KR102528953B1 - Method for providing cognitive training contents using assignment allocation for prevention of dementia - Google Patents

Abstract

Provided is a method for providing dementia prevention cognitive function training service capable of remote home training, wherein at least one user terminal is registered from an administrator's terminal, and the type and level of difficulty of at least one pre-stored cognitive function training content are selected in the administrator's terminal. , generating a task template including at least one cognitive function training content of a selected type and level of difficulty, and designating at least one user terminal registered in the manager terminal and a task exposure time, cognitive function training included in the task template and allocating content to at least one designated user terminal.

Description

A method for providing dementia prevention cognitive function training service that enables remote home training {METHOD FOR PROVIDING COGNITIVE TRAINING CONTENTS USING ASSIGNMENT ALLOCATION FOR PREVENTION OF DEMENTIA}

The present invention relates to a method for providing dementia prevention cognitive function training service capable of remote home training, and provides a platform capable of generating and allocating training contents optimized for individuals as tasks.

Recently, an increase in the elderly population due to an aging society has led to a relative increase in geriatric diseases such as vascular dementia and Alzheimer's disease, resulting in an increase in social costs for nursing care and rehabilitation. Accordingly, the importance of physical exercise, continuous care, daily life, and health care support for the elderly to prevent disease at an early stage and slow down the progression of the disease is emerging. Since the main purpose of dementia treatment is to reactivate degenerating brain cells to maintain brain function or to alleviate or delay the progression of disease, maintenance of language and performance functions of patients with dementia through various non-drug treatments as well as drug treatment, It is very important to maintain and improve the memory function created through repetitive practice. Therefore, it is effective to utilize a cognitive therapy program that activates brain functions and improves cognitive abilities through stimulation.

At this time, a method for providing dementia cognitive therapy contents was researched and developed. In this regard, prior art, Korean Patent Publication No. 2019-0138416 (published on December 13, 2019) and Korean Patent Registration No. 10-1295187 (2013 Announcement on August 09, 2018), content for cognitive training to prevent dementia is provided to the user's terminal, and through repetitive cognitive training, the user's brain function is prevented from deteriorating, and cognitive training by course is performed according to the symptoms of the user's dementia. It provides cognitive training by providing content for cognitive training, provides cognitive training content in the form of a problem-solving game so that users can continue cognitive training for a long time without feeling bored, and trains the user's brain function in various ways. Based on the evaluation result information of content for cognitive training, the configuration that can grasp the user's dementia status and the content that determines the degree of human brain function activation are subdivided into a number of classification areas and levels and stored, and brain function enhancement content A configuration in which contents stored in the storage unit are sorted according to a predetermined classification method for each area, and a user's achievement level is given according to an acquisition score according to feedback delivered by the user to the contents selected in the content selection unit is disclosed. .

However, even if the above configuration is used, it is difficult to induce steady training due to the nature of the cognitive therapy program provided as game content, which is not compulsory and does not necessarily need to be solved. In addition, there are various game contents to maintain and improve frontal lobe execution, visuospatial cognitive ability, attention concentration, memory, language ability, and calculation ability. Complex games are not progressed by giving up or not even trying from the beginning. Even if a game in a complex field is played, the general public, who is not an expert, may proceed with the program in a neutral way due to lack of professional knowledge and lack of systematic training in which field requires training. Accordingly, there is a demand for research and development of a platform that can systematically and complexly proceed with cognitive therapy programs.

An embodiment of the present invention enables an expert manager to register and manage each user, and uses a task assignment function to select and allocate dementia prevention training contents corresponding to cognitive therapy suitable for an individual, thereby using a cognitive therapy program. It can give compulsion to the progress of the program and induce the progress of steady and diverse programs, and can maintain and improve overall cognitive function for maintaining frontal lobe execution, visuospatial cognitive ability, attention concentration, memory, language ability, and calculation ability. When users in a group solve the same problem, competition can be induced by listing the ranking based on the evaluation score, and at least one parameter measured in solving the problem By calculating the evaluation score based on , it is possible to provide a dementia prevention cognitive function training service providing method capable of distance home training, which can use the calculated evaluation score as feedback data and reallocate tasks for each step. However, the technical problem to be achieved by the present embodiment is not limited to the technical problem as described above, and other technical problems may exist.

As a technical means for achieving the above-described technical problem, an embodiment of the present invention includes the step of registering at least one user terminal from an administrator terminal, the type and difficulty of at least one cognitive function training content pre-stored in the administrator terminal If selected, generating a task template including at least one cognitive function training content of the selected type and level of difficulty and designating at least one user terminal registered in the manager terminal and the task exposure time, included in the task template and allocating the cognitive function training content to at least one designated user terminal.

According to any one of the above-described task solving means of the present invention, a task assignment function that allows an expert administrator to register and manage each user and selects and allocates dementia prevention training contents corresponding to cognitive therapy suitable for the individual By using it, it is possible to give coercion to the progress of cognitive therapy programs and induce the progress of steady and diverse programs, and overall cognitive functions for maintaining frontal lobe execution, visuospatial cognitive ability, attention, memory, language ability, and calculation ability. It can be managed so that the ability in one field is not left behind while maintaining and improving, and when users in the group solve the same problem, it is possible to induce competition by listing the ranking based on the evaluation score, and to solve the problem. By calculating an evaluation score based on at least one measured parameter, the calculated evaluation score may be used as feedback data and tasks for each step may be reassigned.

1 is a diagram for explaining a dementia prevention cognitive function training service providing system capable of remote home training according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a training service providing server included in the system of FIG. 1 .
3 and 4 are diagrams for explaining an embodiment in which a dementia prevention cognitive function training service capable of remote home training according to an embodiment of the present invention is implemented.
5 is an operational flowchart for explaining a method for providing a dementia prevention cognitive function training service capable of remote home training according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail so that those skilled in the art can easily practice the present invention with reference to the accompanying drawings. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected" but also the case where it is "electrically connected" with another element interposed therebetween. . In addition, when a part "includes" a certain component, this means that it may further include other components, not excluding other components, unless otherwise stated, and one or more other characteristics. However, it should be understood that it does not preclude the possibility of existence or addition of numbers, steps, operations, components, parts, or combinations thereof.

As used throughout the specification, the terms "about", "substantially", etc., are used at or approximating that value when manufacturing and material tolerances inherent in the stated meaning are given, and do not convey an understanding of the present invention. Accurate or absolute figures are used to help prevent exploitation by unscrupulous infringers of the disclosed disclosure. The term "step of (doing)" or "step of" as used throughout the specification of the present invention does not mean "step for".

In this specification, a "unit" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Further, one unit may be realized using two or more hardware, and two or more units may be realized by one hardware.

In this specification, some of the operations or functions described as being performed by a terminal, device, or device may be performed instead by a server connected to the terminal, device, or device. Likewise, some of the operations or functions described as being performed by the server may also be performed by a terminal, apparatus, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal mean mapping or matching the terminal's unique number or personal identification information, which is the terminal's identifying data. can be interpreted as

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

1 is a diagram for explaining a dementia prevention cognitive function training service providing system capable of remote home training according to an embodiment of the present invention. Referring to FIG. 1 , a dementia prevention cognitive function training service providing system 1 capable of remote home training includes at least one user terminal 100, a training service providing server 300, and at least one manager terminal 400. can include However, since the dementia prevention cognitive function training service providing system 1 in FIG.

At this time, each component of FIG. 1 is generally connected through a network (network, 200). For example, as shown in FIG. 1 , at least one user terminal 100 may be connected to a training service providing server 300 through a network 200 . Also, the training service providing server 300 may be connected to at least one user terminal 100 and at least one manager terminal 400 through the network 200 . In addition, at least one manager terminal 400 may be connected to the training service providing server 300 through the network 200 .

Here, the network means a connection structure capable of exchanging information between each node, such as a plurality of terminals and servers, and examples of such networks include RF, 3rd Generation Partnership Project (3GPP) network, Long Term LTE Evolution) network, 5GPP (5th Generation Partnership Project) network, WIMAX (World Interoperability for Microwave Access) network, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network) , PAN (Personal Area Network), Bluetooth (Bluetooth) network, NFC network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc. are included, but are not limited thereto.

In the following, the term at least one is defined as a term including singular and plural, and even if at least one term does not exist, each component may exist in singular or plural, and may mean singular or plural. It will be self-evident. In addition, the singular or plural number of each component may be changed according to embodiments.

At least one user terminal 100 may be a terminal of a user who executes cognitive function training contents using a web page, app page, program, or application related to dementia prevention cognitive function training service capable of remote home training. In addition, at least one user terminal 100 may be a terminal assigned cognitive function training content as a task from the manager terminal 400 when registered with an institution or the like. And, at least one user terminal 100 outputs the assigned cognitive function training content during the task exposure period of the assigned task, and when the deadline elapses or the task exposure period expires, the assigned cognitive function training content It may be a terminal where exposure is terminated. In addition, when at least one user terminal 100 outputs cognitive function training content and receives an input from a user, data collected through at least one sensor or camera of the user terminal 100 is transferred to the training service providing server 300. ). Also, when the at least one user terminal 100 is grouped or clustered into a group by the administrator terminal 400, it may be a terminal that lists the ranking based on the evaluation scores of other users in the group and the evaluation scores of the user. there is. In addition, at least one user terminal 100 may be a terminal requesting completion of a task as a reminder when the progress rate of cognitive function training content does not satisfy a preset progress rate before the task exposure period expires.

Here, at least one user terminal 100 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop, a desktop, a laptop, and the like equipped with a navigation system and a web browser. In this case, at least one user terminal 100 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one user terminal 100 is, for example, a wireless communication device that ensures portability and mobility, navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet ) may include all kinds of handheld-based wireless communication devices such as terminals, smartphones, smart pads, tablet PCs, and the like.

The training service providing server 300 may be a server that provides a dementia prevention cognitive function training service web page, app page, program or application capable of remote home training. Also, the training service providing server 300 may be a server that registers the user terminal 100 of at least one user managed by the manager from the manager terminal 400 . In addition, the training service providing server 300 may be a server that converts cognitive function training contents into a database by difficulty level and type, and generates an assignment template including cognitive function training contents of a difficulty level and type selected by the manager terminal 400. And, when assigning a task by specifying the task exposure period and at least one user terminal 100, the assigned task is a server that outputs cognitive function training content during the task exposure period in the at least one user terminal 100. can Further, the training service providing server 300 may be a server that collects information such as a progress rate of cognitive function training content in at least one user terminal 100 and outputs the collected information to the manager terminal 400 . In addition, the training service providing server 300 is a server that calculates an evaluation score by collecting at least one event collected from at least one user terminal 100 or an IoT-based terminal interworking with at least one user terminal 100. can be Further, the training service providing server 300 may be a server that allows at least one user terminal 100 to share a rank within a group based on the calculated evaluation score.

Here, the training service providing server 300 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop, a desktop, a laptop, and the like equipped with a navigation system and a web browser.

At least one administrator terminal 400 may be a terminal of a manager using a web page, app page, program, or application related to a dementia prevention cognitive function training service capable of remote home training. At this time, the at least one manager terminal 400 registers at least one user terminal 100 of at least one user managed by the manager, creates and allocates a task template to the at least one user terminal 100, It may be a terminal that receives and outputs the result as feedback.

Here, at least one manager terminal 400 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop, a desktop, a laptop, and the like equipped with a navigation system and a web browser. In this case, at least one administrator terminal 400 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one administrator terminal 400 is, for example, a wireless communication device that ensures portability and mobility, and includes navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet ) may include all kinds of handheld-based wireless communication devices such as terminals, smartphones, smart pads, tablet PCs, and the like.

2 is a block diagram illustrating a training service providing server included in the system of FIG. 1, and FIGS. 3 and 4 are implementations of dementia prevention cognitive function training services capable of remote home training according to an embodiment of the present invention. It is a drawing for explaining one embodiment.

Referring to FIG. 2, the training service providing server 300 includes a registration unit 310, a generation unit 320, an allocation unit 330, a grouping unit 340, a calculation unit 350, a task management unit 360, A sharing unit 370 and an ignition management unit 380 may be included.

The training service providing server 300 according to an embodiment of the present invention or another server (not shown) operating in conjunction with at least one user terminal 100 and at least one administrator terminal 400 can perform remote home training. When a dementia prevention cognitive function training service application, program, app page, web page, etc. is transmitted, at least one user terminal 100 and at least one manager terminal 400 perform dementia prevention cognitive function training capable of remote home training. You can install or open service applications, programs, app pages, web pages, etc. Also, the service program may be driven in at least one user terminal 100 and at least one manager terminal 400 by using a script executed in a web browser. Here, the web browser is a program that enables the use of web (WWW: world wide web) services and means a program that receives and displays hypertext described in HTML (hyper text mark-up language). For example, Netscape , Explorer, Chrome, etc. In addition, an application means an application on a terminal, and includes, for example, an app running on a mobile terminal (smart phone).

Referring to FIG. 2 , the registration unit 310 may register at least one user terminal 100 from the manager terminal 400 . For example, assuming that organization A manages users C through Y in zone B, and administrator Z is in charge of this, administrator Z searches for users C through Y based on identifiers such as IDs and registers users C through Y. can Alternatively, after administrators create and register IDs and passwords of users C to Y, the generated IDs and passwords may be delivered to users C to Y to log in.

When the type and difficulty of at least one cognitive function training content pre-stored in the manager terminal 400 is selected, the generation unit 320 generates a task template including at least one cognitive function training content of the selected type and difficulty. can do. In this case, the task template may include a task template name and cognitive function training content, and the task template name may include the type and level of difficulty of the cognitive function training content. In addition, one task template may include at least one piece of set information in which at least one piece of cognitive function training content is bundled. These task templates can be output as a list of templates, and even if the administrator does not select each cognitive function training content, even if the administrator selects only the type and difficulty, the list of task templates is automatically output, and the administrator selects the list of task templates. If any one of them is selected, it can be configured to create an assignment.

When designating at least one user terminal 100 registered in the manager terminal 400 and the task exposure time, the allocator 330 assigns the cognitive function training contents included in the task template to the at least one user terminal 100 designated. ) can be assigned. At this time, when the assigning unit 330 creates a group in the manager terminal 400 and assigns the same task to the group, designating the group itself can replace the designation of each user included in the group. do. In addition, the task exposure time may be set from the time when the task is assigned to the time when the task is finished, but it is not excluded that the manager terminal 400 arbitrarily designates the task exposure time.

After receiving at least one user terminal 100 from the manager terminal 400 in the registration unit 310, the grouping unit 340 groups the at least one user terminal 100 registered in the manager terminal 400 into a group. In the case of clustering, at least one user terminal 100 included in the group can be identified by tagging a group name. And, when the same task is assigned to at least one user terminal 100 included in the group, the result of performing the task may be shared between the at least one user terminal 100 included in the group. The performance result of the task may be, for example, a ranking based on an evaluation score to be described later.

When the allocator 330 designates at least one user terminal 100 registered in the manager terminal 400 and the task exposure time, the calculation unit 350 assigns the cognitive function training content included in the task template to at least one of the designated user terminals 100 and the task exposure time. After allocating to one user terminal 100, when at least one user terminal 100 outputs the cognitive function training content included in the task template, at least one event occurring in the at least one user terminal 100 can be collected. In addition, the calculation unit 350 calculates the difficulty (wL), correct answer (R), hint usage (H), task performance time (T), opportunity usage (C), and concentration of the cognitive function training contents included in the task template. The evaluation score can be calculated based on (F), free assistance (A), and positive additional points (E). Here, the evaluation score may be calculated by Equation 1 below, but modification according to the embodiment is not excluded.

At this time, R, which is correct answer, means whether or not the task was performed correctly, and is a value measured for matching or similarity with the correct answer according to the task. The amount of hint usage, H, which may be provided while performing a task, means whether or not the provided hint was used, and is measured by the amount of hints used. The task execution time, T, means the time required while performing the task, and is a value measured from the time the task was started to the time it was completed. C, the amount of opportunity use, means the amount of consumption of a given opportunity while performing a task. At this time, C is measured by the amount of opportunities used, and since repetitive learning is possible, it can indicate whether the task is a repetitive learning task. The degree of concentration, F, means the degree of concentration while performing the task, and can be measured by the time spent looking at the screen after analyzing the video and audio using a camera or microphone, but is not limited thereto. At this time, the time and concentration of looking at the screen may be calculated through gaze analysis in the image. Freedom of assistance, A, means whether or not the person received help from others while performing the task. This is also the result of measuring whether there was a helper while performing the task using a camera or microphone.

E (Extra Point), which is a positive extra point, means a score that is measured differently depending on the task. For example, in the case of social activity training, the score may be based on the amount of conversation exchanged while performing a task or cooperation calculated according to the distribution of utterances measured by the user. In the case of physical activity training, it may be a score according to the degree or accuracy of guided physical activity measured by a sensor during task performance. In the case of emotional activity training, it may be the distribution of emotions according to the user's expression calculated by camera input. In summary, if the cognitive function training content included in the task template is social activity training content, the cognitive function training content included in the task template is physical activity training content based on the conversation volume recognized by the user terminal 100. In this case, based on the amount of physical activity measured in the user terminal 100 or an IoT-based terminal linked with the user terminal 100, and when the cognitive function training contents included in the task template are emotional activity training contents, the user terminal 100 It can be based on the emotion distribution of the user, which is an object in the image frame collected from the camera of the user.

At this time, emotion classification can use P. Ekman's human emotion classification model. The reason for using this is that the method using multiple sensors is because there are many instruments that need to be attached to the user's body and because emotions can be classified using facial expressions most simply, but the use of other emotion classifications is not excluded. It will be self-evident.

emotional state change in facial expression Surprise -Eyebrows rise, raised high and bent
-Tightening of the skin under the eyebrows
-Horizontal wrinkles on the forehead
- Eyelids wide open; The upper eyelid is raised and the lower eyelid is lowered. The sclera of the eye is shown above the iris
-The jaw goes down and the mouth and teeth open, but there is no change in the muscles of the mouth Fear -Eyebrows rise and fall together
-Wrinkles on the forehead converge in the middle, and wrinkles do not spread over the entire forehead
- The upper eyelid is raised, the sclera is exposed, and the lower eyelid is pulled down
- Mouth open, lips slightly pulled and lowered or drooped down Disgust - upper lip rises
The lower lip also rises and supports the rise of the upper lip, or it goes down and protrudes slightly.
- Wrinkled nose
- cheeks rise
-A line develops from the lower eyelid, and the eyelid is raised but not tense
-Eyebrows are lowered and upper eyelids are also lowered Anger - lowered eyebrows
- Vertical wrinkles between the eyebrows
-Lower eyelid pulled and lowered by eyebrow
- The lower eyelid is pulled and sometimes raised
- Both eyes stare for a long time and protrude slightly
- The lips are tightly closed, and the corners of the mouth are straight or down. Square-shaped and tense when shouting Happiness - Mouth curls back and rises
- Mouth may be open and teeth may be visible
-Wrinkles form from the nose to the corners of the mouth
- Cheeks rise
- Creases under the lower eyelid, rising but not tense
-Wrinkles around the eyes (Crow's Feet) are created at the outer edges of both eyes Sadness - The inner part of the eyebrows goes down
-The skin under the eyebrows is triangulated and the inner eyebrows are raised
- the inner part of the upper eyelid rises
- Mouth drooping or lip quivering

At this time, the positive emotional state may be set to surprise and happiness among the above-described emotional state classifications, but is not limited to those listed. Here, when the above-described facial features are learned by an artificial intelligence algorithm, when a user's face is input as a query, it may be determined whether or not to add a score. For example, a happy person's face image is accumulated and stored enough to build big data, and the characteristics of the emotional state described above are set as ROI (Region of Interest), that is, a feature within the region of interest, to perform learning and training. If so, when a face image is input as a query later, whether or not the face input as a query is a happy face can be checked. To this end, the calculator 350, when a sufficient amount of data is accumulated to model the artificial intelligence algorithm, stores raw data, which is the accumulated data, in parallel and distributed, and includes the raw data included in the raw data. Unstructured data, structured data, and semi-structured data can be refined, and preprocessing including classification as meta data can be performed. In addition, the calculation unit 350 may build big data by performing analysis including data mining on the preprocessed data. The calculation unit 350 constructs big data by performing analysis including data mining on the preprocessed data, and then divides the data set of the built big data into training data and experimental data to generate artificial Intelligence learning can proceed. Here, learning may consist of any one or a combination of at least one of supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. Not limited.

For example, when using artificial intelligence algorithms, regression models and neural networks can be used, and generalized additive models, random forests, boosted MARS, Non-parametric models such as SVM can be used to predict emotional states, and ensemble learning can be applied to estimate emotional states. Alternatively, based on the data crawled by web crawling, an emotional state prediction model may be created by applying a multiple regression model, a neural network model, or a decision tree model.

At this time, the neural network has a structure in which one or more hidden layers are arranged between an input layer composed of independent variables and an output layer composed of dependent variables, and each layer has an independent Nodes (or neurons) are arranged, and the nodes of the hidden layer receive values from the previous layer and each weight as a weighted sum, and pass the activation function to the next layer. This operation is performed in the hidden layer and finally performed in the output layer, and then a result value can be derived. Unlike linear regression, which assumes a linear relationship between dependent and independent variables, artificial neural networks explain the nonlinearity of data well and show high explanatory power even for complex and irregular patterns, so they are highly suitable for emotional state classification that requires various variables to be set. control can be shown.

Support Vector Regression (SVR) is a regression model based on a Support Vector Machine (SVM). SVM uses a kernel function to express data in a high-dimensional vector space to find a hyperplane that maximizes the margin for classifying these data. SVR is a method that applies the idea of SVM to a regression problem. Existing regression models define the difference between the actual value and the predicted value as a loss function, whereas SVR defines an insensitive loss function that ignores cases where the difference is smaller than a specific value and calculates it as a loss only when the difference is larger than a specific value. SVR is a form of estimating a linear regression model that uses a kernel function to express data in a high-dimensional vector space and minimizes an insensitive loss function in the vector space.

Random forests extract multiple bootstrap samples from training data, learn independent decision trees for each sample, and combine the output values of multiple decision trees to finalize the final decision tree. It is a decision tree-based ensemble method that determines the output value. When growing each decision tree, it has the effect of reducing the correlation of the learned decision trees and consequently reducing the variance of prediction by considering only some randomly extracted variables that are the target of each branch. When growing a tree, a decision tree for the purpose of classification goes through the process of repeatedly separating data in the direction of reducing impurity using a data impurity measure such as the Gini coefficient or entropy. In addition to this, various variable settings, big data collection, preprocessing, and learning may be performed, and the present embodiment is not limited to the above.

The degree of concentration, P, is the pupil size, pupil position, eye fixation, eye leap, saccade, fixation duration, and number of gazes in the image frame input through the camera of the user terminal 100 ( It can be calculated with an eye tracking algorithm based on fixation count). At this time, since various eye tracking algorithms have been developed, any one may be used, but the algorithm for the degree of concentration, that is, the degree of immersion, in one embodiment of the present invention, detects a face from an image generated through a camera, In order to record the continuous information of the face, the face is tracked until it disappears from the camera, and through eye tracking, whether or not to gaze at the content and gaze time are measured and used. First of all, YOLO-v3 can be used to recognize a face, and the part recognized as a face is displayed as a bounding box. In this case, a binarization operation may be performed using a previously disclosed adaptive threshold estimation method for pupil detection. Afterwards, using the characteristic that the gray level of the eye pupil area is lower than the surrounding area, the pupil is separated after binarization, and the center of gravity of the black pixel is obtained to obtain the center of the pupil in order to remove noise other than the eye. Finally, it is possible to determine whether the user is gazing at the screen by performing calibration on the location of the light reflected in the pupil in the captured image.

In the assisting free unmanned A, a face other than a face having a corresponding facial feature point of the user in the image frame received from the camera of the user terminal 100 is recognized, or a face other than the user's voice among voices recognized by the user terminal 100 is recognized. Whether or not the assistant's voice is recognized may be determined by classifying the speaker identification algorithm. At this time, speaker identification is a technique for modeling and classifying phonetic characteristics of individual voices, low-level features such as short-term frequency fluctuations and pitch, and high-level features such as single sounds, words, syllables, or long-term frequency fluctuations. It is preferable to use a machine learning algorithm because it models rich phonetic features such as For example, a Gaussian Mixture Model based on a machine learning algorithm or convolution-pooling operation with robustness that is sensitive to discrepancies between training and test data caused by noise on environmental factors. and STFT (Short-Time Fourier Transform) algorithm may be used. In the case of the former, it can be used simply when performing in a quiet room, but it is not suitable for a noisy environment, and in the case of the latter, it is robust against noise caused by other environmental factors such as living noise. It is also possible to selectively apply the former or the latter based on the execution environment of cognitive function training contents.

Taking the latter case as an example, in the data learning step, speech samples of a plurality of speakers may be input. The input speech sample undergoes a three-step feature extraction process. The first step is to generate a unique sound map of speech, the second step is normalization, and the third step is to sample in a certain interval using a sliding window algorithm. In the preprocessed window, internal weights of the multi-layer convolutional neural network are updated to ensure noise robustness, and general patterns for each speaker are modeled. In the recognition step, the speaker of each window is classified based on the output activation function value without updating the internal weight of the convolutional neural network. Since the speakers classified for each window may be different, the arithmetic average of the classified results is finally classified unlike the learning step.

Since the above-described speech data has time-series characteristics rather than static signals, a single feature for each speech tends to be meaningless. Therefore, in order to extract features without losing the correlation between time, frequency, and volume, an STFT algorithm that performs a Fourier transform operation for each time interval can be used. Since actual speech data is a discrete function, the discrete signal, time measurement value, frequency measurement value, and window length are applied as variables when calculating the STFT. A sound map is a 3D vector with time on the horizontal axis, frequency on the vertical axis, and pixel intensity on the size. Since the generated sound map shows a locally high correlation between time and frequency, the local convolution-pooling operation Appropriate for modeling with Local Connectivity properties. The generated sound map has a different size for each length of speech and has a very high dimension, so it can be sampled in uniform sections using a sliding window algorithm and divided into windows.

In addition, noise robustness is the most important factor in the field of speech recognition, where there is a large discrepancy between training and test data. Noise robustness can be secured by repeatedly applying a convolution-pooling operation to speaker identification according to an embodiment of the present invention. The generalization performance of the convolution operation is suitable for modeling the variance factors of personal phonetic characteristics. The convolution-pooling operation may include, but is not limited to, a convolution-pooling module, a DropOut Layer and a 3-layer fully-connected layer. The learning of convolution operation is the process of finding the weight of a filter that preserves the spatial relationship between features and extracts the correlation. It is a dimensionality reduction process that reduces complexity. If this is repeated, it is possible to secure strong noise robustness to living noise.

The remaining weights except for the difficulty weight (wL) of Equation 1 can be classified into + weights having a value of 1 or more and - weights having a value of less than 1. Alternatively, the + weight can be set in such a way that a + value is literally given, and a - weight is given a - value. That is, when the value is greater than or equal to 1, the corresponding element acts as an element that increases the score, and when the value is less than 1, the element acts as a factor that lowers the score. The + weights are wL, wR, wP, and wE, and the - weights are wH, wT, wC, and wA. That is, the higher the difficulty, the closer or correct the answer is, the higher the concentration, and the higher the positive point, the higher the final evaluation score. Conversely, the more hint usage, the longer task performance time, the greater opportunity usage, and the more help received, the lower the final evaluation score. Therefore, those to which a + weight is added are parameters whose evaluation scores increase as the size increases, and those to which a - weight is added can be defined as parameters whose evaluation scores decrease as the size increases. Of course, it will be apparent that the + weight and - weight are not determined and may be changed according to embodiments. Also, it is not limited to the listed weights and is not excluded for reasons not listed.

The task management unit 360 is based on the difficulty, correct answer, amount of hint usage, task execution time, opportunity usage, concentration, freeness of assistance, and positive points of the cognitive function training contents included in the task template in the calculation unit 350. After calculating the evaluation score, pre-stored tasks corresponding to the evaluation score may be reassigned to at least one user terminal 100 .

When the task management unit 360 designates at least one user terminal 100 registered in the manager terminal 400 and the task exposure time in the allocating unit 330, the cognitive function training content included in the task template is assigned to the designated at least one user terminal 100. After allocating to one user terminal 100, at least one user terminal 100 may monitor a progress rate of the cognitive function training content included in the task template and update it in real time. Then, the task management unit 360 sends a reminder call to at least one user terminal 100 when the remaining task exposure time of the task exposure time enters the preset time or less and the progress rate does not satisfy the preset completion rate. ) or send a message. Through this, compulsory force is given and deadlines are set so that the task can be performed without delay while maintaining a sense of tension in a fixed state on time. In addition, the task performance rate can be analyzed and visualized so that the manager can check the performance level of each user group and task at a glance.

The sharing unit 370 registers at least one user terminal 100 from the manager terminal 400 in the registration unit 310, and then receives a cognitive screening test result from the at least one user terminal 100. In case of registration, the cognitive screening test result may be shared with the manager terminal 400 . Of course, in addition to cognitive screening tests, Mini-Mental Status Examination, Hasegawa Dementia Scale, 7-Minute Screening, Clock Drawing Test, and Blessed Test (Short Blessed Test, SBT), Mini-Memory Test, Korean Version of Community Dementia Screening Tool (CSID-K), Korean Version of Mini-Mental State Examination, Korean Version of MMSE ( Korean Mini-Mental State Examination), Korean version of CERAD assessment book’s MMSE (MMSE-KC), Korean version of Hasegawa Dementia Scale Revised, or IADL (Assessment of Daily Living), etc., but those listed is not limited to and is not excluded for reasons not listed. In addition to this, various inspections can be received from various institutions and integrated, and can be shared with administrators.

After receiving registration of at least one user terminal 100 from the manager terminal 400 in the registration unit 310, the speech management unit 380 receives a conversation from an interactive artificial intelligence speaker linked with the at least one user terminal 100. Voice conversations between the artificial intelligence speaker and the user may be collected, and a result of analyzing the collected voice conversations may be mapped with at least one user terminal 100 and stored. In this case, at least one user terminal 100 may be interlocked with a conversational artificial intelligence speaker based on natural language processing. Among the cognitive abilities of the elderly living alone or those with little social activity, language ability is the first to deteriorate. There is a reason why language ability is lowered due to aging, but what accelerates this is that there is no one to talk to and opportunities to speak are gradually decreasing. Therefore, it is possible to figure out what kind of cognitive function training content to provide in the future by making a daily conversation attempt through a conversational agent and collecting the result.

First of all, if there is no other person to talk to, it can be made to perform the role of a partner. For example, when the user uses the user terminal 100 in the morning after not using the user terminal 100 for a long time from evening, it may be determined that the user wakes up after going to bed. At this time, it is possible to perform a preemptive speech providing a preset comment, such as "Good night? Today's weather is XX and news is XX. What are you planning to do today?" In a study to find out how the agent's interaction strategy according to the degree of autonomy could be accepted by the elderly, it was found that preemptive speech was acceptable, and conversations about practical safety and health aspects of the elderly were preferred. Speech strategy with high autonomy is considered as preemptive speech (Proactive), and speech strategy with low autonomy is regarded as speech on demand (On-Demand). In other words, speech upon request refers to speech that responds only when there is speech by the elderly. Since the human brain reflexively thinks of an answer as soon as it hears a question, it is possible to induce brain rotation by external stimuli even if an answer is not given.

To this end, the interactive agent may use character-based interactive artificial intelligence. It is possible to use conversational artificial intelligence that recognizes situations based on context, and through continuous conversation, it is possible to understand the situation of conversation and express subjective opinions and emotions based on this. In this case, the interactive agent includes a plurality of unit agents, and each agent may be further subdivided into a knowledge base and an inference engine. The interactive agent composed of each unit agent reads and comprehends the conversation of the other party, and recognizes the overall conversation situation considering its own emotional state. Through this, it can proceed in the order of devising a response strategy, establishing an action plan, and executing it.

First, the target language analysis agent is an agent that analyzes the meaning the target wants to convey and the emotions of the target through the sentence received from the other party. This agent identifies the meaning and emotion that the other party wants to convey through fragmentary analysis and in-depth analysis from the decision-making agent's feedback and the other party's remarks, and delivers them to the dialogue situation judging agent. Fragment analysis means semantic and emotional analysis through the sentences currently received from the other party. In-depth analysis is an analysis module to infer the other person's actual intention and emotion by accumulating the other person's intention and emotion updated through the feedback received from the context-aware agent. Since the in-depth analysis consists of only fragment analysis values at the beginning of the conversation, preconceived notions about the target are reflected, which are updated to match the intentions and emotions of the actual target as the conversation progresses.

The second is a self-emotion identification agent, which is an agent for modeling the change of emotion of artificial intelligence itself through sentences transmitted from the other party. Like the target language analysis agent, this agent also identifies its own emotions from the other party's remarks through fragment analysis and in-depth analysis and delivers them to the conversation situation judgment agent. Modeling through fragmentary reactions is an instantaneous emotional change that occurs through the other person's strong reaction above a certain level. This affects sudden emotional changes or momentary emotional expressions caused by strong stimuli. Modeling through in-depth reactions models the cumulative emotional changes that occur from the situation in which a conversation with the other party is progressing.

The third is a conversation situation judgment agent. The conversation situation judgment agent identifies the conversation situation through the meaning and emotional state delivered by the target language analysis agent and the self-emotion recognition agent, and the feedback from the decision-making agent, and delivers it to the decision-making agent. do. In addition, it gives feedback on the identified situation to the target language analysis agent and self-emotion identification agent, and provides them for updating of each in-depth analysis module. Fourth, a decision-making agent is an agent that determines the intention of the next utterance, including the purpose of artificial intelligence utterance, in the situation identified through the dialogue situation judgment agent. The decision-making agent gives feedback to the reasoning engines of the target language analysis agent and dialog situation judgment agent to achieve a subjective interpretation of the given situation. In order to achieve its own purpose, artificial intelligence makes decisions through simulation through emotion models created through target language analysis agents and self-emotion recognition agents.

Fifth, a response generation agent is an agent that generates the intention of the next utterance determined through the decision-making agent at the level of a sentence. The sixth is a sentence expression agent. The sentence expression agent is an agent that transforms the sentence resulting from the response generation agent to conform to grammar and a specific accent. In the case of learning and training each of these agents, it can be modeled so that progressively in-depth conversations are possible by relearning and retraining contents, and pre-set preemptive conversations are like parrots through continuous training and relearning in addition to the same sentences. A database can be built so that you can feel the diversity like a real person, not an artificial intelligence speaker who only speaks the same thing.

Hereinafter, an operation process according to the configuration of the above-described training service providing server of FIG. 2 will be described in detail with reference to FIGS. 3 and 4 as examples. However, it will be apparent that the embodiment is only any one of various embodiments of the present invention, and is not limited thereto.

Referring to FIG. 3A , a screen of a training service according to an embodiment of the present invention is shown. Referring to FIG. 3B, cognitive interventional therapy, that is, a service in which a manager can manage a plurality of users is provided. As shown in FIG. 3C, a relationship structure between an occupational therapist (manager) and a patient (user) is formed. 3D and 3E show content for training cognitive abilities in various fields, and through a task assignment function as shown in FIG. 3F, a platform capable of assigning tasks to content optimized for each individual and analyzing the results thereof. is provided.

Referring to Figure 4a, the training service according to an embodiment of the present invention can save human resources and time resources, enable immediate feedback, enable self-repetitive learning, and precisely measure such as time measurement. Based on this, objective data can be created and each user can be efficiently managed systematically. Figure 4b shows that users using the platform of the present invention are divided into users (individual users) and managers (institutional users), and the user management flow system of the manager is shown in Figure 4c. Referring to FIG. 4D , which illustrates an embodiment of the present invention being provided as an individual training or group training, FIG. 4E illustrates the process of training. From FIG. 4F, an example of the administrator's execution screen is shown. As shown in FIG. 4G, the manager issues IDs for each user (participant), and creates and assigns task templates to each user as shown in FIG. 4H. 4i shows a screen for managing task templates, a plurality of templates can be created or deleted, task templates can be created as shown in FIG. 4j, and assigned to each user as shown in FIG. 4k, and the results are also shown. can be checked in real time. Tasks can be assigned as shown in FIG. 4L, and groups can be created and managed by group as shown in FIG. 4M. To create a group, a simple method of inputting a group name and then pressing an OK button can be used as shown in FIG. 4n. When a plurality of users of a group solve one problem as shown in FIG. 4o, the ranking listed by the evaluation score can be output, and the result of the user executing the cognitive ability training content will be shown as shown in FIG. 4p. can 4q shows a screen for managing the progress of the task. The completion rate of the task is output in a table, and a function to send a message via text message or messenger to users who have not completed the task is included as shown in FIG. 4r, so that management is easy. do. Figure 4s shows a function for creating and sending questions that the administrator wants to know about the user in a survey format, and Figure 4t shows different login and billing methods for personal and institutional accounts, and when belonging to each institution It is shown that the subscription method of can proceed differently. However, since this is a matter of policy, it is not limited to the listed methods. When the administrator assigns the task in this way, as shown in FIG. 4V, the task to be performed by the user today is output, and when the user clicks on it, the cognitive ability training content is immediately executed. 4w is a summary of the menus of the cognitive function training service according to an embodiment of the present invention, but it is obvious that the listed menus are not limited and can be changed according to the embodiment.

Matters not described in the method of providing dementia prevention cognitive function training service capable of remote home training of FIGS. 2 to 4 are described in the method of providing dementia prevention cognitive function training service capable of remote home training through FIG. 1 above. Since it can be easily inferred from the same or described content, the following description will be omitted.

5 is a diagram illustrating a process of transmitting and receiving data between components included in the dementia prevention cognitive function training service providing system capable of distance home training of FIG. 1 according to an embodiment of the present invention. Hereinafter, an example of a process of transmitting and receiving data between each component will be described through FIG. 5, but the present application is not limited to such an embodiment, and according to various embodiments described above, It is obvious to those skilled in the art that a process of transmitting and receiving data may be changed.

Referring to FIG. 5 , the training service providing server registers at least one user terminal from an administrator terminal (S5100).

Then, when the type and difficulty of at least one cognitive function training content pre-stored in the manager terminal is selected, the training service providing server creates a task template including at least one cognitive function training content of the selected type and difficulty (S5200 ) When at least one user terminal registered in the manager terminal and the task exposure time are designated, cognitive function training contents included in the task template are allocated to the at least one designated user terminal (S5300).

The order between the above-described steps (S5100 to S5300) is only an example, and is not limited thereto. That is, the order of the above-described steps (S5100 to S5300) may be mutually changed, and some of the steps may be simultaneously executed or deleted.

Matters not described in the method of providing dementia prevention cognitive function training service capable of remote home training in FIG. 5 are described in the method of providing dementia prevention cognitive function training service capable of remote home training through FIGS. Since it can be easily inferred from the same or described content, the following description will be omitted.

The method for providing a dementia prevention cognitive function training service capable of remote home training according to an embodiment described with reference to FIG. 5 is in the form of a recording medium including instructions executable by a computer such as an application or program module executed by a computer. can also be implemented. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. Also, computer readable media may include all computer storage media. Computer storage media includes both 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.

The above-described method for providing a cognitive function training service for prevention of dementia capable of remote home training according to an embodiment of the present invention is an application basically installed in a terminal (this may include a program included in a platform or operating system basically installed in the terminal). It can be executed by an application (i.e., a program) directly installed in the master terminal through an application providing server such as an application store server, an application, or a web server related to the corresponding service. In this sense, the above-described method for providing a dementia prevention cognitive function training service capable of remote home training according to an embodiment of the present invention is implemented as an application (i.e., a program) that is basically installed in a terminal or directly installed by a user, and is installed on the terminal. It can be recorded on a computer-readable recording medium, such as

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

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

Claims (10)

In the training service providing method executed in the training service providing server,
Receiving registration of at least one user terminal from an administrator terminal;
generating a task template including at least one cognitive function training content of the selected type and difficulty when the type and difficulty of at least one cognitive function training content pre-stored in the manager terminal are selected; and
allocating cognitive function training contents included in the task template to the at least one designated user terminal when the administrator terminal designates the at least one registered user terminal and a task exposure time;
collecting at least one event occurring in the at least one user terminal when the at least one user terminal outputs cognitive function training contents included in the task template; and
Calculating an evaluation score based on the difficulty of the cognitive function training contents included in the task template, correct answers, hint use amount, task performance time, opportunity use amount, concentration level, freeness of assistance, and positive points A method of providing dementia prevention cognitive function training service that can be trained.
According to claim 1,
After the step of registering at least one user terminal from the manager terminal,
when the manager terminal clusters the at least one registered user terminal into a group, identifying the at least one user terminal included in the group by tagging a group name;
Including more,
When the same task is assigned to at least one user terminal included in the group, the performance result of the task is shared between at least one user terminal included in the group, dementia prevention cognitive function training capable of remote home training. How We Provide Our Services.
delete According to claim 1,
The positive points are,
If the cognitive function training content included in the task template is social activity training content, based on the amount of speech recognized by the user terminal,
If the cognitive function training content included in the task template is physical activity training content, based on the amount of physical activity measured in the user terminal or an IoT-based terminal linked with the user terminal,
If the cognitive function training content included in the task template is emotional activity training content, dementia prevention cognitive function training that can be performed remotely, based on the emotional distribution of the user, which is an object in the image frame collected from the camera of the user terminal. How We Provide Our Services.
According to claim 1,
The degree of concentration,
Eye tracking based on pupil size, pupil position, eye fixation, saccade, fixation duration, and fixation count in the image frame input through the camera of the user terminal (EyeTracking) A method of providing dementia prevention cognitive function training service capable of remote home training, which is calculated by an algorithm.
According to claim 1,
In the presence of assistance, a face other than a face having a corresponding facial feature of the user is recognized in an image frame received from a camera of the user terminal, or an assistant's voice other than the user's voice is recognized among voices recognized by the user terminal. A method for providing a dementia prevention cognitive function training service capable of remote home training, which is to determine whether or not it is possible to perform remote home training by using a speaker identification algorithm.
According to claim 1,
After the step of calculating the evaluation score based on the difficulty, correct answer, hint usage, task performance time, opportunity usage, concentration, free assistance, and positive points of the cognitive function training contents included in the task template,
reassigning a pre-stored step-by-step task corresponding to the evaluation score to the at least one user terminal;
Further comprising, a method for providing dementia prevention cognitive function training service capable of remote home training.
According to claim 1,
When the manager terminal designates the at least one registered user terminal and the task exposure time, after allocating the cognitive function training contents included in the task template to the at least one designated user terminal,
monitoring and updating in real time a progress rate of the cognitive function training content included in the task template in the at least one user terminal;
transmitting a reminder call or message to the at least one user terminal when a remaining task exposure time of the task exposure time enters a preset time or less and the progress rate does not satisfy a preset completion rate;
Including more,
When monitoring the progress rate of the cognitive function training content in the manager terminal, the degree of task performance by user, group, and task is visualized and displayed.
According to claim 1,
After the step of registering at least one user terminal from the manager terminal,
sharing the cognitive screening test result with the administrator terminal when registering a cognitive screening test result from the at least one user terminal;
Further comprising, a method for providing dementia prevention cognitive function training service capable of remote home training.
According to claim 1,
The at least one user terminal is interlocked with a natural language processing (Nnatural Language Processing) based conversational artificial intelligence speaker,
After the step of registering at least one user terminal from the manager terminal,
collecting a voice conversation between the interactive artificial intelligence speaker and a user, from an interactive artificial intelligence speaker interlocked with the at least one user terminal;
mapping and storing a result of analyzing the collected voice conversation with the at least one user terminal;
Further comprising, a method for providing dementia prevention cognitive function training service capable of remote home training.

Images