Method and apparatus for recommending content by subdividing users on basis of user data

Abstract

The present specification relates to a system comprising a first device, a second device, and a server, wherein: the first device may acquire user information and transmit same to the server; the second device may provide content to a user on the basis of information received from at least one of the server and the first device; and the server may map the user to at least one life pattern group by acquiring life pattern information of the user from the first device, map the user to at least one log pattern group by acquiring log information of the user from the second device, generate a user grid on the basis of the life pattern group and the log pattern group to which the user is mapped, acquire recommended content information by comparing the user grid with a reference grid, and provide content to the user by transmitting the recommended content information to the second device.

Description

Method and device for recommending content by segmenting users based on user data

[0001] This specification relates to a method and device for segmenting users and recommending content based on user data. Specifically, the present disclosure relates to a method and device for segmenting users and recommending content based on their lifestyle pattern information and user log information.

[0002] Due to scientific advancement and economic growth, people's average life expectancy is gradually increasing.

[0003] However, due to the aging of the social structure along with the increase in average life expectancy, the proportion of the elderly population is increasing, and among them, the proportion of elderly people living alone is rapidly increasing, and elderly people living alone without being able to live with their families are emerging as a new social issue.

[0004] Elderly people living alone spend most of their time alone, and may not be able to replace their caregivers when sudden health problems or issues arise. The management and supervision of these individuals is difficult to address through human resources alone, and solutions may be needed. Specifically, monitoring and supervision of elderly people living alone can be achieved through sensors, cameras, and other devices designed for their homes.

[0005] In addition, active management and supervision may be necessary to stabilize the lives of elderly people living alone and provide a sense of stability, in addition to passive management and supervision of the elderly living alone. Below, we describe a method of providing services through caregiver toys, taking into account the above-mentioned points.

[0006] This specification relates to a method and device for segmenting users based on user data.

[0007] This specification relates to a method and device for recommending content based on user segmentation.

[0008] This specification relates to a method and device for grouping users based on lifestyle pattern information and user log information.

[0009] The present specification relates to a method and device for performing user segmentation based on user grouping.

[0010] According to one embodiment of the present specification, in a system comprising a first device, a second device, and a server, the first device obtains user information and transmits it to the server, the second device provides content to the user based on information received from at least one of the server and the first device, the server obtains user's lifestyle pattern information from the first device and maps the user to at least one lifestyle pattern group, obtains user's log information from the second device and maps the user to at least one log pattern group, generates a user grid based on the lifestyle pattern group and the log pattern group to which the user is mapped, compares the user grid with a reference grid to obtain recommended content information, and transmits the recommended content information to the second device to provide content to the user.

[0011] In addition, according to one embodiment of the present specification, a method for recommending content based on user data may include a step of receiving user life pattern information acquired by a first device and mapping the user to at least one life pattern group, a step of receiving user log information acquired by a second device and mapping the user to at least one log pattern group, a step of generating a user grid based on the user's mapped life pattern group and log pattern group, a step of comparing the user grid with a reference grid and obtaining recommended content information, and a step of transmitting the recommended content information to the second device to provide content to the user.

[0012] Additionally, the following may be commonly applied:

[0013] According to one embodiment of the present specification, each of the lifestyle pattern group and the log pattern group is composed of three groups, and when determining the lifestyle pattern group and the log pattern group of the first user, the lifestyle pattern group of the first user may be determined based on the Euclidean distance between the lifestyle pattern information parameter of the first user and the center of each lifestyle pattern group, and the log pattern group of the first user may be determined based on the Euclidean distance between the log information parameter of the first user and the center of each log pattern group.

[0014] Additionally, according to one embodiment of the present specification, the lifestyle pattern information parameter may be configured based on at least one of the user's gender, the user's age, the user's disease information, the user's depression scale, the user's sleep scale, the user's thinking scale, the user's meal information, the user's medication information, the user's physical activity information, and the user's social relationship information.

[0015] In addition, according to one embodiment of the present specification, the second device measures user interaction based on content provided by the second device, and a log information parameter is configured based on the interaction, wherein the log information parameter can be configured based on at least one of second device-based gymnastic activity information, second device-based play activity information, second device-based music activity information, second device-based religious activity information, second device-based quiz activity information, and second device-based story activity information.

[0016] Additionally, according to one embodiment of the present specification, the recommended content information may be set to at least one of the first type recommended content, the second type recommended content, the third type recommended content, and the fourth type recommended content based on the user grid.

[0017] In addition, according to one embodiment of the present specification, the first type of recommended content may be content based on changes in the user's lifestyle pattern, the second type of recommended content may be content based on changes in the user's log pattern, the third type of recommended content may be content based on merging changes in the user's lifestyle pattern and changes in the log pattern, and the fourth type of recommended content may be content based on maintaining a reference grid.

[0018] Additionally, according to one embodiment of the present specification, when the user grid and the reference grid are the same, the fourth type of recommended content may be determined as recommended content information.

[0019] This specification has the effect of providing a method for segmenting users based on user data.

[0020] This specification has the effect of providing a method for recommending content based on user segmentation.

[0021] This specification has the effect of providing a method for grouping users based on lifestyle pattern information and log information.

[0022] The present specification has the effect of providing a method for performing user segmentation based on user grouping.

[0023] The effects that can be obtained from this specification are not limited to the effects mentioned above, and other effects that are not mentioned can be clearly understood by those skilled in the art to which the present invention pertains from the description below.

[0024] Figure 1 is a reference diagram for explaining a system for supporting elderly people living alone using artificial intelligence according to the present invention.

[0025] Figure 2 is a reference diagram showing the device configuration according to the present invention.

[0026] FIG. 3 is a reference diagram illustrating a method for performing user segmentation according to the present invention.

[0027] FIG. 4 is a reference diagram for a method for deriving an ideal area based on user segmentation according to the present invention.

[0028] FIG. 5 is a reference diagram for a specific method for recommending content based on user segmentation according to the present invention.

[0029] FIG. 6 is a reference diagram for a method of recommending content for each type based on user segmentation according to the present invention.

[0030] FIG. 7 is a reference diagram for a method for recommending content by priority based on user segmentation according to the present invention.

[0031] Figure 8 is a flowchart of a method for segmenting users and recommending content based on user data.

[0032] The present invention is not limited to the description of the embodiments described below, and it is clear that various modifications may be made without departing from the technical spirit of the present invention. In describing the embodiments, descriptions of technical details widely known in the technical field to which the present invention pertains and not directly related to the technical spirit of the present invention will be omitted.

[0033] Meanwhile, in the attached drawings, identical components are represented by identical symbols.

[0034] In addition, some components in the attached drawings may be exaggerated, omitted, or schematically depicted. This is to clearly explain the gist of the present invention by omitting unnecessary explanations unrelated to the gist of the present invention.

[0035] FIG. 1 is a reference diagram for explaining a support system for the elderly living alone according to the present invention. Referring to FIG. 1, the support system for the elderly living alone is composed of at least one caregiver toy (101), a user management server (103), a reference information server (105), and a user device (107). Here, the user device (107) may be a first device. For example, the first device (107) may be a device owned by a manager who manages the elderly living alone (e.g., a manager of a welfare facility) or a service provider manager who provides a second device (101)-based service (e.g., a second device service manager), but may not be limited thereto. For example, the first device may be a smartphone, a smart pad, a PC, or any other device that transmits and receives data to and from another device or server via a network, and is not limited to a specific form. For convenience of explanation, the user device (107) is referred to as a first device below, but may not be limited to that name.

[0036] In addition, the caregiver toy (101) is a device that operates according to preset information. For example, the caregiver toy (101) is a device that can exchange data by communicating with the first device (107) and at least one server (103, 105) through a network. Specifically, the caregiver toy (101) is a device that can store a plurality of preset operations and operates by obtaining command information from the first device (107) or at least one server (103, 105). In addition, the caregiver toy (101) registers a user through the first device (107). The caregiver toy (101) obtains user status information and provides feedback to the user according to the obtained user status information or user behavior. Here, the caregiver toy (101) is equipped with artificial intelligence and performs learning by using user status information and user behavior information about registered users. As data about the user accumulates, the caregiver toy (101) uses artificial intelligence to create more personalized settings based on user-specific settings to communicate emotionally with the user.

[0037] For example, the caregiver toy (101) has a plurality of input modules. The input modules may refer to an image recognition module (e.g., a camera), a voice recognition module (e.g., a speaker), a sensor (e.g., a motion detection sensor, a pressure detection sensor, a temperature detection sensor, etc.), and other modules capable of acquiring user data, and are not limited to a specific form. Here, the user status information may include the user's image, voice, gesture pattern, body temperature, heart rate, blood pressure, grip strength, and other information measured by the input data acquired through the input module. In addition, for example, the caregiver toy (101) acquires feedback information based on the user's interaction. The feedback information includes the result of measuring whether the user performs an interaction according to a predefined cognitive command using a motion detection sensor, or notifying the user of a voice message and measuring whether the user can reproduce it.

[0038] In this way, the caregiver toy (101) can perform the function of collecting information about the user's biometric information and emotional state while in close contact with the user. Therefore, since the caregiver toy (101) performs the function of recognizing and sympathizing with the user's situation and emotions, it can have the shape of a plush toy that the user can feel familiar with. If the caregiver toy, which is in charge of communicating with the user, is manufactured in the shape of a plush toy, it can alleviate the user's resistance compared to surveillance-type monitoring systems or wearable devices, and can evoke a desire in the user to always have the caregiver toy by his or her side. This may be because reclusive elderly people who live alone have closed their hearts and avoid social contact, and therefore an emotional approach rather than a conventional functional approach is required. For example, the caregiver toy (101) is referred to as the second device (101) below, but this is a name for convenience of explanation and is not limited to a specific form.

[0039] In addition, the user management server (103) exchanges data with at least one of the first device (107), the second device (101), and the reference information server (105) via a network. The user management server (103) may transmit command information to the second device (101) or obtain user status information from the second device (101) to provide analysis information. In addition, the user management server (103) resets the second device (101) or performs other control operations, and is not limited to a specific form.

[0040] Additionally, the reference information server (105) may be configured to transmit external attribute information stored according to preset criteria to the user management server (103). Here, the preset criteria may be defined as criteria pre-classified by an administrator, such as medical data or status categories, and are not limited to a specific form.

[0041] Figure 2 is a reference diagram showing the device configuration according to the present invention.

[0042] FIG. 2 shows a device configuration in which the device (200) corresponds to at least one of the devices and servers described above. That is, each device and server is a device. Referring to FIG. 2, the device (200) includes a control unit (201), a memory (203), and a transceiver unit (205). In addition, the device (200) may include other components and is not limited to a specific form. The control unit (201) is a component that controls each component included in the device (200). The memory (203) is a computer recording medium and includes at least one of a non-volatile storage device and a volatile storage device. The memory (203) stores commands driven by the control unit (201) or records applications, software, and other programs that operate in the device (200). That is, the control unit (201) performs a data exchange operation for providing a service with another device or server based on the information stored in the memory (203).

[0043] Specifically, the control unit (201) processes commands of a computer program by performing basic arithmetic, logic, and input / output operations, and is configured to execute commands received according to program code stored in the memory (201).

[0044] The transceiver (205) is configured to exchange data with other devices or servers via a network and is controlled by the control unit (201). For example, the network method used by the transceiver (205) may not be limited, and wired / wireless communication and other communication methods may be applied. For example, LTE, 5G, or Wi-Fi may be used as wireless communication. In addition, other communication methods may be applied and are not limited to a specific form. In addition, the device (200) may include a GPS (Global Positioning System) module, a camera, various sensors, and other components, through which data is acquired.

[0045] Hereinafter, embodiments of the present specification will be described in detail with reference to the drawings.

[0046] FIG. 3 is a reference diagram illustrating a method for performing user segmentation according to the present invention.

[0047] Referring to FIG. 3, the user management server (103) obtains lifestyle information from the first device (107). The first device (107) is a device owned by a manager who manages a senior citizen living alone (e.g., a manager of a welfare facility) or a service provider manager based on the second device (101) (e.g., a second device service manager), and the lifestyle information is lifestyle information of the corresponding user.

[0048] For example, lifestyle pattern information is information related to the user's daily life, such as meals, sleep, exercise, and other aspects of daily life. As another example, lifestyle pattern information is response information to a questionnaire provided by a user management server (103). Specifically, the user management server (103) provides questionnaire information, as shown in Table 1 below, to the first device (107), and the response information created on the first device (107) is provided as lifestyle pattern information. However, Table 1 below is merely an example for convenience of explanation and is not limited thereto.

[0049] As another example, the user management server (103) provides lifestyle pattern-related item information to the first device (107), and response information for the item information can be generated in the first device (107), and the response information is provided as lifestyle pattern information.

[0050] That is, lifestyle pattern information refers to information related to the user's lifestyle obtained through the first device (107), and is not limited to a specific form.

[0051]

[0052] In addition, the user management server (103) obtains user log information from the second device (101). For example, the user log information may be log record information. Here, the second device (101) may be a caregiver toy as described above, and the user log information is user-related information recorded by the caregiver toy, and the user is an elderly person living alone. Here, the owner of the first device (e.g., a manager of a welfare facility, a service manager for the second device) manages the user (e.g., an elderly person living alone). For example, the second device (101) obtains user log information based on user interaction. The second device (101) recognizes user actions based on at least one sensor. In addition, the second device (101) obtains user log information as user-related information based on a camera and other input modules. For example, the user log information may be “stroking, tapping, holding hands” and other actions as user interactions, and is not limited to a specific form. That is, the user log information may be a user interaction sensed by the second device (101). In addition, the user log information may be user action-related information such as “whether to eat, whether to take medication” and other actions, and is not limited to a specific form. The second device (101) acquires user action-related information as user log information based on a camera and other input modules. As another example, the user is an elderly person living alone, and the owner of the first device (e.g., a manager of a welfare facility, a service manager for the second device) inputs user action-related information (e.g., whether to eat, whether to take medication) into the first device (107), and the second device acquires the input information as user log information.

[0053] In addition, the user log information includes information related to services provided to the second device (101). As a specific example, the second device (101) provides various services to the user based on the control of the user management server (103). The second device (101) provides data to the user through an output module based on the control of the user management server (103) and user input. Through this, the user receives services such as “gymnastics, music, quizzes, stories, English classes” and other services from the second device (101). In addition, the second device (101) detects user input based on the provided services. For example, the second device (101) recognizes user actions based on services provided through a camera, microphone, and other input modules, and the recognition information is included in the user log information.

[0054] The second device (101) acquires user log information in real time and transmits it to the user management server (103) for storage. Here, as an example, the user management server (103) may utilize the user log information after a preset period of time has elapsed, without using the initial user log information, and this will be described later.

[0055] For example, the user management server (103) obtains and manages user log information for each user from a plurality of second devices (101) used by each of the plurality of users. Here, the user management server (103) generates and manages digitized information for each item included in the user log information for each user. As a specific example, the second device (101) sets each item of the user log information based on Table 2 below, and generates and manages digitized information for each item. For example, each item includes, based on each user, an item about medication or meal taken by the user, an item about user actions sensed through the second device (101), and an item about actions performed by the user based on interaction with the second device (101). However, Table 2 below is only one example and may not be limited thereto, and other items may be set to generate digitized information.

[0056]

[0057] The user management server (103) performs user segmentation and recommends content based on the lifestyle pattern information and user log information acquired based on the above.

[0058] More specifically, the user management server (103) creates multiple user groups based on the acquired lifestyle pattern information. As an example, the following describes three user groups based on lifestyle pattern information, but the present invention is not limited thereto.

[0059] The user management server (103) assigns each user to a user group based on lifestyle pattern information obtained from each of the multiple users. Here, user group assignment is performed by calculating the distance between the center of each user group and the user based on the Euclidean distance, but this is only one example and is not limited thereto.

[0060] Euclidean distance can be a method of judging similarity based on the distance between two points, and can be as shown in the following mathematical formula 1 for each of the two points p and q, but is not limited thereto.

[0061]

[0062] In addition, as a specific example, Table 3, Mathematical Expressions 2 and 3 below are operations in which user groups are assigned (or determined) based on lifestyle pattern information. In Table 3 below, response information to questionnaire data provided by the user management server (103) is utilized as lifestyle pattern information, but this is merely a configuration for convenience of explanation and is not limited thereto.

[0063] For example, the user management server (103) provides the user with survey data related to the items in Table 3 below via the first device (107), and acquires each item information as lifestyle pattern information based on the user input. Thereafter, the user management server (103) digitizes each item information and calculates the distance between the digitized item information and the center of each group (or cluster) based on the Euclidean distance. Thereafter, the user is assigned to the group corresponding to the minimum distance, as in Mathematical Expression 3 below.

[0064] - Gender (X1), age (X2) - Number of patients with the three major diseases (X3) - Depression score (X4) - Regular waking up and going to bed (X5) - Positive thinking (X6) - Regular medication, meals, and ventilation (X7) - Exercise, walking, and social relationships (X8)

[0065]

[0066]

[0067]

[0068]

[0069] The user management server (103) assigns each user to a user group based on user log information obtained from each of the multiple users. Here, user group assignment is performed by calculating the distance between the center of each user group and the user based on the Euclidean distance, but this is only one example and is not limited thereto. The Euclidean distance may be a method of determining similarity based on the distance between two points, and may be the same as the mathematical expression 1 described above for each of the two points p and q.

[0070] For example, user log information is acquired by considering a weight for a certain period of time (e.g., 1 week) from the time the user uses the second device (101). For example, when a user receives a caregiver toy with the second device (101), the user may experience high usage for about a week due to the honeymoon effect. Accordingly, user log information may be acquired by assigning a weight to a stable period (e.g., 4 weeks) in which the second device (101) is used in a certain pattern after a certain period of time, but the present invention may not be limited thereto.

[0071] Additionally, the user log information may be various user action information acquired based on the second device (101), as described above.

[0072] In addition, as a specific example, Table 4, Mathematical Expressions 4 and 5 below are operations in which user groups are assigned (or determined) based on user log information. In Table 4 below, service-based detected user operation information provided by the second device (101) is utilized as user log information, but this is only a configuration for convenience of explanation and is not limited thereto.

[0073] For example, the user management server (103) obtains information related to the items in Table 4 below through the second device (101). Thereafter, the user management server (103) digitizes each item information and calculates the distance between the digitized item information and the center of each group (or cluster) based on the Euclidean distance. Thereafter, the user is assigned to the group corresponding to the minimum distance, as in the following mathematical expression 5.

[0074] For example, the user management server (103) can exclude variables with low usage or that are difficult to utilize from among user log information, as shown in Table 4 below.

[0075]

[0076] · Gymnastics ratio (X1), reminiscence play ratio (X2), music ratio (X3), religion ratio (X4), quiz ratio (X5), story ratio (X6) - Excluding items that do not become group classification variables due to low usage based on users' overall log data - Weight calculation (%) = (Usage of each function / Sum of function usage) · Interaction ratio per function (X7) - (Holding hands + stroking + patting) / (Holding hands + stroking + patting + gymnastics + reminiscence play + music + classical music + religious music + quiz + story + English class) - Each is the sum of 30 days' usage)

[0077]

[0078]

[0079]

[0080]

[0081] FIG. 4 is a reference diagram for a method for deriving an ideal area based on user segmentation according to the present invention.

[0082] Referring to Figure 4, the user management server (103) creates nine segmentation grids by intersecting user groups related to lifestyle information and user log information-based user groups. However, this is merely an example, and further user groups can be distinguished. For example, user groups related to lifestyle information and user log information-based user groups are classified based on the Euclidean distance method described above.

[0083] As a specific example, referring to FIG. 4, a user group based on user log information is assigned to the X-axis, a user group based on lifestyle pattern information is assigned to the Y-axis, and a segmentation grid is generated by each intersection point. That is, each segmentation grid has a corresponding user group related to lifestyle pattern information and a user group related to user log information. Here, each of the user group related to lifestyle pattern information and the user group related to user log information may have a grade, and the segmentation grid where the highest grades in each user group intersect is derived as an ideal grid (ideal grid, 401). For example, the ideal grid is derived based on criteria such as improved medication habits, increased activity through exercise and gymnastics, improved mental health through reduced depression and loneliness, and other criteria, but is not limited to a specific form. In addition, each segmentation grid (403, 405, 407) exists in a relative position with respect to the ideal grid (401).

[0084] For example, the user management server (103) can manage numerical score information for each subdivision grid (403, 405, 407). For example, the numerical score information may be a life management score, a depression score, and other scores, but is not limited to a specific form. Here, in the case of the ideal grid (401), the use effect for the second device (101) (caregiver toy) is maximized. Therefore, the user management server (103) recommends content so that users included in each subdivision grid (403, 405, 407) change to the ideal grid (401). As a specific example, if the ideal grid (401) user has a high proportion of gymnastics, a medium proportion of music and religion, and a low proportion of stories, the user management server (103) can recommend content so that the second device (101) can be used with the corresponding pattern.

[0085] As another example, the user management server (103) performs content recommendations based on the characteristics of each segmentation grid. That is, the user management server (103) recommends preset content to the second device (101) so that the user can move to the ideal grid (401) based on the characteristics of each segmentation grid, and allows the user to perform the content through the second device (101).

[0086] As a specific example, the user management server (103) sets a preset notification cycle considering the characteristics of each subdivision grid and notifies the user, and allows the user to perform content based on this. As an example, the second device (101) provides a push notification (e.g., "Hyodol is bored. Let's do gymnastics together") to the user based on the user management server (103), but this is only one example and is not limited thereto. As described above, the user management server (103) guides the user of the general grid to move to the ideal grid.

[0087] Here, in relation to the segmentation grid, the X-axis is assigned a user group related to user log information, and the Y-axis is assigned a user group related to lifestyle pattern information, as described above. For example, cross-sectional changes that change lifestyle pattern information and end-to-end changes that change lifestyle pattern information can be considered as characteristics of each segmentation grid in which a user is included.

[0088] As a specific example, FIGS. 5 and 6 are reference diagrams for a specific method of recommending content based on user segmentation according to the present invention. Referring to FIG. 5, the segmentation grid (405) located on the left side of the ideal grid (401) requires a change based on user log information in order to change into the ideal grid (401). For example, the type requiring a change based on user log information may be Type A, but this is merely an example for the convenience of explanation and is not limited thereto. For example, referring to FIG. 6, Type A recommends content so that user log information is improved through cross-sectional changes. The user log information may be user action information based on a second device (101), and for this purpose, the user management server (103) may recommend content related to medication reminders (601), regular meals (603), and guided exercise (605). However, this is merely an example, and other items may be set for cross-sectional changes. For example, the user management server (103) improves user behavior by providing push notifications at preset times for each item.

[0089] In addition, for example, the subdivision grid (403) located under the ideal grid (401) requires a change based on lifestyle pattern information in order to change into the ideal grid (401). For example, the type requiring a change based on lifestyle pattern information may be Type B, but this is merely an example for the convenience of explanation and is not limited thereto. For example, referring to FIG. 6, Type B recommends content so that lifestyle pattern information is improved through inter-species changes. The lifestyle pattern information may be user emotion or environment information, and for this purpose, the user management server (103) may recommend content for music recommendation (607), quiz provision (609), and stroking (611). For example, the user management server (103) provides push notifications at preset times for each item so that user actions are improved.

[0090] Here, the user management server (103) can provide regular action-related push notifications for Type A, and provide push notifications based on the user's leisure time or free time for Type B. In other words, different push notifications are provided based on different item information for each type.

[0091] FIG. 7 is a reference diagram for a method for recommending content by priority based on user segmentation according to the present invention. As segmentation grids, an ideal grid (401) and a segmentation grid (407) located furthest from the ideal grid (401) may be considered. Referring to FIG. 7, both the ideal grid (401) and the segmentation grid (407) located furthest from the ideal grid require both cross-sectional and end-to-end changes. For example, the type requiring all changes may be Type C, but this is merely an example for the convenience of explanation and is not limited thereto. For example, referring to FIG. 7, Type C may be divided into Type C1, which prioritizes cross-sectional changes, and Type C2, which prioritizes end-to-end changes. For example, the user management server (103) may determine Type C1 or Type C2 by reflecting lifestyle pattern information and user log information. As a specific example, Type C1 or Type C2 may be determined as a user group having a long Euclidean distance from the center of the segmentation grid. That is, if the Euclidean distance based on user log information is further than the Euclidean distance based on lifestyle pattern, it may be determined as type C1, and if the Euclidean distance based on lifestyle pattern information is further than the Euclidean distance based on user load information, it may be determined as type C2, but this may not be limited thereto. For example, the user management server (103) may set recommended content and push notifications for the content by considering priorities.

[0092] Figure 8 is a flowchart of a method for segmenting users and recommending content based on user data.

[0093] Referring to FIG. 8, a method for recommending content based on user data can be provided. For example, in FIG. 8, the server is the user management server (103) described above. The server receives the user's lifestyle pattern information acquired by the first device and maps the user to at least one lifestyle pattern group. (S810) Here, the lifestyle pattern group is a user group classified based on the lifestyle pattern information, as described above. In addition, the server receives the user's log information acquired by the second device and maps the user to at least one log pattern group. (S820) Here, the log information may be the user log information described above, and the log pattern group is a user group classified based on the user log information, as described above. Thereafter, the server generates a user grid based on the lifestyle pattern group and the log pattern group to which the user is mapped. (S830) Here, the user grid is the segmentation grid described above. Thereafter, the server compares the user grid and the reference grid to obtain recommended content information (S840), and transmits the recommended content information to the second device to provide content to the user (S850). Here, the reference grid is the ideal grid described above.

[0094] For example, each of the lifestyle pattern group and the log pattern group is composed of three groups, and when determining the lifestyle pattern group and the log pattern group of the first user, the lifestyle pattern group of the first user is determined based on the lifestyle pattern information parameter of the first user and the Euclidean distance between the center of each lifestyle pattern group. Here, the lifestyle pattern information parameter corresponds to each of the aforementioned lifestyle pattern information, and the parameter may be information to which a weight is assigned to each piece of information. In addition, the log pattern group of the first user may be determined based on the log information parameter of the first user and the Euclidean distance between the center of each log pattern group. Here, the log information parameter corresponds to each of the aforementioned user log information, and the parameter may be information to which a weight is assigned to each piece of information.

[0095] As a specific example, the lifestyle pattern information parameter may be configured based on at least one of the user's gender, the user's age, the user's disease information, the user's depression scale, the user's sleep scale, the user's thinking scale, the user's meal information, the user's medication information, the user's physical activity information, and the user's social relationship information.

[0096] Additionally, the log information parameter may be configured based on at least one of second device-based gymnastic activity information, second device-based play activity information, second device-based music activity information, second device-based religious activity information, second device-based quiz activity information, and second device-based story activity information.

[0097] In addition, in one example, the recommended content information may be set to at least one of the first type recommended content, the second type recommended content, the third type recommended content, and the fourth type recommended content based on the user grid. Here, the first type recommended content is the aforementioned B type-based content based on changes in the user's lifestyle pattern, and the second type recommended content is the aforementioned A type-based content based on changes in the user's log pattern. In addition, the third type recommended content is the aforementioned C type-based content based on a combination of changes in the user's lifestyle pattern and changes in the log pattern. In addition, the fourth type recommended content may be content provided to a user included in an ideal grid as a reference grid to maintain the ideal grid. For example, when the user grid and the reference grid are the same, the fourth type recommended content may be determined as the recommended content information.

[0098] The embodiments of the present invention described above may be implemented through various means. For example, the embodiments of the present invention may be implemented through hardware, firmware, software, or a combination thereof.

[0099] In the case of hardware implementation, the method according to embodiments of the present invention may be implemented by one or more ASICs (Application Specific Integrated Circuits), DSPs (Digital Signal Processors), DSPDs (Digital Signal Processing Devices), PLDs (Programmable Logic Devices), FPGAs (Field Programmable Gate Arrays), processors, controllers, microcontrollers, microprocessors, etc.

[0100] When implemented using firmware or software, the methods according to embodiments of the present invention may be implemented in the form of modules, procedures, or functions that perform the functions or operations described above. The software code may be stored in a memory unit and executed by a processor. The memory unit may be located within or outside the processor and may exchange data with the processor using various known means.

[0101] The detailed description of the preferred embodiments of the present invention disclosed as described above has been provided to enable those skilled in the art to implement and practice the present invention. While the present invention has been described above with reference to preferred embodiments, it will be understood by those skilled in the art that various modifications and variations can be made therein without departing from the spirit and scope of the present invention as set forth in the claims below. Accordingly, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein. Furthermore, while the preferred embodiments of the present specification have been illustrated and described above, the present specification is not limited to the specific embodiments described above, and various modifications may be made by those skilled in the art to which the present invention pertains without departing from the gist of the present specification as claimed in the claims. Furthermore, such modifications should not be individually understood from the technical spirit or perspective of the present specification.

[0102] In addition, both the product invention and the method invention are described in the specification, and the description of both inventions may be applied supplementarily as needed.

[0103] Although the embodiments of the present invention have been described with a focus on a system providing content, it can also be applied to various other software-related systems.

Claims

1. In a system consisting of a first device, a second device, and a server, The first device obtains user information and transmits it to the server, The second device provides content to the user based on information received from at least one of the server and the first device, The above server, Obtaining the user's lifestyle pattern information from the first device and mapping the user to at least one lifestyle pattern group, Obtaining the user's log information from the second device and mapping the user to at least one log pattern group, Generate a user grid based on the lifestyle pattern group and the log pattern group to which the user is mapped, Obtain recommended content information by comparing the user grid and the reference grid above, A system that provides the content to the user by transmitting the above recommended content information to the second device.

2. In paragraph 1, Each of the above life pattern group and the above log pattern group is composed of three groups, When determining the above life pattern group and the above log pattern group of the first user, The lifestyle pattern group of the first user is determined based on the lifestyle pattern information parameter of the first user and the Euclidean distance between the center of each lifestyle pattern group, A system in which the log pattern group of the first user is determined based on the log information parameter of the first user and the Euclidean distance between the center of each log pattern group.

3. In paragraph 2, The above lifestyle pattern information parameter is configured based on at least one of the user's gender, the user's age, the user's disease information, the user's depression scale, the user's sleep scale, the user's thinking scale, the user's meal information, the user's medication information, the user's physical activity information, and the user's social relationship information.

4. In paragraph 2, The second device measures user interaction based on the content provided by the second device, Based on the above interaction, the log \pattern information parameter is configured, The system wherein the above log information parameter is configured based on at least one of second device-based gymnastic activity information, second device-based play activity information, second device-based music activity information, second device-based religious activity information, second device-based quiz activity information, and second device-based story activity information.

5. In paragraph 1, A system in which the above recommended content information is set to at least one of the first type recommended content, the second type recommended content, the third type recommended content, and the fourth type recommended content based on the user grid.

6. In paragraph 5, The above first type of recommended content is content based on changes in the user's lifestyle pattern, The above second type of recommended content is content based on changes in the user's log pattern, The third type of recommended content is content based on the combination of changes in the user's lifestyle pattern and changes in log patterns. The above-mentioned fourth type recommended content is a system based on the maintenance of the reference grid.

7. In paragraph 6, A system in which the fourth type of recommended content is determined by the recommended content information when the user grid and the reference grid are the same.

8. In a method for recommending content based on user data, A step of receiving user's lifestyle pattern information acquired by a first device and mapping the user to at least one lifestyle pattern group; A step of receiving the user's log information acquired by the second device and mapping the user to at least one log pattern group; A step of generating a user grid based on the lifestyle pattern group and the log pattern group to which the user is mapped; A step of obtaining recommended content information by comparing the user grid and the reference grid; and A content recommendation method, comprising a step of providing the content to the user by transmitting the recommended content information to the second device.

Images