JP2021110756A - Device and method for recommending information to user while navigation is being given - Google Patents

Abstract

To provide a device and a method for recommending information to a user while a navigation is being given.SOLUTION: The device includes: a generation unit for generating personalization scene information showing an intention of a user about a current navigation on the basis of user data on the user while the current navigation is being given; and a determination unit for determining information to recommend to the user while the navigation is being given, on the basis of the personalization scene information. Selecting an information entry and outputting the entry on the basis of the personalization scene information allows a user to acquire useful information efficiently.SELECTED DRAWING: Figure 1

Description

The present invention relates to the field of navigation, and more specifically to the provision and display of information during the period of navigation.

Navigation technology has already become a popular technology in people's daily lives, and it greatly supports people's daily outings. Currently, navigation techniques can be used not only to accurately plan the route from the user's current location to the destination selected by the user, but also to assist the user's selection, for example, at the destination, around the destination or It is also possible to provide the user with additional information such as information about a place of interest along the way.

However, in general, conventional navigation devices and navigation software display these additional information to each user who is searching for the destination under arbitrary conditions without individual difference, and the user's historical data. In some cases, different information can be recommended for each user. For example, the purpose of navigating the reserved performance facility by reading the meal preference entered by the user, for example, in social software and recommending a different restaurant for each user, or reading the performance information reserved by the user, for example, on a ticket sales site. It can be recommended to users as a place. Some of this information may not match the user's true intentions regarding current navigation. For example, a user who likes Chinese food may try Western food at any time.

Therefore, it is desired to provide further improved navigation.

The present invention determines, for each user, the intent to initiate the current navigation, and personally recommends information that is closely related to the user's intent regarding the current navigation, thereby making the information useful to the user or the user more. Provide a device and a method for recommending information to a user during a navigation period, which can provide the user with information of interest.

According to one aspect of the present invention, there is provided a device for recommending information to a user during a navigation period. The device includes a generation unit for generating personalized scene information indicating the user's intention regarding the current navigation and the personalized scene information based on the user data about the user during the current navigation period. Based on this, it comprises a decision unit for determining information to be recommended to the user during the current navigation period.

Also, according to another aspect of the invention, there is provided a method for recommending information to the user during the navigation period. The method generates personalized scene information indicating the user's intention regarding the current navigation based on user data about the user during the current navigation period, and based on the personalized scene information. Includes determining information to recommend to the user during the current navigation period.

Further, according to another aspect of the invention, there is provided a computer storage medium that stores computer-readable instructions that, when executed by a processor, cause the processor to perform the methods described in each embodiment of the invention. do.

According to each embodiment of each aspect of the present invention, by receiving user data about the user during the current navigation period, i.e., user data generated during the current navigation, for example, artificial intelligence based on a machine learning algorithm. Can generate personalized scene information that can indicate the user's intention to initiate the current navigation. Personalized scene information is related to specific scenes related to the activity that the user intends to perform through the current navigation or the event that the user intends to participate in, such as outdoor play, going out / dinner, participation in parent-child activities, visit to the exhibition, etc. , Can reflect or indicate the user's intention to initiate the current navigation. Based on such personalized scene information, the information recommended to the user can be closely associated with the user's true intentions during the current navigation period. That is, the information output to the user is not the same static information for different users or the same static information for different navigation operations of the same user, but a dynamic personalized for each different navigation of each user. Since it is information, the user can receive the maximum benefit from the acquired information.

One of ordinary skill in the art can recognize other advantages of the present invention after reading and understanding the detailed description below.

A block diagram of a device for recommending information to a user during a navigation period according to an embodiment of the present invention is shown. A flowchart of a method for recommending information to a user during a navigation period according to an embodiment of the present invention is shown.

FIG. 1 shows a block diagram of a device 100 for recommending information to a user during a navigation period according to an embodiment of the present invention.

The device 100 includes a generation unit 101 for generating personalized scene information based on user data 10 about the user during the current navigation period, and the personalized scene information indicates the user's intention regarding the current navigation. show. Personalized scene information can indicate the user's intent regarding the current navigation, the scene information at any point in the current navigation process and / or the activity or event the user intends to perform through the current navigation. Can include scene information representing. It is understood that the scene information of the activity that the user intends to perform or the event that the user intends to participate in can be derived based on the scene information at any time in the current navigation process. The scene information at any point in the current navigation process is related to the current navigation, for example, when two adults and one child, one man and one woman, are having fun chatting in the car. Since it is assumed that the user's intention is a parent-child activity, it can be determined that the scene information to be performed or participated in from now on represents a parent-child activity scene.

The user data 10 about the user during the current navigation period should be understood with respect to the user's historical data and is different from the historical data generated or uploaded by the user prior to the current navigation. It is understood that a user can include not only the person who operates the navigation device or the person who drives the vehicle, but also all the people who are currently participating in the outing, for example, all the people who are in the vehicle. Will be done.

In one embodiment, the user data 10 includes user state data representing the state of the user during the current navigation period. The user state data may include user profile data and / or user behavior data.

User profile data is basic data of users participating in the current navigation, such as the number of users participating in the navigation for going out, each user's age group, gender, appearance and / or current preference. including. The user profile data can be acquired from, for example, real-time sensing data. The real-time sensing data is, for example, image data and / or audio data acquired by the sensor. The sensor can include an image acquisition device such as a camera that can acquire user image data including not only still image data but also moving image data. Further, the sensor can include a voice acquisition device such as a microphone capable of acquiring the user's voice data. In addition, the number of users, the gender of each user, the approximate age group, the appearance and / or the current preference can be derived from the user's image data and / or audio data. For the user profile data, perform image processing such as image division and template matching on the acquired image data, or perform voice processing such as voice recognition and semantic analysis on the acquired voice data. Obtained by. For example, from the image data, it is possible to determine information such as the number of users, whether each user is an adult or a child, the gender of each user, and whether the user is currently wearing work clothes or everyday clothes. .. Also, the voice data can be used to analyze the current user's preferences, for example, the user may have clearly stated his intention to go out to eat Western food during the conversation.

The user behavior data can indicate the behavior of the user participating in the current navigation, including the user's current facial expression, voice tone, etc., for example, whether the user's current facial expression is clear or severe, the user. It can show whether the current voice tone of is fun or heavy. Similarly, for the user behavior data, image processing such as image division and template matching is executed on the acquired image data, or voice processing such as voice recognition and semantic analysis is executed on the acquired voice data. Obtained by

The generation unit 102 can generate personalized scene information based on user state data including user profile data and / or user behavior data, for example, using a model trained by a machine learning algorithm.

For example, based on user status data showing that adults and children are present in the car at the same time, everyone is wearing everyday clothes, and the facial expressions are clear, the user's intention regarding current navigation is to go out to parent-child activities. It can be decided that there is. In addition, it can be determined that the user's intention regarding the current navigation is shopping based on the user state data indicating that there are a plurality of female friends in the car and the user looks fashionable. In addition, based on the user status data indicating that there are a plurality of male friends in the car and wearing sportswear, it can be determined that the user's intention regarding the current navigation is to go out to sports.

In one embodiment, the user data 10 may include destination data for the user's current navigation destination. The destination data can be directly input by the user, and may be, for example, a specific place such as an old palace, or a general term for a certain place such as a park or a restaurant. The generation unit 101 can generate personalized scene information indicating the intention regarding the current navigation, based on the destination data, for example, together with the user's history data. For example, if the user enters the National Palace Museum as a destination and the historical data determines that he likes to see the old coins exhibition, an individual indicating that the user wants to go to the National Palace Museum to see the old coins exhibition. It is possible to generate the changed scene information. If such an exhibition is held in the Forbidden City, related information can be pushed to the user.

Although the above-mentioned example has been given, the present invention is not limited to this, and in some cases, different types of user data 10 may be selected to determine personalized scene information. Also, different weights can be assigned to these different types of user data to determine personalized scene information, for example, higher weight values can be assigned to data determined to indicate the user's current preferences. ..

In addition, the generation unit 101 can generate personalized scene information together with the user's history data 11 based on the user data 10.

For example, information such as age, gender, occupation, and hobbies of each user can be directly extracted from each user's social software, and personalized scene information indicating the user's intention is shown together with the user data 10 sensed in real time. Can be determined more accurately. For example, if the current user data 10 indicates that everyone is currently wearing sportswear, and the historical data of all people shows that their hobbies are all basketball, then the current user data 10 is present. The user's intention regarding navigation can be more accurately determined to be playing basketball.

It is understood that sensors such as cameras, microphones and the like can be included in the device 100 so as to form part of the device 100. Alternatively, these sensors may be separate from the device 100, such as an in-vehicle sensor or a sensor integrated into a mobile device.

The device 100 includes a determination unit 102 for determining information to be recommended to the user during the current navigation period based on the personalized scene information.

In one embodiment, the recommended information includes information about the current navigation destination, which is determined based on the user's personalized scene information.

Information about the current navigation destination may include attributes of the navigation destination recommended based on the user's personalized scene information. For example, if the navigation destination is a historical spot, the user's personalized scene information is determined to indicate that the user is interested in history and the intent is to understand the history of the spot. Navigation destination attributes may include an introduction to the history of the spot. Also, if the navigation destination is a shopping center, it is determined that the user's intention is to purchase children's clothing, and the recommended navigation destination attribute is to sell the children's clothing in the shopping center. It may be information on the store you are in.

The information about the navigation destination may further include the commercial service index of the navigation destination recommended based on the user's personalized scene information. For example, in the case of a specific shopping center, the status of each shopping center nearby (for example, in the same city) is integrated, and the food and drink index (ranking), shopping index (ranking), and entertainment index (ranking) for the specific shopping center are integrated. Etc. can be presented. In the case of a spot or park, the leisure index, parent-child index, sports index, etc. can be presented. For example, if it is determined that the user's intention is a parent-child activity, a parent-child index can be presented.

Further, the information regarding the navigation destination may further include an event occurring at the navigation destination recommended based on the user's personalized scene information. It is understood that temporary events are common at navigation destinations. For example, in the case of navigation destinations such as museums and exhibition halls, different time zones may correspond to different exhibitions. Shopping centers may hold promotional activities such as limited time sales. For example, as described above, if the user's personalized scene information indicates that the user is viewing an exhibition of old coins, information about such an exhibition being held at a museum can be recommended to the user.

The information about the navigation destination may further include the places of interest around the navigation destination recommended based on the user's personalized scene information and information about it. For example, in the case of a commercial center, there may be multiple shopping centers in one area, and when a user searches for one of them, the other nearby shopping centers and their attributes, their commercial service index, etc. Also, one or more of the events occurring there may be included in the information to be recommended based on the user's personalized scene information.

The decision unit 102 may recommend one or more of the above information for different situations, based on personalized scene information indicating the user's intent with respect to the current navigation. For example, when the destination of the navigation is a shopping center, the determination unit 102 should recommend restaurants and food index related to Western food in the shopping center based on the intention of the user to go out to eat Western food. In addition to being able to make decisions, it is possible to recommend restaurants and food and beverage indexes related to other Western foods located around the shopping center. When the destination of the navigation is a spot, the determination unit 102 can determine the leisure index and the parent-child index of the spot as information to be recommended based on the intention of reflecting the parent-child trip. Alternatively, if the navigation destination is only the name of one road, the decision unit 102 determines the location of the library around the navigation destination and its opening time, with the intention of reflecting the desire to go to study. Can be determined as information to be recommended.

This prevents the user from being flooded with unnecessary information about a large number of destinations. For example, when a user wants to go to a shopping center for dinner, various sales promotion information, shopping store information, parent-child activity information, etc. regarding the shopping center are not recommended to the user.

In one embodiment, the recommended information includes information about the user's current location. The current position of the user can be acquired by, for example, GPS (Global Positioning System).

For example, users usually don't want to miss the scenery or entertainment events along the way, when they're out and about, especially on a drive trip. Therefore, the information about the user's current position includes information about an interesting place around the user's driving current position.

Similarly, the information regarding the current position of the user is determined by the determination unit 102 based on the personalized scene information. For example, when the personalized scene information indicates the intention of an outdoor parent-child trip, a playground on the way can be recommended to the user. If the personalized scene information indicates the intention of young people to participate in outdoor sports, information such as a mountain in the middle and the sports index of this mountain can be recommended to the user. Alternatively, if the personalized scene information indicates the intention of eating, a restaurant on the way can be recommended to the user.

Even if the places of interest around the current location are the same, the recommended information depends on the personalized scene information that indicates the user's current intent. For example, for the same spot, if the personalized scene information reveals that the user is elderly and their current intent is an understanding of history, then recommending information about, for example, war ruins at this spot, while If the personalized scene information reveals that the user is a young person and his current intention is tourism, he recommends information about the natural landscape at this spot.

In one embodiment, the device 100 further comprises an output unit 103. For example, the output unit 103 may include a screen display or a speaker. The output unit 103 can output the determined recommendation information to the user at a predetermined timing.

For example, if the navigation is planned to require 4 hours to reach a certain spot, the predetermined timing can be set to the timing after 2 hours, and the information of the spot can be broadcast to the user during the operation. As a result, it is possible to make the user understand the information of interest about the spot, and it is possible to alleviate the boredom during a long trip.

Further, the determination unit 102 can determine a predetermined timing for outputting the determined recommendation information based on the user behavior data. For example, if the user behavior data indicates that the driver's behavior is silent for a long time, it can reflect that the driver feels tired or bored. In this case, the output unit 103 (for example, the voice broadcasting system of the navigation device) can broadcast information that can arouse the driver's interest, thereby alleviating the driver's feeling of fatigue or boredom. Alternatively, if the user behavior data indicates that the child is sleeping in the car, the output unit 103 disables all output functions that may interfere with the child's break, such as audio broadcasting. The user behavior data is similarly obtained from the user's image data and / or voice data.

It is understood that the output unit 103 may be included in the device 100 so as to form part of the device 100. Alternatively, the output unit 103 may be a member separate from the device 100, for example, an in-vehicle display and / or speaker, a mobile device display and / or speaker.

In one embodiment, the generation unit 101 can also generate personalized scene information indicating the intent regarding the current navigation together with the background information 12.

The background information 12 may include information that can reflect the user's current background, such as date and time information (eg, holidays) and / or weather conditions.

For example, user data 10 for users during the current navigation period indicates that parents and children are present in the car at the same time, each user is wearing a sport-friendly casual wear, and the tone of voice is enjoyable. , Background information 12 provides user data (parents, children, sportswear, voice tones are fun) and background information (holidays, fine weather) when the current date and time is a holiday and the weather is sunny. Based on this, it is possible to generate personalized scene information that reflects the user's intention to go on an outdoor parent-child trip. Similarly, if it is determined that a parent and a child are present in the car at the same time, the personalized scene information that reflects the user's intention to participate in indoor parent-child activities is generated based on the background information that the weather is cloudy. be able to. Similarly, if it is determined that parents and children are present in the car at the same time, there is no intention to go on a trip based on the background information that the time for dinner is approaching, for example, the intention to go out to eat out with the family. To estimate.

It is also expected that the corresponding recommendation information will be determined based on both the background information 12 and the personalized scene information generated by the generation unit 101 indicating the user's intention regarding the current navigation. For example, if the user's personalized scene information indicates that the user's intention is parent-child activity, but the current background information indicates that the weather is cloudy, information on indoor parent-child activity can be recommended to the user. ..

In a further embodiment, the generator 101 may generate personalized scene information indicating the current navigation intent, along with vehicle and / or traffic information (not shown). For example, if the vehicle information indicates that the vehicle is in good condition and the oil supply is sufficient, it can be inferred that the user intends to go to a spot of interest far from the current position. Further, if the traffic information indicates that the road condition to a certain spot on the way is bad, it can be presumed that the user does not intend to stop at the spot.

Preferably, the vehicle and / or traffic information can be used by the determination unit 102 to determine information to recommend to the user. For example, when the personalized scene information determined by the generation unit 101 indicates that the user's intention regarding the current navigation is a parent-child activity, the determination unit 102 predetermines the recommendation information based on the personalized scene information. Later, based on the vehicle and / or traffic information, the recommendation information to be finally shown to the user can be determined.

It is understood that one or more of the embodiments described above can be combined. For example, personalized scene information may be generated based on any combination of user data 10, background information 12, vehicle information, traffic information and / or history data 11, or background information, vehicle information, traffic. The information and / or historical data may be further screened after predetermining the recommendation information and used to finally determine the recommendation information to be shown to the user.

Even if one or more of the generation unit 101, the determination unit 102, and the output unit 103 described above are executed as computer-readable instructions for controlling the corresponding hardware device stored in a computer-readable medium. Those skilled in the art will understand that it is good. The functions of the above parts can be realized by the processor, and when the corresponding computer-readable instruction is executed, the function corresponding to the processor can be executed.

Although the device for recommending information to the user during the navigation period has been described above mainly with reference to the generation unit 101 and the determination unit 102, the device can usually be realized as a navigation device. Understood. Of course, the above-mentioned parts of the device may be realized as a part of the car navigation by each part in the vehicle. Alternatively, the functions of the generation unit 101 and the determination unit 102 may be realized by the cloud device.

FIG. 2 shows a flowchart showing a method 200 for recommending information to a user during a navigation period according to an embodiment of the present invention.

At 210, personalized scene information indicating the user's intent regarding the current navigation is generated based on the user data about the user during the current navigation period.

At 220, based on the personalized scene information, information to be recommended to the user during the current navigation period is determined.

At 230, the determined information is output to the user at a predetermined timing.

It is understood that according to the method of the present application, it has the same or similar embodiments as the apparatus of the present application.

The processing of the method shown in FIG. 2 can be realized by the processor executing the corresponding instruction. Instructions can be stored on any suitable computer readable medium.

Although the method of the present invention has been described above with reference to only the embodiment shown in FIG. 2, each operation included in the above embodiment is not limited, and in order to add / modify / delete the corresponding function. , Can be deleted, combined, modified, split and / or recombined as needed.

The apparatus and method of the present invention have been described above with reference to each embodiment. These embodiments may include a particular feature, structure or property, but not all embodiments necessarily include the particular feature, structure or property. Also, some embodiments may have some or all of the features described for other embodiments, or features not described for other embodiments.

Each feature in a different embodiment or example may be combined with some features included and other features excluded to accommodate a variety of different applications. The above description and drawings show an example of an embodiment. Those skilled in the art will appreciate that one or more of the described elements can be combined into one functional element. Alternatively, some elements may be divided into a plurality of functional elements. Moreover, the element of any one embodiment may be added to the other embodiment. For example, the order of the processes described herein is not limited to the forms described herein and may be changed. Also, the actions of any of the flowcharts need not be realized in the order shown, and not all actions need to be performed. Further, an operation that does not depend on another operation may be executed in parallel with the other operation. The scope of the embodiments is not limited to these specific examples. In addition, various changes are possible in the order of operations, product configurations and structural differences, whether or not they are clearly stated in the specification.

10 User data 11 History data 12 Background information 100 Device 101 Generation unit 102 Decision unit 103 Output unit

Claims (15)

A device for recommending information to users during the navigation period.
A generator for generating personalized scene information indicating the user's intent regarding the current navigation, based on user data about the user during the current navigation period.
A decision unit for determining information to be recommended to the user during the current navigation period based on the personalized scene information.
A device characterized by that. The user data includes user state data indicating the state of the user during the current navigation period.
The device according to claim 1. Based on the personalized scene information, the determination unit determines information on the current navigation destination and / or information on the current position of the user as information to be recommended to the user.
The device according to claim 1. An output unit for outputting the determined information to the user at a predetermined timing is further provided.
The device according to claim 3, wherein the device is characterized by the above. The determination unit determines the predetermined timing based on the user behavior data indicating the behavior of the user during the current navigation period.
The device according to claim 4, wherein the device is characterized by the above. The user state data includes user profile data and / or user behavior data.
The generator further
The user profile data and / or the user behavior data is generated based on the image data and / or voice data of the user acquired during the current navigation period.
Based on the user profile data and / or the user behavior data, the personalized scene information is generated by a predetermined model.
2. The apparatus according to claim 2. The generation unit further generates the personalized scene information based on the background information and / or the historical data of the user.
The device according to any one of claims 1 to 6, wherein the device is characterized by the above. A way to recommend information to users during the navigation period,
To generate personalized scene information indicating the user's intention regarding the current navigation based on the user data about the user during the current navigation period.
Based on the personalized scene information, including determining information to recommend to the user during the current navigation period.
A method characterized by that. The user data includes user state data indicating the state of the user during the current navigation period.
The method according to claim 8, wherein the method is characterized by the above. Further comprising determining, based on the personalized scene information, information about the current navigation destination and / or information about the user's current location as information to be recommended to the user.
The method according to claim 8, wherein the method is characterized by the above. Further including outputting the determined information to the user at a predetermined timing.
10. The method of claim 10. Further comprising determining the predetermined timing based on user behavior data indicating the user's behavior during the current navigation period.
11. The method of claim 11. The user state data includes user profile data and / or user behavior data.
Generating the user profile data and / or the user behavior data based on the user's image data and / or voice data acquired during the current navigation period.
Further including generating the personalized scene information by a predetermined model based on the user profile data and / or the user behavior data.
9. The method of claim 9. Further including generating the personalized scene information based on background information and / or historical data of the user.
The method according to any one of claims 8 to 13, characterized in that. A computer storage medium that stores computer-readable instructions that, when executed by a processor, cause the processor to perform the method according to any one of claims 8-14.

Images