KR102608964B1 - Method for providing training content to user by referring to at least one event keyword and computing device using the same - Google Patents

Abstract

The present invention relates to a method for providing training content to a user with reference to at least one event keyword, wherein (a) when at least one event keyword is input from the user, the computing device selects the event keyword from all emotion categories; Mapping each corresponding emotion category and each corresponding event score; and (b) the computing device, among each of the event keywords, a first condition in which each of the emotion categories corresponding to each of the event keywords corresponds to a preset negative emotion category, and each of the event scores is greater than or equal to a preset first threshold. Select a first specific event keyword to a z-th specific event keyword that simultaneously satisfies the corresponding second conditions, and select a first to a first specific event score corresponding to each of the first to the z-th specific event keywords. A method including providing basic training content for lowering z specific event scores below the 2_1th threshold to the 2_zth threshold, respectively.

Description

Method and computing device for providing training content to a user with reference to at least one event keyword {METHOD FOR PROVIDING TRAINING CONTENT TO USER BY REFERRING TO AT LEAST ONE EVENT KEYWORD AND COMPUTING DEVICE USING THE SAME}

The present invention relates to a method and computing device for providing training content to a user with reference to at least one event keyword.

According to the Korea Institute for Advancement of Technology, the global biohealth market size is expected to grow at an average annual growth rate of 9.3% from $1.4835 trillion in 2021 to $2.5315 trillion in 2027. In particular, Korea is experiencing rapid business growth in the medical AI field thanks to its excellent IT technology and digitalized medical infrastructure. In addition, Korea's digital therapy device market is expected to increase from $47.42 million in 2020 to an average annual growth rate of 23.2%, reaching $204.37 million in 2027.

In particular, non-face-to-face medical care is rapidly increasing and digital healthcare is accelerating after COVID-19, and interest in mental health management due to the COVID-19 crisis is also expanding.

In particular, only uniform solutions such as counseling, meditation, and yoga are provided to modern people who are under a lot of mental stress. There are limits to improving mental stress, and another problem is that the characteristics and conditions of each user are not taken into consideration. It is becoming.

In this situation, there is a need for a method and computing device for providing training content to users with reference to at least one event keyword targeting people struggling with mental health.
Prior art literature - Korean registered patent KR10-2097246

The purpose of the present invention is to solve the above-mentioned problems.

In the present invention, when at least one event keyword is input from the user, each emotion category corresponding to each event keyword and each corresponding event score are mapped among all emotion categories, and each emotion category corresponding to each event keyword is preset. After checking whether the first condition and the event score corresponding to the negative emotion category simultaneously satisfy the second condition corresponding to a preset first threshold or more, the first specific event keyword to the z specific event keyword are selected, and the first specific event keyword is selected. Another purpose is to provide basic training content for lowering the first specific event score to the zth specific event score corresponding to each of the specific event keyword to the zth specific event keyword to below the 2_1th threshold to the 2_zth threshold, respectively.

The characteristic configuration of the present invention for achieving the purpose of the present invention as described above and realizing the characteristic effects of the present invention described later is as follows.

According to one aspect of the present invention, in a method for providing training content to a user with reference to at least one event keyword, (a) when at least one event keyword is input from the user, the computing device determines the overall emotion. mapping each of the emotion categories corresponding to each of the event keywords and each of the corresponding event scores among the categories; and (b) the computing device, among each of the event keywords, a first condition in which each of the emotion categories corresponding to each of the event keywords corresponds to a preset negative emotion category, and each of the event scores is greater than or equal to a preset first threshold. Select a first specific event keyword to a z-th specific event keyword that simultaneously satisfies the corresponding second conditions, and select a first to a first specific event score corresponding to each of the first to the z-th specific event keywords. A method including providing basic training content for lowering z specific event scores below the 2_1th threshold to the 2_zth threshold, respectively, is disclosed.

As an example, (c) the x-th specific event score, which is at least one of the first specific event score to the z-th specific event score corresponding to each of the first specific event keyword to the z-th specific event keyword, is the 2_1 threshold. to the 2_z threshold, if it is not lowered below the 2_x threshold corresponding to the Additionally comprising the step of providing additional training content that changes at least some of the place information, the time information, and the opponent information to lower the xth specific event score below the 2_xth threshold. A characterized method is disclosed.

As an example, in step (b), the computing device selects each of the first specific event keyword to the zth specific event keyword among the first negative episode group to the mth negative episode group. Each of the z-th specific event keywords is grouped and managed into negative episode groups corresponding to each, and the k_1-th specific event keyword included in the k-th negative episode group, which is any one of the first negative episode group to the m-th negative episode group. A method is disclosed, characterized in that providing training content for lowering the k_1th specific event score to the k_nkth specific event score corresponding to each of the k_nk specific event keywords to below the 2_k_1 threshold to the 2_k_nk threshold, respectively, as the basic training content. do.

As an example, (d) the k_yk-th specific event score, which is at least one of the k_1-th specific event score to the k_nk-th specific event score corresponding to each of the k_1-th specific event keyword to the k_nk-th specific event keyword, is set to the 2_k_1 threshold. to the 2_k_nk threshold, if it is not lowered below the 2_k_yk threshold corresponding to the k_yk specific event score, the computing device, at least some of location information, time information, and counterpart information for the k_yk specific event keyword. Additionally comprising the step of providing additional training content that changes at least some of the location information, the time information, and the opponent information to lower the k_yk specific event score below the 2_k_yk threshold. A characterized method is disclosed.

As an example, in step (b), training to lower each of the 1_1 specific event score to the 1_n1 specific event score corresponding to each of the 1_1 specific event keyword to the 1_n1 specific event keyword below the 2_1_1 threshold to the 2_1_n1 threshold. a process for providing content as the basic training content; Providing training content for lowering each of the m_1th specific event score to the m_nmth specific event score corresponding to each of the to m_1th specific event keyword to the m_nmth specific event keyword to below the 2_m_1th threshold to the 2_m_nmth threshold as the basic training content. Process; and after step (b), the 1_y1 specific event score, which is at least one of the 1_1 specific event score and the 1_n1 specific event score, is the 1_y1 specific event score among the 2_1_1 threshold and the 2_1_n1 threshold. A process of determining that the specific event score is not lowered below the 2_1_y1 threshold corresponding to the specific event score; The m_ym specific event score, which is at least one of the m_1th specific event score to the m_nmth specific event score, is not lowered below the 2_m_ym threshold corresponding to the m_ymth specific event score among the 2_m_1 to the 2_m_nm thresholds. After performing the process of determining that it is not, the computing device additionally acquires at least some of location information, time information, and counterpart information for each of the 1_y1-th specific event score to the m_ym-th specific event score, Additional training using training content in which at least some of the place information, time information, and opponent information are changed to lower each of the 1_y1 specific event score to the m_ym specific event score below the 2_1_y1 threshold to the 2_m_ym threshold. A method characterized by providing content as content is disclosed.

As an example, in step (a), each of the emotion categories corresponding to each of the event keywords and each of the event scores corresponding thereto are (i) feedback information input from the user, (ii) from at least one image sensor. at least some of the user's facial expressions and actions obtained, (iii) at least some of the user's voice volume and voice tone obtained from at least one voice sensor, and (iv) at least some of the biometric information obtained from the user. A method characterized by calculation using reference is disclosed.

As an example, in step (b), the computing device is in a keyword exposure mode that exposes at least some of (i) at least one of the first specific event keyword to the zth specific event keyword on the basic training content - The keyword exposure mode is characterized in that it provides a visual effect that causes at least some of the first specific event keyword to the zth specific event keyword to be moved from the first area to the second area on the screen -, and (ii) ) At least a portion of the first specific event keyword to the zth specific event keyword is a negative episode corresponding to each of the first specific event keyword to the zth specific event keyword among the first negative episode group to the mth negative episode group. An episode group exposure mode that groups into groups and exposes at least a portion of the grouped negative episode groups - the episode group exposure mode includes a k-th negative episode group that is at least part of the first negative episode group to the m-th negative episode group. At least some of the k_1th specific event keywords to the k_nkth specific event keywords included in are provided with a visual effect that causes them to move from a third area to a fourth area on the screen, A method is disclosed, characterized in that the basic training content is provided according to at least some of the keyword exposure mode and the episode group exposure mode.

As an example, the computing device includes a learning device, and before step (a), the computing device includes: (i) at least one learning episode information obtained from the user, a learning event keyword belonging to the learning episode information; Each of the emotion categories for learning and each of the event scores for learning corresponding thereto, (ii) at least one other episode information for learning acquired from another user having a similarity to the user and a preset third threshold or more, and the other episode information for learning each of the other emotion categories for learning corresponding to each of the other event keywords for learning and each other event score for learning corresponding thereto, (iii) the user receives at least one of the visual features for learning and the auditory features for learning included in the basic training content for learning; After receiving a portion, information about whether the first event score for learning or the hth event score for learning corresponding to each of the first event keyword for learning or the hth event keyword for learning is lowered below the 2_1th threshold for learning or the 2_hth threshold for learning. , (iv) After the other user is provided with at least some of the other visual features for learning and the other auditory features for learning included in other basic training content for learning, the first other event keyword for learning to the ith other event keyword for learning, respectively. Perform learning by inputting at least some of the information about whether the first learning event score or the i th event score for learning corresponding to is lowered below the 2_1 other threshold for learning or the 2_i other threshold for learning into the learning device, , After step (a), the computing device causes the learning device to configure the basic training content including at least some of a specific visual feature and a specific auditory feature, and configure the basic training content to include the basic training content. The user obtains the predicted improvement when provided, and after step (b), (e) the computing device determines the difference between the actual improvement obtained from the user and the predicted improvement. A method is disclosed that further includes the step of performing backpropagation using a loss.

According to another aspect of the present invention, an apparatus for providing training content to a user with reference to at least one event keyword, comprising: at least one memory storing instructions; and at least one processor configured to execute the instructions, wherein the processor is configured to: (I) when at least one event keyword is input from the user, select each emotion category corresponding to each of the event keywords among all emotion categories; and a process for mapping each event score corresponding thereto; and (II) among each of the event keywords, a first condition in which each of the emotion categories corresponding to each of the event keywords corresponds to a preset negative emotion category, and a second condition in which each of the event scores corresponds to a preset first threshold or more. Select a first specific event keyword to a z-th specific event keyword that simultaneously satisfies the conditions, and select a first specific event score to a z-th specific event score corresponding to each of the first specific event keyword to the z-th specific event keyword. A computing device that performs a process of providing basic training content to lower the 2_1 threshold to the 2_z threshold, respectively, is disclosed.

As an example, (III) the x-th specific event score, which is at least one of the first specific event score to the z-th specific event score corresponding to each of the first specific event keyword to the z-th specific event keyword, is the 2_1 threshold. to the 2_z threshold, if it is not lowered below the 2_x threshold corresponding to the Additionally performing a process of obtaining additional training content by changing at least some of the location information, the time information, and the opponent information to lower the xth specific event score below the 2_xth threshold. A computing device is disclosed.

As an example, in the process (II), the processor converts each of the first specific event keyword to the z-th specific event keyword into the first specific event keyword to the m-th negative episode group among the first to m-th negative episode groups. It is managed by grouping into negative episode groups corresponding to each of the z-th specific event keywords, and includes the k_1-th specific event keyword to the k-th negative episode group, which is any one of the first negative episode group to the m-th negative episode group. A computing device is provided, as the basic training content, for lowering the k_1th specific event score to the k_nkth specific event score corresponding to each of the k_nk specific event keywords to below the 2_k_1 threshold to the 2_k_nk threshold, respectively. do.

As an example, (IV) the k_yk-th specific event score, which is at least one of the k_1-th specific event score to the k_nk-th specific event score corresponding to each of the k_1-th specific event keyword to the k_nk-th specific event keyword, is set to the 2_k_1 threshold. to the 2_k_nk threshold, if it is not lowered below the 2_k_yk threshold corresponding to the k_yk specific event score, the processor stores at least some of location information, time information, and opponent information for the k_yk specific event keyword. Additionally performing a process of obtaining additional training content that changes at least some of the location information, the time information, and the opponent information to lower the k_yk specific event score below the 2_k_yk threshold. A computing device is disclosed.

As an example, in the process (II), training to lower each of the 1_1 specific event score to the 1_n1 specific event score corresponding to each of the 1_1 specific event keyword to the 1_n1 specific event keyword below the 2_1_1 threshold to the 2_1_n1 threshold. a process for providing content as the basic training content; Providing training content for lowering each of the m_1th specific event score to the m_nmth specific event score corresponding to each of the to m_1th specific event keyword to the m_nmth specific event keyword to below the 2_m_1th threshold to the 2_m_nmth threshold as the basic training content. process; and after the process (II), the 1_y1 specific event score, which is at least one of the 1_1 specific event score and the 1_n1 specific event score, is the 1_y1 specific event score among the 2_1_1 threshold and the 2_1_n1 threshold. A process of determining that the specific event score is not lowered below the 2_1_y1 threshold corresponding to the specific event score; The m_ym specific event score, which is at least one of the m_1th specific event score to the m_nmth specific event score, is not lowered below the 2_m_ym threshold corresponding to the m_ymth specific event score among the 2_m_1 to the 2_m_nm thresholds. After performing the process of determining that it is not, the processor additionally obtains at least some of location information, time information, and opponent information for each of the 1_y1-th specific event score to the m_ym-th specific event score, and Additional training content in which at least some of the location information, the time information, and the opponent information are changed to lower each of the 1_y1 specific event score to the m_ym specific event score below the 2_1_y1 threshold to the 2_m_ym threshold. A computing device characterized in that it provides as is disclosed.

As an example, in the process (I), each of the emotion categories corresponding to each of the event keywords and each of the event scores corresponding thereto are (i) feedback information input from the user, (ii) from at least one image sensor. at least some of the user's facial expressions and actions obtained, (iii) at least some of the user's voice volume and voice tone obtained from at least one voice sensor, and (iv) at least some of the biometric information obtained from the user. A computing device characterized in that calculation is made by reference is disclosed.

As an example, in the process (II), the processor is configured to, on the basic training content, (i) a keyword exposure mode to expose at least some of the at least one first specific event keyword to the zth specific event keyword - the The keyword exposure mode is characterized by providing a visual effect that causes at least some of the first specific event keyword to the zth specific event keyword to be moved from the first area to the second area on the screen -, and (ii) At least a portion of the first specific event keyword to the z-th specific event keyword is a negative episode group corresponding to each of the first specific event keyword to the z-th specific event keyword among the first negative episode group to the m-th negative episode group. An episode group exposure mode that groups and exposes at least a portion of the grouped negative episode groups - the episode group exposure mode is performed on the kth negative episode group that is at least some of the first negative episode group to the mth negative episode group. At least some of the included k_1-th specific event keywords to k_nk-th specific event keywords are characterized in that they provide a visual effect that causes them to move from a third area to a fourth area on the screen, and at least some of the keywords are provided. A computing device is disclosed, characterized in that it provides the basic training content according to at least some of the exposure mode and the episodic group exposure mode.

As an example, the processor includes a learning device, and before the process (I), the processor includes: (i) at least one learning episode information obtained from the user, each of the learning event keywords belonging to the learning episode information; each of the corresponding emotion categories for learning and each of the event scores for learning corresponding thereto, (ii) at least one other episode information for learning obtained from another user having similarity with the user and a preset third threshold or more, belonging to the other episode information for learning; each other emotion category for learning that corresponds to each other event keyword for learning and each other event score for learning corresponding thereto, (iii) the user uses at least some of the visual features for learning and auditory features for learning included in the basic training content for learning; After being provided, information on whether the first event score for learning or the hth event score for learning corresponding to each of the first event keyword for learning or the hth event keyword for learning is lowered below the 2_1th threshold for learning or the 2_hth threshold for learning, ( iv) After the other user has been provided with at least some of the other visual features for learning and the other auditory features for learning included in other basic training content for learning, the other user responds to each of the first other event keyword for learning and the i other event keyword for learning. Perform learning by inputting at least part of the information about whether the first learning event score or the learning i th event score is lowered below the learning 2_1 learning threshold or the learning 2_i other threshold to the learning device, (I) After the process, the processor causes the learning device to construct the basic training content including at least some of specific visual features and specific auditory features, and provide the basic training content to the user. obtain the predicted improvement when received, and after the process (II), (V) the processor uses a loss determined with reference to the difference between the actual improvement obtained from the user and the predicted improvement. A computing device is disclosed that further performs a process to perform backpropagation.

In the present invention, when at least one event keyword is input from the user, each emotion category corresponding to each event keyword and each corresponding event score are mapped among all emotion categories, and each emotion category corresponding to each event keyword is preset. After checking whether the first condition and the event score corresponding to the negative emotion category simultaneously satisfy the second condition corresponding to a preset first threshold or more, the first specific event keyword to the z specific event keyword are selected, and the first specific event keyword is selected. There is an effect of providing basic training content for lowering the first specific event score to the zth specific event score corresponding to each of the specific event keyword to the zth specific event keyword to below the 2_1th threshold to the 2_zth threshold, respectively.

The following drawings attached for use in explaining embodiments of the present invention are only some of the embodiments of the present invention, and to those skilled in the art (hereinafter “those skilled in the art”), the invention Other drawings can be obtained based on these drawings without further work being done.
1 is a diagram schematically showing a computing device that provides training content to a user with reference to at least one event keyword, according to an embodiment of the present invention.
Figure 2 is a flowchart schematically showing a process performed in a method of providing training content to a user with reference to at least one event keyword, according to an embodiment of the present invention.
Figure 3 is a flowchart schematically showing additional processes performed in a method of providing training content to a user with reference to at least one event keyword, according to an embodiment of the present invention.
Figure 4 is a diagram illustrating examples of event keywords, emotion categories, negative episode groups, negative emotion categories, and event scores, according to an embodiment of the present invention.
Figures 5A and 5B are diagrams showing examples of keyword exposure mode and episode group exposure mode, according to an embodiment of the present invention.
Figure 6 shows, according to an embodiment of the present invention, a learning device that calculates the predicted improvement when the user is provided with basic training content and calculates the difference between the actual improvement obtained from the user and the predicted improvement. This is a drawing showing an example.

The detailed description of the present invention described below refers to the accompanying drawings, which show by way of example specific embodiments in which the present invention may be practiced to make clear the objectives, technical solutions and advantages of the present invention. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention.

Additionally, throughout the description and claims, the word “comprise” and variations thereof are not intended to exclude other technical features, attachments, components or steps. Other objects, advantages and features of the invention will appear to those skilled in the art, partly from this description and partly from practice of the invention. The examples and drawings below are provided by way of example and are not intended to limit the invention.

Moreover, the present invention encompasses all possible combinations of the embodiments shown herein. It should be understood that the various embodiments of the present invention are different from one another but are not necessarily mutually exclusive. For example, specific shapes, structures and characteristics described herein with respect to one embodiment may be implemented in other embodiments without departing from the spirit and scope of the invention. Additionally, it should be understood that the location or arrangement of individual components within each disclosed embodiment may be changed without departing from the spirit and scope of the invention. Accordingly, the detailed description that follows is not intended to be taken in a limiting sense, and the scope of the invention is limited only by the appended claims, together with all equivalents to what those claims assert, if properly described. Similar reference numbers in the drawings refer to identical or similar functions across various aspects.

Hereinafter, in order to enable those skilled in the art to easily practice the present invention, preferred embodiments of the present invention will be described in detail with reference to the attached drawings.

1 is a diagram schematically showing a computing device that provides training content to a user with reference to at least one event keyword, according to an embodiment of the present invention.

As shown in FIG. 1, the computing device 100 that provides training content to a user with reference to at least one event keyword of the present invention may include a memory 110, a processor 120, and a display 130. You can.

The memory 110 of the computing device 100, which provides training content to the user with reference to at least one event keyword, may store instructions to be performed by the processor 120. Specifically, the memory 110 for providing training content Code generated for the purpose of causing computing device 100 to function in a specific manner may be stored in computer-usable or computer-readable memory capable of being directed to a computer or other programmable data processing equipment. Instructions may perform processes to execute functions described in the specification of the present invention.

In addition, the processor 120 of the computing device 100 for providing training content has a hardware configuration such as a Micro Processing Unit (MPU) or Central Processing Unit (CPU), cache memory, and data bus. may include. In addition, it may further include an operating system and software configuration of an application that performs a specific purpose.

Additionally, the computing device 100 may further include a display 130 to provide training content. That is, the computing device 100 may be implemented in a form such as an HMD.

Additionally, the computing device 100 for providing training content may be linked to a database (not shown). Here, the database (not shown) is a flash memory type, hard disk type, multimedia card micro type, or card type memory (for example, SD or XD memory). , RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (ReadOnly Memory, ROM), EEPROM (Electrically Erasable Programmable ReadOnly Memory), PROM (Programmable ReadOnly Memory), magnetic memory, magnetic disk, and optical disk. It may include at least one type of storage medium, but is not limited to this and may include any medium capable of storing data. In addition, the database (not shown) is installed separately from the computing device 100 for providing training content, or, alternatively, is installed inside the computing device 100 for providing training content to transmit or receive data. may be recorded, or, unlike shown, may be implemented separately into two or more parts, which may vary depending on the implementation conditions of the invention.

Additionally, the computing device 100 may include a kiosk (not shown) for providing basic training content and/or additional training content to the user, and may include a head mounted display (HMD), but is not limited thereto. . Additionally, the basic training content and/or additional training content may be virtual reality content, but is not limited thereto.

Figure 2 is a flowchart schematically showing a process performed in a method of providing training content to a user with reference to at least one event keyword, according to an embodiment of the present invention.

Referring to FIG. 2, in the first step, when at least one event keyword is input by the user, the processor 120 maps each emotion category and each corresponding event score corresponding to each event keyword among all emotion categories ( S210) You can. This allows the user to recall events in their head that made them feel bad or depressed for a certain period of time and input the words that come to mind related to the events one by one, so that so-called event keywords can be entered, but it is not limited to this.

For reference, each emotion category corresponding to each event keyword and each corresponding event score include (i) feedback information input from the user, (ii) at least some of the user's facial expressions and actions obtained from at least one image sensor, (iii) at least part of the user's voice volume and voice tone obtained from at least one voice sensor, and (iv) at least part of the biometric information obtained from the user.

Thereafter, in the second step, the processor 120 determines that, among each of the event keywords, each of the emotion categories corresponding to each of the event keywords corresponds to a preset negative emotion category, and each of the first conditions and event scores is equal to or higher than a preset first threshold. Select a first specific event keyword to a z-th specific event keyword that simultaneously satisfies the corresponding second condition, and select a first specific event score to a z-th specific event corresponding to each of the first specific event keyword to the z-th specific event keyword. Basic training content for lowering the score below the 2_1th threshold to the 2_zth threshold may be provided (S220a).

That is, some of the plurality of event keywords may fall into the negative emotion category, and others may fall into the positive emotion category. Here, the first condition is to check whether it falls into a preset negative emotion category. For example, assuming that the entire emotion category is “joy, anger, sadness, joy, love, hate, greed,” the first condition is Satisfied emotion categories may be “No (Seongnam), Ae (Sadness), Oh (Hate), and Greed (Greed).”

Additionally, the second condition is to check whether the event score is greater than or equal to a preset first threshold. It falls into the negative emotion category, but if the event score is below the first threshold, the negative emotion is at a weak level and does not fall under the second condition.

Here, saying that the event score is equal to or higher than the preset first threshold means that the intensity of emotion for the corresponding emotional category is equal to or higher than the first threshold.

In conclusion, selecting the first specific event keyword to the z specific event keyword that simultaneously satisfies the first condition and the second condition means that the entire negative emotion category "No (Seongnam), Ae (sadness), Oh (hate) ), this may mean selecting only some event keywords that belong to at least some negative emotion categories where the intensity of emotion for the corresponding emotion category is greater than the first threshold. Here, z is an integer greater than or equal to 1.

That is, basic training content is provided to lower the first to zth specific event scores corresponding to each of the first to zth specific event keywords below the 2_1th to 2_zth thresholds, respectively. Here, the 2_1 threshold to the 2_z threshold may be the same as the previously mentioned first threshold or may be a value greater than the first threshold, and the 2_1 threshold to the 2_z threshold may all be the same value or may be different values.

In addition, the basic training content is content for lowering the first specific event score to the zth specific event score, and may be content that induces the user to gradually relieve the stress filled in the user's head, or may be a movie or game that the user likes. It may be content related to the first specific event keyword to the zth specific event keyword, and may be pre-stored customized content, or it may be content about the movement information of the first specific event keyword to the zth specific event keyword itself. , but is not limited to this.

Figure 3 is a flowchart schematically showing additional processes performed in a method of providing training content to a user with reference to at least one event keyword, according to an embodiment of the present invention.

After S220a, the processor 120 determines that the If the 2_z threshold is not lowered below the 2_x threshold corresponding to the In order to reduce to below the 2_x threshold, additional training content in which at least some of the location information, time information, and counterpart information are changed may be provided (S230a).

In other words, if the specific event score corresponding to a specific event keyword is not lowered despite providing basic training content, additional training content is provided.

For example, let's take a case where a user goes out on a blind date and has a good time, but is embarrassed by farting and is depressed because the blind date ends badly.

The keyword "farting" entered by the user is one of the event keywords that satisfies the first and second conditions, and is one of the event keywords for which the emotional sensitivity of the negative emotion category is judged to be higher than the first threshold, and the negative emotion related to "farting" is If it is detected that the emotion intensity is still not lowered below the 2_x threshold even though basic training content to reduce the emotion intensity for the emotion category is provided, the x specific event score corresponding to the x specific event keyword is lowered below the 2_x threshold. For this purpose, it is possible to provide additional training content that changes at least some of the location information, time information, and opponent information. For example, let's assume that the negative emotion category corresponding to "farting" is "sorrow" and that the event score corresponding to "farting" is 0.9. For reference, let's assume that the preset 2_x threshold is 0.5.

Despite providing basic training content to lower the event score corresponding to "farting", 0.9, to below the preset 2_x threshold of 0.5, if the event score corresponding to "farting" is not lowered to below 0.5, " It provides additional training content that changes at least some of the location information, time information, and opponent information related to “farting.”

For example, the place where the blind date took place was a coffee shop, but "farting" may leave a bad memory of that coffee shop, so you can provide additional training content by changing the place where the blind date takes place to a boat where farting noises are less audible. there is. Additionally, the time of the blind date can be set to change to sunset time to provide a nice view, and the blind date partner can change into an easy-going person and be provided as additional training content.

In this way, additional training content is provided by changing at least some of the location information, time information, and counterpart information related to blind dates ruined by "farting", thereby reducing the event score of 0.9 corresponding to "farting", which was not lowered below 0.5, to 0.5. This is to encourage you to lower it below.

Meanwhile, referring again to FIG. 2, the processor 120 groups and manages each of the first to zth specific event keywords into the corresponding negative episode group among the first to mth negative episode groups. And, the k_1th specific event score to the k_nkth specific event corresponding to each of the k_1th specific event keyword to the k_nkth specific event keyword included in the kth negative episode group, which is any one of the first negative episode group to the mth negative episode group. Training content for lowering the score below the 2_k_1 threshold to the 2_k_nk threshold may be provided as basic training content (S220b).

S220a provides basic training content focused on the specific event keyword itself, and S220b provides basic training content focused on the negative episode group containing the specific event keyword.

This is explained in more detail as follows.

Figure 4 is a diagram illustrating examples of event keywords, emotion categories, negative episode groups, negative emotion categories, and event scores, according to an embodiment of the present invention.

Referring to Figure 4, the emotion category, negative episode group, negative emotion category, and event score corresponding to each event keyword are mapped.

Following the guidance of the computing device 100, the user can input thoughts that come to mind as event keywords, and in this case, in the order recorded in the “event keywords” in FIG. 4, “blind date,” “farting,” and “disgrace.” , Let's assume that you entered "Busan", "bread", "mom", "pocket money", etc. At this time, as mentioned earlier, when entering "blind date", a smile is detected at the corner of the mouth, and the emotional category is obtained as "joy", and a smile so wide that the corners of the mouth touch the ears is detected. Thus, the event score, that is, the intensity of emotion, can be obtained as 0.8. Of course, it goes without saying that the emotion category and/or event score can be obtained by other methods mentioned above. Afterwards, when entering "farting" and "disgrace," the smile disappears from the corner of the mouth and the appearance of sighing is detected, and the emotional category is obtained as "sadness," and if tears form at the corners of the eyes, the event score is In other words, the intensity of emotion can be obtained as 0.9. Additionally, event keywords such as “Busan,” “bread,” “mom,” and “pocket money” could also be processed in the same way. However, various methods can be assumed for classifying each event keyword into any group from the first negative episode group to the third negative episode group. For example, the user may classify each event keyword according to the guidance of the computing device 100. However, it may also be possible to automatically classify through dictionary data obtained from the user (for example, survey data or natural language processing data for digital pinotype data, etc.). Additionally, in the case of such automatic classification, it may be possible to learn through a learning device to increase classification accuracy.

In this way, by grouping a plurality of event keywords into one of the negative episode groups, basic training content is provided to lower the plurality of event keywords included in the negative episode group below the threshold.

The following is the same as S220a, so description is omitted.

Referring again to FIG. 3, after S220b, the processor 120 generates a k_yk-th specific event score that is at least one of the k_1-th specific event score to the k_nk-th specific event score corresponding to each of the k_1-th specific event keyword to the k_nk-th specific event keyword. If the event score is not lowered below the 2_k_yk threshold corresponding to the k_yk specific event score among the 2_k_1 threshold to the 2_k_nk threshold, at least some of the location information, time information, and opponent information for the k_yk specific event keyword are additionally stored. In order to obtain and lower the k_yk specific event score below the 2_k_yk threshold, additional training content in which at least some of the location information, time information, and opponent information are changed may be provided (S230b).

As with S230a described above, even though basic training content is provided for each negative episode group by grouping by negative episode group, additional training content is provided if the specific event score of the negative episode group containing a specific event keyword is not lowered. It is done.

As in S230a, additional training content is provided by changing at least some of the place information, time information, and counterpart information corresponding to a specific event keyword. For reference, S230b features additional training content for each negative episode group by focusing on the group. The subsequent process is the same as S230a, so description is omitted.

Meanwhile, in S220a, training content for lowering each of the 1_1 specific event score to the 1_n1 specific event score corresponding to each of the 1_1 specific event keyword to the 1_n1 specific event keyword to below the 2_1_1 threshold to the 2_1_n1 threshold is basic training content. The process provided as; A process of providing training content for lowering each of the m_1th specific event scores to the m_nmth specific event scores corresponding to each of the to m_1th specific event keywords to the m_nmth specific event keywords below the 2_m_1th to 2_m_nmth thresholds as basic training content. ; and after S220a, the 1_y1 specific event score, which is at least one of the 1_1 specific event score to the 1_n1 specific event score, is less than or equal to the 2_1_y1 threshold corresponding to the 1_y1 specific event score among the 2_1_1 to 2_1_n1 thresholds. The process of determining that it is not lowered to; A process of determining that the m_ym-th specific event score, which is at least one of the m_1-th to m_nm-th specific event scores, is not lowered below the 2_m_ym-th threshold corresponding to the m_ym-th specific event score among the 2_m_1 to 2_m_nm thresholds. After performing ;, additionally obtain at least some of the place information, time information, and opponent information for each of the 1_y1-th specific event score to the m_ym-th specific event score, and obtain each of the 1_y1-th specific event score to the m_ym-th specific event score. Training content in which at least some of the place information, time information, and opponent information are changed to lower the 2_1_y1 threshold to the 2_m_ym threshold may be provided as additional training content.

Figures 5A and 5B are diagrams showing examples of keyword exposure mode and episode group exposure mode, according to an embodiment of the present invention.

At least some of the keyword exposure mode and episode group exposure mode may be provided on the basic training content.

First, the keyword exposure mode exposes at least some of at least one first specific event keyword to zth specific event keyword. Here, a visual effect may be provided to cause at least some of the first to z-th specific event keywords to be moved from the first area to the second area on the screen.

Meanwhile, the episode group exposure mode corresponds to at least some of the first to z-th specific event keywords to each of the first to z-th specific event keywords among the first to m-th negative episode groups. grouping into negative episode groups, and exposing at least some of the grouped negative episode groups. Here, at least some of the k_1th specific event keyword to k_nkth specific event keyword included in the kth negative episode group, which is at least part of the first negative episode group to the mth negative episode group, moves from the third area to the fourth area on the screen. It is possible to provide the desired visual effect.

Referring to Figure 5a, it can be seen that the event keyword "farting" included in the first negative episode group and the event keyword "bread" included in the second negative episode group flow from the top to the bottom of the screen. In other words, the keyword exposure mode can provide a visual effect for each event keyword. A visual effect of several keywords flowing simultaneously on the screen is shown, but this is not limited to this, and a visual effect of a single keyword flowing down may also be provided.

Additionally, referring to 5b, it can be seen that the event keywords “farting” and “disgrace” included in the first negative episode group are grouped and flow from the top to the bottom of the screen. In other words, the episode group exposure mode can provide a visual effect to event keywords included in the grouped group.

For reference, in FIGS. 5A and 5B, each keyword or group of keywords is expressed as flowing in a stream, but various examples such as being blown away by the wind or broken by a hammer can be assumed, so it is not limited to this.

Meanwhile, the computing device 100 may include a learning device 140.

Figure 6 shows that, according to an embodiment of the present invention, the learning device 140 calculates the predicted improvement when the user is provided with basic training content, and refers to the difference between the actual improvement obtained from the user and the predicted improvement. This is a diagram showing an example of performing learning.

As shown in FIG. 6, the computing device 100 includes (i) at least one learning episode information acquired from the user, each learning emotion category corresponding to each learning event keyword belonging to the learning episode information, and a learning event score corresponding thereto; (ii) at least one other episode information for learning acquired from another user having similarity with the user and a preset third threshold or more, each other emotion category for learning corresponding to each other event keyword belonging to the other episode information for learning, and the other emotion categories therefor; Each of the corresponding other event scores for learning, (iii) After the user is provided with at least some of the visual features for learning and the auditory features for learning included in the basic training content for learning, each of the first event keyword for learning to the h th event keyword for learning Information on whether the first event score for learning or the h event score for learning is lowered below the 2_1 threshold for learning or the 2_h threshold for learning, (iv) other visuals for learning included in other basic training content for learning by other users After receiving at least some of the characteristic elements and other auditory feature elements for learning, the first other event score for learning or the ith other event score for learning corresponding to each of the first other event keyword for learning or the ith other event keyword for learning is the third event for learning. At least some of the information on whether the 2_1 other threshold or the 2_i other threshold for learning is lowered or lower may be input to the learning device 140 to perform learning.

Thereafter, the computing device 100 causes the learning device 140 to configure basic training content including at least some of the specific visual features and specific auditory features, and to configure basic training content when the user receives the basic training content. Prediction improvement can be obtained. Here, the specific visual feature and the specific auditory feature may be features of the location, time, and at least some of the opponents appearing in the basic training content, but are not limited thereto.

Thereafter, the computing device 100 may perform learning by repeating the process of performing backpropagation using a loss determined with reference to the difference between the actual improvement obtained from the user and the predicted improvement.

The above content may be characterized in that a user wears an HMD and a certain wearable device, and the HMD and the wearable device are linked with the computing device.

Additionally, the embodiments according to the present invention described above may be implemented in the form of program instructions that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on the computer-readable recording medium may be specially designed and configured for the present invention, or may be known and usable by those skilled in the computer software field. Examples of computer-readable recording media include hard disks, magnetic media such as floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magneto-optical media such as floptical disks. , and hardware devices specifically configured to store and perform program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include not only machine language code such as that created by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules to perform processing according to the invention and vice versa.

In the above, the present invention has been described with specific details such as specific components and limited embodiments and drawings, but this is only provided to facilitate a more general understanding of the present invention, and the present invention is not limited to the above embodiments. , a person skilled in the art to which the present invention pertains can make various modifications and variations from this description.

Therefore, the spirit of the present invention should not be limited to the above-described embodiments, and the scope of the patent claims described below as well as all modifications equivalent to or equivalent to the scope of the claims fall within the scope of the spirit of the present invention. They will say they do it.

Claims (16)

In a method for providing training content to a user with reference to at least one event keyword,
(a) When at least one event keyword is input from the user, the computing device maps each of the emotion categories corresponding to each of the event keywords and each of the corresponding event scores among all emotion categories;
(b) The computing device is configured to, among each of the event keywords, a first condition in which each of the emotion categories corresponding to each of the event keywords corresponds to a preset negative emotion category and each of the event scores is greater than or equal to a preset first threshold. Select a first specific event keyword to a z-th specific event keyword that simultaneously satisfies the corresponding second condition, and first to a z-th specific event score corresponding to each of the first specific event keyword to the z-th specific event keyword. Providing basic training content for lowering a specific event score below the 2_1th threshold to the 2_zth threshold, respectively; and
(c) the x-th specific event score, which is at least one of the first specific event score to the z-th specific event score corresponding to each of the first specific event keyword to the z-th specific event keyword, is between the 2_1 threshold and the If the 2_z threshold is not lowered below the 2_x threshold corresponding to the x-th specific event score, the computing device additionally acquires at least some of location information, time information, and counterpart information for the x-th specific event keyword. and providing additional training content in which at least some of the place information, the time information, and the opponent information are changed to lower the xth specific event score below the 2_xth threshold;
How to include . delete In a method for providing training content to a user with reference to at least one event keyword,
(a) When at least one event keyword is input from the user, the computing device maps each of the emotion categories corresponding to each of the event keywords and each of the corresponding event scores among all emotion categories; and
(b) The computing device is configured to, among each of the event keywords, a first condition in which each of the emotion categories corresponding to each of the event keywords corresponds to a preset negative emotion category and each of the event scores is greater than or equal to a preset first threshold. Select a first specific event keyword to a z-th specific event keyword that simultaneously satisfies the corresponding second condition, and first to a z-th specific event score corresponding to each of the first specific event keyword to the z-th specific event keyword. Providing basic training content to lower the specific event score below the 2_1th threshold to the 2_zth threshold, respectively,
In step (b) above,
The computing device selects each of the first specific event keyword to the zth specific event keyword to correspond to each of the first specific event keyword to the zth specific event keyword among the first negative episode group to the mth negative episode group. It is managed by grouping into a negative episode group, and corresponds to each of the k_1th specific event keyword to the k_nkth specific event keyword included in the kth negative episode group, which is any one of the first negative episode group to the mth negative episode group. A method characterized in that providing training content for lowering the k_1 specific event score to the k_nk specific event score below the 2_k_1 threshold to the 2_k_nk threshold, respectively, as the basic training content. According to paragraph 3,
(d) the k_yk-th specific event score, which is at least one of the k_1-th specific event score to the k_nk-th specific event score corresponding to each of the k_1-th specific event keyword to the k_nk-th specific event keyword, is between the 2_k_1 threshold and the If the 2_k_nk threshold is not lowered below the 2_k_yk threshold corresponding to the k_yk specific event score, the computing device additionally obtains at least some of location information, time information, and counterpart information for the k_yk specific event keyword. And, in order to lower the k_yk specific event score below the 2_k_yk threshold, providing additional training content in which at least some of the location information, the time information, and the opponent information are changed, characterized in that it further comprises a step of providing additional training content. method. According to paragraph 3,
In step (b) above,
A process of providing training content for lowering each of the 1_1 specific event score to the 1_n1 specific event score corresponding to each of the 1_1 specific event keyword to the 1_n1 specific event keyword to below the 2_1_1 threshold to the 2_1_n1 threshold as the basic training content. ; Providing training content for lowering each of the m_1th specific event score to the m_nmth specific event score corresponding to each of the to m_1th specific event keyword to the m_nmth specific event keyword to below the 2_m_1th threshold to the 2_m_nmth threshold as the basic training content. perform a process;
After step (b) above,
The 1_y1 specific event score, which is at least one of the 1_1 specific event score and the 1_n1 specific event score, is not lowered below the 2_1_y1 threshold corresponding to the 1_y1 specific event score among the 2_1_1 threshold and the 2_1_n1 threshold. the process of determining that The m_ym specific event score, which is at least one of the m_1th specific event score to the m_nmth specific event score, is not lowered below the 2_m_ym threshold corresponding to the m_ymth specific event score among the 2_m_1 to the 2_m_nm thresholds. After performing a process that determines that
The computing device additionally acquires at least some of location information, time information, and opponent information for each of the 1_y1 specific event score to the m_ym specific event score, and the 1_y1 specific event score to the m_ym specific event. A method characterized in that providing training content in which at least some of the location information, the time information, and the opponent information are changed as additional training content in order to lower each score from the 2_1_y1 threshold to the 2_m_ym threshold. In a method for providing training content to a user with reference to at least one event keyword,
(a) When at least one event keyword is input from the user, the computing device maps each of the emotion categories corresponding to each of the event keywords and each of the corresponding event scores among all emotion categories; and
(b) The computing device is configured to, among each of the event keywords, a first condition in which each of the emotion categories corresponding to each of the event keywords corresponds to a preset negative emotion category and each of the event scores is greater than or equal to a preset first threshold. Select a first specific event keyword to a z-th specific event keyword that simultaneously satisfies the corresponding second condition, and first to a z-th specific event score corresponding to each of the first specific event keyword to the z-th specific event keyword. Providing basic training content to lower the specific event score below the 2_1th threshold to the 2_zth threshold, respectively,
In step (a) above,
Each of the emotion categories corresponding to each of the event keywords and each of the event scores corresponding thereto include at least one of (i) feedback information input from the user, (ii) the user's facial expression and behavior obtained from at least one image sensor. A method characterized in that the calculation is made with reference to a portion, (iii) at least a portion of the user's voice volume and voice tone obtained from at least one voice sensor, and (iv) at least a portion of biometric information obtained from the user. . In a method for providing training content to a user with reference to at least one event keyword,
(a) When at least one event keyword is input from the user, the computing device maps each of the emotion categories corresponding to each of the event keywords and each of the corresponding event scores among all emotion categories; and
(b) The computing device is configured to, among each of the event keywords, a first condition in which each of the emotion categories corresponding to each of the event keywords corresponds to a preset negative emotion category and each of the event scores is greater than or equal to a preset first threshold. Select a first specific event keyword to a z-th specific event keyword that simultaneously satisfies the corresponding second condition, and first to a z-th specific event score corresponding to each of the first specific event keyword to the z-th specific event keyword. Providing basic training content to lower the specific event score below the 2_1th threshold to the 2_zth threshold, respectively,
In step (b) above,
The computing device is configured to display (i) at least a portion of the first specific event keyword to the z-th specific event keyword on the basic training content - a keyword exposure mode that exposes at least a portion of the first specific event keyword to the z-th specific event keyword. Characterized by providing a visual effect that causes at least some of the event keywords to the zth specific event keywords to be moved from a first area to a second area on the screen -, and (ii) the first specific event keywords to the zth specific event keywords. At least some of the z-specific event keywords are grouped into negative episode groups corresponding to each of the first to z-th specific event keywords among the first negative episode group to the m-th negative episode group, and the grouped negative episodes An episode group exposure mode that exposes at least part of the group - the episode group exposure mode includes the k_1th specific event keyword to the k_th negative episode group that is at least part of the first negative episode group to the mth negative episode group. k_nk - characterized in that it provides a visual effect that causes at least some of the specific event keywords to be moved from a third area to a fourth area on the screen - providing at least some of the keyword exposure mode and the episode group exposure mode. A method comprising providing basic training content according to at least part of the method. In a method for providing training content to a user with reference to at least one event keyword,
(a) When at least one event keyword is input from the user, the computing device maps each of the emotion categories corresponding to each of the event keywords and each of the corresponding event scores among all emotion categories; and
(b) The computing device is configured to, among each of the event keywords, a first condition in which each of the emotion categories corresponding to each of the event keywords corresponds to a preset negative emotion category and each of the event scores is greater than or equal to a preset first threshold. Select a first specific event keyword to a z-th specific event keyword that simultaneously satisfies the corresponding second condition, and first to a z-th specific event score corresponding to each of the first specific event keyword to the z-th specific event keyword. Providing basic training content to lower the specific event score below the 2_1th threshold to the 2_zth threshold, respectively,
The computing device includes a learning device,
Before step (a) above,
The computing device includes (i) at least one learning episode information acquired from the user, each learning emotion category corresponding to each learning event keyword belonging to the learning episode information, and each learning event score corresponding thereto, (ii) the learning episode information, At least one other-for-learning episode information acquired from another user having similarity with the user and a preset third threshold or more, each other-for-learning emotion category corresponding to each other-for-learning event keyword belonging to the other-for-learning episode information, and the other-for-learning emotion category corresponding thereto Each event score, (iii) after the user is provided with at least some of the visual features for learning and the auditory features for learning included in the basic training content for learning, each of the first event keyword for learning to the h th event keyword for learning Information on whether the first event score for learning or the h event score for learning is lowered below the 2_1 threshold for learning or the 2_h threshold for learning, (iv) other visual features for learning included in other basic training content for learning by the other user And after receiving at least some of the other auditory feature elements for learning, the first other event score for learning or the ith other event score for learning corresponding to each of the first other event keyword for learning or the ith other event keyword for learning is the second_1 other event score for learning. Perform learning by inputting at least some of the information on whether the threshold or the 2_i other threshold for learning is lowered to the learning device,
After step (a) above,
The computing device causes the learning device to configure the basic training content including at least some of specific visual features and specific auditory features, and predict improvement when the user is provided with the basic training content. to obtain,
After step (b) above,
(e) The method further comprising allowing the computing device to perform backpropagation using a loss determined with reference to the difference between the actual improvement obtained from the user and the predicted improvement. In an apparatus for providing training content to a user with reference to at least one event keyword,
at least one memory storing instructions; and
At least one processor configured to execute the instructions,
The processor may include: (I) when at least one event keyword is input from the user, a process of mapping each emotion category and each corresponding event score corresponding to each event keyword among all emotion categories; (II) Among each of the event keywords, a first condition in which each of the emotion categories corresponding to each of the event keywords corresponds to a preset negative emotion category, and a second condition in which each of the event scores corresponds to a preset first threshold or more. Select a first specific event keyword to a z-th specific event keyword that simultaneously satisfies, and set a first specific event score to a z-th specific event score corresponding to each of the first specific event keyword to the z-th specific event keyword, respectively. A process of providing basic training content to lower the 2_1 threshold to the 2_z threshold or lower; and (III) the x-th specific event score, which is at least one of the first specific event score to the z-th specific event score corresponding to each of the first specific event keyword to the z-th specific event keyword, is between the 2_1 threshold and the If the 2_z threshold is not lowered below the 2_x threshold corresponding to the x-th specific event score, the processor additionally acquires at least some of location information, time information, and counterpart information for the x-th specific event keyword. and providing additional training content in which at least some of the place information, the time information, and the opponent information are changed to lower the xth specific event score below the 2_xth threshold. delete In an apparatus for providing training content to a user with reference to at least one event keyword,
at least one memory storing instructions; and
At least one processor configured to execute the instructions,
The processor may include: (I) when at least one event keyword is input from the user, a process of mapping each emotion category and each corresponding event score corresponding to each event keyword among all emotion categories; and (II) among each of the event keywords, a first condition in which each of the emotion categories corresponding to each of the event keywords corresponds to a preset negative emotion category, and a second condition in which each of the event scores corresponds to a preset first threshold or more. Select a first specific event keyword to a z-th specific event keyword that simultaneously satisfies the conditions, and select a first specific event score to a z-th specific event score corresponding to each of the first specific event keyword to the z-th specific event keyword. A process of providing basic training content to lower the 2_1 threshold to the 2_z threshold, respectively;
In process (II) above,
The processor converts each of the first specific event keyword to the z-th specific event keyword into a negative episode corresponding to each of the first specific event keyword to the z-th specific event keyword among the first negative episode group to the m-th negative episode group. It is managed by grouping into episode groups, and the k_1th specific event keyword corresponding to each of the k_1th specific event keyword to the k_nkth specific event keyword included in the kth negative episode group, which is any one of the first negative episode group to the mth negative episode group. A computing device characterized in that it provides training content for lowering a specific event score to a k_nkth specific event score below the 2_k_1th threshold to the 2_k_nkth threshold, respectively, as the basic training content. According to clause 11,
(IV) The k_yk-th specific event score, which is at least one of the k_1-th specific event score and the k_nk-th specific event score corresponding to each of the k_1-th specific event keyword to the k_nk-th specific event keyword, is between the 2_k_1 threshold and the k_nk-th specific event score. If the 2_k_nk threshold is not lowered below the 2_k_yk threshold corresponding to the k_yk specific event score, the processor additionally obtains at least some of location information, time information, and opponent information for the k_yk specific event keyword, and , Computing characterized in that further performing a process of providing additional training content that changes at least some of the location information, the time information, and the opponent information in order to lower the k_th specific event score below the 2_k_yk threshold. Device. According to clause 11,
In process (II) above,
A process of providing training content for lowering each of the 1_1 specific event score to the 1_n1 specific event score corresponding to each of the 1_1 specific event keyword to the 1_n1 specific event keyword to below the 2_1_1 threshold to the 2_1_n1 threshold as the basic training content. ; Providing training content for lowering each of the m_1th specific event score to the m_nmth specific event score corresponding to each of the to m_1th specific event keyword to the m_nmth specific event keyword to below the 2_m_1th threshold to the 2_m_nmth threshold as the basic training content. perform a process;
After process (II) above,
The 1_y1 specific event score, which is at least one of the 1_1 specific event score and the 1_n1 specific event score, is not lowered below the 2_1_y1 threshold corresponding to the 1_y1 specific event score among the 2_1_1 threshold and the 2_1_n1 threshold. the process of determining that The m_ym specific event score, which is at least one of the m_1th specific event score to the m_nmth specific event score, is not lowered below the 2_m_ym threshold corresponding to the m_ymth specific event score among the 2_m_1 to the 2_m_nm thresholds. After performing a process that determines that
The processor additionally obtains at least some of location information, time information, and opponent information for each of the 1_y1 specific event score to the m_ym specific event score, and the 1_y1 specific event score to the m_ym specific event score. A computing device characterized in that it provides training content in which at least some of the location information, the time information, and the counterpart information are changed as additional training content in order to lower each of them below the 2_1_y1 threshold to the 2_m_ym threshold. In an apparatus for providing training content to a user with reference to at least one event keyword,
at least one memory storing instructions; and
At least one processor configured to execute the instructions,
The processor may include: (I) when at least one event keyword is input from the user, a process of mapping each emotion category and each corresponding event score corresponding to each event keyword among all emotion categories; and (II) among each of the event keywords, a first condition in which each of the emotion categories corresponding to each of the event keywords corresponds to a preset negative emotion category, and a second condition in which each of the event scores corresponds to a preset first threshold or more. Select a first specific event keyword to a z-th specific event keyword that simultaneously satisfies the conditions, and select a first specific event score to a z-th specific event score corresponding to each of the first specific event keyword to the z-th specific event keyword. A process of providing basic training content to lower the 2_1 threshold to the 2_z threshold, respectively;
In process (I) above,
Each of the emotion categories corresponding to each of the event keywords and each of the event scores corresponding thereto include at least one of (i) feedback information input from the user, (ii) the user's facial expression and behavior obtained from at least one image sensor. Computing characterized in that the calculation is made with reference to some, (iii) at least some of the user's voice volume and voice tone obtained from at least one voice sensor, and (iv) at least some of the biometric information obtained from the user. Device. In an apparatus for providing training content to a user with reference to at least one event keyword,
at least one memory storing instructions; and
At least one processor configured to execute the instructions,
The processor may include: (I) when at least one event keyword is input from the user, a process of mapping each emotion category and each corresponding event score corresponding to each event keyword among all emotion categories; and (II) among each of the event keywords, a first condition in which each of the emotion categories corresponding to each of the event keywords corresponds to a preset negative emotion category, and a second condition in which each of the event scores corresponds to a preset first threshold or more. Select a first specific event keyword to a z-th specific event keyword that simultaneously satisfies the conditions, and select a first specific event score to a z-th specific event score corresponding to each of the first specific event keyword to the z-th specific event keyword. A process of providing basic training content to lower the 2_1 threshold to the 2_z threshold, respectively;
In process (II) above,
The processor, a keyword exposure mode that exposes (i) at least some of the first specific event keyword to the zth specific event keyword on the basic training content - the keyword exposure mode is configured to expose the first specific event keyword Characterized by providing a visual effect that causes at least some of the keywords to the z-th specific event keywords to be moved from a first area to a second area on the screen -, and (ii) the first specific event keywords to the z-th specific event keywords. At least some of the specific event keywords are grouped into negative episode groups corresponding to each of the first to z-th specific event keywords among the first negative episode group to the m-th negative episode group, and the grouped negative episode group an episode group exposure mode that exposes at least a portion of - the episode group exposure mode includes the k_1th to k_nkth specific event keywords included in the kth negative episode group, which is at least part of the first negative episode group to the mth negative episode group. Characterized in that it provides a visual effect that causes at least some of the specific event keywords to be moved from a third area to a fourth area on the screen, and at least one of the keyword exposure mode and the episode group exposure mode. A computing device, according to some, providing said basic training content. In an apparatus for providing training content to a user with reference to at least one event keyword,
at least one memory storing instructions; and
At least one processor configured to execute the instructions,
The processor may include: (I) when at least one event keyword is input from the user, a process of mapping each emotion category and each corresponding event score corresponding to each event keyword among all emotion categories; and (II) among each of the event keywords, a first condition in which each of the emotion categories corresponding to each of the event keywords corresponds to a preset negative emotion category, and a second condition in which each of the event scores corresponds to a preset first threshold or more. Select a first specific event keyword to a z-th specific event keyword that simultaneously satisfies the conditions, and select a first specific event score to a z-th specific event score corresponding to each of the first specific event keyword to the z-th specific event keyword. A process of providing basic training content to lower the 2_1 threshold to the 2_z threshold, respectively;
The processor includes a learning device,
Prior to process (I) above,
The processor includes (i) at least one learning episode information obtained from the user, each learning emotion category corresponding to each learning event keyword belonging to the learning episode information, and each learning event score corresponding thereto, (ii) the user and at least one other episode information for learning acquired from another user having a similarity of more than a preset third threshold, each other emotion category for learning corresponding to each other event keyword belonging to the other episode information for learning, and other event for learning corresponding thereto. scores, respectively, (iii) after the user is provided with at least some of the visual features for learning and the auditory features for learning included in the basic training content for learning, the learning features corresponding to each of the first event keyword for learning to the h th event keyword for learning; Information on whether the first event score or the hth event score for learning is lowered below the 2_1th threshold for learning or the 2_hth threshold for learning, (iv) other visual features for learning included in other basic training content for learning by the other user, and After receiving at least some of the other auditory feature elements for learning, the first other event score for learning or the i th event score for learning corresponding to each of the first other event keyword for learning or the i th event keyword for learning is the second_1 other event score for learning. to 2_i for learning, perform learning by inputting at least some of the information on whether it is lowered below the other threshold to the learning device,
After process (I) above,
The processor causes the learning device to configure the basic training content including at least some of specific visual features and specific auditory features, and determine the degree of prediction improvement when the user is provided with the basic training content. to obtain it,
After process (II) above,
(V) The processor further performs a process of performing backpropagation using a loss determined with reference to the difference between the actual improvement obtained from the user and the predicted improvement.