Device and method for recommending customized training content for patients

Abstract

The present disclosure relates to a device for recommending customized training content for patients and a method therefor. The device identifies the cognitive abilities that a patient lacks to provide suitable training content for the patient and calculates cognitive scores and predicts scores for different cognitive evaluation methods from the training method acquiring corresponding cognitive scores to provide the predicted score. The research and development project name under this patent is "Development of AI Customized Rehabilitation Training Solution for Stroke Patients and Telehealthcare Service" (Project Number: P0025911), and the project was conducted with the support of the Korea Institute for Advancement of Technology under the Ministry of Trade, Industry and Energy of the Republic of Korea.

Description

Device and method for recommending patient-tailored training content

[0001] The present disclosure relates to a training content recommendation device and method. More specifically, the present disclosure relates to a label code-based, patient-tailored training content recommendation device and method.

[0002] As modern society enters an aging society, cognitive impairment is emerging as a major social problem. Currently, there are no specifically developed medications for cognitive impairment, making treatment difficult.

[0003] Therefore, it is important to diagnose and prevent cognitive impairment early and slow its progression, and there is a growing consumer need for training content to treat patients.

[0004] The purpose of the embodiment disclosed in this disclosure is to identify a patient's cognitive deficiencies and provide training content tailored to the patient.

[0005] The purpose of the embodiments disclosed in this disclosure is to provide a predicted score by calculating a cognitive score and predicting a score for a cognitive ability assessment method different from the training method that obtained the cognitive score.

[0006] The problems to be solved by the present disclosure are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

[0007] A patient-tailored training content recommendation device according to the present disclosure for solving the above-described problem may include a profile receiving unit that receives a patient profile including basic information and cognitive information of the patient; a cognitive ability evaluation unit that evaluates the patient's cognitive ability based on the patient profile and calculates a cognitive score for each function of the patient; a training recommendation unit that recommends at least one training content through an artificial intelligence rehabilitation recommendation model; and a training execution unit that calculates a result for the training content provided to the patient through a user terminal.

[0008] In addition, a method for recommending patient-tailored training content according to the present disclosure for solving the above-described problem may include: receiving a patient profile including basic information and cognitive information of the patient; evaluating the patient's cognitive ability based on the patient profile to calculate a cognitive score for each function of the patient; recommending at least one training content through an artificial intelligence rehabilitation recommendation model; and calculating a result for the training content provided to the patient through the user terminal.

[0009] In addition, a computer program stored in a computer-readable recording medium for executing a method for implementing the present disclosure may be further provided.

[0010] In addition, a computer-readable recording medium recording a computer program for executing a method for implementing the present disclosure may be further provided.

[0011] According to the aforementioned problem solving means of the present disclosure, it provides the effect of identifying a patient's cognitive deficiencies and providing training content suited to the patient.

[0012] According to the aforementioned problem solving means of the present disclosure, a cognitive score is calculated, and an effect of predicting a score for a cognitive ability evaluation method different from the training method that obtained the cognitive score is provided by providing the predicted score.

[0013] The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

[0014] FIG. 1 is a diagram illustrating a patient-tailored training content recommendation system according to the present disclosure.

[0015] FIG. 2 is a drawing illustrating the physical configuration of a patient-tailored training content recommendation device according to the present disclosure.

[0016] FIG. 3 is a diagram illustrating the functional configuration of a patient-tailored training content recommendation device according to the present disclosure.

[0017] FIG. 4 is a diagram illustrating the sequence in which a method for recommending patient-tailored training content according to the present disclosure is performed.

[0018] FIG. 5 is a drawing illustrating a main screen in which a patient-tailored training content recommendation device according to the present disclosure is implemented.

[0019] FIG. 6 is a drawing illustrating a screen providing a patient list through a patient-tailored training content recommendation device according to the present disclosure.

[0020] FIG. 7a and FIG. 7b are diagrams illustrating training content provided by a patient-tailored training content recommendation device according to the present disclosure.

[0021] FIG. 8a and FIG. 8b are diagrams illustrating training content recommended by a patient-tailored training content recommendation device according to the present disclosure.

[0022] FIG. 9 is a diagram illustrating the results of training content provided by a patient-tailored training content recommendation device according to the present disclosure.

[0023] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and any content that is common in the technical field to which this disclosure pertains or that overlaps between embodiments is omitted. The terms "part, module, element, block" used in the specification may be implemented in software or hardware, and depending on the embodiments, multiple "parts, modules, elements, blocks" may be implemented as a single component, or a single "part, module, element, block" may include multiple components.

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

[0025] Additionally, when a part is said to "include" a component, this does not mean that it excludes other components, but rather that it may include other components, unless otherwise specifically stated.

[0026] Throughout the specification, when we say that an element is "on" another element, this includes not only cases where the element is in contact with the other element, but also cases where another element exists between the two elements.

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

[0028] Singular expressions include plural expressions unless the context clearly indicates otherwise.

[0029] The identification codes for each step are used for convenience of explanation and do not describe the order of each step. Each step may be performed in a different order than specified unless the context clearly indicates a specific order.

[0030] The operating principle and embodiments of the present disclosure are described below with reference to the attached drawings.

[0031] As used herein, the term "device according to the present disclosure" encompasses a variety of devices capable of performing computational processing and providing results to a user. For example, the device according to the present disclosure may include a computer, a server device, and a portable terminal, or may be any one of them.

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

[0033] The above server device is a server that processes information by communicating with an external device, 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 above portable terminal may include, for example, a wireless communication device that ensures portability and mobility, and may include all kinds of handheld-based wireless communication devices such as a 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) terminal, a smart phone, and a wearable device such as a watch, a ring, a bracelet, an anklet, a necklace, glasses, contact lenses, or a head-mounted device (HMD).

[0035] FIG. 1 is a drawing illustrating a patient-tailored training content recommendation system (100) according to the present disclosure.

[0036] Referring to FIG. 1, a system (100) for recommending patient-tailored training content may include a user terminal (110), a device (130) for recommending patient-tailored training content, and a database (150).

[0037] The user terminal (110) can check the patient profile, functional cognitive score, and training content provided through the patient-tailored training content recommendation device (130) collected through the patient-tailored training content recommendation device (130), and conversely, the user terminal (110) can be implemented as a smart phone or a wearable device that can provide the patient profile to the patient-tailored training content recommendation device (130), and is not necessarily limited thereto, and can also be implemented as various devices such as a tablet PC. The user terminal (110) can be connected to the patient-tailored training content recommendation device (130) through a network, and a plurality of user terminals (110) can be connected to the patient-tailored training content recommendation device (130) simultaneously.

[0038] A patient-tailored training content recommendation device (130) may be implemented as a server corresponding to a computer or program that sequentially performs operations of receiving a patient profile, evaluating the patient's cognitive ability based on the patient profile to calculate the patient's functional cognitive score, recommending training content based on the obtained functional cognitive score, and receiving performance information on the provided training content. The patient-tailored training content recommendation device (130) may be wirelessly connected to a user terminal (110) via Bluetooth, WiFi, a communication network, etc., and may exchange data with the user terminal (110) via the network.

[0039] The database (150) may correspond to a storage device that stores various pieces of information generated through an operating process of receiving a patient profile, evaluating the patient's cognitive ability based on the patient profile, calculating the patient's functional cognitive score, recommending training content based on the obtained functional cognitive score, and receiving performance information on the provided training content.

[0040] FIG. 2 is a drawing illustrating the physical configuration of a patient-tailored training content recommendation device (130) according to the present disclosure.

[0041] Referring to FIG. 2, a patient-tailored training content recommendation device (130) can be implemented including a processor (210), a memory (230), a user input / output unit (250), and a network input / output unit (270).

[0042] The processor (210) may execute a procedure that performs operations of receiving a patient profile, evaluating the patient's cognitive ability based on the patient profile to calculate the patient's functional cognitive score, recommending training content based on the obtained functional cognitive score, and receiving performance information about the provided training content, and may manage the memory (230) that is read or written throughout the process, and may schedule a synchronization time between the volatile memory and the non-volatile memory in the memory (230). The processor (210) may control the overall operation of the patient-tailored training content recommendation device (130), and may be electrically connected to the memory (230), the user input / output unit (250), and the network input / output unit (270) to control the data flow therebetween. The processor (210) may be implemented as a CPU (Central Processing Unit) of the patient-tailored training content recommendation device (130).

[0043] The memory (230) may include an auxiliary memory device implemented with a non-volatile memory such as an SSD (Solid State Drive) or an HDD (Hard Disk Drive) and used to store all data required for the patient-tailored training content recommendation device (130), and may include a main memory device implemented with a volatile memory such as a RAM (Random Access Memory).

[0044] The user input / output unit (250) may include an environment for receiving user input and an environment for outputting specific information to the user. For example, the user input / output unit (250) may include an input device including an adapter such as a touchpad, a touch screen, a virtual keyboard, or a pointing device, and an output device including an adapter such as a monitor or a touch screen. In the present disclosure, the user input / output unit (250) may correspond to a computing device connected via remote access, and in such a case, the patient-tailored training content recommendation device (130) may be implemented as a server.

[0045] The network input / output unit (270) includes an environment for connecting to an external device or system via a network, and may include an adapter for communication such as a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), and a value added network (VAN).

[0046] FIG. 3 is a diagram illustrating the functional configuration of a patient-tailored training content recommendation device (130) according to the present disclosure. Referring to FIG. 3, the patient-tailored training content recommendation device (130) may include a profile receiving unit (310), a cognitive ability evaluation unit (320), a training recommendation unit (330), a training execution unit (340), a result providing unit (350), a profile updating unit (360), and a patient cognitive score prediction unit (370).

[0047] The profile receiving unit (310) can receive a patient profile including basic information and cognitive information of the patient. The basic information of the patient may include the patient's age, gender, highest level of education, and current status of the patient. In this case, the current status may include at least one of the severity of the patient's cognition and language. The cognitive information may include the result of training content, and if there is no training content previously performed by the patient, it may include a separate pre-defined cognitive score. Here, the pre-performed training content may refer to training content performed through a patient-tailored training content recommendation device (130). That is, if there is training content previously performed by the patient, the profile receiving unit (310) can receive the patient's cognitive score according to the result of the training content.

[0048] Here, the predefined cognitive score may refer to a separate cognitive score, different from the results of training content performed through the patient-tailored training content recommendation device (130). For example, the predefined cognitive score may refer to a score related to measuring cognitive ability, such as the Mini-Mental State Examination (MMSE), the Global Deterioration Scale (GDS), and the Clinical Dementia Rating (CDR).

[0049] The cognitive ability assessment unit (320) can evaluate the patient's cognitive ability based on the patient profile and calculate a cognitive score for each of the patient's functions. For example, the cognitive ability assessment unit (320) can calculate a cognitive score for each of the patient's cognitive functions, such as attention, memory, executive function, reading, writing, speaking, and comprehension. More specifically, the cognitive ability assessment unit (320) can calculate an absolute score and a statistical score for the patient's most common functions, which will be described in detail below.

[0050] In the present disclosure, the cognitive ability evaluation unit (320) can define a cognitive score for each function according to sub-functions that are divided into stages, and can calculate statistical values ​​for each sub-function. For example, the sub-functions divided into stages can include mental functions as a major category, and mental functions can include perception, executive functions, language functions, calculation functions, and memory. In addition, perception functions can include auditory perception, visual perception, and spatiotemporal perception. In addition, executive functions can include abstraction, organization and planning, cognitive flexibility, judgment, and problem-solving. Language functions can include language comprehension and language expression. Calculation functions can include simple calculations and complex calculations. In this way, the sub-functions can be divided into major categories, intermediate categories, and minor categories, but are not limited thereto. Therefore, the cognitive ability evaluation unit (320) can define the sub-functions by defining at least one major category as described below and placing intermediate categories under the corresponding major categories.

[0051] Additionally, the cognitive ability evaluation unit (320) can calculate statistical values ​​for each sub-function. For example, the cognitive ability evaluation unit (320) can calculate statistical values ​​for each sub-function by calculating that the score for mental function corresponds to the top 10% for patients of the same age. Here, the statistical values ​​can refer to statistically processed data, such as calculating a p-value by calculating a difference value from a group of the same age as well as a statistically processed z-score in addition to a percentile.

[0052] In the present disclosure, the cognitive ability evaluation unit (320) can define a cognitive score for each function through a first step of defining at least one sub-function, a second step of defining detailed sub-functions included in at least one sub-function, and a third step of generating a label code for the sub-function and the detailed sub-function by labeling the sub-function and the detailed sub-function. For example, the cognitive ability evaluation unit (320) can define the sub-functions as mental function, sensory function and pain, and voice and speaking function. In addition, the cognitive ability evaluation unit (320) can define the sensory function and pain function to include detailed sub-functions of visual function, function of the structure around the eyes, and auditory function.

[0053] Additionally, the cognitive ability evaluation unit (320) may assign a label code of b1 to mental functions, a label code of b2 to sensory functions and pain, and a label code of b3 to voice and speech functions. Furthermore, the cognitive ability evaluation unit (320) may assign label codes to detailed sub-functions, for example, a label code of b210 may be assigned to visual functions.

[0054] In the present disclosure, the cognitive ability evaluation unit (320) can calculate a cognitive score for each function by adding up statistical values ​​for each sub-function. For example, the cognitive ability evaluation unit (320) can calculate statistical values ​​for each of the sub-functions, namely, voice function, articulation function, speaking and fluency and rhythm function, and alternative vocalization function, and add up these values ​​to calculate a cognitive score for the voice and speaking function, which correspond to the sub-function.

[0055] The training recommendation unit (330) can recommend at least one training content using an AI rehabilitation recommendation model based on the functional cognitive score. For example, the training recommendation unit (330) can recommend training content that can train a cognitive function that falls below the average cognitive function for the patient's age among the functional cognitive scores of the patient. For example, the training recommendation unit (330) can recommend training content that can train attention for a patient with attention deficit, and the method for this is described in detail below.

[0056] Training content may include at least one cognitive training program with a set training type, difficulty level, number of questions, and solution time. For example, the training recommendation unit (330) may provide training content to a patient by setting the training type, difficulty level, number of questions, and solution time.

[0057] In this disclosure, the training recommendation unit (330) may provide training content that can supplement sub-functions with low statistical values. For example, if the statistical value of a patient's mental function is low, the training recommendation unit (330) may provide training content that can supplement the mental function.

[0058] In this disclosure, the training recommendation unit (330) may provide training content that can enhance detailed sub-functions with low statistical values. For example, the training recommendation unit (330) may provide training content that can enhance memory for a patient with low statistical values ​​for memory.

[0059] In the present disclosure, the training recommendation unit (330) may define a specific number of criteria for low statistical values. For example, the training recommendation unit (330) may provide training content to reinforce the four lowest-scoring sub-functions among the sub-functions. In another example, the training recommendation unit (330) may provide training content to protect sub-functions with a z-score of -1.5 or lower.

[0060] In the present disclosure, the training recommendation unit (330) can select cognitive training that includes the most label codes of detailed sub-functions included in sub-functions with low statistical values ​​through an artificial intelligence rehabilitation recommendation model and recommend at least one training content. For example, if the executive function label code among the detailed sub-functions is b164 and the codes of word association training include b1640, b1641, b1642, and b1643, the training recommendation unit (330) can provide the training to the patient by including it in the training content since the word association training includes four training codes belonging to the sub-class of b164. That is, the training recommendation unit (330) can check the label codes of the training included in the training, review whether they match the label codes that the patient lacks, and determine whether to include the training in the training content and recommend it.

[0061] In this disclosure, the training recommendation unit (330) can recommend a list of recommended training content as training content. Here, the AI ​​rehabilitation recommendation model can generate a list of recommended training content containing a specific label code based on the input of a specific label code. For example, the training recommendation unit (330) can receive a specific label code requiring training for a patient visiting for the first time, and provide training content corresponding to the label code through the AI ​​rehabilitation recommendation model.

[0062] In the present disclosure, the artificial intelligence rehabilitation recommendation model can cluster at least one patient based on the performance results for specific training content and generate a list of recommended training content based on the cluster to which the patient belongs.

[0063] Specifically, the AI ​​rehabilitation recommendation model can collect accuracy and reaction time from the patient's performance results for training content and calculate the accuracy, reaction time, and similarity with other patients. Specifically, the AI ​​rehabilitation recommendation model determines at least one benchmark, calculates n-dimensional numerical values ​​including the benchmarks for each patient, and then compares the numerical values ​​in each dimension to calculate the similarity in each dimension and the similarity between specific patients. In one embodiment, the AI ​​rehabilitation recommendation model can generate patient clusters by calculating the cosine similarity between each numerical value.

[0064] In the present disclosure, the AI ​​rehabilitation recommendation model can generate a list of recommended training contents, in addition to the training contents performed by the patient, including training contents performed by other patients in the patient's cluster. For example, the AI ​​rehabilitation recommendation model can generate a list of recommended training contents that the patient did not perform but were performed by other patients in the patient's cluster. In another example, the AI ​​rehabilitation recommendation model can generate a list of recommended training contents that the patient did not perform but were performed by other patients in the patient's cluster, including the training contents that were most frequently performed by other patients.

[0065] In the present disclosure, the AI ​​rehabilitation recommendation model can generate a list of recommended training contents through a first step of determining whether the correct answer rate of the training contents performed by the patient is above a first criterion, a second step of determining whether the reaction time for the training contents performed by the patient is below a second criterion if the patient's correct answer rate is above the first criterion, and a third step of generating a list of recommended training contents with increased difficulty if the training contents performed by the patient are not at the maximum difficulty level if the patient's reaction time is below the second criterion. For example, if the correct answer rate for the training contents performed by the patient is above 80%, the AI ​​rehabilitation recommendation model can determine whether the reaction time for the training contents performed by the patient is below a specific time. Here, the specific time can be preset, and the specific time can be the median reaction speed of the patients in the cluster to which the patient belongs minus 2x the median deviation. If the patient's reaction time is below the specific time, and if the difficulty level of the training contents performed by the patient is not at the maximum, the AI ​​rehabilitation recommendation model can increase the difficulty level of the recommended training contents by 1, and if the difficulty level is at the maximum, the recommendation can be terminated. Additionally, the AI ​​rehabilitation recommendation model can recommend training content with a maintained level of difficulty if the patient's reaction time exceeds a certain amount of time.

[0066] In the present disclosure, the AI ​​rehabilitation recommendation model can generate a list of recommended training contents through a first step of determining whether the correct answer rate of training contents performed by the patient is below a first criterion, a second step of determining whether the correct answer rate of the training contents performed by the patient is above a third criterion if the patient's correct answer rate is below the first criterion, and a third step of generating a list of recommended training contents with maintained difficulty if the patient's correct answer rate is above the third criterion, and generating a list of recommended training contents with reduced difficulty if the patient's correct answer rate is below the third criterion. For example, the AI ​​rehabilitation recommendation model can set the second criterion as a limit value that is 2x the standard deviation from the average correct answer rate of other patients in the cluster to which the patient belongs according to the content performance. In addition, the AI ​​rehabilitation recommendation model can maintain or lower the difficulty of the recommended training contents depending on the correct answer rate of the patient.

[0067] In the present disclosure, the AI ​​rehabilitation recommendation model may include a prediction model that predicts the outcome of a patient's training content and a recommendation model that generates a list of recommended training content based on a recommendation score calculated according to a set target value. For example, the prediction model may predict the outcome of a patient's training content using a learning method such as machine learning. More specifically, the prediction model may utilize a known AI learning method and may predict the accuracy rate of a patient's training content based on the results of training previously performed by the patient. The recommendation model may generate a list of recommended training content based on a recommendation score calculated according to a set target value. For example, the recommendation model may calculate a recommendation score for a training content based on target values ​​for difficulty, performance experience, reaction time, solution time, and sensitivity. More specifically, the recommendation model may calculate a recommendation score according to Equations 1 to 11 below.

[0068]

[0069] (Here, w1 to w5 are preset weights, p is a given patient, t is the type of training, s1 to s5 are preset values, and [ts] is information about the completed training.)

[0070]

[0071]

[0072] (Here, the target (s1) is s1 / 100, s1 is the target performance setting value, and the prediction (t) is 1-(step (t) / maximum step (t)).

[0073]

[0074] (Here, prediction(t) is idx(sort(timerOptionList(t)), t) / len(timerOptionList(t)).)

[0075]

[0076] (Here, s2 is the performance experience preference setting value, w131 is the preset weight, and prediction (t) is the patient's predicted correct answer rate for the corresponding training content.)

[0077]

[0078] (Here, the target (s2) is s2 / 100, s2 is the performance experience preference setting value, the prediction (p,t) is 1 / rank(t), and rank(t) is the position of t in the sorted list sorted by the patient's performance history of the training content (t) among the entire training content (T).)

[0079] For example, if a patient has performed a lot of the training content, the rank(t) value may be large.

[0080]

[0081] (Here, the target (s3) is s3 / 100, s3 is the preferred setting for fast reaction time, w31 is the preset weight, the prediction (p,t) is 1 / rank(t), and rank(t) is the position of t in the list sorted in the order in which the patient is predicted to have a fast reaction time among the entire training contents (T).)

[0082] For example, the higher the rank(t) value, the faster the patient is expected to react to the training content.

[0083]

[0084] (Here, the target (s4) is s4 / 100, s4 is the preferred solution time setting, w41 is the preset weight, the prediction (p,t) is 1 / rank(t), and rank(t) is the position of t in the list sorted in the order in which the patient predicted the solution time to be faster among the entire training contents (T).)

[0085] For example, the higher the rank(t) value, the faster the patient is expected to solve the training content.

[0086]

[0087]

[0088] (Here, w511=s5 / 100, s5 is the private preference setting value, and similarity ([ts], t) is the number of times the recommended training content (t) matches the ICF code in the list of training contents ([ts]) performed by the patient.)

[0089]

[0090] (Here, w521 is s5 / 100, new target(s1,[ts])=(s1-pre-training correct answer rate([ts]))+s1.)

[0091] For example, the recommendation model can calculate the recommendation score (p, t) of the training content according to the setting values ​​of 0 to 100 s1 to s5 and generate a list of recommended content including training content with a high recommendation score.

[0092] The training execution unit (340) can produce results for training content provided to a patient via a user terminal. Here, the training execution unit (340) can produce results for the training content, including the number of problems solved by the patient, the time taken, and the number of correct answers for each area.

[0093] The result provision unit (350) can provide results for training content. For example, the result provision unit (350) can provide the results of performing training content to the patient and compare the results with previously performed training content to provide the results.

[0094] The profile update unit (360) can update the patient profile based on the results of the training content. For example, if the patient's cognitive function has improved by performing the training content compared to the training content performed prior to the training content, the profile update unit (360) can update the patient profile to reflect the improved cognitive function.

[0095] The patient cognitive score prediction unit (370) can generate a cognitive score prediction value by predicting a predefined cognitive score different from the patient's functional cognitive score based on the statistical value for each sub-function. For example, the patient cognitive score prediction unit (370) can predict and display the patient's MMSE, GDS, and CDR scores based on the z-score value for each sub-function. In other words, the patient cognitive score prediction unit (370) can determine the level of cognitive function that the patient has compared to other patients of the same age and match this with other predefined cognitive scores to provide convenience to the patient.

[0096] In the present disclosure, the patient cognitive score prediction unit (370) can calculate the accuracy of the cognitive score prediction value according to the size of the population from which the statistical values ​​for each sub-function are calculated. For example, the patient cognitive score prediction unit (370) can calculate that the accuracy of the matching with the cognitive score prediction value increases as the size of the population from which the statistical values ​​for each sub-function are calculated increases. That is, as the number of patients using the patient-tailored training content recommendation device (130) increases, the patient cognitive score prediction unit (370) can collect more patient data and provide other cognitive score prediction values ​​with higher accuracy. For example, when the patient cognitive score prediction unit (370) collects data from a population exceeding a certain number of people, it can calculate the accuracy of the cognitive score prediction value, and when the number of people does not exceed a certain number of people, it can display it as a simple prediction value and not calculate the accuracy of the prediction value.

[0097] FIGS. 5 to 9 are drawings illustrating a screen in which a patient-tailored training content recommendation device (130) according to the present disclosure is implemented.

[0098] Referring to Figure 5, the patient-tailored training content recommendation device (130) can confirm the hospital name and manager through the main screen, as well as the registration date. Furthermore, the patient-tailored training content recommendation device (130) can count the number of therapists and patients in real time through the main screen, check the amount spent, check the number of recent patient registrations, and check for necessary notices. Furthermore, the patient-tailored training content recommendation device (130) main screen can confirm inquiries, a list of registered therapists, and patient information.

[0099] Referring to Figure 6, the patient-tailored training content recommendation device (130) can register / edit patients through the patient list screen, write brief notes, and check the patient registration status. Furthermore, the patient-tailored training content recommendation device (130) can sort patients through the patient list screen and check detailed information about selected patients.

[0100] Referring to FIGS. 7a and 7b, the patient-tailored training content recommendation device (130) can check the information of a selected patient and the training history of the patient through the general training page, select which area of ​​training is required, and set the order, difficulty, etc. for each training.

[0101] Referring to FIGS. 8a and 8b, the patient-tailored training content recommendation device (130) can check the information of the selected patient through the automatic training page, set the target time and correct answer rate, set the proportion between previously experienced training and new training, select an area that requires special treatment, and control whether or not to set details for automatically recommended recommended content.

[0102] Referring to FIG. 9, the patient-tailored training content recommendation device (130) can check the training frequency for each detailed area through the report page, check the total training time and accuracy, and information on recent training, and can classify each detailed item to check which cognitive function is lacking.

[0103] FIG. 4 is a diagram illustrating the sequence in which a method for recommending patient-tailored training content according to the present disclosure is performed.

[0104] Referring to FIG. 4, a method for recommending patient-tailored training content can receive a patient profile including basic information and cognitive information of the patient through a profile receiving unit (310) (S410).

[0105] The method for recommending patient-tailored training content can evaluate the patient's cognitive ability based on the patient profile through the cognitive ability evaluation unit (320) and calculate the patient's functional cognitive score (S420).

[0106] The method for recommending patient-tailored training content can recommend at least one training content through an artificial intelligence rehabilitation recommendation model based on the functional cognitive score through the training recommendation unit (330) (S430).

[0107] The method for recommending patient-tailored training content can produce results for the training content provided to the patient through the user terminal via the training execution unit (340) (S440).

[0108] Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium storing computer-executable instructions. The instructions may be stored in the form of program code, and when executed by a processor, may generate program modules to perform the operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

[0109] Computer-readable storage media include all types of storage media that store instructions that can be deciphered by a computer. Examples include read-only memory (ROM), random access memory (RAM), magnetic tape, magnetic disks, flash memory, and optical data storage devices.

[0110] The disclosed embodiments have been described with reference to the attached drawings as described above. Those skilled in the art will understand that the present disclosure can be implemented in forms other than the disclosed embodiments without altering the technical spirit or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be construed as limiting.

Claims

1. A profile receiving unit that receives a patient profile including the patient's basic information and cognitive information; A cognitive ability evaluation unit that evaluates the patient's cognitive ability based on the patient profile and calculates the patient's functional cognitive score; A training recommendation unit that recommends at least one training content using an artificial intelligence rehabilitation recommendation model; and A patient-tailored training content recommendation device including a training execution unit that produces results for the training content provided to the patient through a user terminal.

2. In paragraph 1, The basic information of the above patient is: Including the patient's current condition, age, gender and highest level of education, The above cognitive information is, A patient-tailored training content recommendation device comprising a result for the above training content and, if there is no training content previously performed by the patient, a separate pre-defined cognitive score.

3. In paragraph 2, The above cognitive ability evaluation department, A patient-tailored training content recommendation device characterized by defining a cognitive score for each function according to sub-functions divided into stages and calculating statistical values ​​for each sub-function.

4. In paragraph 3, The above cognitive ability evaluation department, Step 1: defining at least one sub-function; A second step of defining detailed sub-functions included in at least one of the above sub-functions; and A patient-tailored training content recommendation device characterized in that the functional-specific cognitive score is defined through a third step of generating a label code for the sub-function and the detailed sub-function by performing labeling for the sub-function and the detailed sub-function.

5. In paragraph 4, The above cognitive ability evaluation department, A patient-tailored training content recommendation device characterized in that the statistical values ​​are added for each sub-function to calculate a cognitive score for each function.

6. In paragraph 3, The above artificial intelligence rehabilitation recommendation model is, Generate a list of recommended training contents containing a specific label code based on the input of a specific label code, The above training recommendation section, A patient-tailored training content recommendation device characterized in that the above-mentioned recommended training content list is recommended as the above-mentioned training content.

7. In paragraph 1, The above artificial intelligence rehabilitation recommendation model is, A patient-tailored training content recommendation device characterized in that it clusters at least one patient based on the performance results for specific training content and generates a list of recommended training contents based on the cluster to which the patient belongs.

8. In paragraph 7, The above artificial intelligence rehabilitation recommendation model is, A patient-tailored training content recommendation device characterized in that, in addition to the training content performed by the patient, training content performed by other patients in the cluster to which the patient belongs is generated as a list of recommended training contents.

9. In paragraph 7, The above artificial intelligence rehabilitation recommendation model is, A first step of determining whether the correct answer rate of the training content performed by the patient is above the first standard; A second step of determining whether the reaction time for the training content performed by the patient is less than the second criterion when the correct answer rate of the patient is greater than or equal to the first criterion; and A patient-tailored training content recommendation device characterized in that the recommended training content list is generated through a third step of generating training content with increased difficulty as the recommended training content list if the patient's reaction time is less than the second criterion and the training content performed by the patient is not at its maximum difficulty.

10. In paragraph 7, The above artificial intelligence rehabilitation recommendation model is, A first step of determining whether the correct answer rate of the training content performed by the patient is below the first standard; A second step of determining whether the correct answer rate for the training content performed by the patient is higher than or equal to the third criterion when the correct answer rate of the patient is lower than the first criterion; and A patient-tailored training content recommendation device characterized in that the recommended training content list is created through a third step of creating training content with a maintained level of difficulty as the recommended training content list when the patient's correct answer rate is higher than the third criterion, and creating training content with a reduced level of difficulty as the recommended training content list when the patient's correct answer rate is lower than the third criterion.

11. In paragraph 1, The above artificial intelligence rehabilitation recommendation model is, A predictive model that predicts the outcome of the training content for the patient; and A patient-tailored training content recommendation device characterized by including a recommendation model that generates a list of recommended training contents based on a recommendation score calculated according to a set target value.

12. In paragraph 5, The above training content is, Includes at least one cognitive training session with a set training type, difficulty, number of problems, and solution time; The above training recommendation section, A patient-tailored training content recommendation device characterized by providing training content that can reinforce sub-functions with low statistical values.

13. In paragraph 12, The above training recommendation section, A patient-tailored training content recommendation device characterized in that it selects cognitive training that includes the most label codes of the detailed sub-functions included in the sub-functions with low statistical values ​​through the artificial intelligence rehabilitation recommendation model and recommends at least one training content.

14. In paragraph 3, A result provision unit that provides results for the above training content; A profile update unit that updates the patient profile based on the results of the above training content; and Further comprising a patient cognitive score prediction unit that predicts the defined cognitive score different from the patient's functional cognitive score based on the statistical value for each of the above sub-functions and generates a cognitive score prediction value. The above patient cognitive score prediction unit is, A patient-tailored training content recommendation device characterized in that the accuracy of the cognitive score prediction value is calculated according to the size of the population that calculated the statistical value for each of the above sub-functions.

15. A method for recommending patient-tailored training content performed on a user terminal, A step of receiving a patient profile including basic information and cognitive information of the patient; A step of evaluating the patient's cognitive ability based on the patient profile and calculating the patient's functional cognitive score; A step of recommending at least one training content using an artificial intelligence rehabilitation recommendation model; and A method for recommending patient-tailored training content, comprising a step of producing a result for the training content provided to the patient through the user terminal.

Images