WO2020207201A1

WO2020207201A1 - Method and apparatus for constructing user behavior prediction model, storage medium and electronic device

Info

Publication number: WO2020207201A1
Application number: PCT/CN2020/079549
Authority: WO
Inventors: 何明; 陈仲铭; 黄粟; 刘耀勇; 陈岩
Original assignee: Oppo广东移动通信有限公司
Priority date: 2019-04-09
Filing date: 2020-03-16
Publication date: 2020-10-15
Also published as: CN111798260A

Abstract

A method and an apparatus for constructing a user behavior prediction model, a storage medium and an electronic device. Said method comprises: acquiring current geographical location information and current sensing data; identifying a current scene according to the sensing data; determining the type of relationship between a user and a scene; acquiring the degree of preference of the user for the scene; acquiring behavior habit information of the user in the scene; and establishing a user behavior prediction model according to the geographical location information, the relationship type, the preference degree and the behavior habit information.

Description

Method, device, storage medium and electronic equipment for constructing user behavior prediction model

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office, the application number is 201910282466.8, and the invention title is "User Behavior Prediction Model Construction Method, Device, Storage Medium, and Electronic Equipment" on April 9, 2019, and its entire content Incorporated in this application by reference.

Technical field

This application relates to the field of electronic technology, and in particular to a method, device, storage medium and electronic equipment for constructing a user behavior prediction model.

Background technique

With the development of electronic technology, electronic devices such as smart phones have become more and more abundant. The electronic device can not only identify the user's movement track, but also identify the geographic location of the user. The electronic device can push various information about the geographic location to the user, so as to facilitate the user to understand the information that he is interested in.

Summary of the invention

The embodiments of the present application provide a method, device, storage medium, and electronic equipment for constructing a user behavior prediction model, which can improve the accuracy of the information pushed by the electronic equipment.

In the first aspect, an embodiment of the present application provides a method for constructing a user behavior prediction model, including:

Acquiring the geographic location information where the electronic device is currently located and the perception data of the scene where the electronic device is currently located;

Identifying the current scene of the electronic device according to the perception data;

Determining the type of relationship between the user and the scene according to the length of time the user stays in the scene and the operation information in the scene;

Acquiring the user's preference for the scene according to the historical track information of the user in the scene;

Acquiring user behavior habit information in the scene according to the user's historical behavior information in the scene;

The user behavior prediction model is established according to the geographic location information, the relationship type, the preference degree, and the behavior habit information.

In a second aspect, an embodiment of the present application provides an apparatus for constructing a user behavior prediction model, including:

The first acquisition module is used to acquire the geographic location information where the electronic device is currently located and the perception data of the scene where the electronic device is currently located;

An identification module, configured to identify the current scene of the electronic device according to the perception data;

A determining module, configured to determine the type of relationship between the user and the scene according to the length of time the user stays in the scene and the operation information in the scene;

The second acquiring module is configured to acquire the user's preference for the scene according to the historical track information of the user in the scene;

The third obtaining module is configured to obtain the user's behavior habit information in the scene according to the user's historical behavior information in the scene;

The establishment module is used to establish the user behavior prediction model according to the geographic location information, the relationship type, the preference degree, and the behavior habit information.

In a third aspect, the embodiments of the present application also provide a storage medium in which a computer program is stored, and when the computer program runs on a computer, the computer is caused to execute:

In a fourth aspect, an embodiment of the present application further provides an electronic device. The electronic device includes a processor and a memory. The memory stores a computer program. The processor calls the computer program stored in the memory. For:

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings that need to be used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

FIG. 1 is a schematic diagram of an application scenario of a method for constructing a user behavior prediction model provided by an embodiment of the application.

FIG. 2 is a schematic diagram of the first flow of a method for constructing a user behavior prediction model provided by an embodiment of the application.

FIG. 3 is a schematic diagram of the second flow of the method for constructing a user behavior prediction model provided by an embodiment of the application.

FIG. 4 is a schematic diagram of the third process of the method for constructing a user behavior prediction model provided by an embodiment of the application.

FIG. 5 is a schematic diagram of the fourth flow of the method for constructing a user behavior prediction model provided by an embodiment of the application.

FIG. 6 is a schematic diagram of the fifth flow of the method for constructing a user behavior prediction model provided by an embodiment of the application.

FIG. 7 is a schematic diagram of the sixth flow of the method for constructing a user behavior prediction model provided by an embodiment of the application.

FIG. 8 is a schematic diagram of the seventh process of the method for constructing a user behavior prediction model provided by an embodiment of the application.

FIG. 9 is a schematic diagram of the eighth process of the method for constructing a user behavior prediction model provided by an embodiment of the application.

FIG. 10 is a schematic structural diagram of an apparatus for constructing a user behavior prediction model provided by an embodiment of the application.

FIG. 11 is a schematic diagram of the first structure of an electronic device provided by an embodiment of this application.

FIG. 12 is a schematic diagram of a second structure of an electronic device provided by an embodiment of the application.

detailed description

The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative work shall fall within the protection scope of this application.

Referring to FIG. 1, FIG. 1 is a schematic diagram of an application scenario of a method for constructing a user behavior prediction model provided by an embodiment of the application. The user behavior prediction model construction method is applied to electronic equipment. The electronic device is provided with a panoramic sensing architecture. The panoramic perception architecture is the integration of hardware and software used to implement the method for constructing the user behavior prediction model in an electronic device.

Among them, the panoramic perception architecture includes an information perception layer, a data processing layer, a feature extraction layer, a scenario modeling layer, and an intelligent service layer.

The information perception layer is used to obtain the information of the electronic device itself or the information in the external environment. The information perception layer may include multiple sensors. For example, the information sensing layer includes multiple sensors such as a distance sensor, a magnetic field sensor, a light sensor, an acceleration sensor, a fingerprint sensor, a Hall sensor, a position sensor, a gyroscope, an inertial sensor, a posture sensor, a barometer, and a heart rate sensor.

Among them, the distance sensor can be used to detect the distance between the electronic device and an external object. The magnetic field sensor can be used to detect the magnetic field information of the environment in which the electronic device is located. The light sensor can be used to detect the light information of the environment in which the electronic device is located. The acceleration sensor can be used to detect the acceleration data of the electronic device. The fingerprint sensor can be used to collect the user's fingerprint information. Hall sensor is a kind of magnetic field sensor made according to Hall effect, which can be used to realize automatic control of electronic equipment. The location sensor can be used to detect the current geographic location of the electronic device. Gyroscopes can be used to detect the angular velocity of electronic devices in various directions. Inertial sensors can be used to detect movement data of electronic devices. The attitude sensor can be used to sense the attitude information of the electronic device. The barometer can be used to detect the air pressure of the environment where the electronic device is located. The heart rate sensor can be used to detect the user's heart rate information.

The data processing layer is used to process the data obtained by the information perception layer. For example, the data processing layer can perform data cleaning, data integration, data transformation, and data reduction on the data acquired by the information perception layer.

Among them, data cleaning refers to cleaning up a large amount of data obtained by the information perception layer to eliminate invalid data and duplicate data. Data integration refers to the integration of multiple single-dimensional data acquired by the information perception layer into a higher or more abstract dimension to comprehensively process multiple single-dimensional data. Data transformation refers to the data type conversion or format conversion of the data acquired by the information perception layer, so that the transformed data meets the processing requirements. Data reduction means to minimize the amount of data while maintaining the original appearance of the data as much as possible.

The feature extraction layer is used to perform feature extraction on data processed by the data processing layer to extract features included in the data. The extracted features can reflect the state of the electronic device itself or the state of the user or the environmental state of the environment in which the electronic device is located.

Among them, the feature extraction layer can extract features or process the extracted features through methods such as filtering, packaging, and integration.

The filtering method refers to filtering the extracted features to delete redundant feature data. The packaging method is used to screen the extracted features. The integration method refers to the integration of multiple feature extraction methods to construct a more efficient and accurate feature extraction method for feature extraction.

The scenario modeling layer is used to construct a model based on the features extracted by the feature extraction layer, and the obtained model can be used to represent the state of the electronic device or the state of the user or the environment. For example, the scenario modeling layer can construct key value models, pattern identification models, graph models, entity connection models, object-oriented models, etc. based on the features extracted by the feature extraction layer.

The intelligent service layer is used to provide users with intelligent services based on the model constructed by the scenario modeling layer. For example, the intelligent service layer can provide users with basic application services, can perform system intelligent optimization for electronic devices, and can also provide users with personalized intelligent services.

In addition, the panoramic perception architecture may also include multiple algorithms, each of which can be used to analyze and process data, and the multiple algorithms can form an algorithm library. For example, the algorithm library may include Markov algorithm, implicit Dirichlet distribution algorithm, Bayesian classification algorithm, support vector machine, K-means clustering algorithm, K-nearest neighbor algorithm, conditional random field, residual network , Long and short-term memory networks, convolutional neural networks, recurrent neural networks and other algorithms.

The embodiment of the present application provides a method for constructing a user behavior prediction model, including:

In some embodiments, the determining the type of relationship between the user and the scene according to the length of time the user stays in the scene and the operation information in the scene includes:

Acquiring the length of time the user stays in the scene and the operation information in the scene, where the operation information includes information about the user's operation of multiple application software of the electronic device;

Acquiring, according to the operation information, the number of times the user has been operated on each of the application software;

The type of relationship between the user and the scene is determined according to the duration and the number of times each application software is operated.

In some embodiments, the determining the type of relationship between the user and the scene according to the duration and the number of times each application software has been operated includes:

Determine the target application software that has been operated most frequently from the multiple application software;

According to the duration, the target application software, and a first preset correspondence, the relationship type between the user and the scene is acquired, where the first preset correspondence includes the duration, the target application software, and the relationship type. Correspondence between.

In some embodiments, the number of times of being operated includes the duration of being operated, and the determining the type of relationship between the user and the scene according to the duration and the number of times of being operated for each application software includes:

Determine the target application software that has been operated for the longest time from the multiple application software;

According to the duration, the target application software, and a second preset correspondence relationship, the relationship type between the user and the scene is acquired, wherein the second preset correspondence relationship includes the duration, the target application software and the relationship type The corresponding relationship.

In some embodiments, the acquiring the user's preference for the scene according to the historical track information of the user in the scene includes:

Acquiring the cumulative number of times the user appears in the scene according to the historical track information;

The user's preference for the scene is determined according to the cumulative number of times.

In some embodiments, the determining the user's preference for the scene according to the accumulated number of times includes:

Obtaining a preset preference degree according to the cumulative number of times and a third preset correspondence relationship, where the third preset correspondence relationship includes a correspondence relationship between the cumulative number of times and the preset preference degree;

The preset preference is determined as the user's preference for the scene.

Acquiring, according to the historical track information, the accumulated time that the user appears in the scene;

Determine the user's preference for the scene according to the accumulated time.

In some embodiments, the acquiring behavior information of the user in the scene according to the historical behavior information of the user in the scene includes:

Determine multiple historical behaviors of the user in the scene according to the historical behavior information;

Get the number of occurrences of each historical behavior;

Establish user behavior habit information in the scene according to the multiple historical behaviors and the corresponding times of each of the historical behaviors.

The method for constructing a user behavior prediction model provided in the embodiments of the present application can be applied to electronic devices. According to the user behavior prediction model, the electronic device can push information that the user is interested in, thereby improving the accuracy of pushing information. And the electronic equipment realizes the effect of intelligent optimization, thereby improving the operating efficiency and operating speed of the electronic equipment.

The electronic device may be a smart phone, a tablet computer, a game device, an AR (Augmented Reality) device, a car, a data storage device, an audio playback device, a video playback device, a notebook computer, a desktop computing device, a wearable device such as Electronic watches, electronic glasses, electronic helmets, electronic bracelets, electronic necklaces, electronic clothing and other equipment. The electronic device can push information and display the pushed information on the display screen of the electronic device.

Referring to FIG. 2, FIG. 2 is a schematic diagram of the first flow of a method for constructing a user behavior prediction model provided by an embodiment of the application.

110. Acquire the geographic location information where the electronic device is currently located and the perception data of the scene where the electronic device is currently located.

When the user arrives at a place, the electronic device can obtain the longitude and latitude information or coordinate points of the user's arrival at the place through the Global Positioning System (GPS). Then, the electronic device converts the latitude and longitude information or coordinate points into geographic location information according to the target software. The geographic location information includes shopping malls, office buildings, bus stations, or communities. The target software includes Baidu map, Tencent map or Gaode map, etc. In addition, when the user arrives at a place, the electronic device can also directly obtain the geographic location information of the electronic device through the target software.

In addition, the electronic device can construct a database to store all the acquired data. Therefore, the geographic location information can be recorded as l _n . The electronic device collects data related to the geographic location. Wherein the correlation data of at least one raw data d _n, and the original data may be related to food, exercise or game. The electronic device can use the MySQL relational database to store the geographic location information and the original data related to the geographic location in the form of a table, without putting all the data together. Therefore, the speed at which the electronic device obtains geographic location information and raw data is improved, and the flexibility of using the electronic device is also improved. For example, the table may be (l _n , d _n ).

Correspondingly, the electronic device obtains the perception data of the current scene. For example, the electronic device may obtain the current ambient light intensity through the light sensor of the information perception layer, the current temperature of the electronic device through the temperature sensor, etc., or the current geographic location of the electronic device through the position sensor.

In addition, the electronic device can also obtain the user's action track. For example, when the electronic device recognizes that the user moves from the current geographic location to another geographic location, the electronic device can track the user's movement track. When the user reaches the target geographic location, the geographic location information of the target geographic location is acquired.

120. Identify the current scene of the electronic device according to the perception data.

The electronic device recognizes the current scene of the electronic device according to the acquired perception data. For example, the acquired sensing data such as temperature, ambient light intensity, and geographic location are used to identify the current scene of the electronic device to determine the current scene of the electronic device. The scene includes: a gas station, a gym, a food court, or a movie theater.

130. Determine the type of relationship between the user and the scene according to the length of time the user stays in the scene and the operation information in the scene.

When the user is in the scene, the electronic device obtains the length of time the user stays in the scene. The duration can be in hours, minutes or seconds. For example, 1 hour, 40 minutes, or 2450 seconds. The electronic device obtains operation information in the scene. The operation information includes the user's operation of multiple application software of the electronic device. The operation information may include: opening Alipay, opening video, or opening navigation. The type of relationship between the user and the scene is determined according to the length of time the user stays in the scene and the operation information in the scene. The relationship type may include home, office, work place, or canteen.

In addition, the electronic device can store the relationship type and record it as c _n .

140. Acquire the user's preference for the scene according to the historical track information of the user in the scene.

The electronic device obtains the historical track information of the user in the scene. The historical track information may be the cumulative number of times the user appears in the scene. Electronic equipment can obtain the cumulative number of times by using common statistical methods. The cumulative number of times may be the number of times the user appears in the scene within a preset time period. The preset time period may be in units of years, months, weeks, hours, minutes, or seconds. For example, the electronic device may count the cumulative number of times the user appears in the movie theater within one year as five or the electronic device may count the cumulative number of times the user appears in the gym within three months as three.

In addition, the preset period of time may also be the period of use by the electronic device from the date when the user starts to use the electronic device to the date on the current calendar. For example, the date when the user starts to use the electronic device may be June 6, 2018. The current or current calendar date is August 8, 2019. Then the length of time the user uses the electronic device is one year, two months, and two days. Then, the electronic device counts that the cumulative number of times the user appeared in the supermarket in one year, two months, and two days is 30 times and the cumulative number of times in the movie theater is 3.

The user's preference for the scene is determined according to the cumulative number of times. The electronic device may use a common statistical method to calculate the user's preference for the scene. The preference includes like, generally like or dislike. The preference is to measure the degree of user's preference for the scene. For example, the cumulative number of times a user appears in a movie theater in a day is 10 times. And the cumulative number of times the user appeared in the subway station in the same day is 3 times, so 10 times is greater than 3 times. Therefore, it can be concluded that users like to appear in movie theaters. I generally like to appear in subway stations.

In addition, the historical track information may also be the cumulative duration of the user's appearance in the scene. Electronic equipment can obtain the accumulated time by using common statistical methods. The cumulative duration may be the cumulative duration of the user appearing in the scene within a preset time period. The preset time period may be in units of years, months, weeks, hours, minutes, or seconds. The cumulative duration may be in units of hours, minutes or seconds. For example, the user appeared in a movie theater on the first day and spent 3 hours in the movie theater. Then, the user appeared in the gym on the next day and stayed in the gym for 2 hours. Then, on the third day, the user appeared in the movie theater again and spent 2 hours in the movie theater, wherein the movie theater where the user appeared on the third day and the movie theater where the user appeared on the first day were the same theater. To sum up, in the three days, the user's electronic device counts the cumulative time that the user appears in the movie theater is 5 hours and the cumulative time that the user appears in the gym is 2 hours.

For another example, the electronic device can count the cumulative time that the user appears in the karaoke hall within one year as 5 hours. Or the electronic device counts the cumulative time that the user appears in the movie theater within one month to be 75 minutes.

In addition, the preset period of time may also be the period of use by the electronic device from the date when the user starts to use the electronic device to the date on the current calendar. For example, the date when the user starts to use the electronic device may be January 1, 2018. The current or current calendar date is January 1, 2019. Then the user has used the electronic device for one year. Then, the electronic device counts that the cumulative number of times the user appears in the gym in the one year is 20 times and the cumulative number of times the library is 2 times.

Determine the user's preference for the scene according to the accumulated time. For example, the cumulative time that the user appears in the movie theater in a day is 3 hours. And in the same day, the cumulative time that the user appears in the parking lot is 60 minutes. Then 3 hours is greater than 60 minutes, so it can be concluded that users like to appear in the cinema. And to appear in the parking lot is generally like.

In addition, the electronic device may record the user's preference for the scene as p _n . According to geographic location information, relationship type and preference degree, MySQL relational database is used to store it in the form of a table. That is, the table can be (l _n , c _n , p _n ).

150. Acquire behavior habit information of the user in the scene according to the historical behavior information of the user in the scene.

It is understandable that the electronic device determines multiple historical behaviors of the user in the scene according to the historical behavior information. The historical behaviors include working out in a gym, eating hot pot in a hot pot restaurant, or shopping in a supermarket. The historical behavior information includes application type information, fitness information, game information, or food information of the application opened by the user.

Then, the electronic device obtains the number of occurrences of each historical behavior. The electronic device records the number of occurrences of each historical behavior of the user. In a preset time period, the user obtains the number of occurrences of each historical behavior in the scene. For example, in the first week, users eat hot pot and play games at a hot pot restaurant. Then the historical behavior of electronic equipment in hot pot restaurants is eating hot pot and playing games. Then, the electronic device records the user's historical behavior in the first week as the eating hot pot and playing games. In the second week, the user’s historical behavior at the same hot pot restaurant was to only eat hot pot. Then the electronic device records the historical behavior of eating hot pot in the same hot pot restaurant in the second week. In summary, by summarizing the historical behaviors that occurred in the hot pot restaurant, it can be obtained that the user's historical behavior in the hot pot restaurant and within the two weeks is eating hot pot twice and playing a game once.

Finally, the user's behavior habit information in the scene is established according to the multiple historical behaviors and the corresponding times of each of the historical behaviors. Please refer to the above example, then the user's behavioral habit information in hot pot restaurants is that they often eat hot pot and rarely play games.

Correspondingly, the electronic device can store the user's behavior habit information, which is recorded as b _n .

160. Establish the user behavior prediction model according to the geographic location information, the relationship type, the preference degree, and the behavior habit information.

First, the electronic device can establish a relationship table for the geographic location information, the relationship type, the preference degree, and the behavior habit information, namely (l _n , c _n , p _n , b _n ). A user behavior prediction model is generated according to the relationship table. Or the geographic location information, the relationship type, the preference degree, and the behavior habit information are stored in the form of a database. A user behavior prediction model is generated according to the database. Or the electronic device may directly establish a user behavior prediction model based on the geographic location information, the relationship type, the preference degree, and the behavior habit information.

Secondly, after the user behavior prediction model is established, the electronic device can obtain social information corresponding to the current scene of the user. The social information can include neighboring resources, laws and customs, customs, or social relations. According to the user behavior prediction model, the electronic device can predict which social information users are interested in. The information of interest is pushed to the user, so that the user can quickly and efficiently receive the information of interest, so that the electronic device improves the accuracy of pushing the information of interest to the user. And it can also enable electronic devices to provide users with relevant information efficiently and quickly. For example, the user is shopping in a shopping mall. Certain merchants in shopping malls are conducting discount promotions. The electronic device predicts that the user is interested in the information of discount promotion activities through the user behavior prediction model. Then the electronic device may send the information of the discount promotion activity to the user, so that the user can quickly understand which merchant is conducting the discount promotion activity and what the content of the discount promotion activity is.

For example, in some embodiments, the electronic device can obtain the geographic location information of the electronic device and the perception data of the scene where the electronic device is currently located through the information perception layer, and the intelligent service layer can identify the location information according to the perception data. Describe the current scene of the electronic device. It is understandable that before the intelligent service layer recognizes the current scene of the electronic device, the electronic device can also process the geographic location data obtained by the information perception layer and the perception data of the current scene through the data processing layer, such as data cleaning and data processing. Transformation and other processing.

Subsequently, the electronic device can determine the type of relationship between the user and the scene according to the length of time the user stays in the scene and the operation information in the scene through the intelligent service layer, and obtain the historical track information of the user in the scene The user's preference for the scene, and the user's behavior habit information in the scene is obtained according to the user's historical behavior information in the scene.

After obtaining the type of relationship between the user and the scene, the user’s preference for the scene, and the user’s behavior habit information in the scene, the electronic device can use the scene modeling layer according to the geographic location information and the relationship The type, the preference degree, and the behavior habit information establish a behavior prediction model of the user.

Subsequently, the intelligent service layer can predict the user's behavior in the future through the behavior prediction model, and provide the user with personalized services based on the prediction result, such as automatically pushing relevant information for the user, and automatically opening related applications.

In the embodiment of the present application, the electronic device constructs a user behavior prediction model. The prediction model based on user behavior can predict the information that the user is interested in when he is in the current scene. Then the information is sent to the user, so that the user can receive the push information in real time, thereby improving the accuracy and efficiency of the electronic device pushing information.

In some embodiments, referring to FIG. 3, FIG. 3 is a schematic diagram of the second flow of the method for constructing a user behavior prediction model provided by an embodiment of the application.

Wherein, step 130, determining the type of relationship between the user and the scene according to the length of time the user stays in the scene and the operation information in the scene includes the following steps:

131. Acquire the length of time the user stays in the scene and the operation information in the scene, where the operation information includes information about the user's operation of multiple application software of the electronic device;

132. Acquire the number of times the user has been operated on each of the application software according to the operation information;

133. Determine the type of relationship between the user and the scene according to the duration and the number of times each application software has been operated.

The electronic device can obtain the length of time the user stays in the scene and the operation information in the scene. For example, the duration of stay in the scene is the duration between when the user enters the scene and leaves the scene. For example, if 2 hours have passed since the user entered the movie theater and left the movie theater, then the 2 hours is the length of time the user stays in the scene. Wherein, the scene operation information may include information that the user operates multiple application software of the electronic device. For example, open the XX game in a movie theater. Open the XX payment software in the restaurant.

Then, the electronic device obtains the number of times the user has been operated on each of the application software. For example, users open payment software, game software, and camera software in a shopping mall. Among them, from the time the user enters the shopping mall to when he leaves the mall, the electronic device obtains that the user has opened the payment software 5 times, opened the game software 2 times, and opened the camera software 3 times.

Finally, the type of relationship between the user and the scene is determined according to the duration and the number of times each application software is operated. It is understandable that the electronic device can determine the type of relationship between the user and the scene according to the number of times each application software is operated during the time that the user stays in the scene. The application software that has been operated many times can be considered that the user frequently operates the application software that has been operated many times in the scene. Then, the type of relationship between the user and the scene is determined according to the application software that has been operated many times.

In some embodiments, referring to FIG. 4, FIG. 4 is a schematic diagram of the third process of the method for constructing a user behavior prediction model provided by an embodiment of the application.

Wherein, step 133, determining the type of relationship between the user and the scene according to the duration and the number of times each application software is operated, includes the following steps:

1331. Determine the target application software that has been operated most frequently from the multiple application software;

1332. Acquire the type of relationship between the user and the scene according to the duration, the target application software, and a first preset correspondence, where the first preset correspondence includes duration, target application software, and relationship Correspondence between types.

The electronic device determines the target application software with the most number of operations based on the acquired number of operations for each application software. Then, according to the duration, the target application software, and a first preset correspondence relationship, the relationship type between the user and the scene is acquired, where the first preset correspondence relationship includes duration, target application software, and relationship Correspondence between types. It is understandable that the target application software that has been operated most frequently is the target application software that the user frequently operates in the scene. The target application software that has been operated many times does not mean that one application software can be multiple application software.

Therefore, the corresponding relationship between the duration, the target application software, and the relationship type may be as shown in Table 1.

Table 1

时长duration	目标应用软件Target application software	关系类型Relationship type
2304秒2304 seconds	支付软件Payment software	购物商场shopping mall
3个小时3 hours	视频软件和淘宝软件Video software and Taobao software	家Home
……...	……...	……...

According to Table 1, the type of relationship between the user and the scene can be determined according to the duration and the target application software. For example, if the user is in the XX community and opened the most frequently operated video software and Taobao software within 3 hours, then according to the 3 hours, video software and Taobao software, the relationship type between the user and the XX community can be obtained as home.

In addition, the electronic device can set a preset threshold for the number of times of operation to accurately obtain target application operations that have been operated many times. That is, the application software that is greater than or equal to the preset threshold of the number of operations can be selected as the target application software. For example, the electronic device obtains that the number of operations of the payment software is 3 times, the number of operations of the photographing software is 5 times, and the number of operations of the video software is 1 time. The preset threshold for the number of operations is 2. Then select the application software corresponding to the number of operations greater than or equal to 2 as the target application software. That is, payment software and camera software are selected as the target application software.

In some embodiments, referring to FIG. 5, FIG. 5 is a schematic flowchart of the fourth method for constructing a user behavior prediction model provided by an embodiment of the application.

1333. Determine the target application software that has been operated for the longest time from the multiple application software;

1334. Obtain a relationship type between the user and the scene according to the duration, the target application software, and a second preset correspondence, where the second preset correspondence includes duration, target application software, and relationship type Correspondence between.

The electronic device determines the target application software for the operating time according to the acquired operating time of each application software. The number of operations includes the duration of operations. Then, obtain the type of relationship between the user and the scene according to the duration, the target application software, and a second preset correspondence relationship, where the second preset correspondence relationship includes duration, target application software, and relationship Correspondence between types. It can be understood that the target application software that has been operated for the longest time is the target application software that the user frequently operates in the scene. The target application software that has been operated for the longest time does not mean that one application software can be multiple application software.

Therefore, the corresponding relationship between the duration, the target application software, and the relationship type may be as shown in Table 2.

Table 2

According to Table 2, the type of relationship between the user and the scene can be determined according to the duration and the target application software. For example, if the user is in the XX community and opened the video software and Taobao software that have been operated for the longest time within 3 hours, then according to the 3 hours, video software and Taobao software, it can be obtained that the type of relationship between the user and the XX community is home.

In addition, the electronic device may set a preset operating time threshold to accurately obtain the target application operation with the longest operating time. That is, the application software that is greater than or equal to the preset operating time threshold can be selected as the target application software. For example, the electronic device obtains that the payment software has been operated for 3 hours, the photographing software has been operated for 2 hours, and the video software has been operated for 40 minutes. The preset operating time threshold is 1 hour. Then, the application software corresponding to the operated time length greater than or equal to 1 is selected as the target application software. That is, payment software and camera software are selected as the target application software.

In some embodiments, referring to FIG. 6, FIG. 6 is a schematic flowchart of the fifth method for constructing a user behavior prediction model provided by an embodiment of this application.

Wherein, step 140, obtaining the user's preference for the scene according to the user's historical track information in the scene, includes the following steps:

141. Acquire the cumulative number of times a user appears in the scene according to the historical track information;

142. Determine a user's preference for the scene according to the cumulative number of times.

In some embodiments, referring to FIG. 7, FIG. 7 is a schematic flowchart of the sixth method for constructing a user behavior prediction model provided by an embodiment of the application.

Wherein, step 142, determining the user's preference for the scene according to the cumulative number of times, includes the following steps:

1421. Obtain a preset preference degree according to the accumulated times and a third preset correspondence relationship, where the third preset correspondence relationship includes a correspondence relationship between the accumulated times and the preset preference degree;

1422. Determine the preset preference as the user's preference for the scene.

Among them, the corresponding relationship between the cumulative number of times and the preset preference degree is shown in Table 3.

table 3

累计次数Cumulative times	预设偏好度Default preference
1010	喜欢like
88	一般喜欢Generally like
66	讨厌hate
……...	……...

According to the cumulative number of times the user appears in the scene in Table 3, the preset preference can be obtained. For example, the cumulative number of times is 10, and according to Table 3, it can be obtained that the user's preference for the scene is like. Then the acquired preset preference degree can be determined as the user's preference degree for the scene.

In addition, the electronic device may store the corresponding relationship between the preset preference level and the preset preference degree. That is, the preset preference degree is obtained according to the corresponding relationship between the accumulated times, the preset preference level and the fourth preset. The fourth preset correspondence relationship includes the correspondence relationship between the cumulative number of times, the preset preference level and the preset preference degree. Then, the corresponding relationship between the accumulated times, the preset preference level and the preset preference degree can be as shown in Table 4.

Table 4

累计次数Cumulative times	预设偏好等级Default preference level	预设偏好度Default preference
1010	5级Level 5	喜欢like
88	4级level 4	一般喜欢Generally like
55	2级level 2	讨厌hate
……...	……...	……...

The electronic device obtains the preset preference degree from Table 4. The preset preference level can also be in the form of a score or a percentage. That is, according to the accumulated number of times, not only the preference level can be obtained, but also the user's preference for the scene can be obtained. Then, the acquired preset preference is determined as the user's preference for the scene.

In some embodiments, referring to FIG. 8, FIG. 8 is a schematic flowchart of the seventh method for constructing a user behavior prediction model provided by an embodiment of this application.

143. Acquire the accumulated time that the user appears in the scene according to the historical track information;

144. Determine the user's preference for the scene according to the accumulated duration.

The historical trajectory information may be the cumulative duration of the user's appearance in the scene. Electronic equipment can obtain the accumulated time by using common statistical methods. The cumulative duration may be the cumulative duration of the user appearing in the scene within a preset time period. The preset time period may be in units of years, months, weeks, hours, minutes, or seconds. The cumulative duration may be in units of hours, minutes or seconds. For example, the user appeared in a movie theater on the first day and spent 3 hours in the movie theater. Then, the user appeared in the gym on the next day and stayed in the gym for 2 hours. Then, on the third day, the user appeared in the movie theater again and spent 2 hours in the movie theater, wherein the movie theater where the user appeared on the third day and the movie theater where the user appeared on the first day were the same theater. To sum up, in the three days, the user's electronic device counts the cumulative time that the user appears in the movie theater is 5 hours and the cumulative time that the user appears in the gym is 2 hours.

In addition, obtaining the preset preference degree according to the accumulated duration and the fifth preset correspondence relationship, where the fifth preset correspondence relationship includes the correspondence relationship between the accumulated duration and the preset preference degree;

The preset preference is determined as the user's preference for the scene.

Therefore, the corresponding relationship between the accumulated duration and the preset preference is shown in Table 5.

table 5

累计时长Cumulative duration	预设偏好度Default preference
1小时1 hour	喜欢like
5分钟5 minutes	一般喜欢Generally like
4秒4 seconds	讨厌hate
……...	……...

According to Table 5, the user's preset preference for the scene can be obtained. For example, the cumulative time that the user appears in the scene is 1 hour, and the user's preset preference for the scene is like. Then the preference is the user's preference for the scene. That is, the preset preference is determined as the user's preference for the scene.

In addition, the electronic device may store the corresponding relationship between the preset preference level and the preset preference degree. That is, according to the corresponding relationship between the accumulated time, the preset preference level and the sixth preset, the preset preference degree is obtained. The sixth preset correspondence relationship includes the correspondence relationship between the accumulated duration, the preset preference level and the preset preference degree. Then, the corresponding relationship between the accumulated duration, the preset preference level and the preset preference degree can be as shown in Table 6.

Table 6

累计时长Cumulative duration	预设偏好等级Default preference level	预设偏好度Default preference
1小时1 hour	5级Level 5	喜欢like
5分钟5 minutes	4级level 4	一般喜欢Generally like
4秒4 seconds	2级level 2	讨厌hate
……...	……...	……...

The electronic device obtains the preset preference degree from Table 6. The preset preference level can also be in the form of a score or a percentage. That is, according to the accumulated duration, not only the preference level can be obtained, but also the user's preference for the scene can be obtained. Then the preset preference is determined as the user's preference for the scene.

In some embodiments, referring to FIG. 9, FIG. 9 is a schematic flowchart of the eighth method for constructing a user behavior prediction model provided by an embodiment of this application.

Wherein, step 150, obtaining the user's behavior habit information in the scene according to the user's historical behavior information in the scene, includes the following steps:

151. Determine multiple historical behaviors of the user in the scene according to the historical behavior information.

152. Acquire the number of occurrences of each historical behavior;

153. Establish user behavior habit information in the scene according to the multiple historical behaviors and the corresponding times of each of the historical behaviors.

It is understandable that the electronic device determines multiple historical behaviors of the user in the scene according to the historical behavior information. The historical behaviors include working out in a gym, eating hot pot in a hot pot restaurant, or shopping in a supermarket. The historical behavior information includes application type information, fitness information, game information, or food information of the application opened by the user. The electronic device can use the k-nearest neighbor classification algorithm (k-nearest neighbor classification, KNN algorithm) to obtain user behavior information.

First, obtain multiple raw data d _n through the MySQL relational database. The multiple raw data are related information collected in the geographic location information. The raw data may be related to food, games or fitness. However, when the original data acquisition d _n, the electronic device does not know what is in the end of the original data d _n Yes. It is necessary to more raw data d _n classified by KNN algorithm, to determine whether each of the original data d _n corresponding to the data type. The data types include food, games, or fitness.

Among them, the principle of the KNN algorithm is to classify new data by calculating the distance between the new data and different types of data points in the historical sample data. For example, the electronic device stores multiple historical food data and multiple historical fitness data. And the type of the historical food data is a food type. The type of the historical fitness data is a fitness type. The electronic equipment collects the original data of A. Input the feature vector of A's original data into the KNN algorithm model. Then the distance between the original data of A and each historical food data can be calculated by Euclidean distance formula or Manhattan distance formula. And calculate the distance between A's original data and each historical fitness data.

Then, arrange them according to the increasing distance. Select K points with the smallest distance value, where K points can be 10, 20, or 100. The larger the value of K, the more accurate the type obtained by the original data of A. Determine the frequency of K points in the food type and the frequency in the fitness type. The type with the highest frequency among the K points is selected as the predicted classification of A's original data. For example, if K points have the highest frequency in the food type, then the original data of A is the food type. Or if K points have the highest frequency in the fitness type, then the original data of A is the fitness type.

Then, the electronic device acquires multiple historical behaviors of historical behavior information. For example, if the historical behavior information is food type information, then the historical behavior can be eating food, eating hot pot, or eating green vegetables. Then, the electronic device obtains the number of occurrences of each historical behavior. The electronic device records the number of occurrences of each historical behavior of the user. In a preset time period, the user obtains the number of occurrences of each historical behavior in the scene. For example, in the first week, users eat hot pot and play games at a hot pot restaurant. Then the historical behavior of the electronic device in the hot pot restaurant is eating hot pot and playing games, and then the electronic device records the eating hot pot and playing games. In the second week, the user’s historical behavior at the same hot pot restaurant was to only eat hot pot. The electronic device records that the user ate hot pot at the same hot pot restaurant in the second week. In summary, summarizing the user's historical behavior in the hot pot restaurant, we can get that the user has eaten hot pot twice and played a game once in the hot pot restaurant.

The establishment of the user's behavior habit information in the scene according to the multiple historical behaviors and the corresponding times of each of the historical behaviors may be as shown in Table 7.

Table 7

历史行为Historical behavior	次数frequency	行为习惯信息Behavior information
吃火锅eat hot pot	88	经常吃火锅Often eat hot pot
吃甜点Eat dessert	55	有时吃甜点Sometimes for dessert
健身Fitness	22	很少健身Little fitness
……...	……...	……...

The user's behavior habit information in the scene can be obtained according to the historical behavior and the number of times. For example, as shown in Table 7, if a user eats hot pot 8 times in a hot pot restaurant, it can be obtained that the user often eats hot pot in a hot pot restaurant. And the user eats dessert 5 times in the hot pot restaurant, you can get the user sometimes eat dessert in the hot pot restaurant.

In addition, the preset frequency interval can be matched according to the frequency. According to the correspondence between historical behavior, frequency, preset frequency interval and the seventh preset, the user's behavior habit information in the scene is acquired. The seventh preset correspondence relationship includes the correspondence relationship between historical behavior, frequency, preset frequency interval, and behavior habit information. Then, the correspondence between historical behavior, frequency, preset frequency interval, and behavior habit information can be as shown in Table 8.

Table 8

历史行为Historical behavior	次数frequency	预设次数区间Preset frequency interval	行为习惯信息Behavior information
吃火锅eat hot pot	88	[5,9][5,9]	经常吃火锅Often eat hot pot
吃甜点Eat dessert	55	[4,6][4,6]	有时吃甜点Sometimes for dessert
健身Fitness	22	[1,3][1,3]	很少健身Little fitness
……...	……...	……...	……...

The electronic device can obtain the user's behavior habit information in the scene according to Table 8. The frequency and the preset frequency interval can be stored in the electronic device in advance, and when the frequency is obtained, the preset frequency interval can be quickly matched.

During specific implementation, this application is not limited by the order of execution of the various steps described, and certain steps may also be carried out in other order or carried out simultaneously without conflict.

It can be seen from the above that the method for constructing a user behavior prediction model provided by the embodiment of the present application includes: acquiring the geographic location information of the electronic device currently located and the perception data of the scene where the electronic device is currently located; The current scene of the electronic device; the type of relationship between the user and the scene is determined according to the length of time the user stays in the scene and the operation information in the scene; the user pair is obtained according to the historical track information of the user in the scene The preference degree of the scene; the user's behavior habit information in the scene is obtained according to the user's historical behavior information in the scene; the preference degree and the behavior habit information are obtained according to the geographic location information, the relationship type, the preference Establish the user behavior prediction model. In the method for constructing a user behavior prediction model, the electronic device can push information of interest to the user according to the user's preference for the geographic location and behavior habit information, so as to improve the accuracy of the electronic device pushing information to the user. And it improves the speed and efficiency of the electronic device when pushing information.

An embodiment of the present application also provides a device for constructing a user behavior prediction model, including:

A user behavior prediction model construction device, including:

In some embodiments, the determining module is used to:

In some embodiments, when determining the type of relationship between the user and the scene according to the duration and the number of times each application software is operated, the determining module is configured to:

In some embodiments, the number of times of operation includes the duration of operation. When determining the type of relationship between the user and the scene according to the duration and the number of times each application software is operated, the determining module is configured to :

In some embodiments, when acquiring the user's preference for the scene according to the historical track information of the user in the scene, the second acquiring module is configured to:

In some embodiments, when determining the user's preference for the scene according to the cumulative number of times, the second acquiring module is configured to:

The preset preference is determined as the user's preference for the scene.

In some embodiments, when acquiring the user's behavior habit information in the scene according to the user's historical behavior information in the scene, the third acquiring module is configured to:

Get the number of occurrences of each historical behavior;

The apparatus for constructing a user behavior prediction model provided in the embodiment of the present application may be integrated in an electronic device. The electronic device may be a smart phone, a tablet computer, a game device, an AR (Augmented Reality) device, a car, a data storage device, an audio playback device, a video playback device, a notebook computer, a desktop computing device, a wearable device such as Electronic watches, electronic glasses, electronic helmets, electronic bracelets, electronic necklaces, electronic clothing and other equipment.

Referring to FIG. 10, FIG. 10 is a schematic structural diagram of a user behavior prediction model construction apparatus provided by an embodiment of the application. Wherein, the user behavior prediction model construction device 200 includes: a first acquisition module 201, an identification module 202, a determination module 203, a second acquisition module 204, a third acquisition module 205, and an establishment module 206.

The first acquisition module 201 is configured to acquire the geographic location information where the electronic device is currently located and the perception data of the scene where the electronic device is currently located.

When the user arrives at a place, the first obtaining module 201 may obtain the longitude and latitude information or coordinate points of the user's arrival at the place through the Global Positioning System (GPS). Then, the first acquisition module 201 converts the latitude and longitude information or coordinate points into geographic location information according to the target software. The geographic location information includes shopping malls, office buildings, bus stations, or communities. The target software includes Baidu map, Tencent map or Gaode map, etc. In addition, when the user arrives at a place, the first obtaining module 201 may also directly obtain the geographic location information of the electronic device through the target software.

In addition, the first acquisition module 201 can construct a database to store all the acquired data. Therefore, the geographic location information can be recorded as l _n . The first obtaining module 201 collects data related to the geographic location. Wherein the correlation data of at least one raw data d _n, and the original data may be related to food, exercise or game. The first obtaining module 201 may use a MySQL relational database to store the geographic location information and the original data related to the geographic location in the form of a table, without putting all the data together. Therefore, the speed at which the electronic device obtains geographic location information and raw data is improved, and the flexibility of using the electronic device is also improved. For example, the table may be (l _n , d _n ).

Correspondingly, the first acquisition module 201 acquires the perception data of the current scene. For example, the electronic device may obtain the current ambient light intensity through the light sensor of the information perception layer, the current temperature of the electronic device through the temperature sensor, etc., or the current geographic location of the electronic device through the position sensor.

In addition, the first acquiring module 201 can also acquire the user's action track. For example, when the electronic device recognizes that the user moves from the current geographic location to another geographic location, the electronic device can track the user's movement track. When the user reaches the target geographic location, the geographic location information of the target geographic location is acquired.

The recognition module 202 is configured to recognize the current scene of the electronic device according to the perception data.

The recognition module 202 recognizes the current scene of the electronic device according to the acquired perception data. For example, the acquired sensing data such as temperature, ambient light intensity, and geographic location are used to identify the current scene of the electronic device to determine the current scene of the electronic device. The scenes include: gas stations, gyms, food courts or scenes around movie theaters.

The determining module 203 is configured to determine the type of relationship between the user and the scene according to the length of time the user stays in the scene and the operation information in the scene.

When the user is in the scene, the determining module 203 obtains the length of time the user stays in the scene. The duration can be in hours, minutes or seconds. For example, 1 hour, 40 minutes, or 2450 seconds. The determining module 203 obtains the user's operation information in the scene. The operation information includes the user's operation of multiple application software of the electronic device. The operation information may include: opening Alipay, opening video, or opening navigation. The type of relationship between the user and the scene is determined according to the length of time the user stays in the scene and the operation information in the scene. The relationship type may include home, office, work place, or canteen.

In addition, the determining module 203 may store the relationship type and record it as c _n .

The second obtaining module 204 obtains the user's preference for the scene according to the historical track information of the user in the scene.

The second acquiring module 204 acquires historical track information of the user in the scene. The historical track information may be the cumulative number of times the user appears in the scene. The second obtaining module 204 can obtain the cumulative number of times by using a common statistical method. The cumulative number of times may be the number of times the user appears in the scene within a preset time period. The preset time period may be in units of years, months, weeks, hours, minutes, or seconds. For example, the second acquisition module 204 can count the cumulative number of times the user appears in the movie theater within one year as five or the second acquisition module 204 can count the cumulative number of times the user appears in the gym within three months as three.

In addition, the preset time period may also be the second obtaining module 204 counts the use time period from the date when the user starts using the electronic device to the date on the current calendar. For example, the date when the user starts to use the electronic device may be June 6, 2018. The current or current calendar date is August 8, 2019. Then the length of time the user uses the electronic device is one year, two months, and two days. Then, the second acquisition module 204 counts that the cumulative number of times the user appeared in the supermarket in one year, two months, and two days is 30 times and the cumulative number of times in the movie theater is 3 times.

The user's preference for the scene is determined according to the cumulative number of times. The second obtaining module 204 may use a common statistical method to calculate the user's preference for the scene. The preference includes like, generally like or dislike. The preference is to measure the degree of user's preference for the scene. For example, the cumulative number of times a user appears in a movie theater in a day is 10 times. And the cumulative number of times the user appeared in the subway station in the same day is 3 times, so 10 times is greater than 3 times. Therefore, it can be concluded that users like to appear in movie theaters. I generally like to appear in subway stations.

In addition, the historical track information may also be the cumulative duration of the user's appearance in the scene. The second obtaining module 204 can obtain the accumulated time length by using a common statistical method. The cumulative duration may be the cumulative duration of the user appearing in the scene within a preset time period. The preset time period may be in units of years, months, weeks, hours, minutes, or seconds. The cumulative duration may be in units of hours, minutes or seconds. For example, the user appeared in a movie theater on the first day and spent 3 hours in the movie theater. Then, the user appeared in the gym on the next day and stayed in the gym for 2 hours. Then, on the third day, the user appeared in the movie theater again and spent 2 hours in the movie theater, wherein the movie theater where the user appeared on the third day and the movie theater where the user appeared on the first day were the same theater. To sum up, in these three days, the second acquisition module 204 counts that the cumulative time that the user appears in the movie theater is 5 hours and the cumulative time that the user appears in the gym is 2 hours.

For another example, the second acquisition module 204 can count the cumulative time that the user appears in the karaoke hall within one year as 5 hours. Or, the second acquiring module 204 counts that the cumulative time that the user appears in the movie theater within one month is 75 minutes.

In addition, the preset time period may also be the second obtaining module 204 counts the use time period from the date when the user starts using the electronic device to the date on the current calendar. For example, the date when the user starts to use the electronic device may be January 1, 2018. The current or current calendar date is January 1, 2019. Then the user has used the electronic device for one year. Then the second acquisition module 204 counts that the cumulative number of times that the user appears in the gym in the one year is 20 times and the cumulative number of times the library is 2 times.

In addition, the second acquiring module 204 may record the user's preference for the scene, which is recorded as p _n . According to geographic location information, relationship type and preference degree, MySQL relational database is used to store it in the form of a table. That is, the table can be (l _n , c _n , p _n ).

The third obtaining module 205 is configured to obtain the user's behavior habit information in the scene according to the user's historical behavior information in the scene.

It is understandable that the third acquiring module 205 determines multiple historical behaviors of the user in the scene according to the historical behavior information. The historical behaviors include working out in a gym, eating hot pot in a hot pot restaurant, or shopping in a supermarket. The historical behavior information includes application type information, fitness information, game information, or food information of the application opened by the user.

Then, the third obtaining module 205 obtains the number of occurrences of each historical behavior. The third obtaining module 205 has the number of occurrences of each historical behavior of the user. In a preset time period, the user obtains the number of occurrences of each historical behavior in the scene. For example, in the first week, users eat hot pot and play games at a hot pot restaurant. Then the historical behavior of electronic equipment in hot pot restaurants is eating hot pot and playing games. Then, the third acquiring module 205 records the user's historical behavior in the first week as the eating hot pot and playing games. In the second week, the user’s historical behavior at the same hot pot restaurant was to only eat hot pot. Then the electronic device records the historical behavior of eating hot pot in the same hot pot restaurant in the second week. In summary, by summarizing the historical behaviors that occurred in the hot pot restaurant, it can be obtained that the user's historical behavior in the hot pot restaurant and within the two weeks is eating hot pot twice and playing a game once.

Correspondingly, the third acquiring module 205 can store the user's behavior habit information, and record it as b _n .

The establishment module 206 is configured to establish the user behavior prediction model according to the geographic location information, the relationship type, the preference degree, and the behavior habit information.

First, the establishment module 206 may establish a relationship table for the geographic location information, the relationship type, the preference degree, and the behavior habit information, namely (l _n , c _n , p _n , b _n ). Generate a user behavior prediction model according to the relationship table. Or the geographic location information, the relationship type, the preference degree, and the behavior habit information are stored in the form of a database. A user behavior prediction model is generated according to the database. Or the establishment module 206 may directly establish a user behavior prediction model based on the geographic location information, the relationship type, the preference degree, and the behavior habit information.

Secondly, after the user behavior prediction model is established, the electronic device can obtain social information corresponding to the current scene of the user. The social information can include neighboring resources, laws and customs, customs, or social relations. According to the user behavior prediction model, the electronic device can predict which social information users are interested in. The information of interest is pushed to the user, so that the user can quickly and efficiently receive the information of interest, so that the electronic device improves the accuracy of pushing the information of interest to the user. And it can also enable electronic devices to provide users with relevant information efficiently and quickly. For example, the user is shopping in a shopping mall. Certain merchants in shopping malls are conducting discount promotions. The establishment module 206 predicts that the user is interested in the information of discount promotion activities through the user behavior prediction model. Then the electronic device may send the information of the discount promotion activity to the user, so that the user can quickly understand which merchant is conducting the discount promotion activity and what the content of the discount promotion activity is.

In some embodiments, the determining module 203 is configured to perform the following steps:

The determining module 203 can obtain the length of time the user stays in the scene and the operation information in the scene. For example, the duration of stay in the scene is the duration between when the user enters the scene and leaves the scene. For example, if 2 hours have passed since the user entered the movie theater and left the movie theater, then the 2 hours is the length of time the user stays in the scene. Wherein, the scene operation information may include information that the user operates multiple application software of the electronic device. For example, open the XX game in a movie theater. Open the XX payment software in the restaurant.

Then, the determining module 203 obtains the number of times the user has been operated on each of the application software. For example, users open payment software, game software, and camera software in a shopping mall. Among them, from the time the user enters the shopping mall to when he leaves the mall, the electronic device obtains that the user has opened the payment software 5 times, opened the game software 2 times, and opened the camera software 3 times.

Finally, the type of relationship between the user and the scene is determined according to the duration and the number of times each application software is operated. It is understandable that, within the length of time the user stays in the scene, the determining module 203 can determine the type of relationship between the user and the scene according to the number of times each application software is operated. The application software that has been operated many times can be considered that the user frequently operates the application software that has been operated many times in the scene. Then, the type of relationship between the user and the scene is determined according to the application software that has been operated many times.

The determining module 203 determines the target application software with the most number of operations based on the acquired number of operations for each application software. Then, according to the duration, the target application software, and a first preset correspondence relationship, the relationship type between the user and the scene is acquired, where the first preset correspondence relationship includes duration, target application software, and relationship Correspondence between types. It is understandable that the target application software that has been operated most frequently is the target application software that the user frequently operates in the scene. The target application software that has been operated many times does not mean that one application software can be multiple application software.

Therefore, the corresponding relationship between the duration, the target application software and the relationship type may be as shown in Table 9.

Table 9

According to Table 9, the type of relationship between the user and the scene can be determined according to the duration and the target application software. For example, if the user is in the XX community and opened the most frequently operated video software and Taobao software within 3 hours, then according to the 3 hours, video software and Taobao software, the relationship type between the user and the XX community can be obtained as home.

In addition, the determining module 203 may set a preset threshold of the number of times of operations to accurately obtain target application operations that have been operated many times. That is, the application software that is greater than or equal to the preset threshold of the number of operations can be selected as the target application software. For example, the electronic device obtains that the number of operations of the payment software is 3 times, the number of operations of the photographing software is 5 times, and the number of operations of the video software is 1 time. The preset threshold for the number of operations is 2. Then select the application software corresponding to the number of operations greater than or equal to 2 as the target application software. That is, payment software and camera software are selected as the target application software.

The determining module 203 determines the target application software for the duration of operation according to the acquired duration of operation of each application software. The number of operations includes the duration of operations. Then, the determining module 203 obtains the type of relationship between the user and the scene according to the duration, the target application software, and a second preset correspondence relationship, where the second preset correspondence relationship includes duration, target application Correspondence between software and relationship types. It can be understood that the target application software that has been operated for the longest time is the target application software that the user frequently operates in the scene. The target application software that has been operated for the longest time does not mean that one application software can be multiple application software.

Therefore, the corresponding relationship between the duration, the target application software, and the relationship type may be as shown in Table 10.

Table 10

In some embodiments, the second acquisition module 204 is configured to perform the following steps:

The second acquiring module 204 acquires historical track information of the user in the scene. The historical track information may be the cumulative number of times the user appears in the scene. Electronic equipment can obtain the cumulative number of times by using common statistical methods. The cumulative number of times may be the number of times the user appears in the scene within a preset time period. The preset time period may be in units of years, months, weeks, hours, minutes, or seconds. For example, the second acquisition module 204 may count the cumulative number of times the user appears in the movie theater within one year as five or the second acquisition module 204 may count the cumulative number of times the user appears in the gym within three months as three.

The preset preference is determined as the user's preference for the scene.

Among them, the corresponding relationship between the cumulative number of times and the preset preference is shown in Table 11.

Table 11

According to the cumulative number of times the user appears in the scene in Table 11, the preset preference can be obtained. For example, the cumulative number of times is 10, and according to Table 10, it can be obtained that the user's preference for the scene is like. Then the acquired preset preference degree can be determined as the user's preference degree for the scene.

In addition, the second acquisition module 204 may store the corresponding relationship between the preset preference level and the preset preference degree. That is, the preset preference degree is obtained according to the corresponding relationship between the accumulated times, the preset preference level and the fourth preset. The corresponding relationship between the cumulative number of times, the preset preference level and the preset preference degree can be shown in Table 12.

Table 12

The second obtaining module 204 obtains the preset preference degree from the table 12. The preset preference level can also be in the form of a score or a percentage. That is, according to the accumulated number of times, not only the preference level can be obtained, but also the user's preference for the scene can be obtained. Then, the acquired preset preference is determined as the user's preference for the scene.

The historical trajectory information may be the cumulative duration of the user's appearance in the scene. The second obtaining module 204 can obtain the accumulated time length by using a common statistical method. The cumulative duration may be the cumulative duration of the user appearing in the scene within a preset time period. The preset time period may be in units of years, months, weeks, hours, minutes, or seconds. The cumulative duration may be in units of hours, minutes or seconds. For example, the user appeared in a movie theater on the first day and spent 3 hours in the movie theater. Then, the user appeared in the gym on the next day and stayed in the gym for 2 hours. Then, on the third day, the user appeared in the movie theater again and spent 2 hours in the movie theater, wherein the movie theater where the user appeared on the third day and the movie theater where the user appeared on the first day were the same theater. To sum up, in these three days, the second acquisition module 204 counts that the cumulative time that the user appears in the movie theater is 5 hours and the cumulative time that the user appears in the gym is 2 hours.

For another example, the second acquisition module 204 can count the cumulative time that the user appears in the karaoke hall within one year as 5 hours. Or, the second obtaining module 204 counts that the cumulative time that the user appears in the movie theater within one month is 75 minutes.

The preset preference is determined as the user's preference for the scene. Therefore, the corresponding relationship between the accumulated duration and the preset preference is shown in Table 13.

Table 13

The second obtaining module 204 can obtain the user's preset preference for the scene according to Table 13. For example, the cumulative time that the user appears in the scene is 1 hour, and the user's preset preference for the scene is like. Then the preference is the user's preference for the scene. That is, the preset preference is determined as the user's preference for the scene.

In addition, the second acquisition module 204 may store the corresponding relationship between the preset preference level and the preset preference degree. That is, according to the corresponding relationship between the accumulated time, the preset preference level and the sixth preset, the preset preference degree is obtained. The corresponding relationship between the accumulated duration, the preset preference level and the preset preference degree can be shown in Table 14.

Table 14

The second obtaining module 204 obtains the preset preference degree from the table 14. The preset preference level can also be in the form of a score or a percentage. That is, according to the accumulated duration, not only the preference level can be obtained, but also the user's preference for the scene can be obtained. Then the preset preference is determined as the user's preference for the scene.

In some embodiments, the third obtaining module 205 is configured to perform the following steps:

Get the number of occurrences of each historical behavior;

It is understandable that the third acquiring module 205 determines multiple historical behaviors of the user in the scene according to the historical behavior information. The historical behaviors include working out in a gym, eating hot pot in a hot pot restaurant, or shopping in a supermarket. The historical behavior information includes application type information, fitness information, game information, or food information of the application opened by the user. The electronic device can use the k-nearest neighbor classification algorithm (k-nearest neighbor classification, KNN algorithm) to obtain user behavior information.

First, obtain multiple raw data d _n through the MySQL relational database. The multiple raw data are related information collected in the geographic location information. The raw data may be related to food, games or fitness. However, when the original data acquisition d _n, a third acquisition module 205 does not know what is in the end of the original data d _n Yes. It is necessary to more raw data d _n classified by KNN algorithm, to determine whether each of the original data d _n corresponding to the data type. The data types include food, games, or fitness.

Among them, the principle of the KNN algorithm is to classify new data by calculating the distance between the new data and different types of data points in the historical sample data. For example, the third acquisition module 205 stores multiple pieces of historical food data and multiple pieces of historical fitness data. And the type of the historical food data is a food type. The type of the historical fitness data is a fitness type. The third acquisition module 205 acquires A raw data. Input the feature vector of A's original data into the KNN algorithm model. Then the distance between the original data of A and each historical food data can be calculated by Euclidean distance formula or Manhattan distance formula. And calculate the distance between A's original data and each historical fitness data.

Next, the third acquiring module 205 acquires multiple historical behaviors of historical behavior information. For example, if the historical behavior information is food type information, then the historical behavior can be eating food, eating hot pot, or eating green vegetables. Then, the third obtaining module 205 obtains the number of occurrences of each historical behavior. The third obtaining module 205 records the number of occurrences of each historical behavior of the user. In a preset time period, the user obtains the number of occurrences of each historical behavior in the scene. For example, in the first week, users eat hot pot and play games at a hot pot restaurant. Then the historical behavior of the electronic device in the hot pot restaurant is eating hot pot and playing games, and then the electronic device records the eating hot pot and playing games. In the second week, the user’s historical behavior at the same hot pot restaurant was to only eat hot pot. The electronic device records that the user ate hot pot at the same hot pot restaurant in the second week. In summary, summarizing the user's historical behavior in the hot pot restaurant, we can get that the user has eaten hot pot twice and played a game once in the hot pot restaurant.

The establishment of user behavior habit information in the scene according to the multiple historical behaviors and the corresponding times of each of the historical behaviors can be as shown in Table 15.

Table 15

The user's behavior habit information in the scene can be obtained according to the historical behavior and the number of times. For example, as shown in Table 15, a user eats hot pot 8 times in a hot pot restaurant, and it can be obtained that the user often eats hot pot in a hot pot restaurant. And the user eats dessert 5 times in the hot pot restaurant, you can get the user sometimes eat dessert in the hot pot restaurant.

In addition, the preset frequency interval can be matched according to the frequency. According to the correspondence between historical behavior, frequency, preset frequency interval and the seventh preset, the user's behavior habit information in the scene is acquired. The seventh preset correspondence relationship includes the correspondence relationship between historical behavior, frequency, preset frequency interval, and behavior habit information. Then, the correspondence between historical behavior, frequency, preset frequency interval, and behavior habit information can be shown in Table 16.

Table 16

The electronic device can obtain the user's behavior habit information in the scene according to Table 16. The frequency and the preset frequency interval can be stored in the electronic device in advance, and when the frequency is obtained, the preset frequency interval can be quickly matched.

It can be seen from the above that the user behavior prediction model construction apparatus 200 provided by the embodiment of the present application includes: a first obtaining module 201, configured to obtain the geographic location information of the electronic device currently located and the perception data of the current scene of the electronic device The identification module 202 is used to identify the current scene of the electronic device according to the perception data; the determination module 203 is used to determine the user and the scene according to the length of time the user stays in the scene and the operating information in the scene The type of relationship between the scenes; the second acquisition module 204 is used to acquire the user’s preference for the scene according to the user’s historical track information in the scene; the third acquisition module 205 is used to acquire the user’s preference for the scene according to the user’s presence in the scene The historical behavior information of the user obtains the user’s behavior habit information in the scene; the establishment module 206 is used to establish the user behavior prediction model according to the geographic location information, the relationship type, the preference degree, and the behavior habit information . In the device for constructing a user behavior prediction model, the electronic device can push information of interest to the user according to the user's preference for the geographic location and behavior habit information, so as to improve the accuracy of the electronic device's pushing information to the user. And it improves the speed and efficiency of the electronic device when pushing information.

The embodiment of the application also provides an electronic device. The electronic device may be a smart phone, a tablet computer, a game device, an AR (Augmented Reality) device, a car, a data storage device, an audio playback device, a video playback device, a notebook computer, a desktop computing device, a wearable device such as Electronic watches, electronic glasses, electronic helmets, electronic bracelets, electronic necklaces, electronic clothing and other equipment. Among them, the electronic device can send information to the user.

Referring to FIG. 11, FIG. 11 is a schematic diagram of a first structure of an electronic device provided by an embodiment of the application.

Among them, the electronic device 300 includes a processor 301 and a memory 302. Wherein, the processor 301 is electrically connected to the memory 302.

The processor 301 is the control center of the electronic device 300. It uses various interfaces and lines to connect the various parts of the entire electronic device. It executes the electronic device by running or calling the computer program stored in the memory 302 and calling the data stored in the memory 302. Various functions and processing data of the equipment, so as to monitor the electronic equipment as a whole.

In this embodiment, the processor 301 in the electronic device 300 will load the instructions corresponding to the process of one or more computer programs into the memory 302 according to the following steps, and the processor 301 will run the instructions stored in the memory 302 The computer program in:

In some embodiments, when determining the type of relationship between the user and the scene according to the length of time the user stays in the scene and the operation information of the scene, the processor 301 is configured to:

In some embodiments, when determining the type of relationship between the user and the scene according to the duration and the number of times each application software has been operated, the processor 301 is configured to:

In some embodiments, when acquiring the user's preference for the scene according to the historical track information of the user in the scene, the processor 301 is configured to:

In some embodiments, the user’s preference for the scene is determined according to the cumulative number of times, and the processor 301 is configured to:

The preset preference is determined as the user's preference for the scene.

In some embodiments, according to the historical track information of the user in the scene, the processor 301 is configured to:

In some embodiments, according to the user's historical behavior information in the scene to obtain the user's behavior habit information in the scene, the processor 301 is configured to:

Get the number of occurrences of each historical behavior;

The memory 302 can be used to store computer programs and data. The computer program stored in the memory 302 contains instructions that can be executed in the processor. Computer programs can be composed of various functional modules. The processor 301 executes various functional applications and data processing by calling a computer program stored in the memory 302.

In some embodiments, referring to FIG. 12, FIG. 12 is a schematic diagram of a second structure of an electronic device provided in an embodiment of this application.

Wherein, the electronic device 300 further includes: a display screen 303, a control circuit 304, an input unit 305, a sensor 306, and a power supply 307. The processor 301 is electrically connected to the display screen 303, the control circuit 304, the input unit 305, the sensor 306, and the power source 307, respectively.

The display screen 303 may be used to display information input by the user or information provided to the user and various graphical user interfaces of the electronic device. These graphical user interfaces may be composed of images, text, icons, videos, and any combination thereof.

The control circuit 304 is electrically connected to the display screen 303 for controlling the display screen 303 to display information.

The input unit 305 may be used to receive inputted numbers, character information, or user characteristic information (such as fingerprints), and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control. The input unit 305 may include a fingerprint recognition module.

The sensor 306 is used to collect the information of the electronic device itself or the information of the user or the external environment information. For example, the sensor 306 may include multiple sensors such as a distance sensor, a magnetic field sensor, a light sensor, an acceleration sensor, a fingerprint sensor, a Hall sensor, a position sensor, a gyroscope, an inertial sensor, an attitude sensor, a barometer, and a heart rate sensor.

The power supply 307 is used to supply power to various components of the electronic device 300. In some embodiments, the power supply 307 may be logically connected to the processor 301 through a power management system, so that functions such as charging, discharging, and power consumption management can be managed through the power management system.

Although not shown in FIG. 12, the electronic device 300 may also include a camera, a Bluetooth module, etc., which will not be repeated here.

It can be seen from the above that an embodiment of the present application provides an electronic device, which performs the following steps: obtains the geographic location information where the electronic device is currently located and the perception data of the scene where the electronic device is currently located; The data identifies the scene where the electronic device is currently located; determines the type of relationship between the user and the scene according to the length of time the user stays in the scene and the operation information in the scene; according to the historical track of the user in the scene The information obtains the user’s preference for the scene; obtains the user’s behavior habit information in the scene according to the user’s historical behavior information in the scene; according to the geographic location information, the relationship type, the preference and the The behavior habit information establishes the user behavior prediction model. In the method for constructing a user behavior prediction model, the electronic device can push information of interest to the user according to the user's preference for the geographic location and behavior habit information, so as to improve the accuracy of the electronic device pushing information to the user. And it improves the speed and efficiency of the electronic device when pushing information.

The embodiment of the present application also provides a storage medium in which a computer program is stored, and the computer program is applied to an electronic device. The electronic device can push information and display the pushed information on the display screen of the electronic device. When the computer program runs on the computer, the computer executes the user behavior prediction model construction method described in any of the above embodiments.

For example, when the computer program runs on a computer, the computer is caused to execute:

It should be noted that those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above-mentioned embodiments can be completed by instructing relevant hardware through a computer program, which can be stored in a computer-readable storage medium. Here, the storage medium may include, but is not limited to: read only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk, etc.

The method, device, storage medium, and electronic equipment for constructing a user behavior prediction model provided by the embodiments of the present application are described in detail above. Specific examples are used in this article to describe the principles and implementation of the application. The description of the above examples is only used to help understand the methods and core ideas of the application; at the same time, for those skilled in the art, according to the There will be changes in the thinking, specific implementation and application scope. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

A method for constructing a user behavior prediction model, including:

Acquiring the geographic location information where the electronic device is currently located and the perception data of the scene where the electronic device is currently located;

Identifying the current scene of the electronic device according to the perception data;

Determining the type of relationship between the user and the scene according to the length of time the user stays in the scene and the operation information in the scene;

Acquiring the user's preference for the scene according to the historical track information of the user in the scene;

Acquiring user behavior habit information in the scene according to the user's historical behavior information in the scene;

The user behavior prediction model is established according to the geographic location information, the relationship type, the preference degree, and the behavior habit information.
The method for constructing a user behavior prediction model according to claim 1, wherein the determining the type of relationship between the user and the scene according to the length of time the user stays in the scene and the operation information of the scene includes:

Acquiring the length of time the user stays in the scene and the operation information in the scene, where the operation information includes information about the user's operation of multiple application software of the electronic device;

Acquiring, according to the operation information, the number of times the user has been operated on each of the application software;

The type of relationship between the user and the scene is determined according to the duration and the number of times each application software is operated.
The method for constructing a user behavior prediction model according to claim 2, wherein the determining the type of relationship between the user and the scene according to the duration and the number of times each application software is operated includes:

Determine the target application software that has been operated most frequently from the multiple application software;

According to the duration, the target application software, and a first preset correspondence, the relationship type between the user and the scene is acquired, where the first preset correspondence includes the duration, the target application software, and the relationship type. Correspondence between.
The method for constructing a user behavior prediction model according to claim 2, wherein the number of times of operation includes the duration of operation, and the determination of the relationship between the user and the scene is based on the duration and the number of times each application software is operated. Types of relationships between, including:

Determine the target application software that has been operated for the longest time from the multiple application software;

According to the duration, the target application software, and a second preset correspondence relationship, the relationship type between the user and the scene is acquired, wherein the second preset correspondence relationship includes the duration, the target application software and the relationship type The corresponding relationship.
The method for constructing a user behavior prediction model according to claim 1, wherein the obtaining the user's preference for the scene according to the historical track information of the user in the scene comprises:

Acquiring the cumulative number of times the user appears in the scene according to the historical track information;

The user's preference for the scene is determined according to the cumulative number of times.
The method for constructing a user behavior prediction model according to claim 5, wherein the determining the user's preference for the scene according to the cumulative number of times comprises:

Obtaining a preset preference degree according to the cumulative number of times and a third preset correspondence relationship, where the third preset correspondence relationship includes a correspondence relationship between the cumulative number of times and the preset preference degree;

The preset preference is determined as the user's preference for the scene.
The method for constructing a user behavior prediction model according to claim 1, wherein the obtaining the user's preference for the scene according to the historical track information of the user in the scene comprises:

Acquiring, according to the historical track information, the accumulated time that the user appears in the scene;

Determine the user's preference for the scene according to the accumulated time.
The method for constructing a user behavior prediction model according to claim 1, wherein the acquiring user behavior habit information in the scene according to the user's historical behavior information in the scene comprises:

Determine multiple historical behaviors of the user in the scene according to the historical behavior information;

Get the number of occurrences of each historical behavior;

Establish user behavior habit information in the scene according to the multiple historical behaviors and the corresponding times of each of the historical behaviors.
A user behavior prediction model construction device, including:

The first obtaining module is used to obtain the geographic location information where the electronic device is currently located and the sensory data of the scene where the electronic device is currently located;

An identification module, configured to identify the current scene of the electronic device according to the perception data;

A determining module, configured to determine the type of relationship between the user and the scene according to the length of time the user stays in the scene and the operation information in the scene;

The second acquiring module is configured to acquire the user's preference for the scene according to the historical track information of the user in the scene;

The third obtaining module is configured to obtain the user's behavior habit information in the scene according to the user's historical behavior information in the scene;

The establishment module is used to establish the user behavior prediction model according to the geographic location information, the relationship type, the preference degree, and the behavior habit information.
The device for constructing a user behavior prediction model according to claim 9, wherein the determining module is configured to:

Acquiring the length of time the user stays in the scene and the operation information in the scene, where the operation information includes information about the user's operation of multiple application software of the electronic device;

Acquiring, according to the operation information, the number of times the user has been operated on each of the application software;

The type of relationship between the user and the scene is determined according to the duration and the number of times each application software is operated.
The device for constructing a user behavior prediction model according to claim 10, wherein when determining the type of relationship between the user and the scene according to the duration and the number of times each of the application software is operated, the determining module is configured to :

Determine the target application software that has been operated most frequently from the multiple application software;

According to the duration, the target application software, and a first preset correspondence, the relationship type between the user and the scene is acquired, where the first preset correspondence includes the duration, the target application software, and the relationship type. Correspondence between.
A storage medium in which a computer program is stored, and when the computer program runs on a computer, the computer executes:

Acquiring the geographic location information where the electronic device is currently located and the perception data of the scene where the electronic device is currently located;

Identifying the current scene of the electronic device according to the perception data;

Determining the type of relationship between the user and the scene according to the length of time the user stays in the scene and the operation information in the scene;

Acquiring the user's preference for the scene according to the historical track information of the user in the scene;

Acquiring user behavior habit information in the scene according to the user's historical behavior information in the scene;

The user behavior prediction model is established according to the geographic location information, the relationship type, the preference degree, and the behavior habit information.
An electronic device, the electronic device includes a processor and a memory, and a computer program is stored in the memory, and the processor is configured to: by calling the computer program stored in the memory:

Acquiring the geographic location information where the electronic device is currently located and the perception data of the scene where the electronic device is currently located;

Identifying the current scene of the electronic device according to the perception data;

Determining the type of relationship between the user and the scene according to the length of time the user stays in the scene and the operation information in the scene;

Acquiring the user's preference for the scene according to the historical track information of the user in the scene;

Acquiring user behavior habit information in the scene according to the user's historical behavior information in the scene;

The user behavior prediction model is established according to the geographic location information, the relationship type, the preference degree, and the behavior habit information.
The electronic device according to claim 13, wherein, when determining the type of relationship between the user and the scene according to the length of time the user stays in the scene and the operation information of the scene, the processor is configured to:

Acquiring the length of time the user stays in the scene and the operation information in the scene, where the operation information includes information about the user's operation of multiple application software of the electronic device;

Acquiring, according to the operation information, the number of times the user has been operated on each of the application software;

The type of relationship between the user and the scene is determined according to the duration and the number of times each application software is operated.
The electronic device according to claim 14, wherein, when determining the type of relationship between the user and the scene according to the duration and the number of times each of the application software is operated, the processor is configured to:

Determine the target application software that has been operated most frequently from the multiple application software;

According to the duration, the target application software, and a first preset correspondence, the relationship type between the user and the scene is acquired, where the first preset correspondence includes the duration, the target application software, and the relationship type. Correspondence between.
The electronic device according to claim 14, wherein the number of times of operation includes the duration of the operation, and when the type of relationship between the user and the scene is determined according to the duration and the number of times each application software is operated, The processor is used for:

Determine the target application software that has been operated for the longest time from the multiple application software;

According to the duration, the target application software, and a second preset correspondence relationship, the relationship type between the user and the scene is acquired, wherein the second preset correspondence relationship includes the duration, the target application software and the relationship type The corresponding relationship.
The electronic device according to claim 13, wherein, when acquiring the user's preference for the scene according to the historical track information of the user in the scene, the processor is configured to:

Acquiring the cumulative number of times the user appears in the scene according to the historical track information;

The user's preference for the scene is determined according to the cumulative number of times.
The electronic device according to claim 17, wherein when determining the user's preference for the scene according to the cumulative number of times, the processor is configured to:

Obtaining a preset preference degree according to the cumulative number of times and a third preset correspondence relationship, where the third preset correspondence relationship includes a correspondence relationship between the cumulative number of times and the preset preference degree;

The preset preference is determined as the user's preference for the scene.
The electronic device according to claim 13, wherein, when acquiring the user's preference for the scene according to the historical track information of the user in the scene, the processor is configured to:

Acquiring, according to the historical track information, the accumulated time that the user appears in the scene;

Determine the user's preference for the scene according to the accumulated time.
The electronic device according to claim 13, wherein, when acquiring the behavior habit information of the user in the scene according to the historical behavior information of the user in the scene, the processor is configured to:

Determine multiple historical behaviors of the user in the scene according to the historical behavior information;

Get the number of occurrences of each historical behavior;

Establish user behavior habit information in the scene according to the multiple historical behaviors and the corresponding times of each of the historical behaviors.