A Brain Cognitive Assessment Method, System, Storage Medium and Computer Device Based on DSM-V

Abstract

The present invention relates to the technical field of cognitive assessment, and specifically discloses a brain cognitive assessment method, system, storage medium and computer device based on DSM-V. This application first obtains the identification feature information and posture feature information of the user, then performs cognitive disorder identification on the identification feature information based on DSM-V and assigns a first evaluation score. Next, it obtains the emotional feature information of the user, and obtains the negative affect value according to the emotional feature information. Then, it obtains the abnormal movement coordination index according to the behavioral feature information. Finally, it obtains a second evaluation score according to the first evaluation score, negative affect value and abnormal movement coordination index, and evaluates the user according to the second evaluation score. In this way, the comprehensive evaluation of the user through the second evaluation score can correct the accuracy of the initial evaluation of DSM-V, thereby avoiding the influence of additional factors of the user on cognitive description and improving the accuracy of cognitive assessment.

Description

Technical Field

[0001] The present invention relates to the technical field of cognitive assessment, and in particular to a brain cognitive assessment method, system, storage medium and computer device based on DSM-V. Background Art

[0002] With the development of society and the aggravation of population aging, the incidence of diseases related to brain cognitive dysfunction has gradually increased. Accurately assessing brain cognitive function is of crucial significance for early diagnosis, disease monitoring, and formulating personalized treatment plans. As an authoritative standard for the diagnosis of mental disorders, DSM-V provides an important theoretical basis and framework for brain cognitive assessment. Among them, DSM-V refers to the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, which is a manual on the classification and diagnostic criteria of mental disorders.

[0003] Currently, the brain cognitive assessment usually adopts a question-and-answer or test-taking mode to score and judge users. However, this method cannot accurately describe their cognitive symptoms due to additional factors of users (such as their own emotions and abnormal behaviors). This single test-taking mode will result in low assessment accuracy. Therefore, a brain cognitive assessment method based on DSM-V is needed to solve the above problems. Summary of the Invention

[0004] The purpose of the present invention is to provide a brain cognitive assessment method, system, storage medium and computer device based on DSM-V to solve the technical problems raised in the above background art.

[0005] To achieve the above purpose, the present invention provides the following technical solutions:

[0006] Obtain the identification feature information and posture feature information of the user;

[0007] Classify the cognitive disorders based on DSM-V for the identification feature information, and obtain the corresponding degree of brain cognitive disorder according to the type obtained from the cognitive disorder classification;

[0008] Assign scores to the degree of cognitive disorder of the user based on the degree of cognitive disorder to obtain the first evaluation score;

[0009] Obtain the emotional feature information of the user, and obtain the depressive feature information and anxiety feature information according to the emotional feature information, and obtain the negative emotion value according to the depressive feature information;

[0010] Obtain pose feature information according to the described behavior feature information, and obtain an abnormal action coordination index according to the pose feature information and anxiety feature information;

[0011] Obtain a second evaluation score according to the first evaluation score, negative emotion value and abnormal action coordination index, and evaluate the user's brain cognition according to the second evaluation score.

[0012] Preferably, the step of obtaining depression feature information and anxiety feature information according to the emotion feature information includes:

[0013] Obtain the mental state feature of the user according to the emotion feature information;

[0014] Obtain the duration of the user's low mood within a preset time according to the mental state feature;

[0015] Obtain the prescription information of the user based on the drug purchase system, and screen whether there is depression-related drug information in the prescription information;

[0016] If there is depression-related drug information in the prescription information, it is determined that the user has potential depression features, and obtain depression feature information according to the potential depression features and the duration of low mood;

[0017] Obtain the physiological reaction feature of the user according to the emotion feature information, and obtain the heartbeat feature and breathing feature according to the physiological reaction feature;

[0018] Obtain the corresponding abnormal heartbeat frequency and abnormal heartbeat duration according to the heartbeat feature, and obtain the abnormal heartbeat frequency according to the number of abnormal heartbeats and the abnormal heartbeat duration;

[0019] Obtain the duration of shortness of breath and the number of shortness of breath within a preset time according to the breathing feature, obtain the shortness of breath frequency according to the duration of shortness of breath and the number of shortness of breath, obtain the comprehensive abnormal frequency according to the abnormal heartbeat frequency and the shortness of breath frequency, and use the anxiety state corresponding to the comprehensive abnormal frequency as anxiety feature information.

[0020] Preferably, the step of obtaining the negative emotion value according to the depression feature information includes:

[0021] Obtain the number of negative features according to the depression feature information, where the negative features include language negative features, attention negative features and physical negative features;

[0022] Establish a two-dimensional coordinate system according to the language negative feature, attention negative feature, physical negative feature and the duration of low mood;

[0023] Obtain multiple coincidence nodes of the language negative feature, attention negative feature, and body negative feature within the duration of low mood according to the two-dimensional coordinate system;

[0024] Obtain the corresponding coincidence frequency according to the multiple coincidence nodes, and use the coincidence frequency as the negative emotion value.

[0025] Preferably, the step of obtaining the abnormal movement coordination index according to the posture feature information and anxiety feature information includes:

[0026] Obtain the first center of gravity position of the user in the initial static state and multiple second center of gravity positions within a preset time according to the posture feature information;

[0027] Obtain the number of times of center of gravity deviation of the user according to the first center of gravity position and the multiple second center of gravity positions;

[0028] Obtain the abnormal posture frequency according to the number of times of center of gravity deviation;

[0029] Obtain the frequency abnormality rate according to the ratio of the comprehensive abnormality frequency corresponding to the anxiety feature information and the abnormal posture frequency to the preset standard frequency, and use the frequency abnormality rate as the abnormal movement coordination index.

[0030] Preferably, the step of obtaining the second evaluation score according to the first evaluation score, negative emotion value, and abnormal movement coordination index includes:

[0031] Obtain the corresponding first ideal value and maximum first evaluation value according to the first evaluation score;

[0032] Obtain the corresponding second ideal value and maximum negative emotion value according to the negative emotion value;

[0033] Obtain the corresponding third ideal value and maximum abnormal movement coordination index according to the abnormal movement coordination index;

[0034] Calculate the second evaluation score according to the first evaluation score, negative emotion value, abnormal movement coordination index, first ideal value, maximum first evaluation value, second ideal value, maximum negative emotion value, third ideal value, and maximum abnormal movement coordination index. The calculation formula is:

[0035] ;

[0036] Among them, D(PG) represents the second evaluation score, where the value range of the second evaluation score is [0, +∞], J(PG) represents the first evaluation score, X(XJ) represents the negative emotion value, F(ZH) represents the abnormal movement coordination index, J ideal represents the first ideal value, J max represents the maximum first evaluation value, Xideal Represents the second ideal value, X max Represents the maximum negative emotion value, F ideal Represents the third ideal value, F max Represents the maximum action coordination abnormality index.

[0037] Preferably, the step of evaluating the user according to the second evaluation score further includes:

[0038] Calculate an evaluation difference according to the first evaluation score and the second evaluation score;

[0039] Judge whether the evaluation difference satisfies a preset threshold range;

[0040] When the evaluation difference does not satisfy the preset threshold range and is less than the minimum value of the preset threshold range, it is determined that the cognitive impairment level corresponding to the first evaluation score is lower than the current cognitive impairment level;

[0041] When the evaluation difference satisfies the preset threshold range, it is determined that the cognitive impairment level corresponding to the first evaluation score is the current cognitive impairment level;

[0042] When the evaluation difference does not satisfy the preset threshold range and is greater than the maximum value of the preset threshold range, it is determined that the cognitive impairment level corresponding to the first evaluation score is higher than the current cognitive impairment level.

[0043] Preferably, after the step of evaluating the user according to the second evaluation score, it includes:

[0044] Obtain negative emotion keywords according to the negative emotion value, extract negative emotion factors according to the negative emotion keywords, map the negative emotion factors into the coding space according to the preset reception time sequence for coding, and obtain negative emotion coding;

[0045] Obtain the action abnormality type according to the action coordination abnormality index, extract the abnormal offset factor according to the action abnormality type, map the abnormal offset factor into the coding space according to the preset reception time sequence for coding, and obtain abnormal offset coding;

[0046] Obtain the cognitive feature information of the user in the next preset period, and map the cognitive feature information into the coding space according to the preset reception time sequence for coding, and obtain cognitive feature coding;

[0047] Construct a reference sample of the clustering model according to the negative emotion coding and the abnormal offset coding to obtain an expanded clustering model;

[0048] Input the cognitive feature encoding into the expanded clustering model, and group and extract the cognitive feature encoding through K-means clustering to obtain the first negative emotion encoding and the first abnormal deviation encoding.

[0049] This application also provides a brain cognitive assessment system based on DSM-V, including:

[0050] A first acquisition module for acquiring the identification feature information and posture feature information of the user;

[0051] A first identification module for classifying cognitive impairments based on DSM-V for the identification feature information, and obtaining the corresponding degree of brain cognitive impairment according to the type obtained from the cognitive impairment classification;

[0052] A second acquisition module for assigning scores to the user's cognitive impairment degree based on the degree of cognitive impairment to obtain the first evaluation score;

[0053] A third acquisition module for acquiring the emotional feature information of the user, obtaining the depressive feature information and anxiety feature information according to the emotional feature information, and obtaining the negative emotion value according to the depressive feature information;

[0054] A fourth acquisition module for obtaining the abnormal movement coordination index according to the posture feature information and anxiety feature information;

[0055] A fifth acquisition module for obtaining the second evaluation score according to the first evaluation score, negative emotion value and abnormal movement coordination index, and evaluating the user's brain cognition according to the second evaluation score.

[0056] This application also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above method are implemented.

[0057] This application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0058] The beneficial effects of this application are as follows: This application first obtains the user's recognition feature information and posture feature information, then conducts cognitive disorder recognition on the recognition feature information based on DSM-V and assigns a first evaluation score. Then, it obtains the user's emotional feature information, obtains the negative emotion value according to the emotional feature information, then obtains the abnormal movement coordination index according to the behavior feature information, and finally obtains the second evaluation score according to the first evaluation score, negative emotion value and abnormal movement coordination index, and evaluates the user's brain cognition according to the second evaluation score. In this way, the comprehensive evaluation of the user through the second evaluation score can correct the accuracy of the initial evaluation of DSM-V, thereby avoiding the influence of the user's additional factors (such as their own emotions and abnormal behaviors) on the cognitive description and improving the accuracy of cognitive evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a schematic flowchart of the method of an embodiment of this application.

[0060] Figure 2 It is a schematic structural diagram of the system of an embodiment of this application.

[0061] Figure 3 It is a schematic internal structure diagram of a computer device of an embodiment of this application.

[0062] Figure 4 It is a schematic diagram of a two-dimensional coordinate system of an embodiment of this application.

[0063] The realization, functional features and advantages of the purpose of this application will be further described in conjunction with the embodiments with reference to the drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0064] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0065] As Figures 1-3 shown, this application provides a method for brain cognition evaluation based on DSM-V, including:

[0066] S1. Obtain the user's recognition feature information and posture feature information;

[0067] S2. Classify the cognitive disorders of the recognition feature information based on DSM-V, and obtain the corresponding degree of brain cognitive disorder according to the type obtained from the cognitive disorder classification;

[0068] S3. Assign a score to the degree of the user's cognitive disorder based on the degree of cognitive disorder to obtain a first evaluation score;

[0069] S4. Obtain the user's emotional feature information, obtain the depression feature information and anxiety feature information according to the emotional feature information, and obtain the negative emotion value according to the depression feature information;

[0070] S5. Obtain the posture feature information according to the behavior feature information, and obtain the abnormal movement coordination index according to the posture feature information and the anxiety feature information;

[0071] S6. Obtain the second evaluation score according to the first evaluation score, the negative emotion value and the abnormal movement coordination index, and evaluate the user's brain cognition according to the second evaluation score.

[0072] As described in the above steps S1 - S6, since the current method for evaluating brain cognition usually uses a question - answering or test - taking mode to score and judge users, but this method cannot accurately describe their cognitive symptoms due to users' additional factors (such as their own emotions and abnormal behaviors). This single test - taking mode results in relatively low evaluation accuracy. Therefore, the present invention first obtains the user's identification feature information and posture feature information, which can collect data related to the user from multiple perspectives, avoiding the limitations of a single information source and providing a basis for the accuracy of the evaluation. Then, based on DSM - V, the identification feature information is classified for cognitive impairment, and the corresponding degree of brain cognitive impairment is obtained according to the type of cognitive impairment classification. Then, the degree of the user's cognitive impairment is scored based on the degree of cognitive impairment to obtain the first evaluation score. By using the existing DSM - V as the basic evaluation basis, the cognitive impairment level of the user can be preliminarily screened out, and it is quantitatively reflected through the scoring method for evaluating the cognitive impairment level. Since the user's emotions will affect the cognitive diagnosis process, resulting in states such as resistance, randomness, or understanding emotions brought about by educational background and cognition, which seriously affect the cognitive evaluation. Therefore, it is necessary to obtain the user's emotional feature information, and obtain the depressive feature information and anxiety feature information according to the emotional feature information, and obtain the negative emotion value according to the depressive feature information. Then, obtain the posture feature information according to the behavior feature information, and obtain the abnormal movement coordination index according to the posture feature information and anxiety feature information. In this way, through the abnormal movement coordination index, the user's mental state can be understood more deeply, and the quantitative value of the abnormal movement coordination index can more accurately measure the degree of influence of these emotional problems on the user's overall state. At the same time, since posture and movement coordination ability reflect the brain's control and regulation function of body movement and are closely related to multiple cognitive fields of the brain, such as the executive function of the frontal lobe and the movement coordination function of the cerebellum, the abnormal movement coordination index can objectively reflect the degree of abnormality in the user's movement coordination, providing an important basis for evaluating the brain's cognitive function. Finally, obtain the second evaluation score according to the first evaluation score, negative emotion value, and abnormal movement coordination index, and evaluate the user's brain cognition according to the second evaluation score. In this way, through the second evaluation score, the comprehensive evaluation of the user can correct the accuracy of the initial evaluation by DSM - V, thereby avoiding the influence of the user's additional factors (such as their own emotions and abnormal behaviors) on cognitive description and improving the accuracy of cognitive evaluation.

[0073] In one embodiment, step S4 of obtaining the depressive feature information and anxiety feature information according to the emotional feature information includes:

[0074] S401. Obtain the mental state features of the user according to the emotional feature information;

[0075] S402. Obtain the duration of the user's low mood within a preset time according to the mental state characteristics;

[0076] S403. Obtain the user's prescription information based on the drug purchase system, and screen whether there is any depression-related drug information in the prescription information;

[0077] If there is depression-related drug information in the prescription information, determine that the user has potential depression characteristics, and obtain depression characteristic information according to the potential depression characteristics and the duration of the low mood;

[0078] S405. Obtain the user's physiological reaction characteristics according to the mood characteristic information, and obtain the heart rate characteristic and the breathing characteristic according to the physiological reaction characteristics;

[0079] S406. Obtain the corresponding abnormal heart rate frequency and the duration of the abnormal heart rate according to the heart rate characteristic, and obtain the abnormal heart rate frequency according to the number of abnormal heart rates and the duration of the abnormal heart rate;

[0080] S407. Obtain the duration of shortness of breath and the number of times of shortness of breath within a preset time according to the breathing characteristic, obtain the shortness of breath frequency according to the duration of shortness of breath and the number of times of shortness of breath, obtain the comprehensive abnormal frequency according to the abnormal heart rate frequency and the shortness of breath frequency, and use the anxiety state corresponding to the comprehensive abnormal frequency as the anxiety characteristic information.

[0081] As described in the above steps S401 - S407, since the user's mood characteristics can be comprehensively judged from the appearance and mental outlook and the physical index values, therefore, the present invention obtains the user's mental state characteristics according to the mood characteristic information, and then obtains the duration of the user's low mood within a preset time according to the mental state characteristics. The obtaining method is based on shooting a video, and based on face recognition to obtain the user's facial state, and then extract the time when the low mood facial state appears within a preset time. In this way, the severity of the user's depression is judged through the duration of the low mood. Among them, short-term low mood may be related to factors such as stress events, while long-term continuous low mood is one of the factors reflecting depression characteristics. When obtaining whether the user has depression characteristics, the user's prescription information can be obtained based on the drug purchase system, and screen whether there is any depression-related drug information in the prescription information. If there is depression-related drug information in the prescription information, determine that the user has potential depression characteristics. Among them, combined with the duration of the low mood, it can more accurately judge whether the user has depressive symptoms. Then, the depression characteristic information can be obtained comprehensively according to the duration of the low mood and the potential depression characteristics. Furthermore, through the depression characteristic information, important influencing factors can be provided for cognitive judgment, and important basis can be provided for the evaluation and judgment of cognition.

[0082] Since a person will experience an accelerated heartbeat and rapid breathing in an anxious situation, and an accelerated heartbeat and rapid breathing are manifestations of anxiety characteristics. At the same time, in an anxious state, the body will automatically enter a stress state, and a large amount of physiological resources will be allocated to the system for coping with potential threats. However, the resources available for cognitive processing in the brain are relatively limited. In this case, the resources originally allocated to cognitive functions such as attention, memory, and thinking will be partially transferred to coping with the body's stress response, resulting in relatively insufficient resources required for cognitive processing, and further leading to insufficient user cognition. On this basis, it is necessary to first obtain the physiological response characteristics of the user according to the emotional characteristic information, and obtain the heartbeat characteristics and breathing characteristics according to the physiological response characteristics. Then, obtain the corresponding abnormal heartbeat frequency and abnormal heartbeat duration according to the heartbeat characteristics, and obtain the abnormal heartbeat frequency according to the number of abnormal heartbeats and the abnormal heartbeat duration. Finally, obtain the rapid breathing duration and the number of rapid breathing times within a preset time according to the breathing characteristics, and obtain the rapid breathing frequency according to the rapid breathing duration and the number of rapid breathing times, and obtain the comprehensive abnormal frequency according to the abnormal heartbeat frequency and the rapid breathing frequency, and use the anxiety state corresponding to the comprehensive abnormal frequency as the anxiety characteristic information. In this way, the reactions of two important physiological systems, the cardiovascular system and the respiratory system, are comprehensively considered, making the judgment of anxiety characteristics more comprehensive and objective. This method of comprehensive evaluation of multiple physiological indicators can more accurately capture anxiety symptoms, avoid misjudgment caused by fluctuations in single physiological indicators, and also provide a quantitative basis for the influence of additional factors in the evaluation process.

[0083] In one embodiment, step S4 of obtaining the negative emotion value according to the depression characteristic information includes:

[0084] S408. Obtain the number of negative characteristics according to the depression characteristic information, where the negative characteristics include language negative characteristics, attention negative characteristics, and physical negative characteristics;

[0085] S409. Establish a two-dimensional coordinate system according to the language negative characteristics, attention negative characteristics, physical negative characteristics, and the duration of emotional depression;

[0086] S4010. Obtain multiple overlapping nodes of the language negative characteristics, attention negative characteristics, and physical negative characteristics within the duration of emotional depression according to the two-dimensional coordinate system;

[0087] S4011. Obtain the corresponding overlapping frequency according to the multiple overlapping nodes, and use the overlapping frequency as the negative emotion value.

[0088] As described in the above steps S408 - S4011, since a negative state can be determined whether there are negative language features from language description words, etc., combined with the negative attention features of being difficult to concentrate, easily distracted, and overly concerned about negative information, and then combined with the negative physical features of listlessness, slow movement, and lack of vitality, the negative state of the user can be comprehensively judged. Therefore, the present invention first obtains the number of negative feature occurrences according to the depressive feature information, where the negative features include negative language features, negative attention features, and negative physical features. In this way, the above - mentioned sub - features can corroborate the influence of user's additional factors on cognitive assessment. Then, a two - dimensional coordinate system is established according to the negative language features, negative attention features, negative physical features, and the duration of low mood. Among them, three points are taken on the Y - axis of the two - dimensional coordinate system, which respectively represent negative language features, negative attention features, and negative physical features. The negative language features count the number of occurrences of negative words (such as "despair", "failure", "pain", etc.) during the duration of low mood. The negative attention features count the number of occurrences of the features that the user is easily distracted and difficult to concentrate in daily activities (such as reading, working, studying, etc.) during the duration of low mood. The negative physical features record the user's body postures through video and count the number of occurrences of body postures (such as the degree of slouching, hanging shoulders), limb movements (such as slow and weak movements), and facial expressions (such as frowning, listless eyes), while the X - axis represents the duration of low mood. In this way, multiple coincidence nodes of negative language features, negative attention features, and negative physical features during the duration of low mood can be obtained according to the two - dimensional coordinate system (such as Figure 4 as shown). Then, the corresponding coincidence frequency is obtained according to the multiple coincidence nodes, and the coincidence frequency is used as the negative emotion value. In this way, the number and distribution of the coincidence nodes reflect the coordination and stability between these features. The more the number and the denser the distribution, the stronger the correlation between these negative features, and the more stable and severe the negative emotion state of the user. At the same time, it can also quantify the negative emotion. This quantification method comprehensively considers multiple depressive features and their mutual relationship in time. Compared with single - index evaluation, it can more accurately reflect the overall negative emotion intensity of the user. For example, if a user frequently shows negative language, inattentiveness, and physical listlessness at the same time (more coincidence nodes) within a period of time, then his negative emotion value will be higher, indicating a heavier degree of depression; on the contrary, fewer coincidence nodes mean a relatively lower negative emotion value. Thus, the negative emotion value can be used as an important basis for evaluating cognitive judgment.

[0089] In one embodiment, step S5 of obtaining the abnormal movement coordination index according to the posture feature information and anxiety feature information includes:

[0090] S501. Obtain the first center-of-gravity position of the user in the initial static state and multiple second center-of-gravity positions within a preset time according to the posture feature information;

[0091] S502. Obtain the number of times of center-of-gravity offset of the user according to the first center-of-gravity position and the multiple second center-of-gravity positions;

[0092] S503. Obtain the posture anomaly frequency according to the number of times of center-of-gravity offset;

[0093] S504. Obtain the frequency anomaly rate according to the comprehensive anomaly frequency corresponding to the anxiety feature information and the ratio of the posture anomaly frequency to the preset standard frequency, and use the frequency anomaly rate as the movement coordination anomaly index.

[0094] As described in the above steps S501 - S504, due to a certain degree of overlap and mutual connection in the regions of the brain responsible for movement coordination and cognitive functions. For example, the cerebellum not only plays a key role in regulating the coordination, balance, and precision of body movements, but also participates in some cognitive processes such as attention, language processing, and working memory. When movement coordination is abnormal, it may imply damage to the function of the cerebellum or its related neural pathways, which in turn affects the activities of the brain regions involved in cognitive functions connected to it, resulting in a decline in cognitive judgment ability. Therefore, in the present invention, first, obtain the first center-of-gravity position of the user in the initial static state and multiple second center-of-gravity positions within a preset time according to the posture feature information, then obtain the number of times of center-of-gravity offset of the user according to the first center-of-gravity position and the multiple second center-of-gravity positions. Calculating the number of times of center-of-gravity offset can convert the posture feature into a quantifiable index. The more the number of times of center-of-gravity offset, the greater the challenge the user faces in maintaining a stable posture, which may imply problems with their movement coordination ability or proprioception. This quantification method can more objectively describe the degree of posture abnormality of the user, avoiding the uncertainty of relying solely on subjective observation. Then, obtain the posture anomaly frequency according to the number of times of center-of-gravity offset, and then obtain the frequency anomaly rate according to the comprehensive anomaly frequency corresponding to the anxiety feature information and the ratio of the posture anomaly frequency to the preset standard frequency, and use the frequency anomaly rate as the movement coordination anomaly index. In this way, the movement coordination anomaly index can provide a unified index to measure the degree of abnormality in the user's movement coordination, and can provide comprehensive data support for evaluating the user's cognitive impairment, avoiding the one-sidedness that may be caused by separately evaluating anxiety or posture features.

[0095] In one embodiment, step S6 of obtaining the second evaluation score according to the first evaluation score, negative emotion value, and movement coordination anomaly index includes:

[0096] S601. Obtain the corresponding first ideal value and maximum first evaluation value according to the first evaluation score;

[0097] S602. Obtain the corresponding second ideal value and the maximum negative emotion value according to the negative emotion value;

[0098] S603. Obtain the corresponding third ideal value and the maximum abnormal movement coordination index according to the abnormal movement coordination index;

[0099] S604. Calculate a second evaluation score according to the first evaluation score, the negative emotion value, the abnormal movement coordination index, the first ideal value, the maximum first evaluation value, the second ideal value, the maximum negative emotion value, the third ideal value, and the maximum abnormal movement coordination index. The calculation formula is as follows:

[0100] ;

[0101] where D(PG) represents the second evaluation score, and the value range of the second evaluation score is [0, +∞). J(PG) represents the first evaluation score, X(XJ) represents the negative emotion value, F(ZH) represents the abnormal movement coordination index, J ideal represents the first ideal value, J max represents the maximum first evaluation value, X ideal represents the second ideal value, X max represents the maximum negative emotion value, F ideal represents the third ideal value, F max represents the maximum abnormal movement coordination index.

[0102] As described in the above steps S601 - S602, the present invention first obtains the corresponding first ideal value and the maximum first evaluation value according to the first evaluation score, then obtains the corresponding second ideal value and the maximum negative emotion value according to the negative emotion value, then obtains the corresponding third ideal value and the maximum abnormal movement coordination index according to the abnormal movement coordination index, and finally calculates the second evaluation score according to the first evaluation score, the negative emotion value, the abnormal movement coordination index, the first ideal value, the maximum first evaluation value, the second ideal value, the maximum negative emotion value, the third ideal value, and the maximum abnormal movement coordination index. In this way, by calculating the distances between the first evaluation score, the negative emotion value, and the abnormal movement coordination index and their respective ideal state values, the overall state of the brain - cognitive patient is comprehensively evaluated, so as to obtain the second evaluation score. The greater the distance, the farther the index deviates from the ideal state, and the greater the impact on the overall evaluation. Therefore, the cognitive state of the user can be more accurately evaluated through the second evaluation score.

[0103] In one embodiment, step S6 of evaluating the user according to the second evaluation score further includes:

[0104] S603. Calculate an evaluation difference according to the first evaluation score and the second evaluation score;

[0105] S604. Determine whether the evaluation difference satisfies a preset threshold range;

[0106] When the evaluation difference does not satisfy the preset threshold range and is less than the minimum value of the preset threshold range, it is determined that the level of cognitive impairment corresponding to the first evaluation score is lower than the current level of cognitive impairment;

[0107] When the evaluation difference satisfies the preset threshold range, it is determined that the level of cognitive impairment corresponding to the first evaluation score is the current level of cognitive impairment;

[0108] When the evaluation difference does not satisfy the preset threshold range and is greater than the maximum value of the preset threshold range, it is determined that the level of cognitive impairment corresponding to the first evaluation score is higher than the current level of cognitive impairment.

[0109] As described in the above steps S603 - S604, in this application, first, the evaluation difference is calculated based on the first evaluation score and the second evaluation score, and then it is determined whether the evaluation difference satisfies the preset threshold range. When the evaluation difference does not satisfy the preset threshold range and is less than the minimum value of the preset threshold range, it is determined that the level of cognitive impairment corresponding to the first evaluation score is lower than the current level of cognitive impairment. When the evaluation difference satisfies the preset threshold range, it is determined that the level of cognitive impairment corresponding to the first evaluation score is the current level of cognitive impairment. When the evaluation difference does not satisfy the preset threshold range and is greater than the maximum value of the preset threshold range, it is determined that the level of cognitive impairment corresponding to the first evaluation score is higher than the current level of cognitive impairment. In this way, the evaluation of the first evaluation score can be corrected through the evaluation difference, which can avoid the influence of additional factors of the user (such as their own emotions and abnormal behaviors) on the cognitive description and improve the accuracy of cognitive evaluation.

[0110] In one embodiment, after step S6 of evaluating the user according to the second evaluation score, it includes:

[0111] S7. Obtain negative emotion keywords according to the negative emotion value, extract negative emotion factors according to the negative emotion keywords, map the negative emotion factors into the coding space according to the preset reception time sequence for coding, and obtain negative emotion coding;

[0112] S8. Obtain the type of movement abnormality according to the movement coordination abnormality index, extract the abnormal deviation factor according to the type of movement abnormality, map the abnormal deviation factor into the coding space according to the preset reception time sequence for coding, and obtain abnormal deviation coding;

[0113] S9. Obtain the cognitive feature information of the user in the next preset period, and map the cognitive feature information into the coding space according to the preset reception time sequence for coding to obtain cognitive feature codes;

[0114] S10. Construct a reference sample of the clustering model based on the negative emotion code and the abnormal offset code to obtain an expanded clustering model.

[0115] S11. Input the cognitive feature codes into the expanded clustering model, and perform grouped extraction on the cognitive feature codes through K-means clustering to obtain the first negative emotion code and the first abnormal offset code.

[0116] As described in the above steps S7 - S11, since the user needs to repeat the steps of the first time during the evaluation process in the next preset period after the initial evaluation, this results in a long time occupation. Therefore, the present invention first obtains negative emotion keywords according to the negative emotion value, extracts negative emotion factors according to the negative emotion keywords, maps the negative emotion factors into the coding space according to the preset reception time sequence for coding to obtain negative emotion codes, then obtains the action abnormal type according to the action coordination abnormal index, extracts abnormal offset factors according to the action abnormal type, maps the abnormal offset factors into the coding space according to the preset reception time sequence for coding to obtain abnormal offset codes, then obtains the cognitive feature information of the user in the next preset period, and maps the cognitive feature information into the coding space according to the preset reception time sequence for coding to obtain cognitive feature codes. Immediately afterwards, obtain the cognitive feature information of the user in the next preset period, and map the cognitive feature information into the coding space according to the preset reception time sequence for coding to obtain cognitive feature codes. Then, construct a reference sample of the clustering model based on the negative emotion code and the abnormal offset code to obtain an expanded clustering model. Finally, input the cognitive feature codes into the expanded clustering model, and perform grouped extraction on the cognitive feature codes through K-means clustering to obtain the first negative emotion code and the first abnormal offset code. The specific steps are as follows: The specific steps are to divide the cognitive feature codes into K clusters, and then each cluster is represented by a centroid. The clustering model algorithm continuously optimizes the centroid position through iteration to minimize the distance between the samples in the same cluster and the centroid. For example, for the extraction of cognitive feature codes, regard the negative emotion code and the abnormal offset code as the centroid of each cluster, and then regard the cognitive feature codes as samples, making the cognitive feature codes close to the negative emotion code and the abnormal offset code, so as to gather the same codes to obtain the first negative emotion code and the first abnormal offset code. Furthermore, through the obtained first negative emotion code and the first abnormal offset code, it can quickly provide a convenient basis for obtaining the additional factors (negative emotion value and action coordination abnormal index) of the user for the next evaluation.

[0117] The present application also provides a brain cognitive assessment system based on DSM-V, including:

[0118] A first acquisition module 1, configured to acquire the identification feature information and posture feature information of a user;

[0119] A first identification module 2, configured to classify cognitive impairments based on DSM-V for the identification feature information, and obtain the corresponding degree of brain cognitive impairment according to the type obtained from the cognitive impairment classification;

[0120] A second acquisition module 3, configured to assign scores to the cognitive impairment degree of the user based on the degree of cognitive impairment to obtain a first evaluation score;

[0121] A third acquisition module 4, configured to acquire the emotional feature information of the user, and obtain depressive feature information and anxiety feature information according to the emotional feature information, and obtain a negative affect value according to the depressive feature information;

[0122] A fourth acquisition module 5, configured to obtain an abnormal movement coordination index according to the posture feature information and the anxiety feature information;

[0123] A fifth acquisition module 6, configured to obtain a second evaluation score according to the first evaluation score, the negative affect value, and the abnormal movement coordination index, and evaluate the brain cognition of the user according to the second evaluation score.

[0124] The present invention also provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned brain cognitive assessment method based on DSM-V are implemented.

[0125] The present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned brain cognitive assessment method for DSM-V are implemented.

[0126] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium provided in this application and used in the embodiments can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0127] It should be noted that, in this article, the term "comprising", "including" or any other variant thereof is intended to cover a non-exclusive inclusion, so that a process, apparatus, article or method comprising a series of elements includes not only those elements but also other elements not expressly listed, or further includes elements inherent to such process, apparatus, article or method. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, apparatus, article or method comprising the element.

[0128] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall equally be included in the patent protection scope of the present invention.

Claims

1. A brain cognitive assessment method based on DSM-V, characterized in that, Including: Obtain the identification feature information and posture feature information of the user; Classify the cognitive impairment based on DSM-V for the identification feature information, and obtain the corresponding degree of brain cognitive impairment according to the type obtained from the cognitive impairment classification; Assign a score to the user's cognitive impairment degree based on the degree of cognitive impairment to obtain a first evaluation score; Obtain the emotional feature information of the user, and obtain the depressive feature information and anxiety feature information according to the emotional feature information, and obtain the negative emotion value according to the depressive feature information; Obtain the abnormal movement coordination index according to the posture feature information and anxiety feature information; Obtain a second evaluation score according to the first evaluation score, negative emotion value and abnormal movement coordination index, and evaluate the user's brain cognition according to the second evaluation score; Obtain negative emotion keywords according to the negative emotion value, extract negative emotion factors according to the negative emotion keywords, map the negative emotion factors into the coding space according to the preset receiving time sequence for coding to obtain negative emotion coding; Obtain the abnormal movement type according to the abnormal movement coordination index, extract the abnormal deviation factor according to the abnormal movement type, map the abnormal deviation factor into the coding space according to the preset receiving time sequence for coding to obtain abnormal deviation coding; Obtain the cognitive feature information of the user in the next preset period, and map the cognitive feature information into the coding space according to the preset receiving time sequence for coding to obtain cognitive feature coding; Construct a reference sample of the clustering model according to the negative emotion coding and the abnormal deviation coding to obtain an expanded clustering model; Input the cognitive feature coding into the expanded clustering model, and perform grouping extraction on the cognitive feature coding through K-means clustering to obtain the first negative emotion coding and the first abnormal deviation coding.

2. The method for brain cognitive assessment based on DSM-V according to claim 1, wherein The step of obtaining the depressive feature information and anxiety feature information according to the emotional feature information includes: Obtain the mental state feature of the user according to the emotional feature information; Obtain the duration of the user's low mood within a preset time according to the mental state feature; Obtain the prescribing information of the user based on the drug purchase system, and screen whether there is depressive-related drug information in the prescribing information; If there is depressive-related drug information in the prescribing information, it is determined that the user has potential depressive features, and obtain the depressive feature information according to the potential depressive features and the duration of the low mood; Obtain the physiological reaction feature of the user according to the emotional feature information, and obtain the heartbeat feature and breathing feature according to the physiological reaction feature; Obtain the corresponding number of heartbeat abnormalities and the duration of heartbeat abnormalities according to the heartbeat feature, and obtain the heartbeat abnormality frequency according to the number of heartbeat abnormalities and the duration of heartbeat abnormalities; Obtain the duration of shortness of breath and the number of shortness of breath within a preset time according to the breathing feature, obtain the shortness of breath frequency according to the duration of shortness of breath and the number of shortness of breath, obtain the comprehensive abnormality frequency according to the heartbeat abnormality frequency and the shortness of breath frequency, and use the anxiety state corresponding to the comprehensive abnormality frequency as the anxiety feature information.

3. The method for brain cognitive assessment based on DSM-V according to claim 1, wherein, The step of obtaining the negative emotion value according to the depressive feature information includes: Obtain the number of negative features according to the depression feature information, where the negative features include language negative features, attention negative features, and physical negative features; Establish a two-dimensional coordinate system based on the language negative features, attention negative features, physical negative features, and the duration of low mood; Obtain multiple overlapping nodes of the language negative features, attention negative features, and physical negative features within the duration of low mood according to the two-dimensional coordinate system; Obtain the corresponding overlapping frequency according to the multiple overlapping nodes, and use the overlapping frequency as the negative emotion value.

4. The method for brain cognitive assessment based on DSM-V according to claim 1, wherein The step of obtaining the abnormal movement coordination index according to the posture feature information and the anxiety feature information includes: Obtain the first center of gravity position of the user in the initial static state and multiple second center of gravity positions within a preset time according to the posture feature information; Obtain the number of times of center of gravity offset of the user according to the first center of gravity position and the multiple second center of gravity positions; Obtain the abnormal posture frequency according to the number of times of center of gravity offset; Obtain the frequency abnormality rate according to the comprehensive abnormality frequency corresponding to the anxiety feature information and the ratio of the abnormal posture frequency to the preset standard frequency, and use the frequency abnormality rate as the abnormal movement coordination index.

5. The brain cognitive assessment method based on DSM-V according to claim 1, wherein The step of obtaining the second evaluation score according to the first evaluation score, the negative emotion value, and the abnormal movement coordination index includes: Obtain the corresponding first ideal value and the maximum first evaluation value according to the first evaluation score; Obtain the corresponding second ideal value and the maximum negative emotion value according to the negative emotion value; Obtain the corresponding third ideal value and the maximum abnormal movement coordination index according to the abnormal movement coordination index; Calculate the second evaluation score according to the first evaluation score, the negative emotion value, the abnormal movement coordination index, the first ideal value, the maximum first evaluation value, the second ideal value, the maximum negative emotion value, the third ideal value, and the maximum abnormal movement coordination index, where the calculation formula is: ； Among them, D(PG) represents the second evaluation score, where the value range of the second evaluation score is [0, +∞], J(PG) represents the first evaluation score, X(XJ) represents the negative emotion value, F(ZH) represents the abnormal movement coordination index, J ideal represents the first ideal value, J max represents the maximum first evaluation value, X ideal represents the second ideal value, X max represents the maximum negative emotion value, F ideal represents the third ideal value, F max represents the maximum abnormal movement coordination index.

6. The method for brain cognitive assessment based on DSM-V according to claim 1, wherein, The step of evaluating the user according to the second evaluation score further includes: Calculate the evaluation difference according to the first evaluation score and the second evaluation score; Judge whether the evaluation difference satisfies the preset threshold range; When the evaluation difference does not satisfy the preset threshold range and is less than the minimum value of the preset threshold range, it is determined that the cognitive impairment level corresponding to the first evaluation score is lower than the current cognitive impairment level; When the evaluation difference satisfies the preset threshold range, it is determined that the cognitive impairment level corresponding to the first evaluation score is the current cognitive impairment level; When the evaluation difference does not satisfy the preset threshold range and is greater than the maximum value of the preset threshold range, it is determined that the cognitive impairment level corresponding to the first evaluation score is higher than the current cognitive impairment level.

7. A brain cognitive assessment system based on DSM-V, characterized in that Including: A first acquisition module for acquiring the identification feature information and the posture feature information of the user; A first identification module for classifying cognitive impairment based on DSM-V for the identification feature information, and obtaining the corresponding brain cognitive impairment level according to the type obtained from the cognitive impairment classification; A second acquisition module for assigning a score to the cognitive impairment level of the user based on the cognitive impairment level to obtain a first evaluation score; A third acquisition module, configured to acquire the emotional characteristic information of a user, and acquire depression characteristic information and anxiety characteristic information according to the emotional characteristic information, and acquire a negative emotion value according to the depression characteristic information; A fourth acquisition module, configured to acquire an abnormal movement coordination index according to the posture characteristic information and the anxiety characteristic information; A fifth acquisition module, configured to acquire a second evaluation score according to the first evaluation score, the negative emotion value and the abnormal movement coordination index, and evaluate the brain cognition of the user according to the second evaluation score; A sixth acquisition module, configured to acquire negative emotion keywords according to the negative emotion value, extract negative emotion factors according to the negative emotion keywords, map the negative emotion factors into a coding space according to a preset reception time sequence for coding, and obtain a negative emotion code; A seventh acquisition module, configured to acquire an abnormal movement type according to the abnormal movement coordination index, extract an abnormal deviation factor according to the abnormal movement type, map the abnormal deviation factor into a coding space according to a preset reception time sequence for coding, and obtain an abnormal deviation code; An eighth acquisition module, configured to acquire the cognitive characteristic information of the user in the next preset period, and map the cognitive characteristic information into a coding space according to a preset reception time sequence for coding, and obtain a cognitive characteristic code; A construction module, configured to construct a reference sample of a clustering model according to the negative emotion code and the abnormal deviation code, and obtain an expanded clustering model; An extraction module, configured to input the cognitive characteristic code into the expanded clustering model, and perform grouping extraction on the cognitive characteristic code through K-means clustering to obtain a first negative emotion code and a first abnormal deviation code.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images