WO2019120024A1

WO2019120024A1 - User gender identification method, apparatus, storage medium, and electronic device

Info

Publication number: WO2019120024A1
Application number: PCT/CN2018/116713
Authority: WO
Inventors: 陈岩; 刘耀勇
Original assignee: Oppo广东移动通信有限公司
Priority date: 2017-12-22
Filing date: 2018-11-21
Publication date: 2019-06-27
Also published as: CN110020167B; CN110020167A

Abstract

Disclosed in the embodiments of the present application are a user gender identification method, an apparatus, a storage medium, and an electronic device. The method comprises: acquiring a sample feature set of a plurality of sample users; acquiring a gender reference feature set; acquiring a multi-dimensional feature of an unknown-gender user having gender identifiability during the use of an application, to obtain a feature set of the unknown-gender user; acquiring the similarity between the feature set and the gender reference feature set, and predicting the gender of the unknown-gender user according to the similarity.

Description

User gender identification method, device, storage medium and electronic device

This application claims the priority of the Chinese patent application filed on December 22, 2017, the Chinese Patent Office, the application number is 201711405392.X, and the invention is entitled "user gender identification method, device, storage medium and electronic device". This is incorporated herein by reference.

Technical field

The present application relates to the field of terminal technologies, and in particular, to a user gender identification method, apparatus, storage medium, and electronic device.

Background technique

With the popularization of electronic devices such as smart phones and the construction of mobile broadband networks, we have entered a new era of mobile Internet. In order to optimize the electronic equipment in various aspects, or to personally recommend applications to users, push news, etc., it is often necessary to know the user's gender.

Summary of the invention

The embodiment of the present application provides a user gender identification method, device, storage medium, and electronic device, which can accurately identify the gender of the user.

In a first aspect, an embodiment of the present application provides a user gender identification method, including:

Obtaining a multi-dimensional feature of the plurality of sample users having gender recognition during application use, and obtaining a sample feature set of the plurality of sample users;

Obtaining average eigenvalues of similar features in the plurality of sample feature sets to obtain a gender reference feature set;

Obtaining a gender-recognized multi-dimensional feature of an unknown gender user during application use, and obtaining a feature set of the unknown gender user;

Obtaining a similarity between the feature set and the gender reference feature set, and identifying a gender of the unknown gender user according to the similarity.

In a second aspect, an embodiment of the present application provides a user gender identification apparatus, including:

a first feature acquiring module, configured to acquire a multi-dimensional feature of the plurality of sample users that has gender recognition during use of the application, and obtain a sample feature set of the plurality of sample users;

a feature set generating module, configured to obtain an average feature value of a similar feature in the plurality of sample feature sets, to obtain a gender reference feature set;

a second feature acquisition module, configured to acquire a multi-dimensional feature that is gender-recognized by an unknown gender user during application use, and obtain a feature set of the unknown gender user;

The user gender identification module is configured to acquire the similarity between the feature set and the gender reference feature set, and identify the gender of the unknown gender user according to the similarity.

In a third aspect, a storage medium provided by an embodiment of the present application has a computer program stored thereon, and when the computer program is run on a computer, the computer is caused to perform a user gender identification method according to any embodiment of the present application.

In a fourth aspect, an electronic device provided by the embodiment of the present application includes a processor and a memory, where the memory has a computer program, and the processor is used to execute a user as provided in any embodiment of the present application by calling the computer program. Gender identification method.

DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the present application. Other drawings can also be obtained from those skilled in the art based on these drawings without paying any creative effort.

FIG. 1 is a schematic diagram of an application scenario of a user gender identification method according to an embodiment of the present application.

FIG. 2 is a schematic flowchart of a user gender identification method provided by an embodiment of the present application.

FIG. 3 is another schematic flowchart of a user gender identification method provided by an embodiment of the present application.

FIG. 4 is a schematic structural diagram of a user gender identification apparatus according to an embodiment of the present application.

FIG. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

FIG. 6 is another schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed ways

References to "an embodiment" herein mean that a particular feature, structure, or characteristic described in connection with the embodiments can be included in at least one embodiment of the present application. The appearances of the phrases in various places in the specification are not necessarily referring to the same embodiments, and are not exclusive or alternative embodiments that are mutually exclusive. Those skilled in the art will understand and implicitly understand that the embodiments described herein can be combined with other embodiments.

The embodiment of the present application provides a user gender identification method, including:

In some embodiments, the gender reference feature set includes a male reference feature set and a female reference feature set, the acquiring the similarity of the feature set and the gender reference feature set, and identifying the similarity according to the similarity The steps for the gender of an unknown gender user include:

Obtaining a first similarity between the feature set and the male reference feature set;

Obtaining a second similarity between the feature set and the female reference feature set;

Comparing the magnitudes of the first similarity and the second similarity;

If the first similarity is greater than the second similarity, the unknown gender user is identified as a male user, and the unknown gender user is identified as a female user.

In some embodiments, the gender reference feature set is a male reference feature set, the similarity of the feature set and the gender reference feature set is obtained, and the gender of the unknown gender user is identified according to the similarity The steps include:

Obtaining a distance between the feature set and the male reference feature set, and using the distance as a similarity between the feature set and the male reference feature set;

Determining whether the distance is in a first preset distance interval;

If yes, the unknown gender user is identified as a male user, otherwise the unknown gender user is identified as a female user.

In some embodiments, the gender reference feature set is a female reference feature set, the similarity of the feature set and the gender reference feature set is obtained, and the gender of the unknown gender user is identified according to the similarity The steps include:

Obtaining a distance between the feature set and the female reference feature set, and using the distance as a similarity between the feature set and the female reference feature set;

Determining whether the distance is in a second preset distance interval;

If yes, the unknown gender user is identified as a female user, otherwise the unknown gender user is identified as a male user.

In some embodiments, the obtaining a plurality of sample users has gender-recognized multi-dimensional features during application use, and the step of obtaining the sample feature sets of the plurality of sample users comprises:

Obtain multi-dimensional features of multiple sample users with gender recognition during application use;

And normalizing the obtained multi-dimensional features to obtain a sample feature set of the plurality of sample users.

In some embodiments, the similarity between the feature set and the gender reference feature set includes: a distance between the feature set and the gender reference feature set.

In some embodiments, the step of obtaining the similarity between the feature set and the gender reference feature set comprises:

The distance between the feature set and the gender reference feature set is calculated by the following formula:

Wherein, l represents the distance between the feature set and the gender reference feature set, and Xn represents a one-dimensional feature in the gender reference feature set.

A one-dimensional feature in a feature set representing an unknown gender user. When the values of n are the same, Xn and

Corresponding to the same feature, n is a positive integer greater than 2.

In some embodiments, the step of acquiring a gender-recognized multi-dimensional feature of the user of the unknown gender during the application use comprises: collecting the gender-recognized multi-dimensional feature of the user of the unknown gender in the application process according to the preset frequency in the historical time period. .

In some embodiments, the gender reference feature set includes a male reference feature set and a female reference feature set; the obtaining a similarity between the feature set and the gender reference feature set, and identifying the similarity according to the similarity The steps for the gender of an unknown gender user include:

Comparing the magnitudes of the first similarity and the second similarity;

If the first similarity is greater than the second similarity, identifying the unknown gender user as a male user;

If the first similarity is less than the second similarity, identifying the unknown gender user as a female user;

If the first similarity is the second similarity, there is no recognition result.

The embodiment of the present application provides a user gender identification method, and the execution subject of the user gender identification method may be the user gender identification device provided by the embodiment of the present application, or an electronic device integrated with the user gender identification device, wherein the user gender recognition The device can be implemented in hardware or software. The electronic device may be a device such as a smart phone, a tablet computer, a palmtop computer, a notebook computer, or a desktop computer.

Referring to FIG. 1 , FIG. 1 is a schematic diagram of an application scenario of a user gender identification method according to an embodiment of the present application. The user identity recognition device is integrated into an electronic device as an example, and the electronic device can obtain a charging feature set when charging behavior occurs, and obtain a plurality of charging feature sets; performing similarity recognition on the plurality of charging feature sets to obtain a similar charging feature set including a plurality of similar charging feature sets; predicting a next charging behavior according to the similar charging feature set; and predicting a next charging behavior Determine the corresponding performance adjustment mode; perform performance adjustment operations according to the determined performance adjustment mode.

Specifically, referring to FIG. 1 , taking the gender of the user a as an example, a plurality of sample users (a sample user, that is, a user of known gender, such as a male user b, a female user c, etc.) may be acquired in a historical time period. Multi-dimensional features with gender recognition during application use (such as the number and duration of user b browsing male products in shopping applications, the length of time user b browses male readings in reading applications, and user c in shopping applications The number and duration of browsing female products, the length of time that user c browses female readings in the reading application, as a sample, obtaining sample feature sets of multiple sample users; obtaining average feature values of similar features in multiple sample feature sets (For example, averaging the characteristics of the user in the reading application to view the length of the male reading in the reading application), and obtaining the gender reference feature set (in other words, the gender reference feature set, that is, the set of the average values of the various types of features) The gender reference feature set is used to describe the multi-dimensional characteristics of the male user in a biased manner, or to describe the multi-dimensional characteristics of the female user in a biased manner; Obtain multi-dimensional features of gender-identified users in the process of application use (such as obtaining the length of time that user a browses male/female readings in reading applications, and obtaining user a to browse male/female products in shopping applications) The number of times and duration, etc.), obtain the feature set of the unknown gender user; obtain the similarity between the feature set of the unknown gender user and the gender reference feature set, and identify the gender of the unknown gender user according to the similarity between the two (for example, identifying the user a as a male) , or female).

Please refer to FIG. 2 , which is a schematic flowchart of a user gender identification method according to an embodiment of the present application. The specific process of the user gender identification method provided by the embodiment of the present application may be as follows:

201. Acquire a multi-dimensional feature that the plurality of sample users have gender recognition during the application, and obtain a sample feature set of the plurality of sample users.

Wherein, the multi-dimensional feature has a dimension of a certain length, that is, the multi-dimensional feature is composed of a plurality of features. The multi-dimensional feature may include gender-recognized behavior characteristics of the user in the process of using the application, for example, the number and duration of browsing the male-type goods (such as men's wear, razors, etc.) in the shopping application, and the user is shopping. The number and duration of browsing female-oriented goods (such as cosmetics, women's clothing, etc.) in the application, the length of time that the user reads the male-like readings in the reading application, and the length of time the user reads the female-oriented readings in the reading application.

In addition, the multi-dimensional feature may further include related behavior characteristic information with the electronic device itself, for example, the number of times the user uses the shooting-type application to call the front camera, the number of times the user uses the shooting-type application to call the rear camera, and the like.

The obtained sample feature set is multiple, and corresponds to each sample user. The multi-dimensional features in each sample feature set may be acquired according to a preset frequency within a historical time period. The historical time period may be, for example, the past 7 days or 10 days; the preset frequency may be, for example, collected every 10 minutes and collected every half hour. It can be understood that, for any sample user, the multi-dimensional feature classification of the sample user collected each time in the historical time period is accumulated (for example, the feature "user browses the male-type goods in the shopping application" is accumulated. For the feature "the user accumulates the partial female products in the shopping application", the sample feature set of the sample user in the historical time period is obtained. For example, for the male user b, by acquiring the multi-dimensional feature of the male user b with gender recognition during the application, the sample feature set (X1, X2, ..., Xn) corresponding to the male user b is obtained, where Xn is One-dimensional feature of user b.

In an embodiment, the multi-dimensional features of each known gender user based on their electronic device usage application process may be collected by the server, and then the electronic device may be obtained from the server at the time of gender recognition. Among them, a gender user is known to be a user who provides gender information when using an electronic device, for example, a user who provides gender information when the account is registered.

After constituting the sample feature set, each sample feature set may be marked to obtain a sample tag of each sample feature set. Since the embodiment of the present application is to identify the gender of the unknown gender user, the labeled sample is The labels include “male” and “female”, ie the sample categories include males and females.

In a specific implementation, the gender information of the known gender user may be marked, for example, the sample feature set corresponding to the male user b may be marked as “male”; for example, the sample feature set corresponding to the female user c may be marked as "female". Alternatively, the sample feature set may be marked using a number, such as the number "1" for "male", the number "0" for "female", and vice versa.

In an embodiment, in order to facilitate subsequent processing of the sample feature set, “acquiring a multi-sample feature that has multiple genders in the application process and obtaining a sample feature set of the plurality of sample users” may include:

The obtained multi-dimensional features are normalized to obtain a sample feature set of a plurality of sample users.

Among them, normalization is a way to simplify the calculation, that is, a dimensional representation, transformed into a dimensionless expression, becomes a scalar. For the specific normalization method, it can be selected by a person skilled in the art according to actual needs, which is not specifically limited in this application.

For example, for the multi-dimensional feature of the sample user “male user b”, the embodiment of the present application normalizes each dimension feature in the multi-dimensional feature, and normalizes the original feature value to a value between 0-1, and then The normalized multidimensional features constitute a sample feature set of male user b.

202. Acquire an average feature value of a similar feature in the plurality of sample feature sets to obtain a gender reference feature set.

As described above, in the embodiment of the present application, the obtained sample feature set is gender-marked, so the calculation of the average feature value can be performed based on the gender flag of the sample feature set. For example, for a sample feature set labeled "male", the average feature value of each feature in the "male" sample feature set can be calculated; for example, for a sample feature set labeled "female", it can be calculated The average eigenvalue of each feature in the "female" sample feature set.

Correspondingly, because the calculated average eigenvalues are different, the obtained gender reference feature sets are also different. For example, when only the average feature value of the same feature in the "male" sample feature set is calculated, then the obtained gender reference feature set is a male reference feature set characterizing "male"; for example, only the "female" sample feature set is calculated. When the average eigenvalues of the similar features are obtained, then the obtained gender reference feature set is a female reference feature set representing "female"; for example, in calculating the average eigenvalue of the same feature in the "male" sample feature set, and calculating " When the female eigenvalues of the similar features in the sample feature set are averaged, a female reference feature set characterizing "female" and a male reference feature set characterizing "male" are respectively obtained.

203. Acquire a multi-dimensional feature of the gender-identified user in the application process, and obtain a feature set of the user of the unknown gender.

The feature set of the unknown gender user may be collected according to a preset frequency within a historical time period. The historical time period may be, for example, the past 7 days or 10 days; the preset frequency may be, for example, collected every 10 minutes and collected every half hour. It can be understood that, for an unknown gender user, the multi-dimensional feature classification of the unknown gender user collected each time in the historical time period is accumulated (for example, the feature “user browses the male-type commodity in the shopping application” is accumulated, For the feature "the user accumulates the partial female products in the shopping application", the feature set of the unknown gender user in the historical time period is obtained. For example, for the user a of unknown gender, the feature set (X1, X2, ..., Xn) of the corresponding user a is obtained by acquiring the multi-dimensional feature of the user a having gender recognition during the application use, wherein Xn is the user a. One-dimensional features.

In order to improve the accuracy of identifying the user's gender, in an embodiment, the historical time period selected by the multi-dimensional feature of the unknown gender user is the same as the historical time period selected by the sample user (ie, the known gender user). For example, when the historical time period selected by the multi-dimensional feature of the sample user is 7 days, when the multi-dimensional feature of the user of the unknown gender is collected, the historical time period is also selected as 7 days. In this way, the gender reference feature set obtained by processing the sample feature set will be in the same time dimension as the feature set of the unknown gender user, thereby achieving the purpose of improving the gender accuracy of the identified user.

204. Acquire a similarity between the feature set and the gender reference feature set, and identify the gender of the unknown gender user according to the similarity.

Among them, the gender reference feature set obtained in the previous step is different, and the gender mode of identifying the unknown gender user according to the similarity is also different. For example, in an embodiment, when the previously obtained gender reference feature set includes a male reference feature set and a female reference feature set, “acquiring the similarity between the feature set and the gender reference feature set, and identifying the unknown gender user according to the similarity degree. Gender can include:

Obtaining a first similarity between the feature set of the unknown gender user and the male reference feature set;

Obtaining a second similarity between the feature set of the unknown gender user and the female reference feature set;

Comparing the magnitudes of the first similarity and the second similarity;

If the first similarity is greater than the second similarity, the unknown gender user is identified as a male user, otherwise the unknown gender user is identified as a female user.

The terms "first," "second," and "third," etc. in this application are used to distinguish different objects, and are not intended to describe a particular order.

The manner of obtaining the first similarity is the same as the manner of obtaining the second similarity. For example, in the embodiment of the present application, the distance between the feature set and the gender reference feature set is used to describe the similarity between the feature set and the gender reference feature set. The larger the distance, the smaller the similarity, the smaller the distance, and the greater the similarity. It should be noted that the method for calculating the distance between the feature set and the gender reference feature set is not limited in the embodiment of the present application, and a suitable calculation method may be selected by a person skilled in the art according to actual needs.

For example, in the embodiment of the present application, the distance between the feature set and the gender reference feature set is calculated according to the following formula:

Where l represents the distance between the feature set of the unknown gender user and the gender reference feature set, and Xn represents the one-dimensional feature in the gender reference feature set.

A one-dimensional feature in a feature set representing an unknown gender user. When the values of "n" are the same, Xn and

Corresponding to the same feature, for example, X1 represents the feature in the gender reference feature set "the length of time the user reads the partial male reading in the reading application",

A feature in a feature set representing an unknown gender user "the length of time a user reads a partial male reading in a reading application." n is a positive integer greater than 2.

The first similarity and the second similarity are obtained after the first similarity of the feature set of the unknown gender user and the male reference feature set is obtained, and the second similarity of the unknown gender user and the female reference feature set is obtained. The size is compared to identify the gender of an unknown gender user based on the similarity comparison result.

Specifically, when the first similarity is greater than the second similarity, the unknown gender user is more similar to the male user, and the unknown gender user is identified as the male user; when the first similarity is less than the second similarity, the unknown gender is indicated. The user is more similar to the female user. At this time, the user who identifies the unknown gender is the female user. When the first similarity and the second similarity are the same, it indicates that the feature set of the unknown gender user collected at this time is not enough to support the identification of the gender. At this time, there is no recognition result.

In an embodiment, when the previously obtained gender reference feature set is a male reference feature set, “acquiring the similarity of the feature set and the gender reference feature set, and identifying the gender of the unknown gender user according to the similarity” may include:

Obtaining a distance between the feature set of the unknown gender user and the male reference feature set, and using the distance as the similarity between the feature set and the male reference feature set;

Determining whether the distance between the feature set and the male reference feature set is located in the first preset distance interval;

If yes, the user who identifies the unknown gender is a male user, otherwise the user who identifies the unknown gender is a female user.

The distance between the feature set and the male reference feature set is used to describe the similarity between the feature set and the male reference feature set. The smaller the distance, the larger the similarity, the larger the distance, and the smaller the similarity. It should be noted that the method for calculating the distance between the feature set and the male reference feature set is not limited in specific embodiments, and a suitable calculation method may be selected by a person skilled in the art according to actual needs.

For example, in the embodiment of the present application, the distance between the feature set and the male reference feature set is calculated according to the following formula:

Where l represents the distance between the feature set of the unknown gender user and the male reference feature set, and Xn represents the one-dimensional feature in the male reference feature set.

Corresponding to the same feature, for example, X1 represents the feature in the male reference feature set "the length of time the user reads the partial male reading in the reading application",

A feature in a feature set representing an unknown gender user "the length of time a user reads a partial male reading in a reading application."

After obtaining the distance between the feature set of the unknown gender user and the male reference feature set, it is further determined whether the distance is located in the first preset distance interval. Specifically, when the distance is within the first preset distance interval, the unknown gender user is inclined to be a male user, and the unknown gender user is identified as a male user; the distance is outside the first preset distance interval. At the same time, it is indicated that the user of the unknown gender does not tend to be a male user. Obviously, the gender of the user is not male or female, and the unknown gender user can be identified as a female user at this time.

In addition, for the setting of the first preset distance interval, the distance between each sample feature set labeled "male" and the male reference feature set may be calculated, and the maximum distance among the distances is taken as the right side of the first preset distance interval. Endpoint and set the left endpoint of the first preset distance interval to zero.

In an embodiment, when the previously obtained gender reference feature set is a female reference feature set, “acquiring the similarity between the feature set and the gender reference feature set, and identifying the gender of the unknown gender user according to the similarity” may include:

Obtaining a distance between the feature set of the unknown gender user and the female reference feature set, and using the distance as the similarity between the feature set and the female reference feature set;

Determining whether the distance is in a second preset distance interval;

If yes, the user who identifies the unknown gender is a female user, otherwise the user who identifies the unknown gender is a male user.

The distance between the feature set and the female reference feature set is used to describe the similarity between the feature set and the female reference feature set. The smaller the distance, the greater the similarity, the larger the distance, and the smaller the similarity. It should be noted that the method for calculating the distance between the feature set and the female reference feature set is not specifically limited in the embodiment of the present application, and a suitable calculation manner may be selected by a person skilled in the art according to actual needs.

For example, in the embodiment of the present application, the distance between the feature set and the female reference feature set is calculated according to the following formula:

Wherein, l represents the distance between the feature set of the unknown gender user and the female reference feature set, and Xn represents the one-dimensional feature in the female reference feature set.

Corresponding to the same feature, for example, X1 represents the feature in the female reference feature set "the length of time the user reads the partial male reading in the reading application",

After obtaining the distance between the feature set of the unknown gender user and the female reference feature set, it is further determined whether the distance is located in the second preset distance interval. Specifically, when the distance is within the second preset distance interval, the unknown gender user tends to be a female user, and the unknown gender user is identified as a female user; the distance is outside the second preset distance interval. At the same time, it is indicated that the user of the unknown gender does not tend to be a female user. Obviously, the gender of the user is not male or female, and the unknown gender user can be identified as a male user at this time.

In addition, for the setting of the second preset distance interval, the distance between each sample feature set labeled as “female” and the female reference feature set may be calculated, and the maximum distance among the distances is taken as the right side of the second preset distance interval. Endpoint and set the left endpoint of the second preset distance interval to zero.

As can be seen from the above, the embodiment of the present application first obtains multi-dimensional features of multiple sample users that have gender recognition during application, obtain sample feature sets of multiple sample users, and then obtain average features of similar features in multiple sample feature sets. Value, obtain the gender reference feature set, and then obtain the gender-recognition multi-dimensional feature of the unknown gender user in the application process, obtain the feature set of the unknown gender user, and finally obtain the similarity between the feature set and the gender reference feature set, and according to the similarity To predict the gender of an unknown gender user, so as to accurately identify the gender of the user and obtain the gender information of the user.

The user gender recognition method of the present application will be further described below based on the method described in the above embodiments. Referring to FIG. 3, the user gender identification method may include:

301. Acquire multiple sample users with gender-recognizing multi-dimensional features during application use.

Among them, the multi-dimensional feature is a multi-dimensional user feature in which a gender user such as a male user or a female user has gender identity during application use. For example, a user has a behavioral characteristic with male or female characteristics in the application process.

The obtained sample feature set is multiple, and corresponds to each sample user. The multi-dimensional features in each sample feature set may be acquired according to a preset frequency within a historical time period. The historical time period may be, for example, the past 7 days or 10 days; the preset frequency may be, for example, collected every 10 minutes and collected every half hour. It can be understood that, for any sample user, the multi-dimensional feature classification of the sample user collected each time in the historical time period is accumulated (for example, the feature "user browses the male-type goods in the shopping application" is accumulated. For the feature "the user accumulates the partial female products in the shopping application", the sample feature set of the sample user in the historical time period is obtained. For example, for the male user b, by obtaining the multi-dimensional feature of the male user b with gender recognition during the application, the sample feature set (X1, X2, ..., Xn) corresponding to the male user b is obtained, where Xn is One-dimensional feature of user b.

302. Perform normalization processing on the acquired multi-dimensional features to obtain a sample feature set of multiple sample users.

A specific set of sample features can be as shown in Table 1 below, including features of multiple dimensions. It should be noted that the features shown in Table 1 are only examples. In practical applications, the number of features included in a sample feature set, The number of features shown in Table 1 may be less than the number of features shown in Table 1, and the specific features may be different from those shown in Table 1, and are not specifically limited herein.

维度Dimension	特征信息Characteristic information
11	用户在购物类应用中浏览偏男性类商品(如男装)的次数The number of times a user viewed a male-type item (such as a men's clothing) in a shopping application.
22	用户在购物类应用中浏览偏男性类商品(如男装)的时长How long does a user browse a male-like item (such as a men's clothing) in a shopping app?
33	用户在购物类应用中浏览偏女性类商品(如化妆品、女装)的次数The number of times a user viewed a female product (such as cosmetics, women's clothing) in a shopping application

44	用户在购物类应用中浏览偏女性类商品(如化妆品、女装)的时长The length of time users browse women-oriented items (such as cosmetics, women's clothing) in the shopping app
55	用户在阅读类应用中阅读偏男性类读物的时长The length of time users read a male-like reading in a reading application
66	用户在阅读类应用中阅读偏女性类读物的时长The length of time a user reads a female reading in a reading application
77	用户在新闻类应用中阅读体育类新闻的时长How long do users read sports news in news apps?
88	用户在新闻类应用中阅读星座类新闻的时长The length of time users read constellation news in news applications
99	用户使用拍摄类应用调用前置摄像头自拍的次数The number of times the user uses the shooting application to call the front camera self-timer
1010	用户使用美颜类应用的次数Number of times users use beauty apps
1111	用户玩不同类别游戏应用的次数Number of times users play different types of game apps
1212	用户玩不同类别游戏应用的时长How long do users play different types of game apps?

Table 1

303. Acquire an average feature value of a similar feature in the plurality of sample feature sets to obtain a gender reference feature set.

304. Acquire a multi-dimensional feature of the gender-identified user in the application process, and obtain a feature set of the user of the unknown gender.

305. Acquire a first similarity between the feature set and the male reference feature set.

That is, the first similarity between the feature set of the unknown gender user and the male reference feature set is calculated.

306. Acquire a second similarity between the feature set and the female reference feature set.

That is, the second similarity of the feature set of the unknown gender user and the female reference feature set is calculated.

The manner of obtaining the first similarity is the same as the manner of obtaining the second similarity. For example, in the embodiment of the present application, the distance between the feature set and the gender reference feature set is used to describe the similarity between the feature set and the gender reference feature set. The larger the distance, the smaller the similarity, and the smaller the distance, the greater the similarity. It should be noted that the method for calculating the distance between the feature set and the gender reference feature set is not limited in specific embodiments, and a suitable calculation method may be selected by a person skilled in the art according to actual needs.

307. Compare the sizes of the first similarity and the second similarity.

308. If the first similarity is greater than the second similarity, identify the unknown gender user as a male user, and otherwise identify the unknown gender user as a female user.

The embodiment of the present application further provides a user gender identification device, including:

In some embodiments, the gender reference feature set includes a male reference feature set and a female reference feature set, and the user gender identification module is further configured to:

Comparing the magnitudes of the first similarity and the second similarity;

In some embodiments, the gender reference feature set is a male reference feature set, and the user gender identification module is further configured to:

Determining whether the distance is in a first preset distance interval;

In some embodiments, the gender reference feature set is a female reference feature set, and the user gender identification module is further configured to:

Determining whether the distance is in a second preset distance interval;

In some embodiments, the first feature acquisition module is further configured to:

In some embodiments, the user gender identification module is configured to calculate a distance between the feature set and the gender reference feature set by:

Corresponding to the same feature, n is a positive integer greater than 2.

In some embodiments, the second feature acquisition module is configured to: collect, during a historical time period, a multi-dimensional feature of an unknown gender user having gender recognition during application use according to a preset frequency.

In some embodiments, the set of gender reference features comprises a set of male reference features and a set of female reference features;

User gender identification module for:

Comparing the magnitudes of the first similarity and the second similarity;

A user gender identification device is also provided in an embodiment. Please refer to FIG. 4. FIG. 4 is a schematic structural diagram of a user gender identification apparatus according to an embodiment of the present application. The user gender identification device is applied to the electronic device, and the user gender recognition device includes a first feature acquisition module 401, a feature set generation module 402, a second feature acquisition module 403, and a user gender identification module 404 as follows:

The first feature obtaining module 401 is configured to obtain a multi-dimensional feature that the plurality of sample users have gender recognition during the application, and obtain a sample feature set of the plurality of sample users;

The feature set generation module 402 is configured to obtain an average feature value of a similar feature in the plurality of sample feature sets, to obtain a gender reference feature set;

The second feature acquisition module 403 is configured to obtain a multi-dimensional feature that is gender-recognized by an unknown gender user during use, and obtain a feature set of an unknown gender user;

The user gender identification module 404 is configured to obtain the similarity between the feature set and the gender reference feature set, and identify the gender of the unknown gender user according to the similarity.

In an embodiment, the gender reference feature set includes a male reference feature set and a female reference feature set, and the user gender identification module 404 can be used to:

Comparing the magnitudes of the first similarity and the second similarity;

In an embodiment, the gender reference feature set is a male reference feature set, and the user gender identification module 404 can be used to:

In an embodiment, the gender reference feature set is a female reference feature set, and the user gender identification module 404 can be used to:

Determining whether the distance is in a second preset distance interval;

In an embodiment, the first feature obtaining module 401 can be used to:

The acquired multi-dimensional features are normalized to obtain a sample feature set of multiple sample users.

In an embodiment, the similarity between the feature set and the gender reference feature set includes: a distance between the feature set and the gender reference feature set.

In an embodiment, the user gender identification module 404 is configured to calculate a distance between the feature set and the gender reference feature set by using the following formula:

Corresponding to the same feature, n is a positive integer greater than 2.

In an embodiment, the second feature acquiring module 403 is configured to: collect, according to a preset frequency, a multi-dimensional feature that the user of the unknown gender has gender recognition during the application in the historical time period.

In an embodiment, the gender reference feature set includes a male reference feature set and a female reference feature set;

User gender identification module 404 for:

Comparing the magnitudes of the first similarity and the second similarity;

The term "module" "unit" as used herein may be taken to mean a software object that is executed on the computing system. The different components, modules, engines, and services described herein can be considered as implementation objects on the computing system. The apparatus and method described herein may be implemented in software, and may of course be implemented in hardware, all of which are within the scope of the present application. The steps performed by each module in the user gender identification device may refer to the method steps described in the foregoing method embodiments. The user gender identification device can be integrated in an electronic device such as a mobile phone, a tablet, or the like.

For the specific implementation, the foregoing modules may be implemented as an independent entity, or may be implemented in any combination, and may be implemented as the same entity or a plurality of entities. For the specific implementation of the foregoing units, refer to the foregoing embodiments, and details are not described herein again.

It can be seen from the above that the user gender identification device of the embodiment can obtain the multi-dimensional feature that the plurality of sample users have gender recognition during the application use process, and obtain the sample feature set of the plurality of sample users; The generating module 402 obtains the average feature value of the same feature in the plurality of sample feature sets to obtain the gender reference feature set; and the second feature acquiring module 403 obtains the multi-dimensional feature of the gender-identified user in the application process, and obtains the unknown gender. The feature set of the user is obtained by the user gender identification module 404, and the gender of the unknown gender user is predicted according to the similarity, so that the gender of the user is accurately recognized, and the gender information of the user is obtained.

An embodiment of the present application further provides an electronic device. Referring to FIG. 5, the electronic device 500 includes a processor 501 and a memory 502. The processor 501 is electrically connected to the memory 502.

The processor 500 is a control center of the electronic device 500 that connects various portions of the entire electronic device using various interfaces and lines, by running or loading a computer program stored in the memory 502, and recalling data stored in the memory 502, The various functions of the electronic device 500 are performed and the data is processed to achieve accurate identification of the user's gender.

The memory 502 can be used to store software programs and modules, and the processor 501 executes various functional applications and data processing by running computer programs and modules stored in the memory 502. The memory 502 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, a computer program required for at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may be stored according to Data created by the use of electronic devices, etc. Moreover, memory 502 can include high speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, memory 502 can also include a memory controller to provide processor 501 access to memory 502.

In the embodiment of the present application, the processor 501 in the electronic device 500 loads the instructions corresponding to the process of one or more computer programs into the memory 502 according to the following steps, and is stored in the memory 502 by the processor 501. The computer program in which to implement various functions, as follows:

Obtaining multi-dimensional features of multiple sample users with gender recognition during application use, and obtaining sample feature sets of multiple sample users;

Obtaining a gender-recognized multi-dimensional feature of an unknown gender user during application use, and obtaining a feature set of an unknown gender user;

The similarity between the feature set and the gender reference feature set is obtained, and the gender of the unknown gender user is identified according to the similarity.

In some embodiments, the gender reference feature set includes a male reference feature set and a female reference feature set, and obtains a similarity between the feature set and the gender reference feature set, and identifies a gender of the unknown gender user according to the similarity, the processor 501 can perform the following steps:

Comparing the magnitudes of the first similarity and the second similarity;

In some embodiments, when the gender reference feature set is a male reference feature set, and the similarity between the feature set and the gender reference feature set is acquired, and the gender of the unknown gender user is identified according to the similarity, the processor 501 may specifically execute the following: step:

In some embodiments, when the gender reference feature set is a female reference feature set, and the similarity between the feature set and the gender reference feature set is acquired, and the gender of the unknown gender user is identified according to the similarity, the processor 501 may specifically execute the following: step:

Determining whether the distance is in a second preset distance interval;

In some embodiments, the processor 501 may further perform the following steps when acquiring a multi-dimensional feature that the plurality of sample users have gender-recognition during application use, and obtaining a sample feature set of the plurality of sample users:

In some embodiments, the similarity between the feature set and the gender reference feature set includes: a distance between the feature set and the gender reference feature set

In some embodiments, when acquiring the similarity between the feature set and the gender reference feature set, the processor 501 may specifically perform the following steps:

Corresponding to the same feature, n is a positive integer greater than 2.

In some embodiments, the processor 501 may perform the following steps when acquiring a multi-dimensional feature of the gender-identified user during the application use process:

In the historical time period, the multi-dimensional features of the gender-identified users in the application process are collected according to the preset frequency.

In some embodiments, the gender reference feature set includes a male reference feature set and a female reference feature set; the acquiring the similarity of the feature set and the gender reference feature set, and identifying according to the similarity When the gender of the unknown gender user is used, the processor 501 may further perform the following steps:

Comparing the magnitudes of the first similarity and the second similarity;

As can be seen from the above, the embodiment of the present application first obtains a charging feature set when charging behavior occurs, and obtains a plurality of charging feature sets; then performs similarity recognition on the plurality of charging feature sets to obtain a similar charging feature set; and then according to the similar charging feature set. Predicting the next charging behavior; determining the corresponding performance adjustment mode according to the predicted next charging behavior; finally performing performance adjustment operation according to the determined performance adjustment mode, thereby realizing dynamic adjustment of the performance of the electronic device itself, and satisfying the actual use of the user demand.

Referring to FIG. 6 together, in some embodiments, the electronic device 500 may further include: a display 503, a radio frequency circuit 504, an audio circuit 505, and a power source 506. The display 503, the radio frequency circuit 504, the audio circuit 505, and the power source 506 are electrically connected to the processor 501, respectively.

The display 503 can be used to display information entered by a user or information provided to a user, as well as various graphical user interfaces, which can be composed of graphics, text, icons, video, and any combination thereof. The display 503 can include a display panel. In some embodiments, the display panel can be configured in the form of a liquid crystal display (LCD) or an organic light-emitting diode (OLED).

The radio frequency circuit 504 can be used to transmit and receive radio frequency signals to establish wireless communication with a network device or other electronic device through wireless communication, and to transmit and receive signals with a network device or other electronic device.

The audio circuit 505 can be used to provide an audio interface between a user and an electronic device through a speaker or a microphone.

The power source 506 can be used to power various components of the electronic device 500. In some embodiments, the power source 506 can be logically coupled to the processor 501 through a power management system to enable functions such as managing charging, discharging, and power management through the power management system.

Although not shown in FIG. 8, the electronic device 500 may further include a camera, a Bluetooth module, and the like, and details are not described herein again.

The embodiment of the present application further provides a storage medium, where the storage medium stores a computer program, and when the computer program runs on a computer, causes the computer to perform the user gender identification method in any of the above embodiments, such as: Obtaining multi-dimensional features of multiple sample users in the process of application use, obtaining sample feature sets of multiple sample users; obtaining average feature values of similar features in multiple sample feature sets, obtaining gender reference feature sets; obtaining unknown The gender user has the gender-recognition multi-dimensional feature in the application process, obtains the feature set of the unknown gender user; obtains the similarity between the feature set and the gender reference feature set, and identifies the gender of the unknown gender user according to the similarity degree.

In the embodiment of the present application, the storage medium may be a magnetic disk, an optical disk, a read only memory (ROM), or a random access memory (RAM).

In the above embodiments, the descriptions of the various embodiments are different, and the details that are not detailed in a certain embodiment can be referred to the related descriptions of other embodiments.

It should be noted that, in the user gender identification method of the embodiment of the present application, a general tester in the field can understand all or part of the process of implementing the user gender identification method in the embodiment of the present application, and the related hardware can be controlled by a computer program. To complete, the computer program may be stored in a computer readable storage medium, such as in a memory of the electronic device, and executed by at least one processor in the electronic device, and may include, for example, user gender during execution. The flow of an embodiment of the identification method. The storage medium may be a magnetic disk, an optical disk, a read only memory, a random access memory, or the like.

For the user gender identification device of the embodiment of the present application, each functional module may be integrated into one processing chip, or each module may exist physically separately, or two or more modules may be integrated into one module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. The integrated module, if implemented in the form of a software functional module and sold or used as a standalone product, may also be stored in a computer readable storage medium, such as a read only memory, a magnetic disk or an optical disk, etc. .

The user gender identification method, apparatus, storage medium, and electronic device provided by the embodiments of the present application are described in detail. The principles and implementation manners of the present application are described in the specific examples, and the foregoing embodiments are described. It is only used to help understand the method of the present application and its core idea; at the same time, for those skilled in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. The contents of the description should not be construed as limiting the application.

Claims

A user gender identification method, which includes:

Obtaining a multi-dimensional feature of the plurality of sample users having gender recognition during application use, and obtaining a sample feature set of the plurality of sample users;

Obtaining average eigenvalues of similar features in the plurality of sample feature sets to obtain a gender reference feature set;

Obtaining a gender-recognized multi-dimensional feature of an unknown gender user during application use, and obtaining a feature set of the unknown gender user;

Obtaining a similarity between the feature set and the gender reference feature set, and identifying a gender of the unknown gender user according to the similarity.
The user gender identification method according to claim 1, wherein the gender reference feature set comprises a male reference feature set and a female reference feature set, wherein the similarity of the feature set and the gender reference feature set is obtained, and The step of identifying the gender of the unknown gender user based on the similarity includes:

Obtaining a first similarity between the feature set and the male reference feature set;

Obtaining a second similarity between the feature set and the female reference feature set;

Comparing the magnitudes of the first similarity and the second similarity;

If the first similarity is greater than the second similarity, the unknown gender user is identified as a male user, and the unknown gender user is identified as a female user.
The user gender identification method according to claim 1, wherein the gender reference feature set is a male reference feature set, and the similarity between the feature set and the gender reference feature set is acquired, and according to the similarity The steps of identifying the gender of the unknown gender user include:

Obtaining a distance between the feature set and the male reference feature set, and using the distance as a similarity between the feature set and the male reference feature set;

Determining whether the distance is in a first preset distance interval;

If yes, the unknown gender user is identified as a male user, otherwise the unknown gender user is identified as a female user.
The user gender identification method according to claim 1, wherein the gender reference feature set is a female reference feature set, and the similarity between the feature set and the gender reference feature set is acquired, and according to the similarity The steps of identifying the gender of the unknown gender user include:

Obtaining a distance between the feature set and the female reference feature set, and using the distance as a similarity between the feature set and the female reference feature set;

Determining whether the distance is in a second preset distance interval;

If yes, the unknown gender user is identified as a female user, otherwise the unknown gender user is identified as a male user.
The user gender identification method according to claim 1, wherein the obtaining a plurality of sample users having gender-recognized multi-dimensional features during application use, and obtaining the sample feature sets of the plurality of sample users comprises:

Obtain multi-dimensional features of multiple sample users with gender recognition during application use;

And normalizing the obtained multi-dimensional features to obtain a sample feature set of the plurality of sample users.
The user gender identification method according to claim 1, wherein the similarity between the feature set and the gender reference feature set comprises: a distance between the feature set and the gender reference feature set.
The user gender identification method according to claim 6, wherein the step of acquiring the similarity between the feature set and the gender reference feature set comprises:

The distance between the feature set and the gender reference feature set is calculated by the following formula:

Wherein, l represents the distance between the feature set and the gender reference feature set, and Xn represents a one-dimensional feature in the gender reference feature set.
A one-dimensional feature in a feature set representing an unknown gender user. When the values of n are the same, Xn and
Corresponding to the same feature, n is a positive integer greater than 2.
The user gender identification method according to claim 1, wherein the step of acquiring a multi-dimensional feature of the gender-identified user during the application use process comprises: collecting the unknown gender user in the application process according to the preset frequency in the historical time period. Among the multi-dimensional features of gender recognition.
The user gender identification method according to claim 1, wherein the gender reference feature set comprises a male reference feature set and a female reference feature set; and the obtaining the similarity between the feature set and the gender reference feature set, and The step of identifying the gender of the unknown gender user based on the similarity includes:

Obtaining a first similarity between the feature set and the male reference feature set;

Obtaining a second similarity between the feature set and the female reference feature set;

Comparing the magnitudes of the first similarity and the second similarity;

If the first similarity is greater than the second similarity, identifying the unknown gender user as a male user;

If the first similarity is less than the second similarity, identifying the unknown gender user as a female user;

If the first similarity is the second similarity, there is no recognition result. 10. A user gender identification device, comprising:

a first feature acquiring module, configured to acquire a multi-dimensional feature of the plurality of sample users that has gender recognition during use of the application, and obtain a sample feature set of the plurality of sample users;

a feature set generating module, configured to obtain an average feature value of a similar feature in the plurality of sample feature sets, to obtain a gender reference feature set;

a second feature acquisition module, configured to acquire a multi-dimensional feature that is gender-recognized by an unknown gender user during application use, and obtain a feature set of the unknown gender user;

The user gender identification module is configured to acquire the similarity between the feature set and the gender reference feature set, and identify the gender of the unknown gender user according to the similarity.
The user gender identification device of claim 10, wherein the gender reference feature set comprises a male reference feature set and a female reference feature set, the user gender identification module, further configured to:

Obtaining a first similarity between the feature set and the male reference feature set;

Obtaining a second similarity between the feature set and the female reference feature set;

Comparing the magnitudes of the first similarity and the second similarity;

If the first similarity is greater than the second similarity, the unknown gender user is identified as a male user, and the unknown gender user is identified as a female user.
The user gender identification device of claim 10, wherein the gender reference feature set is a male reference feature set, and the user gender identification module is further configured to:

Obtaining a distance between the feature set and the male reference feature set, and using the distance as a similarity between the feature set and the male reference feature set;

Determining whether the distance is in a first preset distance interval;

If yes, the unknown gender user is identified as a male user, otherwise the unknown gender user is identified as a female user.
The user gender identification device according to claim 10, wherein the gender reference feature set is a female reference feature set, and the user gender identification module is further configured to:

Obtaining a distance between the feature set and the female reference feature set, and using the distance as a similarity between the feature set and the female reference feature set;

Determining whether the distance is in a second preset distance interval;

If yes, the unknown gender user is identified as a female user, otherwise the unknown gender user is identified as a male user.
The user gender identification device of claim 10, wherein the first feature acquisition module is further configured to:

Obtain multi-dimensional features of multiple sample users with gender recognition during application use;

And normalizing the obtained multi-dimensional features to obtain a sample feature set of the plurality of sample users.
The user gender recognition apparatus according to claim 10, wherein the similarity between the feature set and the gender reference feature set comprises: a distance between the feature set and the gender reference feature set.
The user gender identification device according to claim 15, wherein the user gender identification module is configured to calculate a distance between the feature set and the gender reference feature set by the following formula:

Wherein, l represents the distance between the feature set and the gender reference feature set, and Xn represents a one-dimensional feature in the gender reference feature set.
A one-dimensional feature in a feature set representing an unknown gender user. When the values of n are the same, Xn and
Corresponding to the same feature, n is a positive integer greater than 2.
The user gender identification device according to claim 10, wherein the second feature acquisition module is configured to: collect, according to a preset frequency, a multi-dimensional feature that the gender user has gender recognition during the application use period according to the preset frequency.
The user gender identification device of claim 10, wherein the gender reference feature set comprises a male reference feature set and a female reference feature set;

User gender identification module for:

Obtaining a first similarity between the feature set and the male reference feature set;

Obtaining a second similarity between the feature set and the female reference feature set;

Comparing the magnitudes of the first similarity and the second similarity;

If the first similarity is greater than the second similarity, identifying the unknown gender user as a male user;

If the first similarity is less than the second similarity, identifying the unknown gender user as a female user;

If the first similarity is the second similarity, there is no recognition result.
A storage medium having stored thereon a computer program, wherein when the computer program is run on a computer, the computer is caused to perform the user gender identification method according to any one of claims 1 to 9.
An electronic device comprising a processor and a memory, the memory storing a computer program, wherein the processor is configured to perform user gender recognition according to any one of claims 1 to 9 by calling the computer program method.