CN113268654A - User gender identification method and device and electronic equipment - Google Patents
User gender identification method and device and electronic equipment Download PDFInfo
- Publication number
- CN113268654A CN113268654A CN202010097122.2A CN202010097122A CN113268654A CN 113268654 A CN113268654 A CN 113268654A CN 202010097122 A CN202010097122 A CN 202010097122A CN 113268654 A CN113268654 A CN 113268654A
- Authority
- CN
- China
- Prior art keywords
- user
- browsing
- gender
- categories
- category
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000013145 classification model Methods 0.000 claims abstract description 37
- 230000006399 behavior Effects 0.000 claims description 61
- 238000012549 training Methods 0.000 claims description 53
- 238000002372 labelling Methods 0.000 claims description 11
- 238000007635 classification algorithm Methods 0.000 claims description 5
- 238000003066 decision tree Methods 0.000 claims description 5
- 238000007637 random forest analysis Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000004576 sand Substances 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000035935 pregnancy Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for identifying user gender and electronic equipment, wherein the method comprises the following steps: acquiring historical browsing behavior data of a user in a preset time period; acquiring categories to which the webpages corresponding to each piece of historical browsing behavior data belong, wherein the categories comprise female categories and male categories; acquiring a first browsing frequency and a first click frequency of a user on a webpage belonging to the female category and a second browsing frequency and a second click frequency of the user on the webpage belonging to the male category based on the historical browsing behavior data and the categories; and based on the first browsing times, the first click times, the second browsing times and the second click times, carrying out user gender identification through a pre-trained classification model to obtain a user gender identification result, so that the user gender identification intelligence is realized, and the accuracy of the user gender identification is improved.
Description
Technical Field
The invention relates to the technical field of software, in particular to a user gender identification method and device and electronic equipment.
Background
On one hand, the user gender is used as one of user characteristics in advertisement CTR (Click-Through-Rate) estimation, which plays a very important role in improving the accuracy of advertisement CTR estimation, especially the advertisement CTR estimation aiming at an e-commerce platform and information flow; on the other hand, user gender is also an indispensable item for constructing a user representation system.
However, in most cases, the electronic device provides a personal basic information detail page for the user, and the user fills in the gender of the user, so as to obtain the gender of the user, which has a large dependence on the user, and many users are often unwilling to fill in the personal basic information or mistakenly fill in the personal basic information, so that the electronic device cannot obtain or cannot accurately obtain the gender data of all the users, and a new method is urgently needed to obtain the gender of the user.
Disclosure of Invention
The embodiment of the invention provides a method and a device for identifying user gender and electronic equipment, which are used for realizing intelligent acquisition of the user gender and improving the accuracy of the user gender acquisition.
In a first aspect, an embodiment of the present invention provides a method for identifying a user gender, where the method includes:
acquiring historical browsing behavior data of a user in a preset time period;
acquiring categories to which the webpages corresponding to each piece of historical browsing behavior data belong, wherein the categories comprise female categories and male categories;
acquiring a first browsing frequency and a first click frequency of a user on a webpage belonging to the female category and a second browsing frequency and a second click frequency of the user on the webpage belonging to the male category based on the historical browsing behavior data and the categories;
and based on the first browsing times, the first click times, the second browsing times and the second click times, carrying out user gender identification through a pre-trained classification model to obtain a user gender identification result.
Optionally, based on the first browsing times, the first click times, the second browsing times, and the second click times, performing user gender identification through a pre-trained classification model to obtain a user gender identification result, including:
the following parameters were obtained as model input parameters:
a first ratio between the first browsing times and the total browsing times of all the webpages by the user, a second ratio between the first clicking times and the total clicking times of all the webpages by the user, a third ratio between the second browsing times and the total browsing times and a fourth ratio between the second clicking times and the total clicking times;
and inputting the model input parameters into the classification model to perform user gender identification, and obtaining a user gender identification result.
Optionally, the training method of the classification model includes:
acquiring a training sample set;
aiming at each training sample, acquiring a gender tendency weight of the user according to the first click times of the user on the webpage belonging to the female category and the second click times of the user on the webpage belonging to the male category;
performing gender labeling on each training sample according to the user gender tendency weight to obtain a gender label of each training sample;
and carrying out classification model training according to the training sample set and the gender label of each training sample.
Optionally, the classification algorithm adopted by the classification model is gradient boosting decision tree, random forest or extreme gradient boosting.
Optionally, the method further includes:
according to the user gender identification result, adding a user gender characteristic in the user portrait; and/or the presence of a gas in the gas,
and recommending the webpage to the user according to the gender identification result of the user.
Optionally, the historical browsing behavior data is advertisement browsing behavior data;
the obtaining of the category to which the webpage corresponding to each piece of historical browsing behavior data belongs includes:
acquiring three-level basic categories to which advertisement goods and/or services provided by a webpage corresponding to each piece of advertisement browsing behavior data belong;
and acquiring the gender category of the webpage corresponding to each piece of advertisement browsing behavior data according to the three-level basic categories.
In a second aspect, an embodiment of the present invention provides an apparatus for identifying a gender of a user, where the apparatus includes:
the acquisition unit is used for acquiring historical browsing behavior data of a user in a preset time period;
the category unit is used for acquiring categories to which the webpages corresponding to each piece of historical browsing behavior data belong, wherein the categories comprise female categories and male categories;
the statistical unit is used for acquiring a first browsing frequency and a first click frequency of the user on the webpage belonging to the female category and a second browsing frequency and a second click frequency of the user on the webpage belonging to the male category based on the historical browsing behavior data and the categories;
and the identification unit is used for carrying out user gender identification through a pre-trained classification model based on the first browsing times, the first click times, the second browsing times and the second click times to obtain a user gender identification result.
Optionally, the identification unit is configured to:
the following parameters were obtained as model input parameters:
a first ratio between the first browsing times and the total browsing times of all the webpages by the user, a second ratio between the first clicking times and the total clicking times of all the webpages by the user, a third ratio between the second browsing times and the total browsing times and a fourth ratio between the second clicking times and the total clicking times;
and inputting the model input parameters into the classification model to perform user gender identification, and obtaining a user gender identification result.
Optionally, the apparatus further comprises a training unit, configured to:
acquiring a training sample set;
aiming at each training sample, acquiring a gender tendency weight of the user according to the first click times of the user on the webpage belonging to the female category and the second click times of the user on the webpage belonging to the male category;
performing gender labeling on each training sample according to the user gender tendency weight to obtain a gender label of each training sample;
and carrying out classification model training according to the training sample set and the gender label of each training sample.
Optionally, the classification algorithm adopted by the classification model is gradient boosting decision tree, random forest or extreme gradient boosting.
Optionally, the apparatus further comprises:
the application unit is used for increasing the user gender characteristics in the user portrait according to the user gender identification result; and/or recommending the webpage to the user according to the gender identification result of the user.
Optionally, the historical browsing behavior data is advertisement browsing behavior data;
the category unit is used for:
acquiring three-level basic categories to which advertisement goods and/or services provided by a webpage corresponding to each piece of advertisement browsing behavior data belong; and acquiring the gender category of the webpage corresponding to each piece of advertisement browsing behavior data according to the three-level basic categories.
In a third aspect, an embodiment of the present invention also provides an electronic device, including a memory and one or more programs, where the one or more programs are stored in the memory and configured to be executed by one or more processors to execute operation instructions included in the one or more programs for performing the corresponding method according to any one of the first aspects.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of the method according to any one of claims 1 to 6.
One or more technical solutions in the embodiments of the present application have at least the following technical effects:
the embodiment of the application provides a method for identifying the gender of a user, which comprises the steps of obtaining historical browsing behavior data of the user in a preset time period; acquiring categories to which the webpages corresponding to each piece of historical browsing behavior data belong, wherein the categories comprise female categories and male categories; acquiring a first browsing frequency and a first click frequency of a user on a webpage belonging to the female category and a second browsing frequency and a second click frequency of the user on the webpage belonging to the male category based on historical browsing behavior data and the category; based on the first browsing times, the first click times, the second browsing times and the second click times, the gender identification result of the user is obtained by the classification model trained in advance, so that the intelligent acquisition of the gender of the user is realized, the dependence of the gender acquisition of the user on manual setting is reduced, the authenticity of the user is obtained by acquiring the male category and the female category of the webpage browsed and clicked by the user, the gender of the user is identified, and the accuracy of the gender identification of the user is improved.
Drawings
Fig. 1 is a schematic flowchart of a method for identifying a gender of a user according to an embodiment of the present disclosure;
fig. 2 is a block diagram of a user gender identification device according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
According to the technical scheme, the method for identifying the gender of the user is provided, the gender of the user is identified by the classification model trained in advance by acquiring the browsing and clicking parameters of the user on the male category webpage and the female category webpage, so that the gender of the user is intelligently acquired, and the accuracy of the gender identification of the user is improved.
The main implementation principle, the specific implementation mode and the corresponding beneficial effects of the technical scheme of the embodiment of the present application are explained in detail with reference to the accompanying drawings.
Examples
The embodiment of the application provides a user gender identification method, which can be applied to a browser, an e-commerce platform and other platforms needing user gender information, and can be used for carrying out user gender identification based on advertisement browsing behaviors or commodity browsing behaviors on the e-commerce platform. Referring to fig. 1, the method for identifying gender of a user includes:
s10, acquiring historical browsing behavior data of the user in a preset time period;
s12, obtaining categories to which the webpages corresponding to each piece of historical browsing behavior data belong, wherein the categories comprise female categories and male categories;
s14, acquiring a first browsing frequency and a first click frequency of the user on the webpage belonging to the female category and a second browsing frequency and a second click frequency of the user on the webpage belonging to the male category based on the historical browsing behavior data and the category;
and S16, based on the first browsing times, the first click times, the second browsing times and the second click times, carrying out user gender identification through a pre-trained classification model to obtain a user gender identification result.
In a specific implementation, the preset time period in S10 may be the last week, one month, three months, or the like. The historical browsing behavior data may be advertisement browsing behavior data or merchandise browsing behavior data on an e-commerce platform. Each piece of historical browsing behavior data comprises browsing time, browsed webpages and clicked webpages, the browsed webpages refer to webpages displayed by the electronic equipment and comprise display of webpage titles, webpage links or webpage keywords, and the clicked webpages refer to webpages clicked by users and opened by webpage links. For example: the user searches for a keyword 'top collar sweater', the electronic equipment searches for and obtains search results and displays 5 webpage results A1-A5, the user clicks and opens the webpage A1, then the webpages browsed by the user are A1-A5, and the webpages clicked by the user are A1.
For each web page included in the historical browsing behavior data, S12 is executed to obtain the category to which the web page belongs. Each web page is classified under different three levels of basic categories, such as: and the lipstick recommending webpage is divided into a makeup category according to the commodity 'lipstick' provided by the webpage. Many three-level basic categories have gender tendencies, such as categories "make-up", "women's shoes", "maternity wear", etc., most users who pay attention to these categories are women, so the web pages with female tendencies are classified under the female category, and the web pages with male tendencies are classified under the male category. When the category to which the web page belongs corresponding to the historical browsing behavior record is obtained, the three-level basic category to which the web page belongs can be obtained first, and then the gender category to which the web page belongs can be obtained according to the three-level basic category to which the web page belongs. For example, for the advertisement browsing behavior data, the three-level basic categories to which the advertisement goods and/or services provided by the webpage corresponding to each piece of advertisement browsing behavior data belong may be obtained first; and obtaining the gender category of the webpage corresponding to the advertisement browsing behavior data according to the three-level basic category of the webpage.
After obtaining the category to which the web page belongs at S12, S14 is performed to count the categories of the web pages browsed and clicked by the user. Based on the historical browsing behavior data and the category to which the webpage corresponding to the historical behavior data belongs, the first browsing times N of the user to the webpage belonging to the female category can be counted and obtained11And a first number of clicks C11And a second number of times N of browsing by the user of web pages belonging to the male category21And a second number of clicks C21. Further, S12 may also statistically obtain the total browsing times N of all web pages by the user based on the historical browsing behavior datasAnd total number of clicks Cs。
The first browsing times N of the parameter obtained by the category statistics11First number of clicks C11Second browsing times N21And a second number of clicks C21The gender tendency of the user can be truly reflected, and S16 is executed based on the parameter N11、C11、N21And C21And carrying out user gender identification through a pre-trained classification model to obtain a user gender identification result so as to realize intelligent identification of the user gender. Specifically, the parameter N can be directly set11、C11、N21And C21Inputting a pre-trained classification model as a model input parameter for customizationThe identification can also be based on the parameter N11、C11、N21And C21The following parameters were obtained as model input parameters:
number of views of female category/total number of views of category, i.e. first number of views N11And the total browsing times N of all the web pages by the usersFirst ratio of N between11/Ns；
Number of clicks on female category/total number of clicks category, i.e. the first number of clicks C11And the total click times C of the user on all the web pagessSecond ratio of C between11/Cs；
Number of times of browsing male categories/total number of times of browsing categories, i.e. the second number of times of browsing N21And the total browsing times NsThird ratio of N between21/Ns(ii) a And
number of clicks on female category/total number of clicks category, i.e. the second number of clicks C21And the total click times CsFourth ratio of C between21/Cs；
And inputting the obtained model input parameters into a classification model trained in advance to carry out user gender identification, and obtaining a user gender identification result. In order to increase the accuracy of the gender identification of the user, the total browsing times N of the user to all the webpages can be further determinedsTotal number of clicks CsFirst browsing times N11First number of clicks C11Second browsing times N21And a second number of clicks C21A first ratio N11/NsA second ratio C11/CsA third ratio N21/NsAnd a fourth ratio C21/CsAnd inputting the classification recognition model as a model input parameter for user gender recognition. The parameters for user gender identification are not limited to the above-described forms, and may be based on the parameter N11、C11、N21And C21The change of the user gender tendency can be truly reflected, and the gender tendency is consistent with the mode parameters in the training of the classification model.
The pre-trained classification model can be obtained by training as follows:
firstly, a training sample set is obtained.
The method comprises the steps of obtaining historical browsing behavior data of a large number of users, namely historical browsing behavior logs, obtaining three-level basic categories to which webpages browsed and clicked by each user belong based on the historical browsing behavior logs, and obtaining browsing and clicking times of the three-level basic categories respectively.
Aiming at the historical browsing behavior log of each user, the following parameters of the historical browsing and webpage clicking of the user are obtained: the total number of views, the total number of clicks, the first number of views for viewing a web page belonging to the female category, the second number of views for viewing a web page belonging to the male category, the first number of views/total number of views, the second number of views/total number of views, the first number of clicks for clicking a web page belonging to the female category, the second number of clicks for clicking a web page belonging to the male category, the first number of clicks/total number of clicks, the second number of clicks/total number of clicks, and the like. Model input parameters are selected from the above parameters of each user as a training sample. The model input parameters can be a first browsing frequency, a second browsing frequency, a first click frequency and a second click frequency, and can also be a total browsing frequency, a total click frequency, a first browsing frequency/a total browsing frequency, a second browsing frequency/a total browsing frequency, a first click frequency/a total click frequency and a second click frequency/a total click frequency; but also all the parameters mentioned above.
And secondly, marking a gender label for each user.
And aiming at each training sample, acquiring the gender tendency weight of the user according to the number of clicks of the webpage belonging to the female category and the number of clicks of the webpage belonging to the male category. Specifically, for each training sample, the total number of times C that the user browses and clicks the webpage is obtainedsObtaining the first click frequency C which is the click frequency of the user clicking the webpage belonging to the female category11The first browsing times N being the browsing times of the user browsing the web pages belonging to the female category11(ii) a Obtaining the second click times C which is the click times of the user clicking the web pages belonging to the male category21The second browsing times N which are the browsing times of the user browsing the web pages belonging to the male category21(ii) a Respectively calculate C11/Cs、C21/CsAs the user's gender tendency weight, i.e., female tendency weight and male tendency weight, or, C is calculated separately11/(N11+N21)、C21/(N11+N21) As a user gender propensity weight.
And carrying out gender labeling on each training sample according to the obtained user gender tendency weight to obtain a gender label of each training sample. Specifically, if the female tendency weight in the user gender tendency weight is larger than the male tendency weight, carrying out female labeling on the training sample to obtain a gender label of the training sample as female; if the female tendency weight in the user gender tendency weight is smaller than the male tendency weight, carrying out male labeling on the training sample to obtain a gender label of the training sample as a male; if the female tendency weight is equal to the male tendency weight in the user gender tendency weights, the training sample is discarded. By means of the method, the training samples are labeled, the intellectualization of sample labeling is achieved, the workload of manual labeling is reduced, the labeling efficiency is improved, and the model training cost is reduced.
And thirdly, carrying out classification model training according to the training sample set obtained in the first step and the sex label of each training sample obtained in the second step. The classification algorithm adopted by the classification model may be a Gradient Boosting Decision Tree (GBDT), a random forest or an eXtreme Gradient Boosting (XGBOOST), and the like.
Based on the classification model trained in advance, S16 inputs the obtained model input parameters into the classification model, and the user gender identification result can be obtained. According to the obtained user gender identification result, the user gender characteristics can be increased in the user portrait. If the user gender identification result shows that the probability that the user gender is male is higher, adding a gender characteristic of male in the portrait characteristic of the user; correspondingly, if the user gender identification result shows that the probability that the user gender is female is higher, the gender characteristic female is added in the user portrait characteristic to perfect the user portrait so as to provide targeted service for the user. Furthermore, webpage recommendation can be performed on the user according to the user gender identification result, and the webpage of the female category or the webpage of the male category corresponding to the user gender can be selected for recommendation, so that the accuracy of CTR estimation of webpage recommendation of advertisements, e-commerce and the like can be improved.
In the above embodiment, the obtaining of the behavior parameters representing the gender tendency of the user by classifying the web pages browsed and clicked by the user includes: according to the browsing times and the clicking times of the female category and the male category, the user gender identification is carried out through the pre-trained classification model to obtain the user gender identification result, so that the intelligent acquisition of the user gender is realized, the dependence of the user gender acquisition on manual setting is reduced, the authenticity of the user is obtained through the acquisition of the male category and the female category to which the webpage browsed and clicked by the user belongs, the user gender identification is carried out, and the accuracy of the user gender identification is improved. In addition, the training samples for identifying the gender of the user are labeled through the browsing times and the clicking times of the user on the webpages of the female categories and the male categories, so that the labor cost and the time cost of labeling the samples during model training are greatly reduced, and the efficiency of the model training is improved.
In view of the foregoing, an embodiment of the present invention provides a method for identifying a user gender, and an embodiment of the present invention further provides a device for identifying a user gender, referring to fig. 2, the device includes:
the acquisition unit 21 is configured to acquire historical browsing behavior data of a user within a preset time period;
a category unit 22, configured to obtain a category to which a webpage corresponding to each piece of historical browsing behavior data belongs, where the category includes a female category and a male category;
the statistical unit 23 is configured to obtain, based on the historical browsing behavior data and the category, a first browsing frequency and a first click frequency of the user on a web page belonging to the female category, and a second browsing frequency and a second click frequency of the user on a web page belonging to the male category;
and the identification unit 24 is configured to perform user gender identification through a pre-trained classification model based on the first browsing times, the first click times, the second browsing times and the second click times, so as to obtain a user gender identification result.
As an alternative embodiment, the identification unit 24 is configured to: the following parameters were obtained as model input parameters: a first ratio between the first browsing times and the total browsing times of all the webpages by the user, a second ratio between the first clicking times and the total clicking times of all the webpages by the user, a third ratio between the second browsing times and the total browsing times and a fourth ratio between the second clicking times and the total clicking times; and inputting the model input parameters into the classification model to perform user gender identification, and obtaining a user gender identification result.
As an optional implementation, the apparatus further comprises a training unit 25, configured to obtain a training sample set; aiming at each training sample, acquiring a gender tendency weight of the user according to the first click times of the user on the webpage belonging to the female category and the second click times of the user on the webpage belonging to the male category; performing gender labeling on each training sample according to the user gender tendency weight to obtain a gender label of each training sample; and carrying out classification model training according to the training sample set and the gender label of each training sample.
As an alternative embodiment, the classification model adopts a classification algorithm such as gradient boosting decision tree, random forest or extreme gradient boosting.
As an optional implementation, the apparatus further comprises: an application unit 26, configured to add a user gender feature in the user portrait according to the user gender identification result; and/or recommending the webpage to the user according to the gender identification result of the user.
As an alternative implementation, the historical browsing behavior data is advertisement browsing behavior data;
the category unit 22 is used for: acquiring three-level basic categories to which advertisement goods and/or services provided by a webpage corresponding to each piece of advertisement browsing behavior data belong; and acquiring the gender category of the webpage corresponding to each piece of advertisement browsing behavior data according to the three-level basic categories.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Fig. 3 is a block diagram illustrating an electronic device 800 for implementing a method for user gender identification, according to an example embodiment. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.
Referring to fig. 3, electronic device 800 may include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input/presentation (I/O) interface 812, sensor component 814, and communication component 816.
The processing component 802 generally controls overall operation of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing elements 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.
The memory 804 is configured to store various types of data to support operation at the device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
The power supply component 806 provides power to the various components of the electronic device 800. The power components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 800.
The multimedia component 808 includes a screen that provides a presentation interface between the electronic device 800 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front-facing camera and/or the rear-facing camera may receive external multimedia data when the device 800 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.
The audio component 810 is configured to present and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for presenting audio signals.
The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.
The sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for the electronic device 800. For example, the sensor assembly 814 may detect an open/closed state of the device 800, the relative positioning of components, such as a display and keypad of the electronic device 800, the sensor assembly 814 may also detect a change in the position of the electronic device 800 or a component of the electronic device 800, the presence or absence of user contact with the electronic device 800, orientation or acceleration/deceleration of the electronic device 800, and a change in the temperature of the electronic device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast associated information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communications component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
In an exemplary embodiment, the electronic device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.
In an exemplary embodiment, a non-transitory computer-readable storage medium comprising instructions, such as the memory 804 comprising instructions, executable by the processor 820 of the electronic device 800 to perform the above-described method is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
A non-transitory computer readable storage medium having instructions therein, which when executed by a processor of a mobile terminal, enable the mobile terminal to perform a method of user gender identification, the method comprising: acquiring historical browsing behavior data of a user in a preset time period; acquiring categories to which the webpages corresponding to each piece of historical browsing behavior data belong, wherein the categories comprise female categories and male categories; acquiring a first browsing frequency and a first click frequency of a user on a webpage belonging to the female category and a second browsing frequency and a second click frequency of the user on the webpage belonging to the male category based on the historical browsing behavior data and the categories; and based on the first browsing times, the first click times, the second browsing times and the second click times, carrying out user gender identification through a pre-trained classification model to obtain a user gender identification result.
It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is only limited by the appended claims
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A method for identifying gender of a user, comprising:
acquiring historical browsing behavior data of a user in a preset time period;
acquiring categories to which the webpages corresponding to each piece of historical browsing behavior data belong, wherein the categories comprise female categories and male categories;
acquiring a first browsing frequency and a first click frequency of a user on a webpage belonging to the female category and a second browsing frequency and a second click frequency of the user on the webpage belonging to the male category based on the historical browsing behavior data and the categories;
and based on the first browsing times, the first click times, the second browsing times and the second click times, carrying out user gender identification through a pre-trained classification model to obtain a user gender identification result.
2. The method of claim 1, wherein the obtaining a user gender identification result by performing user gender identification through a pre-trained classification model based on the first browsing times, the first click times, the second browsing times and the second click times comprises:
the following parameters were obtained as model input parameters:
a first ratio between the first browsing times and the total browsing times of all the webpages by the user, a second ratio between the first clicking times and the total clicking times of all the webpages by the user, a third ratio between the second browsing times and the total browsing times and a fourth ratio between the second clicking times and the total clicking times;
and inputting the model input parameters into the classification model to perform user gender identification, and obtaining a user gender identification result.
3. The method of claim 1, wherein the training method of the classification model comprises:
acquiring a training sample set;
aiming at each training sample, acquiring a gender tendency weight of the user according to the first click times of the user on the webpage belonging to the female category and the second click times of the user on the webpage belonging to the male category;
performing gender labeling on each training sample according to the user gender tendency weight to obtain a gender label of each training sample;
and carrying out classification model training according to the training sample set and the gender label of each training sample.
4. The method of claim 1, wherein the classification model employs a classification algorithm that is gradient boosting decision tree, random forest, or extreme gradient boosting.
5. The method of any of claims 1 to 4, further comprising:
according to the user gender identification result, adding a user gender characteristic in the user portrait; and/or the presence of a gas in the gas,
and recommending the webpage to the user according to the gender identification result of the user.
6. The method according to any one of claims 1 to 4, wherein the historical browsing behavior data is advertisement browsing behavior data;
the obtaining of the category to which the webpage corresponding to each piece of historical browsing behavior data belongs includes:
acquiring three-level basic categories to which advertisement goods and/or services provided by a webpage corresponding to each piece of advertisement browsing behavior data belong;
and acquiring the gender category of the webpage corresponding to each piece of advertisement browsing behavior data according to the three-level basic categories.
7. A user gender identification device, comprising:
the acquisition unit is used for acquiring historical browsing behavior data of a user in a preset time period;
the category unit is used for acquiring categories to which the webpages corresponding to each piece of historical browsing behavior data belong, wherein the categories comprise female categories and male categories;
the statistical unit is used for acquiring a first browsing frequency and a first click frequency of the user on the webpage belonging to the female category and a second browsing frequency and a second click frequency of the user on the webpage belonging to the male category based on the historical browsing behavior data and the categories;
and the identification unit is used for carrying out user gender identification through a pre-trained classification model based on the first browsing times, the first click times, the second browsing times and the second click times to obtain a user gender identification result.
8. The apparatus of claim 7, wherein the identification unit is to:
the following parameters were obtained as model input parameters:
a first ratio between the first browsing times and the total browsing times of all the webpages by the user, a second ratio between the first clicking times and the total clicking times of all the webpages by the user, a third ratio between the second browsing times and the total browsing times and a fourth ratio between the second clicking times and the total clicking times;
and inputting the model input parameters into the classification model to perform user gender identification, and obtaining a user gender identification result.
9. An electronic device, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors to execute operation instructions included in the one or more programs for performing the method according to any one of claims 1 to 6.
10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the steps of the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010097122.2A CN113268654A (en) | 2020-02-17 | 2020-02-17 | User gender identification method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010097122.2A CN113268654A (en) | 2020-02-17 | 2020-02-17 | User gender identification method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113268654A true CN113268654A (en) | 2021-08-17 |
Family
ID=77227576
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010097122.2A Pending CN113268654A (en) | 2020-02-17 | 2020-02-17 | User gender identification method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113268654A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105550892A (en) * | 2014-10-29 | 2016-05-04 | 苏宁云商集团股份有限公司 | On-line member gender recognition method and system, and information recommendation system |
| US20160283976A1 (en) * | 2015-03-26 | 2016-09-29 | Appier Inc. | Method of enhancing the accuracy of predicting the gender of network users |
| CN106484762A (en) * | 2015-08-27 | 2017-03-08 | 优像数位媒体科技股份有限公司 | Method for predicting gender by using webpage browsing behavior |
| CN106682686A (en) * | 2016-12-09 | 2017-05-17 | 北京拓明科技有限公司 | User gender prediction method based on mobile phone Internet-surfing behavior |
| CN107766891A (en) * | 2017-10-31 | 2018-03-06 | 广东欧珀移动通信有限公司 | User's gender identification method, device, storage medium and electronic equipment |
| CN108256537A (en) * | 2016-12-28 | 2018-07-06 | 北京酷我科技有限公司 | A kind of user gender prediction method and system |
| CN109034868A (en) * | 2018-06-21 | 2018-12-18 | 上海二三四五网络科技有限公司 | It is a kind of to browse the control method and control device that information determines user's gender based on user |
| CN109948633A (en) * | 2017-12-20 | 2019-06-28 | 广东欧珀移动通信有限公司 | User gender prediction method, apparatus, storage medium and electronic equipment |
| CN109961163A (en) * | 2017-12-22 | 2019-07-02 | 广东欧珀移动通信有限公司 | Gender prediction's method, apparatus, storage medium and electronic equipment |
| CN109961077A (en) * | 2017-12-22 | 2019-07-02 | 广东欧珀移动通信有限公司 | Gender prediction's method, apparatus, storage medium and electronic equipment |
-
2020
- 2020-02-17 CN CN202010097122.2A patent/CN113268654A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105550892A (en) * | 2014-10-29 | 2016-05-04 | 苏宁云商集团股份有限公司 | On-line member gender recognition method and system, and information recommendation system |
| US20160283976A1 (en) * | 2015-03-26 | 2016-09-29 | Appier Inc. | Method of enhancing the accuracy of predicting the gender of network users |
| CN106484762A (en) * | 2015-08-27 | 2017-03-08 | 优像数位媒体科技股份有限公司 | Method for predicting gender by using webpage browsing behavior |
| CN106682686A (en) * | 2016-12-09 | 2017-05-17 | 北京拓明科技有限公司 | User gender prediction method based on mobile phone Internet-surfing behavior |
| CN108256537A (en) * | 2016-12-28 | 2018-07-06 | 北京酷我科技有限公司 | A kind of user gender prediction method and system |
| CN107766891A (en) * | 2017-10-31 | 2018-03-06 | 广东欧珀移动通信有限公司 | User's gender identification method, device, storage medium and electronic equipment |
| CN109948633A (en) * | 2017-12-20 | 2019-06-28 | 广东欧珀移动通信有限公司 | User gender prediction method, apparatus, storage medium and electronic equipment |
| CN109961163A (en) * | 2017-12-22 | 2019-07-02 | 广东欧珀移动通信有限公司 | Gender prediction's method, apparatus, storage medium and electronic equipment |
| CN109961077A (en) * | 2017-12-22 | 2019-07-02 | 广东欧珀移动通信有限公司 | Gender prediction's method, apparatus, storage medium and electronic equipment |
| CN109034868A (en) * | 2018-06-21 | 2018-12-18 | 上海二三四五网络科技有限公司 | It is a kind of to browse the control method and control device that information determines user's gender based on user |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109800325B (en) | Video recommendation method and device and computer-readable storage medium | |
| CN109308334B (en) | Information recommendation method and device and search engine system | |
| CN111556366A (en) | Multimedia resource display method, device, terminal, server and system | |
| CN110222256B (en) | Information recommendation method and device and information recommendation device | |
| CN110598098A (en) | Information recommendation method and device and information recommendation device | |
| CN109918565B (en) | Processing method and device for search data and electronic equipment | |
| CN112508612B (en) | Method for training advertisement creative generation model and generating advertisement creative and related device | |
| CN110766456A (en) | Commodity recommendation method and device | |
| CN112000266B (en) | Page display method and device, electronic equipment and storage medium | |
| CN109670077A (en) | Video recommendation method, device and computer readable storage medium | |
| CN108717403B (en) | Processing method and device for processing | |
| CN112148980B (en) | Article recommending method, device, equipment and storage medium based on user click | |
| CN111369271A (en) | Advertisement sorting method and device, electronic equipment and storage medium | |
| CN107506441B (en) | Data arrangement method and device, electronic equipment and storage medium | |
| CN111127053B (en) | Page content recommendation method and device and electronic equipment | |
| CN112612949B (en) | Method and device for establishing recommended data set | |
| CN112000840B (en) | Business object display method and device | |
| CN112015277B (en) | Information display method and device and electronic equipment | |
| CN112767053A (en) | Information processing method, information processing device, electronic equipment and storage medium | |
| CN112784151A (en) | Method and related device for determining recommendation information | |
| CN108205534B (en) | Skin resource display method and device and electronic equipment | |
| CN114202380A (en) | Recommendation method, device and equipment for financial products | |
| CN115203573A (en) | Portrait label generating method, model training method, device, medium and chip | |
| CN113268654A (en) | User gender identification method and device and electronic equipment | |
| CN112036247A (en) | Expression package character generation method and device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |