Meditation training method and device based on virtual digital human, and storage medium

Abstract

The invention discloses a meditation training method and device based on a virtual digital human and a storage medium, and the method comprises the steps: collecting an electroencephalogram signal of a user when the user carries out meditation training; according to the electroencephalogram signals, the attention concentration degree of the user during meditation training is evaluated; loading a meditation scene for feeding back meditation training of the user; loading a virtual digital person in the meditation scene; when the meditation scene is controlled to change according to the attention concentration degree, meditation voice data for guiding the user to perform meditation training in the meditation scene is generated according to the attention concentration degree; and according to the attention concentration degree, controlling the facial expression and / or limb movement change of the virtual digital person, and controlling the virtual digital person to play meditation voice data so as to guide the user to perform meditation training in the meditation scene. And the user is guided to perform meditation training visually and acoustically, so that the pertinence and speciality of meditation can be effectively improved, and the efficiency of meditation training of the user is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of mindfulness meditation, and in particular to a meditation training method, device and storage medium based on virtual digital human. Background Art

[0002] As the pace of modern life accelerates, more and more people are practicing mindfulness meditation to relieve stress from work and life and improve their physical and mental health.

[0003] At present, mindfulness meditation is mainly guided by professionals, and is practiced independently in spare time. During the independent silent training, people mainly rely on their own understanding of mindfulness meditation, which leads to low efficiency of mindfulness meditation. Summary of the invention

[0004] In view of this, the present invention provides a meditation training method, device and storage medium based on a virtual digital human, so as to improve the efficiency of users practicing mindfulness meditation.

[0005] A first aspect of the present invention provides a meditation training method based on a virtual digital human, comprising:

[0006] When the user is performing mindfulness meditation training, collecting the user's electroencephalogram signal;

[0007] evaluating the user's concentration level during mindfulness meditation training based on the EEG signal;

[0008] Loading a meditation scene that provides feedback on the user's mindfulness meditation training;

[0009] loading a virtual digital human in the meditation scene;

[0010] When controlling the change of the meditation scene according to the concentration level, generating meditation voice data for guiding the user to perform mindfulness meditation training in the meditation scene according to the concentration level;

[0011] The facial expression and / or body movement of the virtual digital person is controlled according to the concentration level, and the virtual digital person is controlled to play the meditation voice data to guide the user to perform mindfulness meditation training in the meditation scene.

[0012] A second aspect of the present invention provides a meditation training device based on a virtual digital human, comprising:

[0013] An EEG signal acquisition module, used to acquire EEG signals of the user during mindfulness meditation training;

[0014] An attention assessment module, used to assess the user's attention concentration during mindfulness meditation training based on the EEG signal;

[0015] A meditation scene loading module, used to load a meditation scene for providing feedback on the user's mindfulness meditation training;

[0016] A virtual digital human loading module, used to load a virtual digital human into the meditation scene;

[0017] a meditation voice data generating module, configured to generate meditation voice data for guiding the user to perform mindfulness meditation training in the meditation scene according to the concentration level when controlling the change of the meditation scene according to the concentration level;

[0018] The meditation guiding module is used to control the facial expressions and / or body movements of the virtual digital human according to the concentration level, and to control the virtual digital human to play the meditation voice data to guide the user's mindfulness meditation training in the meditation scene.

[0019] A third aspect of the present invention provides an electronic device, the electronic device comprising:

[0020] at least one processor; and

[0021] a memory communicatively connected to the at least one processor; wherein,

[0022] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the meditation training method based on the virtual digital human as described in the first aspect above.

[0023] A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the meditation training method based on a virtual digital human as described in the first aspect above.

[0024] A fifth aspect of the present invention provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the meditation training method based on a virtual digital human as described in the first aspect above.

[0025] In this embodiment, when a user is performing mindfulness meditation training, the user's EEG signals are collected; the user's concentration level during mindfulness meditation training is evaluated based on the EEG signals; a meditation scene that provides feedback on the user's mindfulness meditation training is loaded; a virtual digital human is loaded in the meditation scene; when controlling changes in the meditation scene based on the concentration level, meditation voice data that guides the user's mindfulness meditation training in the meditation scene is generated based on the concentration level; the facial expressions and / or body movements of the virtual digital human are controlled based on the concentration level, and the virtual digital human is controlled to play the meditation voice data to guide the user's mindfulness meditation training in the meditation scene. When the user conducts independent silent mindfulness meditation training, the facial expressions and / or body movements of the virtual digital person are adaptively controlled according to the degree of concentration. The virtual robot is adaptively generated and controlled to play meditation voice data according to the meditation scene and the degree of concentration, so as to guide the user's mindfulness meditation training visually and auditorily. The guidance method changes dynamically to adapt to the user's state during mindfulness meditation training, making the guidance method flexible and fitting the user's actual state, which can effectively improve the pertinence and professionalism of mindfulness meditation, reduce the user's own cognitive requirements for mindfulness meditation, and thus improve the efficiency of the user's mindfulness meditation training.

[0026] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0028] Figure 1 This is a flow chart of a meditation training method based on a virtual digital human provided in the first embodiment of the present invention.

[0029] Figure 2 This is an example diagram of a sad expression of a virtual digital person provided in the first embodiment of the present invention.

[0030] Figure 3 This is an example diagram of a calm expression of a virtual digital person provided in the first embodiment of the present invention.

[0031] Figure 4 This is an example diagram of a happy expression of a virtual digital person provided in the first embodiment of the present invention.

[0032] Figure 5This is a flow chart of a meditation training method based on a virtual digital human provided in the second embodiment of the present invention.

[0033] Figure 6 It is a structural schematic diagram of a meditation training device based on a virtual digital human provided in Embodiment 3 of the present invention.

[0034] Figure 7 It is a structural schematic diagram of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0035] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0036] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can cover sequential implementations other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0037] Embodiment 1

[0038] See also Figure 1 , showing a flow chart of a meditation training method based on a virtual digital human provided in Embodiment 1 of the present invention. The method can be performed by a meditation training device based on a virtual digital human. The meditation training device based on a virtual digital human can be implemented in the form of hardware and / or software. The meditation training device based on a virtual digital human can be configured in an electronic device.

[0039] In one case, the electronic device is an integrated device, especially a head-mounted device, such as a smart helmet, smart glasses, etc. The virtual reality device is equipped with components such as a brain-computer interface, speakers, and a screen for providing feedback on mindfulness meditation. The speakers and the screen can be built into the electronic device or can be reused by mobile terminals such as the user's mobile phone.

[0040] In another case, the electronic device may also be a physically separable or detachable device. In this case, the virtual reality device includes a headband and external auxiliary devices that are independent of each other. The headband and the auxiliary devices can be connected by wired or wireless means, such as Wi-Fi (Wireless Fidelity), Bluetooth, ZigBee, etc. The headband is provided with a brain-computer interface, and the auxiliary device is equipped with components such as a screen, speakers, and lights for providing feedback on mindfulness meditation. The auxiliary device can be an independent device that matches the headband, or it can be a non-independent device such as a multiplexed television.

[0041] like Figure 1 As shown, the method includes:

[0042] Step 101: When the user is performing mindfulness meditation training, the user's electroencephalogram signal is collected.

[0043] In this embodiment, the user wears an electronic device for mindfulness meditation training. During this process, the brain-computer interface in the electronic device can be called to collect single-channel or multi-channel EEG signals from the user at a preset frequency.

[0044] Among them, EEG signals, also known as electroencephalograms (EEG), are electrical signals generated by the activity of brain neurons. Neurons are connected to each other through synapses to form a complex neural network. When neurons are activated, bioelectric phenomena are generated, and these EEG signals can be captured by placing electrodes on the scalp.

[0045] Taking a single-channel EEG signal as an example, the brain-computer interface includes electrodes, a signal processor, and an A / D (Analogue to Digital conversion) converter.

[0046] Among them, the electrodes include a reference electrode, a ground electrode, and an EEG electrode of a signal channel; the ground electrode is used to determine the zero potential of the EEG signal, and the reference electrode and the ground electrode are placed at the temples on both sides of the user's head; the EEG electrode is placed at the Fp2 position defined in the 10-20 system.

[0047] The signal processor is used to amplify the collected EEG signal through an amplifier with a sampling frequency of 250 Hz, and to filter out the 50 Hz power frequency noise in the EEG signal through a notch filter, and then use a 0.1-50 Hz bandpass filter to filter out the DC component and high-frequency noise.

[0048] The A / D converter converts the amplified and filtered EEG signals from analog signals to digital signals through a 24-bit resolution digital-to-analog conversion chip.

[0049] Step 102: Evaluate the user's concentration level during mindfulness meditation training based on the EEG signal.

[0050] In this embodiment, a meditation detection model can be pre-constructed, and EEG signals of several users in a relaxed state (or resting state) and a meditative state can be collected as samples to train the meditation detection model, so that the meditation detection model can evaluate the user's concentration level during mindfulness meditation training based on the EEG signals, and realize meditation state evaluation within subjects, across subjects, and across time.

[0051] The degree of concentration can be provided to users as a score (e.g., a value range of [0, 100]) to quantify the effect of mindfulness meditation, allowing users to have an intuitive feeling of their own mindfulness meditation state.

[0052] Among them, the meditation detection model can be a machine learning model, such as a support vector machine (SVM), a decision tree, a random forest, and the like.

[0053] In addition, the meditation detection model can also be a deep learning model, such as Convolutional Neural Networks (CNN), Long Short Term Memory (LSTM), Transformer (a neural network architecture based on self-attention mechanism), etc.

[0054] For deep learning models, the structure of the meditation detection model is not limited to artificially designed neural networks, but can also be a neural network optimized by a model quantization method, a neural network searched by a NAS (Neural Architecture Search) method based on the characteristics of the user's EEG signals during mindfulness meditation training, and so on. This embodiment does not impose any restrictions on this.

[0055] In practical applications, the EEG signal can be divided into multiple segment signals of equal length (such as 10 seconds), and each segment signal is subjected to bandpass filtering, such as Chebyshev filtering, Butterworth bandpass filtering, etc., to improve the quality of the segment signal.

[0056] For each segment signal, analysis may be performed on it in the time domain and / or frequency domain to obtain features in the time domain and / or frequency domain.

[0057] Among them, the time domain analysis may include event-related potential (ERP), statistical analysis, etc. Among them, the event-related potential is used to observe the waveform changes of EEG signals under specific tasks, and the statistical analysis is used to compare the differences in EEG waveforms under different conditions.

[0058] Frequency domain analysis includes Fourier transform (FFT), power spectral density (PSD), etc. Among them, Fourier transform is used to analyze the frequency components of EEG signals, and power spectral density is used to analyze the energy distribution of EEG signals.

[0059] The analysis of time domain and frequency domain is also called time-frequency analysis, including short-time Fourier transform (STFT), wavelet transform, etc. Among them, short-time Fourier transform is used to analyze the frequency components of EEG signals that change over time, and wavelet transform is used to provide better time-frequency resolution.

[0060] The features of each segment signal in the time domain and / or frequency domain are input into the meditation detection model for processing to obtain the user's concentration level during mindfulness meditation training.

[0061] Step 103: Load a meditation scene that provides feedback on the user's mindfulness meditation training.

[0062] In this embodiment, meditation scenes may be recommended to the user based on the user's preferences or business rules (such as randomness, popularity, etc.), or the user may select a meditation scene by himself and load the meditation scene into the auxiliary device.

[0063] The meditation scene is a business scene with multi-dimensional information. The meditation scene can provide at least one sensory feedback among visual feedback, auditory feedback, olfactory feedback, tactile feedback and electrical stimulation feedback to the user's mindfulness meditation training.

[0064] For example, visual feedback may include animations of the sky, clouds, bonfires, waves, and forests; auditory feedback may include pink noise, the sound of raindrops, the sound of flowing water, the sound of flames, music, and other sounds; olfactory feedback may include gases such as aromatherapy; tactile feedback may include vibration of portable devices, seat massage, etc.; electrical stimulation feedback may include direct current stimulation, etc.

[0065] Step 104: Load the virtual digital human in the meditation scene.

[0066] A virtual engine, such as Unreal Engine 5 (UE5), is configured in the electronic device. When the user is practicing mindfulness meditation, the virtual engine can be called to generate a two-dimensional or three-dimensional virtual digital human in the meditation scene. The style of the virtual digital human includes cartoon, realism, etc., which can be default, matched with the meditation scene, or selected by the user.

[0067] For example, the following can be loaded in the meditation scene: Figure 2 , Figure 3 and Figure 4 The virtual digital human shown in the hyper-realistic style.

[0068] Step 105: When controlling the change of the meditation scene according to the degree of concentration, generate meditation voice data for guiding the user to perform mindfulness meditation training in the meditation scene according to the degree of concentration.

[0069] In this embodiment, the changing trend of the concentration level can be evaluated at regular intervals (such as 2 seconds), and the expressiveness of the meditation scene in various feedbacks can be controlled to change according to the changing trend of the concentration level, so that the changing trend of the expressiveness of the meditation scene in various feedbacks is the same as the changing trend of the concentration level, thereby providing feedback on the user's mindfulness meditation training.

[0070] Among them, the expressive changes that control the meditation scene include changes in the clarity and perspective of visual feedback, changes in the volume, pitch, and sound type of auditory feedback, changes in the strength of tactile feedback, changes in the strength of electrical stimulation feedback, and so on.

[0071] Exemplarily, the changing trend of the user's concentration level is evaluated once at regular intervals (such as 2 seconds). If the current concentration level is higher than that of the previous moment, that is, the concentration level has increased, indicating that the user's meditation level has become deeper and the effect has improved, then the picture in the meditation scene is controlled to become clear and beautiful; if the current concentration level is lower than that of the previous moment, that is, the concentration level has decreased, indicating that the user's meditation level has become shallower and the effect has worsened, and there may be distraction, then the picture in the meditation scene is controlled to become blurred and bad.

[0072] In the process of controlling the changes of meditation scenes according to the degree of concentration, the virtual digital human can be synchronously controlled to simulate professionals to give professional guidance to the user's mindfulness meditation training.

[0073] At this time, meditation voice data can be generated based on the changing trend of the degree of concentration to guide the user's mindfulness meditation training in the meditation scene.

[0074] In one embodiment of the present invention, step 105 may include the following steps:

[0075] Step 1051: Map the degree of concentration to the meditation state of the user during mindfulness meditation training.

[0076] In practical applications, the signal-to-noise ratio of EEG signals is relatively low and is easily affected by environmental noise. There are certain differences in the EEG signals of different users, which limits the accuracy of detecting the degree of concentration of users during mindfulness meditation training. In order to reduce the impact of these differences, clustering, piecewise functions, etc. can be used to linearly or nonlinearly map the degree of concentration to the meditation state of the user during mindfulness meditation training.

[0077] Exemplarily, a first interval, a second interval and a third interval can be determined; wherein any value in the first interval is greater than any value in the second interval, and any value in the second interval is greater than any value in the third interval; for example, the third interval is [0, 30), the second interval is [30, 70), and the first interval is [70, 100].

[0078] Compare the degree of concentration with the first interval, the second interval, and the third interval respectively.

[0079] When the concentration level is within the first interval, it is determined that the meditation state of the user during the mindfulness meditation training is an excellent state.

[0080] When the concentration level is within the second interval, it is determined that the meditation state of the user during the mindfulness meditation training is a stable state.

[0081] When the concentration level is within the third interval, it is determined that the meditation state of the user during the mindfulness meditation training is a bad state.

[0082] Of course, the above meditation states are only used as examples. When implementing this embodiment, other meditation states can be set according to actual conditions, and this embodiment does not limit this. In addition, in addition to the above meditation states, those skilled in the art can also use other meditation states according to actual needs, and this embodiment does not limit this.

[0083] Step 1052: When the meditation state is the preset target state, extract the subject words from the meditation scene.

[0084] In this embodiment, some meditation states can be selected from all meditation states as target states, and the virtual digital human can be controlled to guide the user in the target state to train mindfulness meditation.

[0085] Exemplarily, in the case where the meditation state includes a good state, a stable state, and a bad state, the target state includes a good state and a bad state.

[0086] When it is detected that the meditation state is a preset target state, user-guided mindfulness meditation training can be initiated. At this time, theme words can be extracted from the meditation scene, such as campfire, waves, forest, etc.

[0087] Step 1053: Use the keywords to construct first guidance text information for providing feedback on the meditation state in the meditation scene.

[0088] In this embodiment, based on the meditation scene, the guidance information Prompt that uses the subject words to provide feedback on the user's meditation state (especially the target state) is recorded as the first guidance text information, wherein the guidance information Prompt is a text used to guide the language model (LM) to generate a specific type, theme or format content. In NLP (Natural Language Processing), the guidance information Prompt is usually composed of a question or task description.

[0089] In the specific implementation, the corpus for training language models (especially large language models (LLM)) has certain limitations. These corpuses generally include universal knowledge, common sense knowledge and professional knowledge in various fields, such as encyclopedias, news, novels, etc., which makes the language model have certain limitations when dealing with knowledge representation and application in specific fields.

[0090] In this embodiment, a knowledge base may be loaded; the knowledge base includes scene text information for describing each meditation scene and a scene text vector converted from the scene text information.

[0091] For example, some of the information in the knowledge base includes an introduction to the digital robot, an introduction to the definition of mindfulness, an introduction to the content of mindfulness meditation, specifications for guiding users in mindfulness meditation in various meditation scenarios, reminders and encouragements, and so on.

[0092] Question text information for providing feedback on the meditation state in a meditation scenario is constructed based on question templates and other methods using keywords and meditation states.

[0093] Call text vector models such as Embedding to convert question text information into question text vectors.

[0094] The question text vector is input into a preset vector retrieval service (such as DashVector, etc.), and a scene text vector similar to the question text vector is retrieved in the knowledge base as the target text vector.

[0095] The scene text information corresponding to the target text vector is extracted from the knowledge base as the target text information.

[0096] The target text information and the question text information are used to construct the first guiding text information for providing feedback on the meditation state in the meditation scene.

[0097] For example, in a meditation scene with a campfire as visual feedback, if the user's concentration level remains below 30 points, the first guidance text message can be constructed as follows: "My meditation score has always been below 30 points. Give me a mindfulness meditation guide related to campfires to remind me to improve my low meditation score. The theme should be clear and the content should be detailed and specific." Or, "My campfire meditation score is between 0 and 30 points, and it has been in this score range for a long time, which means that I am in a relatively poor meditation state. You need to tell me my current state and give me some direct suggestions to help me concentrate."

[0098] In the meditation scene where the visual feedback is a campfire, if the user's concentration level remains above 70, the first guiding text message can be constructed: "My campfire meditation score is between 70 and 100 points, and it has been in this score range for a long time, which means that I am in a relatively good meditation state. You need to tell me my current state and give some positive feedback to encourage me. Remember to reply with a maximum of 100 words."

[0099] In this way, the language model (especially LLM) can understand and acquire domain knowledge of mindfulness meditation that exists outside the scope of its training knowledge. At the same time, through the construction of a specific first guidance text information Prompt, the language model (especially LLM) can be prompted to understand the intention when answering domain questions obtained in mindfulness meditation and give answers based on the domain knowledge injected into mindfulness meditation.

[0100] Step 1054: input the first guidance text information into a preset language model to generate meditation text information.

[0101] In this embodiment, the first guidance text information Prompt is input into a preset language model (especially LLM), and the language model generates meditation text information that guides the user in the current target state to perform mindfulness meditation training in the current meditation scene according to the guidance of the first guidance text information Prompt.

[0102] Generally, the language model (especially LLM) can be a language model (especially LLM) pre-trained by a third party, or it can be a language model (especially LLM) fine-tuned using corpus related to mindfulness meditation through Lora, Fine-tuning, etc. This embodiment does not limit this.

[0103] In one case, when the meditation state is in an excellent state, the first guiding text information can be input into a preset language model (especially LLM) to generate meditation text information with encouraging emotions, guiding the user to maintain the current physical and mental state to carry out mindfulness meditation training.

[0104] For example, the language model (especially LLM) can generate a meditation text message with the sentiment of encouragement, "It is detected that your current meditation score has been above 70 points. I hope you will continue to persevere and enjoy the tranquility and peace of each meditation. Your concentration and inner peace will gradually increase and bring you more benefits. Believe in your own abilities and the power of meditation. You are on a positive path. Keep working hard and you will achieve greater success!", or "It is detected that your current meditation score has been above 70 points. Congratulations, your meditation state is very good, your concentration and inner peace are constantly improving, and this peace and concentration will help you better deal with stress and difficulties in your daily life. Continue to stay focused and calm and enjoy this quiet moment."

[0105] In another case, when the meditation state is in a bad state, the first guidance text information is input into a preset language model to generate meditation text information with emotion as a reminder, encouraging the user to adjust the physical and mental state to optimize the mindfulness meditation training.

[0106] For example, a language model (especially LLM) may generate a meditation text message with an emotion reminder such as "It is detected that your current meditation score is always below 30 points. Perhaps you are aware of how easily your mind wanders and how easily the sound makes you daydream. If you find yourself tending to think or judge, try to let them go. Return to the sound itself and allow the sound to be presented as it is." Or, "It is detected that your current meditation score is always below 30 points. Please focus on your breathing, slowly gather your attention, and calm your mind. It is important to be patient and not be too hard on yourself. Meditation is a process and it is okay to improve slowly. Please persist and continue to practice."

[0107] Step 1055: Count the duration of the target state.

[0108] When the meditation state is detected as a preset target state, the time the user is in the same target state can be counted, that is, the time the same target state lasts can be counted.

[0109] Step 1056: If the duration exceeds the time threshold configured for the target state, the meditation text information is converted into meditation voice data that guides the user in the target state to perform mindfulness meditation training in the meditation scene.

[0110] In this embodiment, if the duration of the same target state exceeds the time threshold configured for the target state, it means that the user has been in the same target state for a long time and the target state is relatively stable. Then, TTS (Text To Speech) processing can be performed on the meditation text information to convert the meditation text information into meditation voice data to guide the user in the target state in mindfulness meditation training in a meditation scene.

[0111] Step 106: Control the facial expressions and / or body movements of the virtual digital person according to the degree of concentration, and control the virtual digital person to play meditation voice data to guide the user to perform mindfulness meditation training in the meditation scene.

[0112] In the process of controlling the virtual digital human to simulate professionals giving professional guidance on the user's mindfulness meditation training, on the one hand, the facial expressions and / or body movements of the virtual digital human can be controlled in the virtual engine according to the degree of concentration, so that the changing trend of the virtual digital human's expression and / or body movements is the same as the changing trend of the degree of concentration, thereby providing feedback on the user's mindfulness meditation training. On the other hand, the meditation voice data is input into the virtual engine and the virtual digital human is controlled to play the meditation voice data, simulating professionals giving professional advice on the user's mindfulness meditation training in the meditation scene. The combination of the two can guide the user's mindfulness meditation training in the meditation scene.

[0113] When controlling the facial expressions and / or body movements of the virtual digital person, the controllers configured for the parts of the face and / or body of the virtual digital person (such as eyes, nose, mouth, joints, etc.) can be queried in the virtual engine, and each part is configured with a controller.

[0114] For each controller, the parameter amplitude configured for each controller can be queried, wherein the parameter amplitude is a continuously changeable variable.

[0115] Map the degree of attention integration proportionally to the amplitude of each parameter to obtain the value of each parameter.

[0116] The parameter values ​​are input into the corresponding controller adjustment parts to control the facial expressions and / or body movements of the virtual digital person to change from negative emotions to positive emotions when the concentration level changes from low to high. That is, the lower the concentration level, the more negative the facial expressions and / or body movements of the virtual digital person are. Conversely, the higher the concentration level, the more positive the facial expressions and / or body movements of the virtual digital person are.

[0117] For example, Figure 2 As shown in Figure 2, when the concentration level is 0, the virtual digital human shows a sad facial expression, such as Figure 3As shown in Figure 2, when the concentration level is 50, the virtual digital human presents a calm facial expression, such as Figure 4 As shown, when the concentration level is 100, the virtual digital human shows a happy facial expression.

[0118] In this embodiment, when a user is performing mindfulness meditation training, the user's EEG signals are collected; the user's concentration level during mindfulness meditation training is evaluated based on the EEG signals; a meditation scene that provides feedback on the user's mindfulness meditation training is loaded; a virtual digital human is loaded in the meditation scene; when controlling changes in the meditation scene based on the concentration level, meditation voice data that guides the user's mindfulness meditation training in the meditation scene is generated based on the concentration level; the facial expressions and / or body movements of the virtual digital human are controlled based on the concentration level, and the virtual digital human is controlled to play the meditation voice data to guide the user's mindfulness meditation training in the meditation scene. When the user conducts independent silent mindfulness meditation training, the facial expressions and / or body movements of the virtual digital person are adaptively controlled according to the degree of concentration. The virtual robot is adaptively generated and controlled to play meditation voice data according to the meditation scene and the degree of concentration, so as to guide the user's mindfulness meditation training visually and auditorily. The guidance method changes dynamically to adapt to the user's state during mindfulness meditation training, making the guidance method flexible and fitting the user's actual state, which can effectively improve the pertinence and professionalism of mindfulness meditation, reduce the user's own cognitive requirements for mindfulness meditation, and thus improve the efficiency of the user's mindfulness meditation training.

[0119] Embodiment 2

[0120] See also Figure 5 , shows a flowchart of a meditation training method based on a virtual digital human provided by the second embodiment of the present invention. This embodiment adds a voice interaction operation on the basis of the previous embodiment. Figure 5 As shown, the method includes:

[0121] Step 501: When the user is performing mindfulness meditation training, the user's electroencephalogram signal is collected.

[0122] Step 502: Evaluate the user's concentration level during mindfulness meditation training based on the EEG signal.

[0123] Step 503: Load a meditation scene that provides feedback on the user's mindfulness meditation training.

[0124] Step 504: Load the virtual digital human in the meditation scene.

[0125] Step 505: When controlling the change of the meditation scene according to the degree of concentration, generate meditation voice data for guiding the user to perform mindfulness meditation training in the meditation scene according to the degree of concentration.

[0126] Step 506: Control the facial expressions and / or body movements of the virtual digital person according to the degree of concentration, and control the virtual digital person to play meditation voice data to guide the user to perform mindfulness meditation training in the meditation scene.

[0127] Step 507: Collect the first interactive voice data spoken by the user.

[0128] In this embodiment, in addition to actively simulating professionals to provide professional guidance to users on mindfulness meditation training, the virtual digital human can also passively communicate with users in other aspects.

[0129] Then, during the user's mindfulness meditation training, the microphone can be activated to collect the user's voice data, which is recorded as the first interactive voice data. For example, "Who are you? What do you do?".

[0130] Step 508: Generate second interactive voice data in reply to the first interactive voice data.

[0131] In this embodiment, natural language processing can be performed on the first interactive voice data to understand the semantics of the first interactive voice data, and second interactive voice data that is a reply to the first interactive voice data can be generated based on the semantics. In particular, the virtual digital human can simulate a professional and actively give guidance to the user on the entire meditation scene.

[0132] In a specific implementation, speech recognition may be performed on the first interactive speech data, the first interactive speech data may be converted into first interactive text information, and the first interactive text information may be used to construct the second guiding text information Prompt.

[0133] The second guidance text message Prompt is input into a preset language model (especially LLM) to generate a second interactive text message that replies to the first interactive text message.

[0134] The second interactive text information is processed by TTS to convert the second interactive text information into second interactive voice data that responds to the first interactive voice data.

[0135] Step 509: Control the virtual digital human to play the second interactive voice data to interact with the user in the meditation scene.

[0136] The second interactive voice data is input into the virtual engine, and the virtual digital human is controlled to play the second interactive voice data, so that the virtual digital human can interact with the user in many aspects in the meditation scene, providing more information support for the user's mindfulness meditation training.

[0137] Embodiment 3

[0138] See also Figure 6, shows a schematic diagram of the structure of a meditation training device based on a virtual digital human provided by Embodiment 3 of the present invention. Figure 6 As shown, the device comprises:

[0139] The EEG signal collection module 601 is used to collect the EEG signal of the user when the user is performing mindfulness meditation training;

[0140] An attention evaluation module 602 is used to evaluate the user's attention concentration during mindfulness meditation training based on the EEG signal;

[0141] A meditation scene loading module 603 is used to load a meditation scene for providing feedback on the user's mindfulness meditation training;

[0142] A virtual digital human loading module 604 is used to load a virtual digital human into the meditation scene;

[0143] A meditation voice data generating module 605, configured to generate meditation voice data for guiding the user to perform mindfulness meditation training in the meditation scene according to the concentration level when controlling the change of the meditation scene according to the concentration level;

[0144] The meditation guiding module 606 is used to control the facial expression and / or body movement changes of the virtual digital human according to the concentration level, and to control the virtual digital human to play the meditation voice data to guide the user's mindfulness meditation training in the meditation scene.

[0145] In one embodiment of the present invention, the meditation voice data generating module 605 includes:

[0146] A meditation state mapping module, used to map the concentration level to the meditation state of the user during mindfulness meditation training;

[0147] A theme word extraction module, used for extracting theme words from the meditation scene when the meditation state is a preset target state;

[0148] A first guidance text information construction module, used to construct first guidance text information for providing feedback on the meditation state in the meditation scene using the subject words;

[0149] A meditation text information generating module, configured to input the first guiding text information into a preset language model to generate meditation text information;

[0150] A duration statistics module is used to count the duration of the target state; a meditation voice data conversion module is used to convert the meditation text information into meditation voice data for guiding the user in the target state to perform mindfulness meditation training in the meditation scene if the duration exceeds a time threshold configured for the target state.

[0151] In one embodiment of the present invention, the meditation state mapping module includes:

[0152] An interval determination module, used to determine a first interval, a second interval and a third interval; the value in the first interval is greater than the value in the second interval, and the value in the second interval is greater than the value in the third interval;

[0153] A good state determination module, configured to determine that the meditation state of the user during mindfulness meditation training is a good state when the concentration level is within the first interval;

[0154] a stable state determination module, configured to determine that the meditation state of the user during mindfulness meditation training is a stable state when the concentration level is within the second interval;

[0155] The bad state determination module is used to determine that the meditation state of the user during the mindfulness meditation training is a bad state when the concentration level is within the third interval.

[0156] In one embodiment of the present invention, the target state includes the good state and the bad state; the meditation text information generation module includes:

[0157] an encouraging text generating module, configured to input the first guiding text information into a preset language model to generate a meditation text information with an encouraging emotion when the meditation state is the excellent state;

[0158] The reminder text generation module is used to input the first guidance text information into a preset language model to generate meditation text information with reminder emotion when the meditation state is the bad state.

[0159] In one embodiment of the present invention, the first guidance text information construction module includes:

[0160] A knowledge base loading module, used to load a knowledge base; the knowledge base contains scene text information for describing each meditation scene and a scene text vector converted from the scene text information;

[0161] A question text information construction module, used to construct question text information for providing feedback on the meditation state in the meditation scene using the subject word and the meditation state;

[0162] A question text vector conversion module, used to convert the question text information into a question text vector;

[0163] A target text vector retrieval module, used for inputting the question text vector into a preset vector retrieval service, and retrieving the scene text vector similar to the question text vector in the knowledge base as a target text vector;

[0164] A target text information extraction module, used to extract the scene text information corresponding to the target text vector from the knowledge base as target text information;

[0165] A text information fusion construction module is used to use the target text information and the question text information to construct first guiding text information for providing feedback on the meditation state in the meditation scene.

[0166] In one embodiment of the present invention, the meditation guiding module 606 includes:

[0167] A controller query module, used to query the controller configured for the face and / or limbs of the virtual digital human;

[0168] A parameter amplitude query module, used to query the parameter amplitude configured for the controller;

[0169] An attention mapping module, used for mapping the attention integration degree to the parameter amplitude to obtain a parameter value;

[0170] The part adjustment module is used to input the parameter value into the controller to adjust the part, so as to control the facial expression and / or body movement of the virtual digital person to change from negative emotion to positive emotion when the concentration level changes from low to high.

[0171] In one embodiment of the present invention, it also includes:

[0172] A first interactive voice data collection module, used to collect first interactive voice data spoken by the user;

[0173] A second interactive voice data generating module, used to generate second interactive voice data in reply to the first interactive voice data;

[0174] The second interactive voice data playing module is used to control the virtual digital human to play the second interactive voice data so as to interact with the user in the meditation scene.

[0175] In one embodiment of the present invention, the second interactive voice data generating module includes:

[0176] A first interactive text information conversion module, used to convert the first interactive voice data into first interactive text information;

[0177] A second guidance text information construction module, configured to construct second guidance text information using the first interactive text information;

[0178] A second interactive text information generating module, configured to input the second guiding text information into a preset language model to generate a second interactive text information in reply to the first interactive text information;

[0179] The second interactive voice data conversion module is used to convert the second interactive text information into second interactive voice data that replies to the first interactive voice data.

[0180] The meditation training device based on virtual digital human provided in the embodiment of the present invention can execute the meditation training method based on virtual digital human provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the meditation training method based on virtual digital human.

[0181] Embodiment 4

[0182] See also Figure 7 , showing a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0183] like Figure 7 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0184] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0185] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the meditation training method based on a virtual digital person.

[0186] In some embodiments, the meditation training method based on the virtual digital person can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the meditation training method based on the virtual digital person described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the meditation training method based on the virtual digital person in any other appropriate manner (for example, by means of firmware).

[0187] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0188] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0189] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0190] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0191] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0192] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0193] Embodiment 5

[0194] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the meditation training method based on a virtual digital human as provided in any embodiment of the present invention.

[0195] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0196] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0197] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A meditation training method based on virtual digital human, characterized in that: include: When the user is doing mindfulness meditation training, collecting the user's electroencephalogram signal; evaluating the user's concentration level during mindfulness meditation training based on the EEG signal; Loading a meditation scene that provides feedback on the user's mindfulness meditation training; loading a virtual digital human in the meditation scene; When controlling the change of the meditation scene according to the concentration level, generating meditation voice data for guiding the user to perform mindfulness meditation training in the meditation scene according to the concentration level; The facial expression and / or body movement of the virtual digital person is controlled according to the concentration level, and the virtual digital person is controlled to play the meditation voice data to guide the user to perform mindfulness meditation training in the meditation scene.

2. The method according to claim 1, characterized in that The generating of meditation voice data for guiding the user's mindfulness meditation training in the meditation scene according to the concentration level includes: Mapping the concentration level to the meditation state of the user during mindfulness meditation training; When the meditation state is a preset target state, extracting a subject word from the meditation scene; Using the subject words to construct first guiding text information for providing feedback on the meditation state in the meditation scene; Inputting the first guiding text information into a preset language model to generate meditation text information; Counting the duration of the target state; If the duration exceeds a time threshold configured for the target state, the meditation text information is converted into meditation voice data for guiding the user in the target state to perform mindfulness meditation training in the meditation scene.

3. The method according to claim 2, characterized in that Mapping the concentration level to the meditation state of the user during mindfulness meditation training includes: Determine a first interval, a second interval, and a third interval; the value in the first interval is greater than the value in the second interval, and the value in the second interval is greater than the value in the third interval; When the concentration level is within the first interval, determining that the meditation state of the user during the mindfulness meditation training is an excellent state; When the concentration level is within the second interval, determining that the meditation state of the user during the mindfulness meditation training is a stable state; When the concentration level is within the third interval, it is determined that the meditation state of the user during the mindfulness meditation training is a bad state.

4. The method according to claim 3, characterized in that The target state includes the good state and the bad state; the step of inputting the first guidance text information into a preset language model to generate meditation text information includes: When the meditation state is the excellent state, inputting the first guidance text information into a preset language model to generate meditation text information with an encouraging emotion; When the meditation state is the bad state, the first guidance text information is input into a preset language model to generate meditation text information with the emotion of reminder.

5. The method according to claim 2, characterized in that: The first guiding text information for providing feedback on the meditation state in the meditation scene using the subject word includes: Loading a knowledge base; the knowledge base contains scene text information for describing each meditation scene and a scene text vector converted from the scene text information; Using the subject words and the meditation state to construct question text information for providing feedback on the meditation state in the meditation scene; Converting the question text information into a question text vector; Input the question text vector into a preset vector search service, and search the scene text vector similar to the question text vector in the knowledge base as a target text vector; Extracting the scene text information corresponding to the target text vector from the knowledge base as target text information; The target text information and the question text information are used to construct first guiding text information for providing feedback on the meditation state in the meditation scene.

6. The method according to claim 1, characterized in that The controlling of the facial expression and / or body movement of the virtual digital person according to the degree of concentration includes: Querying controllers configured for parts of the face and / or limbs of the virtual digital person; querying a parameter amplitude configured for the controller; Mapping the attention integration degree to the parameter amplitude to obtain a parameter value; The parameter value is input into the controller to adjust the part, so as to control the facial expression and / or body movement of the virtual digital person to change from negative emotion to positive emotion when the concentration level changes from low to high.

7. The method according to any one of claims 1 to 6, characterized in that Also includes: Collecting first interactive voice data spoken by the user; generating second interactive voice data in reply to the first interactive voice data; The virtual digital human is controlled to play the second interactive voice data to interact with the user in the meditation scene.

8. The method according to claim 7, characterized in that The generating second interactive voice data replying to the first interactive voice data includes: Converting the first interactive voice data into first interactive text information; Using the first interactive text information to construct second guidance text information; inputting the second guidance text information into a preset language model to generate second interactive text information in reply to the first interactive text information; The second interactive text information is converted into second interactive voice data that responds to the first interactive voice data.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the meditation training method based on a virtual digital human as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the meditation training method based on a virtual digital human as described in any one of claims 1 to 8 is implemented.

Images