Apparatus and method for providing elderly mental care service

Abstract

Disclosed are an apparatus and a method for providing an elderly mental care service. The psychological service providing device comprises: a psychological evaluation unit for transmitting a questionnaire and instructions to a user terminal and evaluating the psychology of a user on the basis of a response received from the user terminal; a psychological education providing unit for transmitting psychological education content to the user terminal; a memory training providing unit for transmitting hints for autobiographical memory and instructions for autobiographical memory to the user terminal, and evaluating the specificity of the autobiographical memory of the user on the basis of memory responses received from the user terminal; a cognitive training providing unit for transmitting cognitive training content to the user terminal; and a program recommendation unit for transmitting a list of content to be recommended to the user to the user terminal and controlling operations of the psychological evaluation unit, the psychological education providing unit, the memory training providing unit, and the cognitive training providing unit on the basis of selection information received from the user terminal.

Description

Device and method for providing mental care services for the elderly

[0001] The present invention relates to a technique for providing psychological services, and more particularly, to a device and method for providing non-face-to-face customized mental health services, including psychological assessment, intervention, training, and education, for the elderly using a mobile device such as a smartphone.

[0002] The background technology of the present invention is, firstly, a self-report mental health screening tool that can measure the severity of depressive and anxiety disorders. The MHS:D (Mental Health Screening tool: Depression) consists of self-report items that measure the severity of depressive disorder, and the MHS:A (Mental Health Screening tool: Anxiety) consists of self-report items that measure the severity of anxiety disorder. Each item is weighted through an adult validation study, and the examinee's depression and anxiety level can be measured as none, mild, moderate, or severe based on the sum score reflecting the weights.

[0003] Furthermore, the content component of the present invention is an evidence-based psychological intervention based on Autobiographical Memory Training (AMT) and the Verbal Memory Training Program (VMTP). Autobiographical memory refers to specific recollections of specific events, including the location and time. Autobiographical memory training is a training method for enhancing the specificity of autobiographical memory and has been proven effective in alleviating depression in old age and enhancing cognitive functions such as memory. VMTP is a cognitive training program known to be effective in improving cognitive abilities such as attention and verbal memory.

[0004] This invention aims to overcome the existing limitation of older adults accessing mental health services. Elderly users with mobility issues due to aging often find it difficult to travel regularly to receive services. Furthermore, existing mobile mental health services have limited accessibility for older adults who struggle to use smartphones. Furthermore, preliminary interviews revealed that the types of mental health issues experienced and the types of services requested by older adults varied across individuals. However, existing applications offered consistent services, such as memory training, to all users. This invention has designed a mental health application that reflects the characteristics of older adults, enabling users to access desired mental health services from their homes via devices like smartphones without having to travel to meet with a professional in person. Furthermore, the mobile service adopts a user-centered design that is familiar and easy to use for older adults, facilitating easy access for older adults. Finally, based on an initial psychological assessment, the service is tailored to older adults, taking into account the severity of their psychological issues and preferences.

[0005] The technical task to be achieved by the present invention is to provide a device and method for providing psychological services based on ICT (Information Communication Technology).

[0006] A psychological service providing device according to one embodiment of the present invention includes a psychological evaluation unit that transmits a questionnaire and instructions to a user terminal and evaluates the psychology of a user based on a response received from the user terminal, a psychological education providing unit that transmits psychological education content to the user terminal, a memory training providing unit that transmits a clue for autobiographical memory and an instruction for autobiographical memory to the user terminal and evaluates the specificity of the user's autobiographical memory based on a memory response received from the user terminal, a cognitive training providing unit that transmits cognitive training content to the user terminal, and a program recommendation unit that transmits a list of contents to be recommended to the user to the user terminal and controls operations of the psychological evaluation unit, the psychological education providing unit, the memory training providing unit, and the cognitive training providing unit based on selection information received from the user terminal.

[0007] The advantages of this invention lie in its service content and delivery method. First, regarding service content, conventional technologies have limitations in that they rely on unverified content from non-experts, which can lead to the maintenance or worsening of symptoms in users experiencing mental health difficulties. This invention is based on research-based, validated mental health assessment tools and evidence-based training, and the application's design is led by clinical psychologists and related researchers, enabling the provision of highly reliable content. This will lead to increased user satisfaction and symptom improvement.

[0008] To overcome the limitations of existing models that provided identical mental health content to all participants, the present invention utilizes a recommendation algorithm to recommend and provide users with a combination of program modules appropriate for their individual mental health level. This proposed method allows users to utilize program modules with a difficulty level appropriate to the type and severity of their symptoms. By utilizing modules that are effective for each individual, users can improve their symptoms and enhance their function.

[0009] In order to more fully understand the drawings cited in the detailed description of the present invention, a detailed description of each drawing is provided.

[0010] Figure 1 illustrates a psychological service provision system according to one embodiment of the present invention.

[0011] Figure 2 is a functional block diagram of the psychological service providing device illustrated in Figure 1.

[0012] FIG. 3 illustrates an example in which content provided by the cognitive training provider illustrated in FIG. 2 is displayed on a user terminal.

[0013] Figure 4 illustrates a conceptual diagram of a method for setting memory training difficulty.

[0014] Figure 5 illustrates a presentation screen for clues and instructions displayed through a user terminal during a memory training process.

[0015] FIGS. 6A to 6D illustrate examples of generated prompts, with FIG. 6A illustrating a first example for an English prompt, FIG. 6B illustrating a second example for an English prompt, FIG. 6C illustrating an example for a Korean prompt, and FIG. 6D illustrating an example of a sample for ICL.

[0016] Specific structural or functional descriptions of embodiments according to the concept of the present invention disclosed in this specification are merely illustrative for the purpose of explaining embodiments according to the concept of the present invention, and embodiments according to the concept of the present invention may be implemented in various forms and are not limited to the embodiments described in this specification.

[0017] Embodiments according to the concept of the present invention may have various modifications and take various forms, and thus, embodiments are illustrated in the drawings and described in detail herein. However, this is not intended to limit embodiments according to the concept of the present invention to specific disclosed forms, but rather includes all modifications, equivalents, or alternatives falling within the spirit and technical scope of the present invention.

[0018] While terms such as "first" or "second" may be used to describe various components, these components should not be limited by these terms. These terms are only intended to distinguish one component from another. For example, a first component may be referred to as a "second component," and similarly, a second component may be referred to as a "first component," without departing from the scope of the present invention.

[0019] When a component is referred to as being "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. Conversely, when a component is referred to as being "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between. Other expressions that describe the relationship between components, such as "between" and "directly between" or "adjacent to" and "directly adjacent to", should be interpreted similarly.

[0020] The terminology used herein is only used to describe specific embodiments and is not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this specification, it should be understood that the terms "comprises" or "has" indicate the presence of a feature, number, step, operation, component, part, or combination thereof described in this 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.

[0021] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and will not be interpreted in an idealized or overly formal sense unless explicitly defined herein.

[0022] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings attached to this specification. However, the scope of the patent application is not limited or restricted by these embodiments. The same reference numerals in each drawing represent the same elements.

[0023] Figure 1 illustrates a psychological service provision system according to one embodiment of the present invention.

[0024] Referring to FIG. 1, a psychological service provision system (10), which may also be referred to as an ICT (Information Communication Technology)-based (elderly) mind care service provision system, includes a user terminal (100) and a psychological service provision device (300). The user terminal (100) and / or the psychological service provision device (300) may refer to a computing device including at least a processor and / or a memory. The computing device may include a PC (Personal Computer), a server, a laptop computer, a tablet PC, a smart phone, a mobile phone, an HMD (Head Mounted Device), etc. In addition, the computing device may be implemented as a plurality of physically separated devices, and according to an embodiment, the computing device may be implemented in a cloud environment. Additionally, at least some of the operations of the user terminal (100) and / or the psychological service providing device (300) described below may be understood as operations of the processor included in the user terminal (100) and / or the processor included in the psychological service providing device (300).

[0025] The psychological service providing device (300) and the user terminal (100) can exchange data or messages via any wired or wireless communication network. The psychological service providing device (300) can transmit a questionnaire for a psychological evaluation of the user to the user terminal (100), and the user terminal (100) can receive a response to the questionnaire displayed on a display device included in the user terminal (100) from the user and transmit the response to the psychological service providing device (300). In addition, the psychological service providing device (300) can conduct a psychological evaluation of the user based on the user's response, and transmit content to be provided to the user based on the psychological evaluation result to the user terminal (100).

[0026] Figure 2 is a functional block diagram of the psychological service providing device illustrated in Figure 1.

[0027] Referring to FIG. 2, a psychological service providing device (300), which may also be referred to as a psychological service providing server, includes a psychological evaluation unit (310), a psychological education providing unit (320), a memory training providing unit (330), a cognitive training providing unit (340), and a program recommendation unit (350). Depending on the embodiment, the psychological service providing device (300) may further include a storage unit (360).

[0028] The psychological evaluation unit (310) may be configured to conduct a psychological evaluation of a user. The psychological evaluation includes an emotional domain evaluation and / or a cognitive domain evaluation. The emotional domain evaluation may include at least one of a depression evaluation, an anxiety evaluation, and an energy evaluation, and the cognitive domain evaluation may include at least one of an attention evaluation, a working memory evaluation, a logical memory evaluation, and a verbal memory evaluation. The psychological evaluation unit (310) may transmit a questionnaire for the psychological evaluation and / or instructions for the psychological evaluation to the user terminal (100), and may perform a psychological evaluation of the user based on a response received from the user terminal (100). The questionnaire and / or instructions may be stored in the storage unit (360). In addition, the questionnaire and / or instructions may be provided separately by evaluation domain (depression, anxiety, energy, attention, working memory, logical memory, and verbal memory). Depending on the embodiment, a questionnaire for the entire emotional domain and a questionnaire for the entire cognitive domain may be provided.

[0029] The psychological evaluation unit (310) can derive the user's psychological evaluation results by calculating an evaluation score based on the user's responses and according to predetermined criteria. The psychological evaluation results can be calculated as specific numerical values. Depending on the embodiment, the psychological evaluation results can be evaluated as one of good, caution (mild), caution (moderate), and severe, or as one of good and caution. Table 1 shows examples of the psychological evaluation scoring criteria. The results of the psychological evaluation by the psychological evaluation unit (310) can be stored in the storage unit (360).

[0030] Based on the combined score, good (mild) Caution (moderate) Severe Anxiety Less than 10 Less than 20 Less than 30 More than 30 Depression Less than 9 Less than 17 Less than 21 More than 20 Vitality (t score) More than 40 (t score) Cognitive Below 58 More than 58

[0031] In addition, the psychological evaluation unit (310) can perform a psychological evaluation operation under the control of the program recommendation unit (350). For example, the psychological evaluation unit (310) can perform a psychological evaluation on a user according to a predetermined cycle (e.g., once a week) under the control of the program recommendation unit (350).

[0032] The psychological education provider (320) can provide any psychological education content to the user terminal (100). The psychological education content may be pre-stored in the storage unit (360). The content may have any of the following formats: text data format, audio data format, and video data format. Specifically, the psychological education provider (320) can provide psychological education content suitable for the user based on the results of a psychological assessment (depression assessment, anxiety assessment, and cognitive assessment) for the user.

[0033] For example, if the depression, anxiety, and cognitive evaluation results are all at the “good” level, any one of depression prevention education content, anxiety prevention education content, and cognitive prevention education content may be transmitted to the user terminal (100).

[0034] If one or more of the depression, anxiety, and cognitive assessment results are at the "caution" level, preventive education content or intervention education content (i.e., depression intervention education content, anxiety intervention education content, and cognitive intervention education content) corresponding to the "caution" area may be transmitted to the user terminal (100). The specific intervention education content may include at least one of autobiographical memory training, cognitive training, and 1:1 counseling.

[0035] If one or more of the depression, anxiety, and cognitive evaluation results are at a “serious” level, preventive education content and / or intervention education content for the area corresponding to “serious” may be transmitted to the user terminal (100).

[0036] For example, if only the depression assessment result is at the "Caution" level, depression prevention education content and / or depression intervention education content may be provided. At this time, either the depression prevention education content or the depression intervention education content may be randomly provided with equal probability. As another example, if the depression assessment result and the cognitive assessment result are at the "Caution" level, either the depression prevention education content, depression intervention education content, cognitive prevention education content, or cognitive intervention education content may be randomly provided with equal probability. At this time, once provided, educational content may not be provided until the remaining educational content is provided.

[0037] In addition, the psychological education provider (320) can provide content for psychological education to the user terminal (100) under the control of the program recommendation provider (350). That is, the program recommendation provider (350) can control the psychological education provider (320) to provide educational content according to predetermined criteria based on the user's psychological evaluation results.

[0038] The memory training provider (330) can perform memory training on the user by providing clues (which may mean words) and / or instructions to the user terminal (100) to enable the user to recall autobiographical memories.

[0039] In addition, the memory training provider (330) can provide memory training content to the user terminal (100) under the control of the program recommendation provider (350). That is, the program recommendation provider (350) can control the memory training provider (330) to provide memory training content according to predetermined criteria based on the user's psychological evaluation results.

[0040] The detailed operation of the memory training provider (330) will be described later.

[0041] The cognitive training provider (340) may provide at least one of a plurality of cognitive training contents (which may include instructions for performing the contents) to the user terminal (100). The plurality of cognitive training contents may include at least one of "counting numbers in order," "counting numbers backwards," "guessing words immediately," "recalling words," "classifying words," and "remembering stories."

[0042] Counting numbers in order can refer to a game-style content in which a predetermined number of (randomly selected) natural numbers (or integers) are presented within a predetermined range, and the presented natural numbers are selected in descending order. At this time, the predetermined range and / or predetermined number may vary depending on the training level (which may refer to the training difficulty) of the counting numbers in order content. For example, as the training level increases, the predetermined range and / or predetermined number may increase. Additionally, the presented numbers may be arranged in order, in reverse order, or randomly.

[0043] Here's a concrete example of counting numbers in order. The numbers are presented visually. Each number is presented once in the center of the screen and then disappears. Sound effects may be added during the number presentation. A number pad from 1 to 0 is then presented on the screen, and the user is asked to input (touch) the numbers in the order presented. Sound and visual effects may be added during the number entry phase. There is no time limit for the number entry phase. The task is considered successful if the number is entered in the correct order, while failure is considered a failure. A success message is displayed if the number is entered correctly, and a failure message is displayed if the number is not entered correctly. The training level then increases, remains constant, or decreases based on the criteria.

[0044] Accordingly, the cognitive training provider (340) can provide information on numbers corresponding to the training level to the user through the user terminal (100) and receive the user's response from the user terminal (100). The cognitive training provider (340) can receive the user's response and, if the user has completed counting the numbers of the corresponding training level in order, transmit content for counting the numbers of the next training level in order to the user terminal (100).

[0045] In addition, the cognitive training provider (340) can provide content for counting numbers backwards to the user terminal (100) when the user achieves a predetermined training level (e.g., training level 5) for content for counting numbers in order.

[0046] Counting backwards can refer to a game-style content where a predetermined number of (randomly selected) natural numbers (or integers) are presented within a predetermined range, and the player selects the presented natural numbers in ascending order. Depending on the training level of the counting backwards content, the predetermined range and / or predetermined number may vary. For example, as the training level increases, the predetermined range and / or predetermined number may increase. Furthermore, the presented numbers may be arranged in sequential order, reversed order, or randomly.

[0047] Counting backwards is explained with a concrete example. In training, numbers are presented visually. Each number is presented once in the center of the screen and then disappears. Sound effects may be inserted when the number is presented. A number pad from 1 to 0 is then presented on the screen, and the user is asked to input (touch) the numbers presented in reverse order. Sound and visual effects may be inserted when entering numbers. There is no time limit for the number entry phase. Accurate input is considered success, while any error is considered failure. A success message is displayed, while a failure message is displayed. Depending on the criteria, the training level may increase, decrease, or remain constant.

[0048] Accordingly, the cognitive training provider (340) can provide information on numbers corresponding to the training level to the user through the user terminal (100) and receive the user's response from the user terminal (100). The cognitive training provider (340) can receive the user's response and, if the user has completed counting backwards the numbers of the corresponding training level, transmit content for counting backwards the numbers of the next training level to the user terminal (100).

[0049] In addition, the cognitive training provider (340) can provide word matching content to the user terminal (100) when the user achieves a predetermined training level (e.g., training level 3) for the content of counting numbers backwards.

[0050] "Word Guessing" is a verbal memory recognition game that involves remembering and recognizing presented words. If all presented words are correctly guessed for each independent trial, the player is considered successful; otherwise, the player fails. The training level can be increased, decreased, or maintained based on an arbitrary algorithm that reflects the cumulative success / failure of the training. For example, if the player succeeds at least k (where k is a natural number less than or equal to n, an exemplary value being 7) out of n training rounds (where n is any natural number, an exemplary value being 10), the training level can be increased. If the player succeeds at least m (where m is a natural number less than k, an exemplary value being 4) but less than k training rounds, the training level can be maintained. If the player succeeds less than m training rounds, the training level can be decreased. Furthermore, depending on the training level, at least one of the following may vary: the difficulty of the presented words, the number of presented words, the number of words included in the recognition list, and the duration of word presentation. That is, the higher the training level, the more difficult the presented words may be, the more words may be presented, the shorter the time for which words are presented, or the more words may be included in the recognition list.

[0051] In word-guessing training, words are presented visually. The training involves memorizing the words presented on the screen and then selecting the presented word from a list of words presented later. Each word is presented once on the screen (referring to the display device of the user terminal (100)) and disappears after presentation. A sound effect may be inserted when the word is presented. A recognition list consisting of randomly selected words from among correct (presented) and incorrect (unpresented) words can be generated (the number of words included in the recognition list may vary or remain the same depending on the training level). Words are randomly selected from the recognition list and presented one at a time at the center of the screen. The user can select whether the presented word is correct or incorrect, and sound and visual effects may be inserted upon selection. The correct answer selection phase may not have a time limit. A user succeeds if all words are correct, and the training level may be increased, decreased, or maintained depending on the criteria.

[0052] Accordingly, the cognitive training provider (340) can provide the user with words corresponding to the training level through the user terminal (100) and receive the user's response from the user terminal (100). Data necessary for word-matching training, such as presented words, a list of words, and / or the time at which words are presented, can be transmitted to the user terminal (100). The cognitive training provider (340) can determine whether the user's training was successful based on the user's response and can change or maintain the user's training level according to predetermined criteria.

[0053] The cognitive training provider (340) receives the user's response, and if the user has completed the word matching for the corresponding training level, it can transmit the word matching content for the next training level to the user terminal (100).

[0054] In addition, the cognitive training provider (340) may provide content based on the cognitive domain evaluation results when the user achieves a predetermined training level (e.g., training level 6) for the word-guessing content. Specifically, cognitive training content corresponding to “caution” and / or “serious” among the cognitive domain evaluations may be provided. If there are two or more cognitive domain evaluations corresponding to “caution” and / or “serious,” content corresponding to any one of the cognitive domain evaluations may be provided. If all cognitive domain evaluations are “good,” any one of word recall, word classification, and story memory content may be provided. At this time, among the cognitive domains, attention may correspond to aligning numbers in order, working memory may correspond to aligning numbers backwards, logical memory may correspond to story memory, and verbal memory may correspond to word-guessing, word recall, and word classification.

[0055] Word Recall is a verbal memory recall game that involves recalling presented words. If all presented words are correctly identified for each independent trial, it is considered a success; otherwise, it is considered a failure. The training level can be increased, decreased, or maintained based on an arbitrary algorithm that reflects the cumulative success / failure of the training. For example, if a participant succeeds at least k (k is a natural number less than or equal to n, an exemplary value being 7) out of n training rounds (where n is any natural number, an exemplary value being 10), the training level can be increased. If a participant succeeds at least m (m is a natural number less than k, an exemplary value being 4) but less than k training rounds, the training level can be maintained. If a participant succeeds less than m training rounds, the training level can be decreased. Furthermore, depending on the training level, at least one of the following may vary: the difficulty of the presented words, the number of presented words, and the duration of presentation. That is, as the training level increases, the difficulty of the words presented may increase, the number of words presented may increase, or the time for which words are presented may decrease.

[0056] In word recall training, words are presented visually. The user memorizes the words presented on the screen, and then directly inputs the memorized words. Each word is presented once on the screen (referring to the display device of the user terminal (100)) and disappears after presentation. A sound effect may be inserted when the word is presented. The user then directly inputs the word into the word input window. The order of word input is irrelevant, and there may be no time limit for the word input phase. The correct / incorrect answer is not displayed for each word input, but the number of correct answers out of the total number of words may be displayed after all inputs are completed. A sound effect may be inserted for each word input to indicate that the input is ongoing. If all words are correct, the training is considered a success, otherwise a failure. A success message is displayed if the result is a success, and a failure message is displayed if the result is a failure. The training level may then be increased, decreased, or maintained based on criteria.

[0057] Accordingly, the cognitive training provider (340) can provide the user with words corresponding to the training level through the user terminal (100) and receive the user's response from the user terminal (100). Data necessary for word recall training, such as the presented words and / or the time at which the words are presented, can be transmitted to the user terminal (100). The cognitive training provider (340) can determine whether the user's training was successful based on the user's response and can change or maintain the user's training level according to predetermined criteria.

[0058] Word classification is a word sorting game where the task is to sort presented words into their appropriate categories, remember them, and recognize them. If all presented words are correctly identified for each independent trial, the player is considered successful; otherwise, the player is considered a failure. The training level can be increased, decreased, or maintained based on an arbitrary algorithm that reflects the cumulative success / failure of the training. For example, if the player succeeds at least k (where k is a natural number less than or equal to n, an example value is 7) out of n training rounds (where n is any natural number, an example value is 10), the training level can be increased. If the player succeeds at least m (where m is a natural number less than k, an example value is 4) but less than k training rounds, the training level can be maintained. If the player succeeds less than m training rounds, the training level can be decreased. Furthermore, the difficulty of the presented words and the number of presented words may vary depending on the training level. That is, the higher the training level, the higher the difficulty of the words presented or the greater the number of words presented.

[0059] In word classification training, words are presented visually. The screen is divided into two to four sections, depending on difficulty, and each section is assigned a category name. Words from a word list (consisting of words from the presented category) are presented in order at the center of the screen, and the subject selects the appropriate category. Each word is presented once at the center of the screen, and if the correct category is selected, the word disappears (sound and visual effects may be added when selected). If the category is incorrect, a message indicating "incorrect selection" is displayed and the subject is asked to select a new category. After all presented words are selected from the correct category, a recognition list is generated, consisting of correct (presented) and incorrect (unpresented) words randomly selected from the recognition list. Words are randomly selected from the generated recognition list and presented one at a time at the center of the screen. The subject then determines whether the presented word is correct or incorrect. Sound and visual effects may be added when selecting a word. The word selection phase may have no time limit. A perfect score is considered a success, while a failure is considered a failure. If the decision is successful, a success message can be output, and if it is unsuccessful, a failure message can be output. The training level can then be increased, maintained, or decreased based on the criteria.

[0060] Accordingly, the cognitive training provider (340) can provide words, categories, etc. corresponding to the training level to the user through the user terminal (100) and receive the user's response from the user terminal (100). Data necessary for word classification training, such as the presented words, the time at which the words are presented, the recognition list, etc., can be transmitted to the user terminal (100). The cognitive training provider (340) can determine whether the user's training is successful based on the user's response and can change or maintain the user's training level according to predetermined criteria.

[0061] Story memory training is a reality-based logical memory game in which participants are tasked with remembering presented messages and solving related quizzes. The task may not be repeated, and after each trial, the number of correct answers out of the total number of questions is reported. A different task can be randomly generated and repeated. There is no pass or fail judgment. The training messages are presented auditorily. Each scenario and its corresponding choice options are randomly selected. A quiz for each scenario is then presented, requiring the participant to select the correct answer. There is no time limit for the answer selection phase. The total percentage of correct answers is counted. After completing the task, the user can be informed of the number of correct answers out of the total number of questions.

[0062] Accordingly, the cognitive training provider (340) can provide messages corresponding to training to the user through the user terminal (100) and receive the user's response from the user terminal (100). Data necessary for story memory training, such as presented messages and problems, can be transmitted to the user terminal (100).

[0063] In addition, the cognitive training provider (340) can provide cognitive training content to the user terminal (100) under the control of the program recommendation provider (350). That is, the program recommendation provider (350) can control the cognitive training provider (340) to provide cognitive training content according to predetermined criteria based on the user's psychological evaluation results.

[0064] The program recommendation unit (350) can control each component of the psychological service provision device (300) to provide a predetermined content, program, information, or data to the user through the user terminal (100).

[0065] When a user receives a psychological service for the first time, the program recommendation unit (350) can cause a psychological evaluation to be performed on the user. Accordingly, when the user first connects to the psychological service provision device (300) via the user terminal (100), the program recommendation unit (350) can control the psychological evaluation unit (310) to cause a psychological evaluation to be performed on the user. For example, the program recommendation unit (350) can receive a psychological evaluation request from the user terminal (100) and, in response to the received psychological evaluation request, control the psychological evaluation unit (310) to perform the psychological evaluation. The psychological evaluation unit (310) can transmit a questionnaire and / or instructions for the psychological evaluation to the user terminal (100) under the control of the program recommendation unit (350) and receive a response thereto to perform a psychological evaluation on the user.

[0066] The program recommendation unit (350) can transmit a list of recommended programs among the programs (which may be named as content) to be provided to the user terminal (100) to the user terminal (100). The recommended programs can include multiple programs (e.g., three programs).

[0067] The first recommended program among the recommended programs is the psychological assessment program.

[0068] Among the recommended programs, the second recommended program is psychological education content (or psychological education program). Depending on the embodiment, the second recommended program may refer to any one of the psychological education contents selected based on the user's psychological evaluation results. In this case, the program recommendation unit (350) may select the psychological education contents to be included in the second recommended program based on the user's psychological evaluation results (depression, anxiety, and cognitive evaluation results). For example, if the depression, anxiety, and cognitive evaluation results are all at a good level, the program recommendation unit (350) may select any one of the depression prevention education contents, anxiety prevention education contents, and cognitive prevention education contents as the second recommended program.

[0069] The third recommended program among the recommended programs is a memory training program.

[0070] Among the recommended programs, the fourth recommended program is a cognitive training program (or cognitive training content). Depending on the embodiment, the second recommended program may refer to any one of the cognitive training programs (or cognitive training content) selected based on the user's psychological evaluation results. In this case, the program recommendation unit (350) may select a cognitive training program (or cognitive training content) to be included in the third recommended program based on the user's psychological evaluation results (attention, working memory, logical memory, and verbal memory evaluation results). For example, among the cognitive training contents corresponding to the evaluation areas corresponding to "caution" and / or "severe" among the cognitive domain evaluation results, a randomly selected cognitive training content may be selected as the third recommended program. If only the attention assessment result is "Caution" or "Serious", then counting in numerical order can be selected as the fourth recommended program; if only the working memory assessment result is "Caution" or "Serious", then counting backwards; if only the logical memory assessment result is "Caution" or "Serious", then story memory; if only the verbal memory assessment result is "Caution" or "Serious", then any one of word matching, word recall, and word classification can be selected as the fourth recommended program.

[0071] If there are three recommended programs, a list of the three programs ranked higher among the first through fourth recommended programs may be provided. Furthermore, since psychological evaluations of users are preferably conducted periodically, if a predetermined period has not elapsed since the psychological evaluation was conducted, the recommended programs may include the second through fourth recommended programs, excluding the first recommended program.

[0072] A user selects a recommended program displayed on a display device of a user terminal (100), and selection information about the recommended program is transmitted by the user terminal (100) to a psychological service providing device (300), i.e., a program recommendation unit (350). The program recommendation unit (350) can control any one of a psychological evaluation unit (310), a psychological education providing unit (320), a memory training providing unit (330), and a cognitive training providing unit (340) to provide a program (or content) corresponding to the received selection information to the user terminal (100).

[0073] The storage unit (360) may store an OS (Operating System), source code, program, application, etc. required for driving or operating the psychological service providing device (300). In addition, the storage unit (360) may store a questionnaire used for psychological evaluation of a user, instructions corresponding to each questionnaire, data temporarily or non-temporarily generated during a psychological evaluation operation by the psychological evaluation unit (310), data temporarily or non-temporarily generated during a psychological education providing operation by the psychological education providing unit (320), data temporarily or non-temporarily generated during a memory training operation by the memory training providing unit (330), data temporarily or non-temporarily generated during a program recommendation operation by the program recommendation unit (350), data or content provided to the user terminal (100), data received from the user terminal (100), etc.

[0074] Each of the components of the psychological service providing device (300) illustrated in FIG. 2 is shown as being functionally and logically separable, and an average expert in the technical field of the present invention will be able to easily infer that this does not necessarily mean that each component is separated into a separate physical device or written in a separate code.

[0075] Additionally, the term "part" in this specification may refer to a functional and structural combination of hardware for implementing the technical concepts of the present invention and software for operating the hardware. For example, the "part" may refer to a logical unit of a given code and hardware resources for executing the given code, and does not necessarily refer to physically connected code or a single type of hardware.

[0076] Below, the specific operation of the memory training provider (340) is described.

[0077] The memory training provider (340) can transmit at least one clue (which may mean a word) for evoking an (autobiographical) memory and an instruction for recalling the autobiographical memory to the user terminal (100), and can receive a user response thereto from the user terminal (100). In addition, the memory training provider (340) can evaluate the specificity (quality of memory) of the autobiographical memory recalled by the user based on the response received from the user terminal (300). The evaluation result can be transmitted from the memory training provider (340) to the user terminal (100).

[0078] The memory training provider (340) can extract at least one clue used to measure the quality of the autobiographical memory of a user (or subject) and transmit the extracted word to the user terminal (100) along with an instruction for recalling the autobiographical memory.

[0079] At this time, the extracted clues and instructions may be in the form of text data or voice data. To this end, the memory training provider (340) may generate voice signals for the extracted clues and instructions using a predetermined Text-To-Speech (TTS) technology. As another example, voice data corresponding to the extracted clues and instructions may be selected from voice data pre-stored in the storage unit (360).

[0080] To extract clues, multiple words may be pre-stored in the storage unit (360). In the present invention, multiple words to be provided to users (e.g., elderly persons) are collected, and the words are classified into beginner clues, intermediate clues, and advanced clues according to the difficulty of the clues. Beginner clues are words with low to medium emotional stimulation that can be easily recalled in daily life (e.g., 200 words). Intermediate clues are words with low to medium emotional stimulation that can be recalled in daily life (e.g., 200 words). Advanced clues are words with medium to high emotional stimulation that are difficult to recall in daily life (e.g., 200 words). The difficulty of each clue can be understood as the degree of difficulty in providing a memory related to the clue. For example, cues that are difficult to recall or that have a small number of meaningful utterances can be understood as having high cue difficulty.

[0081] Words with high emotional stimulation may refer to words that are highly likely to induce negative emotions such as sadness, fear, anger, and disgust. Words with medium emotional stimulation may refer to words that are somewhat likely to induce negative emotions. Words with low emotional stimulation may refer to words that are almost unlikely to induce negative emotions. The intensity of emotional stimulation and / or the difficulty of words may be evaluated in advance by experts such as clinical psychology researchers, and the evaluation results may be stored in the storage unit (360). For example, after creating a pool of 600 words, each word may be cross-evaluated by two or more clinical psychology researchers on a 3-point scale (0 (low) - 1 (medium) - 2 (high)), and based on the average of the evaluations, the pool may be reorganized into a pool of low-level clues, intermediate clues, and advanced clues.

[0082] The memory training provider (340) can generate multiple clue pools by considering the difficulty of the clues. The clue pools can include a first clue pool (basic clue pool), a second clue pool (basic clue pool), and a third clue pool (advanced clue pool). The first clue pool is generated by selecting (or extracting) beginner clues and intermediate clues in a predetermined ratio, the second clue pool is generated by selecting (or extracting) beginner clues, intermediate clues, and advanced clues in a predetermined ratio, and the third clue pool can be generated by selecting (or extracting) intermediate clues and advanced clues in a predetermined ratio. For example, the first clue pool is composed of clues that a user of the first level, which will be described later, has little difficulty recalling autobiographical memories at that level (e.g., 60% beginner clues and 40% intermediate clues), the second clue pool is composed of clues that a user of the second level has little difficulty recalling autobiographical memories at that level or requires little effort (e.g., 20% beginner clues, 40% intermediate clues, and 20% advanced clues), and the third clue pool is composed of clues that a user of the third level requires little or considerable effort to recall autobiographical memories at that level. The required clues may be composed primarily of intermediate clues (e.g., 40% intermediate clues and 60% advanced clues). The memory training provider (340) may periodically or aperiodically generate multiple clue pools, thereby allowing the composition of the clues included in the clue pool to be changed.

[0083] When each user initially performs memory training (autobiographical memory training or daily memory training), the user's autobiographical memory training level is assessed through multiple rounds of training (e.g., 10 rounds). To this end, the memory training provider (340) transmits random words and instructions (phrases) from the first clue pool to the user terminal (100), and based on the response thereto, the specificity (quality of memory) of the autobiographical memory can be assessed. By repeatedly performing this operation multiple times, the user's autobiographical memory training level can be assessed. For example, the user's training level can be assessed as one of the first, second, and third levels based on the average of the evaluation results. For example, if the average of the evaluation results is in the lower 1 / 3, the user can be assessed as in the first level, if it is in the middle 1 / 3, the user can be assessed as in the second level, and if it is in the upper 1 / 3, the user can be assessed as in the third level.

[0084] The memory training provider (330) can provide autobiographical memory training to the user by considering the user's autobiographical memory training level, depression assessment results (depression level), and cognitive assessment results (cognitive level). The description is provided with reference to Fig. 4, which illustrates a conceptual diagram of a method for setting memory training difficulty.

[0085] 1) First, we explain the case where the user's autobiographical memory training level is level 1.

[0086] If the (recent) depression level is below moderate and the cognitive level is good, autobiographical memory training is performed using the first cue pool (daily memory training (basic) of FIG. 4). That is, one of the cue pools included in the first cue pool and an instruction are transmitted to the user terminal (100), and the quality of autobiographical memory can be evaluated based on the response thereto.

[0087] If the (recent) depression level is moderate or higher and the cognitive level is good, autobiographical memory training is performed using the first cue pool. At this time, cues can be extracted from the words included in the first cue pool so that the ratio (or probability) of low to medium emotional stimulation is 8:2. In other words, the cues and instructions extracted according to the determined emotional stimulation ratio among the cues included in the first cue pool are transmitted to the user terminal (100), and the quality of autobiographical memory can be evaluated based on the response thereto.

[0088] If the (recent) depression level is less than moderate and at least one cognitive level is attention, autobiographical memory training is performed using the first cue pool. At this time, clues can be extracted from the words included in the first cue pool so that the ratio of low to medium emotional stimulation is 8:2 (or probability). That is, the extracted clues and instructions according to the determined emotional stimulation ratio among the clues included in the first cue pool are transmitted to the user terminal (100), and the quality of autobiographical memory can be evaluated based on the response thereto. At this time, if the average of the evaluation results over a predetermined number of times is greater than a threshold (e.g., 65 points), autobiographical memory training corresponding to the next level (second level) can be provided.

[0089] If the (recent) depression level is moderate or higher and at least one cognitive level is attention, autobiographical memory training is performed using the first cue pool. At this time, cues can be extracted from the words included in the first cue pool so that the ratio (or probability) of low to medium emotional stimulation is 8:2. That is, the extracted cues and instructions according to the determined emotional stimulation ratio among the cues included in the first cue pool are transmitted to the user terminal (100), and the quality of autobiographical memory can be evaluated based on the response thereto. At this time, if the average of the evaluation results over a predetermined number of times is higher than a threshold (e.g., 65 points), autobiographical memory training corresponding to the next level (second level) can be provided.

[0090] 2) Describe the case where the user's autobiographical memory training level is level 2.

[0091] If the (recent) depression level is below moderate and the cognitive level is good, autobiographical memory training is performed using the second cue pool (daily memory training (basic) of FIG. 4). That is, one of the cues included in the second cue pool and an instruction are transmitted to the user terminal (100), and the quality of autobiographical memory can be evaluated based on the response thereto.

[0092] If the (recent) depression level is moderate or higher and the cognitive level is good, autobiographical memory training is performed using the second cue pool. At this time, cues can be extracted from the words included in the second cue pool so that the ratio of low to medium emotional stimulation is 8:2 (or probability). That is, the cues and instructions extracted according to the determined emotional stimulation ratio among the cues included in the second cue pool are transmitted to the user terminal (100), and the quality of autobiographical memory can be evaluated based on the response thereto.

[0093] If the (recent) depression level is less than moderate and at least one cognitive level is attention, autobiographical memory training is performed using the second cue pool. At this time, clues can be extracted from the words included in the second cue pool so that the ratio (or probability) of low to medium emotional stimulation is 8:2. That is, the extracted clues and instructions according to the determined emotional stimulation ratio among the clues included in the second cue pool are transmitted to the user terminal (100), and the quality of autobiographical memory can be evaluated based on the response thereto. At this time, if the average of the evaluation results over a predetermined number of times is greater than a threshold (e.g., 65 points), autobiographical memory training corresponding to the next level (third level) can be provided.

[0094] If the (recent) depression level is moderate or higher and at least one cognitive level is attention, autobiographical memory training is performed using the second cue pool. At this time, cues can be extracted from the words included in the second cue pool so that the ratio (or probability) of low to medium emotional stimulation is 8:2. That is, the extracted cues and instructions according to the determined emotional stimulation level ratio among the cues included in the second cue pool are transmitted to the user terminal (100), and the quality of autobiographical memory can be evaluated based on the response thereto. At this time, if the average of the evaluation results over a predetermined number of times is higher than a threshold (e.g., 65 points), autobiographical memory training corresponding to the next level (third level) can be provided.

[0095] 3) Describes a case where the user's autobiographical memory training level is level 3.

[0096] If the (recent) depression level is less than moderate and the cognitive level is good, autobiographical memory training is performed using the third cue pool (daily memory training (advanced) of FIG. 4). That is, one of the cue pools included in the third cue pool and an instruction are transmitted to the user terminal (100), and the quality of autobiographical memory can be evaluated based on the response thereto.

[0097] If the patient's depression level is moderate or higher and their cognitive level is good, autobiographical memory training is performed using the third cue pool. At this time, only those cues with a moderate level of emotional stimulation can be extracted from the words in the third cue pool. That is, the extracted cues and instructions, based on a predetermined level of emotional stimulation from among the cues in the third cue pool, are transmitted to the user terminal (100), and the quality of autobiographical memory can be evaluated based on the response.

[0098] If the (recent) depression level is below moderate and one or more cognitive levels are at attention, autobiographical memory training is performed using the third cue pool. That is, randomly extracted cues and instructions from among the cues included in the third cue pool are transmitted to the user terminal (100), and the quality of autobiographical memory can be evaluated based on the response thereto.

[0099] If the (recent) depression level is moderate or higher and at least one cognitive level is attention, autobiographical memory training is performed using the third cue pool. At this time, only cues with a moderate level of emotional stimulation can be extracted from the words included in the third cue pool. That is, the extracted cues and instructions, based on a predetermined level of emotional stimulation among the cues included in the third cue pool, are transmitted to the user terminal (100), and the quality of autobiographical memory can be evaluated based on the response thereto.

[0100] As a specific example, a 65-year-old female participant can be guided to recall a memory related to “regret,” and to utter a sentence including information such as when it happened, where it happened, who she was with, and what she was doing at the time. At this time, the selected word may be “regret,” and the instruction may be “Recall my memory related to [clue]. When did it happen? Where was it? Who were you with at the time? What did you do at the time?” A presentation screen for the “clue” and “instruction” displayed through the user terminal (100) is illustrated in FIG. 5. In this case, the user can input a memory (response) related to “regret” into the user terminal (100) via voice or text, and the input response can be transmitted to the memory training provider (330). At this time, the response received from the user can be voice data or text data, and the user terminal (100) can convert the voice data into text data and then transmit it. In some embodiments, voice data may be transmitted to a memory training provider (330), and the memory training provider (330) may convert the voice data into text data.

[0101] The memory training provider (330) can receive responses to words and instructions from the user terminal (100) and perform a response processing operation for autobiographical memory evaluation on the received responses.

[0102] The response processing operation can be understood as generating input for the evaluation model. In this case, the evaluation model, which evaluates the specificity of the user's autobiographical memory, can be a Large Language Model (LLM) such as ChatGPT. Therefore, the response processing operation can be understood as generating input data for the Large Language Model (LLM) based on the received response.

[0103] The response processing operation may include at least one of a textualization operation, a co-reference resolution operation, and a pseudo-subject insertion operation for the received response. However, depending on the embodiment, the response processing operation may not include the above-described response processing operation. This is because recently, large language models (LLMs) themselves receive speech input and show excellent performance even without co-reference resolution or pseudo-subject insertion operations. Depending on the embodiment, the response processing operation may include a subword-based tokenization, encoding, and padding process for sentences and words in the response.

[0104] If the received response is voice data, the memory training provider (330) can convert the voice data format response into a text format response. The conversion into a text format response can be performed using any STT (Speech-To-Text) technique. Of course, if the received response is in text format, the text conversion operation for the response can be omitted.

[0105] Text-based responses often have ambiguous sentence structures, such as the presence of pronouns. To alleviate this ambiguity, a coreference resolution operation can be performed on the response. Coreference resolution can employ any technique, such as the Fast End-to-end Coreference Resolution for Korean (https: / aclanthology.org / 2020.findings-emnlp.237.pdf) technique. This technique can resolve syntactic ambiguity in received responses, thereby enhancing model comprehension during the learning and inference processes.

[0106] Furthermore, responses may consist of multiple sentences rather than single sentences, and coherence between sentences may be an important feature. To this end, pseudo-subject insertion can be performed for utterance turns (which may refer to sentences included in the response) with missing subjects. To this end, dependency parsing (DP) is performed, through which sentences with missing subjects are extracted and pseudo-subjects are inserted into the extracted sentences. For an example of syntactic dependency analysis, please refer to https: / github.com / kakaobrain / pororo.

[0107] The response processing operation may include a prompt generation operation that is input to the evaluation model. The prompt may include at least one of information about the task (Task Instruction), a sample for in-context learning (ICL) (may be referred to as a shot), and a user response.

[0108] In some embodiments, the generated prompts, along with the user's responses (which may be preprocessed responses), may be understood as forming the input for the evaluation model. Information about the task may include descriptions of the components of autobiographical memory (i.e., temporal elements, spatial elements, and whether the memory is a personal experience), as well as specific descriptions of each component. In this case, the components of autobiographical memory may also be referred to as "constitutive elements of autobiographical memory."

[0109] Samples for in-context learning (ICL) can include instructions for the task to be performed by the evaluation model, instructions for inferring the applicability of each component of autobiographical memory, at least one positive example, and at least one negative example. For in-context learning (ICL) techniques, configuring high-quality positive and negative samples to effectively draw on the inherent knowledge of the large language model (LLM) is crucial for performance, requiring heuristics from engineers. Therefore, to appropriately assess memory quality based on utterances about autobiographical memories, a sample set encompassing each element of specificity (e.g., temporal, spatial, and personal experience) can be heuristically constructed and provided along with the current input. This can enhance the performance of the LLM in assessing memory quality.

[0110] In this regard, FIGS. 6A to 6D are examples of generated prompts, where FIG. 6A shows a first example for an English prompt, FIG. 6B shows a second example for an English prompt, FIG. 6C shows an example for a Korean prompt, and FIG. 6D shows an example of a sample for ICL. The prompt templates illustrated in FIGS. 6A to 6D are combined with actual inputs (responses) and used as inputs for the evaluation model, and are therefore configured in the form of strings, [·] represents the role of each prompt within the entire prompt template, and {{·}} is a template section for receiving the current relevant sample and input text to configure the actual input.

[0111] The memory training provider (330) can use an evaluation model to evaluate the specificity (quality of memory) of autobiographical memories corresponding to user input. Here, the evaluation model may refer to a Large Language Model (LLM). The evaluation model, which receives a prompt (which may be understood as a concept including user responses), may include at least one of the evaluation results for each component of autobiographical memory, the evaluation result regarding whether the memory corresponds to an autobiographical memory, and the reason why the memory does not correspond to an autobiographical memory. In other words, if it is determined that the memory includes not only essential elements of autobiographical memory (whether it is a subjective experience, whether it has temporal specificity, whether it has spatial specificity, and whether it has event specificity), but also specific memory details such as emotions, thoughts, people, and sensations, a high autobiographical memory specificity score can be awarded. The autobiographical memory specificity score can be used to determine the degree of sophistication of the user's memories and the trend in how detailed the memories can be described.

[0112] Depending on the embodiment, the evaluation model may not be stored in the psychological service providing device (300). In this case, the memory training providing unit (330) may perform the evaluation operation by transmitting the generated prompt to a server providing a large language model service and receiving a response thereto.

[0113] The devices described above may be implemented as hardware components, software components, and / or a collection of hardware components and software components. For example, the devices and components described in the embodiments may be implemented using one or more general-purpose computers or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor (DSP), a microcomputer, a field programmable array (FPA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing instructions and responding to them. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. Furthermore, the processing device may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing device is sometimes described as being used alone; however, one of ordinary skill in the art will recognize that the processing device may include multiple processing elements and / or multiple types of processing elements. For example, a processing unit may include multiple processors, or a processor and a controller. Other processing configurations, such as parallel processors, are also possible.

[0114] Software may include a computer program, code, instructions, or a combination of one or more of these, and may configure a processing device to perform a desired operation or command the processing device, independently or collectively. Software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave to be interpreted by the processing device or to provide instructions or data to the processing device. Software may be distributed on network-connected computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0115] The method according to the embodiment may be implemented in the form of program commands that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program commands, data files, data structures, etc., alone or in combination. The program commands recorded on the medium may be those specially designed and configured for the embodiment or may be those known to and usable by those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specially configured to store and execute program commands, such as ROMs, RAMs, and flash memories. Examples of the program commands include not only machine language codes generated by a compiler but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiment, and vice versa.

[0116] Although the present invention has been described with reference to the embodiments illustrated in the drawings, these are merely exemplary, and those skilled in the art will understand that various modifications and equivalent other embodiments are possible from the described techniques. For example, appropriate results can be achieved even if the described techniques are performed in a different order than the described method, and / or components of the described systems, structures, devices, circuits, etc. are combined or combined in a different form than the described method, or are replaced or substituted with other components or equivalents. Therefore, the true technical protection scope of the present invention should be determined by the technical spirit of the appended claims.

Claims

1. A psychological evaluation unit that sends a questionnaire and instructions to a user terminal and evaluates the user's psychology based on the responses received from the user terminal; A psychological education provider that transmits psychological education content to the above user terminal; A memory training provider that transmits a clue for autobiographical memory and an instruction for autobiographical memory to the user terminal and evaluates the specificity of the user's autobiographical memory based on a memory response received from the user terminal; A cognitive training provider that transmits cognitive training content to the user terminal; and A psychological service providing device including a program recommendation unit that transmits a list of contents to be recommended to the user to the user terminal and controls the operations of the psychological evaluation unit, the psychological education providing unit, the memory training providing unit, and the cognitive training providing unit based on selection information received from the user terminal.

2. In paragraph 1, The above program recommendation section includes a psychological evaluation in the above list when a predetermined period has passed since the time the psychological evaluation was performed on the user. A psychological service provider.

3. In paragraph 1, The above list includes one of the following: psychological assessment, one of the following: psychoeducational programs, one of the following: autobiographical memory training, and three of the following: cognitive training. A psychological service provider.

4. In paragraph 1, The above psychological evaluation section performs an emotional domain evaluation and a cognitive domain evaluation of the user, The emotional domain includes at least one of depression, anxiety, and energy. The cognitive domain includes at least one of attention, working memory, logical memory, and verbal memory. A psychological service provider.

5. In paragraph 1, The above psychological education provider transmits psychological education content to the user terminal based on the depression evaluation results, anxiety evaluation results, and cognitive evaluation results for the user. If the depression evaluation results, anxiety evaluation results, and cognitive evaluation results are all at the “good” level, one of the depression prevention education content, anxiety prevention education content, and cognitive prevention education content is transmitted to the user terminal, If one or more of the depression evaluation results, anxiety evaluation results, and cognitive evaluation results are at the “caution” level, preventive education content for the area corresponding to the “moderate” level is transmitted to the user terminal. If one or more of the depression evaluation results, anxiety evaluation results, and cognitive evaluation results are at a “serious” level, preventive education content for the area corresponding to the “serious” level is transmitted to the user terminal. A psychological service provider.

6. In paragraph 1, The above memory training provider inputs the prompt into the Large Language Model (LLM) to determine the specificity of the autobiographical memory for the above memory response. The above prompt includes information about the task that the giant language model performs, samples for ICL (In-Context Learning), and the memory response. The above task is to infer the specificity of autobiographical memory for the above memory response. A psychological service provider.

7. In paragraph 6, The above memory training provider includes the results of performing a co-reference resolution operation and a pseudo subject insertion operation for the above memory response in the above prompt. A psychological service provider.

8. In paragraph 1, The above cognitive training provider transmits cognitive training content corresponding to the “attention” area among attention evaluation, working memory evaluation, logical memory evaluation, and verbal memory evaluation to the user terminal. A psychological service provider.

9. In paragraph 8, Attention corresponds to the content of counting numbers in order, working memory corresponds to the content of counting numbers backwards, logical memory corresponds to the content of remembering stories, and verbal memory corresponds to the content of immediately matching words, recalling words, and categorizing words. A psychological service provider.

10. In paragraph 1, The above memory training provider extracts clues transmitted to the user terminal based on the results of the user's previous autobiographical memory training. A psychological service provider.

Images