corresponding to the third historical device user is interpolated to obtain a new group contribution coefficient corresponding to the third historical device user, wherein each of the The number of new group contribution coefficients corresponding to the third historical device user is the same as the number of group contribution coefficients corresponding to a second historical device user having a correlation relationship; For each historical device user, based on the statistical quantity threshold, perform sliding window processing on multiple group contribution coefficients currently owned by the historical device user, obtain a plurality of coefficient sliding window sequences corresponding to the historical device user, and calculate The sequence 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 device user, calculate the coefficient sliding window sequence and each other coefficient The average value of the sequence similarity between the sliding window sequences is obtained to obtain the corresponding similarity average value of the coefficient sliding window sequence, and then determine a coefficient sliding window sequence with the largest corresponding similarity average value among the plurality of coefficient sliding window sequences, As the target coefficient sliding window sequence corresponding to the historical device user; For each historical device user, based on the plurality of group contribution coefficients included in the target coefficient sliding window sequence corresponding to the historical device user, determine the target group contribution coefficient corresponding to the historical device user, and for the historical feature For each piece of historical user feature information in the information collection, the target group contribution coefficient corresponding to each historical device user corresponding to the historical user feature information is fused to obtain the contribution coefficient fusion value corresponding to the historical user feature system information; For each piece of historical user characteristic information in the historical characteristic information set, the fusion coefficient corresponding to the historical user characteristic information is determined based on the contribution coefficient fusion value and the first coefficient corresponding to the historical user characteristic information. 6. The user portrait analysis system based on big data as claimed in claim 5, wherein the user portrait acquisition module is specifically used for: Judging whether the user portrait analysis instruction has been obtained, and after obtaining the user portrait analysis instruction, generating user portrait analysis notification information; Sending the user portrait analysis notification information to each user terminal device among a plurality of user terminal devices connected by communication, wherein each of the user terminal devices is configured to, after receiving the user portrait analysis notification information, send to The device user corresponding to the user terminal device displays the user portrait analysis notification information, and generates corresponding user portrait analysis confirmation information in response to the device user agreeing to perform user portrait analysis based on the user portrait analysis notification information, and The user portrait analysis confirmation information is sent to the user data analysis server; After obtaining the user profile analysis confirmation information sent by each of the multiple user terminal devices, respectively obtain the user ID of the device user corresponding to each of the multiple user terminal devices portrait information.

Images