KR102252084B1 - Method, device and computer readable storage medium for user modeling based on blackboard - Google Patents

Abstract

A user modeling device is described. An exemplary user modeling device includes a sensor data collection unit, a context recognition unit, a black board unit, and a user model inference unit. The sensor data collection unit may be configured to acquire sensor data associated with at least one user device of the user. The context recognition unit may be configured to generate user context information using sensor data. The black board unit may have a black board data structure. The blackboard unit may be configured to store the generated user context information in the blackboard data structure. The user model inference unit may be configured to manage the user model.

Description

Method, device and computer-readable storage medium for blackboard-based user modeling {METHOD, DEVICE AND COMPUTER READABLE STORAGE MEDIUM FOR USER MODELING BASED ON BLACKBOARD}

The present disclosure relates to a method, an apparatus, and a computer-readable storage medium for blackboard-based user modeling.

Unless otherwise stated herein, the content described in this section is not prior art to the claims in this application, and should not be admitted to be prior art for reasons described in this section.

As the use of mobile terminals such as smartphones and tablet computers becomes more common, applications that provide various types of services are emerging. Among these applications, we intend to secure competitiveness by providing customized services. In order to provide a user-customized service, unique information that does not change for a user is simply used, but with the development of technology, a situation in which the user is in time or location is also grasped. Data that can be used to objectively grasp the user's situation includes sensor data that can be obtained from various sensors provided in a mobile device carried by the user.

According to Prior Art Document 1 (Korean Patent Laid-Open No. 10-2015-0118780), context information is obtained based on the user's profile information and the user's association, place, and current situation. However, even if the information acquired by using the sensor data is the same, the context may be different according to the unique characteristics such as the user's personality and propensity, and the misidentified user context may not be helpful to the user. In addition, the user's exact current context mutually influences the user's unique characteristics, and may be influenced by the user context in the past.

The present disclosure is to solve the above problems, and proposes a method, an apparatus, and a computer-readable storage medium for effectively performing user context information and user modeling.

In some embodiments of the present disclosure, a user modeling device is described. An exemplary user modeling device may include a sensor data collection unit, a context recognition unit, a black board unit, and a user model inference unit. The sensor data collection unit may be configured to acquire sensor data associated with at least one user device of a user. The context recognition unit may be configured to generate user context information by using sensor data. The blackboard unit has a blackboard data structure, and may be configured to store the generated user context information in the blackboard data structure. The user model inference unit may manage a user model including a plurality of user profiles. The user model inference unit may be configured to evaluate at least one of a plurality of user profiles using context information generated by the context recognition unit. In some examples, the context recognition unit may generate user context information or update user context information stored in the black board unit by further using at least one of user context information and user profile previously stored in the black board unit. In some examples, the black board unit may store sensor data and/or user context information in a time-series, spatial, or spatio-temporal manner.

In some other embodiments, a user modeling method is described. An exemplary user modeling method may be performed under the control of a computing device. The user modeling method includes receiving sensor data from a user device of a user; Generating user context information by using the sensor data; Storing the generated user context information in a blackboard data structure in a memory; And managing a user model including a plurality of user profiles. Managing the user model may include evaluating at least one of a plurality of user profiles using user context information stored in a blackboard data structure of a memory.

According to some implementations, a computer-readable storage medium storing a computer program for modeling a user is described. In some examples, when the computer program stored on the computer-readable storage medium is executed by the computing device, causing the computing device to: receive sensor data from the user's user device; Generating user context information by using the sensor data; Storing the generated user context information in a blackboard data structure of a memory; And evaluating at least one user profile by referring to at least one context information stored in the blackboard data structure.

The above brief summary and description of the effects are merely illustrative and are not intended to limit the technical matters intended in the present disclosure. By referring to the following detailed description and the accompanying drawings, in addition to the above-described exemplary embodiments and technical features, additional embodiments and technical features may be understood.

The above-described and other features of the present disclosure will become sufficiently apparent from the following description with reference to the accompanying drawings. These drawings illustrate only a few embodiments according to the present disclosure, and therefore, with the understanding that they should not be regarded as limiting their scope, the present disclosure is described in more detail and detail through the use of the accompanying drawings. Will be.
1 illustrates an example environment for user modeling in accordance with at least some embodiments of the present disclosure.
2 is a block diagram illustrating a user modeling apparatus according to at least some embodiments of the present disclosure.
3 is an example of sensor data that may be collected according to at least some embodiments of the present disclosure.
4 is an example of user context information that may be generated according to at least some embodiments of the present disclosure.
5 is an example of a user model including a user profile that can be managed according to at least some embodiments of the present disclosure.
6 is a flow diagram illustrating an exemplary process for user modeling in accordance with at least some embodiments of the present disclosure.
7 depicts a product of an exemplary computer program that may be used to model a user in accordance with at least some embodiments of the present disclosure.
8 illustrates a general purpose computing device that may be used to implement a system for user modeling in accordance with at least some implementations of the present disclosure.
9 is a block diagram illustrating a user device that may be used with respect to user modeling according to at least some embodiments of the present disclosure.

Hereinafter, embodiments and embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art may easily implement the present disclosure. However, the present application may be implemented in various different forms and is not limited to the embodiments and examples described herein.

The present disclosure generally relates to a method, an apparatus, a computer-readable storage medium, and a program stored therein for modeling a user.

In this disclosure, “context” is generally any information that can be used to characterize the context of an entity (eg, a person, place, or object considered in connection with the interaction between a user and an application). Refers to. In this respect, "user context" refers to the context in which the target entity is a user (person), and "user context information" is understood to include various types of information that can be used to characterize the user's situation. Can be. For example, the type of user context information is the computing context of the device associated with the user (e.g., network connection, memory availability, processor type, CPU contention, etc.), user context (e.g., name, gender, age). Personal information such as location, behavior, friends around you, information related to social networks, situations, etc.), physical context (e.g., lighting, noise level, traffic, etc.), temporal context (year, month, day, time, season, etc.), It may include their history and the like.

Meanwhile, in the present disclosure, "user model" refers to an integrated information model that can characterize a user, and "user profile" is an individual element of a user model, and refers to data that can characterize individual characteristics of a user. .

1 illustrates an exemplary environment 100 for user modeling in accordance with at least some embodiments of the present disclosure. The exemplary environment 100 may include a user device 110, a network 120, and a server 130 of a user. Additionally, the exemplary environment 100 may include one or more service servers 140.

In the environment 100, a user may use various types of user devices 110 such as user devices 110-1, 110-2, 110-3, ..., 110-n. The user device 110 may collect various sensor data in association with the user's situation. The user device 110 is a device capable of communicating with the server 130 through the network 120, such as a desktop computer, a laptop computer, a smart phone, a tablet computer, a mobile phone, a personal portable terminal (PDA), a personal media play device, Small form factor portable (mobile) electronic devices such as personal headset devices, special purpose devices (eg, e-book readers), or fusion devices including any of the above functions. In some examples, user device 110 may include one or more sensors that generate sensor data. These sensors may be located inside or outside the user device 110. The sensor may include, for example, one or more sensors such as GPS, gyroscope, microphone, temperature sensor, barometer, accelerometer, illuminance sensor, timer, battery condition meter, WiFi module, display condition meter, camera, and the like. In some additional examples, the user device 110 may receive sensor data from an external sensor device 114 installed in a space associated with the user.

The user device 110 may transmit the collected sensor data to the server 130 through the network 120. Depending on the implementation, the user device 110 may transmit sensor data at predetermined time intervals or transmit in real time (ie, immediately when sensor data is acquired). The network 120 includes a personal area network (PAN), a local area network (LAN), a wide area network (WAN), a cable network, a satellite network, a cellular network, a Global System for Mobile Communications (GSM) network, and a Code Division Multiple (CDMA) network. Access) network, Long Term Evolution (LTE) network, Long Term Evolution-Advanced (LTE-A) network, Interoperability for Microwave Access (WiMax) network, Wireless Fidelity (Wi-Fi) network, etc. .

The server 130 is a standalone server such as a single computing device, a server farm including a plurality of servers, a distributed network, a cloud computing configuration and other data transmission and reception functions, any data identification function and data processing functions. It can be a computing device. The server 130 may receive sensor data from at least one of the user device 110, that is, the user devices 110-1, 110-2, 110-3, ..., 110-n. In some examples, the server 130 may obtain at least one of time information associated with sensor data along with the sensor data, for example, information about a time when the sensor data is acquired from the sensor or information about a time when the sensor data is received, and spatial information. have. In some examples, the server 130 may acquire new sensor data by performing an additional operation using the received sensor data. In this way, the server 130 may obtain sensor data associated with the user's user device by receiving sensor data from the user device 110 or generating new sensor data using the sensor data. In some examples, the server 130 may store the acquired sensor data on a black board in a time-series, spatial, or spatio-temporal manner.

The server 130 may generate user context information using sensor data. In some examples, server 130 may calculate user context information using one or more sensor data. A specific example of the calculation and update of user context information will be described later. The server 130 may store the generated user context information in the black board. The black board refers to a data structure in one or more memories, and provides a space in which a plurality of independent elements in the server 110 can work in common, and a plurality of independent elements can communicate with each other through the black board. The sensor data and/or user context information may be stored in a blackboard in a time-series, spatial, or spatio-temporal manner.

The server 130 may manage a plurality of user models, where each user model relates to a corresponding user. The user model may include a plurality of user profiles. The server 130 may evaluate at least one of a plurality of user profiles by using user context information stored in the black board. The evaluation of such a user profile may be performed whenever sensor data is collected, whenever user context information is evaluated, or at a predetermined period (eg, once a day), as required. In some examples, server 130 may store the evaluated user profile in a blackboard.

In some examples, the server 130 may generate user context information using, for example, at least one of sensor data, user context information, and user profile stored in a blackboard. In addition, in some examples, the server 130 may modify or update user context information or user profile in the blackboard by using at least one of sensor data, user context information, and user profile stored in the blackboard.

In some examples, the server 130 may classify a user model based on user context information and/or a user profile. By classifying the user models in this way, when the server 130 evaluates the user profile, it is possible to easily search for a similar user model having a user profile similar to the evaluated user profile. In addition, in this example, the server 130 may generate user context information by using information on the searched similar user model. Such a similar user model may be useful for modifying a user model, and in guessing a user profile when the user model is not sufficiently formed.

The server 130 may transmit at least some of the user context information to the user device 110. In some examples, the server 110 may transmit a message including user context information to the user device 110, and the user device 110 may display the received message. The message may include various types of messages, such as an SMS message, a messenger message, or a push message through a system or application application. In some examples, the user device 110 may use the received user context information to update the user's current user context information. The update of the current user context information may be performed by a service running in the system background of the system of the user device 110.

In some examples, one or more applications may be installed on the user device 110, and each application may provide a specific service to a user, and may have a function of using user context information. When the application is executed, the user device 110 may be connected to the service server 140 corresponding to each application through the network 120. The user device 110 may broadcast the corresponding user context information so that the user context information received from the server 130 can be used in a service related to an application executed on the user device 110. When user context information is broadcast, for example, the service server 140 may select and/or receive user context information as required, and use the selected and/or received user context information to provide services appropriate to the user. Can provide.

In some additional examples, the server 130 may generate recommendation information to the user and transmit it to the user device based on some user profile and/or user context information of the user model. In this example, the user device 130 may receive and display recommended information.

2 is a block diagram illustrating a user modeling apparatus 200 according to at least some embodiments of the present disclosure. The user modeling device 200 may be, for example, an example of the server 110 illustrated in FIG. 1. Therefore, the user modeling device 200 is a standalone server such as a single computing device, a server farm including a plurality of servers, a distributed network, a cloud computing configuration and other data transmission and reception functions, a data identification function, and a data processing function. It may be any computing device equipped with.

In some embodiments, the user modeling apparatus 200 may include a sensor data collection unit 210, a context recognition unit 220, a black board unit 230, and a user model inference unit 240. The sensor data collection unit 210, the context recognition unit 220, and the user model inference unit 240 are independent elements and are connected to the black board unit 230 so that a common operation is possible. In an additional embodiment, the user modeling apparatus 200 may further include a user management unit 250. Although each component of FIG. 2 is shown as a separate component, various components may be separated into additional components, combined into fewer components, or removed without departing from the scope of the disclosed subject matter. Those skilled in the art will understand that each function and/or operation of a component may be implemented individually and/or collectively, by hardware, software, firmware, or any combination thereof.

The sensor data collection unit 210 may be configured to acquire sensor data associated with at least one user device of a user. In some embodiments, the sensor data collecting unit 210 may include a sensor data receiving unit 212 and a sensor data generating unit 214. The receiver 212 may be configured to receive sensor data from a user device of a user, and here, the received type of sensor data may be referred to as a first type of sensor data. The receiving unit 212 may receive sensor data in real time by transmitting sensor data in response to the user device acquiring sensor data, or may receive sensor data every predetermined period. The sensor data received by the receiver 212 is, for example, by one or more physical sensors such as GPS, gyroscope, microphone, temperature sensor, barometer, accelerometer, illuminance sensor, timer, battery condition meter, WiFi module, and display condition meter. It may include logical sensor data recognized from acquired physical sensor data and/or data such as images, messages, and images. A specific example of sensor data received from the user device will be described in more detail below with reference to FIG. 3.

The generation unit 214 may generate new sensor data by performing an additional operation using the first type of sensor data, where the sensor data generated by the generation unit 214 is referred to as the second type of sensor data. Can be referred to. For example, when text that satisfies a specific condition is included in the SMS message and image, the user device may extract the corresponding text data, and the receiving unit 212 may receive the extracted text data, and the generation unit 214 May detect meaningful information such as payment information from the extracted text data. In another example, the user device may obtain voice data from a microphone. In this example, the receiver 212 may receive analog voice data and the generator 214 may recognize text data from the voice data, or the receiver 212 receives text data recognized from the voice data and the generator ( 214) may extract meaningful text data from the text data. In some examples, the sensor data collection unit 210 may classify and organize the sensor data according to, for example, a temporal and/or spatial criterion, so that the black board unit 230 may store the sensor data in time series, spatially, or spatiotemporally.

The context recognition unit 220 may be configured to generate user context information by using sensor data acquired by the sensor data collection unit 210. This user context information may be generated in response to receipt of sensor data. The context recognition unit 220 may calculate user context information based on sensor data. As a non-limiting example, the context recognition unit 220 may obtain the user's context by dividing the user's context information into three criteria, namely, time information, location information, and activity information. These three criteria are not independent but are related to each other to represent the user's context indicating the state or context of the user of the user device at a specific time. For example, the fact that a user does work (activity information) at a company (location information) from 9 am to 1 pm (time information) indicates a specific context for that user's time zone. For example, among sensor data, time data becomes the basis for calculating time information in the user context, and GPS data corresponding to specific time data becomes the basis for calculating the location information in the user context. When the corresponding WiFi data indicates that WiFi is being used, a context in which the user is using the mobile terminal 110 can be derived through WiFi. On the other hand, time information among the user context information can be classified according to various criteria, for example, early morning (midnight to 6 am), morning (6 am to noon), and afternoon (noon to 6 pm) for each time zone. And evening (from 6 pm to midnight), or every hour, or according to the properties and/or functions of the service provided by the application. Among the user context information, the location information can be classified into a place where the user device user is frequently located (e.g., home, company, etc.) and a place with a relatively low frequency of the location, or by a specific location based on GPS data. , This can also be classified into a necessary criterion according to the properties and/or functions of the service provided by the corresponding application. Among the user context information, activity information may be classified into large categories (eg, while moving, during work, while resting, etc.) or by specific activities (eg, while walking, while running, while sleeping, etc.). A specific example of the activity information will be described in more detail in FIG. 4 below.

The context recognition unit 220 may store the generated user context information in the black board unit 230. For example, the user context information may be stored in time series, spatially, or spatiotemporally in the blackboard unit 230. The black board unit 230 has a black board data structure. The black board unit 230 may store user context information generated by the context recognition unit 220 in this black board data structure. Additionally, the black board unit 230 may also store sensor data in the black board data structure. For example, if the user is at home, at work, or traveling, the same behavior may indicate a different context. In this regard, the black board unit 230 may classify and store sensor data and context information according to a space unit and a time series.

In some embodiments, the context recognition unit 220 may correct the calculated user context information by further using the user context information stored in the black board unit 230 when generating user context information based on sensor data. have. For example, when a user moves on a bus during the rush hour, the context recognition unit 220 may recognize the context of “on the bus to work”, and this may be stored together with the time information in the black board unit 230. have. Thereafter, the user may ride the bus at substantially the same rush hour, but may move very slowly due to traffic congestion. The context recognition unit 220 may recognize that it is "walking" due to a generally very slow speed, but may correct that it is moving on a bus by referring to context information stored in the same time zone on the black board.

The user model inference unit 240 may manage a plurality of user modules including a user model 242 and a user model 244. The user model 242 may include a plurality of user profiles. In some examples, a plurality of user profiles may be classified into one or more categories. The category may include, for example, basic information of the user, eating/dining out, moving, repetitive daily information, music, movies, and the like. Some of the categories may include at least one user profile (preferred profile) indicating the user's preference. User profiles include, for example, home location, company location, gender, frequented areas, frequented places, average ambient noise level, average meal time, favorite food, favorite restaurant, commuting time, average daily steps, average stride length, favorite It may be about various individual elements that can represent the user's characteristics, such as music, favorite singers, average time to listen to music per day, preferred volume, and favorite movies.

In some embodiments, the user model inference unit 240 may evaluate at least some of the plurality of user profiles by using the user context information generated by the context recognition unit 220. The user model inference unit 240 may evaluate the user profile whenever user context information is determined or at a predetermined period (eg, once a week or once a day). In some embodiments, the user model inference unit 240 may evaluate at least some of the plurality of user profiles by reading user context information stored in the black board unit 230. For example, when the context that the user is "going to work by subway" is recognized by the context recognition unit 220, the user model inference unit 240 relates to a means of transportation used by the user, a subway station, commuting time, and attendance time. Information on user profiles can be calculated, accumulated, and stored. A specific example of a user model and a user profile will be described in detail in FIG. 5 below.

In some embodiments, the context recognition unit 220 may correct the calculated user context information by further using the user profile 236 when generating user context information based on sensor data. For example, the sensor data collection unit 210 may acquire sensor data on the noise level, and the context recognition unit 220 may recognize that it is “noisy” based on the sensor data, but the average ambient noise or at home With further reference to a user profile such as noise, when the noise level shown in the corresponding user profile is higher than the noise level shown in the sensor data, the user context according to the sensor data may be determined as "quiet".

In some examples, the receiving unit 212 receives a plurality of sensor data from a plurality of user devices, and the context recognition unit 220 uses a plurality of sensor data from such a plurality of user devices, thereby inferring (generating) user context information. ) Can be improved. In one example, when a user uses a smartphone and a tablet computer at the same time, the receiving unit 212 may receive various sensor data from the smartphone and the tablet computer. Thereafter, the context recognition unit 220 may use the received sensor data to distinguish between an action performed by the smartphone and an action performed by the tablet computer, and then, for example, "in working", "in parenting", etc. You can decide on a more specific context. The context recognition unit 220 may make a more accurate determination by further using the user profile 236 stored in the black board unit 230 for this determination. In another example, the receiving unit 212 may receive barometric pressure sensor data from the user's smartphone and desktop, and the context recognition unit 220 is based on a relative difference between the values of the barometric pressure sensor data from the smartphone and the desktop. You can determine your current altitude.

In an additional example, the user management unit 250 may be configured to transmit user context information generated by the context recognition unit 220 and stored in the black board unit 230 to the user device. This user context information may be in the form of a message that may appear on the display of the user device or a form of a system message available in the system. User context information transmitted to the user device of the user may be broadcasted from the user device of the user after that, and may be provided to be used in a service related to an application executed on the user device. In some examples, the user management unit 250 may further transmit a user profile stored in the black board unit 230.

In an additional example, the user management unit 250 may be configured to generate recommendation information for a user based on user context information and a user profile of a user model. The recommendation information may be the recognized user context information, and the blackboard user management unit 250 may determine a correlation between the user context information and a user profile, and generate recommendation information based on this. In one example, when the user context information recognized by the context recognition unit 220 is "going to work by subway", the user management unit 250 refers to the black board unit 230 and is at the same time as the recognized context. It is determined that the context of "listening to music" is the most frequently recognized history, and based on this determination, the user profile of the user model of "music that was listened a lot while going to work" can be determined, and the corresponding data is recommended information Can be determined as The user management unit 250 may transmit the determined recommendation information to the user device of the user.

As described above, according to the present disclosure, by storing at least the user context information in the black board data structure, it is possible to further improve the accuracy of determining the user context information and the characteristics of the user. In addition, by managing the user model, more effective recommendation information can be provided to the user by using the user model of another user having a similar life pattern.

3 is an example of sensor data that may be collected according to at least some embodiments of the present disclosure. Table 300 shown in FIG. 3 illustrates the types of sensor data available in Android and ioS, which are two representative types of operating systems for user devices. However, it will be appreciated that the sensor data is not limited to the type illustrated in FIG. 3, and other types of data may be used.

4 is an example of user context information that may be generated according to at least some embodiments of the present disclosure. The user context information 400 of FIG. 4 categorizes the user's activities into six categories: MOVE (movement), WORK (task), REST (rest), PLAY (play), EAT (meal, etc.), and WATCH (viewing). They were classified, and specific activity information for each category was subdivided. For example, the user's context information about MOVE may be calculated using GPS data and accelerometer data among sensor data. Those of ordinary skill in the art will understand that the category of user context information is not limited thereto, and may include more various categories.

5 is an example of a user model including a user profile that can be managed according to at least some embodiments of the present disclosure. The user model 500 of FIG. 5 is divided into various categories such as, for example, basic information, eating/dining, moving, daily routine, music, and movies, and each category includes one or more user profiles. As shown in FIG. 5, some user profiles may be fixed information obtained by receiving specific information from the user or extracting from accumulated data, such as "home location", "company location", "gender", etc. have. Some other user profiles can be calculated in the manner of cumulative calculations, such as "average lunch time", "work time", "work time", "work time", "sleep time", "average daily steps". have. Some other user profiles include, for example, one or more, such as "Favorite Areas", "Favorite Places", "Favorite Vehicles", "Frequently Used Subway Stations", "Favorite Singers", "Favorite Songs", etc. It can be managed by accumulating and managing data, and selecting one of one or more managed data. Some other user profiles may be data updated by user context information or sensor information, such as "recently viewed movies". It will be well understood by those skilled in the art that the user profile is not limited to the features shown in FIG. 5, and may include other types of user profiles, more detailed user profiles, or more comprehensive user profiles that can be expressed to characterize the user. .

6 is a flow diagram illustrating an exemplary process 600 for user modeling in accordance with at least some embodiments of the present disclosure. For example, the process 600 may be performed under the control of a computing device such as the server 130 of FIG. 1 and the user modeling device 200 of FIG. 2. The process 600 shown in FIG. 6 may include one or more actions, functions, or actions as illustrated by blocks S610, S620, S630, and/or S640. In a further example, process 600 may further include one or more actions, functions, or actions as illustrated by block S650. On the other hand, the schematic operations illustrated in FIG. 6 are provided only as examples, and some of the operations may be optional, may be combined into fewer operations, or may be extended to additional operations without departing from the essence of the disclosed embodiment. I can. Process 600 may begin at block S610 of obtaining sensor data.

In block S610, the computing device may receive sensor data from at least one user device of the user. The reception of such sensor data may be performed in real time or every predetermined period. In some additional examples, the computing device may receive sensor data from the user's user device, and use the received sensor data to generate new sensor data suitable for generating contextual information. Process 600 may continue from block S610 to block S620 of generating user context information.

In block S620, the computing device may generate user context information using sensor data. Generation of such user context information may be performed in response to receipt of sensor data. In some examples, the computing device can calculate user context information based on sensor data. For example, the computing device may determine context information of the user based on user information such as time information, location information, and activity information. Process 600 may continue from block S620 to block S630 of storing user context information in a blackboard data structure.

In block S630, the computing device may store the generated user context information in the blackboard data structure of the memory. Such user context information may be stored in time series, spatially, and spatiotemporally. The blackboard data structure may provide a space in which a plurality of independent elements in the computing device can communicate with each other through the blackboard and work together. The process 600 may continue from block S630 to block S640 for managing the user model.

In block S640, the computing device may manage the user model using the generated user context information. The user model may include a plurality of user profiles, and the computing device may evaluate at least one of the plurality of user profiles by using the user context information generated in block S630. The evaluation of the user profile may be performed whenever user context information is determined or at a predetermined period (eg, once a week or once a day).

Process 600, in its repetitive performance, may have additional features in accordance with the present disclosure. In block S620, in generating the user context information, the computing device may further use other user context information and/or a user profile stored in the blackboard data structure. In block S630, the computing device may further store the sensor data and the evaluated user profile in the blackboard data structure. In block S640, the computing device may further refer to various pieces of information stored in the blackboard data structure in managing the user model.

In a further example, process 600 may lead to block S650 of transmitting user context information to the user device at block S640. In block S650, the computing device may be configured to transmit user context information generated in block S620 and stored in block S630 to the user device. This user context information can be transmitted in various types of messages. Thereafter, the user context information may be broadcast by the user device.

In an additional example, the process 600 may further perform an operation of generating user recommendation information in the user device after block S640. The computing device may generate recommendation information for a user based on the recognized user profile and at least one user profile of the user model. The computing device may transmit the generated user recommendation information to the user device.

7 depicts an exemplary computer program product 700 that may be used to model a user in accordance with at least some embodiments of the present disclosure. An exemplary embodiment of an exemplary computer program product is provided using a signal bearing medium 710. In some embodiments, the signal bearing medium 710 of one or more computer program products 700 may include a computer-readable medium 730 and/or a recordable medium 740.

The instructions 720 included in the signal bearing medium 710 may be executed by a computing device such as the server 130 and the user modeling device 200. When the instruction 720 is executed, one or more instructions for causing the computing device to receive sensor data from the user's user device; One or more instructions for generating user context information using the sensor data; Storing the generated user context information in a blackboard data structure of a memory; And at least one of one or more commands for evaluating at least one user profile with reference to at least one context information stored in the blackboard data structure.

The foregoing description of the present application is for illustrative purposes only, and those of ordinary skill in the art to which the present application pertains will be able to understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present application. Therefore, it should be understood that the embodiments described above are illustrative and non-limiting in all respects. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as being distributed may also be implemented in a combined form.

8 illustrates a general purpose computing device 800 that may be used to implement a system for user modeling, in accordance with at least some embodiments described herein. In this example, the components of computing device 800 may be arranged or configured for a system. In a very basic configuration 802, computing device 800 typically includes one or more processors 804 and system memory 806. Memory bus 808 may be used for communication between processor 804 and system memory 806.

Depending on the required configuration, the processor 804 may be of any type including, but is not limited to, a microprocessor (μP), a microcontroller (μC), a digital signal processor (DSP), or any combination thereof. Processor 804 may include one or more levels of caching, such as level 1 cache 810 and level 2 cache 812, processor core 814 and registers 816. The exemplary processor core 814 may include an arithmetic logic unit (ALU), a floating point unit (FPU), a digital signal processing core (DSP), or any combination thereof. The exemplary memory controller 818 may also be used with the processor 804, or, in some implementations, the memory controller 818 may be an internal component of the processor 804.

Depending on the configuration required, system memory 806 may be of any type, including, but not limited to, volatile memory (such as RAM), nonvolatile memory (such as ROM, flash memory, etc.), or any combination thereof. System memory 806 may include an operating system 820, one or more applications 822, and program data 824. The application 822 may include instructions 826 that may be arranged to perform the functions described herein, including the functions described in FIG. 2 and/or with respect to the process of FIG. 6. Program data 824 may include data 828 that may be used to implement instructions 826, such as user context information stored in a blackboard data structure. In some examples, application 822 may be arranged to operate with program data 824 on operating system 820 to implement the instructions described herein.

Computing device 800 may have additional features or functionality, and additional interfaces to facilitate communication between the basic configuration 802 and any required device and interface. For example, the bus/interface controller 830 may be used to facilitate communication between the basic configuration 802 and one or more data storage devices 832 over the storage interface bus 834. The data storage device 832 may be a removable storage device 836, a non-removable storage device 838, or a combination thereof. Examples of removable and non-removable storage devices include magnetic disk devices such as flexible disk drives and hard disk drives (HDD), compact disk (CD) drives, or optical disks such as digital multifunction disk (DVD) drives, to name a few. Drives, solid state drives (SSDs), and tape drives. Exemplary computer storage media may include volatile and nonvolatile, 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. have.

System memory 806, removable storage device 836, and non-removable storage device 838 are examples of computer storage media. Computer storage media include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital multifunction disk (DVD) or other optical storage device, magnetic cassette, magnetic tape, magnetic disk storage device or other magnetic storage device, or Including, but not limited to, any other medium that can be used to store desired information and that can be accessed by computing device 800. Any such computer storage media may be part of computing device 800.

Computing device 800 facilitates communication from various interface devices (e.g., output device 842, peripheral interface 844, and communication device 846) to basic configuration 802 via bus/interface controller 830 It may also include an interface bus 840 to enable. An exemplary output device 842 includes a graphics processing unit 848 and an audio processing unit 850, which may be configured to communicate with various external devices such as a display or speaker through one or more A/V ports 852. I can. Exemplary peripheral interface 844 includes serial interface controller 854 or parallel interface controller 856, which is an input device (e.g., keyboard, mouse, pen, voice input) via one or more I/O ports 858. Devices, touch input devices, etc.) or other peripheral devices (eg, printers, scanners, etc.). The exemplary communication device 846 includes a network controller 860, which may be arranged to facilitate communication with one or more other computing devices 862 over a network communication link through one or more communication ports 864. .

The network communication link may be an example of a communication medium. Communication media may typically be embodied by 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 may include any information delivery medium. A “modulated data signal” may be a signal that has one or more of its characteristics set or changed in such a way as to encode information within the signal. As a non-limiting example, communication media include wired media such as a wired network or direct wired connection, and wireless media such as acoustic, radio frequency (RF), microwave, infrared (IR) and other wireless media. Can include. The term computer-readable medium as used herein may include both storage media and communication media.

Computing device 800 is a mobile phone, personal data assistant (PDA), personal media player device, wireless web-watch device, personal headset device, special purpose device, or a hybrid device including any of the above functions. It may be implemented as part of a small-form factor portable (or mobile) electronic device such as a device. Computing device 800 may also be implemented as a personal computer including both laptop computer and non-laptop computer configurations.

9 is a block diagram illustrating a user device 900 that may be used with respect to user modeling in accordance with at least some embodiments of the present disclosure. The user device 900 may be, for example, an example of the user device 130 of the user shown in FIG. 1. Accordingly, the user device 900 is a desktop computer, a laptop computer, a smart phone, a tablet computer, a mobile phone, a personal digital assistant (PDA), a personal media play device, a personal headset device, a specific-purpose device (eg, an e-book reader), Or a small form factor portable (mobile) electronic device such as a fusion device including any of the above functions, but is not limited thereto.

In some embodiments, the user device 900 may include a sensor unit 910, a process 920, a memory 930, and a communication unit 940. The sensor unit 910 may be configured to acquire sensor data. The sensor data may include at least one of physical sensor data and logical sensor data. In some examples, the sensor unit 910 may include one or more sensors installed inside or outside the user device 900. The sensor may include, for example, one or more devices such as GPS, gyroscope, microphone, temperature sensor, barometer, accelerometer, illuminance sensor, timer, battery condition meter, WiFi module, display condition meter, camera, and the like. In some other examples, the sensor unit 910 may receive sensor data from an external device, for example, an external sensor device.

In some embodiments, the memory 930 may store one or more user applications including a user context management application 932 and a first user application 936 and a second user application 938. The user context management application 932 may operate between an operating system (OS) of the user device 900 such as middleware and a final application such as user applications 936, 938, ..., for example. Accordingly, the user context management application 932 may be executed as a background process in which the user device 900 operates. When the user context management application 932 stored in the memory 930 is executed by the processor 920, the user device 900 may cause the user device 900 to perform one or more operations according to the present disclosure.

The communication unit 940 may receive user context information for the current user from the server, and the processor 920 may cause the user context management application 932 to update the current user status according to the received user context information. . In some embodiments, the processor 920 may cause the user context management application 932 to broadcast the received user context information to all user applications 936, 938, .... According to a request from another external server connected through the communication unit 940 and associated with each user application (936, 938, ...), the processor 920 causes the corresponding user application (eg, 936) to cause the communication unit 940 User context information can be transmitted through.

As described above, the subject to be claimed in the present disclosure was examined in detail. The subject matter claimed in this disclosure is not limited in scope to the specific implementations described above. For example, in some implementations, it may be in the form of hardware that is operably used on a device or a combination of devices, in other implementations it may be implemented in the form of software and/or firmware, and in another implementation, a signal bearing medium, It may include one or more articles such as storage media. Here, the storage medium, such as a CD-ROM, a computer disk, or a flash memory, is an instruction capable of causing execution of a corresponding processor according to the above-described implementation when executed by a computing device such as a computing system, a computing platform, or other system. Can be saved. Such computing devices may include one or more processing units or processors, one or more input/output devices such as displays, keyboards, and/or mice, and one or more memory such as static random access memory, dynamic random access memory, flash memory and/or hard drive. It may include.

On the other hand, whether to implement the system as hardware or software is a design choice that generally represents a cost-effective tradeoff. In this disclosure, there are various means (e.g., hardware, software and/or firmware) that can be influenced by processes, systems, and other technologies, and the preferred means is that processes and/or systems and/or other technologies are used. It will change according to the context of being. For example, if the implementer decides that speed and accuracy are paramount, the implementer can primarily choose hardware and/or firmware means, and if flexibility is paramount, the implementer can choose primarily software implementation; Or, as another alternative, the implementer may opt for some combination of hardware, software and/or firmware.

In the foregoing detailed description, various embodiments of an apparatus and/or process have been described through block diagrams, flow charts, and/or other examples. Such block diagrams, flow charts, and/or other examples will include one or more functions and/or operations, and those skilled in the art will understand that each function and/or operation in the block diagrams, flow charts, and/or other examples is hardware, software, firmware, Or it will be appreciated that they may be implemented individually or collectively by any combination thereof. In one embodiment, some parts of the object described in the present disclosure may be implemented through an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), or other form of integration. In contrast, some aspects of embodiments of the present disclosure include one or more computer programs running on one or more computers (e.g., one or more programs running on one or more computer systems), one or more programs running on one or more processors ( For example, one or more programs running on one or more microprocessors), firmware, or substantially any combination thereof, may be implemented in an integrated circuit wholly or partially evenly, and writing code for software and/or firmware And/or the design of the circuit is within the skill of those skilled in the art in light of the present disclosure. In addition, those skilled in the art will understand that the mechanisms of the object of the present disclosure can be distributed to various types of program products, and the example of the object of the present disclosure is applied irrespective of the specific type of signal bearing medium used to actually perform the distribution. Will understand.

While certain exemplary techniques have been described and illustrated herein using various methods and systems, those skilled in the art can understand the possibility of substitution with various other modifications or equivalents without departing from the claimed subject matter. Additionally, many modifications can be made to adapt a particular situation to the claimed subject's teachings without departing from the central concept described herein. Thus, while claimed subject matter is not limited to the specific examples disclosed, it is intended that such claimed subject matter may also include all embodiments falling within the scope of the appended claims and their equivalents.

Throughout this disclosure, when a part is said to be "connected" with another part, this includes not only the case that it is "directly connected", but also the case that it is "electrically connected" with another element interposed therebetween. do. In addition, throughout the present disclosure, when a member is said to be positioned "on" another member, this includes not only a case where a member is in contact with another member, but also a case where another member exists between the two members. Furthermore, throughout the present disclosure, when a certain part "includes" a certain component, it means that other components may be further included, rather than excluding other components, unless specifically stated to the contrary. The terms "about," "substantially", etc. of the degree used in the present disclosure are used at or close to the numerical value when manufacturing and material tolerances specific to the stated meaning are presented, and to aid understanding of the present application In order to avoid unreasonable use by unscrupulous infringers of the stated disclosures, either exact or absolute figures are used.

The scope of the present disclosure is indicated by the claims to be described later rather than the detailed description, and all changes or modified forms derived from the meaning and scope of the claims, and the concept of equivalents thereof should be construed as being included in the scope of the present disclosure. do.

Claims (13)

A sensor data collection unit configured to acquire sensor data associated with at least one user device of a user;
A context recognition unit configured to generate user context information by using the sensor data;
A blackboard unit having a blackboard data structure and configured to store the generated user context information in the blackboard data structure;
A user model inference unit configured to manage a user model including a plurality of user profiles and to evaluate at least one of the plurality of user profiles using the user context information
Including,
The user model inference unit searches for a user model of another user having a correlation with the user model of the user, based on the evaluated at least one user profile, and
The context recognition unit is configured to generate user context information or update user context information stored in the black board unit based on the searched user model. The method of claim 1,
The context recognition unit is configured to generate user context information by further using the user context information stored in the black board unit or to update the user context information stored in the black board unit. The method of claim 1,
The context recognition unit is configured to generate user context information by further using at least one of the plurality of user profiles of the user model managed by the user model inference unit. The method of claim 1,
The black board unit is configured to store the sensor data acquired by the sensor data collection unit together with user context information in a black board data structure The method of claim 4,
The black board unit is configured to store at least one of sensor data and user context information in a time-series, spatial, or spatio-temporal manner. delete The method of claim 1,
The plurality of user profiles are classified into one or more categories,
Wherein the user model inference unit is configured to evaluate at least one preference profile for each of the one or more categories. The method of claim 1,
User management unit configured to transmit user context information stored in the blackboard unit to the at least one user device
Including more,
The at least one user device broadcasts the corresponding user context information so that the transmitted user context information is available in a service associated with an application executed in the at least one user device. The method of claim 1,
Based on the user context information stored in the blackboard unit and at least one user profile of the user model, user recommendation information related to the user context information generated by the context recognition unit is generated, and the generated user recommendation information is user User management unit configured to send to
User modeling device further comprising a. As a user modeling method performed under the control of a computing device,
Receiving sensor data from at least one user device of a user;
Generating user context information by using the sensor data;
Storing the generated user context information in a blackboard data structure of a memory; And
Managing a user model including a plurality of user profiles
Including,
The step of managing the user model includes evaluating at least one of the plurality of user profiles using user context information stored in the blackboard data structure of the memory,
After the user modeling method evaluates at least one of the plurality of user profiles,
Searching for a user model of another user having a correlation with the user model of the user based on the evaluated at least one user profile; And
Generating user context information or updating user context information stored in the blackboard data structure based on the retrieved user model
Containing, user modeling method. The method of claim 10,
The generating of the user context information may further include generating user context information by further using at least one of user context information and at least one user profile from among the plurality of user profiles previously stored in the blackboard data structure of the memory. Including, user modeling method. The method of claim 10,
Generating user recommendation information for recognized user context information based on user context information previously stored in the blackboard data structure and at least one user profile evaluated of the user model.
User modeling method further comprising a. A computer readable storage medium storing a computer program for modeling a user, wherein when the computer program is executed by a computing device, the computing device causes the computer program to:
Receiving sensor data from at least one user device of a user;
Generating user context information by using the sensor data;
Storing the generated user context information in a blackboard data structure of a memory; And
An operation of evaluating at least one user profile by referring to at least one context information stored in the blackboard data structure
To perform,
In addition, the computer program, after evaluating at least one of the plurality of user profiles, the computing device,
Searching for a user model of another user having a correlation with the user model of the user based on the evaluated at least one user profile; And
Generating user context information or updating user context information stored in the blackboard data structure based on the retrieved user model
A computer-readable storage medium to perform.

Images