KR102073696B1 - User terminal apparatus and user activity prediction method - Google Patents

Abstract

Initiate a user terminal. The user terminal according to an embodiment of the present invention, a user activity collection unit for collecting user activity, a location information detection unit for detecting the location information of the user terminal when the user activity is collected, the collected user activity and the A place of interest candidate determination unit that selects a place of interest based on the detected location information of the user terminal, and at least one user intention of the selected place of interest candidate based on previously stored user activity information; It includes a user intention analysis unit to analyze.

Description

User terminal and user activity prediction method {USER TERMINAL APPARATUS AND USER ACTIVITY PREDICTION METHOD}

The present invention relates to a location-based service, and more particularly, to a user terminal and a user activity prediction method for determining a user's place of interest and predicting a user's intention to visit the place of interest.

Location-based service refers to a service system that provides various services to a user based on location information obtained through a mobile communication network or a satellite navigation system (GPS). It is a technology that provides various information related to location, such as location tracking service, public safety service, location-based information service, by attaching a chip connected to a base station or a satellite navigation device (GPS) in a mobile phone.

Location-based services include a cell type using a mobile communication base station and a GPS method using a satellite navigation system. The cell system began to be developed and distributed around 2000. The location error range can be up to several kilometers, so it is difficult to find the exact location. It is an advantage. The GPS method is a method in which the chip embedded in the mobile phone reads the location information sent from the satellite and informs the base station. Since the error range of the position is narrow, the position can be known relatively accurately. However, due to the characteristics of satellite signals, it is difficult to use in high-rise buildings or indoors where reflection and refraction are good. In addition, location-based services using short-range communication technologies such as Wi-Fi are also emerging. These location-based services are implemented by various services such as weather service, traffic information service, life information service, and telematics service.

Recently, a technology for extracting information on a place of interest of a user based on location information and providing a personalized service based on the information has emerged. However, the technologies developed to date have a problem that requires the active action of the user to provide the place of interest information in order to collect the place of interest information. For example, when a user visits a favorite restaurant, the user provides information of a place of interest by performing an input (usually called a check-in) indicating that the user has visited the restaurant. . This behavior makes the user feel cumbersome, and in turn, lowers the frequency of service use, making it difficult for the user to make accurate predictions.

Also, in general, the location information detection function provided by the mobile device is not so precise that it is difficult to identify each store from a place where several stores are gathered. Thus, one place may include several points, so the intention of the user to visit a place may have a number of cases. For example, a user who visits an amusement park may want to eat, but may want to purchase a souvenir. In the existing service, in this case, the user has to inconvenience inputting his destination or intention directly through active input.

The present invention has been made to solve the above-described problems, an object of the present invention is to analyze the user's intention by judging the user's place of interest only by the user's daily use of the user terminal without active action of the user to provide the place of interest information To provide a user terminal and a user activity prediction method that can be.

A user terminal according to an embodiment of the present invention for achieving the above object, the user activity collection unit for collecting user activity, and the location information detection unit for detecting the location information of the user terminal when the user activity is collected; A place of interest candidate determiner configured to select a place of interest based on the collected user activity and the detected location information of the user terminal, and the selected place of interest candidate based on previously stored user activity information; It includes a user intention analysis unit for analyzing at least one user intention for.

In this case, the user activity may be a user input for executing a specific function of the user terminal, and may be at least one of camera shooting, video playback, music playback, application execution for a specific purpose, and function setting of the user terminal.

The interest information candidate determiner generates user activity information based on the collected user activity and the detected location information of the user terminal, and selects a place of interest based on the generated user activity information. can do.

In this case, the generated user activity information may include an ID, a timestamp, a title, an application package name, an event, a type, a duration, It may include at least one of metadata, latitude, longitude, address, and location source.

The interested place candidate determiner may determine the interested place candidate based on a home or an office.

In addition, the place of interest candidate may include at least one point.

In addition, the user intention analyzer may analyze at least one user intention of the selected place of interest candidate by further considering a location-knowledge service received from an external device.

The user intention analyzer may analyze a plurality of user intentions with respect to the selected place of interest candidate, and the analyzed plurality of user intentions may have different weights.

The user terminal may further include a user activity predictor that predicts an activity of the user based on at least one of a current time and location information of the user terminal.

In this case, the user activity predictor may predict the activity of the user based on the current time and the current location information of the user terminal when the user activity requiring prediction is a type of activity that occurs after a short time.

In accordance with an aspect of the present invention, there is provided a method of predicting user activity, the method comprising: collecting user activity, detecting location information of the user terminal when the user activity is collected, and collecting the user activity Selecting a place of interest based on an activity and location information of the detected user terminal; analyzing at least one user intention of the selected place of interest candidate based on previously stored user activity information; Steps.

In this case, the user activity may be a user input for executing a specific function of the user terminal, and may be at least one of camera shooting, video playback, music playback, application execution for a specific purpose, and function setting of the user terminal.

The selecting of the interest information candidate may generate user activity information based on the collected user activity and the detected location information of the user terminal, and place a place of interest candidate based on the generated user activity information. of Interest).

In this case, the generated user activity information may include an ID, a timestamp, a title, an application package name, an event, a type, a duration, It may include at least one of metadata, latitude, longitude, address, and location source.

The selecting of the interest information candidate may include determining the interested place candidate based on a home or an office.

In addition, the place of interest candidate may include at least one point.

The analyzing of the user intention may further analyze at least one user intention of the selected place of interest candidate by further considering a location-knowledge service received from an external device.

The analyzing of the user intention may include analyzing a plurality of user intentions with respect to the selected place of interest candidate, and the analyzed plurality of user intentions may have different weights.

The user activity predicting method may further include predicting user activity based on at least one of a current time and location information of the user terminal.

In this case, the estimating of the user activity may include predicting the activity of the user based on a current time and current location information of the user terminal when the user activity requiring prediction is a type of activity that occurs after a short time.

According to various embodiments of the present disclosure as described above, the present invention may analyze a user's intention by determining a user's point of interest without using the user's daily user terminal without active action of providing the user's place of interest information. It is possible to provide a personalized service based on the user intention.

1 is a diagram illustrating a user's movement trajectory on a map;
2 is a block diagram showing the configuration of a user terminal according to an embodiment of the present invention;
3 is a diagram showing an item of user activity information;
4 is a flowchart of an algorithm for detecting a home and an office;
5 illustrates a place of interest candidate composed of at least one point;
6 is a schematic diagram illustrating a process of determining user intention in consideration of additional information;
7 is a diagram illustrating user intention including weights;
8 is a conceptual diagram illustrating a plurality of user intentions having different weights included in one place of interest;
9 is a schematic diagram showing a user prediction situation at some point in the future;
10 is a graph showing strength and weakness of user intention, and
11 and 12 are flowcharts of a user activity prediction method according to various embodiments of the present disclosure.

Hereinafter, various embodiments of the present disclosure will be described with reference to the accompanying drawings.

1 is a diagram illustrating a user's movement trajectory on a map, and FIG. 2 is a block diagram illustrating a configuration of a user terminal 100 according to an exemplary embodiment.

The location-based service using the life log according to the present invention provides a service by determining a user's location to determine a user's intention for a specific location. The service determines the intention of the user visiting a specific location by using geographic information corresponding to the location information of the user terminal 100 possessed by the user.

1 is a diagram illustrating a user's movement trajectory on a map. In the example of FIG. 1, if the user is at home 1 the user will have breakfast, sleep or watch TV. Then, when the user visits the office 2, the user's intention can be regarded as for working or meeting. And in everyday life, it is obvious that the user will rest at home and sleep after a certain time after finishing work. Also, except at mealtimes and weekends, users are very likely to work or meet in the office. In other words, the time the user is at home or in the office and the user's intention at that time is relatively obvious.

On the other hand, other times and places that users visit at that time are relatively variable. For example, a user may have a lunch at a Japanese restaurant located 50 meters east of the office, but may stop by a snack bar 100 meters south of the office, or find a gym located in the other direction. Thus, location-based services using lifelogs focus on predicting a user's intention when visiting a place other than a place where the user's intention is relatively apparent, such as a home or an office. That is, when a user visits a place that is not typical, the user's intention is analyzed by analyzing information about the place and time. The analyzed intent is used to precisely predict the user's behavior patterns in similar conditions in the future. Through these predictions, it is intended to provide customized mobile services to users with relatively high accuracy. As such, a place considered to be visited by a user with a specific intention is defined as a place of interest (POI).

Hereinafter, the configuration and function of the user terminal 100 for realizing the above-described service will be described.

Referring to FIG. 2, the user terminal 100 according to an exemplary embodiment of the present invention for performing the above-described function includes a user activity collector 110, a location information detector 120, and a place of interest candidate determiner 130. , The user intention analyzer 140.

The user activity collector 110 is a component for collecting user activity. User activity means that a user actively operates a specific function of the user terminal 100. For example, when a user executes an SNS application or a game control input by executing a game application, the user terminal 100 may be operated by photographing a camera or playing a video or music. have. User activities encompass not only the case of activating a specific function or application, but also the case where user input is performed in a situation in which a specific function or application is activated. That is, the user inputs a user touch input, drag input, pinch out / in input, keypad input, movement input of the user terminal 100, proximity input, hovering input, and button input while a specific function or application is activated. Includes performing at least one.

The present invention can analyze the user's intention by determining the user's place of interest with only the user's daily use of the user terminal without the active action of the user to provide the place of interest information as described above.

The location information detector 120 detects the location of the user terminal 100. The location information detector 120 detects location information of the user terminal 100 using at least one of a global positioning system (GPS) technology, a cell communication technology, and a short range communication technology such as Wi-Fi. The location information detector 120 may continuously detect the location of the user terminal 100, but may detect the location of the user terminal 100 only when there is user activity. In the latter case, since the battery consumption of the user terminal 100 can be reduced, a power saving effect can be expected, and since the frequency of being performed simultaneously with other tasks is relatively small, the system load of the user terminal 100 can be prevented to maintain stable performance. .

3 is a diagram illustrating items of user activity information.

As a result of the user activity collecting unit 110 collecting user activity and the location information detecting unit 120 detects the location information when the user activity is collected, the user activity information is generated as shown in FIG. Can be stored in That is, when there is a user activity 30 as shown in FIG. 3, user activity information 31 for each user activity 30 is stored. The user activity information 31 has a plurality of items as shown in FIG. The user activity information 31 may be stored in various data types including text data. In addition, the user activity information 31 may be stored in the user terminal 100 or the service providing server.

Each item is explained as follows. ID is an item indicating information for identifying the user terminal 100, a timestamp is an item indicating time information with user activity, and a title is an item indicating a title of user activity. . In addition, a package name is an item representing a package name of an application used to perform a user activity, an event is an item representing an installed, deleted, or updated activity, and a type is a content or an application. The item indicates the type of, the duration is the item indicating the time when the user activity is continuously performed, the meta data (Meta) is the item indicating the information related to the user activity, latitude, longitude ), An address is an item representing a GPS value and a geo-hash code, and a location source is an item representing a means for detecting location information. Can be one.

On the other hand, when the amount of data of the user activity information 31 is large, there is a possibility that a data processing speed delay occurs. In this case, it is also possible to store only the essential user activity information 32. When data processing is performed in the user terminal 100 and user activity information is stored in the user terminal 100, only essential user activity information 32 may be stored to ensure performance of the user terminal 100. However, the more the user activity information 31, the higher the accuracy of the prediction of the user's intention, so which of the user activity information 31 and the required user activity information 32 is traded off between the efficiency and accuracy of the prediction. (trade-off)

The interested place candidate determiner 130 is configured to determine a POI candidate of the user based on the user activity information generated as described above.

The above-described user activity information 31, 32 is primarily a place of interest candidate. Next, the interested place candidate determining unit 130 determines whether the user's intention is relatively obvious, such as a home or an office. The period of minimum user activity due to the user sleeping is not the object of interest determination, so the above judgment must be made for other times. 4 shows a flow diagram of an algorithm that excludes a place where a user's intention is relatively clear and time without significant user activity in accordance with this policy. In the above-described embodiment, since the user's home or office is a place where the intention of the user is relatively obvious, the place of interest is set at other places.

4 shows a flow diagram of a simple algorithm for detecting a home and an office. The algorithm considers a set of user activities (S410). In addition, the section having the least user activity is identified through the time counter TC (S420). The section is regarded as a section located at home or office. Weekends will be mainly at home or office, so consider the time of the week (S430). In addition, day workers and night workers may be distinguished (S425). The time spent at home or in the office is excluded because it is a clear section that does not require analysis of user intention or user activity prediction (S435). Then, the candidates and the office candidates are selected by calculating a user activity or a required date with a low-precision geohash function (S447 to S457). Finally, labels are set for homes or offices (S470, S475, S480).

However, in reality, the location information detector 120 has a limit in detecting the exact location of the user terminal 100. In particular, when a plurality of destinations having different personalities are gathered, such as when multiple shops are gathered in a nearby place, it may be difficult for a user to determine where the actual destination is visited. For example, when different destinations are located on different floors in one building, the GPS module may have a limit in detecting the exact location of the user terminal 100. Thus, typically one point of interest candidate may include at least one destination (generally a plurality of destinations). In this specification, the term Venue is used to distinguish the destination from the place of interest.

FIG. 5 illustrates a place of interest candidate composed of at least one point. FIG.

Referring to FIG. 5, the life log is moved from the place of interest candidate 1 (POI 1) to the office on the first day of recording, and the place of interest candidate 1 (POI 1) is GPS, and the location information is detected and one point It includes recording. On the other hand, on the second day, the user moves to POI 2, and POI 2 may detect that Wi-Fi location information is detected and includes two points. Similarly, place of interest candidate 3 (POI 3) contains three points, place of interest candidate 4 (POI 4) contains six points, and place of interest candidate 5 (POI 5) contains two points. Able to know.

The user intention analyzer 140 is a component that analyzes the intention of the user in order to update the user intention database. The user intention analyzer 140 may consider additional information to accurately determine the user intention. The additional information is information other than the user activity information 31 collected from the user activity and means information useful for determining the intention of the user.

For example, distance information from a home or office, check-in information for a specific point, user review or comment information, place property information such as a price for a restaurant, rating information, category information categorizing the nature of the branch, It may be at least one of weather information, time information, and purchase information. In particular, the point of interest may be matched to a category classified according to a preset manner. For example, when the user visited the restaurant according to the user activity information 31, the food category may be matched with the food category.

Such additional information may be included in a location-knowledge service provided from an external device. The user intention analyzer 140 determines the user intention more precisely in consideration of the additional information. There may be multiple user intents for one point of interest.

6 is a schematic diagram illustrating a process of determining user intention in consideration of additional information.

As shown in FIG. 6, when user activity is collected at a certain location (S610), a place of interest candidate is determined (S620). The user's intention is analyzed using the provided additional information (S630). The analyzed user intent can be used for the purpose of updating the database 60.

However, there may be a plurality of similar user intentions that vary in frequency of occurrence under the same conditions. In this case, each of the plurality of similar user intentions may be given a different weight. 7 is a diagram illustrating such a situation. That is, FIG. 7 is a diagram illustrating a user intention including weights.

The graph of FIG. 7 shows that the user's intention is analyzed when the user is at a place outside the home or office (place of interest). The analysis is done weekly. In the graph shown in Fig. 7, M represents Monday, T represents Tuesday, W represents Wednesday, T represents Thursday, F represents Friday, and subsequent S represents Saturday and Sunday.

When the user was at the place of interest on Saturday S, the user intention ik is indicated by the weight of the play FUN as 0.87 and the weight of the meal FOOD as 0.11. Therefore, the user may know that there are more doctors in FUN than meals in Everland Resort, which is the same place of interest. According to the user intention database 70 thus stored, the user's activity will be predicted as play in the same or similar conditions in the future.

In addition, as described above, since there may be a plurality of user intentions for one place, one place of interest may have a plurality of user intentions having different weights. FIG. 8 is a schematic diagram showing a plurality of user intentions 81, 82, and 83 having different weights included in one place of interest 80.

When the user intention database is created according to the method described so far, the user intention database generated in this way is used to predict the activity of the user. That is, the user terminal 100 provides the information of the predicted future user activity using the database. The database may be stored in an external server for reference by the user terminal 100, or the user terminal 100 may store the database itself.

When the user terminal 100 constructs and manages a database by itself, the aforementioned storage unit 150 stores the database. There is no limit to the type of database. That is, it may be one of a hierarchical database (HDB), a relational database (RDB), and an object-oriented database (OODB). If an external server is constructing a database, it may be implemented as a network type database (NDB) in addition to the above type of database.

Meanwhile, the user terminal 100 according to another embodiment of the present invention may perform a function of predicting user activity at a future time point. That is, the user terminal 100 further includes a user activity predictor (not shown) that predicts an activity of the user based on at least one of a current time and location information of the user terminal 100 with reference to the constructed database. can do.

That is, the user activity predictor may predict the user activity on a time basis or on the basis of a place where the user terminal 100 is located. Or consider both time and place. For example, if a life log was recorded on a weekly basis to build a user intention database, user activity for a particular time of next Tuesday may be predicted.

In a basic embodiment, time may be taken into account for prediction of user activity. 9 is a schematic diagram showing a user prediction situation for a certain time in the future. If any case 90 exists at a future point in time, the user intent is classified accordingly, with each user intent 91, 92 being weighted.

The weight indicates the degree of user intention. Therefore, if a place of interest has a plurality of user intentions, and the weight deviation between each user intention is large, the user intention for that place of interest becomes relatively clear. In this case, the place of interest is expressed as having strong user intention. On the other hand, when a place of interest has a plurality of user intentions and the weight deviation between each user intention is small, it is determined that the place of interest has a weak user intention.

10 shows a graph showing strength and weakness of user intent. As a result of recording user activity in the left graph of FIG. 10, strong user intention was analyzed at the fourth place of interest. The graph on the right shows a graph that predicts future user activity. Since a point of interest with a strong user intention is to be able to predict the user intention relatively accurately, the prediction accuracy of the user activity is also increased.

However, there is a case where the estimated time varies depending on the nature of user activity. For example, meals are generally a user's behavior after a short time, while travel or tracking is a user's behavior that can occur after a long time. According to the nature of the user activity, the user intention can be classified into short-term intention, medium-term intention, and long-term intention.

In the case of short-term intention, since the user's activity occurring after a short time passes from the current point in time, it is performed in consideration of the current location information of the user. Even if a user frequently used a restaurant that is very far from the current location in the past, they would want to eat one hour after the current time at the restaurant close to the current location. On the other hand, in the case of medium-term or long-term intention, the user's current location information is not considered because the user's activity that occurs after a long time from the current time point must be predicted. For example, a user will typically plan a trip well before the trip, and the closer to the travel date, the user will not modify the destination again in consideration of the origin.

The configuration and function of the user terminal 100 according to various embodiments of the present disclosure have been described above. The user terminal 100 described above may be implemented by various mobile devices. For example, it can be implemented with at least one of a smart phone, a tablet PC, a smart watch, a PMP, an MP3 player, a PDA, a cell phone, a laptop computer, and other mobile terminal devices.

In addition, the user terminal includes a configuration that a general electronic computing device has. That is, various wired / wireless communication modules including CPU, cache memory, RAM memory, large capacity auxiliary storage device such as hard disk or Blu-ray disk, input / output device such as touch screen, near field communication module, HDMI having sufficient control and arithmetic capability, It includes a hardware configuration such as a data bus, and includes an application, a framework, and an operating system capable of performing the functions of the above-described user activity collecting unit, location information detecting unit, point of interest candidate breaking unit, user intention analyzing unit, and user activity predicting unit. .

In addition, the configuration and operation of the user terminal 100 described above may be performed in a system consisting of a user terminal (not shown) and a server (not shown). In this case, the functions of the above-described components may be shared by the user terminal (not shown) and the server (not shown), and may be connected to each other by various communication means to transmit and receive data.

Hereinafter, a method of predicting user activity according to various embodiments of the present disclosure will be described.

11 and 12 are flowcharts of a user activity prediction method according to various embodiments of the present disclosure.

Referring to FIG. 11, in the method of predicting user activity according to an embodiment of the present disclosure, collecting user activity (S1110), detecting user location information when the user activity is collected (S1120), Selecting a place of interest candidate based on the collected user activity and the detected location information of the user terminal (S1130), based on previously stored user activity information, at least the selected place of interest candidate; Analyzing one user intention (S1140).

In this case, the user activity may be a user input for executing a specific function of the user terminal, and may be at least one of camera shooting, video playback, music playback, application execution for a specific purpose, and function setting of the user terminal.

The selecting of the interest information candidate may generate user activity information based on the collected user activity and the detected location information of the user terminal, and place a place of interest candidate based on the generated user activity information. of Interest).

In this case, the generated user activity information may include an ID, a timestamp, a title, an application package name, an event, a type, a duration, It may include at least one of metadata, latitude, longitude, address, and location source.

The selecting of the interest information candidate may include determining the interested place candidate based on a home or an office.

In addition, the place of interest candidate may include at least one point.

The analyzing of the user intention may further analyze at least one user intention of the selected place of interest candidate by further considering a location-knowledge service received from an external device.

The analyzing of the user intention may include analyzing a plurality of user intentions with respect to the selected place of interest candidate, and the analyzed plurality of user intentions may have different weights.

Referring to FIG. 12, in the method of predicting user activity according to another exemplary embodiment of the present disclosure, collecting user activity (S1210), detecting location information of the user terminal (S1220), and a place of interest candidate (Place of) Selecting Interest (S1230), analyzing at least one user intention for the selected interest place candidate based on previously stored user activity information (S1240), the current time and the location of the user terminal Predicting user activity based on at least one of the information (S1250). At this time, S1210 to S1240 correspond to the above-described steps S1110 to S1140.

At this time, the step of predicting the user activity (S1250), when the user activity that needs to be predicted is a type of activity that occurs after a short time, to predict the activity of the user based on the current time and the current location information of the user terminal Can be.

Meanwhile, the above-described user activity prediction method may be stored in the form of a program in a non-transitory recording medium readable on a computer. Here, the non-transitory readable medium refers to a medium that can store data semi-permanently and can be read by an electronic device, not a medium that stores data for a short time such as a register or a cache. For example, it may be a CD, a DVD, a hard disk, a Blu-ray disk, a USB, a memory card, a ROM, or the like.

In addition, the above-described user activity prediction method may be provided embedded in a hardware IC chip in the form of embedded software, may be included in the configuration of the user terminal 100 described above, or may be included in the configuration of a system consisting of a user terminal and a server. .

Although the above has been shown and described with respect to preferred embodiments of the present invention, the present invention is not limited to the specific embodiments described above, it is usually in the art to which the invention belongs without departing from the spirit of the invention claimed in the claims. Various modifications can be made by those skilled in the art, and these modifications should not be individually understood from the technical spirit or prospect of the present invention.

100: user terminal
110: user activity collection unit 120: location information detection unit
130: interest place candidate determination unit 140: user intention analysis unit
150: storage unit

Claims (20)

In the user terminal,
A user activity collecting unit collecting user activity;
A location information detector for detecting location information of the user terminal when the user activity is collected;
A place of interest candidate determiner configured to select a place of interest based on the collected user activity and the detected location information of the user terminal; And
And a user intention analyzer configured to analyze user intention of the selected candidate for interest place based on previously stored user activity information.
The user intention analysis unit,
Analyze a plurality of user intentions for the selected places of interest candidates,
The analyzed plurality of user intentions each have a different weight. The method of claim 1,
The user activity is a user input for executing a specific function of the user terminal, the user terminal characterized in that at least one of the camera shooting, video playback, music playback, application execution of a specific purpose and the function setting of the user terminal. . The method of claim 1,
The interested place candidate determination unit,
The user terminal may be configured to generate user activity information based on the collected user activity and the detected location information of the user terminal, and select a place of interest based on the generated user activity information. . The method of claim 3,
The generated user activity information is
ID, Timestamp, Title, Application Package Name, Event, Type, Duration, Meta, Latitude And at least one of a longitude, an address, and a location source. The method of claim 1,
The interested place candidate determination unit,
The user terminal, characterized in that for determining the candidate for the place of interest based on the home or office. The method of claim 1,
The place of interest candidate is a user terminal, characterized in that it comprises at least one point (Venue). The method of claim 1,
The user intention analysis unit, the user terminal characterized in that for analyzing the user intention for the selected place of interest candidate further considering the location-knowledge service received from the external device. delete The method of claim 1,
And a user activity predictor for predicting an activity of a user based on at least one of a current time and location information of the user terminal. The method of claim 9,
The user activity prediction unit,
If the user activity that requires prediction is a type of activity that occurs after a short time, the user terminal, wherein the activity of the user is predicted based on the current time and current location information of the user terminal. In the user activity prediction method of the user terminal,
Collecting user activity;
Detecting location information of the user terminal when the user activity is collected;
Selecting a place of interest based on the collected user activity and the detected location information of the user terminal; And
Analyzing a user's intention of the selected place of interest candidate based on previously stored user activity information;
Analyzing the user intention,
Analyze a plurality of user intentions for the selected places of interest candidates,
And analyzing the plurality of user intentions having different weights. The method of claim 11,
The user activity may be a user input for executing a specific function of the user terminal, and the user activity may include at least one of camera shooting, video playback, music playback, application execution for a specific purpose, and function setting of the user terminal. Forecast method. The method of claim 11,
The selecting a place of interest candidate may include:
User activity information is generated based on the collected user activity and the detected location information of the user terminal, and a place of interest is selected based on the generated user activity information. Forecast method. The method of claim 13,
The generated user activity information is
ID, Timestamp, Title, Application Package Name, Event, Type, Duration, Meta, Latitude And at least one of a longitude, an address, and a location source. The method of claim 11,
The selecting a place of interest candidate may include:
And determining the candidate for the place of interest based on a home or an office. The method of claim 11,
The place of interest candidate comprises at least one point (Venue). The method of claim 11,
Analyzing the user intention,
And analyzing a user's intention of the selected candidate for the place of interest by further considering a location-knowledge service received from an external device. delete The method of claim 11,
Predicting user activity based on at least one of a current time and location information of the user terminal. The method of claim 19,
Predicting the user activity,
If the user activity that requires prediction is a type of activity that occurs after a short time, the user activity prediction method according to the current time and the current location information of the user terminal.

Images