Electroencephalogram-based content recommendation method, system and equipment, medium and program product

Abstract

The invention discloses an electroencephalogram-based content recommendation method, system and device, a medium and a program product, and the method comprises the steps: firstly, collecting a real-time electroencephalogram signal of a target user; according to the mapping relation between the real-time electroencephalogram signals and the mental state, the current mental state of the target user is obtained; and finally, generating recommended content for the target user according to the current mental state of the target user based on the electroencephalogram function tag of each content in a preset electroencephalogram response content library. According to the embodiment of the invention, high-universality and dynamic content recommendation is realized, and accurate requirements of specific individuals can be effectively met.

Description

Technical Field

[0001] This invention relates to the field of content recommendation technology, and in particular to a content recommendation method, system, device, medium, and program product based on electroencephalography (EEG). Background Technology

[0002] Current mainstream content recommendation systems primarily rely on users' historical behavioral data (such as playback history and ratings) or content metadata tags (such as genre, tempo, and style of music content). Existing methods have the following significant limitations:

[0003] Existing recommendation methods rely too heavily on subjective user feedback or behavioral inferences, and cannot objectively and directly quantify the real-time impact of music on users' brain neural activity and internal mental state (such as focus, mood, and relaxation).

[0004] Existing recommendation methods do not fully consider the differences in EEG activity characteristics and content responses among individuals, and the recommendation results may have poor universality and be difficult to meet the precise needs of specific individuals.

[0005] Existing recommendation methods lack an adaptive mechanism that dynamically adjusts based on the user's real-time physiological state (especially EEG state), making it difficult to guarantee recommendation effectiveness when the user's state changes, resulting in insufficient dynamism in recommendations.

[0006] Therefore, there is an urgent need to invent a content recommendation method based on electroencephalogram (EEG) analysis to solve the problems of poor universality, insufficient dynamism, and inability to meet the precise needs of specific individuals in the recommendation results of existing technologies. Summary of the Invention

[0007] In view of this, embodiments of the present invention provide a content recommendation method, system, device, medium, and program product based on electroencephalography (EEG), which at least partially solves the problems existing in the prior art.

[0008] Other features and advantages of the invention will become apparent from the following detailed description, or may be learned in part by practice of the invention.

[0009] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0010] According to a first aspect of the present invention, an EEG-based content recommendation method is provided, the method comprising:

[0011] Collect real-time EEG signals from the target user;

[0012] Based on the mapping relationship between the real-time EEG signals and mental state, the current mental state of the target user is obtained;

[0013] Based on the EEG function tags of each content in the preset EEG response content library, recommended content is generated for the target user according to the target user's current mental state.

[0014] Furthermore, based on the mapping relationship between the real-time EEG signals and mental states, the current mental state of the target user is obtained, including:

[0015] The real-time EEG signal is subjected to signal analysis and processing to obtain EEG indicators. The real-time EEG signal includes EEG band energy and combined characteristics of EEG band energy.

[0016] The EEG indicators include learning ability index, memory index, endurance index, excitement index, mood index, relaxation index, inhibition index and / or sleep index;

[0017] Based on the EEG indicators, the current mental state of the target user is obtained, including learning ability, memory, endurance, excitement level, mood, relaxation level, inhibition state and / or sleep quality;

[0018] The learning ability index is determined by the ratio of alpha wave energy to fast and slow wave energy of the real-time EEG signal.

[0019] The memory index is determined by the gamma wave energy of the real-time electroencephalogram (EEG) signal;

[0020] The endurance index is determined by the low beta wave energy of the real-time EEG signal;

[0021] The excitation index is determined by the proportion of fast wave energy in the real-time EEG signal;

[0022] The emotion index is determined by the high or low beta wave energy of the real-time EEG signal.

[0023] The relaxation index is determined by the low alpha wave energy of the real-time EEG signal;

[0024] The inhibition index is determined by the sum of the delta wave energy and the theta wave energy of the real-time EEG signal;

[0025] The sleep index is determined by the alpha wave structure characteristics and the energy relationship between slow waves and fast waves in the real-time EEG signal.

[0026] The recommended content refers to recommended songs.

[0027] Furthermore, the preset EEG response content library is a group EEG response content library, which includes group library content and EEG function tags corresponding to the group library content;

[0028] The construction process of the group EEG response content library includes:

[0029] Collect EEG data from test subjects for the content of the group database. The EEG data includes EEG data before playback, EEG data during playback, and EEG data after playback.

[0030] Based on the EEG data of the group database, the range of change in mental state corresponding to the group database content is obtained;

[0031] Based on the range of change in mental state, corresponding EEG function tags are matched and categorized for the content in the group database. The EEG function tags include the range of influence of the content in the group database on the mental state of the target user.

[0032] The group EEG response content library is constructed based on the group library content and the corresponding EEG function tags.

[0033] Furthermore, the preset EEG response content library is the personal EEG response content library corresponding to the target user; the personal EEG response content library includes personal library content and EEG function tags corresponding to the personal library content;

[0034] The process of constructing the personal EEG response content library includes:

[0035] Collect EEG data from target users while they are playing content from their personal library;

[0036] Based on the EEG data of the personal database content, corresponding EEG function tags are generated for the personal database content, and the EEG function tags include the extent of the impact of the personal database content on the mental state of the target user;

[0037] Based on the personal database content and the corresponding EEG function tags, a personal EEG response content database for the target user is constructed and continuously updated.

[0038] Furthermore, based on the EEG function tags of each content in the preset EEG response content library, recommended content is generated for the target user according to the target user's current mental state, including:

[0039] Based on the target user's current mental state and the preset mental state goal, a preset number of recommended contents are selected from the preset EEG response content library. The recommended contents are those that can most effectively improve the current mental state to the preset mental state goal.

[0040] According to the preset sorting rules, a list of recommended content is generated using the preset number of recommended content items.

[0041] Furthermore, based on the EEG function tags of each content in the preset EEG response content library, and according to the target user's current mental state, the method for generating recommended content for the target user also includes:

[0042] If, after playing recommended content for a preset duration, the target user's mental state still does not meet the preset mental state target, then the recommended content to be played will be switched sequentially according to the recommended content list.

[0043] According to a second aspect of the present invention, an EEG-based content recommendation system is provided, the system comprising: an EEG signal acquisition device and a data processing terminal;

[0044] The EEG signal acquisition device includes a standard EEG head-mounted device or a wearable EEG sensor;

[0045] The EEG signal acquisition device is used to acquire the EEG signals of the target user;

[0046] The data processing terminal is used to implement the steps of an EEG-based content recommendation method as described in any of the preceding claims.

[0047] According to a third aspect of the present invention, an EEG-based content recommendation device is provided, the device comprising: a processor and a memory;

[0048] The memory is used to store one or more program instructions;

[0049] The processor is configured to run one or more program instructions to perform the steps of an EEG-based content recommendation method as described in any of the preceding claims.

[0050] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of an EEG-based content recommendation method as described in any of the preceding claims.

[0051] According to a fifth aspect of the present invention, a computer program product is provided, the computer program product comprising a computing program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions that, when executed by a computer, cause the computer to implement the steps of an EEG-based content recommendation method as described in any of the preceding claims.

[0052] This invention provides a content recommendation method, system, device, medium, and program product based on electroencephalography (EEG). The method includes: first, acquiring real-time EEG signals of a target user; second, obtaining the target user's current mental state based on the mapping relationship between the real-time EEG signals and mental state; and finally, generating recommended content for the target user based on the EEG function tags of each content in a preset EEG response content library, according to the target user's current mental state. This invention achieves highly universal and dynamic content recommendation, effectively meeting the precise needs of specific individuals. Attached Figure Description

[0053] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0054] Figure 1 This is a flowchart illustrating a content recommendation method based on electroencephalography (EEG) provided in an embodiment of the present invention. Detailed Implementation

[0055] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0056] Furthermore, the terms “comprising” and “having”, and any variations thereof, are intended to cover non-exclusive inclusion, such that a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product, or apparatus.

[0057] Figure 1 The figure shows a flowchart of a content recommendation method based on electroencephalography (EEG) according to an embodiment of the present invention, taking recommended songs as an example.

[0058] like Figure 1 As shown, the EEG-based content recommendation method according to an embodiment of the present invention may include steps S100, S200 and S300.

[0059] In step S100, the real-time EEG signals of the target user are acquired.

[0060] Next, in step S200, the current mental state of the target user is obtained based on the mapping relationship between real-time EEG signals and mental state.

[0061] Specifically, the above steps include:

[0062] Signal analysis and processing are performed on real-time EEG signals to obtain EEG indices.

[0063] The aforementioned real-time EEG signals include a combination of EEG band energy and EEG band energy characteristics.

[0064] The aforementioned EEG indicators include learning ability index, memory index, endurance index, excitement index, mood index, relaxation index, inhibition index, and / or sleep index.

[0065] Based on EEG indicators, the target user's current mental state is obtained, which includes learning ability, memory, endurance, excitement level, mood, relaxation level, inhibition state, and / or sleep quality.

[0066] The learning ability index mentioned above is determined by the ratio of alpha wave energy to fast and slow wave energy (such as β / θ) of real-time EEG signals.

[0067] The aforementioned memory index is determined by the gamma wave energy of real-time electroencephalogram (EEG) signals.

[0068] The aforementioned endurance index was determined by the low beta wave energy of real-time electroencephalogram (EEG) signals.

[0069] The excitation index mentioned above is determined by the energy ratio of fast waves (β / γ) in real-time EEG signals.

[0070] The aforementioned mood index is determined by high or low beta wave energy from real-time EEG signals.

[0071] The relaxation index mentioned above is determined by the low alpha wave energy of real-time EEG signals.

[0072] The above inhibition index is determined by the sum of the delta wave energy and theta wave energy of the real-time EEG signal.

[0073] The aforementioned sleep index is determined by the alpha wave structure characteristics and the energy relationship between slow waves (δ / θ) or fast waves (β / γ) of real-time EEG signals.

[0074] The embodiments of the present invention provide a unified and calculable scientific basis for objectively assessing the impact of music on users' mental state by defining the above-mentioned EEG characteristic index system for quantifying users' mental state.

[0075] In step S300, based on the EEG function tags of each content in the preset EEG response content library, recommended content is generated for the target user according to the target user's current mental state.

[0076] Optionally, the aforementioned preset EEG response content library is a group EEG response content library, which includes group library content and EEG function tags corresponding to the group library content.

[0077] Specifically, the construction process of the aforementioned group EEG response content database includes:

[0078] Recruit a large number of test participants (1000 people) to listen to a preset music library while wearing standardized EEG acquisition devices in a controlled or natural state. Collect EEG data of the test participants for the content of the group library. The EEG data includes EEG data before playback, EEG data during playback, and EEG data after playback.

[0079] Based on the EEG data of the group database content, the change range of the mental state (learning ability index, relaxation index, etc.) corresponding to the group database content is obtained (e.g., "relaxation index increased by 20%" after playback). The average impact value of the group database content on the test subjects on seven types of EEG indicators is recorded (e.g., "Song A" caused the group's "average learning ability index +8%" and "average relaxation index +15%").

[0080] Based on the above average impact value, the content of the group database is matched with corresponding EEG function tags and classified (for example, a threshold is set, if the learning ability index increases by more than 15%, then the tag is "improved concentration" or "significant relaxation"). The EEG function tags include the magnitude of the impact of the content of the group database on the mental state of the target user.

[0081] Based on the content of the group database and the corresponding EEG function tags, a categorized group EEG response content database is constructed.

[0082] Users can directly select music under the corresponding tag according to their own needs (such as "need to relax").

[0083] Optionally, the aforementioned preset EEG response content library can also be a personal EEG response content library corresponding to the target user, wherein the personal EEG response content library includes personal library content and EEG function tags corresponding to the personal library content.

[0084] Specifically, the process of constructing the aforementioned personal EEG response content database includes:

[0085] Collect EEG data from target users while they are playing content from their personal library;

[0086] Based on the EEG data of the personal database content, corresponding EEG function tags are generated for the personal database content. The aforementioned EEG function tags include the extent of the impact of the personal database content on the target user's mental state (e.g., song A increases the user's "endurance index by 12% and decreases the mood index by 8%").

[0087] Based on the content of the personal database and the corresponding EEG function tags, a personal EEG response content database for the target user is constructed and continuously updated.

[0088] Furthermore, based on the target user's current mental state (e.g., detected fatigue) and preset mental state goals (e.g., "need to improve memory"), a preset number of recommended contents are selected from the aforementioned preset EEG response content library according to priority. The recommended contents are those that can most effectively improve the current mental state to the preset mental state goal.

[0089] Based on preset sorting rules (such as the largest increase), a list of recommended content is generated using a preset number of recommended content items.

[0090] Preferably, the EEG feedback of the target user (especially changes in the excitement index) is continuously monitored after playback. If the target user's mental state still does not meet the preset mental state target after playing the recommended content for a preset duration, the recommended music is switched sequentially according to the recommended content list until the user's state reaches the expected target or the user stops.

[0091] This invention, through dynamic adaptation to individual differences, utilizes an AI model (trained based on user EEG feedback data) to achieve a closed-loop iteration of "use-feedback-optimization," resulting in continuously improving recommendation accuracy over time.

[0092] Compared with traditional content recommendation methods, the embodiments of the present invention have the following advantages:

[0093] High accuracy: The embodiments of this invention directly quantify the actual effectiveness of music through changes in electroencephalographic indicators, completely avoiding the bias of subjective evaluation, and the recommendation results are highly matched with the user's real inner needs (mental state regulation);

[0094] Highly adaptive: In the cold start phase, the embodiments of the present invention can use a group content library to provide basic recommendations. In the individual usage phase, by continuously collecting real-time EEG data, it can dynamically learn and adapt to the unique EEG response patterns of the individual. The recommendation strategy is continuously optimized as the user uses it ("the more you use it, the more accurate it becomes").

[0095] Wide range of scenarios: The embodiments of this invention are highly universal and can be flexibly applied to a variety of scenarios that require music-assisted adjustment, such as: improving concentration in learning / working, relieving emotional stress (relaxation / excitement), sleep assistance, cognitive training, etc.

[0096] In addition, this invention also provides a content recommendation system based on electroencephalography (EEG). The system includes an EEG signal acquisition device and a data processing terminal. The EEG signal acquisition device includes a standard EEG head-mounted device or a wearable EEG sensor, and the data processing terminal includes a smartphone, a tablet computer, or a dedicated computing device.

[0097] EEG signal acquisition equipment is used to acquire the EEG signals of a target user.

[0098] The data processing terminal is used to implement the steps of an EEG-based content recommendation method as described above.

[0099] In addition, embodiments of the present invention also provide an EEG-based content recommendation device, the device comprising: a processor and a memory; the memory for storing one or more program instructions; the processor for executing one or more program instructions to perform the steps of an EEG-based content recommendation method as described above.

[0100] In addition, embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of an EEG-based content recommendation method as described above.

[0101] In addition, embodiments of the present invention also provide a computer program product, which includes computer program instructions that, when executed by a processor, implement the steps of an EEG-based content recommendation method as described above.

[0102] This invention presents a pioneering EEG index mapping system, which clearly defines the quantitative mapping relationship between seven core mental states (learning ability, memory, endurance, excitement, emotion, relaxation, inhibition / sleep quality) and calculable EEG energy and combination characteristics, and establishes a scientific, objective, and operable standard for evaluating the effectiveness of music.

[0103] This invention constructs a dual-modal collaborative recommendation mechanism, innovatively integrating a "group big data" recommendation model with an AI-driven intelligent recommendation model based on "individual real-time data." The former provides a universal foundation and cold-start capability, while the latter enables deep personalization. The two work together to balance the system's universality and accuracy.

[0104] This invention also implements dynamic feedback closed-loop optimization: a closed-loop system is established consisting of "user listening to music -> real-time EEG monitoring and analysis -> updating the individual EEG response model -> optimizing subsequent recommendations". The AI ​​model can iterate and optimize itself based on the user's continuous EEG feedback data, ensuring that the recommendation effect continuously improves over time.

[0105] In summary, this invention effectively solves the pain point of traditional recommendation systems being detached from users' actual physiological states, and provides important technical foundations and methodological support for fields such as education (improving learning efficiency), mental health (emotion regulation), human-computer interaction (intelligent environmental background sound), sleep science (music-assisted sleep), and neuromusic therapy, with broad application prospects and market potential.

[0106] In this embodiment of the invention, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in this embodiment of the invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in this embodiment of the invention can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The processor reads information from the storage medium and, in conjunction with its hardware, completes the steps of the above methods. The storage medium can be memory, for example, volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM).The storage media described in the embodiments of this invention are intended to include, but are not limited to, these and any other suitable types of memory. Those skilled in the art will recognize that the functions described in the above examples can be implemented using a combination of hardware and software. When applied software, the corresponding functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of computer programs from one place to another. Storage media can be any available medium accessible to general-purpose or special-purpose computers. Although the invention has been described in detail above with general description and specific embodiments, modifications or improvements can be made to it, which will be apparent to those skilled in the art. Therefore, such modifications or improvements made without departing from the spirit of the invention are all within the scope of protection claimed by the invention.

[0107] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Any simple modifications, equivalent changes, or alterations made by those skilled in the art using the disclosed technical content shall fall within the protection scope of the present invention.

Claims

1. A content recommendation method based on electroencephalography (EEG), characterized in that, The method includes: Collect real-time EEG signals from the target user; Based on the mapping relationship between the real-time EEG signals and mental state, the current mental state of the target user is obtained; Based on the EEG function tags of each content in the preset EEG response content library, recommended content is generated for the target user according to the target user's current mental state.

2. The content recommendation method based on EEG according to claim 1, characterized in that, Based on the mapping relationship between the real-time EEG signals and mental states, the current mental state of the target user is obtained, including: The real-time EEG signal is subjected to signal analysis and processing to obtain EEG indicators. The real-time EEG signal includes EEG band energy and combined characteristics of EEG band energy. The EEG indicators include learning ability index, memory index, endurance index, excitement index, mood index, relaxation index, inhibition index and / or sleep index; Based on the EEG indicators, the current mental state of the target user is obtained, including learning ability, memory, endurance, excitement level, mood, relaxation level, inhibition state and / or sleep quality; The learning ability index is determined by the ratio of alpha wave energy to fast and slow wave energy of the real-time EEG signal. The memory index is determined by the gamma wave energy of the real-time electroencephalogram (EEG) signal; The endurance index is determined by the low beta wave energy of the real-time EEG signal; The excitation index is determined by the proportion of fast wave energy in the real-time EEG signal; The emotion index is determined by the high or low beta wave energy of the real-time EEG signal. The relaxation index is determined by the low alpha wave energy of the real-time EEG signal; The inhibition index is determined by the sum of the delta wave energy and the theta wave energy of the real-time EEG signal; The sleep index is determined by the alpha wave structure characteristics and the energy relationship between slow waves and fast waves in the real-time EEG signal. The recommended content refers to recommended songs.

3. The content recommendation method based on EEG according to claim 1, characterized in that, The preset EEG response content library is a group EEG response content library, which includes group library content and EEG function tags corresponding to the group library content. The construction process of the group EEG response content library includes: Collect EEG data from test subjects for the content of the group database. The EEG data includes EEG data before playback, EEG data during playback, and EEG data after playback. Based on the EEG data of the group database, the range of change in mental state corresponding to the group database content is obtained; Based on the range of change in mental state, corresponding EEG function tags are matched and categorized for the content in the group database. The EEG function tags include the range of influence of the content in the group database on the mental state of the target user. The group EEG response content library is constructed based on the group library content and the corresponding EEG function tags.

4. The content recommendation method based on EEG according to claim 1, characterized in that, The preset EEG response content library is the personal EEG response content library corresponding to the target user; the personal EEG response content library includes personal library content and EEG function tags corresponding to the personal library content. The process of constructing the personal EEG response content library includes: Collect EEG data from target users while they are playing content from their personal library; Based on the EEG data of the personal database content, corresponding EEG function tags are generated for the personal database content, and the EEG function tags include the extent of the impact of the personal database content on the mental state of the target user; Based on the personal database content and the corresponding EEG function tags, a personal EEG response content database for the target user is constructed and continuously updated.

5. A content recommendation method based on electroencephalography (EEG) according to claim 3 or 4, characterized in that, Based on the EEG function tags of each item in a pre-set EEG response content library, recommended content is generated for the target user according to the target user's current mental state, including: Based on the target user's current mental state and the preset mental state goal, a preset number of recommended contents are selected from the preset EEG response content library. The recommended contents are those that can most effectively improve the current mental state to the preset mental state goal. According to the preset sorting rules, a list of recommended content is generated using the preset number of recommended content items.

6. The content recommendation method based on EEG according to claim 5, characterized in that, Based on the EEG function tags of each item in a pre-set EEG response content library, and according to the target user's current mental state, recommended content is generated for the target user, which also includes: If, after playing recommended content for a preset duration, the target user's mental state still does not meet the preset mental state target, then the recommended content to be played will be switched sequentially according to the recommended content list.

7. A content recommendation system based on electroencephalography (EEG), characterized in that, The system includes: an electroencephalogram (EEG) signal acquisition device and a data processing terminal; The EEG signal acquisition device includes a standard EEG head-mounted device or a wearable EEG sensor; The EEG signal acquisition device is used to acquire the EEG signals of the target user; The data processing terminal is used to implement the steps of the content recommendation method based on EEG as described in any one of claims 1 to 6.

8. A content recommendation device based on electroencephalography (EEG), characterized in that, The device includes: a processor and a memory; The memory is used to store one or more program instructions; The processor is configured to run one or more program instructions to perform the steps of an EEG-based content recommendation method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the EEG-based content recommendation method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes computer program instructions that, when executed by a processor, implement the steps of an EEG-based content recommendation method as described in any one of claims 1 to 6.

Images