KR102628042B1 - Device and method for recommeding contact information - Google Patents

Abstract

This disclosure relates to an artificial intelligence (AI) system and its applications that mimic the functions of the human brain, such as cognition and judgment, using machine learning algorithms such as deep learning. A device according to an embodiment includes a processor and a memory that stores instructions executable by the processor, and the processor executes the instructions to determine an identifier from context information of an application running on the device, and to determine at least one identifier related to the identifier. Recommended contacts may be searched, the priority of at least one searched recommended contact may be determined, and the at least one recommended contact may be displayed according to the priority.

Description

Method and device for recommending contact information {DEVICE AND METHOD FOR RECOMMEDING CONTACT INFORMATION}

Various embodiments relate to a method and device for recommending contact information, and more specifically, to a method and device for recommending contact information and means of contact using a user's current context information.

An artificial intelligence (AI) system is a computer system that implements human-level intelligence, and unlike existing rule-based smart systems, it is a system in which machines learn and make decisions on their own and become smarter. As artificial intelligence systems are used, the recognition rate improves and users' preferences can be more accurately understood, and existing rule-based smart systems are gradually being replaced by deep learning-based artificial intelligence systems.

Artificial intelligence technology consists of machine learning (deep learning) and element technologies using machine learning.

Machine learning is an algorithmic technology that classifies/learns the characteristics of input data on its own, and elemental technology is a technology that uses machine learning algorithms such as deep learning to mimic the functions of the human brain such as cognition and judgment, including linguistic understanding and visual It consists of technical areas such as understanding, reasoning/prediction, knowledge expression, and motion control.

The various fields where artificial intelligence technology is applied are as follows. Linguistic understanding is a technology that recognizes and applies/processes human language/characters and includes natural language processing, machine translation, conversation systems, question and answer, and voice recognition/synthesis. Visual understanding is a technology that recognizes and processes objects like human vision, and includes object recognition, object tracking, image search, person recognition, scene understanding, spatial understanding, and image improvement. Inferential prediction is a technology that judges information to make logical inferences and predictions, and includes knowledge/probability-based reasoning, optimization prediction, preference-based planning, and recommendations. Knowledge expression is a technology that automatically processes human experience information into knowledge data, and includes knowledge construction (data creation/classification) and knowledge management (data utilization). Motion control is a technology that controls the autonomous driving of vehicles and the movement of robots, and includes motion control (navigation, collision, driving), operation control (behavior control), etc.

With the development of communication technology, various functions for interacting with people are provided to user terminals, and the number of contacts for communication such as messenger, email, and SNS (Social Network Service) as well as voice calls and text messages has increased.

It is difficult to remember numerous contact information for these various types of communication channels, and for user convenience, each communication channel program provides a function to recommend contact information in various ways. However, most of the existing contact recommendation methods simply recommend contacts based on the number of calls and call duration, and as a result, the need for detailed contact recommendation according to the user's context has increased.

Various embodiments may provide a method and device for recommending contact information based on a user's context information and relationship with the user.

A device according to an embodiment includes a processor and a memory that stores instructions executable by the processor, and the processor executes the instructions to determine an identifier from context information of an application running on the device, and to determine at least one identifier related to the identifier. Recommended contacts may be searched, the priority of at least one searched recommended contact may be determined, and the at least one recommended contact may be displayed according to the priority.

A method of operating a device according to an embodiment includes determining an identifier from context information of an application running on the device, searching for at least one recommended contact related to the identifier, and determining the priority of the searched at least one recommended contact. Depending on the determining step and priority, the method may include displaying at least one recommended contact.

A computer-readable recording medium according to another aspect includes a recording medium recording a program for executing the above-described method on a computer.

1 is a schematic diagram illustrating an example of a method for a device to recommend a contact, according to an embodiment.
Figure 2 is a flowchart showing a method of operating a device according to an embodiment.
FIG. 3 is a diagram illustrating a method for a device to recommend a contact using an identifier, according to an embodiment.
FIG. 4 is a diagram illustrating a method of generating a relationship graph according to intimacy between contacts, according to an embodiment.
FIG. 5 is a diagram illustrating a method of estimating recommended contact information from the contents of a user's mail using a user relationship graph in a device, according to an embodiment.
FIG. 6 is a diagram illustrating a method of displaying a contact means linked to a recommended contact point selected by a device according to an embodiment.
FIG. 7 is a diagram illustrating a method of displaying other contact means linked to recommended contact information when not connected to recommended contact information, according to one embodiment.
Figure 8 is a diagram for explaining a method of recommending other recommended contact information according to an embodiment.
FIG. 9 is a diagram illustrating a method of estimating recommended contact information based on schedule information and location information according to an embodiment.
FIG. 10 is a diagram illustrating a method of creating an address book after acquiring new contacts on a device, according to an embodiment.
FIG. 11 is a diagram illustrating a method of updating an address book in a device based on a user relationship graph, according to an embodiment.
FIG. 12 is a diagram illustrating how a device recommends message content based on schedule information and group information, according to an embodiment.
Figure 13 is a block diagram showing the configuration of a device according to an embodiment.
Figure 14 is a block diagram showing the detailed configuration of a device according to an embodiment.
Figure 15 is a block diagram of a processor according to one embodiment.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts that are not related to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected," but also the case where it is "electrically connected" with another element in between. . Additionally, when a part "includes" a certain component, this means that it may further include other components rather than excluding other components, unless specifically stated to the contrary.

Hereinafter, the present invention will be described in detail with reference to the attached drawings.

<Figure 1>

1 is a schematic diagram illustrating an example of a method for a device to recommend a contact, according to an embodiment.

Referring to FIG. 1, according to one embodiment, the device 10 may determine at least one identifier 101, 102, and 103 from context information of an application running on the device 10.

The identifier according to one embodiment may be a keyword of text or an expression characteristic point through facial recognition. The device 10 may determine at least one identifier and group identifiers that are related to each other.

According to one embodiment, the device 10 may extract words used more than a certain frequency from context information as an identifier using a language processing algorithm. At this time, the identifier may be a keyword.

According to one embodiment, the device 10 may obtain a keyword by maintaining a map between two or more dictionaries so that a word/phrase in one dictionary can be mapped to another word/phrase in another dictionary. In an embodiment, when a word/phrase in one dictionary has an association with a word/phrase in another dictionary, the device 10 may obtain interchangeable keywords using a map. The association relationship may indicate how a pair of nodes corresponding to a pair of data are related to each other. In various embodiments, an association relationship can be expressed as a predicate with a pair of data/nodes as the subject and object, respectively. In an embodiment, the association relationship between two or more dictionaries may include an identical relationship or an inclusion relationship, but is not limited thereto. For example, the words "Korea" and "KR", which are in the same relationship, may be interchangeable unless the context requires otherwise. Alternatively, the embedded words “Sports” and “Basketball” may be interchangeable unless the context requires otherwise. Dictionaries can be language dictionaries, search context dictionaries, AdWords dictionaries, user intent maps, and custom dictionaries.

Language processing algorithms may be, for example, Neuro-Linguistic Programming algorithms or Natural language processing algorithms, and various other algorithms and algorithms that can analyze and process human language. It may include combinations of

According to one embodiment, the device 10 may use a face recognition algorithm to extract faces detected at a predetermined frequency or more from context information as an identifier. At this time, the identifier may be an facial expression feature point.

The device 10 can detect feature points of the face area using coordinate information corresponding to the face. For example, feature points of the face area can be detected using the position coordinates of the eyes, nose, mouth, and ears of the face.

The face recognition algorithm according to one embodiment may, as an example, include an algorithm that mixes dynamic compensation fuzzy neural network (DCFNN) and eigenface recognition-LCA (Eigen face-LDA) and a combination of algorithms. According to one embodiment, the device 10 may obtain context information of the currently executing application. According to one embodiment, the application may include applications such as mail, SNS, text, photo album, diary, and news, and is not limited to the type of application.

According to one embodiment, the context information may include photos, pictures, text, videos, animations, etc. included in the application, and in particular, it may include the tone, tone of voice, and facial expression of the person in the photo included in the context information. . Additionally, according to one embodiment, the context information may include the current time, application running time, application properties, application type, etc.

According to one embodiment, the device 10 may obtain context information from data displayed on the device 10 according to execution of an application running on the device 10. In an embodiment, the device 10 may obtain context information based on the contents of the text displayed on the device 10. For example, text displayed on the device 10 may include at least one of the email title, email body, sender, or referrer displayed depending on the execution of the email application. In an embodiment, the device 10 may obtain context information with different weights depending on the field containing the text. For example, the device 10 may obtain context information by assigning the text included in the email title to the greatest weight and the text included in the referrer to the least weight. Alternatively, the device 10 may obtain context information by classifying each text into different categories depending on the field containing the text. For example, the device 10 may obtain context information by classifying the text included in the email subject into the 'Purpose' category and the text included in the sender into the 'Person' category.

Alternatively, the device 10 may obtain context information based on a video image displayed on the device 10. For example, the image displayed on the device 10 may include at least one of a video, a still image, and a representative image displayed for a predetermined period of time according to execution of the video application. In an embodiment, the device 10 may obtain context information with different weights depending on the field containing the video image. Alternatively, the device 10 may obtain context information by classifying each text into different categories depending on the field containing the video image.

According to one embodiment, the device 10 may analyze the context information to extract at least one identifier, for example, at least one keyword and facial feature point, and determine the tendency of the context information using the extracted identifier. there is. For example, if the first identifier 101 is 'mother's face', the second identifier 102 is 'family trip', and the third identifier 103 is 'fun', the device 10 is currently It can be determined that the tendency of the context information being executed is 'fun family trip'. In an embodiment, the device 10 may process a plurality of identifiers into text representing a time-series operation in order to determine the tendency of the context information. For example, based on a plurality of identifiers, the device 10 may determine, 'The user searched for travel attractions in Canada,' 'The user searched for restaurant information in Canada,' and 'The user searched for restaurant information in Canada.' You can generate text such as 'I went to play basketball' and determine the nature of the context information based on the generated text.

According to one embodiment, the device 10 may search for recommended contacts related to the identifier. The device 10 may search for a plurality of recommended contacts related to a plurality of identifiers. The device 10 may utilize a learning model based on deep neural network technology to search for recommended contacts related to at least one identifier.

The device 10 may search for recommended contacts related to one identifier or a combination of identifiers. For example, if the first identifier 101 is 'mother's face', the second identifier 102 is 'family trip', and the third identifier 103 is 'fun', the device 10 recommends You can search for family contact information as contact information.

According to one embodiment, the device 10 may determine the priority of at least one searched recommended contact. According to one embodiment, the device 10 may determine the priority of recommended contacts by considering the frequency of contact with the recommended contacts, contact time, contact means, contact period, etc.

According to one embodiment, the device 10 may display recommended contact information on a portion of the display. According to one embodiment, the device 10 may display recommended contact information in the form of a pop-up window, a separate window, or a message.

According to one embodiment, the device 10 may display a recommendation message in a pop-up window 104 at the bottom of the screen. According to one embodiment, the pop-up window 104 may include identification information 106 of the recommended contact, for example, the name in which the recommended contact is stored. According to one embodiment, the pop-up window 104 may include an icon 107 for a means to connect to recommended contacts. According to one embodiment, the pop-up window 104 may display detailed information 105 of recommended contacts. Detailed information 105 of the recommended contact information may include a phone number if the contact method is a phone call, and ID information if the contact method is SNS.

<Figure 2>

Figure 2 is a flowchart showing a method of operating a device according to an embodiment. In step 201, according to one embodiment, device 10 may determine an identifier from context information of a running application. According to one embodiment, the device 10 may determine at least one identifier from context information using a language processing algorithm or a face recognition algorithm. According to one embodiment, the identifier may be determined using words, similar words, synonyms, etc. detected at a predetermined frequency or higher.

At step 202, according to one embodiment, device 10 may retrieve at least one recommended contact related to the identifier. According to one embodiment, the device 10 uses history information in which the identifier has been used for a predetermined period of time to create an artificial intelligence learning model based on the results of learning the relationship between the identifier and a plurality of contact information (graph learning). can be obtained.

For example, the device 10 may process a plurality of identifiers into text representing time-series operations. For example, based on a plurality of identifiers, the device 10 may determine, 'The user searched for travel attractions in Canada,' 'The user searched for restaurant information in Canada,' and 'The user searched for restaurant information in Canada.' You can create text such as 'I went to play basketball.'

According to one embodiment, device 10 uses information about the user's communications with other users, such as contact owners, to determine relationships between the user and other users, or between other users and other users. Gender can be learned. Information about communication may include frequency of contact between multiple users, contact time, contact location, intimacy of contact content, common interests, intimacy, etc. The device 10 can learn by inputting the above-described communication information into a first learning model for determining the relationship between a plurality of users and thereby generate a relationship graph.

For example, the device 10 may create a relationship graph that is trained to connect the user and other users who have contacted the user with a high frequency of travel or foreign country-related content into a 'travel' relationship. Alternatively, the device 10 may create a relationship graph learned to connect other users who have contacted the user with a high frequency to do the same exercise with the user, or with a plurality of other users, in an 'exercise' relationship. there is. The relationship graph will be explained in more detail with reference to FIG. 4.

According to one embodiment, the device 10 may use an artificial intelligence learning model to identify an association relationship between an identifier and a relationship graph and search for recommended contacts based on the identified association relationship. In an embodiment, an artificial intelligence learning model may be trained to identify an association relationship between an identifier and a relationship graph using text processed in the time-series operation described above.

For example, when the device 10 extracts 'Canada' as an identifier, the device 10 uses an artificial intelligence learning model learned based on history information in which 'Canada' is used together with 'travel' to connect the user and 'Canada' in the relationship graph. Contacts of other users connected through a ‘travel’ relationship can be identified as recommended contacts.

Alternatively, when 'John's face' is extracted as an identifier, the device 10 uses an artificial intelligence learning model learned based on the history information of 'John's face' being used together with 'Tom's face' to create a relationship graph. You can identify Tom's contact information, which is connected to John as a 'friend', as a recommended contact. However, this is an example, and the contents of the artificial intelligence learning model and relationship graph learned based on the history information of this disclosure are not limited to the examples described above.

According to one embodiment, the device 10 may search for at least one recommended contact number using the acquired artificial intelligence learning model.

According to one embodiment, in step 203, the device 10 may determine the priority of at least one searched recommended contact. According to one embodiment, the device 10 is based on historical information such as the number of contacts with recommended contacts, contact means, contact period, correlation with identifiers, and current information such as current time, current location, and application information currently in use. This allows you to determine the priority of recommended contacts.

According to one embodiment, in step 204, the device 10 may display at least one recommended contact number according to priority. According to one embodiment, the device 10 may display a plurality of recommended contacts at once or sequentially. According to one embodiment, the device 10 may display at least one connection means linked to the recommended contact information at once or display them one by one multiple times.

<Figure 3>

FIG. 3 is a diagram illustrating a method for a device to recommend a contact using an identifier, according to an embodiment.

Referring to FIG. 3, according to one embodiment, the device 10 may determine the first identifier 101, the second identifier 102, and the third identifier 103 from context information.

According to one embodiment, the device 10 can search for at least one recommended contact using an artificial intelligence learning model obtained based on a result of learning the relationship between an identifier and a plurality of contact information (graph learning). there is.

According to one embodiment, the device 10 may give weight to the contact information used according to the application, period, time, number, and place in which the identifier was used. Additionally, the device 10 may determine at least one recommended contact based on the assigned weight.

According to one embodiment, the device 10 may collect usage history for at least one personal contact function, such as a call, text, messenger, email, or SNS. According to one embodiment, the usage history may include the date and time when contact for each function was made. Additionally, the usage history may include call time if a call function is provided, and contact details of the remaining functions if the call function is not provided.

According to one embodiment, the device 10 analyzes the collected usage history for each function according to at least one criterion of period, time, and number of times and assigns weight to the used contacts. For example, by assigning a weight of 2.0 to contacts used within the last two days to select contacts with high recent usage, or by assigning a weight of 1.5 to contacts used from 6 PM to 12 PM, the user mainly contacts people with whom the user is close. You can select contacts with high usage during certain times.

According to one embodiment, the device 10 may assign weight to contacts that have exchanged content containing words or emoticons expressing preset emotions in the use history of functions other than the call function among personal contact functions. For example, email contact history containing the word "love" or emoticons is given a weight of 2.0 to select contacts with high intimacy. Or, conversely, by assigning a weight of 0.1 to email contact history containing the word "loan", contacts such as loan advertisements can be selected to have lower priority.

According to one embodiment, the device 10 may determine the priority of contacts for each function according to the weight and select at least one contact as a recommended contact.

According to one embodiment, the device 10 may activate a contact means linked to the recommended contact information when one of the recommended contact information for each function displayed on the screen is selected. Additionally, the device 10 may assign weight to recommended contacts selected by the user so that frequently selected contacts are recommended more often. According to one embodiment, the device 10 may assign weight to contacts whose number of selections is equal to or greater than a preset number of times. Through this, the device 10 can achieve the effect of further activating the use of recommended contacts.

According to one embodiment, the device 10 may determine recommended contact information including a recommended partner 302 and a contact information 303. According to one embodiment, the recommended partner 302 may be identification information of a person or company that is highly related to at least one of the first identifier 101, the second identifier 102, and the third identifier 103. According to one embodiment, the device 10 may determine an identifier that can identify a recommended contact associated with a plurality of identifiers from internal storage, a cloud, or a server. According to one embodiment, the identification name is the recommended partner 302 and may include a name stored in the device 10, a company name searched through the web, and identification information searched through SNS.

According to one embodiment, the device 10 may search for at least one contact number corresponding to the recommended partner 302. According to one embodiment, the contact information corresponding to the recommended partner 302 may include an SNS address, a phone number that can be called, an email address, an SNS ID, etc. According to one embodiment, the device 10 may determine the priority of the recommended partner 302 by reflecting a situation in which information associated with at least one identifier is detected. For example, if at least one of the identifiers 101, 102, and 103 is related to a family trip, the contact information of the family member “mom” may be determined as priority.

According to one embodiment, the device 10 may set the priority of the contact information 303 corresponding to the recommended partner 302. According to one embodiment, the device 10 may determine the priority of the contact information 303 by reflecting a situation in which information associated with at least one identifier is detected. According to one embodiment, the device 10 may determine the priority of the contact 303 corresponding to the recommended partner 302 based on a weight assigned based on a frequently contacted means, a recently contacted means, a contact location, etc. For example, if you mainly talk on the phone with “Mom,” the recommended partner (302) whose priority (301) is first, and often talk about family trips over the phone, phone calls are linked to mom as the first priority. It can be decided by means of contact (301). Additionally, in the same way, the second priority communication method 302 can be determined as a text message, and the third priority communication method 303 can be determined as SNS.

<Figure 4>

FIG. 4 is a diagram illustrating a method of generating a relationship graph according to intimacy between contacts, according to an embodiment.

According to one embodiment, the device 10 may learn the relationship between the user and other users using communication information between the user and other users. According to one embodiment, the device 10 learns using the frequency of contact with other users, contact time, contact location, intimacy of contact content, common interests, intimacy, etc., and creates a relationship graph accordingly. .

According to one embodiment, the device 10 collects newly disclosed information from SNS, mail, call content, etc., based on pre-stored labeled information such as another user's name, contact information, group affiliation, and frequency of contact. Unlabeled information such as contact information can be reflected in the initial graph.

In Figure 4, circle-shaped nodes represent people. The placement location and color of nodes may be data fields that indicate similarity, interest, intimacy, etc. between nodes. In an embodiment, a node may include a plurality of patterns occupying a predetermined area. The shape of each pattern can represent a different data field, and the area that each pattern occupies within a node can represent the relative ratio between the values of each data field. For example, in the first graph of Figure 4, B1 and B2 may have a common data field of interest called “Canada.” Additionally, in the relationship graph, R1 may have a data field called “travel” as an interest. According to one embodiment, the line connecting each node may indicate the relationship between users corresponding to each node. Additionally, the thickness of the line connecting each node may indicate the strength of the relationship between each node. The strength of the relationship may include intimacy, similarity, membership in a public group, etc. For example, in the first graph of Figure 4, the strength of the relationship between B2 and G3 may be stronger than the strength of the relationship between G3 and G2. In the graph of FIG. 4, the thickness of the line connecting nodes may be a value representing the strength of a standardized relationship based on a plurality of data fields included in each node. However, this is an example, and in the graph of FIG. 4, lines connecting each node may exist depending on each data field. For example, B2 and G3 may be connected by a line of first thickness when based on the 'Travel' data field and a line of second thickness when based on the 'Canada' data field. In addition, the line connecting each node may include fields indicating relationships as well as values. For example, a field indicating an association relationship on a line connecting B2 and G3 may include an identical relationship (sameAs), a membership relationship (type), or an inclusion relationship (subClassOf).

According to one embodiment, the device 10 may generate an initial graph using information obtained based on predefined people and communication information. In the first graph of Figure 4, G1, G2, and G3 have not yet been learned.

After learning 1, the device 10 can learn G2 based on the conversation contents, message contents, mail contents, etc. between B1 and G2. Referring to the second graph in Figure 4, it can be seen that G2's similarity to Canada has increased due to the influence of B1. Additionally, G3 can be learned simultaneously in relation to B2 and R1. Because the connection strength between G3 and B2 is stronger than that between G3 and R1, G3 can be learned to place greater weight on Canada than on travel.

Referring to the third graph in FIG. 4, after learning 2, the device 10 can learn a relationship graph based on communication information with B1, B2, G1, G2, G3, and R1. According to one embodiment, G2 and G3 may be learned based on connection strength and communication information in device 10. According to one embodiment, the proportion of interests in Canada and travel in G2 and G3 may change while going through Learning 2. Referring to the third graph in Figure 4, G2 generated similarity for travel, and G3's proportion of Canada increased compared to travel. In addition, it can be seen that the proportion of Canada has increased in G1 through connection with B1 through G2.

In this way, the relationship graph of B1, B2, G1, G2, G3, and R1 can be learned through repetitive learning using information collected from the device 10 and information received from the outside. According to one embodiment, if the user is writing a message on the device 10 with the topic “Travel to Canada,” the contacts of G2 and G3 may be searched as recommended contacts based on the extracted identifiers Canada and Travel. .

<Figure 5>

FIG. 5 is a diagram illustrating a method of estimating recommended contact information from the contents of a user's mail using a user relationship graph in a device, according to an embodiment.

According to one embodiment, the device 10 may provide a mail service to Tom, a user. The device 10 can display an email received on November 1, 2017 from Sunny, who is traveling. According to one embodiment, the device 10 may determine the identifier by analyzing the contents of the mail received from Sunny. For example, the device 10 may analyze the text of the email and determine keywords such as “Canada,” “travel,” “Jake,” “travel agency,” and “reply” as identifiers.

According to one embodiment, the device 10 may search for recommended contact information based on at least one identifier. According to one embodiment, the device 10 may search for recommended contacts using a user relationship graph created based on intimacy and interests between users.

According to one embodiment, the device 10 uses a user relationship graph formed around Tom (501), Sunny (502), Jake (503), Yoon (504), June (505), and the travel agency (506). You can search. For example, Sunny (502) may have a common interest in Canada and may include a common interest in travel with Jake (503).

In embodiments, the data fields of each user node may include different affinities, frequency of contact, each user's location, other interests, etc. For example, the device 10 may determine each user's location information as a data field based on contact details with each user, identification information of each user, externally displayed status information, etc. In one embodiment, According to this, the device 10 may determine a recommended contact that fits the current situation among the searched contacts. According to one embodiment, the device 10 may determine recommended contact information based on the current location and time. The location and time considered by the device 10 may include all or each of the location and time of the user and the contact owner. For example, the device 10 may recommend Yoon (504), which is located in Korea, over Sunny (502), considering that Sunny (502) is located overseas.

Additionally, the device 10 may determine recommended contact information based on the contents of the email. For example, device 10 may consider a recommendation from Jake 503 because Sunny 502 mentioned traveling with Jake 503, and a recommendation from travel agency 506 because Sunny 502 mentioned looking into a travel agency. can be considered. Additionally, device 10 may consider Sunny 502's recommendation from what Sunny 502 requested a reply to. Additionally, the device 10 can determine recommended contact information by considering both email content and location information. If it is determined that the user intends to leave for Canada in the near future, the device 10 may recommend Jake (511), who resides in Canada, the travel destination, over Yoon (504), who resides in Korea.

According to one embodiment, the device 10 may display the determined recommended contact information on the screen as a pop-up window 510. According to one embodiment, the device 10 may display a plurality of recommended contacts simultaneously.

According to one embodiment, the device 10 may display the properties of recommended contacts differently depending on the priority of the recommended contacts. The device 10 may display the size, color, and degree of deformation of recommended contacts differently depending on the priority of the recommended contacts. According to one embodiment, the device 10 may display Jake 511, which has been determined as the first priority, larger than other contact information or change its color to make it stand out.

According to one embodiment, the device 10 may display Jake (511) as the first priority, Sunny (512) as the second priority, and Yoon (513) as the third priority by linking the contact means. For example, if it is determined that mail is the means of contacting Sunny 512, which has the second priority, and Sunny 512 is selected in the pop-up window 510, the device 10 can run an application related to mail.

<Figure 6>

FIG. 6 is a diagram illustrating a method of displaying a contact means linked to a recommended contact information selected by a device, according to an embodiment.

According to one embodiment, when one of a plurality of recommended contacts is selected by the user, the device 10 may display a means of connecting to the recommended contacts.

According to one embodiment, the device 10 may display Jake's contact information using a pop-up window 610. According to one embodiment, the device 10 may display contact means according to the priority of the contact means.

According to one embodiment, the device 10 may use context information of a running application to obtain an artificial intelligence learning model based on a result of learning the relationship between the running application and applications in the device.

In an embodiment, the context information of the application may include, but is not limited to, at least one of the surrounding environment information of the application, device status information of the application, status information of the user of the application, and application usage history information. . The surrounding environment information of an application refers to environmental information within a certain radius while the application is running and may include, for example, weather information, temperature information, humidity information, illuminance information, noise information, sound information, etc. It is not limited to this. The device status information of the application includes device mode information (e.g., sound mode, vibration mode, silent mode, power saving mode, blocking mode, multi-window mode, auto-rotation mode, etc.) of the device while the application is running, device location information, It may include, but is not limited to, time information, activation information of the communication module (e.g., Wi-Fi ON / Bluetooth OFF / GPS ON / NFC ON, etc.), network connection status information, etc. The user's status information is information about the user's movements, life patterns, etc., and may include, but is not limited to, information about the user's walking status, exercising status, driving status, sleeping status, and user's mood status, etc. . Application usage history information is information about the user's history of using the application, and may include, but is not limited to, the history of functions executed in the application, the user's call history, and the user's text message history.

The device 10 uses context information of the running application to perform artificial intelligence based on the results of learning the relationship between the running application and applications installed in the device or running on the device based on external control. A learning model can be obtained. In an embodiment, an application installed on or running on a device may be an application associated with contacting other users. For example, using an artificial intelligence learning model, the device 10 may learn that when a user uses an SNS application outdoors, the device 10 communicates with other users through the same SNS application at a high frequency. Alternatively, the device 10 may learn, using an artificial intelligence learning model, that when a user uses a mail server application at work, the device 10 communicates with other users through a phone application at a high frequency. However, this is an example, and the method of learning by the artificial intelligence learning model of the present disclosure is not limited to the above-described example. According to one embodiment, the device 10 provides context information of a running application and communication between a plurality of users. Using information about, an artificial intelligence learning model can be obtained based on the results of learning the relationship between the running application, recommended contact information, and applications in the device.

According to one embodiment, the device 10 may use the acquired artificial intelligence learning model to determine an application to be linked to at least one recommended contact. For example, the device 10 uses an artificial intelligence learning model to learn that when a user uses a mail server application at a company and the recommended contact is a company employee, the device 10 communicates with the user through an in-house messenger application. You can. Alternatively, the device 10 may be taught using an artificial intelligence learning model to communicate with the user through a phone application when the user uses a mail server application at work and the recommended contact is a transaction partner.

According to one embodiment, the device 10 may link a plurality of contact means to one recommended contact information. A plurality of contact means may include a plurality of applications. According to one embodiment, the device 10 may search for a plurality of applications based on the frequency, execution time, execution location, execution period, and main functions of the application used for communication with recommended contacts.

According to one embodiment, the device 10 may apply information about communication between a plurality of users to an artificial intelligence learning model for determining relationships between recommended contacts and applications in the device. The device 10 may use the searched recommended contact information and the learned artificial intelligence learning model to search for a plurality of applications associated with the searched recommended contact information.

For example, the device 10 may use an artificial intelligence learning model to search for an email application as a related application when the recommended contact is a user with a 'work' data field. Alternatively, the device 10 may use an artificial intelligence learning model to search for an in-house messenger application as a related application when the recommended contact is a user with a 'company employee' data field.

According to one embodiment, the device 10 may determine the priorities of the plurality of applications described above.

According to one embodiment, the device 10 may simultaneously display a plurality of contact means 611, 612, and 613 linked to the selected recommended contact information as shown in FIG. 6. The device 10 may set displayed attributes differently according to the priorities of the plurality of communication means 611, 612, and 613. For example, if the contact method recommended for communication with Jake in the current situation is SNS, the SNS contact method 611 is displayed in a larger window than the phone contact method 612 or the email contact method 613, or is displayed in color. can be displayed differently. Additionally, the device 10 can change and display properties such as size, color, shape, brightness, and blinking of a plurality of communication means according to priority.

According to one embodiment, the device 10 may execute a communication method selected by the user from among a plurality of communication methods. For example, when the user selects the SNS contact method 61, the SNS application with which the user and Jake communicated the most can be executed.

<Figure 7>

FIG. 7 is a diagram illustrating a method of displaying other contact means linked to recommended contact information when not connected to recommended contact information, according to one embodiment.

According to one embodiment, the device 10 may display at least one recommended contact information based on the contents of the currently running application.

According to one embodiment, the device 10 may display recommended contacts linked to the first priority application. The device 10 may display recommended contact information in a preset area 701 on the screen. According to one embodiment, the preset area 701 may be any one of the bottom, top, center, left, and right of the screen.

According to one embodiment, the device 10 may display an icon of an application linked to the recommended contact information. For example, the device 10 displays the identification name 703 of the recommended contact, the icon 702 of the linked application, and the phone number 704 of the recommended contact in a predetermined area 701 of the screen, that is, at the bottom. It can be displayed.

According to one embodiment, the device 10 may execute an application linked to the selected contact according to a user input for selecting a recommended contact. For example, when the user selects a recommended contact, the user may call the phone number 704 whose identification name 703 is registered as mother. At this time, a method of making a call can use a function provided by the device 10 itself or a phone application.

According to one embodiment, if communication using the first priority application of the recommended contact fails, the device 10 may display the second priority application. For example, if a phone call with your mother fails, you may display the mail service as a secondary application. On the screen of the device 10, an icon 705 of the second priority application, an email address 706 of a recommended contact, and an identification name 703 may be displayed.

Alternatively, if communication using the first priority application fails, the device 10 may immediately execute the second priority application. For example, if the phone connection with the mother fails, an email service to the mother may be launched.

<Figure 8>

FIG. 8 is a diagram illustrating a method of recommending other recommended contact information according to an embodiment.

By way of example, the device 10 may display recommended contacts recommended based on user context in the lower area 801 of the screen. The recommended contact information may include Jake, which is the user's identification name (803), and an icon (802) of an application linked to the recommended contact information.

In one disclosure, device 10 may receive input 804 from a user requesting another recommended contact. For example, a user input that touches the bottom area 801 of the screen where recommended contacts are displayed may be received. By another example, user input may include tap, touch and hold, double tap, drag, panning, flick, drag and drop, etc. User input requesting other suggested contacts The method can be specified by the user.

According to one disclosure, the device 10 may display other recommended contacts in the lower area 801 of the screen of the device 10 according to the user's input 804 requesting other recommended contacts. For example, the device 10 may display an identification name 805 of Kim, a mail icon that is an icon 807 of an application linked to a recommended contact, and Kim's mail address 705.

According to one embodiment, other recommended contacts may have lower priority than the recommended contact currently displayed on the screen.

According to one embodiment, when displaying recommended contact information, the device 10 may also display coupons for advertisements or advertising products provided by the recommended contact information. According to one embodiment, the device 10 can provide the convenience of recommending contacts while simultaneously increasing convenience of life through providing advertisements and increasing the possibility of selecting recommended contacts.

<Figure 9>

FIG. 9 is a diagram illustrating a method of estimating recommended contact information based on schedule information and location information according to an embodiment.

By way of example, the device 10 may determine recommended contact information using the server 3000 or the SNS server 4000 using the network 5000.

The device 10 may provide the server 3000 with information related to communication with other people performed by the device 10, receive a recommended contact list from the server 3000, and display it on the screen.

Additionally, the device 10 can provide information related to communication, including location information and time information, to the server 3000, and the device 10 can provide the server 3000 with the current location and the user's schedule information. You can.

The server 300 may generate a recommended contact list using the schedule information, location information, and time information of the user of the device 10. Additionally, the server 3000 may generate a recommended contact list based on schedule information of the user of the device 10 and the user's acquaintances. In this case, the server 300 may receive the user's schedule information and the acquaintance's schedule information from at least one of the device 10 or the SNS server 4000.

The network 5000 is a wired network, mobile radio communication network, or satellite communication network, such as a Local Area Network (LAN), Wide Area Network (WAN), or Value Added Network (VAN). It can be implemented as a wireless network such as the like. In addition, it is a data communication network in a comprehensive sense that allows each network constituent shown in FIG. 3 to communicate smoothly with each other, and includes wired Internet, wireless Internet, and mobile wireless communication networks.

<Figure 10>

FIG. 10 is a diagram illustrating a method of creating an address book after acquiring new contacts in a device, according to an embodiment.

According to one embodiment, when the device 10 acquires new contact information through communication with another user, the device 10 may add the new contact information to the address book based on intimacy with the new contact information, interests, schedule, etc. According to one embodiment, the device 10 can create, change, and delete groups in the address book based on relationships with other users.

According to one embodiment, the device 10 may acquire new contact information I and new contact information J. The device 10 can use the user's relationship graph to determine the personality of contact I and contact J, their relationship with the user, and whether or not they have a public relationship. For example, the device 10 may determine that contact I and contact J are contact information of people met at a travel meeting. If the groups in the address book previously stored in the device 10 are company 1001, family 1002, and friends 1003, a travel group 1004 group can be created to classify contacts I and contacts J. The device 10 may add contact I and contact J to the newly created travel group 1004 group.

<Figure 11>

FIG. 11 is a diagram illustrating a method of updating an address book in a device based on a user relationship graph, according to an embodiment.

According to one embodiment, the device 10 may update the user relationship graph based on the user's communication information with other users. According to one embodiment, the device 10 may classify the address book based on the updated user relationship graph.

According to one embodiment, the device 10 may determine that a personal relationship has been created with B (1101) based on communication information between B (1101) and the user classified in the company (1001) group. The device 10 may determine that B (1101) is similar to users included in the friend (1003) group. The device 10 can move B (1101) from the company (1001) group to the friend (1003) group. The user can check B (1102) in the friend (1003) group of the address book of the device (10).

Accordingly, according to one disclosure, an address book may be automatically organized based on information about a user's communications with other users.

<Figure 12>

FIG. 12 is a diagram illustrating how a device recommends message content based on schedule information and group information, according to an embodiment.

According to one embodiment, the device 10 may obtain user schedule information and determine an application linked to the recommended contact information based on the obtained user information. For example, the device 10 may obtain information “2018.09.04 H's birthday” from the user's schedule information. The device 10 may recommend H's contact information on September 4, 2018. At this time, the device 10 may indicate that an SNS message 1203 will be sent to H, reflecting the fact that SNS is a means of frequent contact with H.

According to one embodiment, the device 10 may provide a document form with predetermined tone, grammar, sentence structure, etc. based on the intimacy determined with the recommended contact. For example, the device 10 sends the SNS message 1203 based on the fact that the user often called H “our cutie” in conversations with H, the phrase “our cutie” 1204, and the fact that it is H’s birthday. Thus, the phrase “Happy Birthday” can be provided.

According to one embodiment, the device 10 may provide a predetermined document form based on group properties of the address book. For example, the device 10 may obtain schedule information for “2018.09.04 Chuseok.” According to one embodiment, the device 10 may transmit a message related to Chuseok greetings for each group on September 24, 2018. According to one embodiment, the device 10 uses a text message 1205 to send a message to a company group, and can provide message content in a public tone. According to another embodiment, the device 10 uses SNS 1206 to send a message to a friend group, and can provide message content with a friendlier tone than the text message 1205 to a company group.

According to one embodiment, the device 10 may automatically transmit a recommended message to a recommended contact based on certain information.

<Figure 13, Figure 14>

Figure 13 is a block diagram showing the configuration of a device according to an embodiment.

Figure 14 is a block diagram showing the detailed configuration of a device according to an embodiment.

As shown in FIG. 13, the device 10 according to one embodiment may include a memory 1100, a display unit 1210, and a processor 1300.

However, not all of the components shown in FIG. 13 are essential components of the device 10. The device 10 may be implemented with more components than those shown in FIG. 13 , or the device 10 may be implemented with fewer components than the components shown in FIG. 13 .

For example, as shown in FIG. 14, the device 10 according to one embodiment includes, in addition to a memory 1100, a display unit 1210, a camera 1610, and a processor 1300, an output unit 1200, It may further include a communication unit 1500, a sensing unit 1400, an A/V input unit 1600, and a user input unit 1700.

The memory 1100 may store programs for processing and controlling the processor 1300, and may also store images input to the device 10 or guide information output from the device 10. Additionally, the memory 1100 may store specific information for determining whether to output guide information.

The memory 1100 may be a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (for example, SD or XD memory, etc.), or RAM. (RAM, Random Access Memory) SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk , and may include at least one type of storage medium among optical disks.

Programs stored in the memory 1100 can be classified into a plurality of modules according to their functions, for example, a UI module 1110, a touch screen module 1120, a notification module 1130, etc. .

The UI module 1110 may provide specialized UI, GUI, etc. that are linked to the device 10 for each application. The touch screen module 1120 may detect a user's touch gesture on the touch screen and transmit information about the touch gesture to the processor 1300. The touch screen module 1120 according to one embodiment can recognize and analyze a touch code. The touch screen module 1120 may be composed of separate hardware including a controller.

The notification module 1130 may generate a signal to notify the occurrence of an event in the device 10. Examples of events that occur in the device 10 include receiving a call signal, receiving a message, inputting a key signal, and schedule notification. The notification module 1130 may output a notification signal in the form of a video signal through the display unit 1210, may output a notification signal in the form of an audio signal through the sound output unit 1220, and the vibration motor 1230 A notification signal can also be output in the form of a vibration signal. For example, the notification module 1130 may generate a signal to output guide information based on estimated lane information.

The output unit 1200 may output an audio signal, a video signal, or a vibration signal, and the output unit 1200 may include a display unit 1210, an audio output unit 1220, and a vibration motor 1230. there is.

The display unit 1210 displays and outputs information processed by the device 10. Specifically, the display unit 1210 may output an image captured by the camera 1610. Additionally, the display unit 1210 may synthesize the guide information generated by the processor 1300 with the captured image and output it.

Additionally, the display unit 1210 may display a user interface for executing an operation related to the response in response to the user's input.

The audio output unit 1220 outputs audio data received from the communication unit 1500 or stored in the memory 1100. Additionally, the sound output unit 1220 outputs sound signals related to functions performed by the device 10 (eg, call signal reception sound, message reception sound, notification sound). For example, the audio output unit 1220 may output guide information generated as a signal by the notification module 1130 as an audio signal under the control of the processor 1300.

The processor 1300 typically controls the overall operation of the device 10. For example, the processor 1300 executes programs stored in the memory 1100, thereby controlling the user input unit 1700, output unit 1200, sensing unit 1400, communication unit 1500, and A/V input unit 1700. ) can be controlled overall. Additionally, the processor 1300 may perform the function of the device 10 by executing programs stored in the memory 1100.

The sensing unit 1400 may detect the state of the device 10 or the state surrounding the device 10 and transmit the sensed information to the processor 1300.

The sensing unit 1400 includes a geomagnetic sensor 1410, an acceleration sensor 1420, a temperature/humidity sensor 1430, an infrared sensor 1440, a gyroscope sensor 1450, and a position sensor. It may include at least one of (eg, GPS) 1460, an air pressure sensor 1470, a proximity sensor 1480, and an RGB sensor 1490, but is not limited thereto. Since the function of each sensor can be intuitively deduced by a person skilled in the art from its name, detailed description will be omitted.

According to one embodiment, the sensing unit 1400 may measure the distance between the vehicle and at least one object determined in the captured image.

The communication unit 1500 may include one or more components that allow the device 10 to communicate with other devices (not shown) and servers (not shown). The other device (not shown) may be a computing device such as device 10 or a sensing device, but is not limited thereto. For example, the communication unit 1500 may include a short-range communication unit 1510, a mobile communication unit 1520, and a broadcast reception unit 1530.

The short-range wireless communication unit 1510 includes a Bluetooth communication unit, a Bluetooth Low Energy (BLE) communication unit, a Near Field Communication unit, a WLAN (Wi-Fi) communication unit, a Zigbee communication unit, and an infrared ( It may include, but is not limited to, an IrDA (infrared Data Association) communication unit, WFD (Wi-Fi Direct) communication unit, UWB (ultra wide band) communication unit, and Ant+ communication unit. For example, the short-range communication unit 1510 may receive information on the number of lanes through short-range wireless communication from a navigation device included in the vehicle.

The mobile communication unit 1520 transmits and receives wireless signals with at least one of a base station, an external terminal, and a server on a mobile communication network. Here, the wireless signal may include various types of data according to voice call signals, video call signals, or text/multimedia message transmission and reception.

The broadcast receiver 1530 receives broadcast signals and/or broadcast-related information from the outside through a broadcast channel. Broadcast channels may include satellite channels and terrestrial channels. Depending on the implementation example, the device 10 may not include the broadcast reception unit 1530.

The A/V (Audio/Video) input unit 1600 is for inputting audio or video signals, and may include a camera 1610, a microphone 1620, etc. The camera 1610 can obtain image frames such as still images or videos through an image sensor in video call mode or shooting mode. Images captured through the image sensor may be processed through the processor 1300 or a separate image processing unit (not shown).

According to one embodiment, the camera 1610 may capture images of the exterior of the vehicle. For example, the camera 1610 may capture a front image of a driving vehicle, but is not limited thereto.

The microphone 1620 receives external sound signals and processes them into electrical voice data. For example, the microphone 1620 may receive an acoustic signal from an external device or a user. The microphone 1620 can receive a user's voice input. The microphone 1620 can use various noise removal algorithms to remove noise generated in the process of receiving an external acoustic signal.

The user input unit 1700 refers to a means through which a user inputs data to control the device 10. For example, the user input unit 1700 includes a key pad, a dome switch, and a touch pad (contact capacitive type, pressure resistance type, infrared detection type, surface ultrasonic conduction type, and integral type). Tension measurement method, piezo effect method, etc.), jog wheel, jog switch, etc., but are not limited to these.

<Figure 15>

Figure 15 is a block diagram of a processor according to one embodiment.

Referring to FIG. 15, the processor 1300 according to one embodiment may include a data learning unit 1310 and a data recognition unit 1320.

The data learning unit 1310 may learn a relationship graph between a user and other users based on information related to communication between the user and other users. The data learning unit 1310 can learn standards regarding what data to use to increase the accuracy of the relationship graph and whether to expand the relationship graph using the data. The data learning unit 1310 can acquire data to be used for learning and apply the acquired data to a data recognition model to be described later, thereby learning standards for forming an appropriate relationship network according to learning of the relationship graph.

According to one embodiment, when there are a plurality of pre-built data recognition models, the data learning unit 1310 may determine a data recognition model with a high correlation between the input learning data and the basic learning data as the data recognition model to be learned. there is. In this case, the basic learning data may be pre-classified by data type, and the data recognition model may be pre-built by data type. For example, the basic training data is pre-classified by various criteria such as the region where the training data was created, the time the training data was created, the size of the training data, the genre of the training data, the creator of the training data, the type of object in the training data, etc. It may be.

The data recognition unit 1320 can increase the accuracy of contextual contact recommendation based on the user's relationship graph. The data recognition unit 1320 may increase the accuracy of contact recommendation based on the results of learning the relationship between the identifier of the context and a plurality of contact information using the learned data recognition model. The data recognition unit 1320 can increase the accuracy of contact recommendation by acquiring predetermined data according to a preset standard through learning and using a data recognition model using the acquired data as an input value. Additionally, the result value output by the data recognition model using the acquired data as an input value can be used to update the data recognition model.

At least one of the data learning unit 1310 and the data recognition unit 1320 may be manufactured in the form of at least one hardware chip and mounted on a device. For example, at least one of the data learning unit 1310 and the data recognition unit 1320 may be manufactured in the form of a dedicated hardware chip for artificial intelligence (AI), or an existing general-purpose processor (e.g. CPU Alternatively, it may be manufactured as part of an application processor) or a graphics-specific processor (e.g., GPU) and may be mounted on the various devices described above.

In this case, the data learning unit 1310 and the data recognition unit 1320 may be mounted on one device or may be mounted on separate devices. For example, one of the data learning unit 1310 and the data recognition unit 1320 may be included in the device, and the other may be included in the server. In addition, the data learning unit 1310 and the data recognition unit 1320 may provide model information built by the data learning unit 1310 to the data recognition unit 1320 through wired or wireless communication, and the data recognition unit ( Data input through 1320) may be provided to the data learning unit 1310 as additional learning data.

Meanwhile, at least one of the data learning unit 1310 and the data recognition unit 1320 may be implemented as a software module. When at least one of the data learning unit 1310 and the data recognition unit 1320 is implemented as a software module (or a program module including instructions), the software module is a readable non-transitory program that can be read by a computer. It may be stored on a readable recording medium (non-transitory computer readable media). Additionally, in this case, at least one software module may be provided by an operating system (OS) or a predetermined application. Alternatively, part of at least one software module may be provided by an operating system (OS), and the remaining part may be provided by a predetermined application.

Additionally, the data recognition unit 1320 can train a data recognition model used for situation determination using learning data. In this case, the data recognition model may be a pre-built model. For example, a data recognition model may be a pre-built model that receives basic training data (e.g., sample images, etc.) as input.

A data recognition model may be built considering the application field of the recognition model, the purpose of learning, or the computer performance of the device. The data recognition model may be, for example, a model based on a neural network. For example, models such as Deep Neural Network (DNN), Recurrent Neural Network (RNN), and Bidirectional Recurrent Deep Neural Network (BRDNN) may be used as data recognition models, but are not limited thereto.

According to various embodiments, when there are a plurality of pre-built data recognition models, the data learning unit 1310 may determine a data recognition model with a high correlation between the input learning data and the basic learning data as the data recognition model to be learned. there is. In this case, the basic learning data may be pre-classified by data type, and the data recognition model may be pre-built by data type. For example, the basic training data is pre-classified by various criteria such as the region where the training data was created, the time the training data was created, the size of the training data, the genre of the training data, the creator of the training data, the type of object in the training data, etc. It may be.

One embodiment may also be implemented in the form of a recording medium containing instructions executable by a computer, such as program modules executed by a computer. Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and non-volatile media, removable and non-removable media. Additionally, computer-readable media may include both computer storage media and communication media. Computer storage media includes both volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. Communication media typically includes computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave, or other transmission mechanism, and includes any information delivery medium.

Additionally, in this specification, a “unit” may be a hardware component such as a processor or circuit, and/or a software component executed by the hardware component such as a processor.

The description of the present invention described above is for illustrative purposes, and those skilled in the art will understand that the present invention can be easily modified into other specific forms without changing the technical idea or essential features of the present invention. will be. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. For example, each component described as unitary may be implemented in a distributed manner, and similarly, components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims described below rather than the detailed description above, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

Claims (20)

processor; and
Includes a memory that stores instructions executable by the processor,
Includes a memory that stores instructions executable by the processor,
The processor,
By executing the above commands,
Extract context information from displayed data based on the application running on the device,
From the context information, determine a plurality of identifiers,
Obtain a relationship graph created based on information about communication between a plurality of users,
Search for at least one recommended contact related to the plurality of identifiers based on the relationship graph and the plurality of identifiers,
Determine the priority of the searched at least one recommended contact,
A device that displays the at least one recommended contact information according to the priority, and also displays an icon of an application corresponding to a contact means to be linked to the at least one recommended contact information. According to clause 1,
The processor,
Using a language processing algorithm, a word used more than a certain frequency in the context information is determined as an identifier, or
A device that determines a face detected at a predetermined frequency or more from the context information as an identifier using a face recognition algorithm. According to claim 1,
The processor,
Displaying a first recommended contact number according to the priority of the at least one recommended contact number,
A device that displays a second-rank recommended contact if communication with the first-rank recommended contact fails. According to claim 1,
The processor,
Retrieving the at least one recommended contact using a first learning model,
The relationship graph is,
a plurality of nodes corresponding to the plurality of users; and
At least one line indicating a relationship between the plurality of users,
The device of claim 1, wherein the thickness of the at least one line indicates the strength of the relationship between the users. According to claim 4,
The first learning model is,
By analyzing the history information in which the identifier has been used in the information about the communication, weight is given to the contact information used according to the application in which the identifier is used, period of use, time of use, number of times of use, and location of use,
A device that determines the at least one recommended contact based on the assigned weight. According to claim 4,
The processor,
A device that determines intimacy between a plurality of pieces of contact information using the first learning model and generates an address book by classifying the plurality of contact information into a plurality of groups based on the determined intimacy. According to claim 4,
The processor,
When acquiring new contact information, the device classifies the new contact information into one of a plurality of groups based on communication information with the user including the new contact information and adds the address book. According to claim 7,
The processor is
A device for reclassifying a group of contact information whose intimacy has changed among the plurality of contact information. According to claim 6,
The processor,
Obtain user schedule information,
A device that displays all contact information included in one of the plurality of groups as recommended contact information based on the acquired user schedule information. According to clause 1,
The processor,
By applying information regarding communications between the plurality of users to a second learning model to determine relationships between recommended contacts and applications within the device.
, A device that determines an application to be linked to the at least one recommended contact. According to claim 10,
The processor,
A device that executes an application linked to the selected contact based on a user input for selecting one of the at least one recommended contact. According to claim 10,
The processor,
Decide on multiple applications to link to one recommended contact,
Determine the priority of the plurality of applications based on the frequency, execution time, execution location, execution period, and main function of the application used for communication with the recommended contact,
A device that displays icons of the plurality of applications in priority order according to the user's selection of recommended contact information. According to clause 12,
The processor,
According to the user's selection of recommended contacts, executing the first priority application,
If communication with the recommended contact using the first priority application fails, the device executes a second priority application. According to claim 10,
The processor,
Obtain user schedule information,
A device that determines an application to be linked to the recommended contact information according to the acquired user schedule information. According to claim 1,
The processor,
A device that provides a document form with predetermined tone, grammar, sentence structure, paragraph format, etc. based on the intimacy with the recommended contact information. According to claim 1,
The processor,
A device that displays the at least one recommended contact information in a preset area on the device screen. According to claim 1,
The processor,
A device that displays an icon of at least one application linked to the at least one recommended contact. delete extracting context information from displayed data based on an application running on the device;
determining a plurality of identifiers from the extracted context information;
Obtaining a relationship graph generated based on information about communication between a plurality of users;
searching for at least one recommended contact information related to the plurality of identifiers based on the relationship graph and the plurality of identifiers;
determining a priority of the searched at least one recommended contact; and
A method comprising: displaying the at least one recommended contact information according to the priority, and also displaying an icon of an application corresponding to a contact means to be linked to the at least one recommended contact information. A computer-readable recording medium that records a program for executing the method of claim 19 on a computer.

Images