Feedback delivery method and system for cognitive behavioral therapy based on language models

Abstract

A method for providing feedback for cognitive behavioral therapy based on a language model according to the present invention may include the steps of: providing at least one questionnaire related to cognitive behavioral therapy on a user terminal; receiving response data of the questionnaire through the user terminal; generating a prompt to be input into a generative language model using the response data; inputting the prompt into the generative language model to generate feedback related to the response data; and providing the generated feedback to the user terminal.

Description

Technical Field

[0001] The present invention relates to a method and system for providing feedback for cognitive behavioral therapy based on a language model.

Background Art

[0002] Cognitive Behavioral Therapy (CBT) is a type of psychotherapy based on the premise that a person's thoughts, emotions, and behaviors are closely related to each other. During the treatment process, patients are helped to recognize their emotions, identify incorrect thoughts, and change problematic behaviors.

[0003] Recently, as the effectiveness of cognitive behavioral therapy has been scientifically proven, the use of cognitive behavioral therapy for mental health problems such as depression, anxiety, insomnia, and pain has gradually increased.

[0004] On the other hand, due to the development of technology, the popularity of electronic devices (such as smartphones, tablet PCs, etc.) has become widespread, and as a result, the dependence on the Internet in many parts of daily life has gradually increased.

[0005] Thus, due to the development of various technologies including the Internet, the consumption pattern that was highly dependent on offline in the past has gradually shifted to online, and currently, online-centered consumption has increased dramatically.

[0006] In response to such a trend change, industrial fields that depend on offline due to the nature of services, such as the medical industry, are increasing their attempts to provide medical services via the Internet.

[0007] For example, Korean Registered Patent No. 10-2195512 discloses a technology related to a server and system for providing an online medical platform, and provides information about medical service providers via the Internet to patients.

[0008] Furthermore, the rapid development of artificial intelligence (AI) technology in recent years has led to the emergence of large language models (LLMs) capable of natural dialogue with humans.

[0009] Unlike traditional chatbots that are manually built and only provide limited responses, large-scale language models possess the technological capability to communicate naturally like humans and provide fast and accurate information, demonstrating innovation in the artificial intelligence market.

[0010] Therefore, there is still a need for methods to provide a wider variety of medical services, even for medical services delivered online, by utilizing large-scale language models. [Overview of the project] [Problems that the invention aims to solve]

[0011] The present invention provides a feedback delivery method and system for cognitive behavioral therapy that can generate appropriate feedback based on the user's pain level, sense of competence, mood, short records, etc., and provide the generated feedback to the user.

[0012] More specifically, the present invention provides a feedback method and system for cognitive behavioral therapy that can generate prompts for a generative language model using response data from a questionnaire related to cognitive behavioral therapy, and generate feedback related to the questionnaire response data by inputting the generated prompts into the generative language model.

[0013] Furthermore, the present invention aims to provide a feedback method and system for cognitive behavioral therapy that can provide users with feedback related to response data.

[0014] Furthermore, the present invention provides a feedback method and system for language model-based cognitive behavioral therapy that can provide cognitive behavioral therapy for pain patients based on digital devices. [Means for solving the problem]

[0015] To solve the above problems, the method for providing feedback for cognitive behavioral therapy based on a language model according to the present invention may include the steps of: providing at least one questionnaire related to cognitive behavioral therapy on a user terminal; receiving response data of the questionnaire through the user terminal; generating a prompt to be input into a generative language model using the response data; inputting the prompt into the generative language model to generate feedback related to the response data; and providing the generated feedback to the user terminal.

[0016] Furthermore, the questionnaire includes a multiple-choice questionnaire of the multiple-choice type, wherein the multiple-choice questionnaire consists of pairs of questions related to cognitive behavioral therapy and a plurality of selection items corresponding to a plurality of different responses to the questions, and in the step of generating the prompt, the prompt may be generated using the questions and the responses to a specific selection item selected by the user terminal from the plurality of selection items.

[0017] Furthermore, each of the multiple distinct responses may be associated with a different score related to cognitive behavioral therapy, and the prompt may include a keyword for the question and a score associated with the specific choice item.

[0018] Furthermore, the questionnaire further includes a written questionnaire that corresponds to a written type, the response data includes memo information received from the user terminal regarding the written type questionnaire, and in the step of generating the prompt, the prompt may be generated using the memo information.

[0019] Furthermore, the method may further include a step of analyzing the meaning of the memo information, which is response data from the descriptive questionnaire, and the meaning of the specific selection items for the multiple-choice questionnaire, and then, based on the results of the analysis, carrying out different processes depending on the degree of similarity between the meaning of the memo information and the meaning of the specific selection items.

[0020] Furthermore, in the steps of performing the different processes, if the similarity is equal to or greater than a preset threshold, the prompt may be generated using the memo information and the response to the specific selection item.

[0021] Furthermore, if the similarity is less than the predetermined threshold value, the step of conducting a re-survey may be further included, and in the step of conducting the re-survey, guide information on the reason for conducting the re-survey may also be provided on the user terminal when conducting the re-survey.

[0022] Furthermore, the server stores multiple treatment programs, each associated with a different topic, and the user terminal is provided with the multiple treatment programs sequentially according to the treatment weeks set for each of the multiple treatment programs, so that the user can perform the cognitive behavioral therapy according to each of the multiple treatment programs. The further steps include extracting user information about the user registered on the server and information about a specific treatment program among the multiple treatment programs provided to the user terminal, and in the step of generating the prompt, the prompt may be generated by combining at least a portion of the response data, the user information, and the information about the specific treatment program.

[0023] Furthermore, the user information may include at least one of the user's gender, age, sexual orientation, and disease, and the information regarding the specific treatment program may include information regarding a specific treatment week corresponding to the specific treatment program, a specific topic associated with the specific treatment program, and the user's treatment history information up to the specific treatment week.

[0024] Furthermore, the feedback may include summary information relating to at least a portion of the response data, user information, and information relating to the specific treatment program included in the prompt, and recommendation information relating to the specific treatment program scheduled to be implemented in the week following the specific treatment week corresponding to the specific treatment program.

[0025] On the one hand, the feedback providing system for cognitive behavioral therapy based on a language model according to the present invention includes a control unit that provides at least one questionnaire related to cognitive behavioral therapy on a user terminal. The control unit receives questionnaire response data for the questionnaire through the user terminal, generates a prompt to be input into a generative language model using the response data, inputs the prompt into the generative language model to generate feedback related to the response data, and may provide the generated feedback to the user terminal.

[0026] On the other hand, the program according to the present invention is a program that is executed according to one or more processes in an electronic device and can be stored in a computer-readable recording medium. The program includes instruction words for executing steps of providing at least one questionnaire related to cognitive behavioral therapy on a user terminal, receiving response data of the questionnaire through the user terminal, generating a prompt to be input into a generative language model using the response data, inputting the prompt into the generative language model to generate feedback related to the response data, and providing the generated feedback to the user terminal.

Advantages of the Invention

[0027] As described above, the feedback providing method and system for cognitive behavioral therapy based on a language model according to the present invention receive a user's response in real time through an online-provided questionnaire, and provide feedback based on this. Thus, even when it is difficult for the user to have regular face-to-face consultations, the user can receive continuous therapeutic support related to cognitive behavioral therapy.

[0028] In addition, the feedback providing method and system for cognitive behavioral therapy based on the language model according to the present invention can grasp the user's state and needs from various perspectives through multiple-choice and descriptive questionnaires. As a result, it is possible to provide more accurate feedback to the user and provide a treatment plan corresponding to the actual needs of the user.

[0029] Furthermore, the feedback providing method and system for cognitive behavioral therapy based on the language model according to the present invention input a prompt generated by combining the user's response data to the questionnaire, the user's gender, age, orientation, disease information, and information related to a specific treatment program into a generative language model, and by using the generative language model, it is possible to generate customized feedback for the user. Through the customized feedback, the user can more deeply understand the state information regarding the level of their pain and the level of cognitive distortion, and receive effective treatment guidance accordingly.

Brief Description of the Drawings

[0030] [Figure 1] It is a conceptual diagram for explaining a feedback providing system for cognitive behavioral therapy based on the language model according to the present invention. [Figure 2] It is a flowchart for explaining a feedback providing method for cognitive behavioral therapy based on the language model according to the present invention. [Figure 3a] It is a conceptual diagram for explaining a feedback providing method for cognitive behavioral therapy based on the language model according to the present invention. [Figure 3b] It is a conceptual diagram for explaining a feedback providing method for cognitive behavioral therapy based on the language model according to the present invention. [Figure 4a] It is a conceptual diagram for explaining a feedback providing method for cognitive behavioral therapy based on the language model according to the present invention. [Figure 4b] It is a conceptual diagram for explaining a feedback providing method for cognitive behavioral therapy based on the language model according to the present invention. [Figure 4c] This is a conceptual diagram illustrating a method for providing feedback for cognitive behavioral therapy based on a language model according to the present invention. [Figure 4d] This is a conceptual diagram illustrating a method for providing feedback for cognitive behavioral therapy based on a language model according to the present invention. [Figure 4e] This is a conceptual diagram illustrating a method for providing feedback for cognitive behavioral therapy based on a language model according to the present invention. [Figure 4f] This is a conceptual diagram illustrating a method for providing feedback for cognitive behavioral therapy based on a language model according to the present invention. [Figure 4g] This is a conceptual diagram illustrating a method for providing feedback for cognitive behavioral therapy based on a language model according to the present invention. [Figure 5] This is a conceptual diagram illustrating a method for providing feedback for cognitive behavioral therapy based on a language model according to the present invention. [Figure 6] This is a conceptual diagram illustrating a method for providing feedback for cognitive behavioral therapy based on a language model according to the present invention. [Figure 7a] This is a conceptual diagram illustrating how to deliver a cognitive behavioral therapy program through feedback. [Figure 7b] This is a conceptual diagram illustrating how to deliver a cognitive behavioral therapy program through feedback. [Figure 7c] This is a conceptual diagram illustrating how to deliver a cognitive behavioral therapy program through feedback. [Modes for carrying out the invention]

[0031] The embodiments disclosed herein will be described in detail below with reference to the accompanying drawings, but regardless of the reference numerals used in the drawings, identical or similar components will be given the same reference numerals, and redundant descriptions thereof will be omitted. The suffixes “module” and “part” used for components in the following description are added or mixed for the sake of ease of writing the specification and do not have any distinguishing meaning or role in themselves. Furthermore, when describing the embodiments disclosed herein, if it is determined that a detailed description of the relevant prior art would obscure the gist of the embodiments disclosed herein, such detailed description will be omitted. In addition, the accompanying drawings are intended solely to facilitate the understanding of the embodiments disclosed herein, and the technical ideas disclosed herein should not be limited by the accompanying drawings and should be understood to include all modifications, equivalents and substitutions that fall within the concept and technical scope of the present invention.

[0032] Terms including ordinal numbers such as "1st," "2nd," etc., may be used to describe various components, but the components are not limited to those defined by these terms. These terms are used solely to distinguish one component from another.

[0033] When it is stated that one component is “connected” or “linked” to another component, it should be understood that it may be directly connected or linked to the other component, but there may also be another component between them. On the other hand, when it is stated that one component is “directly connected” or “directly linked” to another component, it should be understood that there is no other component between them.

[0034] A singular expression includes plural forms unless otherwise clearly indicated in the context.

[0035] In this application, terms such as “includes” or “having” are intended to specify the presence of features, figures, steps, actions, components, parts, or combinations thereof as described in the specification, and should be understood not to preemptively exclude the possibility of the presence or addition of one or more other features, figures, steps, actions, components, parts, or combinations thereof.

[0036] The present invention relates to a method and system for generating appropriate feedback based on the user's pain level, sense of competence, mood, short records, etc., and for providing the generated feedback to the user, and in particular to providing feedback for cognitive behavioral therapy for pain patients, focusing on patients with pain due to musculoskeletal disorders.

[0037] More specifically, the present invention relates to a method and system for providing feedback for cognitive behavioral therapy, which generates prompts for a generative language model using response data from a questionnaire related to cognitive behavioral therapy, and generates feedback related to the questionnaire response data by inputting the generated prompts into the generative language model.

[0038] The questionnaire described in this invention may include cognitive behavioral therapy-related questions to examine at least one of the following: the user's pain level, level of cognitive distortion, duration of pain, severity of pain, mood during the pain experience, degree of negative feelings towards pain, degree of stress towards pain, physical health status, and mental health status.

[0039] Here, "pain level" can be understood as a measure of the intensity or severity of pain experienced by an individual. Pain is a subjective and personal experience, and the way in which people feel and interpret pain varies from person to person. Pain can be accompanied by physical discomfort, emotional discomfort, and distress. Various methods can be used to assess such pain levels. For example, a numerical rating scale (NRS) can be provided to the patient to assess the intensity of the pain they feel (e.g., no pain, mild pain, severe pain).

[0040] Furthermore, "cognitive distortion" refers to cognitive errors that lead to incorrect assumptions or false concepts about pain, surrounding circumstances, and events, and "level of cognitive distortion" can be understood as a term that expresses the degree to which a patient exhibits cognitive distortion. In this invention, the level of cognitive distortion can be quantified as a "cognitive distortion score" or "cognitive distortion score."

[0041] Furthermore, the term "pain patient" as used in this invention refers to a patient experiencing pain due to a disease, and in this invention, "pain patient" can be used interchangeably with "patient" or "user."

[0042] For the sake of explanation, this invention will primarily focus on "musculoskeletal disorders," but it is not necessarily limited to these. In other words, the pain patients described in this invention may include patients with various other diseases (e.g., cancer, diabetes, hypertension, etc.) in addition to those with musculoskeletal disorders.

[0043] On the other hand, the feedback system for cognitive behavioral therapy based on the language model according to the present invention (hereinafter referred to as the "feedback system") can be implemented in the form of various platforms such as applications, software, and websites.

[0044] According to the software implementation of the feedback provision system of the present invention, embodiments such as the procedures and functions described herein can be implemented as individual software treatment modules. Each software treatment module can perform one or more functions and operations described herein.

[0045] Thus, a software-based feedback system may be downloaded via a program that allows applications to be downloaded onto a user terminal (or patient terminal) (e.g., the Play Store, App Store, etc.), or it may be implemented via an initial installation program on the user terminal. In this case, at least one of the components of the feedback system can be utilized as a component of the user terminal.

[0046] In the present invention, "terminal" is also referred to as "mobile terminal" or "electronic device," and the terminals described in the present invention may include at least one of the following: mobile phone, smartphone, notebook computer, laptop computer, slate PC, tablet PC, ultrabook, desktop computer, digital broadcasting terminal, PDA (personal digital assistant), PMP (portable multimedia player), navigation system, and wearable device (e.g., smartwatch, smart glass, HMD (head mounted display)).

[0047] On the other hand, the feedback provision system may reside within a server (hereinafter referred to as "the server") built for a specific purpose (for example, a function related to providing feedback for cognitive behavioral therapy), separate from the user terminal, or it may exist as a system separate from the server. When the feedback provision system resides within the server, it can provide various services related to the present invention (for example, a feedback provision service for cognitive behavioral therapy or a cognitive behavioral therapy provision service) through at least one component located within the server, or through a configuration module that performs a similar function to the above-mentioned component. In this case, the application can provide various services related to the present invention on the user terminal on which the application is installed through communication with the server.

[0048] Furthermore, the feedback provision system can work in conjunction with a central server or an external server to provide the feedback provision method for cognitive behavioral therapy and the cognitive behavioral therapy provision method according to the present invention to user terminals.

[0049] Furthermore, the feedback system can use a user terminal to diagnose the patient's pain level and cognitive distortion level, and, taking this into consideration, provide appropriate summaries and feedback for cognitive behavioral therapy, or provide various services related to cognitive behavioral therapy (e.g., providing treatment programs for cognitive behavioral therapy).

[0050] On the other hand, patients can diagnose their own pain level and cognitive distortion level through the feedback system or application or webpage provided according to the present invention, and receive appropriate feedback based on their own pain level and cognitive distortion level. They can also receive various services related to cognitive behavioral therapy (e.g., provision of cognitive behavioral therapy programs) and manage at least one of their mental health and physical health.

[0051] In this case, the patient may have a user account registered in the feedback system. For the purposes of this specification, a user account that is a patient will be referred to as a "patient account" or "user account."

[0052] The aforementioned "account" can be generated through a page linked to the aforementioned feedback system. Alternatively, the "account" can also be generated in at least one other system linked to the aforementioned feedback system.

[0053] Therefore, in this specification, without specifically distinguishing the systems in which accounts are issued, all accounts based on the feedback provision system according to the present invention are referred to as "accounts pre-registered in the feedback provision system according to the present invention."

[0054] For the sake of clarity, this specification will describe an embodiment in which the feedback provision system according to the present invention is implemented as an application on a user terminal.

[0055] On the other hand, in the case of pain patients, even with the same disease (or illness), the level of pain and cognitive distortion that occurs on a daily basis can differ from patient to patient.

[0056] Therefore, the present invention can generate appropriate feedback based on the user's pain level, sense of competence, mood, short records, etc., and provide the generated feedback to the user.

[0057] The configuration of the feedback system for cognitive behavioral therapy based on the language model according to the present invention will be described in more detail below, along with the attached drawings. Figure 1 is a conceptual diagram illustrating the feedback system for cognitive behavioral therapy based on the language model according to the present invention.

[0058] As shown in Figure 1, the feedback provision system 100 according to the present invention may include at least one of the following components: an input unit 110, a communication unit 120, a storage unit 130, and a control unit 140.

[0059] The input unit 110 can receive input from the user (or patient) via the configuration of the input unit provided in the user terminal 10 (or patient terminal) (for example, a touch screen, virtual keys, physical keys (or hardware buttons), input sensors, microphones, etc.).

[0060] Specifically, the input unit 110 may be configured to select a user's response to at least one questionnaire related to cognitive behavioral therapy using the configuration of the input unit provided in the user terminal 10. Here, "selected" may mean that when a user's selection is made via the configuration of the input unit provided in the user terminal 10, a selection signal (or input signal or user input) corresponding to such user selection is received.

[0061] The communication unit 120 may be connected to servers and other devices via a wireless or wired network and may be configured to receive or transmit overall data and information necessary for the feedback provision system 100.

[0062] Specifically, the communication unit 120 may include one or more treatment modules that enable wireless or wired communication between the feedback provision system 100 and the user terminal 10, or between the feedback provision system 100 and the artificial intelligence server 200 (or LLM server), a central server, or an external server. The communication unit 120 may also include one or more communication modules that connect the feedback provision system 100 to one or more networks.

[0063] For example, the communication unit 120 can receive (or collect) response data from at least one questionnaire related to cognitive behavioral therapy from at least one source via the user terminal 10. In another example, the communication unit 120 can receive a request from the user terminal 10 for the provision of a specific treatment program for cognitive behavioral therapy.

[0064] Furthermore, the communication unit 120 can support various communication methods depending on the communication standard of the device performing the communication.

[0065] For example, the communication unit 120 supports WLAN (Wireless LAN), Wi-Fi (Wireless-Fidelity), Wi-Fi (Wireless Fidelity) Direct, 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), LTE-A (Long Term Evolution-Advanced), 5G (5th Generation Mobile Telecommunication), and Bluetooth. TM The system may be configured to communicate with a communication target using at least one of the following technologies: (registered trademark), RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra-Wideband), ZigBee, NFC (Near Field Communication), Wi-Fi Direct, or Wireless USB (Wireless Universal Serial Bus).

[0066] On the other hand, the storage unit 130 is also called a database (DB) or memory, and may be configured to store various information related to the present invention. In the present invention, the storage unit 130 may be provided in the feedback provision system 100 itself. Also, at least a part of the storage unit 130 may consist of a cloud server (or cloud storage). In other words, the storage unit 130 only needs to be a space in which information necessary for the operation of the feedback provision system 100 according to the present invention is stored, and it can be understood that there are no restrictions on physical space. Hereinafter, the storage unit 130, the cloud server (or cloud storage), and the storage of a server linked to the feedback provision system 100 (not shown) will not be particularly distinguished, and will all be referred to as the storage unit 130.

[0067] The memory unit 130 may store user information registered in the feedback provision system 100 (or server). For example, the user information may include information about at least one of the following: the user's gender, age, sexual orientation (or personality), and disease (or illness). However, the user information may also include various other information besides the information listed above, such as the user's disease onset date, treatment (or medical) history, occupation, interests, and hobbies.

[0068] Furthermore, the memory unit 130 may store information about a specific treatment program provided to the user. For example, the information about a specific treatment program may include at least one of the following: information about a specific treatment week corresponding to the specific treatment program, a specific topic associated with the specific treatment program, and the user's treatment history information up to the specific treatment week.

[0069] On the other hand, the control unit 140, also called a processor, can cooperate with memory to control the overall operation of the feedback system 100 related to the present invention. The control unit 140 can process signals, data, information, etc. that are input or output through the above-mentioned components, or can perform a series of data processing to provide or process appropriate information and functions to the user.

[0070] In one embodiment of the present invention, the control unit 140 can generate prompts for a generative language model using response data from a questionnaire related to cognitive behavioral therapy, and input the generated prompts into the generative language model to generate feedback related to the questionnaire response data. The control unit 140 can also provide the feedback generated using the generative language model to the user terminal 10.

[0071] The following describes in more detail the method for providing feedback for cognitive behavioral therapy based on the language model according to the present invention, based on the configuration of the feedback provision system 100 described above. Figure 2 is a flowchart illustrating the method for providing feedback for cognitive behavioral therapy based on the language model according to the present invention. Figures 3a, 3b, 4a, 4b, 4c, 4e, 4f, 4g, 5 and 6 are conceptual diagrams illustrating the method for providing feedback for cognitive behavioral therapy based on the language model according to the present invention. Figures 7a, 7b and 7c are conceptual diagrams illustrating a method for providing a cognitive behavioral therapy program through feedback.

[0072] On the other hand, the present invention can provide at least one questionnaire related to cognitive behavioral therapy on the user terminal (see S210, Figure 2).

[0073] For example, as shown in Figure 3a, the control unit 140 can provide a survey page (or service page) containing multiple questionnaires on the user terminal 10. In this case, the page containing the multiple questionnaires may be output via the touchscreen (or display) of the user terminal 10.

[0074] Herein, the questionnaire (or questions, problems, items, or tests) provided on the aforementioned page may include a questionnaire for the relative assessment of pain-related factors.

[0075] The pain-related factors in this invention can be diverse. For example, pain-related factors may include various elements for evaluating the patient's condition regarding pain, such as the level of pain, the duration of pain, mental health, and physical health. However, the factors mentioned above are merely examples, and it is sufficient for the pain-related factors described in this invention to include all elements for evaluating the patient's condition.

[0076] Such pain-related factors may include reliable questionnaires that are actually used in mental health departments to diagnose patients' conditions. Furthermore, the control unit 140 can periodically update the questionnaires by collecting more questionnaires for diagnosing patients' conditions via a central server, an external server, or a website.

[0077] On the other hand, in the present invention, the questionnaire related to cognitive behavioral therapy may include multiple-choice questionnaires and open-ended questionnaires.

[0078] A multiple-choice questionnaire may consist of pairs of questions related to cognitive behavioral therapy and multiple selection items corresponding to each of several different responses to the said questions. For example, as shown in Figures 3a and 3b(a), a first multiple-choice questionnaire 310 may consist of a question 311 related to cognitive behavioral therapy (e.g., "How is your pain today?") and multiple selection items 311a, 311b, 311c, 311d, 311e corresponding to each of several different responses to the said question (e.g., "No pain," "Very little pain," "Normal," "Somewhat severe pain," "Very severe pain").

[0079] Furthermore, multiple different responses may be associated with different scores related to cognitive behavioral therapy. For example, among the multiple different responses (e.g., "no pain," "very slight pain," "normal," "moderately severe pain," "very severe pain") that make up the first questionnaire 310, the first response (e.g., "no pain") may be associated with a first score related to cognitive behavioral therapy (e.g., "0 points"), and the fifth response (e.g., "very severe pain") may be associated with a fifth score related to cognitive behavioral therapy (e.g., "4 points").

[0080] Therefore, as a response to any of the displayed questionnaires, users can select a specific item from among multiple options corresponding to several different responses that they believe best reflects (or is appropriate for or accurate to) their situation.

[0081] Furthermore, the open-ended questionnaire may include questions related to cognitive behavioral therapy and a response area (or input area) configured to allow the user to input their response to the question as text. For example, as shown in Figure 3a, the fourth questionnaire 340, which corresponds to the open-ended questionnaire, may include questions related to cognitive behavioral therapy (e.g., "One-line memo" or "Please record your day in a one-line memo!") and a response area 341 configured to allow the user to input their response to the question as text. In this case, the fourth questionnaire may be a questionnaire in which information about the user's various states (e.g., pain level, competence, mood, etc.) is input as text, and which detects the user's state information based on the text.

[0082] In this invention, for the sake of explanation, response data from a written questionnaire will be referred to as "memo information."

[0083] In this case, the present invention can receive memo information, which is response data from a written questionnaire, from the user terminal 10, and analyze the meaning of the memo information based on pre-set criteria.

[0084] Here, "analyzing the meaning of memo information" can be understood as analyzing the meaning of the text content contained in the memo information and determining whether the meaning of the text content corresponds to a positive or negative meaning.

[0085] For this purpose, the feedback system 100 according to the present invention may have pre-set criteria for analyzing the meaning of memo information. For example, as shown in Figure 3b(b), if the memo information corresponds to a positive meaning, it may include text relating to positive state expressions (e.g., "Today is great!, I feel great, I'm in good physical condition and in great shape!, It's a pretty good day, I'm neither happy nor sad..."). As another example, if the memo information corresponds to a negative meaning, it may include text relating to negative state expressions (e.g., "Today is the worst!, I feel terrible, I'm in so much pain and in the worst condition, I don't want to do anything, I'm in the worst physical and mental state, I'm not feeling very well, I'm irritated...").

[0086] However, the present invention does not limit the method by which a user responds to (or completes) multiple questionnaires to a single method. For example, the first questionnaire 310, the second questionnaire 320, and the third questionnaire 330, which correspond to multiple-choice questionnaires, may all be configured to allow responses by text input, such as the fourth questionnaire 340, which corresponds to a written questionnaire. Furthermore, in the present invention, responses to questionnaires may be configured to be input not only by selecting specific items or text input, but also by voice, images, videos, etc.

[0087] Next, the present invention allows for the process of receiving questionnaire response data through a user terminal (see S220, Figure 2).

[0088] As described above, the questionnaire related to cognitive behavioral therapy in the present invention may include multiple-choice questionnaires and open-ended questionnaires.

[0089] The response data for a multiple-choice questionnaire may be a selection signal for any one of several selection items, and the control unit 140 can determine a specific selection item corresponding to the received selection signal as the response data.

[0090] The control unit 140 can receive response data from a multiple-choice questionnaire via the user terminal 10. For example, as shown in Figure 3a, the control unit 140 can receive a selection signal from the user terminal 10 based on the selection of one specific selection item 311e from among the multiple selection items 311a, 311b, 311c, 311d, and 311e configured in the first questionnaire 310. The control unit 140 can also receive the specific selection item 311e corresponding to the received selection signal as response data for the first questionnaire.

[0091] Furthermore, the control unit 140 can receive response data from the written questionnaire through the user terminal 10. For example, based on the input of memo information 342 (for example, "My leg hurts so badly today, everything is awful...") from the user terminal 10 into the response area 341 configured in the fourth questionnaire 340, the control unit 140 can receive an input signal corresponding to the memo information 342. The control unit 140 can also receive the memo information 342 corresponding to the received input signal as response data for the fourth questionnaire.

[0092] On the other hand, a server linked to the feedback provision system 100 according to the present invention may store multiple treatment programs, each associated with a different topic.

[0093] As a result, the user terminal 10 can be sequentially provided with multiple treatment programs, according to the treatment week set for each of the multiple treatment programs, so that the user can carry out cognitive behavioral therapy according to each of the multiple treatment programs. For the sake of explanation, the following description will focus on the control unit 140 rather than the server linked to the feedback provision system 100.

[0094] In this invention, a "treatment week" can be understood as the sequence (or period) in which the treatment program is provided (or activated) through the user terminal 10 so that the user performs cognitive behavioral therapy according to the treatment program. In this invention, the "total number" of treatment weeks and the "weekly treatment period" corresponding to each treatment week may be predetermined. In addition, in this invention, it can be understood that the "total treatment period" is predetermined. The total treatment period can be determined by the product of the predetermined total number and the predetermined weekly treatment period. For example, if the total number is "8" and the weekly treatment period is 1 week (7 days), the predetermined total treatment period may be "8 weeks".

[0095] For the sake of explanation, the following will be described as an example where eight different treatment weeks occur within each one-week treatment period. That is, in the present invention, the first treatment week can occur during the first treatment session, and the second treatment week can occur during the second treatment session. Therefore, in the present invention, "treatment week" can be used interchangeably with "treatment session," "treatment number," "treatment period," and "treatment sequence."

[0096] As described above, in the present invention, the total number of treatment weeks (e.g., "8") may be predetermined. For example, as shown in Figure 4a, in the present invention, the total number of treatment weeks (e.g., "8 sessions") may be predetermined. Here, let us assume that there are multiple treatment programs, namely "the first treatment program to the eighth treatment program". In this case, each of the first to eighth treatment programs may have one of the first to eighth treatment weeks set.

[0097] Each of the multiple treatment programs (for example, the first to the eighth treatment program) may have multiple topics associated with it (or matched to it). For example, i) the first treatment program may be for training or treatment on the first topic (e.g., strengthening motivation); ii) the second treatment program may be for training or treatment on the second topic (e.g., acknowledging feelings); iii) the third treatment program may be for training or treatment on the third topic (e.g., behavioral strategies); iv) the fourth treatment program may be for training or treatment on the fourth topic (e.g., shifting attention); v) the fifth treatment program may be for training or treatment on the fifth topic (e.g., shifting thoughts); vi) the sixth treatment program may be for training or treatment on the sixth topic (e.g., recording thoughts); vii) the seventh treatment program may be for training or treatment on the seventh topic (e.g., management strategies); and viii) the eighth treatment program may be for training or treatment on the eighth topic (e.g., my future self).

[0098] Furthermore, each of the multiple treatment programs may consist of at least one treatment module related to a specific topic associated with that particular treatment program. For example, the first treatment program may consist of multiple treatment modules relating to the first topic (e.g., motivation enhancement).

[0099] Here, “treatment module” may mean content relating to a specific category (or subtopic) for cognitive behavioral therapy for pain patients on a particular topic. In the present invention, a treatment module included in a treatment program related to a particular topic may also be called a “topic-specific treatment module,” and “treatment module” may be used interchangeably with “chapter.”

[0100] In this invention, specific treatment modules constituting multiple specific treatment programs can be sequentially provided to the user terminal 10 according to the treatment week set for each of the multiple specific treatment programs. For example, the control unit 140 can sequentially provide multiple treatment modules constituting the first treatment program to the user terminal 10 during the treatment week corresponding to the first week.

[0101] Here, "the order of treatment modules" can be understood as the sequence in which multiple treatment modules included in a particular treatment program are provided.

[0102] Furthermore, "therapy module activation mode" can be understood as a mode in which the therapy module can be viewed (or used). On the other hand, "therapy module deactivation mode" can be understood as a mode in which the therapy module cannot be viewed (or used).

[0103] Furthermore, in this invention, based on the completion of cognitive behavioral therapy using the treatment module corresponding to a specific sequence, according to the sequence of treatment modules, the mode of the treatment module corresponding to the next sequence in a particular sequence can be changed (or switched) from deactivation mode to activation mode.

[0104] For example, suppose the first treatment program consists of the first to fifth treatment modules. The control unit 140 may switch the mode of the second treatment module from deactivation mode to activation mode based on the completion of cognitive behavioral therapy in the first treatment module.

[0105] In other words, each of the multiple treatment programs may consist of at least one treatment module related to a topic associated with that treatment program, and such a treatment program may mean a program for providing treatment in response to a topic associated with a particular treatment program.

[0106] On the other hand, each of the multiple treatment programs may include a worksheet module for checking at least one of the following: the level of pain, the duration of pain, the mental health status, and the physical health status of the pain patient.

[0107] In this case, each worksheet module may contain user response information to check at least one of the following: the pain level, duration of pain, mental health status, and physical health status of the pain patient, in relation to a specific topic in the treatment program that contains the worksheet module. Furthermore, each worksheet module may contain a variety of user response information to check at least one of the following: the pain level, duration of pain, mental health status, and physical health status of the pain patient, in addition to content related to a specific topic in the treatment program.

[0108] For example, a worksheet module included in the first treatment program may contain user response information to check at least one of the following in relation to the first topic (e.g., reinforcement of motivation): the level of pain, the duration of pain, the mental health status, and the physical health status of the pain patient.

[0109] As another example, a worksheet module included in the second treatment program may contain user response information to check at least one of the following in relation to the second topic (e.g., emotional assessment): the level of pain, the duration of pain, mental health status, and physical health status of the pain patient.

[0110] Such worksheet modules may be provided at various points in each treatment program. For example, a worksheet module may be located at the end or in the middle of each treatment module. In other words, the position in which a worksheet module is included in each treatment program can be varied depending on the condition of the patient experiencing pain.

[0111] On the other hand, the worksheet module may be provided as the final module in each treatment program. The worksheet module may be placed as the last module among the treatment modules that make up each treatment program, and may be configured so that the pain patient performs the worksheet module after completing all the treatment modules of the treatment program. This may include the purpose of receiving feedback from the pain patient regarding the treatment effect of the treatment program, objectification of that effect, or the pain patient's response.

[0112] Furthermore, the worksheet modules included in each treatment program may be configured to allow the patient to score (e.g., select and input scores) for factors such as the severity of pain, mood during the pain experience, degree of negative feelings towards the pain, and degree of stress related to the pain. The control unit 140 can use the scores received from the worksheet modules to determine whether the treatment program containing the worksheet module was beneficial and effective for the patient.

[0113] In this regard, as shown in Figure 4b, the control unit 140 can control the output of a page 400 (or service page) for providing cognitive behavioral therapy services through the display unit (or touchscreen) provided on the user terminal 10. Such a page 400 may also be output on the user terminal 10 via an application or web page installed on the user terminal 10.

[0114] Page 400 is a page linked to the feedback provision system 100 (or a server linked to the feedback provision system) according to the present invention, and is configured to be controlled by the feedback provision system 100 according to the present invention.

[0115] Furthermore, if the page 400 is provided in the form of an application, the page 400 may be controlled by the CPU (Central Processing Unit) of the user terminal 10 on which the application is installed. In this case, the CPU of the user terminal 10 can provide services related to cognitive behavioral therapy to pain patients based on the information provided by the feedback provision system 100 according to the present invention.

[0116] The control unit 140 can sequentially provide multiple treatment programs to the user terminal 10 where user account U is logged in, according to the treatment week set for each of the multiple treatment programs.

[0117] Specifically, the control unit 140 can activate the state of a specific treatment program so that a specific treatment program with a set specific treatment week can be provided to the user terminal 10 during the treatment period corresponding to a specific treatment week. To avoid confusion of terminology, the state of a specific treatment program will be referred to as the "mode" of the specific treatment program below.

[0118] In the present invention, "treatment program activation mode" can be understood as a mode in which at least a portion of the multiple treatment modules included in the treatment program can be viewed (or used). On the other hand, "treatment program deactivation mode" can be understood as a mode in which all of the multiple treatment modules included in the treatment program cannot be viewed (or used).

[0119] For example, suppose that the cognitive behavioral therapy week for user account U is "First Treatment Week (e.g., Week 1)". As shown in Figures 4c and 4d, the control unit 140 can activate the state of the first treatment program 410 (e.g., a program related to motivation enhancement) on the user terminal 10 so that the first treatment program 410 (e.g., a program related to motivation enhancement) for which the first treatment week is set can be provided on the user terminal 10 during the treatment period corresponding to the first treatment week.

[0120] Furthermore, the control unit 140 can provide worksheet modules included in a specific treatment program to the user terminal 10 and receive user response information to the worksheet modules. For example, the control unit 140 can provide the user terminal 10 with a first worksheet module 411 (e.g., "Which part of your knee pain is the most difficult to deal with?") and a second worksheet module 412 (e.g., "My future self who can cope with pain well") included in the first treatment program 410, and receive the user's first response information to the first worksheet module 411 (e.g., "A physical part") and the user's second response information to the second worksheet module 412 (e.g., "My future self enjoying travel with a healthier body"). At this time, the control unit 140 can receive the received first and second response information as worksheet response data for the first and second worksheet modules.

[0121] Furthermore, when the next treatment week arrives, the control unit 140 can activate a specific treatment program mode corresponding to the next treatment week. For example, when the first treatment week has passed and the next treatment week, the second treatment week (e.g., week 2), has arrived, the control unit 140 can activate a second treatment program mode for which the second treatment week is set.

[0122] Therefore, patients can systematically receive cognitive behavioral therapy by sequentially using multiple treatment programs according to a predetermined treatment week.

[0123] On the other hand, the control unit 140 can calculate (or derive or calculate) the user's pain score and cognitive distortion score based on worksheet response data (or user response information) for at least one worksheet module included in a specific treatment program.

[0124] As described above, each worksheet module may contain user response information to check at least one of the following: the user's pain level, duration of pain, severity of pain, mood during the pain experience, degree of negative feelings towards pain, degree of stress towards pain, mental health status, physical health status, and the user's therapeutic effect on the treatment program.

[0125] The control unit 140 can calculate the user's pain score and cognitive distortion score from the worksheet response data using various methods. In this case, the worksheet module may be configured to include a worksheet corresponding to either a multiple-choice or open-ended format, and the worksheet corresponding to the multiple-choice format may be configured to include multiple selection items to which different scores are associated. For example, the control unit 140 can use (or calculate) the worksheet response data corresponding to the multiple-choice format to calculate the user's pain score and cognitive distortion score.

[0126] Furthermore, the control unit 140 may store the user's pain score and cognitive distortion score in the storage unit 130 in association with the user's user account U. For example, as shown in Figure 4g, the control unit 140 can store the user's pain score (e.g., "24 points") and cognitive distortion score (e.g., "26 points") calculated based on the user's cognitive behavioral therapy results, along with the user's cognitive behavioral therapy week (e.g., "week 2"), in the storage unit 130 in association with the user account U.

[0127] In this case, the pain score and cognitive distortion score may be scores calculated based on the user's pain level, duration of pain, severity of pain, mood during pain experiences, degree of negative feelings towards pain, degree of stress towards pain, mental health status, physical health status, feedback, and the user's therapeutic effect on the treatment program, all collected through the user terminal 10 during the user's cognitive behavioral therapy process. In other words, the scores may be calculated based on the results of cognitive behavioral therapy up to a specific week of ongoing treatment.

[0128] In this regard, the control unit 140 can provide summary information on the user terminal 10 regarding the results of cognitive behavioral therapy up to a specific treatment week in progress. For example, as shown in Figures 4e and 4f, the control unit 140 can output a page 420 on the user terminal 10 containing summary information 421 and 422 regarding the user's cognitive behavioral therapy results.

[0129] In this case, the information included in summary information 421 and 422 may include at least one of the following: a pain score, a competence score, and a mood score, calculated based on the user's response information to a worksheet module that includes at least one of the following: the user's pain level, the duration of pain, the severity of pain, mood at the time of pain experience, the degree of negative feelings towards pain, the degree of stress towards pain, mental health status, physical health status, feedback, and the user's therapeutic effect on the treatment program.

[0130] In other words, the summary information 421 and 422 contained in page 420 may be information calculated based on the user's response to at least one worksheet module included in a particular treatment program.

[0131] Furthermore, such summary information 421 and 422 may be provided in various formats to allow users to more intuitively review the detection results of their own condition information for each treatment week (or day). For example, the first summary information 421 may be provided in the form of a graph (or chart, or table), and the second summary information 422 may be provided in the form of text.

[0132] Thus, the present invention provides a user environment that allows users to more intuitively check their own condition information and continuously monitor and compare the changes in their results before and after cognitive behavioral therapy, by providing a highly readable interface to users undergoing cognitive behavioral therapy.

[0133] On the other hand, the control unit 140 can extract user information about users registered on the server, and information about a specific treatment program provided to the user terminal 10 from among multiple treatment programs.

[0134] The server (or feedback system 100) may store user information associated with user account U. For example, the user information may include at least one of the following: the user's gender, age, disease (or illness), date of disease onset, treatment (or medical treatment) history, personality (or disposition), occupation, interests, and hobbies.

[0135] Furthermore, the information provided to the user terminal 10 regarding a specific treatment program may include at least one of the following: information regarding a specific treatment week corresponding to the specific treatment program, a specific topic associated with the specific treatment program, and the user's treatment history information up to the specific treatment week.

[0136] Here, the user's treatment history information may include, for example, the user's pain level, duration of pain, mental and physical health status, mood during pain experiences, degree of negative feelings towards pain, degree of stress towards pain, and the user's therapeutic effect on a particular treatment program.

[0137] In other words, the control unit 140 can extract user information and information about a specific treatment program provided to the user terminal 10 from the server. This information can be partially utilized in the process of generating prompts to be input to the generative language model. More specific details will be described later.

[0138] On the other hand, the control unit 140 can compare the user's responses to the open-ended questionnaire and the user's responses to the multiple-choice questionnaire to determine whether the user responded consistently throughout the cognitive behavioral therapy process. Based on the determination that the user responded consistently, the control unit 140 can generate a prompt using the questionnaire responses. On the other hand, if the control unit 140 determines that the user did not respond consistently, it can conduct a re-questionnaire and generate a prompt using the responses obtained as a result of the re-questionnaire.

[0139] The control unit 140 can determine whether the user's response is consistent, ensure the accuracy of the cognitive results perceived by the user, and provide more effective feedback based on accurate responses.

[0140] To this end, the control unit 140 can perform a semantic analysis on the memo information received from the user terminal for the descriptive questionnaire and on the specific selection items selected by the user terminal for the multiple-choice questionnaire, and calculate the degree of semantic similarity between the memo information and the specific selection items.

[0141] The control unit 140 can determine whether the degree of semantic similarity meets a preset criterion. For example, the control unit can calculate the degree of semantic similarity as a numerical value and determine whether the calculated value is equal to or greater than a preset criterion value. In this case, a higher calculated value indicates a higher degree of semantic similarity between the memo information and the specific selected item, while a lower calculated value indicates a lower degree of semantic similarity between the memo information and the specific selected item.

[0142] Here, the pre-set criteria (or pre-set criterion values) may be pre-set or set by a healthcare professional. Furthermore, the control unit 140 can identify customized cognitive criteria pre-set for each user based on the user's cognitive behavioral therapy history (e.g., responses to questionnaires). For example, the control unit 140 can identify pre-set criteria that correspond to the degree of similarity calculated in the past, based on the cognitive behavioral therapy history. Users who have consistently responded in the past may have a high degree of similarity, and the control unit may set the pre-set criteria high and strictly judge the consistency of responses because such users have consistently responded. On the other hand, users who have not consistently responded in the past may have a low degree of similarity, and the control unit 140 may set the pre-set criteria low and flexibly judge the consistency of responses because such users have not consistently responded.

[0143] On the other hand, the control unit 140 can perform different processes related to prompt generation depending on whether the degree of semantic similarity meets a preset criterion.

[0144] The first of the two distinct processes can generate prompts using memo information and specific selection items based on whether the degree of similarity meets a predetermined criterion. The control unit 140 can generate prompts using memo information and specific selection items to provide feedback to the user, based on whether the memo information for the open-ended questionnaire and the specific selection items for the multiple-choice questionnaire meet a consistency requirement according to a predetermined criterion.

[0145] Furthermore, the second process, which is one of the distinct processes, can generate a prompt using different memo information than the aforementioned memo information, based on the fact that the degree of similarity does not meet a predetermined criterion.

[0146] More specifically, the control unit 140 can conduct a re-questionnaire for at least one of the multiple-choice questionnaire and the open-ended questionnaire according to the second process. In this case, the control unit 140 can provide the user terminal with at least one of the multiple-choice questionnaire and the open-ended questionnaire from the re-questionnaire, as well as guide information including the reason for conducting the re-questionnaire.

[0147] Guide information may be structured in various forms. For example, if a written questionnaire is to be administered again, the control unit 140 may provide as guide information a specific selection item that the user has chosen for a multiple-choice questionnaire, and information explaining why that specific selection item is inconsistent with the memo information previously entered by the user.

[0148] On the other hand, if the degree of similarity between the memo information and a specific selection item does not meet a pre-set standard, the control unit 140 can decide which of the descriptive questionnaires and multiple-choice questionnaires to re-administer.

[0149] The control unit 140 can determine which of the descriptive and multiple-choice questionnaires to repeat by comparing the degree of similarity with a threshold value. In this case, the threshold value may be lower than the set standard value.

[0150] More specifically, if the degree of similarity is less than a preset standard value but greater than or equal to a threshold, the control unit 140 may re-administer either the open-ended questionnaire or the multiple-choice questionnaire. The control unit 140 may re-administer the open-ended questionnaire or the multiple-choice questionnaire whichever was administered later, or it may re-administer only the open-ended questionnaire. Generally, users find it more difficult to objectively express their thoughts in an open-ended questionnaire than in a multiple-choice questionnaire, so even if the user's cognitive abilities are normal, they may make errors when expressing themselves in an open-ended questionnaire. Therefore, the control unit 140 may re-administer the open-ended questionnaire.

[0151] Furthermore, if the degree of similarity is below the threshold, the control unit 140 may re-administer both the multiple-choice questionnaire and the open-ended questionnaire. If the degree of similarity is below the threshold, the control unit 140 may determine that the user's self-awareness is not adequate and may provide guide information to assist the user's perception along with the questionnaire.

[0152] On the other hand, the present invention can perform the process of generating prompts to be input into a generative language model using the received questionnaire response data (see S230, Figure 2).

[0153] The control unit 140 can use the prompt generation unit 150 to generate prompts to be input to the language generation model based on the received questionnaire response data and the various information described above.

[0154] First, the prompt may include a predefined role for deriving cognitive behavioral therapy-related feedback from the generative language model. For example, as shown in Figure 5, the control unit 140 can create a prompt 500 by predefining information 510 regarding a role for deriving feedback related to feature information and questionnaire response data from the generative language model (for example, "Please take on the role of a therapist who derives appropriate summaries and feedback for cognitive behavioral therapy based on the patient's pain level and cognitive distortion level").

[0155] Furthermore, the control unit 140 can generate a prompt 500 using memo information, which is response data from a written questionnaire, and responses to specific selection items, which are response data from a multiple-choice questionnaire. In this case, the memo information and responses to specific selection items used to generate the prompt 500 can be understood as satisfying a pre-set standard value or higher for the similarity between the memo information and the responses to specific selection items.

[0156] The control unit 140 can generate a prompt 500 using response data from a multiple-choice questionnaire. More specifically, the control unit 140 can generate a prompt 500 using responses to specific selection items selected by the user terminal from among the questions and multiple selection items configured in the multiple-choice questionnaire. For example, as shown in Figures 3a and 5, suppose the user terminal 10 selected the 5th item 311e (e.g., "4 points," "very severe pain") as a response to the 1st questionnaire (e.g., "pain," "How is your pain today?"), the 1st item 312a (e.g., "0 points," "not confident at all") as a response to the 2nd questionnaire (e.g., "competence," "Are you confident that you can manage your daily life well despite the pain?"), and the 1st item 313a (e.g., "0 points," "very bad") as a response to the 3rd questionnaire (e.g., "mood," "How was your mood today?"). The prompt 500 may include questions from each of the multiple multiple-choice questionnaires 310, 320, and 330, as well as responses 540 to a specific selection item chosen by the user terminal 10 from among multiple selection items (for example, "In the questionnaire administered today, the patient's pain score was 4, their competence score was 0, and their mood score was 0...").

[0157] Furthermore, the control unit 140 can generate a prompt 500 using memo information, which is response data from a written questionnaire (for example, "My knee hurts so badly today, everything is awful"). For example, the prompt 500 may include memo information, which is response data from a written questionnaire (for example, "The one-line memo records, 'My knee hurts so badly today, everything is awful'.").

[0158] Furthermore, the control unit 140 can generate prompts 500 by combining user information and at least some of the information regarding the specific treatment program. For example, as shown in Figure 5, the control unit 140 can generate system prompts 151 that include the user's age (e.g., "30 years old"), gender (e.g., "male"), disease (e.g., "knee sprain"), week of cognitive behavioral therapy (e.g., "week 2"), pain level (e.g., "severe pain"), duration of pain (e.g., "lasts for about 10 days"), physical health status (e.g., "physically inconvenient"), mental health status (e.g., "suffered significant emotional shock and mental health has deteriorated"), and temperament (e.g., "this patient tends to become very focused once they become engrossed in something, but also has a personality that makes it difficult for them to try new things due to a lack of confidence").

[0159] In other words, the control unit 140 can combine response data, user information, and at least a portion of the information regarding the specific treatment program to generate a prompt 500 that is input to the generating language model.

[0160] On the other hand, the present invention can perform the process of inputting a prompt into a generating language model to generate feedback related to the response data (S240, see Figure 2), and providing the generated feedback to the user terminal (S250, see Figure 2).

[0161] The control unit 140 can input the prompt 500 generated in the process of S230 into the generating language model to generate feedback related to the questionnaire response data. For example, as shown in Figure 6, the control unit 140 inputs a prompt 500, which combines response data, user information, and at least a portion of the information regarding the specific treatment program, into the generating language model, and can obtain feedback 600 from the generating language model as a response to the prompt 500 (for example, "Despite the progress made over two weeks of cognitive behavioral therapy, it sounds like you had a terrible day. You are currently experiencing severe pain from a knee sprain that has lasted for about 10 days, and this has caused you significant emotional distress, which may be leading to mental health issues such as emotional problems, depression, or anxiety. The pain is still severe today, making it difficult to concentrate on daily activities, and your mood and condition are quite low. It is important for you to continue with the ongoing cognitive behavioral therapy without interruption to prevent your condition from worsening further. The third week of cognitive behavioral therapy, which starts today, is a behavioral strategy therapy that uses breathing exercises and progressive relaxation techniques to manage pain, so please be sure to attend every session!").

[0162] Such feedback 600 may include summary information relating to at least some of the survey response data, user information, and information relating to a particular treatment program, as well as recommendation information relating to a particular treatment program that is scheduled to be implemented in the week following the particular treatment week corresponding to the particular treatment program.

[0163] In other words, the generative language model can receive a prompt 500 as input, which is a combination of response data, user information, and at least a portion of information about the specific treatment program, and generate feedback 600 for the user's cognitive behavioral therapy.

[0164] Furthermore, the control unit 140 can provide the generated feedback 600 to the user terminal 10. For example, the user can receive feedback 600, review summary information that summarizes the user's pain level, cognitive distortion level, physical health status, and mental health status, and receive information about a specific treatment program scheduled to be implemented the following week after a specific treatment program is currently underway.

[0165] In this regard, the control unit 140 can provide a user environment that allows users undergoing cognitive behavioral therapy to continue performing the therapy. For example, as shown in Figure 6, the control unit 140 can provide a GUI 610 (Graphical User Interface) that allows the user to access a specific treatment program, along with recommendation information regarding the specific treatment program scheduled to be performed in the week following a particular treatment week. The user can select the GUI (e.g., "Perform Now"), access a screen where they can perform the specific treatment program related to the recommendation information, and then perform cognitive behavioral therapy using the specific treatment program.

[0166] The control unit 140 can provide a page on which the specific treatment program can be implemented based on the selection of the GUI 610 from the user terminal 10. For example, as shown in Figures 7a to 7c, the control unit 140 can provide a page 700 containing the specific treatment program on the user terminal 10. The user can then perform cognitive behavioral therapy through the specific treatment program contained on page 700.

[0167] As described above, the feedback provision method and system for cognitive behavioral therapy based on the language model according to the present invention receives user responses in real time through online questionnaires and provides feedback based on these responses, thereby enabling users to receive continuous therapeutic support related to cognitive behavioral therapy even when regular face-to-face consultations are difficult.

[0168] Furthermore, the feedback method and system for cognitive behavioral therapy based on the language model according to the present invention can grasp the user's condition and needs from various perspectives through multiple-choice and open-ended questionnaires. This makes it possible to provide more accurate feedback to the user and to provide treatment plans that address the user's actual needs.

[0169] Furthermore, the feedback provision method and system for cognitive behavioral therapy based on the language model according to the present invention can generate customized feedback for the user by inputting prompts generated by combining user response data to questionnaires, the user's gender, age, sexual orientation, disease information, and information about a specific treatment program into a generative language model, and using the generative language model. Through the customized feedback, the user can gain a deeper understanding of their state information regarding their pain level and cognitive distortion level, and receive effective treatment guidance tailored to that understanding.

[0170] On the other hand, the present invention described above can be implemented as a program that is executed in accordance with one or more processes on a computer and can be stored on a medium (or recording medium) that is readable by such a computer.

[0171] Furthermore, the present invention described above can be implemented as computer-readable code or instruction words on a medium on which a program is recorded. In other words, the present invention can be provided in the form of a program.

[0172] On the other hand, computer-readable media include all types of recording devices that store data readable by a computer system. Examples of computer-readable media include HDDs (Hard Disk Drives), SSDs (Solid State Disks), SSDs (Silicon Disk Drives), ROMs, RAMs, CD-ROMs, magnetic tapes, floppy disks, and optical data storage devices.

[0173] Furthermore, the computer-readable medium may include storage and may be a server or cloud storage accessible by the electronic device via communication. In this case, the computer can download the program according to the present invention from the server or cloud storage via wired or wireless communication.

[0174] Furthermore, in this invention, the computer described above is an electronic device equipped with a processor, i.e., a CPU (Central Processing Unit), and its type is not particularly limited.

[0175] On the other hand, the above detailed description should not be interpreted restrictively in any respect and should be considered illustrative. The scope of the invention should be determined by a reasonable interpretation of the appended claims, and any modifications within the scope of the equivalents of the invention are included within the scope of the invention.

Claims

1. The steps include providing at least one questionnaire related to cognitive behavioral therapy on the user's terminal, The steps include receiving the response data of the questionnaire through the user terminal, The steps include generating a prompt to be input to a generative language model using the aforementioned response data, The steps include inputting the prompt into the generative language model to generate feedback related to the response data, A method for providing feedback for cognitive behavioral therapy based on a language model, comprising the step of providing the generated feedback to the user terminal.

2. The aforementioned questionnaire This includes multiple-choice questionnaires that fall under the category of multiple-choice questions. The aforementioned multiple-choice questionnaire is, The cognitive behavioral therapy-related questions and multiple selection items corresponding to each of the multiple different responses to the questions are arranged in pairs. In the step of generating the aforementioned prompt, A method for providing feedback for cognitive behavioral therapy based on a language model according to claim 1, characterized in that the prompt is generated using the aforementioned question and the response to a specific selection item selected by the user terminal from among the plurality of selection items.

3. Each of the aforementioned multiple distinct responses is associated with a distinct score related to cognitive behavioral therapy. The aforementioned prompt will include: A method for providing feedback for cognitive behavioral therapy based on a language model according to claim 2, characterized in that it includes keywords for the aforementioned questions and scores associated with the specific selection items.

4. The aforementioned questionnaire This includes further descriptive questionnaires that fall under the category of descriptive questions. The response data is, The aforementioned written questionnaire includes memo information received from the user terminal, In the step of generating the aforementioned prompt, A method for providing feedback for cognitive behavioral therapy based on a language model according to claim 3, characterized in that the prompt is generated using the memo information.

5. The process further includes the step of analyzing the meaning of the memo information, which is response data from the descriptive questionnaire, and the meaning of the specific selection items for the multiple-choice questionnaire. A method for providing feedback for cognitive behavioral therapy based on a language model according to claim 4, further comprising the step of performing different processes depending on the degree of similarity between the meaning of the memo information and the meaning of the specific selected item, as a result of the analysis.

6. In the step of carrying out the aforementioned different processes, A method for providing feedback for cognitive behavioral therapy based on a language model according to claim 5, characterized in that if the similarity is equal to or greater than a preset threshold, the prompt is generated using the memo information and the response to the specific selection item.

7. If the similarity is less than the predetermined threshold, the step further includes conducting a re-questionnaire. In the step of conducting the aforementioned follow-up questionnaire, A method for providing feedback for cognitive behavioral therapy based on a language model according to claim 6, characterized in that when conducting the aforementioned re-questionnaire, guide information regarding the reason for conducting the re-questionnaire is also provided on the user terminal.

8. The server stores multiple treatment programs, each associated with a different topic. The aforementioned user terminal includes: The multiple treatment programs are provided sequentially according to the treatment weeks set for each of the multiple treatment programs, so that the user performs the cognitive behavioral therapy according to each of the multiple treatment programs. The process further includes extracting user information relating to the user registered on the server, and information relating to a specific treatment program provided to the user terminal from among the multiple treatment programs, In the step of generating the aforementioned prompt, A method for providing feedback for cognitive behavioral therapy based on a language model according to claim 1, characterized in that the prompt is generated by combining at least a portion of the response data, the user information, and the information relating to a specific treatment program.

9. The user information includes at least one of the user's gender, age, sexual orientation, and disease. Information regarding the aforementioned specific treatment program is, A method for providing feedback for cognitive behavioral therapy based on a language model according to claim 8, characterized by including information regarding a specific treatment week corresponding to the specific treatment program, a specific topic associated with the specific treatment program, and the user's treatment history information up to the specific treatment week.

10. The aforementioned feedback is, A method for providing feedback for cognitive behavioral therapy based on a language model according to claim 9, characterized in that it includes summary information relating to at least a portion of the response data, user information, and information relating to a specific treatment program included in the prompt, and recommendation information relating to a specific treatment program scheduled to be implemented in the week following the specific treatment week corresponding to the specific treatment program.

11. Includes a control unit that provides at least one questionnaire related to cognitive behavioral therapy on the user terminal, The control unit, The user terminal receives the survey response data for the survey. Using the aforementioned response data, a prompt is generated to be input to the generative language model. The prompt is input to the generating language model to generate feedback related to the response data, A feedback system for cognitive behavioral therapy based on a language model, characterized by providing the generated feedback to the user terminal.

12. A program that is executed in accordance with one or more processes in an electronic device and stored on a computer-readable recording medium, The aforementioned program, The steps include providing at least one questionnaire related to cognitive behavioral therapy on the user's terminal, The steps include receiving the response data of the questionnaire through the user terminal, The steps include generating a prompt to be input to a generative language model using the aforementioned response data, The steps include inputting the prompt into the generative language model to generate feedback related to the response data, A program stored on a computer-readable recording medium, characterized by including a command word to perform the steps of providing the generated feedback to the user terminal.

Images