WO2025071377A1 - Method and system for providing feedback for cognitive behavioral therapy based on language model - Google Patents

Abstract

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

Description

Method and system for providing feedback for cognitive behavioral therapy based on language model

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

Cognitive Behavioral Therapy (CBT) is a psychological treatment method that assumes that a person's thoughts, emotions, and behaviors are closely connected, and helps patients recognize their own emotions, identify incorrect thoughts, and change problematic behaviors during the treatment process.

In recent years, as the effectiveness of cognitive behavioral therapy has been scientifically proven, cases of using cognitive behavioral therapy for mental health problems such as depression, anxiety, insomnia, and pain are gradually increasing.

Meanwhile, as technology advances, electronic devices (e.g., smartphones, tablet PCs, etc.) have become more widespread, and our dependence on the Internet in many areas of our daily lives is gradually increasing.

In this way, thanks to the development of various technologies including the Internet, consumption patterns that were previously highly dependent on offline have gradually shifted to online, and currently, online-centered consumption is increasing exponentially.

In line with these changing trends, industries such as the medical industry, which is based on offline services due to its nature, are also increasingly attempting to provide medical services online.

For example, Korean Patent No. 10-2195512 discloses technology related to a server and system that provides an online medical platform, and provides patients with information about medical service providers online.

Furthermore, with the rapid development of artificial intelligence (AI) technology in recent years, large language models (LLMs) capable of natural conversations with people have emerged.

Large-scale language models are showing innovation in the artificial intelligence market by demonstrating the technological ability to communicate naturally and provide fast and accurate information, unlike existing manually built chatbots that only provide limited answers.

Accordingly, there is still a need for ways to provide more diverse medical services by utilizing large-scale language models, even for medical services provided online.

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

More specifically, the present invention provides a method and system for providing feedback for cognitive behavioral therapy, which can generate a prompt for a generative language model using response data for a questionnaire related to cognitive behavioral therapy, and input the generated prompt into the generative language model to generate feedback related to the questionnaire response data.

Furthermore, the present invention provides a method and system for providing feedback for cognitive behavioral therapy that can provide feedback related to response data to a user.

Furthermore, the present invention provides a method and system for providing feedback for language model-based cognitive behavioral therapy that can provide cognitive behavioral therapy for pain patients based on a digital device.

In order to solve the problem discussed above, a method for providing feedback for language model-based cognitive behavioral therapy 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 for the questionnaire through the user terminal, generating a prompt to be input into a generative language model using the response data, generating feedback related to the response data by inputting the prompt into the generative language model, and providing the generated feedback to the user terminal.

Furthermore, the questionnaire includes an objective questionnaire of an objective type, and the objective questionnaire is configured by pairing a question related to the cognitive behavioral therapy and a plurality of choice items each corresponding to a plurality of different responses to the question, and in the step of generating the prompt, the prompt can be generated by using a response to a specific choice item selected from the user terminal among the question and the plurality of choice items.

Furthermore, the plurality of different responses may each be matched with different scores related to the cognitive behavioral therapy, and the prompt may include keywords for the question and scores matched to the specific selection items.

Furthermore, the questionnaire further includes a subjective questionnaire corresponding to a subjective type, and the response data includes memo information received from the user terminal for the subjective type questionnaire, and in the step of generating the prompt, the prompt can be generated using the memo information.

Furthermore, the method further includes a step of analyzing the meaning of the memo information, which is response data for the subjective questionnaire, and the meaning of the specific selection item for the objective questionnaire, and, as a result of the analysis, different processes can be performed depending on the degree of similarity between the meaning of the memo information and the meaning of the specific selection item.

Furthermore, in the step of performing the above different processes, if the similarity is greater than a preset standard value, the prompt can be generated using the memo information and the response to the specific selection item.

Furthermore, if the similarity is less than the preset standard value, the method further includes a step of conducting a re-survey, and in the step of conducting the re-survey, when conducting the re-survey, guide information regarding the reason for conducting the re-survey can be provided on the user terminal.

Furthermore, the server stores and matches multiple treatment programs, each of which matches a different subject, and the user terminal sequentially provides the multiple treatment programs according to a treatment week 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, and the method further includes a step of extracting user information about the user registered in the server and information about a specific treatment program provided to the user terminal among the multiple treatment programs, and in the step of generating the prompt, the prompt can be generated by combining at least some of the response data, the user information, and the information about the specific treatment program.

Furthermore, the user information may include at least one of the user's gender, age, tendency, and disease, and the information on the specific treatment program may include information on a specific treatment week corresponding to the specific treatment program, a specific subject matched to the specific treatment program, and the user's treatment history information up to the specific treatment week.

Furthermore, the feedback may include summary information about at least some of the response data included in the prompt, the user information, and information about the specific treatment program, and recommendation information about a specific treatment program scheduled to be performed in the next week of the specific treatment week corresponding to the specific treatment program.

Meanwhile, a 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, wherein 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 provides the generated feedback to the user terminal.

Meanwhile, a program according to the present invention is a program that is executed by one or more processes in an electronic device and can be stored in a computer-readable recording medium, wherein the program may include commands that perform the steps of providing at least one questionnaire related to cognitive behavioral therapy on a user terminal, receiving response data to the questionnaire through the user terminal, generating a prompt to be input into a generative language model using the response data, generating feedback related to the response data by inputting the prompt into the generative language model, and providing the generated feedback to the user terminal.

As described above, the method and system for providing feedback for cognitive behavioral therapy based on a language model according to the present invention receives user responses in real time through a questionnaire provided online and provides feedback based on the responses, thereby enabling users to receive continuous treatment support related to cognitive behavioral therapy even when regular face-to-face counseling is difficult.

In addition, the method and system for providing feedback for cognitive behavioral therapy based on a language model according to the present invention can grasp the user's condition and needs from various perspectives through objective and subjective questionnaires. Through this, more precise feedback can be provided to the user and a treatment plan that meets the user's actual needs can be provided.

Furthermore, the method and system for providing feedback for cognitive behavioral therapy based on a language model according to the present invention inputs a prompt generated by combining the user's response data for a questionnaire, the user's gender, age, tendencies, disease information, and information on a specific treatment program into a generative language model, and generates user-customized feedback using the generative language model. Through the customized feedback, the user can more deeply understand the status information related to the degree of his or her pain and cognitive distortion, and receive an effective treatment direction accordingly.

Figure 1 is a conceptual diagram illustrating a feedback providing system for cognitive behavioral therapy based on a language model according to the present invention.

Figure 2 is a flowchart illustrating a method for providing feedback for cognitive behavioral therapy based on a language model according to the present invention.

FIGS. 3a, 3b, 4a, 4b, 4c, 4e, 4f, 4g, 5 and 6 are conceptual diagrams illustrating a method for providing feedback for language model-based cognitive behavioral therapy 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.

Hereinafter, embodiments disclosed in this specification will be described in detail with reference to the attached drawings. Regardless of the drawing symbols, 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 assigned or used interchangeably only for the convenience of writing the specification, and do not have distinct meanings or roles in themselves. In addition, when describing embodiments disclosed in this specification, if it is determined that a specific description of a related known technology may obscure the gist of the embodiments disclosed in this specification, the detailed description thereof will be omitted. In addition, the attached drawings are only intended to facilitate easy understanding of the embodiments disclosed in this specification, and the technical ideas disclosed in this specification are not limited by the attached drawings, and should be understood to include all modifications, equivalents, and substitutes included in the spirit and technical scope of the present invention.

Terms including ordinal numbers, such as first, second, etc., may be used to describe various components, but the components are not limited by the terms. The terms are used only to distinguish one component from another.

When it is said that a component is "connected" or "connected" to another component, it should be understood that it may be directly connected or connected to that other component, but that there may be other components in between. On the other hand, when it is said that a component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between.

Singular expressions include plural expressions unless the context clearly indicates otherwise.

In this application, it should be understood that terms such as “comprises” or “have” are intended to specify the presence of a feature, number, step, operation, component, part or combination thereof described in the specification, but do not exclude in advance the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts or combinations thereof.

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 providing the generated feedback to the user, and particularly, to providing feedback for cognitive behavioral therapy of pain patients, focusing on patients with pain due to musculoskeletal disorders.

More specifically, the present invention relates to a method and system for providing feedback for cognitive behavioral therapy, which can generate a prompt for a generative language model using response data for a questionnaire related to cognitive behavioral therapy, and input the generated prompt into the generative language model to generate feedback related to the questionnaire response data.

The questionnaire described in the present invention may include questions related to cognitive behavioral therapy to check at least one of the user's pain level, cognitive distortion level, pain duration, pain severity, mood when experiencing pain, degree of negative emotion due to pain, degree of stress due to pain, physical health status, and mental health status.

In leisure, “pain level” can be understood as a scale representing the intensity or severity of pain experienced by an individual. Pain is a subjective and personal experience, and each person may feel and interpret pain differently, and pain can involve physical discomfort, emotional discomfort, and suffering. Various methods can be used to assess this pain level. For example, a numerical rating scale (NRS) can be provided to the patient to rate the intensity of the pain felt by the patient (e.g., no pain, slight pain, severe pain, etc.).

In addition, “cognitive distortion” refers to a cognitive error that leads to incorrect assumptions or wrong concepts about pain, surrounding situations, and events, and “the degree of cognitive distortion” can be understood as a term expressing how much the patient is cognitively distorted. In the present invention, the degree of cognitive distortion can be quantified as a “cognitive distortion score” or “cognitive distortion score.”

Furthermore, the “pain patient” described in the present invention may mean a patient who feels pain due to a disease, and in the present invention, the pain patient may be used interchangeably with “patient” or “user.”

In the present invention, for the convenience of explanation, the description focuses on “musculoskeletal diseases,” but is not necessarily limited thereto. That is, the pain patients described in the present invention may include patients with various diseases (e.g., cancer, diabetes, hypertension, etc.) in addition to patients with musculoskeletal diseases.

Meanwhile, the feedback provision system for cognitive behavioral therapy based on a language model according to the present invention (hereinafter referred to as the “feedback provision system”) can be implemented in various platform forms such as an application, software, and a website.

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

In this way, the feedback provision system implemented in software can be downloaded through a program (e.g., Play Store, App Store, etc.) that can download an application onto a user terminal (or patient terminal), or implemented through an initial installation program on the user terminal. In this case, at least one of the components of the feedback provision system can be utilized as a component of the user terminal.

In the present invention, the “terminal” may also be called a “mobile terminal” or an “electronic device,” and the terminal described in the present invention may include at least one of a mobile phone, a smart phone, a notebook computer, a laptop computer, a slate PC, a tablet PC, an ultrabook, a desktop computer, a digital broadcasting terminal, a personal digital assistant (PDA), a portable multimedia player (PMP), a navigation device, and a wearable device (e.g., a smartwatch, a smart glass, an HMD (head mounted display)).

Meanwhile, the feedback provision system may exist within a server (hereinafter referred to as a server) constructed to perform a specific purpose (e.g., a function related to providing feedback for cognitive behavioral therapy) separately from a user terminal, and may exist as a separate system from the server. When the feedback provision system exists within the server, various services related to the present invention (e.g., a feedback provision service for cognitive behavioral therapy or a cognitive behavioral therapy provision service, etc.) can be provided through at least one component located within the server, or component modules that perform functions similar to the components. In this case, the application can provide various services related to the present invention on a user terminal on which the application is installed through communication with the server.

In addition, the feedback provision system can provide a feedback provision method for cognitive behavioral therapy and a cognitive behavioral therapy provision method according to the present invention to a user terminal by linking with a central server or an external server.

Furthermore, the feedback provision system can use a user terminal to diagnose the degree of pain and cognitive distortion of a patient's pain, and, taking this into consideration, provide an appropriate summary and feedback for cognitive behavioral therapy, or provide various services related to cognitive behavioral therapy (e.g., providing a treatment program for cognitive behavioral therapy).

Meanwhile, the patient can diagnose the degree of pain and cognitive distortion of his/her own pain through the application or webpage provided by the feedback provision system according to the present invention, and receive appropriate feedback according to the degree of pain and cognitive distortion of the patient. In addition, the patient can receive various services related to cognitive behavioral therapy (e.g., provision of cognitive behavioral therapy program) to manage at least one of mental health and physical health conditions.

At this time, the patient may have a user account registered in the feedback provision system. In this specification, for convenience of explanation, the account of the patient user is called “patient account” or “user account.”

The “account” described above can be created through a page linked to the feedback provision system discussed above. Alternatively, the “account” can also be created in at least one other system linked to the feedback provision system.

Accordingly, in this specification, the system in which the account is issued is not separately distinguished, and all accounts based on the feedback provision system according to the present invention are referred to as “accounts already registered in the feedback provision system according to the present invention.”

For convenience of explanation, in this specification, a feedback provision system according to the present invention is described according to an embodiment implemented as an application on a user terminal.

Meanwhile, in the case of pain patients, even if they have the same disease (or illness), the degree of pain and cognitive distortion that occurs every day may vary for each patient.

Accordingly, in the present invention, appropriate feedback can be generated based on the user's pain level, sense of competence, mood, short records, etc., and the generated feedback can be provided to the user.

Hereinafter, the configuration of a feedback providing system for language model-based cognitive behavioral therapy according to the present invention will be described in more detail with reference to the attached drawings. Figure 1 is a conceptual diagram for explaining a feedback providing system for language model-based cognitive behavioral therapy according to the present invention.

As illustrated in FIG. 1, the feedback provision system (100) according to the present invention may include at least one of an input unit (110), a communication unit (120), a storage unit (130), and a control unit (140).

The input unit (110) can receive user (or patient) input through an input unit configuration (e.g., a touch screen, a virtual key, a physical key (or hardware button), an input sensor, a microphone, etc.) provided in the user terminal (or patient terminal, 10).

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

The communication unit (120) can be connected to a server and devices, etc. via a wireless or wired network, and can be configured to receive or transmit overall data and information required for the feedback provision system (100).

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

For example, the communication unit (120) may receive (or collect) response data for at least one questionnaire related to cognitive behavioral therapy from at least one source through the user terminal (10). As another example, the communication unit (120) may receive a request for providing a specific treatment program for cognitive behavioral therapy from the user terminal (10).

Furthermore, the communication unit (120) can support various communication methods depending on the communication standards of the communicating device.

For example, the communication unit (120) may be configured to communicate with a communication target using at least one of the following technologies: 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), Bluetooth™ (Bluetooth™), RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra-Wideband), ZigBee, NFC (Near Field Communication), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus).

Meanwhile, the storage unit (130) may also be called a database (DB) or a 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. In addition, at least a part of the storage unit (130) may be configured as a cloud server (or cloud storage). That is, the storage unit (130) may 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 may be understood that there are no restrictions on the physical space. Hereinafter, the storage unit (130), the cloud server (or cloud storage), and the storage (not shown) of the server linked with the system (100) will not be separately distinguished, and will all be referred to as the storage unit (130).

The storage unit (130) may store and exist user information registered in the feedback provision system (or server, 100). For example, the user information may include information related to at least one of the user's gender, age, tendencies (or personality), and disease (or illness). However, in addition to the information listed above, the user information may further include various information such as the user's disease occurrence date, treatment (or clinical) history, occupation, interests, and hobbies.

In addition, the storage unit (130) may store information on a specific treatment program provided to the user. For example, the information on a specific treatment program may include at least one of information on a specific treatment week corresponding to a specific treatment program, a specific subject matched to a specific treatment program, and information on the user's treatment history up to a specific treatment week.

Meanwhile, the control unit (140) may also be referred to as a processor, and may perform a role of controlling the overall operation of the feedback provision system (100) related to the present invention in cooperation with the memory. The control unit (140) may process signals, data, information, etc. input or output through the components discussed above, or perform a series of data processing to provide or process appropriate information and functions to the user.

According to one embodiment of the present invention, the control unit (140) can generate a prompt of a generative language model using response data for a questionnaire related to cognitive behavioral therapy, and input the generated prompt into the generative language model to generate feedback related to the questionnaire response data. In addition, the control unit (140) can provide the feedback generated using the generative language model to the user terminal (10).

Hereinafter, based on the configuration of the feedback provision system (100) discussed above, a feedback provision method for language model-based cognitive behavioral therapy according to the present invention will be described in more detail. FIG. 2 is a flowchart for explaining a feedback provision method for language model-based cognitive behavioral therapy according to the present invention. FIGS. 3a, 3b, 4a, 4b, 4c, 4e, 4f, 4g, 5 and 6 are conceptual diagrams for explaining a feedback provision method for language model-based cognitive behavioral therapy according to the present invention. FIGS. 7a, 7b and 7c are conceptual diagrams for explaining a method for providing a cognitive behavioral therapy program through feedback.

Meanwhile, in the present invention, a process of providing at least one questionnaire related to cognitive behavioral therapy on a user terminal may be performed (S210, see FIG. 2).

For example, as illustrated in FIG. 3a, the control unit (140) may provide a survey page (or service page) including a plurality of surveys on the user terminal (10). In this case, the page including a plurality of surveys may be output through the touch screen (or display) of the user terminal (10).

Here, the questionnaire (or question, or problem, or item, or test) provided on the above page may include a questionnaire for the relative evaluation of factors related to pain.

The pain-related factors in the present invention may be diverse. For example, the pain-related factors may include various factors for evaluating the patient's condition related to pain, such as the degree of pain, duration of pain, mental health, and physical health. However, the factors described above are only examples, and the pain-related factors described in the present invention may include all factors for evaluating the patient's condition.

These pain-related factors may include a credible questionnaire that is actually used in psychiatry to diagnose the patient's condition. In addition, the control unit (140) may periodically update the questionnaire by additionally collecting the questionnaire for diagnosing the patient's condition through a central server, an external server, a website, etc.

Meanwhile, in the present invention, the questionnaire related to cognitive behavioral therapy may include an objective questionnaire corresponding to an objective type and a subjective questionnaire corresponding to a subjective type.

The objective questionnaire may be configured by pairing a question related to cognitive behavioral therapy and multiple choice items corresponding to each of multiple different responses to the question. For example, as illustrated in (a) of FIGS. 3a and 3b, the first questionnaire (310) corresponding to the objective type may be configured by pairing a question related to cognitive behavioral therapy (ex: “How is your pain today?”, 311) and multiple choice items (311a, 311b, 311c, 311d, 311e) corresponding to each of multiple different responses to the question (ex: “No pain”, “Almost slight pain”, “Normal”, “Slightly severe pain”, “Terrible pain”).

In addition, for multiple different responses, different scores related to cognitive behavioral therapy may be matched and exist, respectively. For example, among multiple different responses (ex: “no pain”, “almost slight pain”, “normal”, “slightly severe pain”, “terrible pain”) configured in the first questionnaire (310), the first response (ex: “no pain”) may be matched with the first score (ex: “0 points”) related to cognitive behavioral therapy, and the fifth response (ex: “almost slight pain”) may be matched with the fifth score (ex: “4 points”) related to cognitive behavioral therapy.

Accordingly, the user may, in response to any one of the displayed questionnaires, select a specific item from among multiple choice items corresponding to each of the multiple different responses that the user deems most appropriate (or appropriate, or accurate) for the user's condition.

In addition, the subjective questionnaire may include a question related to cognitive behavioral therapy and a response area (or input area) configured to allow text input for a response to the question. For example, as illustrated in FIG. 3A, the fourth questionnaire (340), which is a subjective questionnaire, may include a question related to cognitive behavioral therapy (ex: “One-line memo” or “Write today’s record as a one-line memo!”) and a response area (341) configured to allow text input for a response to the question. In this case, the fourth questionnaire may be a questionnaire for detecting the user’s status information based on text by receiving information related to various user states (e.g., pain level, sense of competence, mood, etc.) as text.

In the present invention, for convenience of explanation, response data for a subjective type questionnaire is named “memo information” and explained.

At this time, in the present invention, when memo information, which is response data for a subjective questionnaire, is received from a user terminal (10), the meaning of the memo information can be analyzed based on preset criteria.

Here, “analyzing the meaning of memo information” can be understood as analyzing the meaning of the text content included in the memo information to determine whether the text content corresponds to a positive meaning or a negative meaning.

To this end, a standard for analyzing the meaning of the memo information may be preset and exist in the feedback provision system (100) according to the present invention. For example, as illustrated in (b) of FIG. 3B, if the memo information corresponds to a positive meaning, text related to a positive state expression (ex: “Today is the best!, I feel really good, I feel good so my condition is also the best!, I’m having a pretty good day, neither good nor sad…”) may be included. As another example, if the memo information corresponds to a negative meaning, text related to a negative relative expression (ex: “Today is the worst!, I feel really bad, I’m so sick so my condition is the worst, I don’t want to do anything, I’m both in the worst condition and the worst, I’m not in the best mood, I’m so frustrated…”) may be included.

However, the present invention does not limit the method by which a user proceeds (or performs) with responses to multiple questionnaires to any one. For example, the first questionnaire (310), the second questionnaire (320), and the third questionnaire (330), which are objective questionnaires, can all be responded to through text input, just like the fourth questionnaire (340), which is a subjective questionnaire. Furthermore, in the present invention, responses to questionnaires can be input not only by selecting specific items or entering text, but also by voice, image, video, etc.

Next, in the present invention, a process of receiving response data to a questionnaire through a user terminal can be performed (S220, see FIG. 2).

As examined above, the questionnaire related to cognitive behavioral therapy in the present invention may include an objective questionnaire corresponding to an objective type and a subjective questionnaire corresponding to a subjective type.

Response data for a questionnaire of the objective type may be a selection signal for one of multiple selection items, and the control unit (140) may determine a specific selection item corresponding to the received selection signal as the response data.

The control unit (140) can receive response data for an objective questionnaire through the user terminal (10). For example, as illustrated in FIG. 3a, the control unit (140) can receive a selection signal corresponding to a specific selection item (311e) based on the selection of one of the multiple selection items (311a, 311b, 311c, 311d, 311e) configured in the first questionnaire (310) from the user terminal (10). Then, the control unit (140) can receive the specific selection item (311e) corresponding to the received selection signal as response data for the first questionnaire.

In addition, the control unit (140) can receive response data for a subjective questionnaire through the user terminal (10). For example, the control unit (140) can receive an input signal corresponding to the memo information (342) based on the memo information (ex: Today, everything is the worst because of the leg pain that is so painful…, 342) being input into the response area (341) configured in the fourth questionnaire (340) from the user terminal (10). Then, the control unit (140) can receive the memo information (342) corresponding to the received input signal as response data for the fourth questionnaire.

Meanwhile, in a server linked to the feedback provision system (100) according to the present invention, multiple treatment programs each matching different topics can be matched and stored.

Accordingly, a plurality of treatment programs can be sequentially provided to the user terminal (10) according to the treatment week set for each of the plurality of treatment programs, so that the user can perform cognitive behavioral therapy according to each of the plurality of treatment programs. In the following, for the convenience of explanation, the server linked to the feedback provision system (100) will not be described as the main body, but the control unit (140) will be described as the main body.

The “treatment week” described in the present invention can be understood as a sequence (or period) in which a treatment program is provided (or activated) through a user terminal (10) so that the user can perform cognitive behavioral therapy according to the treatment program. In the present invention, the “total number of times” of the treatment week and the “weekly treatment period” corresponding to each treatment week may be preset and exist. And, in the present invention, it can be understood that the “total treatment period” is predefined. The total treatment period can be determined as the product of the preset total number of times and the preset weekly treatment period. For example, if the total number of times is “8” and the weekly treatment period is 1 week (7 days), the preset total treatment period can be “8 weeks.”

In the following, for the convenience of explanation, it will be explained by exemplifying that different treatment weeks come “8 times” during each one-week treatment period. That is, in the present invention, the first treatment week may come during the first treatment session, and the second treatment week may come during the second treatment session. Accordingly, in the present invention, “treatment week” may be used interchangeably with “treatment session,” “treatment number,” “treatment period,” and “treatment order.”

As discussed above, in the present invention, the total number of treatment weeks (ex: “8”) may be predefined and exist. For example, as illustrated in FIG. 4a, in the present invention, the total number of treatment weeks (ex: “8 sessions”) may be predefined and exist. Here, let us assume that there are multiple treatment programs, “the first treatment program to the eighth treatment program.” In this case, for each of the first treatment program to the eighth treatment program, one of the first treatment week to the eighth treatment week may be set and exist.

In each of the plurality of treatment programs (e.g., the first treatment program to the eighth treatment program), a plurality of topics may exist corresponding to (or matching with) each other. For example, the first treatment program may be for training or treatment related to the first topic (e.g., motivation enhancement), ii) the second treatment program may be for training or treatment related to the second topic (e.g., emotion identification), iii) the third treatment program may be for training or treatment related to the third topic (e.g., behavioral strategy), iv) the fourth treatment program may be for training or treatment related to the fourth topic (e.g., attention shifting), v) the fifth treatment program may be for training or treatment related to the fifth topic (e.g., thought shifting), vi) the sixth treatment program may be for training or treatment related to the sixth topic (e.g., thought recording), vii) the seventh treatment program may be for training or treatment related to the seventh topic (e.g., management strategy), and viii) the eighth treatment program may be for training or treatment related to the eighth topic (e.g., future me).

Additionally, each of the plurality of treatment programs may be configured to include at least one treatment module related to a specific topic matched to the specific treatment program. For example, a first treatment program may be configured to include a plurality of treatment modules related to a first topic (e.g., motivation enhancement).

Here, the “treatment module” may mean contents related to a detailed category (or sub-topic) for cognitive behavioral treatment of a pain patient for a specific topic. In the present invention, a treatment module included in a treatment program related to a specific topic may be named a “specific topic-corresponding treatment module,” and the “treatment module” may be used interchangeably with “chapter.”

In the present invention, specific treatment modules constituting a plurality of specific treatment programs can be sequentially provided to a user terminal (10) according to the treatment week set for each of the plurality of specific treatment programs. For example, the control unit (140) can sequentially provide a plurality of treatment modules constituting a first treatment program to the user terminal (10) in the first treatment week.

Here, the “treatment module sequence” can be understood as the order in which multiple treatment modules included in a specific treatment program are provided.

And, the “activation mode of the treatment module” can be understood as a mode in which viewing (or use) of the treatment module is possible. On the other hand, the “deactivation mode of the treatment module” can be understood as a mode in which viewing (or use) of the treatment module is impossible.

Furthermore, in the present invention, based on the completion of cognitive behavioral therapy according to a treatment module corresponding to a specific order in accordance with the order of the treatment modules, the mode of the treatment module corresponding to the next turn in the specific order can be changed (or switched) from a deactivated mode to an activated mode.

For example, let's assume that the first treatment program consists of the first treatment module to the fifth treatment module. The control unit (140) can switch the mode of the second treatment module from the deactivated mode to the activated mode based on the completion of the cognitive behavioral treatment of the first treatment module.

That is, each of the plurality of treatment programs may be configured to include at least one treatment module related to a topic matching each treatment program, and the treatment program may mean a program for performing treatment according to a topic matching a specific treatment program.

Meanwhile, each of the plurality of treatment programs may include a worksheet module for checking at least one of the pain level, pain duration, mental health status, and physical health status of the pain patient.

In this case, each worksheet module may be input with user response information for checking at least one of the pain level, pain duration, mental health status, and physical health status of a pain patient in relation to a specific topic of a treatment program including the worksheet module. Furthermore, each worksheet module may be input with various user response information for checking at least one of the pain level, pain duration, mental health status, and physical health status of a pain patient in addition to content related to a specific topic of the treatment program.

For example, a worksheet module included in a first treatment program may have user response information input to check at least one of the pain level, pain duration, mental health status, and physical health status of a pain patient in relation to a first topic (e.g., motivation enhancement).

As another example, a worksheet module included in a second treatment program may have user response information input to check at least one of the pain level, pain duration, mental health status, and physical health status of a pain patient in relation to a second topic (e.g., emotion identification).

These worksheet modules can be provided at various points in each treatment program. For example, the worksheet module can be located at the very end or in the middle of each treatment module. In other words, the location where the worksheet module is included in each treatment program can be varied depending on the condition of the pain patient.

Meanwhile, the worksheet module may be provided as the last module in each treatment program. The worksheet module may be arranged as the last module among the treatment modules constituting each treatment program, so that the pain patient may proceed with the worksheet module after proceeding with all of the treatment modules of the treatment program. This may include the purpose of receiving feedback from the pain patient, objectification, or the treatment effect of the pain patient for the treatment program.

In addition, the worksheet modules included in each treatment program can be configured to allow pain patients to score (select score, input score, etc.) on the severity of pain, mood when experiencing pain, degree of negative emotion about pain, degree of stress about pain, etc. The control unit (140) can use the scores received from the worksheet modules to determine whether the treatment program including the corresponding worksheet module was helpful or effective for the pain patient.

In this regard, as illustrated in FIG. 4b, the control unit (140) can control to output a page (or service page, 400) for providing a cognitive behavioral therapy service through a display unit (or touch screen) equipped in the user terminal (10). This page (400) can be output on the user terminal (10) through an application or web page installed in the user terminal (10).

The above page (400) is a page linked to a feedback providing system (or a server 100 linked to a feedback providing system) according to the present invention, and is configured to be controlled by the feedback providing system (100) according to the present invention.

In addition, when the above page (400) is provided in the form of an application, the page (400) can 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 a service related to cognitive behavioral therapy to a pain patient based on the information provided by the feedback provision system (100) according to the present invention.

The control unit (140) can sequentially provide multiple treatment programs to a user terminal (10) to which a user account (U) is logged in, according to the treatment week set for each of the multiple treatment programs.

Specifically, the control unit (140) can activate the state of a specific treatment program so that a specific treatment program set for a specific treatment week can be provided on the user terminal (10) during the treatment period corresponding to a specific treatment week. In the following, in order to avoid confusion in terminology, the state of a specific treatment program will be described by naming it as a “mode” of the specific treatment program.

In the present invention, the “treatment program activation mode” may be understood as a mode in which at least some of the plurality of treatment modules included in the treatment program can be viewed (or used). On the other hand, the “treatment program deactivation mode” may be understood as a mode in which all of the plurality of treatment modules included in the treatment program cannot be viewed (or used).

For example, let's assume that the cognitive behavioral therapy week of a user account (U) is "the first treatment week (ex: week 1)". As shown in FIGS. 4c and 4d, the control unit (140) can activate the state of the first treatment program (410) so that the first treatment program (e.g., a program related to motivation reinforcement, 410) set for the first treatment week can be provided on the user terminal (10) during the treatment period corresponding to the first treatment week.

And, the control unit (140) can provide a worksheet module included in a specific treatment program on the user terminal (10) and receive the user's response information for the worksheet module. For example, the control unit (140) can provide a first worksheet module (ex: "What part of knee pain is the most difficult to deal with?", 411) and a second worksheet module (ex: "Future me who will be able to deal with pain well", 412) included in the first treatment program (410) on the user terminal (10), and receive the user's first response information for the first worksheet module (411) (ex: "physical part") and the user's second response information for the second worksheet module (412) (ex: "Me who can travel with a healthier body"). At this time, the control unit (140) can receive the received first response information and second response information as worksheet response data for the first worksheet module and the second worksheet module.

Furthermore, when the next treatment week arrives, the control unit (140) can activate the mode of a specific treatment program corresponding to the next treatment week. For example, when the first treatment week has passed and the next treatment week, the second treatment week (ex: the second week), arrives, the control unit (140) can activate the mode of the second treatment program for which the second treatment week is set.

Accordingly, patients can systematically receive cognitive behavioral therapy by sequentially utilizing multiple treatment programs according to preset treatment periods.

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

As discussed above, each worksheet module may input user response information to check at least one of the user's pain level, pain duration, pain severity, mood when experiencing pain, degree of negative emotion due to pain, degree of stress due to pain, mental health status, physical health status, and the user's treatment effect on the treatment program.

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 can be configured to include a worksheet corresponding to either an objective or subjective type, and the worksheet corresponding to the objective type can be configured to include a plurality of selection items with different scores matched to each other. For example, the control unit (140) can calculate the user's pain score and cognitive distortion score by using (or calculating) the worksheet response data corresponding to the objective type.

And, the control unit (140) can match the user's pain score and cognitive distortion score with the user account (U) of the user and store them in the storage unit (130). For example, as illustrated in FIG. 4d, the control unit (140) can match the user's pain score (ex: "24 points") and cognitive distortion score (ex: "26 points") calculated based on the user's cognitive behavioral therapy results and the user's cognitive behavioral therapy week (ex: "2nd week") with the user account (U) and store them in the storage unit (130).

In this case, the pain score and cognitive distortion score may be scores calculated based on the user's pain level, pain duration, pain severity, mood during pain experience, degree of negative emotion about pain, degree of stress about pain, mental health status, physical health status, feedback, and the user's treatment effect for the treatment program, etc., collected through the user terminal (10) during the user's cognitive behavioral therapy process. In other words, the scores may be scores calculated based on the results of cognitive behavioral therapy up to a specific treatment week that the user is in progress with.

In this regard, the control unit (140) may provide summary information on the results of cognitive behavioral therapy up to a specific treatment week that the user is currently undergoing on the user terminal (10). For example, as illustrated in FIG. 4e, the control unit (140) may output a page (420) including summary information (421, 422) on the results of the user's cognitive behavioral therapy on the user terminal (10).

At this time, the information included in the summary information (421, 422) may include at least one of a pain temperature score, a competence score, and a mood score calculated based on the user's response information to a worksheet module including at least one of the user's pain level, pain duration, pain severity, mood when experiencing pain, degree of negative emotion regarding pain, degree of stress regarding pain, mental health status, physical health status, feedback, and the user's treatment effect regarding the treatment program.

That is, the summary information (421, 422) included in the above page (420) may be information calculated based on the user's response to at least one worksheet module included in a specific treatment program.

Furthermore, the summary information (421, 422) may be provided in various forms so that the user can more intuitively check the detection results for the user's status information by treatment week (or date). 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.

In this way, the present invention provides a user environment in which a user performing cognitive behavioral therapy can more intuitively check his or her own status information and continuously check and compare the results before and after cognitive behavioral therapy by providing a highly readable interface to the user.

Meanwhile, the control unit (140) can extract user information about a user registered in the server and information about a specific treatment program provided to a user terminal (10) among multiple treatment programs.

The above server (or feedback provision system (100)) may store and exist user information matching the user account (U). For example, the user information may include at least one of the user's gender, age, disease (or illness), disease occurrence date, treatment (or care) history, personality (or tendencies), occupation, interests, and hobbies.

Furthermore, information on a specific treatment program provided to the user terminal (10) may include at least one of information on a specific treatment week corresponding to a specific treatment program, information on a specific subject matched to a specific treatment program, and information on the user's treatment history up to a specific treatment week.

Here, the user's treatment history information may include, for example, the user's pain level, pain duration, mental health status and physical health status, mood when experiencing pain, degree of negative emotion about pain, degree of stress about pain, and the user's treatment effect for a specific treatment program.

That is, the control unit (140) can extract user information of the user and information about a specific treatment program provided to the user terminal (10) from the server. Some of this information can be utilized in the process of generating a prompt to be input into the generative language model. More specific details will be described later.

Meanwhile, the control unit (140) can compare the user's response to the subjective questionnaire and the response to the objective questionnaire to determine whether the user has given consistent responses during the cognitive behavioral therapy process. Based on the determination result, the control unit (140) can generate a prompt using the response to the questionnaire. On the other hand, if the control unit (140) determines that the user has given inconsistent responses, it can conduct a re-questionnaire and generate a prompt using the response obtained as a result of the re-questionnaire.

The control unit (140) can determine whether the user's response is consistent, secure the accuracy of the cognitive result perceived by the user, and provide more effective feedback based on the accurate response.

To this end, the control unit (140) can perform semantic analysis on memo information received from a user terminal for a subjective questionnaire and on specific selection items selected from the user terminal for an objective questionnaire, and calculate the degree of semantic similarity between the memo information and the specific selection items.

The control unit (140) can determine whether the degree of semantic similarity satisfies a preset criterion. For example, the control unit can calculate the degree of semantic similarity as a numerical value and determine whether the calculated numerical value is greater than or equal to a preset criterion value. In this case, the degree of semantic similarity may be such that the higher the calculated numerical value, the higher the degree of semantic similarity between the memo information and the specific selection item, and the lower the calculated numerical value, the lower the degree of semantic similarity between the memo information and the specific selection item.

Here, the preset criterion (or preset criterion value) may be preset or set by the medical staff. In addition, the control unit (140) may specify a customized cognitive preset criterion for each user based on the user's cognitive behavioral treatment history (e.g., responses to a questionnaire). For example, the control unit (140) may specify a preset criterion to correspond to the degree of similarity calculated in the past based on the cognitive behavioral treatment history. The degree of similarity of a user who has responded consistently in the past may be high, and the control unit may strictly judge the consistency of the response by setting the preset criterion high because the user is a user who has responded consistently. On the other hand, the degree of similarity of a user who has responded inconsistently in the past may be low, and the control unit (140) may flexibly judge the consistency of the response by setting the preset criterion low because the user is a user who has responded inconsistently.

Meanwhile, the control unit (140) can perform different processes related to prompt generation depending on whether the degree of semantic similarity satisfies a preset standard.

Among the different processes, the first process can generate a prompt using memo information and specific selection items based on whether the degree of similarity satisfies a preset criterion. The control unit (140) can generate a prompt using memo information and specific selection items based on whether the memo information for a subjective questionnaire and specific selection items for an objective questionnaire satisfy consistency according to a preset criterion, so that feedback to be provided to the user can be provided.

Furthermore, a second process among the different processes can generate a prompt using memo information different from the memo information based on the degree of similarity not satisfying a preset criterion.

More specifically, the control unit (140) may conduct a re-survey on at least one of the objective questionnaire and the subjective questionnaire according to the second process. In this case, the control unit (140) may provide the user terminal with guide information including at least one of the objective questionnaire and the subjective questionnaire according to the re-survey and the reason for conducting the re-survey.

The guide information can be provided in various ways. For example, when a subjective questionnaire is re-administered, the control unit (140) can provide, as guide information, information explaining the specific selection items selected by the user for the objective questionnaire and the reason why the specific selection items and the memo information previously entered by the user are inconsistent.

Meanwhile, the control unit (140) can determine which questionnaire among the subjective and objective questionnaires to re-conduct if the degree of similarity between the memo information and a specific selection item does not satisfy a preset standard.

The control unit (140) can determine which of the subjective and objective questionnaires to re-conduct by comparing the similarity level with a threshold value. In this case, the threshold value may be lower than a set reference value.

More specifically, if the degree of similarity is less than the preset reference value and greater than the threshold value, the control unit (140) can re-conduct either the subjective questionnaire or the objective questionnaire. The control unit (140) can re-conduct either the subjective questionnaire or objective questionnaire that was conducted late, or the subjective questionnaire. In general, since it is more difficult for a user to objectively express his or her thoughts in a subjective questionnaire than in an objective questionnaire, the user's cognition may be normal, but he or she may make a mistake in expressing the subjective questionnaire. Accordingly, the control unit (140) can re-conduct the subjective questionnaire.

Furthermore, if the similarity level is less than the threshold value, the control unit (140) can re-conduct both the objective and subjective questionnaires. If the similarity level is less than the threshold value, the control unit (140) can determine that the user has not properly recognized himself and provide guide information to guide the user's recognition along with the questionnaire.

Meanwhile, in the present invention, a process of generating a prompt to be input into a generative language model using received questionnaire response data can be performed (S230, see FIG. 2).

The control unit (140) can use the prompt generation unit (150) to generate a prompt to be input into the generative language model based on the received questionnaire response data and various pieces of information discussed above.

First, the prompt may include a role for deriving feedback related to cognitive behavioral therapy from a generative language model, which is defined in advance. For example, as illustrated in FIG. 5, the control unit (140) may create a prompt (500) by defining in advance information about a role for deriving feedback related to feature information and questionnaire response data from a generative language model (ex: “Based on the patient’s degree of pain and degree of cognitive distortion, act as a therapist who derives an appropriate summary and feedback for cognitive behavioral therapy.”, 510).

And, the control unit (140) can generate a prompt (500) using memo information, which is response data for a subjective questionnaire, and a response to a specific selection item, which is response data for an objective questionnaire. At this time, the memo information and the response to the specific selection item used for generating the prompt (500) can be understood as satisfying a similarity between the memo information and the response to the specific selection item that is greater than a preset standard value.

The control unit (140) can generate a prompt (500) using response data for an objective questionnaire. More specifically, the control unit (140) can generate a prompt (500) using a question configured in an objective questionnaire and a response to a specific selection item selected from among multiple selection items on a user terminal. For example, as illustrated in FIG. 3a and FIG. 5, let us assume that the fifth item (ex: “4 points”, “Terrible pain”, 311e) is selected in response to the first questionnaire (ex: “Pain”, “How is your pain today?”), the first item (ex: “0 points”, “Not at all confident”, 312a) is selected in response to the second questionnaire (ex: “Sense of competence”, “Are you confident that you can carry out your daily life well despite the pain?”), and the first item (ex: “0 points”, “Very bad”, 313a) is selected in response to the third questionnaire (ex: “Mood”, “How did you feel today?”). The prompt (500) may include a question composed of each of a plurality of objective questionnaires (310, 320, 330) and a response to a specific selection item selected from among a plurality of selection items on the user terminal (10) (ex: “In the questionnaire conducted today, the patient’s pain score was 4 points, the competence score was 0 points, the mood score was 0 points…”, 540).

In addition, the control unit (140) may generate a prompt (500) using memo information (ex: “Today, everything is the worst because of the too-painful knee pain”), which is response data for a subjective questionnaire. For example, the prompt (500) may include memo information (ex: “The one-line memo is written as “Today, everything is the worst because of the too-painful knee pain”), which is response data for a subjective questionnaire.

Furthermore, the control unit (140) may generate a prompt (500) by combining at least a portion of the user information and the information about the specific treatment program. For example, as illustrated in FIG. 5, the control unit (140) may generate a system prompt (151) including the user's age (ex: "30 years old"), gender (ex: "male"), disease (ex: "knee sprain"), cognitive behavioral therapy week (ex: "2 weeks"), pain level (ex: "severe pain"), pain duration (ex: "lasts about 10 days"), physical health status (ex: "severe physical discomfort"), mental health status (ex: "has suffered a lot of mental shock and his mental health status is also worsening"), tendency (ex: "this patient tends to become extremely absorbed in something once he gets into it, but also has a tendency not to easily challenge something because he lacks confidence"), etc.

That is, the control unit (140) can generate a prompt (500) to be input into the generative language model by combining at least some of the response data, user information, and information about the specific treatment program.

Meanwhile, in the present invention, a process of inputting a prompt into a generative language model to generate feedback related to response data (S240, see Fig. 2) and providing the generated feedback to a user terminal can be performed (S250, see Fig. 2).

The control unit (140) can input the prompt (500) generated in the process of S230 into a generative language model to generate feedback related to the questionnaire response data. For example, as shown in FIG. 6, the control unit (140) inputs a prompt (500) that combines at least some of the response data, the user information, and the information about the specific treatment program into the generative language model, and can obtain feedback (ex: “Despite the two weeks of cognitive behavioral therapy, today was the worst day. I guess it was a tough day. The pain from the knee sprain that has been going on for about 10 days is severe, and I am suffering from a lot of mental shock due to it, so I think I may have mental health problems such as emotional problems, depression, and anxiety. I am unable to concentrate on my daily life due to the severe pain today, and my mood and condition are quite low. I think it would be good for the patient to not miss the ongoing cognitive behavioral therapy and to proceed steadily so that the condition does not worsen further in the future. The third week of cognitive behavioral therapy starting today is a behavioral strategy treatment that uses breathing techniques and progressive relaxation techniques to cope with pain, so please do not miss it and be sure to attend!”, 600).

Such feedback (600) may include summary information about at least some of the response data to the questionnaire, user information, and information about a specific treatment program, as well as recommendation information about a specific treatment program scheduled to be performed in the following week of the specific treatment program corresponding to the specific treatment program.

That is, the generative language model can receive as input a prompt (500) that is a combination of at least some of response data, user information, and information about the specific treatment program, and generate feedback (600) for the user's cognitive behavioral treatment.

In addition, the control unit (140) can provide the generated feedback (600) on the user terminal (10). For example, the user can receive the feedback (600) to check summary information summarizing the user's pain level, cognitive distortion level, physical health status, mental health status, etc., and receive information about a specific treatment program scheduled to be conducted in the following week of a specific treatment program currently in progress.

In this regard, the control unit (140) may provide a user environment that allows a user undergoing cognitive behavioral therapy to continuously perform cognitive behavioral therapy. For example, as illustrated in FIG. 6, the control unit (140) may provide a GUI (Graphical User Interface, 610) that allows a user to access a specific treatment program, along with recommended information about a specific treatment program scheduled to be performed in the week following a specific treatment week. The user may select the GUI (ex: “Proceed now”) to access a screen that allows a user to proceed with a specific treatment program related to the recommended information, and may proceed with cognitive behavioral therapy through the specific treatment program.

The control unit (140) may provide a page for performing the specific treatment program based on the selection of the GUI (610) from the user terminal (10). For example, as shown in FIGS. 7A to 7C, the control unit (140) may provide a page (700) including the specific treatment program on the user terminal (10). The user may perform cognitive behavioral therapy through the specific treatment program included in the page (700).

As described above, the method and system for providing feedback for cognitive behavioral therapy based on a language model according to the present invention receives user responses in real time through a questionnaire provided online and provides feedback based on the responses, thereby enabling users to receive continuous treatment support related to cognitive behavioral therapy even when regular face-to-face counseling is difficult.

In addition, the method and system for providing feedback for cognitive behavioral therapy based on a language model according to the present invention can grasp the user's condition and needs from various perspectives through objective and subjective questionnaires. Through this, more precise feedback can be provided to the user and a treatment plan that meets the user's actual needs can be provided.

Furthermore, the method and system for providing feedback for cognitive behavioral therapy based on a language model according to the present invention inputs a prompt generated by combining the user's response data for a questionnaire, the user's gender, age, tendencies, disease information, and information on a specific treatment program into a generative language model, and generates user-customized feedback using the generative language model. Through the customized feedback, the user can more deeply understand the status information related to the degree of his or her pain and cognitive distortion, and receive an effective treatment direction accordingly.

Meanwhile, the present invention discussed above can be implemented as a program that is executed by one or more processes on a computer and can be stored on a medium (or recording medium) that can be read by the computer.

Furthermore, the present invention discussed above can be implemented as a computer-readable code or command on a medium in which a program is recorded. That is, the present invention can be provided in the form of a program.

Meanwhile, computer-readable media include all types of recording devices that store data that can be read by a computer system. Examples of computer-readable media include hard disk drives (HDDs), solid state disks (SSDs), silicon disk drives (SDDs), ROMs, RAMs, CD-ROMs, magnetic tapes, floppy disks, and optical data storage devices.

Furthermore, the computer-readable medium may be a server or cloud storage that includes storage and that the electronic device can access through communication. In this case, the computer can download the program according to the present invention from the server or cloud storage through wired or wireless communication.

Furthermore, in the present invention, the computer described above is an electronic device equipped with a processor, i.e., a CPU (Central Processing Unit), and there is no particular limitation on its type.

Meanwhile, the above detailed description should not be construed as restrictive in all respects but should be considered as illustrative. The scope of the present invention should be determined by a reasonable interpretation of the appended claims, and all changes within the equivalent scope of the present invention are included in the scope of the present invention.

Claims (12)

A step of providing at least one questionnaire related to cognitive behavioral therapy on a user terminal; A step of receiving response data to the questionnaire through the user terminal; A step of generating a prompt to be input into a generative language model using the above response data; a step of inputting the above prompt into the generative language model to generate feedback related to the response data; and A method for providing feedback for cognitive behavioral therapy based on a language model, characterized by comprising a step of providing the generated feedback to the user terminal. In the first paragraph, The above questionnaire is, Includes multiple choice questionnaires that correspond to the multiple choice type, The above multiple choice questionnaire is, The above cognitive behavioral therapy-related questions and multiple choice items are paired to correspond to each of the multiple different responses to the above questions, In the step of generating the above prompt, A method for providing feedback for cognitive behavioral therapy based on a language model, characterized in that the prompt is generated by using a response to a specific selection item selected from the user terminal among the above question and the above multiple selection items. In the second paragraph, In the above multiple different responses, different scores related to the cognitive behavioral therapy are respectively matched and exist, The above prompt says, A method for providing feedback for cognitive behavioral therapy based on a language model, characterized in that the method includes keywords for the above question and scores matching the above specific selection items. In the third paragraph, The above questionnaire is, Include more subjective questionnaires corresponding to the subjective type, The above response data is, Contains memo information received from the user terminal for the above subjective type of questionnaire, In the step of generating the above prompt, A method for providing feedback for cognitive behavioral therapy based on a language model, characterized by generating the prompt using the above memo information. In paragraph 4, It further includes a step of analyzing the meaning of the memo information, which is response data for the subjective questionnaire, and the meaning of the specific selection item for the objective questionnaire. A method for providing feedback for cognitive behavioral therapy based on a language model, characterized in that it further includes a step of performing different processes depending on the degree of similarity between the meaning of the memo information and the meaning of the specific selection item as a result of the analysis. In paragraph 5, In the steps of performing the above different processes, A method for providing feedback for cognitive behavioral therapy based on a language model, characterized in that the prompt is generated using the memo information and the response to the specific selection item when the similarity is greater than a preset reference value. In Article 6, If the above similarity is less than the above preset standard value, the step of conducting a re-survey is further included. At the stage of conducting the above re-survey, A method for providing feedback for cognitive behavioral therapy based on a language model, characterized in that when conducting the above re-survey, guide information regarding the reason for conducting the above re-survey is provided on the user terminal. In the first paragraph, On the server, multiple treatment programs, each matching a different topic, are matched and stored. In the above user terminal, In order for the user to perform the cognitive behavioral therapy according to each of the plurality of treatment programs, the plurality of treatment programs are sequentially provided according to the treatment week set for each of the plurality of treatment programs. Further comprising a step of extracting user information about the user registered in the server and information about a specific treatment program provided to the user terminal among the plurality of treatment programs, In the step of generating the above prompt, A method for providing feedback for cognitive behavioral therapy based on a language model, characterized in that the prompt is generated by combining at least some of the response data, the user information, and information about the specific treatment program. In Article 8, The above user information includes at least one of the user's gender, age, tendencies, and diseases, Information about the specific treatment program above, A method for providing feedback for cognitive behavioral therapy based on a language model, characterized in that it includes information on a specific treatment week corresponding to the specific treatment program, a specific topic matched to the specific treatment program, and information on the user's treatment history up to the specific treatment week. In Article 9, The above feedback is, A method for providing feedback for cognitive behavioral therapy based on a language model, characterized in that it includes summary information about at least some of the response data included in the prompt, the user information, and the information about the specific treatment program, and recommendation information about a specific treatment program scheduled to be performed in the following week of the specific treatment week corresponding to the specific treatment program. A control unit comprising, on a user terminal, at least one questionnaire related to cognitive behavioral therapy, The above control unit, Through the above user terminal, survey response data for the above survey is received, Using the above response data, a prompt to be input into the generative language model is generated. By inputting the above prompt into the generative language model, feedback related to the response data is generated, A feedback providing system for cognitive behavioral therapy based on a language model, characterized in that it provides the generated feedback to the user terminal. A program that is executed by one or more processes on an electronic device and stored on a computer-readable recording medium. The above program is, A step of providing at least one questionnaire related to cognitive behavioral therapy on a user terminal; A step of receiving response data to the questionnaire through the user terminal; A step of generating a prompt to be input into a generative language model using the above response data; a step of inputting the above prompt into the generative language model to generate feedback related to the response data; and A program stored on a computer-readable recording medium, characterized in that it includes commands for performing a step of providing the generated feedback to the user terminal.

Images