CN116739037A - Personality model construction method and device with personality characteristics - Google Patents
Personality model construction method and device with personality characteristics Download PDFInfo
- Publication number
- CN116739037A CN116739037A CN202310656903.4A CN202310656903A CN116739037A CN 116739037 A CN116739037 A CN 116739037A CN 202310656903 A CN202310656903 A CN 202310656903A CN 116739037 A CN116739037 A CN 116739037A
- Authority
- CN
- China
- Prior art keywords
- personality
- data
- model
- personal
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000010276 construction Methods 0.000 title claims abstract description 13
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 64
- 238000012549 training Methods 0.000 claims abstract description 40
- 238000011156 evaluation Methods 0.000 claims abstract description 39
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000007619 statistical method Methods 0.000 claims abstract description 33
- 238000010801 machine learning Methods 0.000 claims abstract description 28
- 238000012360 testing method Methods 0.000 claims abstract description 21
- 238000007781 pre-processing Methods 0.000 claims abstract description 19
- 238000012795 verification Methods 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims description 39
- 239000011159 matrix material Substances 0.000 claims description 24
- 239000013598 vector Substances 0.000 claims description 22
- 230000006399 behavior Effects 0.000 claims description 19
- 230000009467 reduction Effects 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000000354 decomposition reaction Methods 0.000 claims description 13
- 230000004044 response Effects 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 13
- 238000013507 mapping Methods 0.000 claims description 7
- 238000011160 research Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 230000014759 maintenance of location Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 230000002996 emotional effect Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 239000000090 biomarker Substances 0.000 description 4
- 210000004369 blood Anatomy 0.000 description 4
- 239000008280 blood Substances 0.000 description 4
- 238000003066 decision tree Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000000513 principal component analysis Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 241000282414 Homo sapiens Species 0.000 description 3
- 230000036772 blood pressure Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008451 emotion Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 230000003304 psychophysiological effect Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000004630 mental health Effects 0.000 description 2
- 230000006996 mental state Effects 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 1
- 241000282412 Homo Species 0.000 description 1
- 238000000342 Monte Carlo simulation Methods 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 239000012472 biological sample Substances 0.000 description 1
- 238000004820 blood count Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 235000018183 breakfast habits Nutrition 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000005686 eating Nutrition 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 230000004424 eye movement Effects 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 239000008103 glucose Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003054 hormonal effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 210000000265 leukocyte Anatomy 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 150000002632 lipids Chemical class 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000036387 respiratory rate Effects 0.000 description 1
- 210000003296 saliva Anatomy 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 230000003860 sleep quality Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 210000002700 urine Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/008—Artificial life, i.e. computing arrangements simulating life based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Evolutionary Computation (AREA)
- Mathematical Optimization (AREA)
- Robotics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Algebra (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a personality model construction method and device with personality characteristics, wherein the method comprises the following steps: collecting personal information data; preprocessing personal information data; extracting feature data sets representing different dimensions of personal personality from the preprocessed data; carrying out statistical analysis on the characteristic data set; selecting a proper machine learning algorithm according to task requirements; taking a part of feature data in the feature data set after statistical analysis as training data, and inputting the training data into a selected machine learning algorithm for training so as to create an individual personality model; using the rest part of characteristic data in the characteristic data set as test data, and evaluating and verifying the created individual personality model; and adjusting and optimizing the individual personality model according to the evaluation and verification result. The invention reduces multiple collinearity among different features and unnecessary redundant information, thereby being beneficial to the establishment of a model and improving the reliability of the model.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a personality model construction method and device with personality characteristics.
Background
With the development of artificial intelligence (ArtificialIntelligence, AI) technology, a voice assistant or chat robot created based on AI technology can interact with humans in various forms.
The voice assistant or chat robot currently on the market can realize the appearance and sound of the imitation person, but the common voice assistant or chat robot does not have individual differences like a person.
For human beings, the individual differences are mainly represented by the differences of personal personality, which are the differences of individuals in thinking mode, emotion, motivation and behavior characteristics, and the personality has great influence on life and can determine the selection of a person in the aspects of websites, books, music, movies and the like.
How to enable artificial intelligent devices such as voice assistants or chat robots to have personality characteristics is a problem that needs to be considered continuously at present.
At present, artificial intelligent devices capable of reflecting certain personality characteristics exist, but the artificial intelligent devices do not have more comprehensive personality characteristics, so long as the reason is that the established personality model has certain defects, the characteristics of each dimension are not well combined and associated, and therefore the personality model has no more obvious friendly user experience in the application process and cannot be fully applied to certain technical scenes.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides a personality model construction method and device with personality characteristics, which aim to improve the comprehensiveness of a personality model and further improve the friendliness and wide applicability of the application of the personality model.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
in a first aspect, the present invention provides a personality model building method having personality characteristics, including:
collecting personal information data including personal behavior data, personal physiological data, and personal self-evaluation data;
preprocessing personal information data;
extracting feature data sets representing different dimensions of personal personality from the preprocessed data;
carrying out statistical analysis on the characteristic data set;
selecting a proper machine learning algorithm according to task requirements;
taking a part of feature data in the feature data set after statistical analysis as training data, and inputting the training data into a selected machine learning algorithm for training so as to create an individual personality model;
using the rest part of characteristic data in the characteristic data set as test data, and evaluating and verifying the created individual personality model;
And adjusting and optimizing the individual personality model according to the evaluation and verification result.
Based on the first aspect, the further technical scheme is as follows: the extracting feature data sets representing different dimensions of personal personality from the preprocessed data includes:
converting the preprocessed data into feature vectors;
performing dimension reduction processing on the feature vector to obtain feature data sets with different dimensions;
and selecting the characteristics related to the required personality dimension from the characteristic data sets of different dimensions, and performing fitting processing to obtain the characteristic data sets of different dimensions of the personal personality.
Based on the first aspect, the further technical scheme is as follows: the statistical analysis of the feature data set includes:
carrying out standardization processing on feature data sets of different dimensions of the personal personality so as to obtain standardized data;
calculating a covariance matrix according to the standardized data;
performing eigenvalue decomposition on the covariance matrix to obtain eigenvectors and eigenvalues, wherein the eigenvectors represent directions of different principal components, and the eigenvalues represent importance degrees of the principal components;
selecting the maximum K principal components according to the size of the characteristic values, reserving the maximum K principal components, and mapping characteristic data sets of different dimensions of personal personality into a K-dimensional space;
The principal components selected for retention are subjected to an explanatory analysis.
Based on the first aspect, the further technical scheme is as follows: the selecting a proper machine learning algorithm according to task demands comprises the following steps:
determining a required prediction variable or response variable according to the research problem and the target;
determining the type of the algorithm to be selected according to the required predicted variable or the required response variable;
and selecting a plurality of algorithms from the algorithm types according to the determined algorithm types to be selected for comparison so as to determine the optimal machine learning algorithm according with the requirements.
Based on the first aspect, the further technical scheme is as follows: the method for evaluating and verifying the created individual personality model by using the rest part of characteristic data in the characteristic data set as test data comprises the following steps:
the created individual personality model predicts the test set and calculates the prediction result;
calculating a plurality of prediction indexes according to a prediction result, wherein the prediction indexes comprise: accuracy of the model, and recall.
In a second aspect, the invention also provides a personality model construction device with personality characteristics, which comprises a collecting unit, a preprocessing unit, a characteristic extracting unit, a statistical analysis unit, an algorithm selecting unit, a model training unit, a model evaluation verification unit and a model adjustment optimizing unit;
The collecting unit is used for collecting personal information data, wherein the personal information data comprises personal behavior data, personal physiological data and personal self-evaluation data;
the preprocessing unit is used for preprocessing the personal information data;
the feature extraction unit is used for extracting feature data sets representing different dimensions of personal personality from the preprocessed data;
the statistical analysis unit is used for carrying out statistical analysis on the characteristic data set;
the algorithm selection unit is used for selecting a proper machine learning algorithm according to task requirements;
the model training unit is used for taking part of characteristic data in the characteristic data set after statistical analysis as training data, inputting the training data into a selected machine learning algorithm for training so as to create an individual personality model;
the model evaluation unit is used for evaluating and verifying the created individual personality model by using the rest part of characteristic data in the characteristic data set as test data;
and the model adjustment and optimization unit is used for adjusting and optimizing the individual personality model according to the evaluation and verification result.
Based on the second aspect, the further technical scheme is as follows: the preprocessing unit comprises a feature vector conversion module, a dimension reduction module and a fitting processing module;
The feature vector conversion module is used for converting the preprocessed data into feature vectors;
the dimension reduction module is used for carrying out dimension reduction processing on the feature vectors so as to obtain feature data sets with different dimensions;
and the fitting processing module is used for selecting the characteristics related to the required personality dimension from the characteristic data sets with different dimensions and performing fitting processing to obtain the characteristic data sets with different dimensions of the personal personality.
Based on the second aspect, the further technical scheme is as follows: the statistical analysis unit comprises a standardized processing module, a variance matrix calculation module, a characteristic value decomposition module, a principal component selection module and an analysis module;
the standardized processing module is used for carrying out standardized processing on characteristic data sets of different dimensions of the personal personality so as to obtain standardized data;
the variance matrix calculation module is used for calculating a covariance matrix according to the standardized data;
the eigenvalue decomposition module is used for carrying out eigenvalue decomposition on the covariance matrix to obtain eigenvectors and eigenvalues, wherein the eigenvectors represent directions of different principal components, and the eigenvalues represent importance degrees of the principal components;
the principal component selection module is used for selecting the maximum K principal components according to the size of the characteristic values, reserving the maximum K principal components, and mapping characteristic data sets of different dimensions of personal personality into a K-dimensional space;
And the analysis module is used for carrying out explanatory analysis on the main components which are selected and reserved.
In a third aspect, the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the personality model building method with personality characteristics as described above when the processor executes the computer program.
In a fourth aspect, the present invention also provides a computer readable storage medium storing a computer program, the computer program comprising program instructions which, when executed by a processor, cause the processor to perform a personality model building method having personality characteristics as described above.
Compared with the prior art, the invention has the beneficial effects that: the personality model construction method with personality characteristics comprises the following steps: collecting personal information data including personal behavior data, personal physiological data, and personal self-evaluation data; preprocessing personal information data; extracting feature data sets representing different dimensions of personal personality from the preprocessed data; carrying out statistical analysis on the characteristic data set; selecting a proper machine learning algorithm according to task requirements; taking a part of feature data in the feature data set after statistical analysis as training data, and inputting the training data into a selected machine learning algorithm for training so as to create an individual personality model; using the rest part of characteristic data in the characteristic data set as test data, and evaluating and verifying the created individual personality model; and adjusting and optimizing the individual personality model according to the evaluation and verification result. The collected personal information data comprises personal data with a plurality of attributes, and the extracted characteristic data can reveal information such as distribution conditions, correlation and the like of personality characteristics through analysis and processing, so that basic data support is established for a subsequent model, meanwhile, multiple collinearity among different characteristics is reduced, unnecessary redundant information is reduced, thus being beneficial to establishing the model, in addition, a foundation is provided for optimizing and adjusting the model through evaluating and verifying the established individual personality model, and further, the reliability of the model is indirectly improved.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the present invention so that the same may be more clearly understood, as well as to provide a better understanding of the present invention with reference to the following detailed description of the preferred embodiments.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a personality model building method with personality characteristics according to an embodiment of the present invention;
FIG. 2 is a second flowchart of a personality model building method with personality characteristics according to an embodiment of the present invention;
FIG. 3 is a flowchart III of a personality model building method with personality characteristics according to an embodiment of the present invention;
FIG. 4 is a flowchart fourth of a personality model building method with personality characteristics according to an embodiment of the present invention;
FIG. 5 is a flowchart fifth of a personality model building method with personality characteristics according to an embodiment of the present invention;
FIG. 6 is a schematic block diagram of a personality model building apparatus with personality characteristics provided by an embodiment of the present invention;
fig. 7 is a schematic block diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that the terms "comprises" and "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
As shown in fig. 1, the embodiment of the invention provides a personality model building method with personality characteristics, which comprises the following steps: S10-S80.
S10, collecting personal information data, wherein the personal information data comprises personal behavior data, personal physiological data and personal self-evaluation data.
To construct an accurate personality model, multiple types of personal information data need to be collected.
Personal behavior data refers to recording various behaviors that an individual exhibits in daily life reflecting their personality traits and mental states. These actions may be recorded and collected in a variety of ways, such as social media posts, emails, cell phone notes, mobile device usage, and so forth. In particular, the personal behavior data may include the following aspects: text data: text data is one of the most common personal behavior data, typically including social media posts, comments, blog articles, emails, chat recordings, and the like. Through text mining and natural language processing on the text data, the characteristics of emotion, attitude, mood, word frequency and the like in the text can be extracted so as to reflect the personality characteristics and psychological states of the individual. Behavior data: behavior data refers to various behaviors of an individual in daily life, such as shopping, eating, exercising, sleeping, and the like. By recording and analyzing these behavioral data, one can infer personal preferences, interests and lifestyles, revealing their personality traits and mental states. Environmental data: environmental data refers to various data generated in the personal living and working environment, such as geographical location, weather, time, event, etc. By analyzing and mining the environmental data, the information such as the behavior pattern, social circle, work habit and the like of the individual can be known, so that the personality characteristics and psychological states of the individual are reflected.
Personal physiological data refers to various data that record the physical condition and physiological changes of an individual. Such data may be collected and acquired in a variety of ways, such as medical examination, sensor monitoring, biomarker sampling, and the like. In particular, personal physiological data may include the following aspects: psychophysiological data: psychophysiological data refers to data reflecting psychological states and physiological changes of an individual, such as heart rate, blood pressure, skin resistance, eye movement, brain waves, and the like. These data may be collected and analyzed by means of psychophysiological testing, biofeedback equipment, brain-computer interfaces, etc. Biomarker data: biomarker data refers to chemical and biological indicators reflecting the health and vital activities of an individual, such as white blood cell count in blood, blood glucose levels, blood lipid levels, hormonal levels, and the like. These data may be obtained by collection and detection of biological samples of blood, urine, saliva, etc.
Exercise physiological data: the exercise physiological data refers to various physiological changes and data generated during exercise, such as the number of steps, consumed energy, respiratory rate, body posture, etc. These data may be monitored and collected by smart bracelets, sports watches, smart insoles, etc.
Personal self-evaluation data refers to subjective evaluation and description of individual character characteristics and psychological states. These data may be collected by various questionnaires, interviews, and self-describing materials, among others. Specifically, the human self-evaluation data may include the following aspects:
personal trait: personal traits refer to relatively stable patterns and attitudes that people have, such as inside/outside, neurology/stability, openness/conservation, and the like. These traits can be generally assessed by common questionnaires such as the NEO five factor personality questionnaire. The life value is as follows: the human life value refers to the meaning of an individual to life and the attitudes and beliefs associated therewith, such as freedom, equality, honoring, responsibility, etc. These value views may be obtained through some specially designed questionnaires or interviews. Emotional state and emotional experience: emotional state and emotional experience refers to the emotional state and specific emotional experience in which an individual is currently located, such as pleasure, anxiety, tension, and the like. These data may be obtained by using questionnaires such as emotion scale, stress scale, depression scale, etc. Self-concept: self-concepts refer to an individual's knowledge and opinion of himself, such as self-esteem, confidence, self-efficacy, etc., which data may be obtained by using a self-concept questionnaire.
S20, preprocessing the personal information data.
The main purpose of preprocessing personal behavior data, personal physiological data and personal self-assessment data is to clean and transform the raw data to fit for subsequent analysis and modeling, the preprocessing including the following aspects:
data cleaning: data cleansing refers to checking and correcting errors, deletions, anomalies or repeated values in data to improve data quality and reliability. For example, null values may be deleted, duplicate records removed, data formats and units adjusted, and so forth.
Feature coding and normalization: feature encoding and normalization refers to converting discrete or non-digital features into digital form for training and prediction of machine learning models. At the same time, the characteristics are required to be standardized or normalized so as to eliminate the influence among different scales and different units.
Sample balance: sample balancing is a condition of unbalance in a data set, and a plurality of methods are used for balancing the number of samples of each class so as to avoid influencing model training and prediction results. Such as over-sampling, under-sampling, or SMOTE.
S30, extracting feature data sets representing different dimensions of personal personality from the preprocessed data.
Based on actual questions and data conditions, personality-related characteristics, such as regular exercise, breakfast habits, sleep quality, blood pressure index, emotional state, etc., are extracted from the pre-processed data. Meanwhile, different types of features need to be classified and encoded, so that the processing of a subsequent model is facilitated.
As shown in fig. 2, in an embodiment, step S30 specifically includes the following steps: S301-S303.
S301, converting the preprocessed data into feature vectors.
S302, performing dimension reduction processing on the feature vector to obtain feature data sets with different dimensions.
S303, selecting the features related to the required personality dimensions from the feature data sets with different dimensions, and performing fitting processing to obtain the feature data sets with different dimensions of the personal personality.
For steps SS301-S303, the preprocessed data is converted into a more representative feature vector representation. For example, for personal behavior data, an average number of steps per day, a movement duration, etc. may be calculated; for personal physiological data, indexes such as blood pressure, heart rate and the like can be calculated; for personal self-evaluation data, standardized questionnaire results or the like may be used. And (3) dimension reduction treatment: feature vectors are reduced in dimension using Principal Component Analysis (PCA) or factor analysis, etc., to facilitate finding potential relationships and dimensions between different features. For example, when using the PCA method, it is possible to determine how many principal components remain according to the variance ratio between the features to achieve an optimized dimension reduction effect. Determining personality dimensions: according to the prior research and domain knowledge, different personality dimensions and types are determined, and the reduced data set is used for exploration and fitting. For example, in the large five personality model, five dimensions of openness, responsibility, exotic, anthropogenic, and emotional stability are covered; in MBTI personality types, four aspects are outward/inward, perceptual/rational, emotional/thinking, and judgment/perception.
S40, carrying out statistical analysis on the characteristic data set.
The mode, the relation and the potential dimension in the data can be identified through statistical analysis, basic data support is established for the subsequent model, meanwhile, multiple collinearity among different features is reduced, unnecessary redundant information is reduced, and therefore the establishment of the model is facilitated.
As shown in fig. 3, in an embodiment, step S40 specifically includes the following steps: s401 to S405.
S401, carrying out standardization processing on feature data sets of different dimensions of the personal personality so as to obtain standardized data.
And (3) performing normalization processing, namely converting each feature into a standard normal distribution form with the mean value of 0 and the standard deviation of 1, so as to facilitate subsequent calculation and comparison.
S402, calculating a covariance matrix according to the standardized data.
And calculating a covariance matrix according to the standardized data to measure the correlation and variance between different features.
S403, carrying out eigenvalue decomposition on the covariance matrix to obtain eigenvectors and eigenvalues, wherein the eigenvectors represent directions of different principal components, and the eigenvalues represent importance degrees of the principal components.
S404, selecting the maximum K principal components according to the size of the characteristic values, reserving the maximum K principal components, and mapping characteristic data sets of different dimensions of personal personality into a K-dimensional space;
S405, performing explanatory analysis on the main components selected and reserved.
By means of an explanatory analysis it can be further determined which features are most relevant, which features can be ignored, etc.
The interpretive analysis may use decision trees, logistic regression, etc. interpretive models to facilitate the discovery of critical features and factors related to personality and to account for the effects of these features and factors. For example, in studying workplace personality, decision tree models may be used to identify the most important workplace personality characteristics and occupation types.
S50, selecting a proper machine learning algorithm according to task requirements.
As shown in fig. 4, in an embodiment, step S50 specifically includes the following steps: S501-S503.
S501, determining a required prediction variable or response variable according to the research problem and the target.
Depending on the study question and goal, the desired predicted variables or response variables are determined. For example, when using a personality model to predict mental health, the desired prediction variables are various types of personality characteristics and the response variables are mental health indices.
S502, determining the type of algorithm to be selected according to the required predicted variable or response variable.
Depending on the desired prediction variables or response variables, the appropriate algorithm type is selected. For example, for discrete classification problems, algorithms such as decision trees, random forests, support vector machines, etc. can be used; for the continuous regression problem, linear regression, ridge regression, lasso regression, etc. algorithms may be used.
S503, according to the determined algorithm type to be selected, selecting a plurality of algorithms from the algorithm types to be compared so as to determine the optimal machine learning algorithm meeting the requirements.
After determining the algorithm type, one or more specific algorithms need to be selected for comparison and selection. Common algorithms include: decision trees, KNNs, naive bayes, support vector machines, neural networks, random forests, GBDT, etc.
S60, taking part of the feature data in the feature data set after statistical analysis as training data, and inputting the training data into a selected machine learning algorithm for training so as to create a personal personality model.
Namely, model parameters are continuously optimized through inputting training data, so that the model can better fit the data and reach an expected target. In the training process, the proper hyper-parameters and loss functions are selected, so that the problem of over-fitting or under-fitting is avoided.
And S70, using the rest part of characteristic data in the characteristic data set as test data, and evaluating and verifying the created individual personality model.
It is important to evaluate the created personality model, and the purpose of this process is to determine the performance and generalization ability of the model, and to discover and solve problems that may exist. Specifically, the meaning of evaluating a personality model includes the following:
Evaluating the predictive performance of the model: and (3) through evaluating indexes such as accuracy, recall rate, precision and AUC of the model, knowing how the model predicts the performance on new data, so as to judge whether the model is effective. Stability of the model was evaluated: by using methods such as cross-validation technology or Monte Carlo simulation, the performance of the model on different data sets is evaluated, and the generalization capability and stability of the model are checked. The potential problems are found and solved: by analyzing the evaluation result of the model, possible defects, deviations or errors of the model can be found, the problems can be solved in a targeted manner, and the reliability and the accuracy of the model are improved. Confirming the application range of the model: through evaluation and comparison of the models, the application range and limitation of the models can be determined, so that the application of the models in unsuitable scenes is avoided. Improving the interpretability of the model: by evaluating the model, the basis and process of model prediction can be understood, thereby improving the interpretability and reliability of the model.
As shown in fig. 5, in an embodiment, step S70 specifically includes the following steps: S701-S702.
S701, the created individual personality model predicts the test set, and calculates a prediction result.
S702, calculating a plurality of prediction indexes according to a prediction result, wherein the prediction indexes comprise: accuracy of the model, and recall.
For steps S701-S702, in the previous training link, a part of the feature data in the feature data set after the statistical analysis has been used as training data, and the remaining part of the feature data has been used as a test set. For example, the feature data set after statistical analysis is divided into K subsets with equal size, K-1 subsets are used as training sets, one subset is left as testing set, the steps S701-S702 are repeated for K times, different subsets are selected each time as testing sets, the rest K-1 subsets are used as training sets, K models are obtained, and average errors of the K models are calculated. Different error measures may be used here, such as Mean Absolute Error (MAE), mean Square Error (MSE), etc.
In evaluating a personality model, multiple predictors need to be considered to integrate the performance of the evaluation model. The following are several types of models that are commonly used to evaluate predictors:
accuracy (Accuracy): accuracy represents the proportion of samples that the model correctly predicts. The calculation formula is as follows: (TP+TN)/(TP+FP+FN+TN), wherein TP represents the true number of cases, TN represents the true number of cases, FP represents the false number of cases, and FN represents the false number of cases.
Accuracy (Precision): accuracy means the proportion of samples correctly predicted as positive classes to all samples predicted as positive classes. The calculation formula is as follows: TP/(tp+fp).
Recall (Recall): recall represents the proportion of samples predicted to be positive to all samples truly positive. The calculation formula is as follows: TP/(tp+fn).
F1 value (F1-score): the F1 value is a harmonic mean of accuracy and recall for the comprehensive evaluation of classifier performance. The calculation formula is as follows: 2x (PrecisionxRecall)/(precision+recall).
AUC value (areaundercurrve): the AUC value is the area under the ROC curve and is used for measuring the credibility of the model prediction result. AUC values range between 0 and 1, with larger values indicating better performance of the model.
Confusion matrix (connectionmatrix): the confusion matrix is used for displaying the classification result of the model. The confusion matrix is divided into two dimensions, namely a real category and a predicted category, wherein a row represents the real category and a column represents the predicted category.
And S80, adjusting and optimizing the individual personality model according to the evaluation and verification result.
In the establishment of the personality model, the specific steps of adjusting and optimizing the individual personality model according to the evaluation verification result include:
Analysis and evaluation results: and (3) finding out problems and defects of the model, such as low prediction accuracy, over-fitting or under-fitting, and the like, by analyzing the evaluation result.
Adjusting parameters: aiming at the found problems, the related parameters or super parameters are tried to be adjusted so as to improve the performance of the model. For example, one may attempt to increase the number of hidden layers of the model, select different activation functions, adjust learning rates, regularize terms, and the like.
The added characteristics are as follows: if the evaluation result shows that the prediction capability of the model is poor, the increase of the feature quantity in the data set can be considered, and the complexity of the model is improved. For example, some features related to the study goal may be added, or new features may be constructed using methods of feature engineering.
The reduction features are as follows: if the evaluation result shows that the model possibly has an overfitting problem, the reduction of the feature quantity in the data set can be considered, so that the complexity of the model is reduced. For example, the feature selection method may be used to screen out the most representative features, or a dimension reduction method such as PCA may be used to perform feature compression.
Adjusting a model algorithm: if the evaluation result shows that the currently selected model algorithm cannot meet the research target, it is possible to consider changing a different machine learning algorithm or adjusting parameters of the currently selected algorithm.
And (5) evaluating again: after adjustment and optimization, evaluation and verification are carried out again to verify the improvement effect of the model, and adjustment and optimization are continued as required until a satisfactory prediction result is obtained.
By evaluating and verifying the created individual personality model, a foundation is provided for optimizing and adjusting the model, and the reliability of the model is indirectly improved.
FIG. 6 is a schematic block diagram of a personality model building apparatus with personality characteristics provided by an embodiment of the present invention; corresponding to the personality model building method with personality characteristics described above, the embodiment of the present invention further provides a personality model building device 100 with personality characteristics.
As shown in fig. 6, the personality model building apparatus 100 having personality characteristics includes a collecting unit 110, a preprocessing unit 120, a feature extracting unit 130, a statistical analysis unit 140, an algorithm selecting unit 150, a model training unit 160, a model evaluation verifying unit 170, and a model adjustment optimizing unit 180.
A collection unit 110 for collecting personal information data including personal behavior data, personal physiological data, and personal self-evaluation data; the preprocessing unit 120 is configured to preprocess personal information data. The feature extraction unit 130 is configured to extract feature data sets representing different dimensions of the personal personality from the preprocessed data. And a statistical analysis unit 140 for performing statistical analysis on the feature data set. An algorithm selection unit 150 is configured to select an appropriate machine learning algorithm according to task requirements. The model training unit 160 is configured to input a part of the feature data in the feature data set after the statistical analysis as training data into the selected machine learning algorithm for training, so as to create a personal personality model. The model evaluation unit 170 is configured to perform evaluation verification on the created individual personality model using the remaining part of the feature data in the feature data set as test data. The model adjustment optimization unit 180 is configured to adjust and optimize the individual personality model according to the evaluation verification result.
In one embodiment, the preprocessing unit 120 includes a feature vector conversion module, a dimension reduction module, and a fitting processing module. The feature vector conversion module is used for converting the preprocessed data into feature vectors. And the dimension reduction module is used for carrying out dimension reduction processing on the feature vectors so as to obtain feature data sets with different dimensions. And the fitting processing module is used for selecting the characteristics related to the required personality dimension from the characteristic data sets with different dimensions and performing fitting processing to obtain the characteristic data sets with different dimensions of the personal personality.
In one embodiment, the statistical analysis unit 140 includes a normalization processing module, a variance matrix calculation module, a eigenvalue decomposition module, a principal component selection module, and a parsing module. The standardized processing module is used for carrying out standardized processing on the characteristic data sets of different dimensions of the personal personality so as to obtain standardized data. And the variance matrix calculation module is used for calculating a covariance matrix according to the standardized data. And the eigenvalue decomposition module is used for carrying out eigenvalue decomposition on the covariance matrix to obtain eigenvectors and eigenvalues, wherein the eigenvectors represent directions of different principal components, and the eigenvalues represent importance degrees of the principal components. And the principal component selection module is used for selecting the maximum K principal components according to the size of the characteristic values, reserving the maximum K principal components, and mapping characteristic data sets of different dimensions of the personal personality into a K-dimensional space. And the analysis module is used for carrying out explanatory analysis on the main components which are selected and reserved.
In one embodiment, the algorithm selection unit 150 includes a first determination module, a second determination module, and a comparison module. The first determining module is used for determining a required prediction variable or a response variable according to the research problem and the target. And the second determining module is used for determining the type of the algorithm to be selected according to the required predicted variable or the response variable. And the comparison module is used for selecting a plurality of algorithms from the algorithm types according to the determined algorithm types to be selected for comparison so as to determine the optimal machine learning algorithm according with the requirements.
In one embodiment, the model evaluation verification unit 170 includes a prediction module and a prediction index calculation module. The prediction module is used for predicting the test set by the created individual personality model and calculating a prediction result. A prediction index calculation module, configured to calculate a plurality of prediction indexes according to a prediction result, where the prediction indexes include: accuracy of the model, and recall.
The personality model building method described above with personality characteristics may be implemented in the form of a computer program that may be run on a computer device as shown in fig. 7.
Referring to fig. 7, fig. 7 is a schematic block diagram of a computer device according to an embodiment of the present application. The computer device 700 may be a server, where the server may be a stand-alone server or may be a server cluster formed by a plurality of servers.
As shown in fig. 7, the computer device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the personality model building method steps having personality characteristics as described above when the computer program is executed by the processor.
The computer device 700 may be a terminal or a server. The computer device 700 includes a processor 720, a memory, and a network interface 750, which are connected through a system bus 710, wherein the memory may include a non-volatile storage medium 730 and an internal memory 740.
The non-volatile storage medium 730 may store an operating system 731 and computer programs 732. The computer program 732, when executed, may cause the processor 720 to perform any one of a number of personality model building methods having personality characteristics.
The processor 720 is used to provide computing and control capabilities to support the operation of the overall computer device 700.
The internal memory 740 provides an environment for the execution of a computer program 732 in the non-volatile storage medium 730, which computer program 732, when executed by the processor 720, causes the processor 720 to perform any one of a number of personality model building methods having personality characteristics.
The network interface 750 is used for network communications such as sending assigned tasks and the like. It will be appreciated by those skilled in the art that the structure shown in FIG. 7 is merely a block diagram of some of the structures associated with the present inventive arrangements and does not constitute a limitation of the computer device 700 to which the present inventive arrangements may be applied, and that a particular computer device 700 may include more or fewer components than shown, or may combine certain components, or may have a different arrangement of components. Wherein the processor 720 is configured to execute the program code stored in the memory to implement the following steps:
the personality model construction method with personality characteristics comprises the following steps:
collecting personal information data including personal behavior data, personal physiological data, and personal self-evaluation data;
preprocessing personal information data;
extracting feature data sets representing different dimensions of personal personality from the preprocessed data;
carrying out statistical analysis on the characteristic data set;
selecting a proper machine learning algorithm according to task requirements;
taking a part of feature data in the feature data set after statistical analysis as training data, and inputting the training data into a selected machine learning algorithm for training so as to create an individual personality model;
Using the rest part of characteristic data in the characteristic data set as test data, and evaluating and verifying the created individual personality model;
and adjusting and optimizing the individual personality model according to the evaluation and verification result.
In an embodiment, the extracting the feature data set representing different dimensions of the personal personality from the preprocessed data includes:
converting the preprocessed data into feature vectors;
performing dimension reduction processing on the feature vector to obtain feature data sets with different dimensions;
and selecting the characteristics related to the required personality dimension from the characteristic data sets of different dimensions, and performing fitting processing to obtain the characteristic data sets of different dimensions of the personal personality.
In an embodiment, the performing a statistical analysis on the feature dataset includes:
carrying out standardization processing on feature data sets of different dimensions of the personal personality so as to obtain standardized data;
calculating a covariance matrix according to the standardized data;
performing eigenvalue decomposition on the covariance matrix to obtain eigenvectors and eigenvalues, wherein the eigenvectors represent directions of different principal components, and the eigenvalues represent importance degrees of the principal components;
selecting the maximum K principal components according to the size of the characteristic values, reserving the maximum K principal components, and mapping characteristic data sets of different dimensions of personal personality into a K-dimensional space;
The principal components selected for retention are subjected to an explanatory analysis.
In an embodiment, the selecting an appropriate machine learning algorithm according to task requirements includes:
determining a required prediction variable or response variable according to the research problem and the target;
determining the type of the algorithm to be selected according to the required predicted variable or the required response variable;
and selecting a plurality of algorithms from the algorithm types according to the determined algorithm types to be selected for comparison so as to determine the optimal machine learning algorithm according with the requirements.
In an embodiment, the evaluating and verifying the created individual personality model using the remaining part of the feature data in the feature data set as the test data includes:
the created individual personality model predicts the test set and calculates the prediction result;
calculating a plurality of prediction indexes according to a prediction result, wherein the prediction indexes comprise: accuracy of the model, and recall.
It should be appreciated that in embodiments of the present application, processor 720 may be a Central processing unit (Central ProcessingUnit, CPU), and that processor 720 may also be other general purpose processors, digital signal processors (DigitalSignalProcessor, DSP), application specific integrated circuits (ApplicationSpecificIntegrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-ProgrammableGateArray, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Those skilled in the art will appreciate that the computer device 700 structure shown in fig. 7 is not limiting of the computer device 700 and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
In another embodiment of the present invention, a computer-readable storage medium is provided. The computer readable storage medium may be a non-volatile computer readable storage medium. The computer readable storage medium stores a computer program, wherein the computer program when executed by a processor implements the personality model building method with personality characteristics disclosed by the embodiments of the present invention.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, specific working procedures of the apparatus, device and unit described above may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein. Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, and for example, the division of the units is merely a logical function division, there may be another division manner in actual implementation, or units having the same function may be integrated into one unit, for example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices, or elements, or may be an electrical, mechanical, or other form of connection.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment of the present invention.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units may be stored in a storage medium if implemented in the form of software functional units and sold or used as stand-alone products. Based on such understanding, the technical solution of the present invention is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only memory (ROM), a magnetic disk, an optical disk, or other various media capable of storing program codes.
While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
1. The personality model construction method with personality characteristics is characterized by comprising the following steps:
collecting personal information data including personal behavior data, personal physiological data, and personal self-evaluation data;
preprocessing personal information data;
extracting feature data sets representing different dimensions of personal personality from the preprocessed data;
carrying out statistical analysis on the characteristic data set;
selecting a proper machine learning algorithm according to task requirements;
taking a part of feature data in the feature data set after statistical analysis as training data, and inputting the training data into a selected machine learning algorithm for training so as to create an individual personality model;
using the rest part of characteristic data in the characteristic data set as test data, and evaluating and verifying the created individual personality model;
And adjusting and optimizing the individual personality model according to the evaluation and verification result.
2. The personality model construction method with personality characteristics according to claim 1, wherein extracting feature data sets representing different dimensions of the personality of the individual from the preprocessed data includes:
converting the preprocessed data into feature vectors;
performing dimension reduction processing on the feature vector to obtain feature data sets with different dimensions;
and selecting the characteristics related to the required personality dimension from the characteristic data sets of different dimensions, and performing fitting processing to obtain the characteristic data sets of different dimensions of the personal personality.
3. The personality model building method with personality characteristics according to claim 1, wherein the performing a statistical analysis on the characteristic data set includes:
carrying out standardization processing on feature data sets of different dimensions of the personal personality so as to obtain standardized data;
calculating a covariance matrix according to the standardized data;
performing eigenvalue decomposition on the covariance matrix to obtain eigenvectors and eigenvalues, wherein the eigenvectors represent directions of different principal components, and the eigenvalues represent importance degrees of the principal components;
Selecting the maximum K principal components according to the size of the characteristic values, reserving the maximum K principal components, and mapping characteristic data sets of different dimensions of personal personality into a K-dimensional space;
the principal components selected for retention are subjected to an explanatory analysis.
4. The personality model building method with personality characteristics according to claim 1, wherein the selecting an appropriate machine learning algorithm according to task requirements includes:
determining a required prediction variable or response variable according to the research problem and the target;
determining the type of the algorithm to be selected according to the required predicted variable or the required response variable;
and selecting a plurality of algorithms from the algorithm types according to the determined algorithm types to be selected for comparison so as to determine the optimal machine learning algorithm according with the requirements.
5. The personality model construction method with personality characteristics according to claim 1, wherein the evaluating and verifying the created individual personality model using the remaining part of the feature data in the feature data set as test data includes:
the created individual personality model predicts the test set and calculates the prediction result;
calculating a plurality of prediction indexes according to a prediction result, wherein the prediction indexes comprise: accuracy of the model, and recall.
6. The personality model construction device with personality characteristics is characterized by comprising a collection unit, a preprocessing unit, a characteristic extraction unit, a statistical analysis unit, an algorithm selection unit, a model training unit, a model evaluation verification unit and a model adjustment optimization unit;
the collecting unit is used for collecting personal information data, wherein the personal information data comprises personal behavior data, personal physiological data and personal self-evaluation data;
the preprocessing unit is used for preprocessing the personal information data;
the feature extraction unit is used for extracting feature data sets representing different dimensions of personal personality from the preprocessed data;
the statistical analysis unit is used for carrying out statistical analysis on the characteristic data set;
the algorithm selection unit is used for selecting a proper machine learning algorithm according to task requirements;
the model training unit is used for taking part of characteristic data in the characteristic data set after statistical analysis as training data, inputting the training data into a selected machine learning algorithm for training so as to create an individual personality model;
the model evaluation unit is used for evaluating and verifying the created individual personality model by using the rest part of characteristic data in the characteristic data set as test data;
And the model adjustment and optimization unit is used for adjusting and optimizing the individual personality model according to the evaluation and verification result.
7. The personality model building apparatus with personality characteristics according to claim 6, wherein the preprocessing unit includes a feature vector conversion module, a dimension reduction module, and a fitting processing module;
the feature vector conversion module is used for converting the preprocessed data into feature vectors;
the dimension reduction module is used for carrying out dimension reduction processing on the feature vectors so as to obtain feature data sets with different dimensions;
and the fitting processing module is used for selecting the characteristics related to the required personality dimension from the characteristic data sets with different dimensions and performing fitting processing to obtain the characteristic data sets with different dimensions of the personal personality.
8. The personality model construction apparatus with personality characteristics according to claim 6, wherein the statistical analysis unit includes a normalization processing module, a variance matrix calculation module, a feature value decomposition module, a principal component selection module, and an analysis module;
the standardized processing module is used for carrying out standardized processing on characteristic data sets of different dimensions of the personal personality so as to obtain standardized data;
The variance matrix calculation module is used for calculating a covariance matrix according to the standardized data;
the eigenvalue decomposition module is used for carrying out eigenvalue decomposition on the covariance matrix to obtain eigenvectors and eigenvalues, wherein the eigenvectors represent directions of different principal components, and the eigenvalues represent importance degrees of the principal components;
the principal component selection module is used for selecting the maximum K principal components according to the size of the characteristic values, reserving the maximum K principal components, and mapping characteristic data sets of different dimensions of personal personality into a K-dimensional space;
and the analysis module is used for carrying out explanatory analysis on the main components which are selected and reserved.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the personality model building method having personality characteristics according to any one of claims 1 to 5 when the computer program is executed.
10. A computer-readable storage medium, characterized in that the storage medium stores a computer program comprising program instructions that, when executed by a processor, cause the processor to perform the personality model building method having personality characteristics according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310656903.4A CN116739037A (en) | 2023-06-05 | 2023-06-05 | Personality model construction method and device with personality characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310656903.4A CN116739037A (en) | 2023-06-05 | 2023-06-05 | Personality model construction method and device with personality characteristics |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116739037A true CN116739037A (en) | 2023-09-12 |
Family
ID=87903767
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310656903.4A Pending CN116739037A (en) | 2023-06-05 | 2023-06-05 | Personality model construction method and device with personality characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116739037A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116910376A (en) * | 2023-09-14 | 2023-10-20 | 北京师范大学 | Sleep quality-based large five personality detection method and device |
-
2023
- 2023-06-05 CN CN202310656903.4A patent/CN116739037A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116910376A (en) * | 2023-09-14 | 2023-10-20 | 北京师范大学 | Sleep quality-based large five personality detection method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7316358B2 (en) | Systems, methods, and devices for biophysical modeling and response prediction | |
| CN108351862B (en) | Method and apparatus for determining developmental progress using artificial intelligence and user input | |
| Patro et al. | Ambient assisted living predictive model for cardiovascular disease prediction using supervised learning | |
| EP3783619A1 (en) | Human body health assessment method and system based on sleep big data | |
| CN116829050A (en) | Systems and methods for machine learning assisted cognitive assessment and therapy | |
| JP2018524137A (en) | Method and system for assessing psychological state | |
| JP2018524750A (en) | Method and system for monitoring stress conditions | |
| WO2023087917A1 (en) | Cognitive decision-making evaluation method and system based on multi-dimensional hierarchical drift diffusion model | |
| EP3890598A1 (en) | Passive data collection and use of machine-learning models for event prediction | |
| Galvan-Tejada et al. | Depression episodes detection in unipolar and bipolar patients: a methodology with feature extraction and feature selection with genetic algorithms using activity motion signal as information source | |
| CN115249541A (en) | Dynamic blood glucose prediction model construction method based on deep learning | |
| Sahoo et al. | Heart failure prediction using machine learning techniques | |
| CN116739037A (en) | Personality model construction method and device with personality characteristics | |
| Tripathi et al. | Keystroke-dynamics for Parkinson's disease signs detection in an at-home uncontrolled population: a new benchmark and method | |
| CN110299207A (en) | For chronic disease detection in based on computer prognosis model data processing method | |
| CN117133464A (en) | Intelligent monitoring system and monitoring method for health of old people | |
| Hart et al. | Using smartphone sensor paradata and personalized machine learning models to infer participants’ well-being: Ecological momentary assessment | |
| Melnykova et al. | Anomalies detecting in medical metrics using machine learning tools | |
| US20200321082A1 (en) | Confidence evaluation to measure trust in behavioral health survey results | |
| Kour et al. | An Advance Approach for Diabetes Detection by Implementing Machine Learning Algorithms | |
| Natarajan et al. | An Exploration of the Performance using Ensemble Methods Utilizing Random Forest Classifier for Diabetes Detection | |
| CN112397204B (en) | Method, device, computer equipment and storage medium for predicting altitude sickness | |
| Sharma et al. | Artificial neural network classification models for stress in reading | |
| Kalatzis et al. | Interactive dimensionality reduction for improving patient adherence in remote health monitoring | |
| Fournier et al. | Cross-situational consistency, variability and the behavioral signature |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |