A music-fused cognitive improvement method and system

Abstract

This invention discloses a method and system for cognitive enhancement through music integration. The method includes the following steps: collecting user information based on demographics and obtaining initial recommended music based on this information; obtaining corresponding human-computer interaction tasks based on the user's cognitive assessment results; pushing the human-computer interaction tasks to the user within the recommended music environment; updating the recommended music based on a joint analysis model and a Chmiel-Schubert model; and pushing the human-computer interaction tasks to the user again within the updated recommended music environment. This invention utilizes a music recommendation algorithm based on psychological theory and joint analysis to recommend music that users like and that maximizes cognitive enhancement based on objective data generated during the human-computer interaction process, thereby significantly improving the cognitive enhancement training effect.

Description

Technical Field

[0001] This invention relates to a cognitive enhancement method that integrates music, and also to a corresponding cognitive enhancement system, belonging to the field of healthcare information technology. Background Technology

[0002] According to estimates by the World Health Organization, by 2050, the global population aged 60 and over will reach 2 billion, making aging a new challenge facing the world. For older adults, increasing age is not only accompanied by a decline in physical function, but also often by a decline in cognitive function.

[0003] Existing research has shown that specially designed cognitive training can slow down or even reverse age-related cognitive decline. Moreover, cognitive training combined with music that the patient enjoys, compared to cognitive training alone, can effectively slow down the process of cognitive decline. Chinese invention application No. 202011112852.1 discloses a cognitive, music, and exercise-based intellectual training system, including a music library, an exercise library, a training module, a recording module, a recognition module, and a scoring module. The music library stores music, the exercise library stores tutorials for various exercises, the training module selects at least one tutorial from the exercise library and at least one style of music from the music library based on the user's individual circumstances to form a training tutorial and guide the user through training, the recording module records user actions to generate a user action sequence including a sequence of exercise actions, the recognition module obtains key actions and their execution time points, and the scoring module obtains the user's overall cognitive ability score.

[0004] However, there is currently no cognitive enhancement system on the market that can deeply integrate cognitive training with users' favorite music. Summary of the Invention

[0005] The primary technical problem to be solved by this invention is to provide a method for enhancing cognition by incorporating music.

[0006] Another technical problem to be solved by the present invention is to provide a cognitive enhancement system that integrates music.

[0007] To achieve the above-mentioned technical objectives, the present invention adopts the following technical solution:

[0008] According to a first aspect of the present invention, a cognitive enhancement method incorporating music is provided, comprising the following steps:

[0009] User information is collected based on demographic data, and initial music recommendations are obtained based on this user information.

[0010] Based on the user's cognitive assessment results, obtain the corresponding human-computer interaction task;

[0011] In the recommended music environment, the human-computer interaction task is pushed to the user for human-computer interaction;

[0012] The recommended music is updated based on the joint analysis model and the Chmiel-Schubert model;

[0013] In the updated recommended music environment, the human-computer interaction task is pushed to the user again for human-computer interaction.

[0014] Preferably, updating the recommended music based on the joint analysis model and the Chmiel-Schubert model specifically includes:

[0015] Obtain the music attribute to which the recommended music belongs;

[0016] Obtain the attribute tags to which the recommended music belongs under each of the aforementioned music attributes;

[0017] Based on the user's human-computer interaction results, the recommended values ​​of each attribute tag are obtained based on the joint analysis model;

[0018] Based on the user's human-computer interaction results, the recommendation weights of each attribute label are obtained using the Chmiel-Schubert model;

[0019] Based on the recommendation value and recommendation weight of each attribute tag, obtain the weighted recommendation value of each attribute tag;

[0020] The attribute tags are sorted according to their weighted recommendation values, and a predetermined number of the attribute tags with the highest ranking are selected.

[0021] Based on the selected predetermined number of attribute tags, corresponding music is matched from a preset music library and used as the updated recommended music.

[0022] Preferably, the step of obtaining the recommended values ​​of each attribute tag based on the user's human-computer interaction results and using a joint analysis model specifically includes:

[0023] Based on the user's human-computer interaction results, the utility value of each attribute tag for improving user cognition is obtained based on the joint analysis model;

[0024] The average utility value of the music attribute is obtained by averaging the utility values ​​of each attribute tag under the music attribute.

[0025] The recommended value of the attribute tag is calculated using the average utility value of the music attribute and the utility value of the attribute tag.

[0026] The expression for the joint analysis model is:

[0027]

[0028] Where: y j Recommended value for attribute label j of music attribute i; μ i a is the average utility value of the music attribute i; ij The utility value of attribute tag j for the music attribute i;

[0029] Preferably, the step of obtaining the recommendation weights of each attribute label based on the user's human-computer interaction results and using the Chmiel-Schubert model specifically includes:

[0030] Based on the user's human-computer interaction results, the number of times the attribute label appears is obtained using the Chmiel-Schubert model;

[0031] The time difference of the occurrence of the attribute labels is obtained based on the Chmiel-Schubert model;

[0032] Based on the number of times and the time difference, the recommendation weight of the attribute tag is calculated;

[0033] The expression for the Chmiel-Schubert model is:

[0034]

[0035] Among them, w j S is the recommendation weight for attribute label j; j The number of times attribute tag j appears; t j Let t be the time difference in the appearance of attribute tag j, in days. j =t bj -t aj , t bj For the time when attribute tag j appears this time, t aj This represents the last occurrence time of attribute tag j.

[0036] Preferably, the step of weighting the recommendation values ​​and recommendation weights of each attribute tag to obtain a weighted recommendation value for each attribute tag specifically includes:

[0037] Based on the recommendation value and recommendation weight of each attribute tag, the weighted recommendation value of the attribute tag is calculated using the following formula;

[0038]

[0039] Among them, Rj μ is the weighted recommendation value for attribute tag j. i a is the average utility value of music attribute i; ij The utility value of attribute tag j for music attribute i; w j Let be the recommendation weight for attribute label j.

[0040] One preferred approach is to prioritize matching music that has not been selected before when matching corresponding music from the preset music library.

[0041] Preferably, obtaining recommended music based on the user information specifically includes:

[0042] Based on the user's age, gender, education level, and preferred music genres, specific music preference groups are obtained;

[0043] Music from the specific music preference group is retrieved as recommended music and recommended to the user.

[0044] Preferably, obtaining the corresponding human-computer interaction task based on the user's cognitive assessment results specifically includes:

[0045] Based on the cognitive assessment results, obtain the user's damaged brain network;

[0046] Based on the preset mapping relationship between brain networks and human-computer interaction tasks, the human-computer interaction tasks corresponding to the damaged brain networks are obtained.

[0047] Preferably, the user's cognitive assessment results are obtained based on a cognitive scale and an assessment task.

[0048] According to a second aspect of the present invention, a cognitive enhancement system incorporating music is provided, comprising a processor and a memory, wherein the processor reads a computer program from the memory for performing the following operations:

[0049] User information is collected based on demographic data, and initial music recommendations are obtained based on this user information.

[0050] Based on the user's cognitive assessment results, obtain the corresponding human-computer interaction task;

[0051] In the recommended music environment, the human-computer interaction task is pushed to the user for human-computer interaction;

[0052] The recommended music is updated based on the joint analysis model and the Chmiel-Schubert model;

[0053] In the updated recommended music environment, the human-computer interaction task is pushed to the user again for human-computer interaction.

[0054] Compared with existing technologies, the cognitive enhancement method and system that integrates music provided by this invention utilizes a music recommendation algorithm based on psychological theory and joint analysis. It targets different users' human-computer interaction tasks under different brain networks, and based on the objective data generated during the user's human-computer interaction process, it selectively pushes music that users like and that can maximize cognitive effects, thereby significantly improving the cognitive enhancement training effect. Attached Figure Description

[0055] Figure 1 A flowchart illustrating a cognitive enhancement method incorporating music, provided as an embodiment of the present invention;

[0056] Figure 2 This is a flowchart of the music recommendation process in an embodiment of the present invention;

[0057] Figure 3 A graph showing the change in recommendation weights for attribute tags with different frequencies of occurrence at different time intervals;

[0058] Figure 4 This is a structural diagram of a cognitive enhancement system that integrates music, provided as an embodiment of the present invention. Detailed Implementation

[0059] The technical content of the present invention will now be described in detail with reference to the accompanying drawings and specific embodiments.

[0060] Figure 1 and Figure 2 The illustration shows a method for enhancing cognition through music integration, provided by an embodiment of the present invention, comprising at least steps S1 to S5:

[0061] S1: Get the initial recommended music.

[0062] Specifically, this includes sub-steps S11 to S13:

[0063] S11: Collect user information based on demographics, including at least the user's age, gender, education level, and preferred music genres.

[0064] S12: Based on the above user information, obtain specific music preference groups.

[0065] In one embodiment of the present invention, the specific components include: the types of music that users generally prefer based on their age group, the types of music that male and female users generally prefer, the types of music that users with different educational levels (primary school, junior high school, high school, and undergraduate) generally prefer, and the types of music that the user personally prefers. By combining the above information, a user's music preference result can be generated, thereby determining a specific music preference group for that user.

[0066] S13: Obtain music from specific music preference groups as recommended music and recommend it to the user.

[0067] It's understandable that, since there's no user-specific interaction information during the initial cognitive training, a demographic filtering algorithm is needed to recommend initial music. Subsequently, as the user continues to interact with the system, the music can be updated based on these interactions (explained in detail below), eliminating the need for demographic methods to obtain recommended music.

[0068] S2: Obtain human-computer interaction tasks.

[0069] Specifically, this includes sub-steps S21 to S22:

[0070] S21: Based on the cognitive assessment results, obtain the user's damaged brain network. In one embodiment of the present invention, the user's cognitive assessment results are obtained based on a cognitive scale and assessment task to improve the accuracy of the cognitive assessment results.

[0071] S21: Based on the preset mapping relationship between brain networks and human-computer interaction tasks, obtain the human-computer interaction task corresponding to the damaged brain network.

[0072] Specifically, as shown in Table 1, in one embodiment of the present invention, each brain network corresponds to multiple secondary brain abilities (e.g., spatial memory, associative memory, object memory, memory span, etc.), and each secondary brain ability has at least one corresponding human-computer interaction task. For example, in Table 1, the secondary brain ability of spatial memory corresponds to the peek-a-boo chess task and the wandering task.

[0073] Table 1: Mapping Table of Brain Abilities and Human-Computer Interaction Tasks

[0074]

[0075] S3: In a recommended music environment, push human-computer interaction tasks to users for human-computer interaction.

[0076] Specifically, after obtaining recommended music through step S1 and obtaining human-computer interaction tasks through step S2, users need to complete various human-computer interaction tasks in the context of the recommended music, thereby achieving the effect of cognitive enhancement training.

[0077] During this process, the order in which the human-computer interaction tasks are pushed is random. For example, if a total of 5 human-computer interaction tasks are obtained in step S2 and numbered from 1 to 5, then the order in which these 5 human-computer interaction tasks are pushed can be 1-2-3-4-5 or 3-5-4-1-2, as long as the user completes all the human-computer interaction tasks.

[0078] S4: Update recommended music based on the joint analysis model and the Chmiel-Schubert model.

[0079] Conjoint analysis models, originating from marketing, are models used to analyze the importance of various product attributes to predict the optimal combination of product attribute labels. The purpose of this model is to simulate potential products and, based on consumers' purchase intentions for these simulated products, to quantitatively analyze the importance of each product attribute label. The principle of this model is to assume that a product has certain attributes, and by combining different levels of different attributes (for example, for milk, flavor is an attribute of milk, and manufacturers can provide different attribute labels such as coconut flavor and chocolate flavor), different virtual products are created. Consumers then evaluate these virtual products according to their preferences, and mathematical statistical methods are used to separate the utility of these attributes and attribute labels, thereby quantifying the importance of each attribute and attribute label.

[0080] The Chmiel-Schubert model is a novel model that integrates the Ebbinghaus forgetting curve and the Berlyne inverted U model. Compared to traditional similarity-based recommendation models, the Chmiel-Schubert model avoids over-recommendation of the same type of information. The Chmiel-Schubert model has two main advantages: First, it avoids over-exposing users to similar environments (the same human-computer interaction task and the same music), which can lead to boredom, reduce the effectiveness of music enhancement, and even conversely reduce cognitive improvement. Second, by using different stimuli within the same human-computer interaction task (the same task, different music), it enhances the universality of the task (avoiding the situation where the task is only effective with specific music).

[0081] In one embodiment of the present invention, by viewing a piece of music as a combination of different musical attributes, and by assigning different attribute labels to any musical attribute (for example, style is a musical attribute, and style can be divided into different attribute labels such as classical, pop, country, folk, etc.), the importance of each musical attribute and the utility value of each attribute label are analyzed based on the results of human-computer interaction, thereby enhancing the objectivity of the model.

[0082] Specifically, this includes sub-steps S41 to S47:

[0083] S41: Obtain the musical attributes of the recommended music.

[0084] In one embodiment of the present invention, multiple music attributes are pre-defined, and each music attribute includes multiple attribute tags. For example: style (including: classical, pop, country, folk, blues, rap, opera, etc.); mood (including: sad, passionate, quiet, comfortable, sweet, etc.); language / region (including: Mandarin, Cantonese, Hokkien, European and American, Korean, Japanese, French, Spanish); era (including: classic old songs, European and American classics, 1950s, 1960s, etc.); singer (including: Jay Chou, JJ Lin, Michael Jackson, etc.).

[0085] Each piece of music possesses a set of musical attributes, which are a subset of pre-defined musical attributes. In one embodiment of the present invention, it is necessary to obtain the musical attributes corresponding to the recommended music.

[0086] S42: Retrieve the attribute tags of the recommended music under each music attribute.

[0087] For example, if recommended music includes three attributes: style, mood, and era, then based on the style attribute, the recommended music would be tagged as "classical"; based on the mood attribute, it would be tagged as "sad"; and based on the era attribute, it would be tagged as "classic oldie." Therefore, the attribute tag combination for this recommended music is: Classical + Sad + Classic Oldie.

[0088] S43: Obtain recommended values ​​for each attribute label based on the joint analysis model.

[0089] Specifically, based on the user's human-computer interaction results, the utility value of different attribute tags for improving user cognition is obtained through the aforementioned joint analysis model. This utility value reflects whether each attribute tag can play a positive role in improving user cognition.

[0090] Furthermore, by averaging the utility values ​​of each attribute label under this music attribute, the average utility value of this music attribute can be obtained. The average utility value of this music attribute can reflect the average utility that this music attribute can play in improving the user's cognitive training.

[0091] The recommended value of the attribute tag is calculated by using the average utility value of the music attribute and the utility value of the attribute tag.

[0092] The expression for the joint analysis model is:

[0093]

[0094] Among them, y j Recommended value for attribute label j of music attribute i; μ i The average utility value of music attribute l; a ijThe utility value of attribute tag j for music attribute i.

[0095] S44: Obtain the weighted recommendation weights for each attribute label based on the Chmiel-Schubert model.

[0096] Specifically, this includes sub-steps S441 to S443:

[0097] S441: Based on the user's human-computer interaction results, obtain the number of times attribute label j appears using the Chmiel-Schubert model;

[0098] S442: Obtain the time difference of occurrence of attribute label j based on the Chmiel-Schubert model;

[0099] S443: Based on the number of times and the time difference, the recommendation weight of attribute label j is calculated.

[0100] The expression for the Chmiel-Schubert model is:

[0101]

[0102] Among them, w j S is the recommendation weight for attribute label j; j The number of times attribute tag j appears; t j Let t be the time difference in the appearance of attribute tag j, in days. j =t bj -t aj , t bj For the time when attribute tag j appears this time, t aj This represents the last occurrence time of attribute tag j.

[0103] like Figure 3 As shown in the figure, the change in the recommendation weight of attribute label j exhibits an inverted U-shape under all time difference conditions.

[0104] S45: Obtain the weighted recommendation value for each attribute tag.

[0105] Specifically, based on the recommendation value and recommendation weight of each attribute tag, the weighted recommendation value of the attribute tag is calculated using the following formula.

[0106]

[0107] Among them, R j μ is the weighted recommendation value for attribute tag j. i For music attributes i The average utility value; a ij The utility value of attribute tag j for music attribute i; wj Let be the recommendation weight for attribute label j.

[0108] S46: Select the attribute tag.

[0109] Specifically, multiple attribute tags are sorted according to their weighted recommendation values, and a predetermined number of attribute tags with the highest ranking are selected.

[0110] In one embodiment of the present invention, the first five attribute tags, preferably ordered, are used as the basis for subsequent music recommendations. The number of attribute tags can be adjusted adaptively as needed.

[0111] S47: Updated recommended music.

[0112] Based on the selected predetermined number of attribute tags, corresponding music is matched from a preset music library and used as the updated recommended music. For example, if the attribute tags selected in step S46 are: classical + sad + Mandarin + classic old songs + Jay Chou, then music corresponding to these five attribute tags will be matched.

[0113] Understandably, if a perfect match is not possible, then the music that best covers the selected attribute tags needs to be matched. For example, if the preset music library cannot perfectly match music that has all five attribute tags, but can match music that has four attribute tags, then the music with four attribute tags can be used as the updated recommended music. In subsequent push notifications, this music recommendation process can loop infinitely, continuously approaching user needs and changing subsequent recommended music as user behavior changes.

[0114] S5: In the updated recommended music environment, push human-computer interaction tasks to users again for human-computer interaction.

[0115] After updating the recommended music based on step S4, the user needs to complete the human-computer interaction task obtained in step S2 again in the updated recommended music environment. In one embodiment of the present invention, the human-computer interaction task remains the same, but the recommended order of each human-computer interaction task will be adjusted, so that the same human-computer interaction process can be performed in different music environments, so as to facilitate data comparison and demonstration of cognitive improvement effects.

[0116] Understandably, once a user completes a phase of cognitive improvement (e.g., continuous training for 2-3 months), the user can undergo cognitive testing again to reassess the user's damaged brain network and thus update the human-computer interaction task obtained in step S2.

[0117] As can be seen from the above description, the cognitive enhancement method for music integration provided in this embodiment of the invention not only includes the similarity recommendation function of the joint analysis model, but also the recommendation weight function of the Chmiel-Schubert model. The recommendation weight can increase the recommendation frequency of important attribute tags. When the recommendation frequency of a certain attribute tag is too high (exceeding the U-shaped fixed point), the Chmiel-Schubert model can reduce the recommendation frequency of the attribute tag that is recommended too frequently, thereby avoiding the effect of music being counterproductive due to users repeatedly hearing the same music in a short period of time.

[0118] Based on the aforementioned methods for enhancing cognition through music fusion, this invention further provides a system for enhancing cognition through music fusion. For example... Figure 4 As shown, the cognitive enhancement system includes one or more processors 21 and a memory 22. The memory 22 is coupled to the processors 21 and stores one or more programs. When the one or more programs are executed by the one or more processors 21, the one or more processors 21 implement the cognitive enhancement method of music fusion as described in the above embodiment.

[0119] The processor 21 controls the overall operation of the cognitive enhancement system to complete all or part of the steps of the aforementioned cognitive enhancement method involving music integration. The processor 21 can be a central processing unit (CPU), graphics processing unit (GPU), field-programmable gate array (FPGA), application-specific integrated circuit (ASIC), digital signal processing (DSP), etc. The memory 22 stores various types of data to support the operation of the cognitive enhancement system. This data may include, for example, instructions for any application or method operating on the cognitive enhancement system, as well as application-related data. The memory 22 can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, etc.

[0120] In one exemplary embodiment, the cognitive enhancement system may be implemented by a computer chip or physical entity, or by a product with certain functions, to perform the aforementioned cognitive enhancement method incorporating music and achieve the same technical effect as described above. A typical embodiment is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, an in-vehicle human-machine interface device, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0121] In another exemplary embodiment, the present invention also provides a computer-readable storage medium including program instructions that, when executed by a processor, implement the steps of the cognitive enhancement method for fused music in any of the above embodiments. For example, the computer-readable storage medium may be a memory including program instructions that can be executed by a processor of a cognitive enhancement system to complete the cognitive enhancement method for fused music described above and achieve the same technical effects as the method described above.

[0122] In summary, the cognitive enhancement method and system integrating music provided by this invention utilizes the principle that "listening to music you like can enhance the effect of cognitive training," forming a commercially viable targeted music-enhanced cognitive enhancement solution. This invention employs a music recommendation algorithm based on psychological theory and conjoint analysis. For different users performing human-computer interaction tasks under different brain networks, it uses objective data generated during the user's human-computer interaction process to specifically recommend music that the user likes and that can maximize cognitive enhancement, thereby significantly improving the cognitive enhancement training effect.

[0123] The above provides a detailed description of the cognitive enhancement method and system for integrated music provided by this invention. Any obvious modifications made by those skilled in the art without departing from the essential content of this invention will constitute an infringement of the patent rights of this invention and will incur corresponding legal liability.

Claims

1. A method for enhancing cognition by integrating music, characterized in that... Includes the following steps: User information is collected based on demographic data, and initial music recommendations are obtained based on this user information. Based on the user's cognitive assessment results, obtain the corresponding human-computer interaction task; In the recommended music environment, the human-computer interaction task is pushed to the user for human-computer interaction; The recommended music is updated based on a joint analysis model and a Chmiel-Schubert model. Specifically, this includes: obtaining the music attributes to which the recommended music belongs; obtaining the attribute tags to which the recommended music belongs under each music attribute; obtaining the recommendation values ​​of each attribute tag based on the joint analysis model according to the user's human-computer interaction results; obtaining the recommendation weights of each attribute tag based on the Chmiel-Schubert model according to the user's human-computer interaction results; weighting the recommendation values ​​and recommendation weights of each attribute tag to obtain a weighted recommendation value for each attribute tag; sorting the multiple attribute tags according to their weighted recommendation values ​​and selecting a predetermined number of attribute tags from the top-ranked list; and matching corresponding music from a preset music library based on the selected predetermined number of attribute tags as the updated recommended music. The step of obtaining the recommendation weight of each attribute tag based on the user's human-computer interaction results and using the Chmiel-Schubert model specifically includes: obtaining the frequency of occurrence of the attribute tag based on the user's human-computer interaction results and using the Chmiel-Schubert model; obtaining the time difference of occurrence of the attribute tag based on the Chmiel-Schubert model; and calculating the recommendation weight of the attribute tag based on the frequency and time difference. The expression of the Chmiel-Schubert model is: , where w j S is the recommendation weight for attribute label j; j The number of times attribute tag j appears; t j Let t be the time difference in the appearance of attribute tag j, in days. j =t bj - t aj , t bj For the time when attribute tag j appears this time, t aj The time when attribute tag j last appeared; In the updated recommended music environment, the human-computer interaction task is pushed to the user again for human-computer interaction.

2. The cognitive enhancement method as described in claim 1, characterized in that, The step of obtaining recommended values ​​for each attribute tag based on the user's human-computer interaction results and using a joint analysis model specifically includes: Based on the user's human-computer interaction results, the utility value of each attribute tag for improving user cognition is obtained based on the joint analysis model; The average utility value of the music attribute is obtained by averaging the utility values ​​of each attribute tag under the music attribute. The recommended value of the attribute tag is calculated using the average utility value of the music attribute and the utility value of the attribute tag. The expression for the joint analysis model is: ， Where: y j Recommended value for attribute tag j of music attribute l; μ i The average utility value of the music attribute l; a ij The utility value of attribute tag j of the music attribute l.

3. The cognitive enhancement method as described in claim 2, characterized in that, The step of weighting the recommendation values ​​and recommendation weights of each attribute tag to obtain the weighted recommendation value of each attribute tag specifically includes: Based on the recommendation value and recommendation weight of each attribute tag, the weighted recommendation value of the attribute tag is calculated using the following formula; ， Among them, R j μ is the weighted recommendation value for attribute tag j. i The average utility value of music attribute l; a ij The utility value of attribute tag j for the music attribute l; w j Let be the recommendation weight for attribute label j.

4. The cognitive enhancement method as described in claim 1, characterized in that, When matching corresponding music from the preset music library, priority is given to matching music that has not been selected.

5. The cognitive enhancement method as described in claim 1, characterized in that, The step of obtaining recommended music based on the user information specifically includes: Based on the user's age, gender, education level, and preferred music genres, specific music preference groups are obtained; Music from the specific music preference group is retrieved as recommended music and recommended to the user.

6. The cognitive enhancement method as described in claim 1, characterized in that, The step of obtaining the corresponding human-computer interaction task based on the user's cognitive assessment results includes: Based on the cognitive assessment results, obtain the user's damaged brain network; Based on the preset mapping relationship between brain networks and human-computer interaction tasks, the human-computer interaction tasks corresponding to the damaged brain networks are obtained.

7. The cognitive enhancement method as described in claim 1, characterized in that, The user's cognitive assessment results were obtained based on a cognitive scale and assessment tasks.

8. A cognitive enhancement system integrating music, characterized in that... It includes a processor and a memory, wherein the processor reads a computer program from the memory for executing the cognitive enhancement method as described in any one of claims 1-7.

Images