Method and device for providing content for custom made type rehabilitation based on cloud server

Abstract

To provide a content for custom made type rehabilitation based on a cloud server.SOLUTION: A content providing method comprises the steps of: collecting at least one medical information item relating to a patient which has been input from at least one connected account linked to a patient account when a log-in by the specific account to a platform linked to a cloud server is detected, and the specific account is the patient account; generating state information of the relevant patient by analyzing the at least one medical information item; searching for at least one content item on the basis of the state information by using an artificial intelligence-based learning model; generating training information by using the at least one searched content; and providing the generated training information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a method and system for cognitive or speech therapy, and more particularly to a cloud server-based content provision method for cognitive or speech rehabilitation. [Background technology]

[0002] Generally, brain diseases such as stroke and dementia cause impairment of cognitive and language abilities.

[0003] A language disorder is a delay in language acquisition due to a defect in one part of the speech chain, which is a series of processes necessary for understanding and expressing spoken language, namely, the input process, cognitive process, and calculation process.A type of communication disorder in which the acquisition process shows a significant deviation from normal cases is commonly referred to as a language disorder.

[0004] Such language disorders not only cause communication difficulties for individuals but also place many restrictions on social and economic activities, so it is of utmost importance to provide accurate treatment for them.

[0005] Previously, patients and medical professionals (doctors, nurses, speech-language pathologists, etc.) would work together offline to carry out various activities for the purpose of speech therapy, but this had limitations as the patients and medical professionals had to meet face-to-face in a limited space.

[0006] Therefore, it is necessary to develop technology that overcomes the traditional face-to-face treatment and provides speech therapy services that allow patients to receive a variety of customized speech therapy treatments at the time and place of their choice based on a cloud server, as well as technology that allows for continuous service improvement by reflecting the opinions of patients or their guardians. Summary of the Invention [Problem to be solved by the invention]

[0007] The present disclosure has been made in consideration of the above circumstances, and its purpose is to provide a cloud server-based content provision method and system for cognitive or language rehabilitation that not only provides a training content provision service that enables patients to undergo various customized rehabilitation at a desired time and place based on a cloud server, but also enables continuous service improvement by reflecting the opinions of customers (patients, guardians, medical personnel, speech-language-hearing therapists, medical institution administrators, etc.).

[0008] Another object of the present disclosure is to provide a cloud server-based content provision method and system for cognitive or language rehabilitation that can provide customized content for rehabilitation related to at least one or more areas of memory, executive function, attention, auditory comprehension, speaking, reading, and writing, as well as enable patients to receive customized speech therapy without spatial and time constraints, and enable guardians and / or medical personnel (doctors, nurses, speech-language-hearing therapists, etc.) to monitor the patient's speech rehabilitation process, results, current status, etc.

[0009] Furthermore, another object of the present disclosure is to provide a content providing method and system for cloud server-based cognitive or language rehabilitation that provides content that enables rehabilitation tailored to the patient's level, such as stage (level), speed, and time, and provides analytical information that analyzes the training pattern and / or training history, allowing not only the patient himself / herself but also guardians, medical personnel, etc. to easily check the results of the training, and by accumulating and recording this, it is possible to continuously manage the patient's condition through rehabilitation.

[0010] The problems to be solved by the present disclosure are not limited to those mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the following description. [Means for solving the problem]

[0011] In order to achieve the above technical objectives, a cloud server-based content providing method for cognitive or language rehabilitation according to one aspect of the present disclosure includes: upon detecting login of a specific account to a platform linked to the cloud server, confirming the authority of the specific account; if it is determined as a result of the confirmation that the specific account is a patient account, collecting at least one piece of medical information about the patient input from at least one linked account linked to the patient account; analyzing the at least one piece of medical information to generate condition information of the patient; searching for at least one piece of content based on the condition information using an AI-based learning model; and generating and providing training information using the searched at least one piece of content, wherein the at least one linked account includes at least one of a guardian account, a speech-language-hearing-therapy therapist account, a medical professional account, and a medical institution administrator account; the at least one piece of medical information includes at least one of symptom information, diagnosis information, medical professional information, speech-language-hearing-therapy therapist information, environmental information, and questionnaire information about the patient; and the condition information may indicate a condition of the patient using a quantitative indicator.

[0012] In addition, a cloud server-based content providing device for cognitive or language rehabilitation according to one aspect of the present disclosure includes a communication module, a storage module that stores various information about at least one patient, an AI-based learning model for providing the cognitive or language rehabilitation content, and at least one process, and a control module that performs an operation to provide the cognitive or language rehabilitation content based on the at least one process, wherein the control module, upon detecting a login of a specific account to a platform linked to the cloud server, checks the authority of the specific account, and if the check results in the specific account being a patient account, executes at least one authentication process linked to the patient account. The system collects at least one piece of medical information about the patient input from a linked account, analyzes the at least one piece of medical information to generate condition information about the patient, searches for at least one piece of content based on the condition information using an artificial intelligence-based learning model, and generates and provides training information using the at least one piece of searched content, wherein the at least one linked account includes at least one of a guardian account, a speech-language-hearing-pathologist account, a medical professional account, and a medical institution administrator account, and the at least one piece of medical information includes at least one of symptom information, diagnosis information, medical professional information, speech-language-hearing-pathologist information, environmental information, and questionnaire information about the patient, and the condition information may indicate the condition of the patient using a quantitative indicator.

[0013] In addition, a computer program stored on a computer-readable recording medium for causing a computer to execute a method for realizing the present disclosure can also be provided.

[0014] In addition, a computer-readable recording medium can be provided that records a computer program that causes a computer to execute a method for realizing the present disclosure. [Effects of the Invention]

[0015] According to the solution to the above-mentioned problem of the present disclosure, a cloud server is used to provide a training content provision service that enables patients to undergo a variety of customized rehabilitation at a desired time and place, and also enables continuous service improvement by reflecting the opinions of customers (patients, guardians, medical personnel, speech-language-hearing therapists, medical institution administrators, etc.).

[0016] In addition, the present disclosure not only provides customized content for rehabilitation related to at least one or more areas of memory, executive function, attention, auditory comprehension, speech, and reading and writing, but also allows patients to receive customized speech therapy without spatial and time constraints, and allows parents and / or medical professionals (doctors, nurses, speech-language pathologists, etc.) to monitor the patient's speech rehabilitation process, results, current status, etc.

[0017] Furthermore, according to the present disclosure, content is provided that enables rehabilitation that is suited to the patient's level, speed, time, etc., and analysis information is provided that analyzes the training pattern and / or training history, allowing not only the patient himself / herself but also guardians, medical personnel, etc. to easily check the results of training, and by accumulating and recording this, the patient's condition through rehabilitation can be continuously managed.

[0018] The effects of the present disclosure are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a diagram illustrating a network structure of a cloud server-based content provision system for cognitive or language rehabilitation according to an embodiment of the present disclosure. [Figure 2] FIG. 1 is a diagram illustrating a flow for providing content in a cloud server-based content providing system for cognitive or language rehabilitation according to an embodiment of the present disclosure. [Figure 3] FIG. 1 is a diagram illustrating the operational configuration of a cloud server-based content provision system for cognitive or language rehabilitation according to an embodiment of the present disclosure. [Figure 4] FIG. 1 is a diagram illustrating the operational configuration of a cloud server-based content provision system for cognitive or language rehabilitation according to an embodiment of the present disclosure. [Figure 5] FIG. 1 is a diagram illustrating the operational configuration of a cloud server-based content provision system for cognitive or language rehabilitation according to an embodiment of the present disclosure. [Figure 6] FIG. 1 is a diagram illustrating the operational configuration of a cloud server-based content provision system for cognitive or language rehabilitation according to an embodiment of the present disclosure. [Figure 7] 1 is a diagram illustrating a configuration of a cloud server-based content providing device for cognitive or language rehabilitation according to an embodiment of the present disclosure. [Figure 8] 10 is a diagram illustrating an operation for generating training information in a content providing method for cloud server-based cognitive or language rehabilitation according to an embodiment of the present disclosure. [Figure 9] 10 is a diagram illustrating an operation for generating analysis information in a content provision method for cloud server-based cognitive or language rehabilitation according to an embodiment of the present disclosure. [Figure 10] 10 is a diagram illustrating specific operations performed when searching for at least one content in a content provision method for cloud server-based cognitive or language rehabilitation according to an embodiment of the present disclosure. FIG. [Figure 11] 10A and 10B are diagrams illustrating specific operations performed when generating training information in a content providing method for cloud server-based cognitive or language rehabilitation according to an embodiment of the present disclosure. [Figure 12] FIG. 2 illustrates an example of patient information about a patient stored and managed via a content provider according to an embodiment of the present disclosure. [Figure 13]FIG. 10 is a diagram showing an example of a screen on which the content of training execution according to training information is displayed via a display unit on a patient terminal according to an embodiment of the present disclosure. [Figure 14] FIG. 10 is a diagram showing an example of a screen on which the content of training execution according to training information is displayed via a display unit on a patient terminal according to an embodiment of the present disclosure. [Figure 15] FIG. 10 is a diagram illustrating an example of a screen on which the content of training execution according to training information is displayed via a display unit on a patient terminal according to an embodiment of the present disclosure. [Figure 16] FIG. 10 is a diagram showing an example of a screen displayed to enable training settings for performing training via a display unit on a patient terminal according to an embodiment of the present disclosure. [Figure 17] FIG. 10 is a diagram showing an example of a screen displayed to enable training via a display unit on a patient terminal according to an embodiment of the present disclosure. [Figure 18] FIG. 10 is a diagram illustrating an example of a screen displayed on a display unit of a patient terminal to enable confirmation of training results according to an embodiment of the present disclosure. [Figure 19] FIG. 10 is a diagram illustrating an example of a screen on which analytical information based on the performance of training is displayed via a display unit on a patient terminal according to an embodiment of the present disclosure. [Figure 20] FIG. 10 is a diagram illustrating an example of a screen displaying a training performance history for a specific patient via a display unit on a patient terminal according to an embodiment of the present disclosure. [Figure 21] FIG. 10 is a diagram illustrating an example of a screen in which training results performed by a specific patient on different dates are compared and displayed via a display unit on a patient terminal according to an embodiment of the present disclosure. [Figure 22] FIG. 10 is a diagram showing an example of a screen on which results reports of training sessions conducted on different dates are displayed via a display unit on a patient terminal according to an embodiment of the present disclosure. [Figure 23]FIG. 10 is a diagram showing an example of a screen on which content for training attention via a patient terminal is displayed via a display unit on the patient terminal according to an embodiment of the present disclosure. [Figure 24] FIG. 10 is a diagram showing an example of a screen on which content for training memory via a patient terminal is displayed via a display unit on the patient terminal according to an embodiment of the present disclosure. [Figure 25] FIG. 10 is a diagram showing an example of a screen on which content for training executive function via a patient terminal is displayed via a display unit on the patient terminal according to an embodiment of the present disclosure. [Figure 26] FIG. 10 is a diagram showing an example of a screen on a display unit of a patient terminal, which displays content for training listening skills (auditory comprehension), conversation, reading and writing via the patient terminal, according to one embodiment of the present disclosure. [Figure 27] FIG. 10 is a diagram showing an example of a screen on a display unit of a patient terminal, which displays content for training listening skills (auditory comprehension), conversation, reading and writing via the patient terminal, according to one embodiment of the present disclosure. [Figure 28] FIG. 10 is a diagram showing an example of a screen on a display unit of a patient terminal, which displays content for training listening skills (auditory comprehension), conversation, reading and writing via the patient terminal, according to one embodiment of the present disclosure. [Figure 29] FIG. 10 is a diagram showing an example of a screen on a display unit of a patient terminal, which displays content for training listening ability (auditory comprehension), speaking, reading, and writing via the patient terminal, according to one embodiment of the present disclosure. [Figure 30] FIG. 10 illustrates an example of a graph generated by an embodiment of the present disclosure. [Figure 31] FIG. 10 illustrates an example of a graph generated by an embodiment of the present disclosure. [Figure 32]FIG. 10 illustrates an example of a graph generated by an embodiment of the present disclosure. [Figure 33] FIG. 10 illustrates an example of a graph generated by an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0020] The advantages and features of the present disclosure, as well as methods for achieving them, will become apparent from the following detailed description of the embodiments in conjunction with the accompanying drawings. However, the present disclosure is not limited to the embodiments shown below, and may be realized in various different forms. However, the embodiments are provided to complete the disclosure and to allow those skilled in the art to fully understand the scope of the present disclosure, and the present disclosure is defined only by the scope of the claims.

[0021] The terms used in this specification are for the purpose of describing the embodiments and are not intended to limit the present disclosure. In this specification, the singular includes the plural unless otherwise specified. The terms "comprises" and / or "comprising" used in this specification do not exclude the presence or addition of one or more other elements other than the elements listed. The same reference numerals refer to the same elements throughout this specification, and "and / or" includes each and every combination of one or more of the listed elements. Even if "first," "second," etc. are used to describe various elements, it should be understood that these elements are not limited by these terms. These terms are used merely to distinguish one element from another. Therefore, it goes without saying that a first element referred to below may also be a second element within the technical spirit of this disclosure.

[0022] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the meaning commonly understood by a person of ordinary skill in the art to which this disclosure belongs. Furthermore, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless they are clearly and specifically defined.

[0023] The same reference numerals refer to the same components throughout this disclosure. This disclosure does not describe all elements of the embodiments, and general content in the technical field to which the disclosure pertains or content that overlaps between embodiments will be omitted. The terms "module" or "module" used in this specification refer to software or hardware components such as FPGAs or ASICs, and a "module" or "module" performs a specific function. However, the term "module" or "module" is not limited to software or hardware. A "module" or "module" may be configured to reside on an addressable storage medium or to execute one or more processors. Thus, by way of example, a "module" or "module" includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, program code segments, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within the components and "units" or "modules" may be combined into fewer components and "units" or "modules" or may be further separated into additional components and "units" or "modules," etc.

[0024] Throughout this specification, when a part is said to be "coupled" to another part, this includes not only direct coupling but also indirect coupling, and indirect coupling includes connection via a wireless communication network.

[0025] Furthermore, when a part is described as "comprising" a certain component, this does not mean that other components are excluded, unless otherwise specified, and means that other components may also be included.

[0026] Throughout this specification, when an element is said to be "on" another element, this includes not only when the element is in contact with the other element, but also when there is another element between the two elements.

[0027] The terms "first," "second," etc. are used to distinguish one component from another, and the components are not limited to the terms described above.

[0028] Any expression in the singular includes a plural expression unless the context clearly indicates otherwise.

[0029] The identification numbers in each step are used for convenience of explanation and do not dictate the order of the steps, and the steps may be performed out of the order specified unless the context clearly dictates a particular order.

[0030] The terms used in the following description are defined as follows.

[0031] Although the present disclosure is limited to the content providing device 100, it may further include or take the form of a server, a computer, and / or a portable terminal.

[0032] Here, the computer may include, for example, a notebook computer, a desktop computer, a laptop computer, a tablet PC, a slate PC, etc., equipped with a web browser.

[0033] The server device is a server that communicates with external devices and processes information, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.

[0034] The portable terminal is, for example, a wireless communication device that ensures portability and mobility, and may include all kinds of handheld-based wireless communication devices such as 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) terminals, smartphones, etc., as well as wearable devices such as watches, rings, bracelets, anklets, necklaces, glasses, contact lenses, or head-mounted devices (HMDs).

[0035] The working principle and embodiments of the present disclosure will be described below with reference to the accompanying drawings.

[0036] FIG. 1 is a diagram illustrating a network structure of a cloud server-based content provision system for cognitive or language rehabilitation according to an embodiment of the present disclosure.

[0037] Referring to FIG. 1, a cloud server-based content provision system 10 for cognitive or language rehabilitation (hereinafter referred to as the "content provision system") according to one embodiment of the present disclosure can be configured to include a content provision device 100, a patient terminal 200, a parent terminal 300, a speech-language-hearing-hearing-therapy terminal 400, a medical personnel terminal 500, and a medical institution terminal 600.

[0038] The content providing device 100 is a device for providing a content providing service for rehabilitation in the content providing system 10, and can be connected by wire or wireless communication to at least one of the patient terminal 200, the guardian terminal 300, the speech-language-hearing-pathologist terminal 400, the medical staff terminal 500, and the medical institution terminal 600. In this case, the content providing device 100 is a server, but is not limited to this.

[0039] The content providing device 100 provides a content providing service based on a platform linked to a cloud server and performs subscription procedures for patients, guardians, speech-language-hearing therapists, medical professionals, and / or medical institutions who wish to receive the content providing service. At this time, accounts and permissions are set (created) for the patients, guardians, speech-language-hearing therapists, medical professionals, and / or medical institutions upon subscription, and the content providing device 100 can further perform a linking procedure between related accounts. As a result, the content providing service can be provided via the platform through each of the patient terminal 200, guardian terminal 300, speech-language-hearing therapist terminal 400, medical professional terminal 500, and medical institution terminal 600. However, different permissions may be set for each terminal, which may result in different services being provided. Each permission may be set by the service provider of the content providing device 100 and / or the medical professionals.

[0040] Specifically, when the content providing device 100 detects a login of a specific account to the platform, it checks the authority of the specific account. If the check reveals that the specific account is a patient account, the content providing device 100 collects at least one piece of medical information about the patient input from at least one linked account linked to the patient account. In this case, the at least one linked account may include at least one of a guardian account, a speech-language-hearing-therapy therapist account, a medical professional account, and a medical institution administrator account. The medical information may include at least one of medical treatment data, treatment data, symptom information, diagnosis information, medical professional information, speech-language-hearing-therapy therapist information, environmental information, and questionnaire information about the patient. Each piece of data or information included in the medical information may be input (acquired) from at least one of the patient terminal 200, the guardian terminal 300, the speech-language-hearing-therapy therapist terminal 400, the medical professional terminal 500, and the medical institution terminal 600. Here, the symptom information may include at least one piece of information regarding the patient's symptoms confirmed during medical treatment, and the diagnosis information may include at least one piece of information determined and input by the medical staff based on the symptom information, such as a diagnosis name, hearing level, expression level, and cognitive ability level.

[0041] The content providing device 100 then analyzes at least one piece of medical information to generate condition information for the patient and searches for at least one piece of content based on the condition information. The content providing device 100 generates training information for the patient using the searched at least one piece of content, and then provides the generated training information through a terminal to which the specific account is logged in, or, upon an additional request, through a patient terminal 200 corresponding to the specific account. When providing the training information, the content providing device 100 may perform a separate payment procedure. The payment may be automatically made using pre-stored payment information or may be made by manually entering payment information. The pre-stored at least one terminal may include at least one of the patient terminal 200, parent terminal 300, speech-language-hearing-therapy terminal 400, medical professional terminal 500, and medical institution terminal 600 of the patient.

[0042] In this case, when the content providing device 100 receives training result information generated by the patient performing training through the corresponding terminal to which the training information is provided, the content providing device 100 analyzes the training result information to generate analysis information about the corresponding patient, and then transmits the analysis information to at least one pre-set terminal. This training result information may store (record) the training execution level, training ratio, training area, and accuracy for each training area for the cognitive or language area by date, and each time training is performed through the patient account, the training result information is accumulated and stored, and analysis information about the corresponding patient analyzed based on the accumulated information may also be accumulated and stored or updated.

[0043] As described above, the content providing device 100 may include an AI-based learning model to generate the status information, training information, and analysis information. Here, a learning model may be provided separately for each piece of information. The operation of generating each piece of information will be described in detail below with reference to FIGS. 2 to 11.

[0044] Meanwhile, if the content providing device 100 checks the authority of the specific account and finds that the specific account is one of a parent account, a speech-language-hearing-pathologist account, a medical professional account, and a medical institution account, the content providing device 100 checks at least one patient account linked to the confirmed account. When a user of the confirmed account selects one of the patient accounts, the content providing device 100 provides analysis information corresponding to the selected patient account. In this case, the analysis information may be generated based on setting conditions (including training date, training time, training area, etc.) set by the user of the account (i.e., one of a parent, a speech-language-hearing-pathologist, a medical professional, and a medical institution administrator) through their own terminal (i.e., one of the parent terminal 300, the speech-language-hearing-pathologist terminal 400, the medical professional terminal 500, and the medical institution terminal 600). For example, analysis information including graphs and / or numerical values ​​of accuracy for each cognitive domain and / or language domain performed during a date interval (period) set according to the setting conditions may be generated.

[0045] Meanwhile, the content providing device 100 may further grant editing authority for patient information to each of the speech-language-hearing-therapy therapist account, the medical professional account, and the medical institution account. In this case, the editing authority may be different from each other. For example, a speech-language-hearing-therapy therapist may add content for further intensive training or remove content deemed unnecessary from the training information of the patient. After reviewing the training result information, the speech-language-hearing-therapy therapist may additionally perform operations such as inputting opinions (including treatment data) and / or preparing a questionnaire survey for speech-language-hearing-therapy therapists. Furthermore, a medical professional (administrator of a medical institution) may be granted authority including that of a speech-language-hearing-therapy therapist to perform the above-mentioned additional operations. After treating the patient, the medical professional may input at least one of medical data, symptom information, and diagnosis information (symptom information, diagnosis information, etc. may be included in the medical data), and after reviewing the analysis information, the medical professional may additionally perform operations such as inputting opinions and / or preparing a questionnaire survey for medical professionals (medical institutions).

[0046] Meanwhile, the patient terminal 200 is a terminal of the patient. Using the patient terminal 200, the patient receives the content provision service from the content providing device 100 based on a platform linked to a cloud server. Specifically, the patient receives training information from the content providing device 100 based on the platform via the patient terminal 200, performs training based on the training information, and transmits training result information to the content providing device 100. Thereafter, in response to this, analysis information generated based on the training result information is received from the content providing device 100, and the analysis information is displayed on the display unit of the patient terminal 200 so that the patient can check it.

[0047] Meanwhile, the parent / guardian terminal 300, the speech-language-hearing-pathologist terminal 400, and the medical personnel terminal 500 are terminals used by a parent / guardian, a speech-language-hearing-pathologist, and a medical personnel for a specific patient (i.e., linked to the account of the specific patient). The medical institution terminal 600 may include at least one of a terminal provided in the medical institution and a terminal used by an administrator of the medical institution. Through the parent / guardian terminal 300, the speech-language-hearing-pathologist terminal 400, the medical personnel terminal 500, and the medical institution terminal 600, each user inquires about or edits (including creating, inputting, and deleting) various information about a specific patient from the content providing device 100, or receives various information and / or notifications from the content providing device 100. In this case, since various information and / or notifications can be transmitted only to at least one terminal that has already been set up, even the parent / guardian, the speech-language-hearing-pathologist, the medical personnel, and the medical institution for the specific patient may not be able to receive the various information and / or notifications.

[0048] In addition, templates including formats for inputting data and information may be displayed differently depending on the respective authorities on the display units of the parent terminal 300, speech-language-hearing-hearing therapist terminal 400, medical personnel terminal 500, and medical institution terminal 600. The templates may be changed or edited by the administrator of the content providing device 100.

[0049] In explaining the present invention, the description has been limited to a case in which a specific patient receives training information via the patient terminal 200 and performs the training. However, the specific patient can also receive training information and perform the training via other terminals in addition to the patient terminal 200. For example, when a specific patient logs in via a terminal provided at a medical institution, i.e., the medical institution terminal 600, the content providing device 100 can confirm whether the login information is a patient account or a medical institution account and provide different training information depending on the confirmed account. In other words, when generating training information, the content providing device 100 can generate different training information depending on the type of terminal from which the login was performed, i.e., whether it was the patient terminal 200 or another terminal (including the parent terminal 300, speech-language-hearing-hearing therapist terminal 400, medical professional terminal 500, medical institution terminal 600, or other terminal).

[0050] Meanwhile, each of the patient terminal 200, the guardian terminal 300, the speech-language-hearing-hearing therapist terminal 400, the medical personnel terminal 500, and the medical institution terminal 600 may be a computer capable of installing and executing a number of application programs (i.e., applications) desired by the user, an Ultra Mobile PC (UMPC), a workstation, a net-book, a personal digital assistant (PDA), a portable computer, a web tablet, a wireless phone, a mobile phone, a smart phone, a pad, a smart watch, a wearable terminal, an e-book, a portable multimedia player (PMP), a portable game console, a navigation device, a black box or digital camera, or other mobile communication terminal.

[0051] That is, for each of the patient terminal 200, guardian terminal 300, speech-language-hearing-pathologist terminal 400, medical personnel terminal 500, and medical institution terminal 600, a separate application or program can be installed or connected to a web page and a content provision service can be provided from the content providing device 100 through a platform.

[0052] 1 is merely one example for convenience of explanation, and the patient terminal 200, the guardian terminal 300, the speech-language-hearing-therapy terminal 400, the medical staff terminal 500, and the medical institution terminal 600 correspond to user terminals, i.e., user terminals, for receiving services provided by the content providing system 10, and may further include terminals of other authorized institutions or other related parties. The type (model) and number of each terminal are not limited. That is, the patient terminal 200, the guardian terminal 300, the speech-language-hearing-therapy terminal 400, the medical staff terminal 500, and / or the medical institution terminal 600 may each be configured in plurality, and each terminal may be different from each other, or some or all of the terminals may be the same model.

[0053] FIG. 2 is a flowchart illustrating a method for providing predictive information through artificial intelligence-based data analysis according to one embodiment of the present disclosure, illustrating a case in which a specific patient attempts to train from the content providing device 100 via the patient terminal 200.

[0054] 2, in order to receive the content provision service, a specific patient can complete a subscription procedure through the content providing device 100. To do this, the specific patient runs the platform through the patient terminal 200, inputs subscription information into a subscription template (S101), and transmits the subscription information to the content providing device 100 (S103).

[0055] Next, the content providing device 100 registers a new patient based on the subscription information received from the patient terminal 200 (S105). Here, the subscription information includes basic information and account information (including at least one of a patient account, a guardian account, a speech-language-hearing-pathologist account, and a medical professional account) related to the specific patient. For example, the subscription information may include at least one of the name, patient number, date of birth, gender, residential address, current condition, registration date, ID (identifier), and password of the specific patient.

[0056] In this case, the operation of registering a new patient may include an operation of adding the specific patient as a recipient of service and storing the subscription information thereof, as well as an operation of linking at least one of a patient account, a guardian account, a speech-language-hearing-pathologist account, and a medical professional account related to the specific patient. However, this is only one example, and the operation of linking each account related to the specific patient may be performed by each account requesting connection with the content providing device 100.

[0057] After that, after the medical staff has treated a specific patient, they run the platform via the medical personnel terminal 500 to search for that specific patient (S107), and when medical data is input via the medical personnel terminal 500 as one of the medical information included in the patient information of the searched specific patient (S109), the medical data is sent to the content providing device 100 (S111).

[0058] Next, when the content providing device 100 receives the medical data via the medical professional terminal 500, the content providing device 100 stores the medical data together with the patient information (S113).

[0059] Thereafter, when the patient runs the platform and inputs login information (S115), the patient terminal 200 transmits the login information to the content providing device 100 (S117).

[0060] Next, the content providing device 100 performs a login completion or login rejection process based on the login information received from the patient terminal 200 (S119). Although not shown in FIG. 2, when performing login rejection process, the content providing device 100 can send a rejection notice to the patient terminal 200.

[0061] When performing the login completion process, the content providing device 100 checks the account based on the login information, checks the authority (checks whether it is a patient account) (S121), generates training information using the patient information corresponding to the patient account (S123), and then transmits the training information to the patient terminal 200 (S125).

[0062] Thereafter, when the patient performs training by displaying the training information on the display unit of the patient terminal 200 (S127), training result information is transmitted to the content providing device 100 (S129).

[0063] Next, the content providing device 100 stores the training result information received from the patient terminal 200, generates analysis information using the information (S131), and then transmits the analysis information to at least one of the previously set terminals (S133 to S139). FIG. 2 illustrates a case where the patient terminal 200, the guardian terminal 300, the speech-language-hearing-therapy terminal 400, and the medical professional terminal 500 are set as at least one terminal connected to the patient account. The analysis information is transmitted to each terminal according to the settings, but this corresponds to one embodiment. That is, the analysis information may not be transmitted to some of the terminals connected to the patient account. This can be changed and set by any terminal with setting (editing) authority. While FIG. 2 illustrates the analysis information being transmitted sequentially, this is merely one embodiment, and the analysis information may also be transmitted simultaneously. The transmission format and / or transmission order are not limited.

[0064] Meanwhile, although not shown in Figure 2, after the speech-language-hearing therapist trains with the patient based on the training information, or after the speech-language-hearing-pathologist terminal 400 receives the analysis information, the speech-language-hearing-pathologist can run the platform via the speech-language-hearing-pathologist terminal 400 and input the results of the training (i.e., training result information) or their opinions on the analysis information (including treatment data), or conduct a questionnaire survey of speech-language-hearing-pathologists related to the training result information or analysis information and send the survey results, and the training information can be further edited and / or generated to include reinforcement training.

[0065] 3 to 6 are diagrams illustrating the operational configuration of a cloud server-based content provision system for cognitive or language rehabilitation according to an embodiment of the present disclosure.

[0066] In a content providing system 10 according to an embodiment of the present disclosure, the content providing device permits access by patients, guardians, speech-language-hearing therapists (or facilitators), medical personnel (attending doctors, attending nurses, or rehabilitation staff), and administrators of medical institutions based on their respective permissions via a terminal application (mobile application) or a web application (web application) provided on a website. As a result, the content providing device 100 not only receives information about patients from patients, guardians, speech-language-hearing therapists (or facilitators), medical personnel (attending doctors, attending nurses, or rehabilitation staff in hospitals), and medical institutions, but also manages patients, provides assignments, generates content, and manages content.

[0067] Referring to FIG. 3, a medical professional or a medical institution administrator provides a function for a content provision service using a mobile application or a web application provided on a website, and a speech-language-hearing therapist provides training assignments (or additional assignments) and provides training information to patients who are training recipients via a content providing device 100. More specifically, referring to FIG. 4, a medical professional manages at least one patient and / or speech-language-hearing therapist (or facilitator) via a medical professional terminal 500 and manages API user authentication and authority. Meanwhile, a service provider of the content providing device 100 manages training assignments and content based on training assignments for each patient provided by a speech-language-hearing therapist via a speech-language-hearing therapist terminal 400. Each patient can receive training information including at least one content for training by running a platform via a patient terminal 200, or can receive the training information via email, SNS, or SMS.

[0068] 5 and 6, the content providing device 100 can manage at least one patient and manage training tasks and content for each patient through a mobile application and a web application. In addition, the content providing device 100 can provide training appropriate for each patient, manage information, data, and training history for each patient, and manage detailed item levels for providing content recommendations.

[0069] In describing the above-mentioned Figures 3 to 6, the training tasks are tasks for performing at least one of cognitive therapy and speech therapy, and may further include tasks in which cognitive therapy and speech therapy are linked to each other.

[0070] FIG. 7 is a diagram illustrating a configuration of a content providing device for cloud server-based cognitive or language rehabilitation according to an embodiment of the present disclosure.

[0071] Referring to FIG. 7, a content providing device 100 according to an embodiment of the present disclosure may include a communication module 110, a storage module 120, and a control module .

[0072] The communication module 110 performs wired or wireless communication with at least one external device (such as a server), and in particular, when performing wireless communication, transmits and receives wireless signals through a communication network using wireless internet technology.

[0073] The communication module 110 may include one or more components that enable communication with an external device, and may include, for example, at least one of a wired communication module, a wireless communication module, and a short-range communication module, based on which signals are transmitted and received.

[0074] Here, the wired communication module may include various wired communication modules such as a local area network (LAN) module, a wide area network (WAN) module, or a value-added network (VAN) module, as well as various cable communication modules such as a universal serial bus (USB), a high definition multimedia interface (HDMI), a digital visual interface (DVI), a recommended standard-232 (RS-232), a power line communication module, or a plain old telephone service (POTS).

[0075] The wireless communication module may include a Wi-Fi module, a WiBro (Wireless Broadband) module, or a wireless communication module supporting various wireless communication methods such as GSM (Global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), UMTS (universal mobile telecommunications system), TDMA (Time Division Multiple Access), WLAN (Wireless LAN), DLNA (Digital Living Network Alliance), WiBro (Wireless Broadband), WiMAX (World Interoperability for Microwave Access), HSDPA (High Speed ​​Downlink Packet Access), HSUPA (High Speed ​​Uplink Packet Access), LTE (Long Term Evolution), 4G, 5G, and 6G.

[0076] The short-range communication module is for short-range communication and can support short-range communication using at least one of Bluetooth (registered trademark), RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra Wideband), ZigBee (registered trademark), NFC (Near Field Communication), Wi-Fi (Wireless-Fidelity), Wi-Fi Direct, and Wireless Universal Serial Bus (Wireless USB) technologies.

[0077] Specifically, the communication module 110 transmits and receives various information via wired or wireless communication to and from at least one of the patient terminal 200, the guardian terminal 300, the speech-language-hearing-therapy terminal 400, the medical staff terminal 500, and the medical institution terminal 600. That is, via the communication module 110, it is possible to receive subscription information, login information, medical data, treatment data, training result information, etc., and transmit training information, analysis information, etc.

[0078] The storage module 120 stores data and / or various information supporting various functions of the content providing device 100. It can store data and commands for the operation of a number of application programs (or applications) run by the content providing device 100. At least some of these application programs can be downloaded from an external server via wireless communication. Meanwhile, the application programs can be stored in at least one memory included in the storage module 120, installed on the content providing device 100, and driven to perform operations (or functions) by at least one processor included in the control module 130.

[0079] Meanwhile, the at least one memory may include at least one type of storage medium selected from the group consisting of flash memory type, hard disk type, multimedia card micro type, card-type memory (e.g., SD or XD memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, and optical disk. The memory may store information temporarily, permanently, or semi-permanently, and may be built-in or removable.

[0080] The storage module 120 may build and include a database for providing content for cognitive or language rehabilitation based on a cloud server. This database may store patient information (e.g., basic information, medical information (including at least one of symptom information, diagnosis information, medical data, treatment data, and treatment history information) and / or additional information) for each of at least one patient who has subscribed to the content providing service. To this end, the storage module 120 may interface with a cloud server.

[0081] The control module 130 may include at least one processor and may control all components within the content providing device 100 to process input or output signals, data, information, etc., or may execute instructions, algorithms, and application programs stored in at least one memory to perform various processes, provide predictive information through data analysis using artificial intelligence, or provide or process appropriate information or functions for managing a database.

[0082] That is, the control module 130 controls all operations performed by the content providing device 100 described above with reference to FIGS.

[0083] Specifically, when the control module 130 detects a login of a specific account to a platform linked to a cloud server, it checks the authority of the specific account and controls the control module 130 to generate and provide one of the pieces of information that can be provided based on the check result.

[0084] For example, if the control module 130 determines that the specific account is a patient account as a result of the verification, it collects at least one piece of medical information about the patient input from at least one linked account linked to the patient account, analyzes the at least one piece of information, and generates condition information for the patient. Thereafter, the control module 130 searches for at least one piece of content based on the condition information using an AI-based learning model, generates training information using the at least one piece of content, and controls the generation of training information to be transmitted to the patient terminal 200, thereby providing the content provision service to the patient.

[0085] Meanwhile, when the control module 130 receives training result information from the patient terminal 200 in response to the training information, it generates analysis information based on the training result information and controls the information to be sent not only to the patient terminal 200 but also to at least one of the terminals already set up among the terminals linked to the patient account (including at least one of the parent terminal 300, speech-language-hearing-hearing therapist terminal 400, medical personnel terminal 500, and medical institution terminal 600).

[0086] Meanwhile, if the control module 130 determines that the specific account is one of a guardian account, a speech-language-hearing-pathology therapist account, a medical professional account, and a medical institution account, it provides the medical information of the patient searched and selected by the corresponding account and controls to allow editing operations such as inputting or deleting additional information or data. At this time, the provided medical information may include different information or data depending on the authority of the corresponding account. That is, it may not provide all of the patient's medical information, but may provide only partially permitted information / data depending on the authority.

[0087] FIG. 8 is a diagram illustrating an operation for generating training information in a content providing method for cloud server-based cognitive or language rehabilitation according to an embodiment of the present disclosure.

[0088] 8, when the content providing device 100 detects a login of a specific account to the platform, it checks the authority of the specific account (S210). If the check result shows that the specific account is a patient account, the content providing device 100 collects at least one piece of medical information about the patient input from at least one linked account linked to the patient account (S220).

[0089] Thereafter, the content providing apparatus 100 analyzes at least one piece of medical information collected in step S220 to generate condition information of the patient (S230), and searches for at least one piece of content based on the condition information (S240).

[0090] The content providing device 100 then generates training information for the patient using at least one of the retrieved contents, and transmits and provides the generated training information to the terminal where the login was made or the terminal designated (selected) by the patient (S250).

[0091] Meanwhile, although not shown in FIG. 8, after generating the training information in step S250, a payment operation can be further performed before providing the training information to the terminal where a specific account is logged in.

[0092] FIG. 9 is a diagram illustrating an operation for generating analysis information in a content providing method for cloud server-based cognitive or language rehabilitation according to an embodiment of the present disclosure.

[0093] Referring to FIG. 9, when the content providing device 100 receives training result information generated by the patient training through the corresponding terminal to which the training information has been provided (S260), the content providing device 100 analyzes the training result information to generate analysis information about the corresponding patient (S270), and then transmits the analysis information to at least one terminal that has been previously set (S280).

[0094] In describing FIGS. 8 and 9, the same details as those described above with reference to FIGS. 1 to 7 will be omitted.

[0095] FIG. 10 is a diagram showing specific operations performed when searching for at least one content in a content provision method for cloud server-based cognitive or language rehabilitation according to one embodiment of the present disclosure, and shows detailed operations of step S240 of FIG. 8.

[0096] Referring to FIG. 10, the content providing device 100 checks the type of each content based on tag information of the content already stored on the cloud server through big data analysis (S241), and searches for at least one content based on the checked type of content (S242).

[0097] Here, the tag information includes detailed sub-categories, thereby providing language rehabilitation content more suited to each individual patient. That is, the content providing device 100 can identify a patient's weaknesses in the sub-categories among the tag information and search for language rehabilitation content including tag information for strengthening the corresponding sub-categories. Specifically, the language rehabilitation content includes tag information of #memory, #executive ability, and #attention in the cognitive rehabilitation category area, and tag information of #auditory comprehension, #speaking, #reading, and #writing in the language rehabilitation category area. For example, when a patient clicks on the cognitive rehabilitation category area for language rehabilitation, content for language rehabilitation including tag information of #memory and #attention may be displayed at the top so that the patient can improve their memory and attention.

[0098] Meanwhile, the pre-stored content may be content collected based on big data and / or content transmitted and accumulated / stored from at least one of the speech-language-hearing-pathologist terminal 400, the medical personnel terminal 500, and the medical institution terminal 600. For example, the pre-stored content may include at least one of cognitive therapy content, first speech-language therapy content, and second speech-language therapy content. Here, the first speech-language therapy content may be content that can be used in conjunction with cognitive therapy without a speech-language-hearing-pathologist, and the second speech-language therapy content may be content that can be performed offline or online through a speech-language-hearing-pathologist.

[0099] This involves searching for at least one content that needs to be performed based on the condition information of the patient, and this operation can be performed by any one of at least one learning model provided in the content providing device 100.

[0100] FIG. 11 is a diagram illustrating specific operations performed when generating training information in a content providing method for cloud server-based cognitive or language rehabilitation according to an embodiment of the present disclosure.

[0101] Referring to FIG. 11, the content providing device 100 evaluates at least one of the cognitive level and language level of the patient using previously stored quantitative indicators (S251), and determines the difficulty of training for the patient based on the evaluation results (S252).

[0102] Next, the content providing device 100 selects at least one content corresponding to the determined training difficulty level from the at least one content searched for in step S250 (S253), and then determines a training order for the at least one selected content and generates training information (S254).

[0103] That is, the user can perform training in the order in which at least one selected content is arranged (deployed) on the display unit of the corresponding terminal according to the training order determined in step S254.

[0104] However, this is only one example, and step S254 can be omitted. In this case, at least one selected content is arranged (displayed) in a desired order on the display unit of the corresponding terminal, so that the user can train in the order he or she desires.

[0105] 7, the content providing device 100 has been described as including only the communication module 110, the storage module 120, and the control module 130. However, this is merely for convenience of explanation, and the components may further include modules classified according to the operations for providing the content providing service. For example, an evaluation module for step S251, a content selection module for step S253, an analysis module for step S270, etc. The names of these modules are not limited.

[0106] FIG. 12 is a diagram illustrating an example of patient information about a patient that is stored and managed via a content providing device according to an embodiment of the present disclosure.

[0107] 12, a content providing device 100 according to an embodiment of the present disclosure stores (registers) patient information for each patient to create a database. At this time, each patient information may include basic information, symptom information, and additional information of the patient.

[0108] Here, the basic information may be information input when the patient subscribes to a content provision service provided by the content provision device 100 via the platform. The symptom information may include the diagnosis, hearing level, expression level, and cognitive ability level of the patient, and may further include other additional information (notes). Here, the symptom information is information input according to the authority of a medical professional and a speech-language-hearing therapist who are capable of making a medical diagnosis (judgment), while the additional information may be information input by at least one of the patient, guardian, speech-language-hearing therapist, medical professional, and medical institution administrator via the platform.

[0109] For example, the language ability of the patient can be evaluated in each rehabilitation field within the language rehabilitation category (cognitive rehabilitation category, comprehension rehabilitation category, and expression rehabilitation category) based on basic information, symptom information, and additional information about the patient, and content for language rehabilitation can be recommended and provided. Below, an example of providing training information for providing content for language rehabilitation tailored to the patient will be described with reference to Figures 13 to 15.

[0110] 13 to 15 are diagrams showing examples of screens on which the content of training performed based on training information is displayed on the display unit 201 of the patient terminal 200 according to an embodiment of the present disclosure.

[0111] 13, the content providing device 100 provides a training mode 930 for providing customized language rehabilitation content to a patient through a platform. The training mode 930 may be provided according to the cognitive rehabilitation category and the language rehabilitation category. Furthermore, the training mode 930 may provide patient list information 910 and patient profile information 920, and provide training content according to the cognitive rehabilitation category 940, i.e., a list 950 including content for language rehabilitation. As shown in FIG. 13, the language rehabilitation content provided in the cognitive rehabilitation category 940 includes tag information of #attention, #memory, #calculation, and #thinking, and provides a type of training corresponding to each tag information.

[0112] Referring to FIG. 14, the comprehension rehabilitation category 1010 also provides a list of content for language rehabilitation. The content for language rehabilitation provided in the comprehension rehabilitation category 1010 includes tag information of #auditory comprehension and #reading comprehension, respectively. In the list of content for language rehabilitation, each training content box 1020 displays a content preview photo, name, and difficulty level (training difficulty of the corresponding content). For example, when a patient selects (checks, touches, or clicks) a training content box, the selected training content 1030 can be provided in the right tab bar. In this case, the selected training content can be displayed together with the name / area exposure and a deselect button. When multiple training contents are selected, the selected multiple training contents can be displayed in a list in the tab bar. Meanwhile, when a patient presses the start button 1040, training for at least one content selected by the patient begins.

[0113] Referring to FIG. 15, information about the expression rehabilitation category is provided, and the expression rehabilitation category also provides a list of content for language rehabilitation. The content for language rehabilitation provided in the expression rehabilitation category may include tag information such as #speaking, #speechreading, and #writing. Both the list and tab bar composed of content for language rehabilitation as described above can be supported in training mode.

[0114] 16 is a diagram showing an example of a screen displayed to allow a patient to set up training via a display unit on a patient terminal according to an embodiment of the present disclosure. This training setting screen can be displayed on the display unit 201 of the patient terminal 200 when the patient checks, touches, clicks, or otherwise presses the "Start button" in a tab bar listing one of the training contents in a list of contents for language rehabilitation.

[0115] 16, a training content preview photo 1210 and a training field description 1220 including the difficulty level, content name, and training description are provided, and information on the stage description 1240, stage setting 1250, number of questions 1260, and presentation time setting 1270 can be provided along with training keywords 1230 applicable to eight improvement areas. Then, by pressing the "Start button," training for the content selected by the patient begins.

[0116] Fig. 17 is a diagram showing an example of a screen displayed on a display unit of a patient terminal to allow a patient to perform training according to an embodiment of the present disclosure. Fig. 18 is a diagram showing an example of a screen displayed on a display unit of a patient terminal to allow a patient to check training results according to an embodiment of the present disclosure. Here, the screen displayed to allow a patient to perform training is a screen that appears when training starts, and the screen displayed to allow a patient to check training results is a screen that appears when training ends, i.e., when all training is completed.

[0117] Referring to Figure 17, the training content provided to the patient can be moved to the previous question 1310 or the next question 1320, and the training can also be ended by clicking the Stop Training button 1330. When all the training provided through this screen is completed, a training end screen can be displayed as shown in Figure 18. Referring to Figure 18, the training results can be simply provided, and buttons for "Go to Home Screen" and "Check Report" can also be provided.

[0118] FIG. 19 is a diagram showing an example of a screen on which analytical information resulting from the execution of training is displayed via a display unit on a patient terminal according to one embodiment of the present disclosure, and may be a screen that appears when the patient checks, touches, or clicks the “Check Report” button shown in FIG. 18 .

[0119] Referring to FIG. 19, the patient's training area ratio and area data query result 1510 is provided, along with detailed area-specific accuracy results 1520. The patient's training area ratio and area data query result 1510 visualizes cumulative data for each area by learning date in a donut chart, providing notation results for eight notation areas (attention, memory, problem-solving, auditory comprehension, reading comprehension, conversation, speech reading and writing), and providing area data query results for the area name, training ratio, total number of questions, and average level. The detailed area-specific accuracy results 1520 provide a bar graph showing the accuracy rate for each learning area on the query date and the accuracy rate (y-axis) for each of the eight areas (x-axis). Furthermore, the present invention provides summary results 1530 for each training area, including summary boxes summarizing each of the three areas—cognitive rehabilitation category, comprehension rehabilitation category, and expression rehabilitation category—as well as calculating and providing the average level of all training questions, and displaying the accuracy rate for the entire training. Detailed data query result 1540 is also provided, showing the training history for the corresponding area content. For example, information about the average level, name, average stage, total number of questions, number of correct answers, accuracy, and average reaction time can be provided.

[0120] FIG. 20 is a diagram illustrating an example of a screen on which a training performance history for a specific patient is displayed via a display unit on a patient terminal according to an embodiment of the present disclosure.

[0121] Referring to Figure 20, the accuracy (correct answer rate) for each question included in the training content is provided as a numerical graph, and a "Go to Training" button can be provided to move to the screen for setting up training for the corresponding question (Figure 16) and perform training.

[0122] FIG. 21 is a diagram showing an example of a screen on which training results performed on different dates by a specific patient are compared and displayed via a display unit on a patient terminal according to an embodiment of the present disclosure, and FIG. 22 is a diagram showing an example of a result report for each of the training results performed on different dates according to an embodiment of the present disclosure.

[0123] First, referring to FIG. 21, a result comparison screen 1710 before date selection and a result comparison screen 1720 after date selection are provided, allowing the patient to visually confirm the results of improved language training by performing the training content themselves.

[0124] 22, a result comparison screen 1710 before the date selection and a result comparison screen 1720 after the date selection can provide respective result reports. For example, result data for the training name / total number of questions / average accuracy / average reaction time for the periods of comparison groups A and B can be provided, and the total number of questions by area, accuracy and stage comparison by detailed area, average reaction time by area, and accuracy and stage comparison results for the cognition / comprehension / expression areas can be provided in graph form.

[0125] Even if FIG. 22 is not shown as a screen displayed on the display unit 201 of the patient terminal 200, this can also be displayed and provided on the display unit 201 of the patient terminal 200.

[0126] On the other hand, the training provided by the present disclosure can be classified into the areas of attention, memory, executive function (executive function), comprehension (perceptual function), and language ability (language function). Below, training for each area will be explained with reference to Figures 23 to 29.

[0127] FIG. 23 is a diagram illustrating an example of a screen on which content for training attention via a patient terminal is displayed on a display unit of the patient terminal according to an embodiment of the present disclosure.

[0128] First, attention can be divided into the sub-domains of sustained attention (the mental function of concentrating for a required period of time), selective attention (the mental function of selecting from competing internal or external stimuli and focusing on the selected stimulus), shifting attention (the mental function of refocusing from one stimulus to another), and divided attention (the mental function of focusing on two or more stimuli simultaneously).

[0129] For example, attention is the ability to focus on the information we need at that moment among the many pieces of information that come in through our eyes and ears, which are the organs that receive the main information from the outside world, and it is a means of limiting the amount of information we actually process. Attention training can include sub-categorization areas such as "reacting," "checking the same picture," "following a pattern," "calculating," and "counting numbers."

[0130] Referring to Figure 23, this corresponds to the "check the same picture" training in attention training, which is training to recognize visual stimuli (pictures), maintain attention, and respond to the same visual stimuli (pictures).

[0131] For example, you can set the training stage, number of questions, and presentation speed, check the picture, and then press a button if a picture similar to the example picture appears. Whether the answer is correct or not can be automatically determined.

[0132] FIG. 24 is a diagram illustrating an example of a screen on which content for training memory is displayed via a patient terminal on a display unit of the patient terminal according to an embodiment of the present disclosure.

[0133] First, memory can be divided into the sub-areas of short-term memory (a mental function that involves short-term memory, which is temporary and easily lost, stored for about 30 seconds, and is lost unless it is consolidated into long-term memory), long-term memory (a mental function that organizes short-term memory, autobiographical memory, which is information stored about past events, and semantic memory, which is information stored about language and facts, into a memory system that stores information for a long period of time), and working memory (a mental function that compares and processes information recalled in both short-term and long-term memory).

[0134] For example, memory is a series of processes in which information is registered, retained, or stored, and then recalled or retrieved after a period of time, and refers to not only receiving but also processing and combining received information, and recall is the recall of stored information in a specific situation. Memory training can include sub-categorization areas such as "remembering the same picture," "remembering the same sound," "remembering a location," "remembering a word," and "remembering a number."

[0135] Referring to Figure 24, this corresponds to "remembering the same sound" among memory training, and this training is training to recognize auditory stimuli (sounds) and remember the positional relationships between the same stimuli.

[0136] For example, you can set the training stage, number of questions, and presentation speed, select the flipped cards, check all the sounds, and then select the memorized sound position to match the pairs. Whether the answer is correct or not is automatically determined.

[0137] FIG. 25 is a diagram illustrating an example of a screen on which content for training executive ability is displayed via a display unit on a patient terminal according to an embodiment of the present disclosure.

[0138] First, executive abilities can be divided into the following subcategories: abstraction (mental functions that create general concepts, properties, or characteristics that are distinct from concrete facts, specific objects, or actual situations), organizing and planning (mental functions that organize and systematize parts into a whole; mental functions involved in developing ways to proceed or perform a task), cognitive flexibility (mental functions involved in problem-solving, that change strategies or shift mental states), judgment (mental functions involved in distinguishing between alternatives, such as functions involved in forming opinions), and problem-solving (mental functions that identify, analyze, and integrate irrelevant or conflicting information to find a solution).

[0139] For example, executive skills include understanding numbers, symbols and mathematical expressions, solving numerical problems by reasoning and understanding, and cognitive strategies for processing information and making inferences. Training for executive skills can include such sub-areas as "calculating amounts," "finding differences," "categorizing," "finding rules," and "decoding symbols."

[0140] Referring to Figure 25, this corresponds to the "find something different" training in executive function training, which trains participants to recognize and interpret visual stimuli (pictures) and to abstract and judge the relationships between stimuli.

[0141] For example, you can set the training stage, the number of questions, and the time limit, and after checking the pictures presented, you can select one of the pictures that corresponds to a different one. Whether the answer is correct or not can be automatically determined.

[0142] 26 to 29 are diagrams showing examples of screens on which content for training in listening (auditory comprehension), speaking, reading and writing is displayed via a patient terminal on a display unit of the patient terminal according to one embodiment of the present disclosure.

[0143] Language ability can be divided into the following subcategories: spoken language comprehension (the mental function of interpreting spoken messages and grasping their meaning), spoken language expression (the mental function necessary to create meaningful spoken messages), written language comprehension (the mental function of interpreting written messages and grasping their meaning), and written language expression (the mental function necessary to create meaningful written messages).

[0144] In other words, language ability can be divided into speaking, listening, reading, and writing, but listening (auditory comprehension) belongs to the area of ​​language comprehension, and this ability is the ability to hear and understand messages in oral communication situations and communicate smoothly. Training for listening (auditory comprehension) can include sub-categorization areas such as "O / X selection (picture)", "O / X selection (word)", "auditory word recognition", "finding the correct answer from a picture (listening)", "meaning-picture matching (listening)", "listening and arranging words", and "following instructions (listening)".

[0145] Referring to Figure 26, this corresponds to the "O / X selection" training in listening (auditory comprehension), which is training to interpret visual stimuli (pictures) and auditory stimuli (words), understand their meanings, and compare them.

[0146] For example, you can set the training stage, number of questions, and time limit, press the sound button to hear the audio, compare the meaning of the stimuli, and select O or X. Whether the answer is correct or not will be automatically determined.

[0147] Conversation, on the other hand, belongs to the expressive domain of language, and this ability is the ability to express a message and communicate smoothly in oral communication situations. Non-verbal communication, such as speed, pitch, volume, and voice characteristics, greatly influences how we interpret what is being said. Conversation training can include sub-domains such as "practicing prosody," "practicing automatic speech," "talking about words," "talking about non-words," "speaking names," "talking about numbers," "listening to explanations and speaking the correct answer," "talking about sentences," "associating words," "explaining," and "combining words (speaking)."

[0148] Referring to Figure 27, this corresponds to "word association" among conversational training, which is training to interpret visual stimuli (presented words), understand their meaning, infer and judge them, and convert them into audio expressions (words).

[0149] For example, you can set the training stage, number of questions, and time limit, check the suggested words, press the record button to speak the correct answer, and press the play button to confirm. Whether the answer is correct or not will be automatically determined.

[0150] Reading also refers to reading fluency, i.e., reading aloud with the correct intonation and expression at an appropriate speed using words that have been read aloud. Reading training can include sub-categorization areas such as "picture-word matching," "word-picture matching," "fill in the blank," "find the answer in the picture (reading)," "reading numbers," "reading non-words," "meaning-picture matching (reading)," "meaning-word matching (reading)," "reading a sentence," and "following instructions (reading)."

[0151] Referring to FIG. 28, this corresponds to "word reading" among the reading training, and this training involves interpreting visual stimuli (words) and converting them into audio expressions (words).

[0152] For example, you can set the training stage, number of questions, and time limit, and after checking the words, you can press the record button to speak the words and press the play button to check. Whether the answer is correct or not will be automatically determined.

[0153] Writing, on the other hand, is a complex language domain that is based on listening, speaking, and reading skills. It includes writing, spelling, and composition. The ultimate goal is composition, which requires orthographic notation and the executive functions required in the writing process. Writing training can include sub-domains such as "copying," "fill in the blanks," "picture-based writing," "dictation," and "word combination (writing)."

[0154] Referring to Figure 29, this corresponds to the "copying" part of writing training, which involves interpreting visual stimuli (words) and converting them into physical movements (writing).

[0155] For example, you can set the training stage, number of questions, and time limit, and then have the user press the write button to copy the words (the eraser button can erase all the input). The system can automatically determine whether the answer is correct or not.

[0156] 23 to 29, the difficulty level of each of the small classification areas can be set before training. For example, the greater the number of visual and / or auditory stimulating elements, or the shorter the presentation speed and / or time limit, the higher the difficulty level is set.

[0157] Each of FIGS. 30 to 33 is a diagram showing an example of a graph generated by an embodiment of the present disclosure.

[0158] 30 and 31, five higher-level areas, namely, attention, memory, executive function, comprehension (perceptual function), and language ability (language function), can be configured to generate a spider web chart as shown in Figure 30 and / or a bar chart as shown in Figure 31. The score for each area is a total score, calculated based on the scores for the lower-level areas (average score).

[0159] In this case, scores for each of the areas of attention, memory, executive function, comprehension (perceptual function), and language ability (language function) can be calculated based on the scoring system shown in Table 1 below.

[0160] [Table 1]

[0161] The scores thus calculated for each region can be used to generate spider web charts, semicircle charts and / or bar charts.

[0162] 32 and 33, the scores can be viewed by selecting the upper regions, and by configuring the subregions of each of the five upper regions, a semicircle chart as shown in Fig. 32 and / or a progress chart as shown in Fig. 33 can be generated. In this case, a standard score (Z-score) or an inverse efficiency score (IES) for accuracy and reaction time can be calculated based on the Pass / Fail scoring system.

[0163] In this case, the standard score is calculated by calculating the accuracy and reaction time related scores using the following formula 1, and the ranking is analyzed based on these two scores.

[0164]

number

[0165] Meanwhile, the reaction time for each task in each content has a speed-accuracy trade-off effect. According to the speed-accuracy trade-off effect, if the subject responds quickly, the number of incorrect responses increases, and if the subject responds slowly, the number of correct responses increases. In other words, an accurate response requires more time for processing, so reaction time inevitably becomes slower.

[0166] Reaction times were converted to inverse efficiency scores (IES) (Townsend & Ashby, 1983), which are calculated by taking into account the presence or absence of correct responses in reaction time. The inverse efficiency score (IES) is calculated by dividing the reaction time (RT) by the "1 - error response rate" and can be calculated using the following formula:

[0167]

number

[0168] Here, RT indicates the reaction time of correct response, and PC indicates the proportion of correct response.

[0169] On the other hand, additional analysis methods may be used, including at least one of a first analysis method using perseverative responses, a second analysis method using trails to complete the first task, a third analysis method using failure to maintain, and a fourth analysis method using unilateral neglect.

[0170] Specifically, the first analysis method measures the number of times the same behavior is repeated without correction (for example, repeatedly touching the same area or repeatedly choosing the same answer as before, which means that new things cannot be learned and adapted), while the second analysis method measures the process of learning and adapting through repeated failures (for example, the number of attempts required to get the correct answer to a one-step number memorization problem).

[0171] The third analysis method measures the process from consecutively giving correct answers (for example, 3 to 5 consecutive correct answers) to making an error (for example, making 3 consecutive errors after 5 consecutive correct answers in a 4-step number counting test). The fourth analysis method uses the characteristic that correct responses are concentrated on the left or right side, and standardized tests for this include star cancellation, the Albert test, and the Bells test (for example, if the example presented on the right is the correct answer, the subject will respond correctly, but if the correct answer is on the right, the subject will respond slowly or will select the example on the right and respond incorrectly).

[0172] Meanwhile, the disclosed embodiments may be realized in the form of a recording medium storing computer-executable instructions. The instructions may be stored in the form of program code, which, when executed by a processor, generates program modules to perform the operations of the disclosed embodiments. The recording medium may be realized as a computer-readable recording medium.

[0173] Computer-readable recording media include all types of recording media that store computer-readable instructions, such as ROM (Read Only Memory), RAM (Random Access Memory), magnetic tape, magnetic disk, flash memory, and optical data storage devices.

[0174] The disclosed embodiments have been described above with reference to the accompanying drawings. Those skilled in the art will understand that the present disclosure may be embodied in forms different from the disclosed embodiments without changing the technical concept or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be construed as limiting.

[0175] This invention is the result of research and development conducted as part of the research theme "Demonstration of computerized cognitive rehabilitation treatment technology for home rehabilitation of patients with cognitive impairment" (RS-2023-00263587).

Claims

1. A content provision method for cloud server-based customized rehabilitation, which is performed by a device, comprising: detecting a login of a specific account to a platform linked with the cloud server, and if the specific account is a patient account, collecting at least one piece of medical information about the corresponding patient input from at least one linked account linked with the patient account; analyzing the at least one piece of medical information to generate condition information for the corresponding patient; searching for at least one content based on the state information using an artificial intelligence-based learning model; generating training information using the at least one retrieved content; providing the generated training information; A content providing method for custom-made rehabilitation based on a cloud server, including:

2. The step of searching for at least one piece of content includes: determining the type of each content based on tag information of the content already stored in the cloud server through big data analysis; searching for the at least one piece of content based on the identified type of content; The method of claim 1, further comprising:

3. After the step of providing the training information, receiving training result information generated by the patient training based on the training information, and analyzing the training result information to generate analysis information regarding the patient; transmitting the analysis information to at least one pre-configured terminal; The method of claim 2, further comprising:

4. The training result information is The extent of training for cognitive and language areas, training ratio, training area, and accuracy for each training area are recorded by date. The analytical information is The content provision method for customized rehabilitation based on a cloud server, as described in claim 3, characterized in that when a user of the at least one terminal sets a date range, the content is generated using training result information included in the set date range and displayed as at least one of a graph and a numerical value through the display of the at least one terminal.

5. The step of generating training information comprises: Evaluating at least one of the cognitive level and language level of the patient using a quantitative index; determining the difficulty level of training for the patient based on the evaluation results; selecting, from the at least one piece of retrieved content, the at least one piece of content that corresponds to the determined difficulty level of the training; determining a training order based on the at least one selected content; The method for providing content for customized rehabilitation based on a cloud server according to claim 2, comprising:

6. At least one terminal that has already been configured The system includes at least one of a patient terminal of the patient, a medical personnel terminal of each of at least one medical personnel, a speech-language-hearing-pathologist terminal of each of at least one speech-language-hearing-pathologist, a parent terminal of each of at least one parent, and a terminal provided in each of at least one medical institution, The patient, the at least one medical professional, the at least one speech-language-hearing therapist, the at least one guardian, and the at least one medical institution are set to have different authorities for information about the patient; The content providing method for customized rehabilitation based on a cloud server according to claim 3, wherein the analysis information is generated differently depending on the set authority.

7. When request information requesting that the training information be provided to the patient terminal is received, a payment procedure is performed; The content providing method for customized rehabilitation based on a cloud server according to claim 6, wherein the payment procedure is performed automatically or manually based on pre-registered payment information.

8. Content already stored is cognitive therapy content, first language therapy content, and second language therapy content; The first speech therapy content is content that can be used in conjunction with cognitive therapy without a speech-language-hearing therapist, The method of claim 2, wherein the second speech therapy content is content that can be executed offline or online through a speech-language-hearing therapist.

9. The training information is transmitted to the terminal where the login is performed; The step of generating training information comprises: The method of claim 8, wherein the training information is generated differently depending on the type of the logged-in terminal.

10. a communication module; a storage module storing at least one process for providing content for cloud server-based cognitive or language customized rehabilitation; a control module that performs operations to provide the content based on the at least one process; Including, The control module A login of a specific account to a platform linked to the cloud server is detected, and if the specific account is a patient account, at least one piece of medical information about the corresponding patient input from at least one linked account linked to the patient account is collected; analyzing the at least one medical information to generate condition information for the corresponding patient; Searching for at least one piece of content based on the state information using an artificial intelligence-based learning model; A content providing device for cloud server-based customized rehabilitation, which generates and provides training information using the at least one retrieved content.

Images