Personality classification method and device, electronic equipment and storage medium

Abstract

The invention discloses a personality classification method and device, electronic equipment and a storage medium. The method comprises the following steps: obtaining resting state functional magnetic resonance image data of a plurality of individuals; performing spatial independent component analysis on the resting state functional magnetic resonance image data of each individual to obtain a spatial independent component of each individual; determining a standardized mutual information similarity matrix of a cross-individual spatial mode based on the spatial independent component of each individual; and determining a personality label of each individual based on the standardized mutual information similarity matrix of the cross-individual spatial pattern. According to the technical scheme, the independent component analysis method and the resting state functional magnetic resonance technology are combined, completely objective data-driven personality classification is achieved, the inherent limitation that a traditional personality classification method depends on subjective questionnaire measurement is broken through, and personality traits are classified more objectively and accurately.

Description

Technical Field

[0001] This invention relates to the field of biomedical technology, and in particular to a personality classification method, device, electronic device, and storage medium. Background Technology

[0002] Personality is the sum of an individual's stable behavioral patterns and internal tendencies, and it is a core influencing factor in human cognition, emotion, and behavior. Personality classification, as a crucial task in psychological research, not only has significant guiding implications for fields such as psychological counseling, educational guidance, and career assessment, but also holds important application value in the early diagnosis and personalized treatment of mental illnesses.

[0003] The most widely used personality assessment tools are questionnaire-based methods (such as the Big Five Personality Inventory (NEO), the Eysenck Personality Questionnaire (EPQ), and the Minnesota Multiphasic Personality Inventory (MMPI)). However, questionnaires have significant limitations:

[0004] (1) It is highly subjective and easily affected by individual subjective bias and self-report bias: Traditional personality questionnaires usually rely on individual subjective reports, which may be significantly biased due to individual self-awareness limitations, social expectation effect or deliberate concealment, thus seriously affecting the reliability and validity of the assessment.

[0005] (2) The personality classification criteria lack an objective biological basis and make it difficult to achieve stable cross-individual comparisons: Existing personality measurement tools are usually based on behavioral observation or subjective assessment. These classifications cannot fundamentally reflect the neurobiological mechanisms of personality differences between individuals and are difficult to provide a stable objective basis for psychological diagnosis and intervention.

[0006] In the process of realizing this invention, it was found that at least the following technical problems exist in the prior art: existing personality classification schemes are highly subjective and have the problem of inaccurate personality classification. Summary of the Invention

[0007] This invention provides a personality classification method, apparatus, electronic device, and storage medium to improve the objectivity and accuracy of personality classification.

[0008] According to one aspect of the present invention, a personality classification method is provided, comprising:

[0009] Acquire resting-state functional magnetic resonance imaging data from multiple individuals;

[0010] Spatial independent component analysis was performed on the resting-state functional magnetic resonance imaging data of each individual to obtain the spatial independent components of each individual;

[0011] Based on the spatially independent components of each individual, a standardized mutual information similarity matrix for cross-individual spatial patterns is determined;

[0012] The personality label for each individual is determined based on the standardized mutual information similarity matrix of the cross-individual spatial pattern.

[0013] According to another aspect of the present invention, a personality classification device is provided, comprising:

[0014] The resting-state functional magnetic resonance imaging data acquisition module is used to acquire resting-state functional magnetic resonance imaging data of multiple individuals.

[0015] The spatially independent component analysis module is used to perform spatially independent component analysis on the resting-state functional magnetic resonance imaging data of each individual to obtain the spatially independent components of each individual.

[0016] The standardized mutual information similarity matrix determination module is used to determine the standardized mutual information similarity matrix of cross-individual spatial patterns based on the spatially independent components of each individual.

[0017] The individual personality subtype determination module is used to determine the personality label of each individual based on the standardized mutual information similarity matrix of the cross-individual spatial patterns.

[0018] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0019] At least one processor;

[0020] and a memory communicatively connected to the at least one processor;

[0021] The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the personality classification method according to any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the personality classification method according to any embodiment of the present invention.

[0023] The technical solution of this invention acquires resting-state functional magnetic resonance imaging (fMRI) data of multiple individuals, then performs spatial independent component analysis (SDI) on the resting-state fMRI data of each individual to obtain the spatial independent components of each individual. Based on the spatial independent components of each individual, a standardized mutual information similarity matrix of cross-individual spatial patterns is determined, and finally, a personality label for each individual is determined based on the standardized mutual information similarity matrix of cross-individual spatial patterns. This technical solution, by combining independent component analysis with resting-state fMRI technology, achieves completely objective data-driven personality classification, breaking through the inherent limitations of traditional personality classification methods that rely on subjective questionnaire measurements, making personality trait classification more objective and accurate.

[0024] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a flowchart of a personality classification method provided in Embodiment 1 of the present invention;

[0027] Figure 2 This is a flowchart of a personality classification method provided in Embodiment 2 of the present invention;

[0028] Figure 3 This is a flowchart of a personality classification method provided in Embodiment 3 of the present invention;

[0029] Figure 4 This is a schematic diagram of the structure of a personality classification device provided in Embodiment 4 of the present invention;

[0030] Figure 5 This is a schematic diagram of the structure of an electronic device that implements the personality classification method of this invention. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be used interchangeably where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices. The acquisition, storage, use, and processing of data in the technical solutions of this application all comply with the relevant provisions of national laws and regulations.

[0033] Example 1

[0034] Figure 1 This is a flowchart of a personality classification method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where independent component analysis is combined with resting-state functional magnetic resonance imaging (fMRI) for personality classification. This method can be executed by a personality classification device, which can be implemented in hardware and / or software and can be configured in electronic devices such as terminals and servers. Figure 1 As shown, the method includes:

[0035] S110. Acquire resting-state functional magnetic resonance imaging data of multiple individuals.

[0036] Among them, resting-state functional magnetic resonance imaging data are medical images acquired from individuals using resting-state functional magnetic resonance imaging (rs-fMRI) technology.

[0037] For example, resting-state functional magnetic resonance imaging data can be acquired for each individual using a 3.0T or other type of magnetic resonance imaging device.

[0038] S120. Spatial independent component analysis was performed on the resting-state functional magnetic resonance imaging data of each individual to obtain the spatial independent components of each individual.

[0039] Among them, spatial independent component analysis refers to spatial independent component analysis (ICA), and spatial independent component (IC) refers to the result of spatial independent component analysis on resting-state functional magnetic resonance imaging data.

[0040] Specifically, for any individual, the individual's resting-state functional magnetic resonance imaging data can be decomposed into a temporal mixing matrix and a spatially independent component matrix, thereby obtaining the individual's spatially independent components, where the spatially independent component matrix is ​​in matrix form of the spatially independent components.

[0041] In some embodiments, independent component analysis can specifically be generalized ranking and averaging independent component analysis by reproducibility (gRAICAR).

[0042] It should be noted that traditional ICA methods often employ simple superposition or serial models, assuming that all individuals share a uniform spatial pattern, thus ignoring the differences in spatial patterns between individuals and making it difficult to accurately and effectively identify real-world personality subtypes. Generalized ranking and mean independent component analysis fully consider the variability of multiple ICA decompositions within an individual and the heterogeneity of brain network patterns between individuals, significantly improving the accuracy and stability of cross-individual registration of brain networks and effectively capturing individual differences.

[0043] S130. Determine the standardized mutual information similarity matrix of cross-individual spatial patterns based on the spatial independent components of each individual.

[0044] Among them, the standardized mutual information similarity matrix of cross-individual spatial patterns is a similarity matrix calculated based on the spatial independent components of multiple individuals. Any element in the similarity matrix represents the spatial distribution similarity between the spatial independent components of two individuals.

[0045] Specifically, standardized normalized mutual information (SNMI) and registration of cross-individual spatial patterns can be performed based on the spatially independent components of each individual, thereby obtaining a standardized mutual information similarity matrix of cross-individual spatial patterns. It should be noted that SNMI, by statistically analyzing the higher-order dependencies between independent components, can objectively assess the stability and consistency of cross-individual spatial patterns. Furthermore, through SNMI processing, the spatial similarity between each spatially independent component becomes comparable, reducing the interference of random noise and individual differences, and improving the accuracy and stability of cross-individual spatial independent component registration.

[0046] S140. Determine the personality label for each individual based on the standardized mutual information similarity matrix of the cross-individual spatial pattern.

[0047] Among them, personality labels can be subtypes such as open personality, conscientious personality, extraversion personality, or agreeable personality.

[0048] Specifically, based on the standardized mutual information similarity matrix of cross-individual spatial patterns, the personality tags of each individual can be objectively identified through community detection algorithms.

[0049] Based on the above embodiments, optionally, after acquiring resting-state functional magnetic resonance imaging (fMRI) data of multiple objects, the method further includes: performing preprocessing operations on the resting-state fMRI data of each individual to obtain preprocessed resting-state fMRI data of each individual. The preprocessing operations include at least one of removing initial time point data, correcting head motion, spatial normalization to a standard spatial template, spatial smoothing, and bandpass filtering. Correspondingly, performing spatial independent component analysis on the resting-state fMRI data of each individual to obtain the spatial independent components of each individual includes: performing spatial independent component analysis on the preprocessed resting-state fMRI data of each individual to obtain the spatial independent components of each individual.

[0050] For example, data preprocessing includes the following steps: removing images from the initial 10 time points of the resting-state functional magnetic resonance imaging (fMRI) data to eliminate the influence of initial instability of the magnetic resonance signal; registering the resting-state fMRI data at each time point using a rigid body registration method to correct for head displacement generated by the individual during the scanning process; spatially normalizing the resting-state fMRI data to a standard spatial template, which can be the Montreal Neurological Institute 152 (MNI152) template, to achieve spatial alignment of data between different individuals; spatially smoothing the images using a Gaussian kernel to improve the signal-to-noise ratio and enhance spatial consistency, wherein the size of the Gaussian kernel can be 6 mm in full width at half maximum (FWHM); and performing bandpass filtering on the resting-state fMRI data to retain low-frequency spontaneous brain activity signals and remove high-frequency physiological noise (such as heartbeat, respiration, etc.) and low-frequency drift, wherein the filtering frequency band can be set to 0.01–0.1 Hz.

[0051] The technical solution of this invention acquires resting-state functional magnetic resonance imaging (fMRI) data of multiple individuals, then performs spatial independent component analysis (SDI) on the resting-state fMRI data of each individual to obtain the spatial independent components of each individual. Based on the spatial independent components of each individual, a standardized mutual information similarity matrix of cross-individual spatial patterns is determined, and finally, a personality label for each individual is determined based on the standardized mutual information similarity matrix of cross-individual spatial patterns. This technical solution, by combining generalized ranking and average independent component analysis methods with resting-state fMRI technology, achieves completely objective data-driven personality classification, breaking through the inherent limitations of traditional personality classification methods that rely on subjective questionnaire measurements, making personality trait classification more objective and accurate.

[0052] Example 2

[0053] Figure 2 This is a flowchart of a personality classification method provided in Embodiment 2 of the present invention. The method in this embodiment can be combined with various optional schemes in the personality classification methods provided in the above embodiments. The personality classification method provided in this embodiment has been further optimized. Optionally, determining the standardized mutual information similarity matrix of cross-individual spatial patterns based on the spatially independent components of each individual includes: determining the spatial distribution similarity between the spatially independent components of each individual; and constructing a standardized mutual information similarity matrix of cross-individual spatial patterns based on the spatial distribution similarity between the spatially independent components of each individual.

[0054] like Figure 2 As shown, the method includes:

[0055] S210. Acquire resting-state functional magnetic resonance imaging data of multiple individuals.

[0056] S220. Spatial independent component analysis was performed on the resting-state functional magnetic resonance imaging data of each individual to obtain the spatial independent components of each individual.

[0057] S230. Determine the spatial distribution similarity between the spatially independent components of each individual.

[0058] The formula for determining the spatial distribution similarity between the spatially independent components of each individual is as follows:

[0059]

[0060] MI(S i ,S j )=H(S i )+H(S j )-H(S i ,S j );

[0061] Among them, R ij S represents the spatial distribution similarity between the spatially independent components of individual i and the spatially independent components of individual j. i S represents the spatially independent component of individual i. j MI(S) represents the spatially independent component of individual j. i ,S j H(S) represents the mutual information value between the spatially independent components of individual i and the spatially independent components of individual j. i H(S) represents the entropy of the spatially independent components of individual i. j The entropy of the spatially independent components of individual j, H(S) i ,S j Let represent the joint entropy of the spatially independent components of individual i and individual j, mean(MI) represent the average value of the mutual information values ​​among the spatially independent components of all individuals, and std(MI) represent the standard deviation of the mutual information values ​​among the spatially independent components of all individuals.

[0062] Specifically, H(S i )=-∑ k p(s ik logp(s) ik ); where s ik S represents i The value at the k-th spatial location; p(s) ik ) represents S i In s ik The probability density at a given point can be obtained through histogram statistics. Similarly, H(S) j )=-∑ l p(s jllogp(s) jl ); where s jk S represents j The value at the l-th spatial location; p(s) jl ) represents S j In s jl The probability density at a given point can be obtained through histogram statistics. Similarly, H(S) i ,S j )=-∑ k,l p(s ik ,s jl logp(s) ik ,s jl ), p(s ik ,s jl ) represents s ik and s jl The joint probability density can be obtained from the joint histogram statistics.

[0063] S240. Construct a standardized mutual information similarity matrix of cross-individual spatial patterns based on the spatial distribution similarity between the spatially independent components of each individual.

[0064] The standardized mutual information similarity matrix of cross-individual spatial patterns is composed of the spatial distribution similarity between the spatially independent components of an individual. In other words, each element in the standardized mutual information similarity matrix of cross-individual spatial patterns corresponds to a spatial distribution similarity.

[0065] For example, each individual is decomposed K times using ICA to obtain all spatially independent components of each individual. The spatial distribution similarity between any two individuals is calculated, thereby forming a standardized mutual information similarity matrix of cross-individual spatial patterns. Each element R in the standardized mutual information similarity matrix of cross-individual spatial patterns... ij This represents the spatial distribution similarity between the spatially independent components of individual i and the spatially independent components of individual j.

[0066] In some embodiments, after obtaining the standardized mutual information similarity matrix of cross-individual spatial patterns, gRAICAR registration can be performed on the standardized mutual information similarity matrix of cross-individual spatial patterns to obtain aligned components (AC). Then, cross-individual consistency index is calculated based on the aligned components. The cross-individual consistency index can be used to screen components with high consistency for cluster analysis, personality subtype identification, or as a basis for determining whether an individual deviates from a certain subgroup.

[0067] For example, the formula for calculating the cross-individual consistency index can be:

[0068]

[0069] Where, α ac This indicates the consistency index between individuals a and c in terms of registration components. Let represent the standardized mutual information similarity matrix across individual spatial patterns, and let represent the standardized spatial similarity values ​​between the spatially independent components of individuals a and c in the b-th and d-th ICA decompositions. K represents the number of repetitions of the ICA for each individual. N represents the total number of individuals. i(a,b) and j(c,d) represent the IC indices of individuals a and c that best match the target registration component in their b-th and d-th ICA decompositions, respectively.

[0070] S250. Determine the personality label for each individual based on the standardized mutual information similarity matrix of the cross-individual spatial pattern.

[0071] The technical solution of this invention provides an accurate data foundation for personality classification by determining the spatial distribution similarity between the spatially independent components of each individual, and then constructing a standardized mutual information similarity matrix of cross-individual spatial patterns based on the spatial distribution similarity between the spatially independent components of each individual.

[0072] Example 3

[0073] Figure 3 This is a flowchart of a personality classification method provided in Embodiment 3 of the present invention. The method in this embodiment can be combined with various optional schemes in the personality classification methods provided in the above embodiments. The personality classification method provided in this embodiment has been further optimized. Optionally, determining the personality label of each individual based on the standardized mutual information similarity matrix of the cross-individual spatial pattern includes: constructing an undirected graph of individual connections based on the standardized mutual information similarity matrix of the cross-individual spatial pattern, where each node in the undirected graph of individual connections represents an individual, and the edges between nodes represent the spatial distribution similarity between the spatial independent components of the individuals; clustering the undirected graph of individual connections based on the preset community detection algorithm to obtain at least one personality subtype group, where individuals in each personality subtype group have the same personality subtype; and identifying the personality subtype of each personality subtype group to obtain the personality label of each individual.

[0074] like Figure 3 As shown, the method includes:

[0075] S310. Acquire resting-state functional magnetic resonance imaging data of multiple individuals.

[0076] S320. Spatial independent component analysis was performed on the resting-state functional magnetic resonance imaging data of each individual to obtain the spatial independent components of each individual.

[0077] S330. Determine the standardized mutual information similarity matrix of cross-individual spatial patterns based on the spatially independent components of each individual.

[0078] S340. Construct an undirected graph of individual connections based on the standardized mutual information similarity matrix of the cross-individual spatial pattern. Each node in the undirected graph of individual connections represents an individual, and the edges between nodes represent the spatial distribution similarity between the spatial independent components of the individuals.

[0079] Among them, an individual-connected undirected graph refers to a graph structure network in which multiple individuals are connected.

[0080] Specifically, if the spatial distribution similarity Rij between the spatially independent components of two individuals exceeds a preset threshold (e.g., 75th percentile), then a weighted edge e is constructed between the nodes corresponding to the two individuals. ij ∈E, where the weight of the weighted edge is Rij, thus obtaining the individual connected undirected graph G(V,E).

[0081] S350. Based on the preset community detection algorithm, cluster the individual connected undirected graph to obtain at least one personality subtype group, and the individuals in each personality subtype group have the same personality subtype.

[0082] The preset community detection algorithm can be the k-clique community detection algorithm or other community detection algorithms, without specific limitations.

[0083] It should be noted that this invention creatively introduces the k-clique community detection algorithm, making personality subtype identification more automated and accurate, achieving efficient and robust automatic personality subtype detection, and effectively overcoming the shortcomings of traditional methods such as strong subjectivity and poor stability.

[0084] S360. Identify personality subtypes for each personality subtype group to obtain the personality label for each individual.

[0085] For example, assuming there are 4 individuals (numbered P1–P4), the standardized mutual information similarity matrix of cross-individual spatial patterns is shown in Table 1.

[0086] Table 1

[0087] P1 P2 P3 P4 P1 — 0.87 0.45 0.78 P2 0.87 — 0.51 0.80 P3 0.45 0.51 — 0.44 P4 0.78 0.80 0.44 —

[0088] If the preset threshold is 0.75, the following node pairs are considered to have significant similarity: P1–P2 (0.87), P1–P4 (0.78), and P2–P4 (0.80). Therefore, the constructed undirected graph G(V,E) of individual connections contains the following three edges: E = {(P1,P2), (P1,P4), (P2,P4)}. The three individuals P1, P2, and P3 may be identified as a personality subtype group in subsequent k-clique clustering.

[0089] Based on the above embodiments, optionally, after determining the personality label of each individual based on the standardized mutual information similarity matrix of cross-individual spatial patterns, the method further includes: for any personality subtype group, performing feature extraction on individuals in the personality subtype group to obtain the brain functional network features corresponding to the personality subtype group; for any personality subtype group, determining the personality label corresponding to the personality subtype group; and constructing a model based on the brain functional network features corresponding to each personality subtype group and the personality label corresponding to each personality subtype group to obtain an individual personality classification model.

[0090] For example, feature extraction is performed on individuals within a personality subtype group to obtain brain functional network features corresponding to the subtype, such as the average spatial activation map or frequency features of the registered components. Then, using the scores of a standard personality scale (such as NEO-FFI) for each personality subtype group as personality labels, and based on the corresponding brain functional network features and personality labels for each subtype group, multivariate statistical methods (such as principal component analysis (PCA) followed by classification) or machine learning models (such as support vector machines or random forests) are used for training and modeling. This yields an objective, repeatable, and verifiable individual personality classification model, providing a new technical means for mental health assessment and personalized intervention.

[0091] Based on the above embodiments, optionally, after constructing a model based on the brain functional network features corresponding to each personality subtype group and the personality labels corresponding to each personality subtype group to obtain an individual personality classification model, the method further includes: obtaining the brain functional network features of the individual to be tested; inputting the brain functional network features of the individual to be tested into the individual personality classification model to obtain the personality subtype of the individual to be tested.

[0092] Specifically, after the individual personality classification model, features can be extracted from new individuals to be tested to obtain the brain functional network features of the individuals to be tested. Then, the brain functional network features of the individuals to be tested are input into the individual personality classification model for rapid classification and prediction. The individual personality classification model outputs the personality subtype of the individuals to be tested.

[0093] The technical solution of this invention constructs an undirected graph of individual connections based on a standardized mutual information similarity matrix of cross-individual spatial patterns. Then, based on a preset community detection algorithm, the undirected graph is clustered to obtain at least one personality subtype group. Individuals within each personality subtype group share the same personality subtype. Personality subtype identification is then performed on each personality subtype group to obtain the personality label for each individual. This technical solution, by introducing a community detection algorithm, makes individual subgroup identification more automated and accurate, achieving efficient and robust automatic personality subtype discovery, effectively overcoming the shortcomings of traditional methods such as strong subjectivity and poor stability.

[0094] Example 4

[0095] Figure 4 This is a schematic diagram of a personality classification device provided in Embodiment 4 of the present invention. Figure 4 As shown, the device includes:

[0096] The resting-state functional magnetic resonance imaging data acquisition module 410 is used to acquire resting-state functional magnetic resonance imaging data of multiple individuals.

[0097] The spatially independent component analysis module 420 is used to perform spatially independent component analysis on the resting-state functional magnetic resonance imaging data of each individual to obtain the spatially independent components of each individual.

[0098] The standardized mutual information similarity matrix determination module 430 is used to determine the standardized mutual information similarity matrix of cross-individual spatial patterns based on the spatial independent components of each individual.

[0099] The individual personality subtype determination module 440 is used to determine the personality label of each individual based on the standardized mutual information similarity matrix of the cross-individual spatial pattern.

[0100] The technical solution of this invention acquires resting-state functional magnetic resonance imaging (fMRI) data of multiple individuals, then performs spatial independent component analysis (SDI) on the resting-state fMRI data of each individual to obtain the spatial independent components of each individual. Based on the spatial independent components of each individual, a standardized mutual information similarity matrix of cross-individual spatial patterns is determined, and finally, a personality label for each individual is determined based on the standardized mutual information similarity matrix of cross-individual spatial patterns. This technical solution, by combining generalized ranking and average independent component analysis methods with resting-state fMRI technology, achieves completely objective data-driven personality classification, breaking through the inherent limitations of traditional personality classification methods that rely on subjective questionnaire measurements, making personality trait classification more objective and accurate.

[0101] In some optional embodiments, the personality classification device further includes:

[0102] The image data preprocessing module is used to perform preprocessing operations on the resting-state functional magnetic resonance imaging data of each individual to obtain preprocessed resting-state functional magnetic resonance imaging data of each individual. The preprocessing operations include at least one of the following: removing initial time point data, correcting head motion, spatial normalization to a standard spatial template, spatial smoothing, and bandpass filtering.

[0103] Correspondingly, the spatially independent component analysis module 420 can be specifically used for:

[0104] Spatial independent component analysis was performed on the resting-state functional magnetic resonance imaging data of each individual after preprocessing to obtain the spatial independent components of each individual.

[0105] In some optional implementations, the standardized mutual information similarity matrix determination module 430 can specifically be used for:

[0106] Determine the spatial distribution similarity among the spatially independent components of each individual;

[0107] A standardized mutual information similarity matrix for cross-individual spatial patterns is constructed based on the spatial distribution similarity between the spatially independent components of each individual.

[0108] The formula for determining the spatial distribution similarity between the spatially independent components of each individual is as follows:

[0109]

[0110] MI(S i ,S j )=H(S i )+H(S j )-H(S i ,S j );

[0111] Among them, R ij S represents the spatial distribution similarity between the spatially independent components of individual i and the spatially independent components of individual j. i S represents the spatially independent component of individual i. j MI(S) represents the spatially independent component of individual j. i ,S j H(S) represents the mutual information value between the spatially independent components of individual i and the spatially independent components of individual j. i H(S) represents the entropy of the spatially independent components of individual i. j The entropy of the spatially independent components of individual j, H(S) i ,S jLet represent the joint entropy of the spatially independent components of individual i and individual j, mean(MI) represent the average value of the mutual information values ​​among the spatially independent components of all individuals, and std(MI) represent the standard deviation of the mutual information values ​​among the spatially independent components of all individuals.

[0112] In some alternative implementations, the individual personality subtype determination module 440 can specifically be used for:

[0113] Based on the standardized mutual information similarity matrix of the cross-individual spatial pattern, an individual connection undirected graph is constructed. Each node in the individual connection undirected graph represents an individual, and the edges between nodes represent the spatial distribution similarity between the spatial independent components of the individuals.

[0114] Based on the preset community detection algorithm, the individual connected undirected graph is clustered to obtain at least one personality subtype group, and the individuals in each personality subtype group have the same personality subtype.

[0115] For each personality subtype group, personality subtype identification is performed to obtain the personality label for each individual.

[0116] In some optional embodiments, the personality classification device further includes:

[0117] The feature extraction module is used to extract features from individuals in any personality subtype group to obtain the brain functional network features corresponding to the personality subtype group.

[0118] The personality label determination module is used to determine the personality label corresponding to any personality subtype group.

[0119] The model building module is used to build models based on the brain functional network features corresponding to each personality subtype and the personality labels corresponding to each personality subtype, so as to obtain individual personality classification models.

[0120] In some optional embodiments, the personality classification device further includes:

[0121] The test individual feature acquisition module is used to acquire the brain functional network features of the test individual;

[0122] The individual personality subtype prediction module is used to input the brain functional network characteristics of the individual to be tested into the individual personality classification model to obtain the individual personality subtype.

[0123] The personality classification device provided in this embodiment of the invention can execute the personality classification method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0124] Example 5

[0125] Figure 5 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0126] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An I / O interface 15 is also connected to the bus 14.

[0127] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0128] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a personality classification method, which includes:

[0129] Acquire resting-state functional magnetic resonance imaging data from multiple individuals;

[0130] Spatial independent component analysis was performed on the resting-state functional magnetic resonance imaging data of each individual to obtain the spatial independent components of each individual;

[0131] Based on the spatially independent components of each individual, a standardized mutual information similarity matrix for cross-individual spatial patterns is determined;

[0132] The personality label for each individual is determined based on the standardized mutual information similarity matrix of the cross-individual spatial pattern.

[0133] In some embodiments, the personality classification method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the personality classification method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the personality classification method by any other suitable means (e.g., by means of firmware).

[0134] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0135] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0136] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0137] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0138] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0139] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0140] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0141] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A personality classification method, characterized in that, include: Acquire resting-state functional magnetic resonance imaging data from multiple individuals; Spatial independent component analysis was performed on the resting-state functional magnetic resonance imaging data of each individual to obtain the spatial independent components of each individual; Based on the spatially independent components of each individual, a standardized mutual information similarity matrix for cross-individual spatial patterns is determined; The personality label for each individual is determined based on the standardized mutual information similarity matrix of the cross-individual spatial pattern.

2. The method according to claim 1, characterized in that, After acquiring resting-state functional magnetic resonance imaging data of multiple objects, the method further includes: Preprocessing operations are performed on the resting-state functional magnetic resonance imaging data of each individual to obtain preprocessed resting-state functional magnetic resonance imaging data of each individual. The preprocessing operations include at least one of the following: removing initial time point data, correcting head motion, spatial normalization to a standard spatial template, spatial smoothing, and bandpass filtering. Accordingly, the spatially independent component analysis of the resting-state functional magnetic resonance imaging data of each individual is performed to obtain the spatially independent components of each individual, including: Spatial independent component analysis was performed on the resting-state functional magnetic resonance imaging data of each individual after preprocessing to obtain the spatial independent components of each individual.

3. The method according to claim 1, characterized in that, The determination of the standardized mutual information similarity matrix of cross-individual spatial patterns based on the spatially independent components of each individual includes: Determine the spatial distribution similarity among the spatially independent components of each individual; A standardized mutual information similarity matrix for cross-individual spatial patterns is constructed based on the spatial distribution similarity between the spatially independent components of each individual.

4. The method according to claim 3, characterized in that, The formula for determining the spatial distribution similarity between the spatially independent components of each individual is as follows: MI(S i ,S j )=H(S i )+H(S j )-H(S i ,S j ); Among them, R ij S represents the spatial distribution similarity between the spatially independent components of individual i and the spatially independent components of individual j. i S represents the spatially independent component of individual i. j MI(S) represents the spatially independent component of individual j. i ,S j H(S) represents the mutual information value between the spatially independent components of individual i and the spatially independent components of individual j. i H(S) represents the entropy of the spatially independent components of individual i. j The entropy of the spatially independent components of individual j, H(S) i ,S j Let represent the joint entropy of the spatially independent components of individual i and individual j, mean(MI) represent the average value of the mutual information values ​​among the spatially independent components of all individuals, and std(MI) represent the standard deviation of the mutual information values ​​among the spatially independent components of all individuals.

5. The method according to claim 1, characterized in that, The determination of each individual's personality label based on the standardized mutual information similarity matrix of the cross-individual spatial pattern includes: Based on the standardized mutual information similarity matrix of the cross-individual spatial pattern, an individual connection undirected graph is constructed. Each node in the individual connection undirected graph represents an individual, and the edges between nodes represent the spatial distribution similarity between the spatial independent components of the individuals. Based on the preset community detection algorithm, the individual connected undirected graph is clustered to obtain at least one personality subtype group, and the individuals in each personality subtype group have the same personality subtype. For each personality subtype group, personality subtype identification is performed to obtain the personality label for each individual.

6. The method according to claim 5, characterized in that, After determining the personality label for each individual based on the standardized mutual information similarity matrix of the cross-individual spatial patterns, the method further includes: For any personality subtype group, feature extraction is performed on individuals in the personality subtype group to obtain the brain functional network features corresponding to the personality subtype group; For any personality subtype group, determine the personality label corresponding to the personality subtype group; Based on the brain functional network characteristics corresponding to each personality subtype and the personality labels corresponding to each personality subtype, a model is constructed to obtain an individual personality classification model.

7. The method according to claim 6, characterized in that, After constructing the individual personality classification model based on the brain functional network characteristics and personality labels corresponding to each personality subtype, the following steps are also included: Obtain the brain functional network characteristics of the individual to be tested; The brain functional network characteristics of the individual to be tested are input into the individual personality classification model to obtain the personality subtype of the individual to be tested.

8. A personality classification device, characterized in that, include: The resting-state functional magnetic resonance imaging data acquisition module is used to acquire resting-state functional magnetic resonance imaging data of multiple individuals. The spatially independent component analysis module is used to perform spatially independent component analysis on the resting-state functional magnetic resonance imaging data of each individual to obtain the spatially independent components of each individual. The standardized mutual information similarity matrix determination module is used to determine the standardized mutual information similarity matrix of cross-individual spatial patterns based on the spatially independent components of each individual. The individual personality subtype determination module is used to determine the personality label of each individual based on the standardized mutual information similarity matrix of the cross-individual spatial patterns.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the personality classification method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the personality classification method according to any one of claims 1-7.

Images