Rehabilitation training game apparatus and rehabilitation training game providing method

Abstract

This rehabilitation training game apparatus comprises: a rehabilitation training terminal that displays a rehabilitation training game performed according to a rehabilitation operation and obtains a user image; and a server including an operation determination unit for determining whether the rehabilitation operation is successful by analyzing the user image, and an operation calculation unit that generates operation information for operating a character of the rehabilitation training game according to the content of the determination of the operation determination unit.

Description

Rehabilitation training game device and method for providing rehabilitation training game

[0001] The present invention relates to a rehabilitation training game device and a method for providing a rehabilitation training game, and more specifically, to .

[0002] In recent years, cases of families with developmental disabilities taking extreme measures have been on the rise every year. This stems from a lack of protection for families with disabilities. The role of guardians is particularly crucial in pediatric rehabilitation, and expanding the support system for rehabilitation environments is essential. Because the time burden associated with visiting treatment centers accounts for a significant portion of the difficulties faced by pediatric rehabilitation, technologies that facilitate the rehabilitation of children with disabilities can alleviate the burden on parents.

[0003] There is technology that can help physically disabled children receive rehabilitation, using systems based on image processing technologies such as AR and VR. However, it is difficult to accurately measure the user's condition, and it is especially difficult to maintain the child's concentration during rehabilitation treatment movements, so there are limitations to its practical use.

[0004] [Prior Art Literature]

[0005] [Patent Document]

[0006] Republic of Korea Patent Publication No. 10-2020-0136255

[0007] Republic of Korea Patent Publication No. 10-2022-0064593

[0008] Accordingly, the technical problem of the present invention was conceived from this point, and the purpose of the present invention is to provide a rehabilitation training game device that reduces the burden on guardians of disabled children who have to spend time visiting a treatment institution, and reduces the patient's resistance to rehabilitation by making it fun and comfortable for the disabled children to undergo rehabilitation.

[0009] Another object of the present invention is to provide a method for providing a rehabilitation training game using the above rehabilitation training game device.

[0010] According to one embodiment of the present invention for realizing the above-described purpose, a rehabilitation training game device includes a rehabilitation training terminal that displays a rehabilitation training game that is performed according to a rehabilitation movement and acquires a user image, a motion judgment unit that analyzes the user image and determines whether the rehabilitation movement is successful, and a server that includes a manipulation operation unit that generates manipulation information for manipulating a character of the rehabilitation training game according to the judgment result of the motion judgment unit.

[0011] In one embodiment of the present invention, the rehabilitation training terminal may include a camera for obtaining the user image, a display for displaying the rehabilitation training game, and a control unit for transmitting image information obtained by dividing the user image into frames to the server.

[0012] In one embodiment of the present invention, the motion determination unit of the server can recognize a hand portion from the image information using a motion recognition artificial intelligence model, extract coordinates of each finger joint, and then analyze the movement of the coordinates using a motion determination artificial intelligence model to determine whether the rehabilitation motion is successful.

[0013] In one embodiment of the present invention, the motion judgment artificial intelligence model can determine the success, failure, or malfunction of the rehabilitation motion, and output a differentiated score according to the success, failure, or malfunction as a result value.

[0014] In one embodiment of the present invention, the manipulation operation unit can convert the result value into a manipulation numerical value to be used for manipulation of the rehabilitation training game and transmit the result value to a rehabilitation training terminal.

[0015] In one embodiment of the present invention, the control unit of the rehabilitation training terminal can receive the manipulation numerical value, process an input corresponding to the manipulation numerical value, and display the operation of the rehabilitation training game through the display according to the input.

[0016] In one embodiment of the present invention, the manipulation value may correspond to inputting a value for manipulation of the rehabilitation training game (press), maintaining the value in an input state (hold), or terminating the input of the value (release).

[0017] In one embodiment of the present invention, the rehabilitation operation is an operation including a first hand shape and a second hand shape different from the first hand shape, and the operation calculation unit, when the rehabilitation operation is successful, generates a first input value at a time corresponding to the first hand shape and generates a second input value at a time corresponding to the second hand shape, so that real-time operation of the rehabilitation training game is possible through the rehabilitation operation.

[0018] In one embodiment of the present invention, the motion determination unit of the server recognizes a hand portion from the image information using a motion recognition artificial intelligence model, extracts coordinates of each finger joint, and then analyzes the movement of the coordinates using a motion determination artificial intelligence model to determine the type of the rehabilitation motion and determine whether the rehabilitation motion is successful.

[0019] According to one embodiment of the present invention for realizing the above-described object, a method for providing a rehabilitation training game includes: a motion description step of displaying a video explaining a rehabilitation motion on a rehabilitation training terminal; a game execution step of analyzing a video of a user captured through the rehabilitation training terminal on a server and executing a rehabilitation training game for manipulating a character; and a game training step of analyzing the user video as the user repeats the rehabilitation training motion, determining whether the rehabilitation motion is successful, generating operation information for manipulating a character of the rehabilitation training game based on the determination, and manipulating the character based on the operation information.

[0020] In one embodiment of the present invention, the game training step may include a frame-by-frame image information transmission step of generating image information by dividing the image of the user into frames at the rehabilitation training terminal and transmitting the generated image information to the server, a hand part recognition and finger coordinate extraction step of recognizing a hand part from the image information using a motion recognition artificial intelligence model and extracting coordinates of each finger joint, a motion success determination step of analyzing the movement of the coordinates using a motion determination artificial intelligence model and determining whether the rehabilitation movement is successful, a manipulation information generation and transmission step of generating manipulation information according to the success of the movement and transmitting the generated manipulation information to the rehabilitation training terminal, and a character manipulation display step of displaying manipulation of the character of the rehabilitation training game displayed on the rehabilitation training terminal according to the manipulation information.

[0021] In one embodiment of the present invention, the method for providing a rehabilitation training game may further include, after the motion description step, a motion confirmation step for analyzing an image of the user captured through the rehabilitation training terminal to determine whether the user's rehabilitation motion was successful. In the motion confirmation step, the success or failure of the rehabilitation motion can be determined for each user by considering the user's status information determined using pre-entered user information.

[0022] According to embodiments of the present invention, a rehabilitation training game device can be provided so that a disabled child can receive rehabilitation training at home, thereby reducing the burden of time taken by guardians to go to the hospital, and by incorporating rehabilitation training into a game, the resistance felt by the disabled child toward rehabilitation training can be reduced and interest increased.

[0023] In other words, through the above rehabilitation training game device, it is possible to provide an AR rehabilitation treatment service and solution that allows one to obtain the effect of going to a rehabilitation treatment center and receiving rehabilitation treatment assigned by a rehabilitation therapist from anywhere.

[0024] However, the effects of the present invention are not limited to the above effects, and may be expanded in various ways without departing from the spirit and scope of the present invention.

[0025] Figure 1 is a schematic diagram of a rehabilitation training game device according to one embodiment of the present invention.

[0026] Figure 2 is a schematic diagram showing the configuration of the server of Figure 1.

[0027] Figure 3 is a flowchart illustrating a method for providing a rehabilitation training game according to one embodiment of the present invention.

[0028] Figure 4 is a flowchart showing in detail the game training steps of the method for providing a rehabilitation training game of Figure 3.

[0029] FIG. 5 (a) is a drawing showing a user interface (UI) of a rehabilitation training terminal in an operation description step and an operation confirmation step of a rehabilitation training game providing method of FIG. 3, FIG. 5 (b) is a drawing showing a user interface (UI) of a rehabilitation training terminal in a game execution step and a game training step, and FIG. 5 (c) is a drawing for explaining a hand part recognition and finger coordinate extraction step of a game training step of FIG. 4.

[0030] Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the drawings.

[0031] The present invention is susceptible to various modifications and takes various forms. Specific embodiments are illustrated in the drawings and described in detail herein. However, this is not intended to limit the present invention to specific disclosed forms, but rather to encompass all modifications, equivalents, and alternatives falling within the spirit and technical scope of the present invention.

[0032] Figure 1 is a schematic diagram of a rehabilitation training game device according to one embodiment of the present invention.

[0033] Referring to FIG. 1, the rehabilitation training game device includes a rehabilitation training terminal (100) and a server (200).

[0034] The above rehabilitation training terminal (100) displays a rehabilitation training game that progresses according to the rehabilitation movements of the patient user and captures the user's user image. To this end, the rehabilitation training terminal (100) includes a camera (110), a display (120), and a control unit (130).

[0035] The camera (110) can capture the user's hand movements to obtain the user image, which is a video of the user's hand movements. The user image can be divided into frames by the control unit (130), and the image information divided into frames can be transmitted to the server (200). The user image is an image for evaluating rehabilitation movements, and for accurate judgment, it is preferable that the user image be a video of 30 frames or more.

[0036] The above image information is generated by processing the user image at the rehabilitation training terminal (100), and the rehabilitation training terminal (100) performs real-time recording and frame-by-frame division processing of the image, thereby reducing traffic to the server (200).

[0037] The above display (120) can display a video explaining rehabilitation movements to the user or display the rehabilitation training game to enable the user to perform rehabilitation movements.

[0038] The above rehabilitation training terminal (100) includes, for example, a portable terminal such as a desktop, laptop, or tablet PC equipped with a web browser, and the portable terminal may include, for example, all types of handheld-based wireless communication devices such as a smartphone, a personal communication system (PCS), a global system for mobile communication (GSM), a personal digital cellular (PDC), a personal handyphone system (PHS), a personal digital assistant (PDA), an international mobile telecommunication (IMT)-2000, a code division multiple access (CDMA)-2000, a W-Code Division Multiple Access (W-CDMA), and a wireless broadband internet (Wibro) terminal, as wireless communication devices that ensure portability and mobility.

[0039] The server (200) analyzes the user image, evaluates the rehabilitation movement, and manipulates the character of the rehabilitation training game accordingly, thereby providing the user with fun, a sense of accomplishment, and immersion in rehabilitation training.

[0040] The above server (200) includes a learning unit (210), an operation judgment unit (220), and an operation calculation unit (230).

[0041] The learning unit (210) can train a motion recognition artificial intelligence model and a motion judgment artificial intelligence model, which will be described later, using various data such as image information received from the rehabilitation training terminal (100), personal information of the patient user, other information about the patient's condition, results of the rehabilitation training game, and training content. Since the rehabilitation training game device can accumulate data about the rehabilitation movements of the patient user, it can train an artificial intelligence model by utilizing the accumulated data to evaluate the results of the rehabilitation training and improve the recognition rate and judgment rate.

[0042] The above-described motion determination unit (220) can determine whether the above-described rehabilitation motion is successful. The motion determination unit (220) can first recognize the movement of the user's hand from the image information and then determine whether the movement is suitable for rehabilitation training. Specifically, the motion determination unit (220) can recognize the hand from the image information using a motion recognition artificial intelligence model and extract the coordinates of each finger joint. For example, the coordinates can be extracted using a mediapipe hand tracking model.

[0043] Thereafter, the motion judgment unit (220) can analyze the movement of the coordinates using a motion judgment artificial intelligence model to determine whether the rehabilitation motion is successful.

[0044] That is, the above-mentioned motion judgment artificial intelligence model can receive the above-mentioned coordinates as input values ​​and generate a numerical value that can evaluate the rehabilitation motion as an output value.

[0045] For example, the above-mentioned motion judgment artificial intelligence model can determine the success, failure, or malfunction of the above-mentioned rehabilitation motion, and output a differentiated score according to the success, failure, or malfunction as a result value. That is, when n coordinates are input into a deep learning model, it determines whether the rehabilitation motion was performed correctly (scores the success, failure, or malfunction of the rehabilitation motion) and outputs a judgment accordingly. The above-mentioned deep learning model can utilize, for example, an LSTM (Long short-term memory) algorithm.

[0046] Meanwhile, the above-mentioned motion judgment artificial intelligence model can not only determine whether a rehabilitation motion is successful, but also determine the type of the rehabilitation motion and determine whether the rehabilitation motion is successful.

[0047] Specifically, the rehabilitation movement for hand movements may include 23 predetermined rehabilitation movements, and there may be a judgment model for each rehabilitation movement and an integrated model that measures the classification and score of the reactivation work when any movement is performed.

[0048] The above-mentioned manipulation operation unit (230) can generate manipulation information for manipulating the character of the rehabilitation training game based on the judgment result of the above-mentioned motion judgment unit (220). The above-mentioned manipulation operation unit (230) can convert the determined information into a numerical value to be used as input for the rehabilitation training game and transmit the same to the above-mentioned rehabilitation training terminal (100).

[0049] Thereafter, the permanent rehabilitation training terminal (100) converts the received numerical value into an input processing system operation equivalent to a keyboard or mouse, and converts it into Down, Up, and Press events for each of the 23 rehabilitation actions, so that it can be utilized in various ways within the rehabilitation training game. For example, for a designated rehabilitation action, if the user does not make any action or the action is unrelated to the rehabilitation action, there is no input value in the ready state, and if the designated rehabilitation action is performed, it corresponds to Down, and an action of pressing a switch (for example, a space bar button corresponding to a character's jump in a rehabilitation training game) is performed, and if the state in which rehabilitation training is normally progressing continues, it corresponds to Press, and is processed as a state in which the switch is continuously pressed, and if one rehabilitation training action is completed and the state is ready, it corresponds to Up, and can be processed as a state in which the switch is released.

[0050] For example, the rehabilitation operation may be an operation including a first hand shape and a second hand shape different from the first hand shape, and the manipulation operation unit (230) may generate a first input value at a time corresponding to the first hand shape and generate a second input value at a time corresponding to the second hand shape when the rehabilitation operation is successful, thereby enabling real-time manipulation of the rehabilitation training game through the rehabilitation operation.

[0051] Additionally, depending on the individual user's condition, the range of possible rehabilitation actions may vary. Therefore, the input threshold can be adjusted accordingly to allow multiple users to use the game.

[0052] That is, the control unit (130) of the rehabilitation training terminal (100) receives the manipulation numerical value, processes an input corresponding to the manipulation numerical value, and can display the operation of the rehabilitation training game through the display (120) according to the input.

[0053] Meanwhile, the time from processing and transmitting the patient image at the rehabilitation training terminal (100), processing at the motion determination unit (220) and the operation operation unit (230) of the server (200) and transmitting the result value to the rehabilitation training terminal (100), to manipulation and display of the rehabilitation training game character at the rehabilitation training terminal (100) is performed within a delay time that allows for gameplay, so that the character is manipulated according to the user's rehabilitation training motion, thereby enabling rehabilitation training through gameplay.

[0054] Figure 2 is a schematic diagram showing the configuration of the server of Figure 1.

[0055] Referring to FIG. 2, the server (200) may be formed in the form of a device such as a server or a terminal, and may operate in a cloud computing service model such as SaaS (Software as a Service), PaaS (Platform as a Service), or IaaS (Infrastructure as a Service). In addition, the server (10) may be constructed in the form of a server such as a private cloud, a public cloud, or a hybrid cloud system.

[0056] The above server (200) includes a communication module (11), a memory (12), and a processor (14), and may further include a database (13).

[0057] The above communication module (11) performs information transmission and reception with a rehabilitation treatment terminal (see 100 in FIG. 1). The above communication module (110) may include a device including hardware and software necessary for transmitting and receiving signals, such as control signals or data signals, through wired or wireless connections with other network devices.

[0058] The above memory (12) analyzes the user image, determines whether the rehabilitation operation is successful, and stores a program for generating operation information for operating a character of a rehabilitation training game based on the analysis. In addition, the memory (12) may include source code information including information on one or more programming languages. Here, the source code information may include variable information, class information, function information, and relationship information used in one or more programming languages. The name of the text semantic analysis program is set for convenience of explanation, and the name itself does not limit the function of the program.

[0059] The above memory (12) can store at least one of information and data input to the communication module (11), information and data required for functions performed by the processor (14), and data generated according to the execution of the processor (14). The memory (12) should be interpreted as a general term for a non-volatile storage device that maintains stored information even when no power is supplied and a volatile storage device that requires power to maintain the stored information. In addition, the memory (12) can perform a function of temporarily or permanently storing data processed by the processor (14). The memory (12) may include a magnetic storage media or a flash storage media in addition to a volatile storage device that requires power to maintain the stored information, but the scope of the present invention is not limited thereto.

[0060] The database (13) may be where data used by the rehabilitation training game device is stored. For example, the database (13) may store metadata and big data for semantic analysis of user information and data related to rehabilitation movements. The database (13) may constitute part of the memory (12), but may not necessarily be located within the rehabilitation training game device and may be located externally.

[0061] The processor (14) is configured to execute a text semantic analysis program stored in the memory (12). The processor (14) may include various types of devices that control and process data. The processor (14) may refer to a data processing device built into hardware that has a physically structured circuit to perform a function expressed by a code or command included in the program. In one example, the processor (14) may be implemented in the form of a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), etc., but the scope of the present invention is not limited thereto.

[0062] The processor (14) is configured to execute a program that performs a rehabilitation training game and perform the following functions and procedures. The processor (14) receives the user's image data from the rehabilitation treatment terminal (200) through the communication module (11), analyzes the user's rehabilitation movement based on the input data, and generates output data regarding the success or failure of the rehabilitation movement, which can be provided to the rehabilitation treatment terminal (200).

[0063] FIG. 3 is a flowchart illustrating a method for providing a rehabilitation training game according to one embodiment of the present invention. FIG. 4 is a flowchart illustrating in detail the game training steps of the method for providing a rehabilitation training game of FIG. 3.

[0064] Referring to FIGS. 3 and 4, the method for providing a rehabilitation training game includes an operation description step (S100), an operation confirmation step (S200), a game execution step (S300), and a game training step (S400). The method for providing a rehabilitation training game can be provided using the rehabilitation training game device described in FIG. 1.

[0065] In the above motion description step (S100), a video explaining the rehabilitation motion can be displayed on the rehabilitation training terminal.

[0066] In the above-mentioned motion verification step (S200), the user's video captured via the rehabilitation training terminal is analyzed to determine whether the user's rehabilitation motion was successful. At this time, the success or failure of the rehabilitation motion can be determined for each user by considering the user's status information determined using pre-entered user information.

[0067] In the above game execution step (S300), a user's video captured through the rehabilitation training terminal is analyzed by the server, and a rehabilitation training game that manipulates a character can be executed.

[0068] In the above game training step (S400), as the user repeats the rehabilitation training movement, the user image is analyzed to determine whether the rehabilitation movement is successful, and based on the determination, operation information for manipulating the character of the rehabilitation training game is generated, so that the character can be manipulated based on the operation information.

[0069] The above game training step (S400) may specifically include a frame-by-frame video information transmission step (S410), a hand part recognition and finger coordinate extraction step (S420), a motion success determination step (S430), an operation information generation and transmission step (S440), and a character operation display step (S450).

[0070] In the above frame unit video information transmission step (S410), the rehabilitation training terminal can generate video information by dividing the user's video into frame units and transmit it to the server.

[0071] In the above hand part recognition and finger coordinate extraction step (S420), a motion recognition artificial intelligence model can be used to recognize a hand part from the image information and extract the coordinates of each finger joint.

[0072] In the above operation success determination step (S430), the movement of the coordinates can be analyzed using the operation determination artificial intelligence model to determine whether the rehabilitation operation is successful.

[0073] In the above operation information generation and transmission step (S440), the operation information can be generated and transmitted to the rehabilitation training terminal depending on whether the operation is successful.

[0074] In the above character manipulation display step (S450), manipulation of the character of the rehabilitation training game displayed on the rehabilitation training terminal can be displayed according to the manipulation information.

[0075] FIG. 5 (a) is a drawing showing a user interface (UI) of a rehabilitation training terminal in an operation description step and an operation confirmation step of a rehabilitation training game providing method of FIG. 3, FIG. 5 (b) is a drawing showing a user interface (UI) of a rehabilitation training terminal in a game execution step and a game training step, and FIG. 5 (c) is a drawing for explaining a hand part recognition and finger coordinate extraction step of a game training step of FIG. 4.

[0076] Referring to Fig. 5 (a), the display of the rehabilitation training terminal can display a video of the type of rehabilitation movement and a description of the movement. The user's hand movements can be recorded in response to the video, and the user's hand movements can be displayed on the display to confirm whether the rehabilitation movement is being performed correctly.

[0077] Referring to (b) of Fig. 5, a rehabilitation training game is executed on the display of the rehabilitation training terminal, and a character in the game is manipulated according to the user's rehabilitation movements, enabling real-time manipulation.

[0078] Referring to Figure 5 (c), the extracted coordinates are displayed when the motion recognition AI model recognizes the hand and extracts the finger coordinates. Coordinates are extracted for the finger joints and palm joints, and the motion judgment AI model analyzes the movement of these coordinates to determine the success or failure of the rehabilitation movement.

[0079] According to embodiments of the present invention, a rehabilitation training game device can be provided so that a disabled child can receive rehabilitation training at home, thereby reducing the burden of time taken by guardians to go to the hospital, and by incorporating rehabilitation training into a game, the resistance felt by the disabled child toward rehabilitation training can be reduced and interest increased.

[0080] In other words, through the above rehabilitation training game device, it is possible to provide an AR rehabilitation treatment service and solution that allows one to obtain the effect of going to a rehabilitation treatment center and receiving rehabilitation treatment assigned by a rehabilitation therapist from anywhere.

[0081] Although the present invention has been described with reference to the above embodiments, it will be understood by those skilled in the art that various modifications and changes can be made to the present invention without departing from the spirit and scope of the present invention as set forth in the claims below.

Claims

1. A rehabilitation training terminal that displays a rehabilitation training game that progresses according to rehabilitation movements and acquires user images; and A rehabilitation training game device including a server including a motion judgment unit that analyzes the user image to determine whether the rehabilitation movement is successful and a manipulation operation unit that generates manipulation information for manipulating a character of the rehabilitation training game based on the judgment result of the motion judgment unit.

2. In paragraph 1, The above rehabilitation training terminal is, A camera for obtaining the above user image; A display displaying the above rehabilitation training game; and A rehabilitation training game device characterized by including a control unit that transmits image information divided into frame units by the user image to the server.

3. In paragraph 2, The above operation judgment unit of the above server is, Using a motion recognition artificial intelligence model, the hand part is recognized from the above image information, and the coordinates of each finger joint are extracted. A rehabilitation training game device characterized in that it analyzes the movement of the coordinates using a motion judgment artificial intelligence model to determine whether the rehabilitation motion is successful.

4. In paragraph 3, A rehabilitation training game device characterized in that the above-mentioned motion judgment artificial intelligence model determines the success, failure, or malfunction of the rehabilitation motion and outputs a differentiated score according to the success, failure, or malfunction as a result value.

5. In paragraph 4, A rehabilitation training game device characterized in that the above-mentioned manipulation operation unit converts the result value into a manipulation numerical value to be used in the manipulation of the rehabilitation training game and transmits the result value to a rehabilitation training terminal.

6. In paragraph 5, A rehabilitation training game device characterized in that the control unit of the rehabilitation training terminal receives the manipulation numerical value, processes an input corresponding to the manipulation numerical value, and displays the operation of the rehabilitation training game through the display according to the input.

7. In paragraph 5, A rehabilitation training game device characterized in that the above manipulation value corresponds to inputting a value for manipulation of the rehabilitation training game (press), maintaining the value in an input state (hold), or terminating the input of the value (release).

8. In paragraph 1, The above rehabilitation movement is a movement including a first hand shape and a second hand shape different from the first hand shape, The above operation unit, When the above rehabilitation operation is successful, a first input value is generated at a time corresponding to the first hand shape, and a second input value is generated at a time corresponding to the second hand shape. A rehabilitation training game device characterized in that real-time operation of the rehabilitation training game is possible through the above rehabilitation movement.

9. In paragraph 1, The above operation judgment unit of the above server is, Using a motion recognition artificial intelligence model, the hand part is recognized from the above image information, and the coordinates of each finger joint are extracted. A rehabilitation training game device characterized in that it analyzes the movement of the coordinates using a motion judgment artificial intelligence model, determines the type of the rehabilitation motion, and determines whether the rehabilitation motion is successful.

10. Movement description step of displaying a video explaining the rehabilitation movement on the rehabilitation training terminal; A game execution step in which the server analyzes the user's video captured through the above rehabilitation training terminal and executes a rehabilitation training game that manipulates a character; and A method for providing a rehabilitation training game, comprising: analyzing the user image as the user repeats the rehabilitation training movement, determining whether the rehabilitation movement is successful, generating operation information for manipulating a character of the rehabilitation training game based on the determination, and manipulating the character based on the operation information.

11. In paragraph 10, The above game training phase is, A frame-by-frame image information transmission step in which the rehabilitation training terminal generates image information by dividing the user's image into frame units and transmits the image information to the server; A hand part recognition and finger coordinate extraction step of recognizing a hand part from the image information using a motion recognition artificial intelligence model and extracting coordinates of each finger joint; A motion success determination step for determining whether the rehabilitation motion is successful by analyzing the movement of the coordinates using a motion determination artificial intelligence model; An operation information generation and transmission step for generating the operation information and transmitting it to the rehabilitation training terminal depending on whether the above operation is successful; and A method for providing a rehabilitation training game, characterized in that it includes a character operation display step for displaying the operation of the character of the rehabilitation training game displayed on the rehabilitation training terminal according to the operation information.

12. In paragraph 11, After the above operation description step, It further includes a motion verification step of analyzing the image of the user captured through the rehabilitation training terminal to confirm whether the user's rehabilitation motion is successful. A method for providing a rehabilitation training game, characterized in that, in the above-mentioned operation confirmation step, the success or failure of the rehabilitation operation is determined for each user by considering the status information of the user determined using the user information entered in advance.

Images