Psychological testing method and system based on artificial intelligence
By using multidimensional data collection and deep learning algorithms, the problems of insufficient sample size and low efficiency in existing psychological testing methods have been solved, achieving efficient and accurate mental health testing.
Patent Information
- Application Number
- CN202411066044.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-11-22
AI Technical Summary
Existing psychological testing methods lack a multi-dimensional data collection process, thus failing to increase the total sample size and failing to incorporate deep learning algorithms, resulting in low testing efficiency.
We employ an AI-based psychological testing method, which includes multi-dimensional user data collection, preprocessing, feature extraction, deep learning, model building, training, and diagnosis. We utilize technologies such as natural language processing, sentiment analysis, and convolutional neural networks to conduct mental health testing.
It increases sample size and detection accuracy, reduces feature extraction computation, improves detection efficiency and accuracy, and ensures model stability and application effectiveness.
Smart Images

Figure CN119007983A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of psychological testing technology, and in particular relates to a psychological testing method and system based on artificial intelligence. Background Art
[0002] Mental health refers to people's efficient and happy adaptation to the environment, or the ability to happily accept the norms of life. A mentally healthy person should be able to maintain a calm mood, sharp intelligence, behavior that adapts to the social environment, and a pleasant temperament. In today's highly competitive society, the mental health of many people is not so perfect. It is necessary to regularly test the psychology to ensure mental health, and psychological testing methods need to be applied.
[0003] A Chinese patent discloses (CN101331490A) a method for detecting a psychological state, including receiving a biological signal of an object from one or more biological signal detectors in a processor, and determining in the processor whether the biological signal indicates that the object has a specific psychological state. A method for using a detected psychological state, including receiving a signal in a processor indicating whether the psychological state appears in an object. The psychological state can be an unintentional psychological state, such as an emotion, preference, feeling, physiological state, and condition. A processor can be configured to execute these methods, and a computer program product, tangibly stored on a machine-readable medium, has operable instructions to enable the processor to execute these methods. Although the current psychological detection method also has a certain detection effect, it does not have a multidimensional data collection process for a large number of users, and cannot improve the total sample amount in the overall method, and cannot improve the subsequent detection effect. In addition, the method does not incorporate a deep learning algorithm, resulting in the need for a large amount of calculations for the subsequent feature extraction of information, which affects the efficiency of the overall method and the poor actual application effect. In order to solve this problem, a psychological detection method and system based on artificial intelligence are urgently needed. Summary of the invention
[0004] The purpose of the present invention is to solve the problem that although the current psychological detection method has a certain detection effect, it does not have a multidimensional data collection process for a large number of users, cannot increase the total sample amount in the overall method, cannot improve the subsequent detection effect, and the method does not incorporate a deep learning algorithm, resulting in the subsequent feature extraction of information requiring a large amount of calculation, affecting the efficiency of the overall method and resulting in poor actual application effect. A psychological detection method and system based on artificial intelligence is proposed to solve the problem.
[0005] In order to achieve the above object, the present invention adopts the following technical solution: a psychological detection method based on artificial intelligence, comprising the following steps:
[0006] S1. Collect multi-dimensional user data;
[0007] S2. Preprocess the collected data;
[0008] S3, extracting features from different information respectively;
[0009] S4, deep learning for information feature extraction process;
[0010] S5, construct the model;
[0011] S6. Train and optimize the model;
[0012] S7. Apply and diagnose the model;
[0013] S8. Evaluate the model and feed back the results to the receiving terminal.
[0014] As a further description of the above technical solution:
[0015] In S1, multi-dimensional user data is collected, and the user data includes text information, voice information, picture information and video information about emotions of users on social media.
[0016] As a further description of the above technical solution:
[0017] In S2, the collected data is preprocessed, and the preprocessing process is: first, the collected data is classified, then the data is cleaned, the data is denoised, and finally the data is standardized.
[0018] As a further description of the above technical solution:
[0019] In S3, feature extraction is performed on different information respectively, and natural language processing and sentiment analysis techniques are used to extract emotion, attitude and behavior features from text data, and speech emotion recognition, facial muscle psychological emotion recognition and face emotion recognition techniques are used to extract emotion features from sound and image data.
[0020] As a further description of the above technical solution:
[0021] In S4, deep learning is performed on the information feature extraction process, wherein the algorithm to be applied is one or more of a convolutional neural network, a recurrent neural network, and a long short-term memory network.
[0022] As a further description of the above technical solution:
[0023] In S5, model construction is performed, and the specific steps are to combine big data with deep learning algorithms to establish a psychological detection model, classify the mental health models, and label the data for each classified mental health model.
[0024] As a further description of the above technical solution:
[0025] In S6, one or more algorithms selected from the group consisting of a batch gradient descent algorithm, a stochastic gradient descent algorithm, a mini-batch gradient algorithm, an Adam algorithm, and an RMSprop algorithm are used to train and optimize the model.
[0026] As a further description of the above technical solution:
[0027] In S7, the model is applied and diagnosed, and the specific steps are: applying the trained model to a new, unlabeled data set, analyzing and diagnosing the user's mental health status, and outputting the diagnosis results. The diagnosis structure includes the type of mental health problem, the severity of the mental health problem, and the harmfulness of the mental health problem.
[0028] As a further description of the above technical solution:
[0029] In S8, the model is evaluated and the result is fed back to a receiving terminal, which is one or more of a mobile phone and a tablet computer.
[0030] The present invention also discloses a psychological detection system based on artificial intelligence, including a multidimensional user data acquisition module, the output end of the multidimensional user data acquisition module is connected to the input end of a data preprocessing module, the output end of the data preprocessing module is connected to the input end of an information feature extraction module, the output end of the information feature extraction module is connected to the input end of a deep learning module, the output end of the deep learning module is connected to the input end of a model construction module, the output end of the model construction module is connected to the input end of a model training and optimization module, the output end of the model training and optimization module is connected to the input end of a model application and diagnosis module, and the output end of the model application and diagnosis module is connected to the input end of a model evaluation feedback module.
[0031] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:
[0032] In the present invention, the method is provided with a data collection process for multiple categories of different users, and the process can collect a large amount of psychological data from different users. These data can increase the overall sample capacity and improve the subsequent detection accuracy. At the same time, the method also incorporates a deep learning algorithm, which can perform deep learning on the information feature extraction process, thereby reducing the amount of calculation for subsequent feature extraction, greatly improving the feature extraction efficiency and accuracy, and improving the application effect of the method. At the same time, the method also performs a series of training and optimization on the generated model, which helps to improve the stability of the model and ensure detection accuracy. The overall method has a good practical application effect. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] Figure 1 The flowchart of a psychological detection method based on artificial intelligence is shown in FIG.
[0034] Figure 2 A schematic diagram of the module structure of a psychological detection system based on artificial intelligence. DETAILED DESCRIPTION
[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.
[0036] Example 1
[0037] See also Figure 1 The present invention provides a technical solution: a psychological detection method based on artificial intelligence, comprising the following steps:
[0038] S1. Collect multi-dimensional user data, including text, voice, picture and video information about emotions of users on social media;
[0039] S2. Preprocess the collected data. The preprocessing process is: first classify the collected data, then clean the data, denoise the data, and finally standardize the data;
[0040] S3, extract features from different information respectively, use natural language processing and sentiment analysis technology to extract emotion, attitude and behavior features from text data, and use speech emotion recognition, facial emotion recognition and face emotion recognition technology to extract emotion features from sound and image data;
[0041] S4. Perform deep learning on the information feature extraction process, wherein the algorithm to be applied is one or more of a convolutional neural network, a recurrent neural network, and a long short-term memory network;
[0042] S5. Model building. The specific steps are: combining big data with deep learning algorithms to build a psychological testing model, classifying mental health models, and labeling data for each classified mental health model;
[0043] S6. Use one or more algorithms selected from the group consisting of batch gradient descent algorithm, stochastic gradient descent algorithm, mini-batch gradient algorithm, Adam algorithm and RMSprop algorithm to train and optimize the model.
[0044] S7. Applying and diagnosing the model, the specific steps are: applying the trained model to a new, unlabeled data set, analyzing and diagnosing the user's mental health status, and outputting the diagnosis results, the diagnosis structure includes the type of mental health problem, the severity of the mental health problem, and the harmfulness of the mental health problem;
[0045] S8. Evaluate the model and feed back the result to a receiving terminal, which may be one or more of a mobile phone and a tablet computer.
[0046] See also Figure 2 The present invention also provides an artificial intelligence-based psychological detection system, including a multidimensional user data acquisition module, the output end of the multidimensional user data acquisition module is connected to the input end of the data preprocessing module, the output end of the data preprocessing module is connected to the input end of the information feature extraction module, the output end of the information feature extraction module is connected to the input end of the deep learning module, the output end of the deep learning module is connected to the input end of the model construction module, the output end of the model construction module is connected to the input end of the model training and optimization module, the output end of the model training and optimization module is connected to the input end of the model application and diagnosis module, and the output end of the model application and diagnosis module is connected to the input end of the model evaluation feedback module.
[0047] In this embodiment, the method is internally provided with a data collection process for multiple categories of different users, and the process can collect a large amount of psychological data from different users. Such data can increase the overall sample capacity and improve the subsequent detection accuracy.
[0048] Example 2
[0049] See also Figure 1 The present invention provides a technical solution: a psychological detection method based on artificial intelligence, comprising the following steps:
[0050] S1. Collect multi-dimensional user data, including text, voice, picture and video information about emotions of users on social media;
[0051] S2. Preprocess the collected data. The preprocessing process is: first classify the collected data, then clean the data, denoise the data, and finally standardize the data;
[0052] S3, extract features from different information respectively, use natural language processing and sentiment analysis technology to extract emotion, attitude and behavior features from text data, and use speech emotion recognition, facial emotion recognition and face emotion recognition technology to extract emotion features from sound and image data;
[0053] S4. Perform deep learning on the information feature extraction process, wherein the algorithm to be applied is one or more of a convolutional neural network, a recurrent neural network, and a long short-term memory network;
[0054] S5. Model building. The specific steps are: combining big data with deep learning algorithms to build a psychological testing model, classifying mental health models, and labeling data for each classified mental health model;
[0055] S6. Use one or more algorithms selected from the group consisting of batch gradient descent algorithm, stochastic gradient descent algorithm, mini-batch gradient algorithm, Adam algorithm and RMSprop algorithm to train and optimize the model.
[0056] S7. Applying and diagnosing the model, the specific steps are: applying the trained model to a new, unlabeled data set, analyzing and diagnosing the user's mental health status, and outputting the diagnosis results, the diagnosis structure includes the type of mental health problem, the severity of the mental health problem, and the harmfulness of the mental health problem;
[0057] S8. Evaluate the model and feed back the result to a receiving terminal, which may be one or more of a mobile phone and a tablet computer.
[0058] See also Figure 2The present invention also provides an artificial intelligence-based psychological detection system, including a multidimensional user data acquisition module, the output end of the multidimensional user data acquisition module is connected to the input end of the data preprocessing module, the output end of the data preprocessing module is connected to the input end of the information feature extraction module, the output end of the information feature extraction module is connected to the input end of the deep learning module, the output end of the deep learning module is connected to the input end of the model construction module, the output end of the model construction module is connected to the input end of the model training and optimization module, the output end of the model training and optimization module is connected to the input end of the model application and diagnosis module, and the output end of the model application and diagnosis module is connected to the input end of the model evaluation feedback module.
[0059] In this embodiment, a deep learning algorithm is also integrated into the method, which can perform deep learning on the information feature extraction process, thereby reducing the amount of calculation for subsequent feature extraction, greatly improving the efficiency and accuracy of feature extraction, and improving the application effect of the method.
[0060] Example 3
[0061] See also Figure 1 The present invention provides a technical solution: a psychological detection method based on artificial intelligence, comprising the following steps:
[0062] See also Figure 1 The present invention provides a technical solution: a psychological detection method based on artificial intelligence, comprising the following steps:
[0063] S1. Collect multi-dimensional user data, including text, voice, picture and video information about emotions of users on social media;
[0064] S2. Preprocess the collected data. The preprocessing process is: first classify the collected data, then clean the data, denoise the data, and finally standardize the data;
[0065] S3, extract features from different information respectively, use natural language processing and sentiment analysis technology to extract emotion, attitude and behavior features from text data, and use speech emotion recognition, facial emotion recognition and face emotion recognition technology to extract emotion features from sound and image data;
[0066] S4. Perform deep learning on the information feature extraction process, wherein the algorithm to be applied is one or more of a convolutional neural network, a recurrent neural network, and a long short-term memory network;
[0067] S5. Model building. The specific steps are: combining big data with deep learning algorithms to build a psychological testing model, classifying mental health models, and labeling data for each classified mental health model;
[0068] S6. Use one or more algorithms selected from the group consisting of batch gradient descent algorithm, stochastic gradient descent algorithm, mini-batch gradient algorithm, Adam algorithm and RMSprop algorithm to train and optimize the model.
[0069] S7. Applying and diagnosing the model, the specific steps are: applying the trained model to a new, unlabeled data set, analyzing and diagnosing the user's mental health status, and outputting the diagnosis results, the diagnosis structure includes the type of mental health problem, the severity of the mental health problem, and the harmfulness of the mental health problem;
[0070] S8. Evaluate the model and feed back the result to a receiving terminal, which may be one or more of a mobile phone and a tablet computer.
[0071] See also Figure 2 The present invention also provides an artificial intelligence-based psychological detection system, including a multidimensional user data acquisition module, the output end of the multidimensional user data acquisition module is connected to the input end of the data preprocessing module, the output end of the data preprocessing module is connected to the input end of the information feature extraction module, the output end of the information feature extraction module is connected to the input end of the deep learning module, the output end of the deep learning module is connected to the input end of the model construction module, the output end of the model construction module is connected to the input end of the model training and optimization module, the output end of the model training and optimization module is connected to the input end of the model application and diagnosis module, and the output end of the model application and diagnosis module is connected to the input end of the model evaluation feedback module.
[0072] In this embodiment, the method also performs a series of training and optimization on the generated model, which helps to improve the stability of the model and ensure the detection accuracy. The overall method has good practical application effect.
[0073] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.
Claims
1. A psychological detection method based on artificial intelligence, characterized in that: The steps include: S1. Collect multi-dimensional user data; S2. Preprocess the collected data; S3, extracting features from different information respectively; S4, deep learning for information feature extraction process; S5, construct the model; S6. Train and optimize the model; S7. Apply and diagnose the model; S8. Evaluate the model and feed back the results to the receiving terminal.
2. The psychological detection method based on artificial intelligence according to claim 1, characterized in that: In S1, multi-dimensional user data is collected, and the user data includes text information, voice information, picture information and video information about emotions of users on social media.
3. The psychological detection method based on artificial intelligence according to claim 1, characterized in that: In S2, the collected data is preprocessed, and the preprocessing process is: first, the collected data is classified, then the data is cleaned, the data is denoised, and finally the data is standardized.
4. The psychological detection method based on artificial intelligence according to claim 1, characterized in that: In S3, feature extraction is performed on different information respectively, and natural language processing and sentiment analysis techniques are used to extract emotion, attitude and behavior features from text data, and speech emotion recognition, facial muscle psychological emotion recognition and face emotion recognition techniques are used to extract emotion features from sound and image data.
5. The psychological detection method based on artificial intelligence according to claim 1, characterized in that: In S4, deep learning is performed on the information feature extraction process, wherein the algorithm to be applied is one or more of a convolutional neural network, a recurrent neural network, and a long short-term memory network.
6. The psychological detection method based on artificial intelligence according to claim 1, characterized in that: In S5, model construction is performed, and the specific steps are to combine big data with deep learning algorithms to establish a psychological detection model, classify the mental health models, and label the data for each classified mental health model.
7. The artificial intelligence-based psychological testing method according to claim 1, characterized in that: In S6, one or more algorithms selected from the group consisting of a batch gradient descent algorithm, a stochastic gradient descent algorithm, a mini-batch gradient algorithm, an Adam algorithm, and an RMSprop algorithm are used to train and optimize the model.
8. The artificial intelligence-based psychological detection method according to claim 1, characterized in that: In S7, the model is applied and diagnosed, and the specific steps are: applying the trained model to a new, unlabeled data set, analyzing and diagnosing the user's mental health status, and outputting the diagnosis results. The diagnosis structure includes the type of mental health problem, the severity of the mental health problem, and the harmfulness of the mental health problem.
9. The artificial intelligence-based psychological testing method according to claim 1, characterized in that: In S8, the model is evaluated and the result is fed back to a receiving terminal, which is one or more of a mobile phone and a tablet computer.
10. A psychological detection system based on artificial intelligence, characterized in that: It includes a multi-dimensional user data acquisition module, the output end of the multi-dimensional user data acquisition module is connected to the input end of the data preprocessing module, the output end of the data preprocessing module is connected to the input end of the information feature extraction module, the output end of the information feature extraction module is connected to the input end of the deep learning module, the output end of the deep learning module is connected to the input end of the model construction module, the output end of the model construction module is connected to the input end of the model training and optimization module, the output end of the model training and optimization module is connected to the input end of the model application and diagnosis module, and the output end of the model application and diagnosis module is connected to the input end of the model evaluation feedback module.
Citation Information
Patent Citations
Detection of and interaction using mental states
CN101331490A
