AI-based psychological counseling methods, devices, equipment, and storage media

Abstract

The present invention relates to an AI-based psychological counseling method, which aims to provide personalized psychological counseling services through intelligent technology. The present invention first obtains the user's voice data and converts it into text data using automatic speech recognition technology. The user's voice and text data are then analyzed to extract user characteristics, including gender, age, and emotional characteristics. Based on these analysis results, a prompt word template is generated to guide the target psychological counseling model to generate personalized text-based psychological counseling suggestions that meet the user's needs. Through an automated and intelligent analysis process, the present invention significantly improves the real-time and targeted nature of psychological counseling, and can provide users with more accurate mental health support.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an AI-based psychological counseling method, device, equipment, and storage medium. Background Art

[0002] In existing technologies, psychological counseling services are mainly carried out through traditional face-to-face communication. Although this method can effectively deal with various psychological problems, it also has many shortcomings, especially when responding to the growing demand for mental health.

[0003] Traditional psychological counseling relies on face-to-face interaction between counselors and users, which severely limits the reach of services. Users typically need to make appointments and travel to specific locations for consultations, which imposes significant time and geographical constraints. This makes it particularly difficult for users in remote or resource-poor areas to receive timely and effective psychological support. Furthermore, due to limited counselor resources, users often have long wait times, which reduces the timeliness and effectiveness of psychological interventions.

[0004] Traditional psychological counseling methods also have limitations in providing personalized services. Counselors often rely on a few meetings to understand their clients, making it difficult to gain a deep understanding of their clients' long-term emotional changes and psychological patterns in a short period of time, thereby providing highly personalized advice. Furthermore, counselors' subjective judgments can lead to inconsistent advice quality, making it difficult to ensure consistency and professionalism.

[0005] In traditional psychological counseling, data such as users' emotional changes and feedback is often not systematically collected and analyzed. This lack of data makes it difficult for counselors to track emotional trends and adjust and optimize advice in subsequent sessions. The lack of an effective data feedback mechanism makes it difficult to continuously improve counseling effectiveness.

[0006] Face-to-face psychological counseling services struggle to provide 24 / 7 real-time responses. When users encounter urgent psychological issues outside of working hours, they often struggle to get timely help. This shortcoming can cause users to miss the optimal opportunity for intervention, exacerbating their psychological problems. Summary of the Invention

[0007] The main purpose of the present invention is to provide an AI-based psychological counseling method, device, equipment and storage medium, aiming to solve the technical problem that existing psychological counseling methods are unable to automatically acquire and analyze users' voice data and emotional characteristics in real time to generate personalized psychological counseling suggestions.

[0008] To achieve the above objectives, the present invention provides an AI-based psychological consultation method, comprising:

[0009] Acquire user voice data, convert the user voice data into text data, and analyze the user voice data to identify user feature information, including gender, age, and emotional characteristics;

[0010] generating a prompt word template according to the text data and the feature information, wherein the prompt word template is used to guide the target psychological counseling model to generate psychological counseling suggestions;

[0011] The text data and the prompt word template are input into a target psychological counseling model to generate personalized text psychological counseling suggestions.

[0012] In one embodiment, before inputting the text data and the prompt word template into the target psychological counseling model, the method further includes:

[0013] Obtain psychological data and perform structured processing to generate knowledge base documents that can be used by language models;

[0014] The knowledge base document is input into the artificial intelligence framework and combined with the preset language model to generate the target psychological counseling model.

[0015] In one embodiment, after generating the target psychological consultation model, the method further includes:

[0016] Record the user's emotional changes, user feedback, and the actual effect of consultation suggestions for each consultation;

[0017] Generate new knowledge entries based on the recorded information, and update the knowledge base document using the new knowledge entries;

[0018] Utilize the updated knowledge base documentation to adjust the target psychological counseling model.

[0019] In one embodiment, after generating personalized text psychological counseling suggestions, the method further includes:

[0020] Converting the text psychological counseling suggestions into voice psychological counseling suggestions through text-to-speech technology, and using the voice psychological counseling suggestions to provide feedback to the user on the psychological counseling;

[0021] Adjusting the timbre and pitch of the voice psychological counseling suggestion according to the characteristic information of the user;

[0022] The voice psychological counseling advice is played to the user via a playback device.

[0023] In one embodiment, analyzing the user voice data to identify the user's characteristic information includes:

[0024] extracting basic frequency components from the user voice data, the basic frequency components including high-pitched frequencies and pitches, and inferring the user's gender and age characteristics based on the basic frequency components;

[0025] The pitch fluctuation of the user's voice data is analyzed to identify the user's emotional characteristics and optimize gender characteristics and age characteristics.

[0026] In one embodiment, the text data and the prompt word template are input into a target psychological counseling model to generate personalized text psychological counseling suggestions, including:

[0027] Obtaining the user's historical consultation records, which include the user's historical text data, historical text psychological consultation suggestions, and user feedback information;

[0028] The historical consultation records are analyzed to generate user behavior and emotion pattern analysis results, and the text data and the prompt word template are combined to input the target psychological consultation model to generate the personalized text psychological consultation suggestions.

[0029] In one embodiment, after generating personalized text psychological counseling suggestions, the method further includes:

[0030] Collect data statistics on the user's consultation records within a preset period, including statistics on the content of each consultation, user feedback, and emotional changes;

[0031] Generate a consultation report containing emotional change trends and consultation effect evaluation based on statistical data, and generate personalized mental health management suggestions based on the consultation report;

[0032] The personalized mental health management suggestions are fed back to the user in text and / or voice form.

[0033] Furthermore, to achieve the above-mentioned purpose, the present invention also provides an AI-based psychological consultation device, comprising:

[0034] A voice processing module acquires user voice data, converts the user voice data into text data, and analyzes the user voice data to identify user feature information, including gender, age, and emotional characteristics;

[0035] A feature extraction module generates a prompt word template based on the text data and the feature information, wherein the prompt word template is used to guide the target psychological counseling model to generate psychological counseling suggestions;

[0036] The consultation generation module inputs the text data and the prompt word template into the target psychological consultation model to generate personalized text psychological consultation suggestions.

[0037] Furthermore, to achieve the above-mentioned purpose, the present invention also provides an AI-based psychological counseling device, which includes a memory, a processor, and an AI-based psychological counseling program stored in the memory and executable on the processor. When the AI-based psychological counseling program is executed by the processor, the steps of the AI-based psychological counseling method as described above are implemented.

[0038] Furthermore, to achieve the above-mentioned purpose, the present invention also provides a computer storage medium, on which an AI-based psychological counseling program is stored. When the AI-based psychological counseling program is executed by a processor, the steps of the AI-based psychological counseling method as described above are implemented.

[0039] Beneficial effects: The present invention relates to an AI-based psychological counseling method, which aims to provide personalized psychological counseling services through intelligent technology. The present invention first obtains the user's voice data and converts it into text data through automatic speech recognition technology. The user's voice and text data are then analyzed to extract user feature information including gender, age, emotional characteristics, etc. Based on these analysis results, a prompt word template is generated to guide the target psychological counseling model to generate personalized text psychological counseling suggestions that meet user needs. The present invention significantly improves the real-time and targeted nature of psychological counseling through automated and intelligent analysis processes, and can provide users with more accurate mental health support. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0041] Figure 1 This is a flow chart of an embodiment of an AI-based psychological consultation method of the present invention;

[0042] Figure 2 This is a schematic diagram of the functional modules of a preferred embodiment of the AI-based psychological counseling device of the present invention;

[0043] Figure 3 This is a structural diagram of the device hardware operating environment involved in the embodiment of the AI-based psychological counseling device of the present invention. DETAILED DESCRIPTION

[0044] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0045] It should be noted that in existing technologies, psychological counseling services are mainly carried out through traditional face-to-face communication. Although this method can effectively deal with various psychological problems, it also has many shortcomings, especially when responding to the growing demand for mental health.

[0046] Traditional psychological counseling relies on face-to-face interaction between counselors and users, which severely limits the reach of services. Users typically need to make appointments and travel to specific locations for consultations, which imposes significant time and geographical constraints. This makes it particularly difficult for users in remote or resource-poor areas to receive timely and effective psychological support. Furthermore, due to limited counselor resources, users often have long wait times, which reduces the timeliness and effectiveness of psychological interventions.

[0047] Traditional psychological counseling methods also have limitations in providing personalized services. Counselors often rely on a few meetings to understand their clients, making it difficult to gain a deep understanding of their clients' long-term emotional changes and psychological patterns in a short period of time, thereby providing highly personalized advice. Furthermore, counselors' subjective judgments can lead to inconsistent advice quality, making it difficult to ensure consistency and professionalism.

[0048] In traditional psychological counseling, data such as users' emotional changes and feedback is often not systematically collected and analyzed. This lack of data makes it difficult for counselors to track emotional trends and adjust and optimize advice in subsequent sessions. The lack of an effective data feedback mechanism makes it difficult to continuously improve counseling effectiveness.

[0049] Face-to-face psychological counseling services struggle to provide 24 / 7 real-time responses. When users encounter urgent psychological issues outside of working hours, they often struggle to get timely help. This shortcoming can cause users to miss the optimal opportunity for intervention, exacerbating their psychological problems.

[0050] See also Figure 1 , Figure 1 This is a flowchart of an embodiment of an AI-based psychological counseling method provided by the present invention. It should be noted that although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than shown here.

[0051] like Figure 1 As shown, the AI-based psychological consultation method proposed by the present invention includes the following steps:

[0052] S10, acquiring user voice data, converting the user voice data into text data, and analyzing the user voice data to identify user feature information, the feature information including gender, age, and emotional features;

[0053] In this embodiment, the user's voice input can be converted into machine-processable text data through Automatic Speech Recognition (ASR) technology. This process involves multiple core technical links, including voice signal processing, noise elimination, voiceprint recognition, etc.

[0054] Multi-level analysis of the user's voice characteristics is performed to extract gender, age, and emotional characteristics. This characteristic information is the key input for generating personalized psychological counseling recommendations. Specifically, gender and age characteristics can be inferred from voiceprint features (such as frequency and pitch), while emotional characteristics can be identified through voice parameters such as pitch fluctuation, speaking speed, and tone.

[0055] In one specific embodiment, the basic automatic speech recognition and feature extraction method includes:

[0056] Acquiring voice data: Users input voice data into the system through a microphone or smart device, and the data is captured in real time by the voice acquisition module.

[0057] Voice data conversion: The system uses automatic speech recognition technology to convert captured voice signals into text data. ASR technology achieves efficient and accurate transcription by matching the voice sound wave signal with a preset voice model.

[0058] Feature Extraction: After text is generated, the system performs feature analysis on the raw voice data, including frequency and pitch analysis, to extract the user's gender and age. Furthermore, the system uses a sentiment analysis module to detect emotional states in the voice, such as anxiety, anger, and calmness.

[0059] In another specific embodiment, the method based on enhanced speech feature analysis includes:

[0060] Acquiring voice data: Users input voice through the high-quality microphone of the smart device. The system will pre-process it according to the environmental noise conditions to reduce the interference of background noise.

[0061] Voice data conversion: The system not only uses ASR technology to convert speech into text, but also utilizes multimodal fusion technology to combine speech with other perceptual information (such as facial expressions, heart rate, etc.) to improve the accuracy of text transcription.

[0062] Multi-level feature extraction: The system uses a deep learning model to comprehensively analyze user voice and text data, further refining the classification of gender, age, and emotional characteristics. For example, by using specific frequency components and tone characteristics in speech, the system can identify changes in user emotions in specific situations and dynamically adjust analysis strategies.

[0063] In other specific embodiments, methods based on real-time emotional state monitoring and feedback include:

[0064] Acquiring voice data: Users input information through voice, and the system will monitor the emotional state in the voice in real time and mark the emotional fluctuations when capturing the voice.

[0065] Voice data conversion: While converting voice to text, the system performs real-time analysis of the emotional fluctuations in the voice and synchronizes the analysis results with the text data.

[0066] Dynamic feature extraction: The system combines historical user emotion data with current voice input and continuously adjusts feature extraction weights through a real-time updated model to identify more accurate emotion signatures. This approach is particularly suitable for scenarios where the user's emotional state changes rapidly.

[0067] Example description:

[0068] Users interact with the system through a psychological counseling app on their smartphone. They express their current anxiety, and the system captures their voice data through a microphone and instantly converts it into text. During the speech recognition process, ASR technology accurately transcribes each word of the speech while eliminating background noise.

[0069] While generating text, the system analyzes the user's voice, identifies higher-frequency voice components, and combines pitch fluctuations to infer that the user is a young woman who shows obvious anxiety and uneasiness.

[0070] Based on this information, the system generates a customized prompt template containing specific coping strategies and encouraging phrases for anxiety. This template, along with the user's text data, is then fed into the targeted psychological counseling model to generate personalized text-based counseling advice, including deep breathing exercises and several practical relaxation techniques.

[0071] Finally, the system converts the generated suggestions into speech through text-to-speech technology, gently feeds back to the user, and displays the corresponding text suggestions on the application interface.

[0072] Through ASR technology and voice data analysis, the system can capture and process users' emotional states in real time, generating timely and effective psychological counseling recommendations. This addresses the slow response times and lack of personalization inherent in traditional counseling. By analyzing users' gender, age, and emotional characteristics, the system can provide highly personalized counseling services, ensuring recommendations are tailored to their actual needs and increasing the effectiveness of counseling.

[0073] S20, generating a prompt word template based on the text data and the feature information, wherein the prompt word template is used to guide the target psychological counseling model to generate psychological counseling suggestions;

[0074] In this example, the user's text data is combined with extracted feature information (such as gender, age, and emotional characteristics) to generate a template that guides the target psychological counseling model to generate personalized recommendations. The prompt template is a structured data input that generates corresponding guidance content based on the user's specific situation (such as current emotional state and personalized needs), ensuring that the psychological counseling model can generate more accurate and personalized recommendations.

[0075] In one specific embodiment, the rule-based prompt word template generation method includes:

[0076] Feature information matching: The system first matches the user's text data and feature information (such as gender, age, and emotional characteristics) against a pre-set rule library. For example, if the user is detected to be depressed and a middle-aged woman, the system may select a template related to anxiety relief.

[0077] Template generation: The system selects terms from a pre-set prompt word library that match the criteria and generates a prompt word template. This template might include terms like "anxiety management techniques" or "emotional support suggestions," which guide the model in generating corresponding psychological counseling recommendations.

[0078] In another specific embodiment, the method of generating the prompt word template based on machine learning includes:

[0079] Data Input and Model Training: The system uses a large amount of user data to train the prompt word generation model. The model learns how to automatically generate prompt word templates based on user text and feature information. Through deep learning technology, the model can identify more complex user emotions and needs and generate more customized prompt words.

[0080] Dynamic adjustment: The system dynamically adjusts the prompt word template based on real-time feedback and new data to ensure that the generated psychological counseling suggestions can reflect the user's latest emotional state and needs.

[0081] In other specific implementations, methods for generating prompt word templates based on multimodal information fusion include:

[0082] Multimodal information acquisition: In addition to text data and voice features, the system can also combine multimodal information such as the user's expression and heart rate to generate a more comprehensive prompt word template.

[0083] Template Optimization: The system integrates multimodal information and generates prompt word templates through comprehensive analysis, guiding the psychological counseling model to produce more detailed and accurate psychological counseling advice. For example, the system can combine tension detected in speech and anxiety in facial expressions to generate targeted counseling prompts.

[0084] Example description:

[0085] The user inputs voice data through a smart device, which the system converts into text. The system then detects that the user is expressing anxiety during the consultation. The user's profile indicates she is a woman in her 30s. Based on this information, the system generates a prompt template containing topics like "anxiety management techniques," "mindfulness practice guidance," and "positive emotion reinforcement."

[0086] These prompt word templates were fed into the target psychological counseling model, which generated a personalized psychological counseling recommendation. It recommended that the user alleviate anxiety through deep breathing exercises and mindfulness meditation, and provided some practical steps. In addition, the system recommended that the user keep a daily emotional journal to help her better manage her emotions.

[0087] By generating prompt word templates, we can generate highly customized psychological counseling suggestions based on the user's specific situation, significantly improving the personalization of the service. This simplifies the process of model-generated suggestions and improves the accuracy and efficiency of generated suggestions through structured input.

[0088] S30, inputting the text data and the prompt word template into a target psychological counseling model to generate personalized text psychological counseling suggestions.

[0089] In this embodiment, the target psychological counseling model is a large-scale language model based on artificial intelligence (AI) technology. It has been trained on a wealth of psychological knowledge and counseling cases, and is able to generate counseling recommendations tailored to specific user needs based on input text data and prompt word templates. This process involves not only analyzing the user's current input but also understanding and applying the prompt word templates to ensure that the generated recommendations are highly consistent with the user's emotional state and specific needs.

[0090] In one embodiment, the method of generating recommendations based on the standard model includes:

[0091] Data Input: The system inputs the user's text data and a prompt word template generated based on the user's characteristics into the target psychological counseling model. This model may be a specially optimized large-scale pre-trained language model such as GPT or BERT, which already has strong language understanding and generation capabilities.

[0092] Suggestion Generation: The model performs semantic understanding based on the input data and prompt word templates, and combines this with the content of the internal knowledge base to generate personalized text-based psychological counseling suggestions that meet the user's current needs. These suggestions may include emotional support, emotion management methods, and daily mental health maintenance strategies.

[0093] In another specific embodiment, the method of generating suggestions based on the context-aware model includes:

[0094] Context-aware input: The system inputs not only the current text data and prompt word templates, but also the user's historical interaction records, enabling the model to understand the context of the current conversation. This helps generate more consistent and coherent psychological counseling recommendations, especially across multiple consecutive consultations.

[0095] Emotion-matching generation: Based on the prompt word template, the model focuses on the user's current emotional state and generates more empathetic suggestions. For example, if the user is anxious, the model may generate encouraging or soothing suggestions.

[0096] In other specific implementations, methods for generating suggestions based on the real-time feedback model include:

[0097] Dynamic Input Adjustment: During the recommendation generation process, the system dynamically adjusts the weighting of text data and prompt word templates based on real-time user feedback. For example, if a user's mood changes during a consultation, the system can adjust the input data to encourage the model to generate recommendations that are more appropriate for the user's current state.

[0098] Generation and feedback loop: After the model generates preliminary recommendations, the system can immediately provide feedback to the user and further adjust the recommendations based on the user's response. This real-time interaction makes the generated psychological counseling recommendations more targeted and timely.

[0099] Example description:

[0100] The user enters the phrase "I've been very stressed lately and feel a bit short of breath" via voice. The system inputs this text data, along with the user's previously detected anxiety, into the targeted psychological counseling model. Template prompts include "anxiety management techniques" and "breathing control methods."

[0101] The model combines the user's text data with a prompt word template to generate a personalized suggestion: "When you feel overly stressed, try deep breathing exercises. Find a quiet place, inhale and exhale slowly, and try to focus on your breathing. Also, you can organize your thoughts by writing in a journal to help you better cope with stress."

[0102] The generated text suggestions are presented to the user through the application interface, and suggest that the user can reduce anxiety through daily exercises.

[0103] By combining text data with prompt word templates, the targeted psychological counseling model generates highly personalized advice, ensuring that users' emotional and psychological needs are accurately addressed. Leveraging the powerful computing power of AI models, the system generates personalized counseling recommendations tailored to user needs in record time, significantly improving counseling efficiency and response speed. This real-time generation and feedback capability enables the system to provide more personalized and immediate psychological support, enhancing user experience and satisfaction.

[0104] The present invention relates to an AI-based psychological counseling method, which aims to provide personalized psychological counseling services through intelligent technology. The present invention first obtains the user's voice data and converts it into text data using automatic speech recognition technology. The user's voice and text data are then analyzed to extract user characteristics, including gender, age, and emotional characteristics. Based on these analysis results, a prompt word template is generated to guide the target psychological counseling model to generate personalized text-based psychological counseling suggestions that meet the user's needs. Through an automated and intelligent analysis process, the present invention significantly improves the real-time and targeted nature of psychological counseling, and can provide users with more accurate mental health support.

[0105] In one embodiment, in the above S30, before inputting the text data and the prompt word template into the target psychological counseling model, the process further includes:

[0106] a1. Obtain psychological data and perform structural processing to generate knowledge base documents that can be used by language models;

[0107] a2. Input the knowledge base document into the artificial intelligence framework and combine it with the preset language model to generate the target psychological counseling model.

[0108] In this embodiment, before inputting text data and prompt word templates into the target psychological counseling model, it is necessary to first obtain psychological data and structure it to generate a knowledge base document for use by the language model. This step is fundamental to ensuring that the target psychological counseling model can accurately generate personalized recommendations. By building a rich and structured knowledge base, the system can provide the model with professional and reliable psychological background knowledge, enhancing the quality and scientific nature of the generated recommendations.

[0109] Acquiring psychology data involves collecting a large number of psychology books, research papers, case studies, consultation conversation records, etc. After cleaning, classifying, annotating, and structuring this data, the generated knowledge base documents can provide accurate reference for the language model in the artificial intelligence framework.

[0110] The goal of feeding knowledge base documents into an AI framework and combining them with a pre-set language model is to train or fine-tune the target psychological counseling model, enabling it to understand and apply psychological knowledge. This allows the model to not only generate fluent recommendations but also ensure they align with psychological theory and practice.

[0111] In one specific implementation, the method of building and generating a model based on a basic knowledge base includes:

[0112] Psychology data collection: The system extracts important data from public psychology literature, books, and research papers to ensure that the knowledge base contains rich psychological theories and practical cases.

[0113] Data cleaning and structuring: The system removes noise, duplicates, classifies, and labels the collected psychology data. The processed data is then structured into knowledge base documents to accommodate the input format of language models, such as knowledge graphs or structured databases.

[0114] Model training: Input structured knowledge base documents into the artificial intelligence framework and train or fine-tune them in combination with preset language models (such as GPT, BERT, etc.) to enable the model to generate psychological counseling advice.

[0115] In another specific embodiment, the method of constructing a knowledge base based on domain expert review includes:

[0116] Expert participation in knowledge base construction: During the data cleaning and structuring phase, experts in the field of psychology are brought in to review and ensure the professionalism and reliability of the knowledge base content. Experts can also annotate the data or add additional knowledge items to make the knowledge base more complete.

[0117] Model fine-tuning: After inputting the knowledge base documents into the artificial intelligence framework, the system fine-tunes the language model based on feedback from domain experts, so that the model can more accurately apply psychological knowledge when generating psychological counseling recommendations.

[0118] In other specific implementations, methods based on dynamic knowledge base updating and model generation include:

[0119] Real-time data updates: The system extracts data from the latest psychology research and consulting cases periodically or in real time to dynamically update the knowledge base. The updated knowledge base is restructured and used to fine-tune the existing language model.

[0120] Model adaptive training: After each knowledge base update, the system will perform adaptive training on the target psychological counseling model to ensure that the model can apply the latest psychological knowledge and generate psychological counseling suggestions that are in line with the development of the times and new discoveries.

[0121] Example description:

[0122] The system collects a wealth of psychological data from authoritative psychology journals, research databases, and clinical case reports. This data includes the latest research findings in anxiety management, depression treatment, cognitive behavioral therapy, and other areas. The system first cleans and structures this data, converting it into a knowledge graph format. Once the knowledge base is complete, the system inputs it into a GPT-based artificial intelligence framework and fine-tunes it using a pre-defined language model.

[0123] The trained target psychological counseling model can generate more scientific and personalized suggestions. For example, when a user expresses anxiety, the model can recommend deep breathing and mindfulness exercises based on the latest psychological research, while also providing specific strategies for coping with anxiety in daily life.

[0124] This embodiment acquires and structures psychological data to construct a scientific and professional knowledge base, ensuring that the generated psychological counseling recommendations are consistent with psychological theory. Combining this structured knowledge base with a pre-set language model, the target counseling model can generate more accurate and personalized counseling recommendations to meet the actual needs of users. By regularly updating the knowledge base and adaptively training the model, the system can maintain the timeliness and cutting-edge nature of counseling recommendations, ensuring that users receive the highest-quality mental health support.

[0125] In one embodiment, in a2 above, after generating the target psychological counseling model, the method further includes:

[0126] b1, record the user's emotional changes, user feedback information, and the actual effect of the consultation suggestions for each consultation;

[0127] b2, generating new knowledge entries based on the recorded information, and updating the knowledge base document using the new knowledge entries;

[0128] b3. Use the updated knowledge base documents to adjust the target psychological counseling model.

[0129] In this embodiment, after generating the target psychological counseling model, the system further records user emotional changes, user feedback, and the actual effectiveness of counseling recommendations during each consultation. This recorded information is used to generate new knowledge items and update the knowledge base document. This process is key to dynamically adjusting and optimizing the target psychological counseling model, enabling the model to continuously learn and adapt to changing user needs, thereby improving the accuracy and effectiveness of counseling recommendations.

[0130] After each psychological consultation, the user's emotional changes during the consultation process (such as the transition from anxiety to relaxation) and the user's feedback on the consultation suggestions (such as whether the user adopted the suggestions and the effectiveness). This data can provide a basis for generating new knowledge items.

[0131] Based on this recorded data, the system generates new knowledge items that reflect the user's emotional changes and behavioral responses in specific situations. These new knowledge items are then integrated into the existing knowledge base documents, ensuring that the knowledge base can continuously reflect the latest user behavior and psychological developments.

[0132] Using the updated knowledge base documents, the system can adjust and optimize the target psychological counseling model, so that it can generate more accurate and personalized psychological counseling suggestions in future counseling processes.

[0133] In one specific embodiment, the method based on regular recording and knowledge base updating includes:

[0134] Emotion and feedback records: After each psychological consultation, the system records the user's emotional changes and feedback information. The recorded information includes the user's emotional fluctuations during the consultation process and the degree of acceptance of the generated suggestions.

[0135] Knowledge item generation: The system generates new knowledge items based on recorded data. These items may include new emotional response patterns, user response methods in specific situations, etc.

[0136] Knowledge base update: Integrate the generated knowledge entries into the existing knowledge base documents to ensure that the knowledge base always contains the latest user behavior and feedback information.

[0137] Model adjustment: After the knowledge base is updated, the system will fine-tune the target psychological counseling model so that it can adapt to the content of the new knowledge items and improve the quality of counseling advice.

[0138] In another specific embodiment, the method based on real-time dynamic update and model optimization includes:

[0139] Real-time data recording: During the psychological consultation process, the system records the user's emotional changes and feedback information in real time. These data will be used to generate new knowledge entries immediately after the consultation.

[0140] Automated knowledge entry generation: The system uses machine learning algorithms to automatically convert real-time recorded data into new knowledge entries and dynamically update the knowledge base.

[0141] Continuous model optimization: The system continuously monitors the performance of the model and, after the knowledge base is updated, adjusts and optimizes the reasoning and generation logic of the target psychological counseling model in real time to ensure that the model can quickly adapt to the user's new needs.

[0142] In other specific embodiments, the personalized feedback loop and knowledge base adaptation methods include:

[0143] Personalized feedback loop: The system generates personalized feedback mechanisms for different users, recording detailed feedback information based on their long-term behavior patterns and emotional changes. This information will serve as the core data source for generating new knowledge items.

[0144] Adaptive knowledge base updates: The system adaptively updates the knowledge base based on personalized feedback and data analysis results. This approach enables the knowledge base to more accurately reflect the user's individual state of mind and needs.

[0145] Model refinement: Based on the updated knowledge base, the system refines the target psychological counseling model to ensure that the generated counseling suggestions can accurately match the user's current status and long-term needs.

[0146] Example description:

[0147] During a psychological consultation, a user expressed mild anxiety and, afterward, reported that a recommended breathing technique had been very helpful. The system recorded the user's emotional changes during the consultation, from initial anxiety to final relaxation, and also recorded the user's positive feedback on the suggestions.

[0148] Based on this data, the system generated new knowledge items, including "Anxious users' positive response to breathing regulation" and "The effectiveness of guiding users to breathe regulation under mild anxiety." These knowledge items were integrated into the existing knowledge base and used to fine-tune the target psychological counseling model.

[0149] In the next consultation, when the system detects similar anxiety, the model is more inclined to generate suggestions related to breathing regulation and can further optimize the content of the suggestions based on user feedback.

[0150] By recording the data from each consultation and updating the knowledge base, this embodiment enables the system to continuously learn from users' behavioral patterns and emotional responses, thereby continuously adapting and optimizing the psychological counseling model and generating more precise recommendations. New knowledge items reflect the user's individual psychological state and needs, enabling the system to provide more personalized recommendations in future consultations and improve user satisfaction. Knowledge base updates and model fine-tuning ensure that the system remains scientific and cutting-edge, ensuring high-quality mental health support for different users and situations.

[0151] In one embodiment, in the above S30, after generating the personalized text psychological counseling suggestion, the following step is further included:

[0152] c1, converting the text psychological counseling suggestions into voice psychological counseling suggestions through text-to-speech technology, and the voice psychological counseling suggestions are used to provide feedback on the user's psychological counseling;

[0153] c2, adjusting the timbre and pitch of the voice psychological counseling suggestion according to the characteristic information of the user;

[0154] c3. Play the voice psychological counseling advice to the user through a playback device.

[0155] In this embodiment, after generating personalized text-based psychological counseling suggestions, the system also converts these text-based suggestions into voice suggestions using text-to-speech (TTS) technology. The core of this step is to provide psychological counseling suggestions to users in a more natural and friendly way, especially when users need to obtain advice through hearing. In this way, the system can not only provide counseling suggestions in text form, but also respond to user needs in real time and flexibly through voice, thereby improving the user experience.

[0156] Text-to-speech technology converts text-generated psychological counseling advice into natural language speech output using speech synthesis technology. TTS technology can adjust the voice's timbre, speaking speed, and emotional expression based on the user's gender, age, and emotional state, making the voice advice more tailored to the user's psychological state and acceptance habits.

[0157] In one specific implementation, the standard TTS conversion and feedback method includes:

[0158] TTS conversion: The system inputs the generated text psychological counseling suggestions into the TTS module, and the TTS module converts the text content into speech according to the preset speech synthesis parameters (such as speaking speed, timbre, and pitch).

[0159] Voice feedback: The system plays the generated psychological counseling suggestions to the user through speakers or headphones, ensuring that the user can receive the suggestions in the form of voice. This method is particularly suitable for users who are on the move or find it inconvenient to read.

[0160] In another specific embodiment, the method of emotion-enhanced TTS conversion includes:

[0161] Emotional Adaptive Conversion: During the TTS conversion process, the system dynamically adjusts the emotional expression of the voice based on the user's current emotional state and psychological characteristics. For example, if the user is anxious, the system can select a calmer and more soothing voice style.

[0162] Emotion-matching feedback: The generated voice suggestions are not only accurate in content, but also can further enhance the user's psychological acceptance and comfort through voice tone and emotion adjustment.

[0163] In other specific implementations, methods based on multilingual TTS support include:

[0164] Multilingual Conversion: The system supports TTS conversion in multiple languages ​​and can generate corresponding voice suggestions based on the user's language preferences. For example, the system can automatically select the corresponding TTS language pack based on the user's voice input language and generate voice suggestions that suit the user's language habits.

[0165] Personalized language feedback: The system can provide personalized voice suggestion services to users with different language backgrounds through multilingual support, improving the system's applicability and user satisfaction

[0166] Example description:

[0167] The user generated a text-based psychological counseling suggestion for coping with anxiety, including tips like "deep breathing exercises" and "emotional journaling." The system fed this text into the TTS module, which selected a gentle female voice appropriate to the user's gender and age, and adjusted the speech speed to match the user's current anxiety.

[0168] The generated voice suggestions are played in real time through the user's headphones. Gentle voice guidance guides users through deep breathing exercises and encourages them to organize their emotions by writing in an emotional journal. Users not only hear the clear guidance but also feel the soothing emotion conveyed by the voice, significantly enhancing their acceptance and effectiveness of the suggestions.

[0169] By converting text-based psychological counseling advice into voice, this embodiment enables the system to interact with users in a more natural and approachable manner, especially for users who struggle with reading or prefer auditory information, thereby improving user acceptance and satisfaction. Through emotion-enhanced TTS conversion, the system can adjust the emotional expression of voice output based on the user's current psychological state, making the advice more tailored to the user's psychological needs and further improving the effectiveness of psychological counseling. Multilingual support ensures that the system can provide high-quality voice advice services to users from different language backgrounds, expanding the system's scope of application and market potential.

[0170] In one embodiment, in the above S10, analyzing the user voice data and identifying the user's characteristic information includes:

[0171] d1, extracting basic frequency components from the user's voice data, the basic frequency components including high-pitched frequencies and pitches, and inferring the user's gender and age characteristics based on the basic frequency components;

[0172] d2, analyzing the pitch fluctuation of the user's voice data, identifying the user's emotional characteristics and optimizing the gender characteristics and age characteristics.

[0173] In this embodiment, when analyzing user voice data, the system extracts the fundamental frequency components of the voice, including high-pitched frequencies and pitch, to infer the user's gender and age. Furthermore, the system analyzes pitch fluctuations in the voice to identify the user's emotional characteristics, and uses these emotional characteristics to further refine gender and age recognition.

[0174] Treble frequency usually refers to the relatively high fundamental frequency part of the speech signal. For human speech, the fundamental frequency (F0) is the frequency produced by the vibration of the vocal cords and reflects the pitch of the sound. Generally speaking:

[0175] The fundamental frequency in men is usually in the range of 85Hz to 180Hz.

[0176] The fundamental frequency in women is usually in the range of 165Hz to 255Hz.

[0177] In children, the fundamental frequency is usually above 250 Hz and can sometimes reach 400 Hz or higher.

[0178] Therefore, in gender and age recognition, high-pitched frequencies are usually defined as the frequency portion greater than 165 Hz.

[0179] In gender recognition, fundamental frequency is one of the most significant distinguishing features. Specifically:

[0180] Male voice: Usually has a lower fundamental frequency. Due to the length and thickness of the vocal cords, the fundamental frequency of men is lower, and the frequency is mainly concentrated between 85Hz and 180Hz.

[0181] Female voices: Due to their shorter and thinner vocal cords, women have a higher fundamental frequency, primarily between 165Hz and 255Hz. Therefore, if a higher fundamental frequency (e.g., above 165Hz) is detected during analysis, the system is more likely to identify the voice as female.

[0182] Fundamental frequency is also related to age:

[0183] Children: Because their vocal cords are not fully developed, children's fundamental frequencies are usually higher, usually above 250Hz.

[0184] Adults: The fundamental frequency decreases with age, especially after puberty, and then tends to stabilize.

[0185] Elderly people: In old age, relaxation of the vocal cords may cause a slight decrease in fundamental frequency, but the change is not as significant as before and after puberty.

[0186] Therefore, fundamental frequency can reflect age characteristics to a certain extent:

[0187] If a fundamental frequency above 250Hz is detected, the system may identify it as a child.

[0188] If the fundamental frequency is between 165 Hz and 250 Hz, it may be identified as a female or a late adolescent male.

[0189] The following frequency ranges can be preset for gender and age recognition:

[0190] 85Hz-180Hz: Identified as male (usually an adult male).

[0191] 165Hz-255Hz: Identified as female.

[0192] Above 250Hz: Identified as a child or pre-adolescent individual.

[0193] For example, during speech analysis, the system detected a fundamental frequency of 220Hz for the user's voice. Based on the preset frequency range, this frequency falls between 165Hz and 255Hz, leading the system to preliminarily determine that the user is likely female. Further analysis of the voice's pitch fluctuations, combined with the emotional characteristics displayed, confirms the user's gender and, based on this information, generates personalized psychological counseling recommendations.

[0194] Extracting fundamental frequency components involves frequency analysis of the voice signal. By analyzing the fundamental frequency (F0) and harmonic components in the voice signal, the system can identify the user's pitch range. These frequency components not only reflect the user's gender (generally, men have lower fundamental frequencies, while women have higher fundamental frequencies), but also provide clues about the user's age (for example, changes in vocal cords with age may cause changes in pitch).

[0195] Pitch fluctuation analysis focuses on dynamic changes in speech, particularly fluctuations in intonation, speaking rate, and volume. These factors are often closely correlated with emotion, and by analyzing these fluctuations, the system can identify the user's current emotional state, such as anxiety, anger, or calmness. Furthermore, by incorporating these emotional characteristics, the system can further optimize the recognition of gender and age characteristics, ensuring the accuracy and reliability of the analysis results.

[0196] In one specific embodiment, the method based on spectrum analysis and feature extraction includes:

[0197] Fundamental Frequency Extraction: The system performs spectral analysis on the user's voice signal, extracting the fundamental frequency and harmonic components. By analyzing these frequency components, the system can infer the user's gender (e.g., different frequency distributions for males and females) and age (e.g., different frequency distributions for children, adults, and the elderly).

[0198] Pitch Fluctuation Analysis: The system further performs time series analysis on the pitch fluctuations in the voice signal. By analyzing the continuous changes in the voice, it can identify the user's emotional state. For example, anger may be manifested as a faster speaking rate and higher pitch fluctuations.

[0199] In another specific embodiment, the method based on multimodal information fusion analysis includes:

[0200] Combining voice frequency with facial expressions: In addition to frequency analysis of voice signals, the system can also combine data from the user's facial expressions to more accurately infer gender and age. For example, by analyzing the user's voice frequency and facial features, the system can further refine its age prediction.

[0201] Emotion recognition optimization: By combining pitch fluctuations in speech and changes in facial expressions, the system can more accurately identify the user's emotional state and use this emotional information to optimize recognition results for gender and age characteristics.

[0202] In other specific implementations, methods based on dynamic adjustment and feedback mechanisms include:

[0203] Real-time frequency analysis adjustments: The system can adjust frequency analysis parameters in real time while analyzing voice data to adapt to the voice characteristics of different users. For example, when noise interference is detected in the voice signal, the system can improve the accuracy of gender and age recognition by adjusting the frequency analysis algorithm.

[0204] Feedback-based optimization: The system uses user feedback to verify and adjust gender, age, and emotion recognition results. Users can provide feedback on the system's recognition results, which the system then uses to further optimize frequency analysis and pitch fluctuation analysis.

[0205] Example description:

[0206] When a user seeks psychological counseling through a voice assistant, the system first analyzes the voice frequency, extracting the fundamental frequency and harmonic components of the voice signal. The system detects that the user's fundamental frequency is around 220Hz, which falls within the preset range of 165Hz to 255Hz, presumably inferring that the user is female. Further analysis of pitch fluctuations reveals significant emotional fluctuations in the user's voice, manifested by an increased speaking rate and a significantly higher pitch, indicating possible anxiety.

[0207] Based on these preset high-frequency characteristics and the detection results, the system generates a personalized psychological counseling recommendation, suggesting that the user try deep breathing exercises and providing some specific relaxation techniques to alleviate anxiety. The system also provides feedback to the user via voice and encourages users to provide feedback on the actual effectiveness of these suggestions later, so that the system can further optimize the recommendation generation process in the future.

[0208] By extracting the basic frequency components in the voice and analyzing pitch fluctuations, this embodiment enables the system to more accurately identify the user's gender, age, and emotional characteristics, ensuring that the generated psychological counseling recommendations meet the user's actual needs. It has the ability to conduct real-time analysis and dynamic adjustments, and can instantly adjust analysis parameters based on changes in the voice signal, improving the accuracy and reliability of the recognition results. By combining voice frequency with other modal data (such as facial expressions), the system can further optimize the recognition of gender, age, and emotional characteristics, providing more comprehensive and personalized psychological counseling services.

[0209] In one embodiment, in the above S30, the text data and the prompt word template are input into the target psychological counseling model to generate personalized text psychological counseling suggestions, including:

[0210] e1, obtaining the user's historical consultation records, which include the user's historical text data, historical text psychological consultation suggestions and user feedback information;

[0211] e2. Analyze the historical consultation records to generate user behavior and emotion pattern analysis results, combine the text data with the prompt word template and input them into the target psychological consultation model to generate the personalized text psychological consultation suggestions.

[0212] In this embodiment, when generating personalized text-based psychological counseling recommendations, the system not only relies on the current text data and prompt word templates, but also obtains the user's historical counseling records. This historical record includes the user's past text data, generated text-based psychological counseling recommendations, and user feedback. After the system analyzes these historical records, it generates an analysis of the user's behavior and emotional patterns. These analysis results, combined with the current text data and prompt word templates, are then input into the target psychological counseling model to generate more accurate and personalized psychological counseling recommendations.

[0213] By deeply analyzing historical user data, the system can identify behavioral patterns and emotional trends. For example, it can detect recurring emotional reactions or behavioral habits in similar situations and apply these patterns to current consulting recommendations, improving the accuracy and relevance of the recommendations.

[0214] User behavior and sentiment analysis involves using machine learning algorithms to perform cluster analysis and sentiment curve plotting on user history records, thereby deriving user sentiment patterns (such as patterns of mood swings and preferred coping strategies) and behavioral patterns (such as the high adoption rate of certain specific suggestions). This approach can better predict user needs in the current context and generate recommendations that are more aligned with the user's long-term psychological state.

[0215] In one specific embodiment, the method of analyzing historical records based on time series includes:

[0216] Historical record acquisition: The system acquires the user's historical consultation records, including text data, generated suggestions, and user feedback. The recorded data is arranged in chronological order to form time series data.

[0217] Behavioral Pattern Analysis: The system uses time series analysis algorithms to detect user emotional trends and behavioral patterns over time. For example, the system might identify that users exhibit higher levels of anxiety during stressful workdays and prefer certain mitigation strategies.

[0218] Suggestion generation: Combining the current text data and prompt word templates, the system inputs the user's behavior and emotional pattern analysis results into the target psychological counseling model to generate highly personalized text psychological counseling suggestions.

[0219] In another specific embodiment, the behavior and emotion pattern recognition method based on machine learning includes:

[0220] Historical record data classification: The system uses a clustering algorithm to classify historical record data, grouping similar emotional reactions and behavioral patterns together. These classification results help the system better understand the user's emotional patterns.

[0221] Emotional Curve Graphing: By analyzing the emotional tags in historical data, the system plots a user's emotional curve, reflecting patterns in their emotional changes. The system uses this curve to predict the user's current emotional state and generate corresponding recommendations.

[0222] Model optimization generation: Based on the input of current text data and prompt word templates, the system combines the analysis results of historical behavior and emotional patterns to further optimize the generated psychological counseling suggestions to make them more in line with the user's long-term needs.

[0223] In other specific embodiments, the personalized feedback loop and adaptive optimization approach include:

[0224] Dynamic feedback and record updates: The system not only analyzes historical data but also records the user's response to the current consultation in real time. The system can dynamically update the user's behavior and emotional patterns based on the latest feedback.

[0225] Personalized Analysis and Generation: The system quickly analyzes newly recorded data and integrates it with historical records to generate more personalized psychological counseling recommendations. This cycle allows the system to further optimize the accuracy of recommendations after each consultation.

[0226] Example description:

[0227] The user had repeatedly expressed anxiety about social situations in past consultations and had also expressed positive feedback on deep breathing exercises in several recommendations. The system, drawing on this historical data, used time series analysis to identify that the user's mood swings were particularly pronounced on Monday mornings, and that deep breathing exercises were most effective during these times.

[0228] During the current consultation, the user again expressed anxiety. The system combined historically high acceptance of deep breathing exercises with the current text data and the prompt word template to generate a personalized recommendation: practice a few minutes of deep breathing exercises before a social situation. The system also provided a psychological tip to help the user stay calm in social situations. This recommendation not only incorporates the user's current needs but also takes into account their long-term emotional patterns and historical feedback.

[0229] By combining historical records with current data, this embodiment generates highly personalized psychological counseling recommendations, ensuring that they not only meet the user's current needs but also align with their long-term behavioral and emotional patterns. Through continuous feedback and historical record updates, the generated recommendations are continuously optimized, improving the accuracy of counseling and user satisfaction. Through in-depth analysis of historical data, users' behavioral and emotional patterns can be understood, enabling the provision of more targeted counseling services in different contexts.

[0230] In one embodiment, in the above S30, after generating the personalized text psychological counseling suggestion, the following step is further included:

[0231] f1, collects data on the user's consultation records within a preset period, including the content of each consultation suggestion, user feedback, and emotional changes;

[0232] f2, generating a consultation report containing emotional change trends and consultation effect evaluation based on statistical data, and generating personalized mental health management suggestions based on the consultation report;

[0233] f3, feeding back the personalized mental health management suggestions to the user in text and / or voice form.

[0234] In this embodiment, after generating personalized text-based psychological counseling advice, the system also collects data on the user's counseling records within a preset period. This statistical process includes the content of each counseling session, user feedback, and emotional change data. By analyzing this data, the system can generate a counseling report that includes emotional change trends and an evaluation of counseling effectiveness. Based on this counseling report, the system further generates personalized mental health management advice and provides feedback to the user via text or voice. This process enables the system to continuously monitor and optimize the user's mental health management over a longer period of time.

[0235] We regularly aggregate and analyze user consultation records, including the amount of advice received, feedback on those suggestions (e.g., satisfaction, effectiveness), and emotional changes (e.g., mood swings, improvements or deteriorations in emotional states). These statistics provide a foundation for subsequent analysis of emotional trends and evaluation of consultation effectiveness.

[0236] By analyzing statistical data, we can identify trends in user sentiment over a specific period and assess the effectiveness of each consultation suggestion. The report will show a graph of user sentiment over time, along with the effectiveness of each suggestion in different contexts.

[0237] Based on the generated consultation report, personalized mental health management recommendations are generated. These recommendations may include emotional management strategies, mental health maintenance plans, and recommended frequency of future consultations.

[0238] In one specific embodiment, the method based on periodic data statistics and report generation includes:

[0239] Data statistics: At the end of a preset period (such as weekly or monthly), the system automatically counts all consultation records of the user within that period, including each psychological consultation suggestion generated, user feedback information, and the user's emotional changes before and after the consultation.

[0240] Report generation: The system generates a detailed consultation report based on statistical data, including a chart of user emotional trends, the adoption of suggestions, and an evaluation of the effectiveness of the consultation. The report is presented in charts and text to help users understand their mental health status during the cycle.

[0241] In another specific embodiment, the method based on dynamic trend analysis and personalized management suggestions includes:

[0242] Emotional Trend Analysis: The system uses time series analysis to identify the periodicity and trends of user emotional changes. For example, the system can identify that users experience greater mood swings on Monday mornings and express fatigue or anxiety at the end of the month. Through these analyses, the system can predict potential future emotional fluctuations.

[0243] Management suggestion generation: Based on the trend of emotional changes and the evaluation of consultation effects, the system generates personalized mental health management suggestions, such as suggesting that users increase the frequency of consultations in a specific time period, or try new emotional regulation methods.

[0244] In other specific embodiments, the method based on combining comprehensive feedback with multimodal data includes:

[0245] Multimodal data statistics: In addition to text and voice data, the system can also combine user behavior data (such as activity level, sleep quality) for comprehensive statistics and analysis to provide more comprehensive consulting reports.

[0246] Comprehensive feedback and optimization: After providing personalized management suggestions, the system allows users to provide feedback on the effectiveness of the suggestions. Based on this feedback, the system continuously optimizes subsequent management suggestions to ensure that users receive the best mental health support.

[0247] Example description:

[0248] The user received psychological counseling through the system for a month. After each session, the system recorded the generated suggestions, user feedback, and changes in their emotions. At the end of the month, the system conducted a statistical analysis of this data and generated a detailed report. The report showed that the user's emotional state was relatively stable at the beginning of the month, but showed significant anxiety in the middle and end of the month, especially during periods of high work pressure.

[0249] Based on the emotional trends reported, the system recommends increasing the frequency of deep breathing exercises during high-stress periods over the next month and meditating before bed. Furthermore, the system recommends keeping a weekly emotional journal to better manage emotions. These personalized mental health management suggestions are provided to users via voice and text feedback, helping them better cope with future emotional fluctuations.

[0250] This embodiment generates reports on users' emotional trends through regular data collection and analysis, providing users with mental health management recommendations based on long-term observations. Personalized management recommendations generated based on these reports can help users better cope with emotional fluctuations and psychological challenges, providing more targeted mental health support. Incorporating user feedback enables the system to continuously optimize management recommendations, ensuring their effectiveness and practicality, thereby improving users' mental health and satisfaction.

[0251] The present invention also provides an AI-based psychological consultation device, referring to Figure 2 , Figure 2 The following is a functional module diagram of a preferred embodiment of an AI-based psychological counseling device according to the present invention. The AI-based psychological counseling device includes:

[0252] A voice processing module acquires user voice data, converts the user voice data into text data, and analyzes the user voice data to identify user feature information, including gender, age, and emotional characteristics;

[0253] A feature extraction module generates a prompt word template based on the text data and the feature information, wherein the prompt word template is used to guide the target psychological counseling model to generate psychological counseling suggestions;

[0254] The consultation generation module inputs the text data and the prompt word template into the target psychological consultation model to generate personalized text psychological consultation suggestions.

[0255] The specific implementation of the AI-based psychological counseling device of the present invention is basically the same as the above-mentioned embodiments of the AI-based psychological counseling method, and will not be repeated here.

[0256] The present invention also provides an AI-based psychological consultation device, such as Figure 3 As shown, the AI-based psychological counseling device may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0257] Those skilled in the art will understand that Figure 3 The hardware structure of the AI-based psychological counseling device shown in the figure does not constitute a limitation on the AI-based psychological counseling device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0258] like Figure 3As shown, the memory 1005, which is a storage medium, may include an operating system, a network communication module, a user interface module, and an AI-based psychological counseling program. The operating system is a program that manages and controls AI-based psychological counseling equipment and software resources, supporting the operation of the network communication module, the user interface module, the AI-based psychological counseling program, and other programs or software. The network communication module is used to manage and control the network interface 1004; the user interface module is used to manage and control the user interface 1003.

[0259] exist Figure 3 In the hardware structure of the AI-based psychological counseling device shown, the network interface 1004 is mainly used to connect to the background server and communicate data with the background server; the user interface 1003 is mainly used to connect to the client and communicate data with the client; the processor 1001 can call the AI-based psychological counseling program stored in the memory 1005 and perform the same operations as the AI-based psychological counseling method.

[0260] The specific implementation of the AI-based psychological counseling device of the present invention is basically the same as the above-mentioned embodiments of the AI-based psychological counseling method, and will not be repeated here.

[0261] In addition, an embodiment of the present invention further proposes a computer storage medium on which an AI-based psychological counseling program is stored. When the AI-based psychological counseling program is executed by a processor, the steps of the AI-based psychological counseling method described above are implemented.

[0262] The specific implementation of the storage medium of the present invention is basically the same as the above-mentioned embodiments of the AI-based psychological counseling method, and will not be repeated here.

[0263] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of the present invention, or directly or indirectly used in other related technical fields, all fall within the protection of the present invention.

[0264] It should be noted that if software tools or components other than those of our company appear in the embodiments of this application, they are only used for illustration and do not represent actual use.

Claims

1. An AI-based psychological consultation method, characterized in that: The following steps are involved: Acquiring user voice data, converting the user voice data into text data, extracting basic frequency components from the user voice data, the basic frequency components including high-pitched frequencies and pitches, and inferring the user's gender and age characteristics based on the basic frequency components; Analyzing the pitch fluctuation of the user's voice data, identifying the user's emotional characteristics and optimizing the gender characteristics and age characteristics, wherein the characteristic information includes gender, age and emotional characteristics; generating a prompt word template according to the text data and the feature information, wherein the prompt word template is used to guide the target psychological counseling model to generate psychological counseling suggestions; Obtaining the user's historical consultation records, which include the user's historical text data, historical text psychological consultation suggestions, and user feedback information; Analyze the historical consultation records to generate user behavior and emotion pattern analysis results, combine the text data with the prompt word template and input them into the target psychological consultation model to generate personalized text psychological consultation suggestions; Converting the text psychological counseling suggestions into voice psychological counseling suggestions through text-to-speech technology, and using the voice psychological counseling suggestions to provide feedback to the user on the psychological counseling; Adjusting the timbre and pitch of the voice psychological counseling suggestion according to the characteristic information of the user; The voice psychological counseling advice is played to the user via a playback device.

2. The AI-based psychological counseling method according to claim 1, wherein: Before inputting the text data and the prompt word template into the target psychological counseling model, the method further includes: Obtain psychological data and perform structured processing to generate knowledge base documents that can be used by language models; The knowledge base document is input into the artificial intelligence framework and combined with the preset language model to generate the target psychological counseling model.

3. The AI-based psychological counseling method according to claim 2, characterized in that: After generating the target psychological consultation model, the method further includes: Record the user's emotional changes, user feedback information and the actual effect of consultation suggestions for each consultation; Generate new knowledge entries based on the recorded information, and update the knowledge base document using the new knowledge entries; Utilize the updated knowledge base documentation to adjust the target psychological counseling model.

4. The AI-based psychological counseling method as claimed in claim 1, characterized in that: After generating personalized text psychological counseling suggestions, it also includes: Collect data statistics on the user's consultation records within a preset period, including statistics on the content of each consultation, user feedback, and emotional changes; Generate a consultation report containing emotional change trends and consultation effect evaluation based on statistical data, and generate personalized mental health management suggestions based on the consultation report; The personalized mental health management suggestions are fed back to the user in the form of voice.

5. An AI-based psychological counseling device, characterized in that: The AI-based psychological counseling device includes: A voice processing module acquires user voice data, converts the user voice data into text data, extracts basic frequency components from the user voice data, including high-pitched frequencies and pitches, and infers the user's gender and age characteristics based on the basic frequency components; analyzes pitch fluctuations in the user voice data, identifies the user's emotional characteristics, and optimizes the gender and age characteristics, where the characteristic information includes gender, age, and emotional characteristics; A feature extraction module generates a prompt word template based on the text data and the feature information, wherein the prompt word template is used to guide the target psychological counseling model to generate psychological counseling suggestions; A consultation generation module obtains a user's historical consultation records, which include the user's historical text data, historical text psychological consultation suggestions and user feedback information; analyzes the historical consultation records to generate user behavior and emotional pattern analysis results, combines the text data with the prompt word template and inputs them into a target psychological consultation model to generate personalized text psychological consultation suggestions; converts the text psychological consultation suggestions into voice psychological consultation suggestions through text-to-speech technology, and the voice psychological consultation suggestions are used to provide feedback on the user's psychological consultation; adjusts the timbre and tone of the voice psychological consultation suggestions according to the user's characteristic information; and plays the voice psychological consultation suggestions to the user through a playback device.

6. An AI-based psychological consultation device, characterized in that: The AI-based psychological counseling device includes a memory, a processor, and an AI-based psychological counseling program stored in the memory and capable of running on the processor. When the AI-based psychological counseling program is executed by the processor, the steps of the AI-based psychological counseling method as described in any one of claims 1 to 4 are implemented.

7. A computer storage medium, characterized in that The storage medium stores an AI-based psychological counseling program, which, when executed by a processor, implements the steps of the AI-based psychological counseling method according to any one of claims 1 to 4.

Images