A method, device, equipment and readable storage medium for predicting mental disorders

Abstract

The present invention relates to the technical field of psychological disorder assessment. Specifically, it relates to a method, device, equipment and readable storage medium for predicting psychological disorders. The method includes obtaining information on the tendency scale of emotion regulation strategies and at least one psychological disorder label. The information on the tendency scale of emotion regulation strategies includes at least one emotion regulation strategy, and the psychological disorder label includes the type, severity and behavioral manifestations of the psychological disorder of the person to be evaluated; collecting the information on the tendency scale of emotion regulation strategies within the sampling time to obtain sampling information, where the sampling information includes the frequency sequence of each emotion regulation strategy adopted by the person to be evaluated; establishing a first psychological disorder prediction model according to the sampling information and at least one psychological disorder label; predicting the current psychological disorder of the person to be evaluated according to the first psychological disorder prediction model. The present invention can quickly predict psychological disorders through the frequencies of each emotion regulation strategy selected by the person to be evaluated.

Description

Technical Field

[0001] The present invention relates to the technical field of psychological disorder assessment, and more particularly, to a method, device, equipment, and readable storage medium for predicting psychological disorders. Background Art

[0002] Emotion regulation strategies refer to the behavioral and cognitive strategies that individuals adopt when coping with emotional experiences. Some studies have shown that there is a positive correlation between maladaptive emotion regulation strategies such as rumination and expressive suppression and psychological disorders such as depression and anxiety. However, in the current field of psychological disorder assessment technology, research in this area is still in a blank. It is urgent to predict and evaluate psychological disorders by how patients choose emotion regulation strategies. Summary of the Invention

[0003] The purpose of the present invention is to provide a method, device, equipment, and readable storage medium for predicting psychological disorders to improve the above problems.

[0004] To achieve the above purpose, the embodiments of the present application provide the following technical solutions:

[0005] On the one hand, the embodiments of the present application provide a method for predicting psychological disorders, the method comprising:

[0006] Obtaining emotion regulation strategy tendency scale information and at least one psychological disorder label, the emotion regulation strategy tendency scale information including at least one emotion regulation strategy, and the psychological disorder label including the type, severity, and behavioral manifestations of the psychological disorder of the person to be evaluated;

[0007] Collecting the emotion regulation strategy tendency scale information within the sampling time to obtain sampling information, the sampling information including the frequency sequence of the person to be evaluated adopting each emotion regulation strategy;

[0008] Establishing a first psychological disorder prediction model according to the sampling information and at least one of the psychological disorder labels;

[0009] Predicting the current psychological disorder of the person to be evaluated according to the first psychological disorder prediction model.

[0010] On the second hand, the embodiments of the present application provide a device for predicting psychological disorders, the device comprising:

[0011] A first acquisition module, configured to obtain emotion regulation strategy tendency scale information and at least one psychological disorder label, the emotion regulation strategy tendency scale information including at least one emotion regulation strategy, and the psychological disorder label including the type, severity, and behavioral manifestations of the psychological disorder of the person to be evaluated;

[0012] The first processing module is configured to collect the information of the emotion regulation strategy tendency scale within the sampling time to obtain sampling information, where the sampling information includes the frequency sequence of each emotion regulation strategy adopted by the person to be evaluated.

[0013] The second processing module is configured to establish a first psychological disorder prediction model according to the sampling information and at least one of the psychological disorder labels.

[0014] The third processing module is configured to predict the current psychological disorder of the person to be evaluated according to the first psychological disorder prediction model.

[0015] In a third aspect, an embodiment of the present application provides a psychological disorder prediction device, which includes a memory and a processor. The memory is used to store a computer program; the processor is configured to implement the steps of the above psychological disorder prediction method when executing the computer program.

[0016] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the above psychological disorder prediction method.

[0017] The beneficial effects of the present invention are as follows:

[0018] The present invention collects the information of the emotion regulation strategy tendency scale of the person to be evaluated within the sampling time to obtain the frequency sequence of each emotion regulation strategy adopted by the person to be evaluated, and then constructs a first psychological disorder prediction model according to the frequency sequence information and the corresponding psychological disorder labels to predict the psychological disorder data of the person to be evaluated at the current moment, establishing a connection between the emotion regulation strategy and the psychological disorder prediction. According to the frequency of each emotion regulation strategy selected by the person to be evaluated, the rapid prediction of the psychological disorder can be realized, effectively solving the problem that the prediction and evaluation of the psychological disorder need to be realized through cumbersome expert interviews in the prior art.

[0019] Other features and advantages of the present invention will be described in the subsequent description, and part of them will become obvious from the description, or be understood by implementing the embodiments of the present invention. The objectives and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. Description of the Drawings

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 Schematic flowchart of the psychological disorder prediction method described in the embodiments of the present invention.

[0022] Figure 2 Schematic structural diagram of the psychological disorder prediction device described in the embodiments of the present invention.

[0023] Figure 3 Schematic structural diagram of the psychological disorder prediction device described in the embodiments of the present invention.

[0024] Annotations in the figure: 901, First acquisition module; 902, First processing module; 903, Second processing module; 904, Third processing module; 905, Second acquisition module; 906, Fourth processing module; 907, Fifth processing module; 908, Sixth processing module; 909, Seventh processing module; 9011, First acquisition unit; 9012, First calculation unit; 9013, First processing unit; 9014, Second calculation unit; 9015, Second processing unit; 9016, Third processing unit; 90121, Second acquisition unit; 90122, Third calculation unit; 90123, Fourth calculation unit; 90124, Fifth calculation unit; 90125, Sixth calculation unit; 9041, Fourth processing unit; 9042, Fifth processing unit; 9043, Sixth processing unit; 9044, Iteration unit; 9045, Seventh processing unit; 9046, Eighth processing unit; 90441, Third acquisition unit; 90442, Optimization unit; 90443, Ninth processing unit; 800, Psychological disorder prediction device; 801, Processor; 802, Memory; 803, Multimedia component; 804, I / O interface; 805, Communication component. Detailed implementation manners

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Components of the embodiments of the present invention described and illustrated in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed present invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0026] It should be noted that similar reference numerals and letters denote similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. At the same time, in the description of the present invention, terms such as "first", "second", etc. are only used for differential description and cannot be construed as indicating or implying relative importance. Embodiment 1:

[0027] This embodiment provides a method for predicting mental disorders. It can be understood that in this embodiment, a scenario can be set up. For example: a scenario of recording and counting the frequencies of a person to be evaluated choosing various emotion regulation strategies in a day and predicting and evaluating the mental disorders of the person to be evaluated according to the frequencies of choosing various emotion regulation strategies.

[0028] See Figure 1 , the figure shows that this method includes step S1, step S2, step S3 and step S4.

[0029] Step S1: Obtain information of an emotion regulation strategy tendency scale and at least one mental disorder label. The information of the emotion regulation strategy tendency scale includes at least one emotion regulation strategy, and the mental disorder label includes the type, severity and behavioral manifestations of the mental disorder of the person to be evaluated;

[0030] It can be understood that emotion regulation strategies refer to the behavioral and cognitive strategies adopted by individuals when coping with emotional experiences, including positive and negative strategies; mental disorders refer to the abnormal, maladaptive or pathological states of individuals in terms of emotions, cognitions, behaviors or social interactions. There is a close relationship between emotion regulation strategies and mental disorders. Therefore, in this step, by collecting sampling information and mental disorder labels to further explore the relationship between emotion regulation strategies and mental disorders. It should be noted that the emotion regulation strategies included in the information of the emotion regulation strategy tendency scale can be attention diversion, cognitive reappraisal, rumination, reflection, acceptance, expressive suppression, but are not limited to attention diversion, cognitive reappraisal, rumination, reflection, acceptance, expressive suppression.

[0031] It can be understood that step S1 also includes step S11, step S12, step S13, step S14, step S15 and step S16, specifically as follows:

[0032] Step S11: Obtain a measurement scale, which includes at least one measurement question, and each measurement question corresponds to at least one measurement option;

[0033] In this step, the measurement scales mainly include the Beck Depression Inventory, the Patient Health Questionnaire, the Self-Rating Anxiety Scale, the Athens Insomnia Scale, the Hamilton Depression Rating Scale, the Hamilton Anxiety Rating Scale, etc.

[0034] Step S12: Calculate the importance degree of each option corresponding to each assessment question in the assessment scale to obtain the first information;

[0035] It can be understood that step S12 further includes steps S121, S122, S123, S124, and S125, specifically as follows:

[0036] Step S121: Obtain at least two pieces of first scale information, where the first scale information includes at least one piece of first sub-scale information and at least one piece of second sub-scale information. The first sub-scale information includes the scale information filled in by personnel with mental disorders, and the second sub-scale information includes the scale information filled in by personnel without mental disorders;

[0037] In this step, the first scale information is a large amount of sample data collected, including the scale information filled in by personnel with mental disorders and the scale information filled in by personnel without mental disorders. Among them, the number of personnel with mental disorders is often less than that of healthy personnel, resulting in the number of the first sub-scale information being often less than the number of the second sub-scale information.

[0038] Step S122: Calculate the proportion of the selected first option in all the first sub-scale information to obtain the first calculation result;

[0039] In this step, the first option is any selected option in the scale, and calculate how many scales in the first sub-scale filled in by personnel with mental disorders have selected the first option.

[0040] Step S123: Calculate the proportion of the selected first option in all the second sub-scale information to obtain the second calculation result;

[0041] In this step, calculate how many scales in the second sub-scale filled in by personnel without mental disorders (i.e., healthy personnel) have selected the first option.

[0042] Step S124: Calculate according to the selected first option and all the first scale information to obtain the third calculation result;

[0043] Step S125: Calculate according to the first calculation result, the second calculation result, and the third calculation result to obtain the importance degree of the first option.

[0044] In this step, the specific calculation process of the importance degree of the first option is as follows:

[0045] ;

[0046] In the above formula, represents the selected first option X iThe proportion in all the first sub-scale information; Indicates the selected first option X i The proportion in all the second sub-scale information; N represents the number of all the first scales. Indicates the number of the first scales that select the first option. By calculating through the above formula, the importance degree of the first option can be quantified.

[0047] In this embodiment, it can effectively avoid the problem of inaccurate calculation of the importance degree of options caused by uneven data between the first sub-scale information and the second sub-scale information, thereby further improving the accuracy of generating psychological disorder labels.

[0048] Step S13: Simplify the assessment scale according to the first information to obtain a simplified assessment scale;

[0049] In this step, through calculation, the importance degree of multiple options corresponding to each assessment question can be obtained. The option with the highest importance degree is used as the main option of this question to obtain the second option. It is judged whether the importance degree corresponding to the second option is greater than the preset threshold information. If it is greater, the assessment question corresponding to the second option is retained. If it is less, the assessment question corresponding to the second option is removed, so as to realize the simplification of the assessment scale. By streamlining the assessment scale, it is possible to avoid the cumbersome answering of questions by the assessors, improve the assessment efficiency while ensuring the accuracy, and further improve the efficiency of generating psychological disorder labels.

[0050] Step S14: Calculate the importance degree of each assessment question in the simplified assessment scale to obtain the second information;

[0051] It can be understood that the assessment questions are not independent of each other. For example, in the assessment questions of this scale, there is a correlation between "I feel more nervous and anxious than usual" and "I am easily upset or feel panicked". Therefore, in this step, by introducing an attention mechanism to calculate the problem weight matrix, specifically:

[0052] ;

[0053] In the above formula, Q represents the query matrix, K represents the key matrix. is the adjustment factor. is the problem weight matrix represents the activation function. By sending all the assessment questions to the attention layer, the weight matrix can assign corresponding weights to each assessment question to represent the importance degree of each assessment question.

[0054] Step S15: Calculate according to the second information and the first information to obtain the scoring information;

[0055] In this step, the score of each assessment question can be calculated based on the importance of each option of the assessment question and the importance of the assessment question; by calculating according to the scores of each assessment question, the scoring information of each assessment scale can be obtained.

[0056] Step S16: Generate a mental disorder label according to the scoring information.

[0057] In this step, according to the scoring range where the scoring information is located, the mental disorder data corresponding to the assessor, that is, the type, severity, and behavioral manifestations of the assessor's mental disorder, can be determined. According to the corresponding mental disorder data, a mental disorder label can be generated, preparing a data set for establishing the first mental disorder prediction model in the follow-up.

[0058] Step S2: Collect the information of the emotion regulation strategy tendency scale within the sampling time to obtain sampling information, where the sampling information includes the frequency sequence of each emotion regulation strategy adopted by the person to be assessed.

[0059] In this step, the sampling time is preset artificially. Here, the sampling time is two weeks. Within the sampling time, the frequencies of each emotion regulation strategy adopted by the person to be assessed are collected, and a frequency sequence is constructed in turn, providing a data basis for the training of the first mental disorder prediction model.

[0060] Step S3: Establish a first mental disorder prediction model according to the sampling information and at least one of the mental disorder labels.

[0061] Step S4: Predict the current mental disorder of the person to be assessed according to the first mental disorder prediction model.

[0062] It can be understood that step S4 further includes steps S41, S42, S43, S44, S45, and S46, which are specifically as follows:

[0063] Step S41: Calculate the matching degree value according to the prediction result and the actual result of the trained first mental disorder prediction model.

[0064] In this step, the first mental disorder prediction model is a BP neural network model. Calculating the matching degree between the prediction result of the trained first mental disorder prediction model and the actual result is a well-known technical solution to those skilled in the art, so it will not be elaborated here.

[0065] Step S42: Adjust the fitness function of the BP neural network according to the matching degree value.

[0066] In this step, the fitness function is specifically:

[0067] ;

[0068] In the above formula, is the i-th matching degree value, is the predicted value of the i-th matching degree value. N is the total number of all matching degree values. The predicted value of the matching degree value is the matching degree value predicted based on neural network training or the value predicted based on a preset.

[0069] Step S43: Calculate the fitness function of each particle, and determine the individual optimal position and the particle swarm optimal position in the first iteration;

[0070] In this step, the update criterion for the individual optimal position is to select the individual position with a larger fitness value as the individual optimal position according to the size of the fitness value. The update criterion for the global optimal position is to select the global position with a larger fitness value as the global optimal position according to the size of the fitness value.

[0071] Step S44: Iteratively update the individual optimal position and the particle swarm optimal position until the optimal particle position is found;

[0072] In this step, the update of the particle's own position is achieved through two formulas, one is the velocity formula and the other is the position formula. Among them, the velocity formula is specifically:

[0073] ;

[0074] In the above formula, is the updated velocity, is the current velocity, and are acceleration factors, and their values are in the range of [1, 2]. w is the inertia factor, is the best position found by this particle so far, is the best position found by all particles so far. r1 and r2 are random numbers on [0, 1].

[0075] The position formula is specifically:

[0076] ;

[0077] In the above formula, is the position of the particle after update, is the position of the particle before update, is the velocity of the particle after update.

[0078] It can be understood that step S44 also includes step S441, step S442, and step S443, where specifically:

[0079] Step S441: Obtain the velocity weight parameter;

[0080] Step S442: Optimize the initial position formula with the velocity weight parameter to obtain an optimized position formula;

[0081] In this step, the optimized position formula is specifically:

[0082] ;

[0083] In the above formula, is the position of the particle after update, is the position of the particle before update, is the velocity of the particle after update, is the maximum number of iterations, is the current number of iterations.

[0084] Step S443: Iteratively update the particle position according to the optimized position formula.

[0085] In this embodiment, by adding a velocity weight parameter to the position formula, the particle can jump out of the range of the local optimal solution, and thus is more likely to search for the global optimal solution, so as to output better weight values and thresholds, and improve the prediction accuracy of the psychological disorder prediction model.

[0086] Step S45: Obtain the initial connection weights and thresholds according to the optimal particle position;

[0087] In this step, when the optimal particle position is found, the iteration stops, and the weight values and thresholds of the neural network algorithm are output.

[0088] Step S46: Learn from the training set according to the initial connection weights and the thresholds to establish an optimal first psychological disorder prediction model.

[0089] In this embodiment, using the particle swarm optimization algorithm to optimize the BP neural network can effectively improve the prediction accuracy.

[0090] It can be understood that after step S4, there are also steps S5, S6, S7, S8, and S9, where specifically:

[0091] Step S5: Obtain the sampling interval period;

[0092] It can be understood that the sampling interval period is preset artificially, and in this step, one month is used as the sampling interval period.

[0093] Step S6: Repeatedly sample the information of the emotional regulation strategy tendency scale of the person to be evaluated according to the sampling interval period to obtain sample data;

[0094] In this step, the preset sampling time is two weeks, and the frequency sequence of each emotion regulation strategy adopted by the person to be evaluated within two weeks is collected once every month to obtain sample data. It should be noted that the psychological disorder label of the person to be evaluated is obtained corresponding to each sampling time.

[0095] Step S7: Divide the sample data according to the sampling interval period to obtain the divided sample data;

[0096] In this step, using the sample data as historical data, the sample data is formed into a one-dimensional time series data in chronological order. Since the change of psychological disorders is time-varying, therefore, the sample data is divided according to the sampling interval period, and the one-dimensional time series is divided into multiple time periods, and each time period is used as a dimension, so as to construct a multi-dimensional time series and obtain the divided sample data. By dividing the sample data, the understanding of the change law of the frequency sequence information in the time series is strengthened, so as to further improve the accuracy of the prediction result of the second psychological disorder prediction model.

[0097] Step S8: Construct a training set according to the psychological disorder label and at least one of the divided sample data;

[0098] Step S9: Train the second psychological disorder prediction model using the training set to obtain the trained second psychological disorder prediction model, and the second psychological disorder prediction model is used to predict the psychological disorder after the current moment.

[0099] In this embodiment, by dividing the sample data to obtain a multi-dimensional time series, the understanding of the change law of the frequency sequence information in the time series can be effectively improved, and the change law of the frequency data within different sampling interval periods can be further explored, making the prediction result more accurate. It should be noted that the second psychological disorder prediction model is used to predict the psychological disorder after the current moment, where the time after the current moment is related to the sampling interval period. If the sampling interval period is one month, it is used to predict the psychological disorder data at least one month later.

[0100] Embodiment 2:

[0101] As Figure 2 shown, this embodiment provides a psychological disorder prediction device, and the device includes a first acquisition module 901, a first processing module 902, a second processing module 903, and a third processing module 904.

[0102] The first acquisition module 901 is used to acquire the emotion regulation strategy tendency scale information and at least one psychological disorder label, where the emotion regulation strategy tendency scale information includes at least one emotion regulation strategy, and the psychological disorder label includes the psychological disorder type, severity, and behavior performance of the person to be evaluated;

[0103] The first processing module 902 is configured to collect the information of the emotion regulation strategy tendency scale within the sampling time to obtain sampling information, where the sampling information includes the frequency sequence of each emotion regulation strategy adopted by the person to be evaluated.

[0104] The second processing module 903 is configured to establish a first psychological disorder prediction model according to the sampling information and at least one of the psychological disorder labels.

[0105] The third processing module 904 is configured to predict the current psychological disorder of the person to be evaluated according to the first psychological disorder prediction model.

[0106] In a specific implementation manner of the present disclosure, the first acquisition module 901 further includes a first acquisition unit 9011, a first calculation unit 9012, a first processing unit 9013, a second calculation unit 9014, a second processing unit 9015, and a third processing unit 9016, where specifically:

[0107] The first acquisition unit 9011 is configured to acquire a measurement scale, where the measurement scale includes at least one measurement question, and each measurement question corresponds to at least one measurement option.

[0108] The first calculation unit 9012 is configured to calculate the importance degree of each option corresponding to each measurement question in the measurement scale to obtain first information.

[0109] The first processing unit 9013 is configured to simplify the measurement scale according to the first information to obtain a simplified measurement scale.

[0110] The second calculation unit 9014 is configured to calculate the importance degree of each measurement question in the simplified measurement scale to obtain second information.

[0111] The second processing unit 9015 is configured to calculate according to the second information and the first information to obtain scoring information.

[0112] The third processing unit 9016 generates a psychological disorder label according to the scoring information.

[0113] In a specific implementation manner of the present disclosure, the first calculation unit 9012 further includes a second acquisition unit 90121, a third calculation unit 90122, a fourth calculation unit 90123, a fifth calculation unit 90124, and a sixth calculation unit 90125, where specifically:

[0114] The second acquisition unit 90121 is configured to acquire at least two pieces of first scale information, where the first scale information includes at least one piece of first sub-scale information and at least one piece of second sub-scale information, the first sub-scale information includes scale information filled in by a person with a mental disorder, and the second sub-scale information includes scale information filled in by a person without a mental disorder;

[0115] The third calculation unit 90122 is configured to calculate the proportion of the selected first option in all the first sub-scale information to obtain a first calculation result;

[0116] The fourth calculation unit 90123 is configured to calculate the proportion of the selected first option in all the second sub-scale information to obtain a second calculation result;

[0117] The fifth calculation unit 90124 is configured to perform calculations based on the selected first option and all the first scale information to obtain a third calculation result;

[0118] The sixth calculation unit 90125 is configured to perform calculations based on the first calculation result, the second calculation result, and the third calculation result to obtain the importance degree of the first option.

[0119] In a specific embodiment of the present disclosure, the third processing module 904 further includes a fourth processing unit 9041, a fifth processing unit 9042, a sixth processing unit 9043, an iteration unit 9044, a seventh processing unit 9045, and an eighth processing unit 9046, specifically:

[0120] The fourth processing unit 9041 is configured to perform calculations based on the prediction result and the actual result of the trained first mental disorder prediction model to obtain a matching degree value;

[0121] The fifth processing unit 9042 is configured to adjust the fitness function of the BP neural network according to the matching degree value;

[0122] The sixth processing unit 9043 is configured to calculate the fitness function of each particle and determine the individual optimal position and the particle swarm optimal position for the first iteration;

[0123] The iteration unit 9044 is configured to iteratively update the individual optimal position and the particle swarm optimal position until the optimal particle position is found;

[0124] The seventh processing unit 9045 is configured to obtain the initial connection weights and thresholds according to the optimal particle position;

[0125] The eighth processing unit 9046 is configured to learn from the training set according to the initial connection weights and the thresholds to establish an optimal first mental disorder prediction model.

[0126] In a specific embodiment of the present disclosure, the iterative unit 9044 further includes a third acquisition unit 90441, an optimization unit 90442, and a ninth processing unit 90443, specifically as follows:

[0127] The third acquisition unit 90441 is configured to acquire a speed weight parameter;

[0128] The optimization unit 90442 is configured to optimize the initial position formula with the speed weight parameter to obtain an optimized position formula;

[0129] The ninth processing unit 90443 is configured to iteratively update the particle position according to the optimized position formula.

[0130] In a specific embodiment of the present disclosure, after the third processing module 904, there further includes a second acquisition module 905, a fourth processing module 906, a fifth processing module 907, a sixth processing module 908, and a seventh processing module 909, specifically as follows:

[0131] The second acquisition module 905 is configured to acquire a sampling interval period;

[0132] The fourth processing module 906 is configured to repeatedly sample the mood regulation strategy tendency scale information of the person to be evaluated according to the sampling interval period to obtain sample data;

[0133] The fifth processing module 907 is configured to divide the sample data according to the sampling interval period to obtain divided sample data;

[0134] The sixth processing module 908 is configured to construct a training set according to the psychological disorder label and at least one of the divided sample data;

[0135] The seventh processing module 909 is configured to train the second psychological disorder prediction model with the training set to obtain a trained second psychological disorder prediction model, and the second psychological disorder prediction model is used to predict psychological disorders after the current moment.

[0136] It should be noted that for the devices in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0137] Embodiment 3:

[0138] Corresponding to the above method embodiment, in this embodiment, there is also provided a psychological disorder prediction device, and a psychological disorder prediction device described below can be mutually corresponding and referred to with a psychological disorder prediction method described above.

[0139] Figure 3 is a block diagram of a mental disorder prediction device 800 shown according to an exemplary embodiment. As Figure 3 shown, the mental disorder prediction device 800 may include: a processor 801, a memory 802. The mental disorder prediction device 800 may further include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0140] Among them, the processor 801 is used to control the overall operation of the mental disorder prediction device 800 to complete all or part of the steps in the above mental disorder prediction method. The memory 802 is used to store various types of data to support the operation of the mental disorder prediction device 800. These data may include, for example, instructions for any application or method operating on the mental disorder prediction device 800, as well as application-related data, such as contact data, received and sent messages, pictures, audio, video, and so on. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disc. The multimedia component 803 may include a screen and an audio component. Among them, the screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone, and the microphone is used to receive external audio signals. The received audio signals may be further stored in the memory 802 or sent through the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above other interface modules may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the mental disorder prediction device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G or 4G, or a combination of one or more of them. Accordingly, the communication component 805 may include: a Wi-Fi module, a Bluetooth module, an NFC module.

[0141] In an exemplary embodiment, the mental disorder prediction device 800 can be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components, and is used to execute the above-mentioned mental disorder prediction method.

[0142] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided. When the program instructions are executed by a processor, the steps of the above-mentioned mental disorder prediction method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions can be executed by the processor 801 of the mental disorder prediction device 800 to complete the above-mentioned mental disorder prediction method.

[0143] Embodiment 4:

[0144] Corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment. A readable storage medium described below can be correspondingly referred to with a mental disorder prediction method described above.

[0145] A readable storage medium has a computer program stored thereon. When the computer program is executed by a processor, the steps of the mental disorder prediction method in the above method embodiment are implemented.

[0146] The readable storage medium can specifically be various readable storage media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc that can store program codes.

[0147] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

[0148] As described above, it is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for predicting mental disorders, characterized in that, Including: Obtaining information of an emotion regulation strategy tendency scale and at least one psychological disorder label, where the information of the emotion regulation strategy tendency scale includes at least one emotion regulation strategy, and the psychological disorder label includes the type, severity, and behavioral manifestations of the psychological disorder of the person to be evaluated during the sampling time; Collecting the information of the emotion regulation strategy tendency scale during the sampling time to obtain sampling information, where the sampling information includes the frequency sequence of each emotion regulation strategy adopted by the person to be evaluated; Establishing a first psychological disorder prediction model based on the sampling information and at least one of the psychological disorder labels to predict the current psychological disorder of the person to be evaluated, and the model is a BP neural network model; Among them, obtaining at least one of the psychological disorder labels includes: Obtaining a measurement scale, which includes at least one question, and each question corresponds to at least one option. The measurement scale includes the Beck Depression Inventory, Patient Health Questionnaire, Self-Rating Anxiety Scale, Athens Insomnia Scale, Hamilton Depression Rating Scale, Hamilton Anxiety Rating Scale; Calculating the importance degree of each option of the measurement scale to obtain first information, including: Obtaining at least two pieces of first scale information, where the first scale information includes at least one piece of first sub-scale information and at least one piece of second sub-scale information. The first sub-scale information includes the scale information filled in by people with psychological disorders, and the second sub-scale information includes the scale information filled in by people without psychological disorders; Calculating the proportion of the selected first option in all the first sub-scale information to obtain a first calculation result; Calculating the proportion of the selected first option in all the second sub-scale information to obtain a second calculation result; Calculating based on the selected first option and all the first scale information to obtain a third calculation result; Calculating based on the first calculation result, the second calculation result, and the third calculation result to obtain the importance degree of the first option; Among them, the calculation process of the importance degree of the first option is specifically: ； In the above formula, represents the proportion of the selected first option Xi in all the information of the first sub-scale; represents the proportion of the selected first option Xi in all the information of the second sub-scale; N represents the number of all the first scales, represents the number of the first scales in which the first option is selected. By calculating through the above formula, the importance degree of the first option can be quantified; Simplifying the measurement scale according to the first information and calculating the importance degree of each measurement question in the simplified measurement scale to obtain second information; Calculating based on the second information and the first information to obtain scoring information; Generating a psychological disorder label according to the scoring information.

2. The psychological disorder prediction method according to claim 1, wherein Predicting the current psychological disorder of the person to be evaluated includes: Calculating based on the prediction result and the actual result of the trained first psychological disorder prediction model to obtain a matching degree value; Adjusting the fitness function of the BP neural network according to the matching degree value; Calculating the fitness function of each particle and determining the individual optimal position and the particle swarm optimal position in the first iteration; Iteratively updating the individual optimal position and the particle swarm optimal position until the optimal particle position is found; Obtaining the initial connection weights and thresholds according to the optimal particle position; Learning from the training set according to the initial connection weights and the thresholds to establish an optimal first psychological disorder prediction model.

3. The psychological disorder prediction method according to claim 1, characterized in that After identifying the current psychological disorder of the person to be evaluated, it further includes: Obtaining the sampling interval period; Repeatedly sample the information of the emotional regulation strategy tendency scale of the person to be evaluated according to the sampling interval period to obtain sample data; Divide the sample data according to the sampling interval period to obtain the divided sample data; Construct a training set based on the psychological disorder label and at least one of the divided sample data; Train the second psychological disorder prediction model using the training set to obtain the trained second psychological disorder prediction model, which is used to predict the psychological disorder after the current moment.

4. A psychological disorder prediction device, characterized in that, Including: The first acquisition module is used to acquire an evaluation scale, where the evaluation scale includes at least one evaluation question, and each evaluation question corresponds to at least one evaluation option. The evaluation scale includes the Beck Depression Inventory, the Patient Health Questionnaire, the Self-Rating Anxiety Scale, the Athens Insomnia Scale, the Hamilton Depression Rating Scale, and the Hamilton Anxiety Rating Scale; The first processing module is used to collect the information of the emotional regulation strategy tendency scale within the sampling time to obtain sampling information, where the sampling information includes the frequency sequence of the person to be evaluated adopting each emotional regulation strategy; The second processing module is used to establish a first psychological disorder prediction model based on the sampling information and at least one of the psychological disorder labels. The first psychological disorder prediction model is a BP neural network model; The third processing module is used to predict the current psychological disorder of the person to be evaluated according to the first psychological disorder prediction model; Among them, the first acquisition module further includes: The first acquisition unit is used to acquire an evaluation scale, where the evaluation scale includes at least one evaluation question, and each evaluation question corresponds to at least one evaluation option; The first calculation unit is used to calculate the importance degree of each option corresponding to each evaluation question in the evaluation scale to obtain the first information; The first processing unit is used to simplify the evaluation scale according to the first information to obtain the simplified evaluation scale; The second calculation unit is used to calculate the importance degree of each evaluation question in the simplified evaluation scale to obtain the second information; The second processing unit is used to calculate according to the second information and the first information to obtain the scoring information; The third processing unit generates a psychological disorder label according to the scoring information; Among them, the first calculation unit includes: The second acquisition unit is used to acquire at least two pieces of first scale information, where the first scale information includes at least one piece of first sub-scale information and at least one piece of second sub-scale information. The first sub-scale information includes the scale information filled in by the person with a psychological disorder, and the second sub-scale information includes the scale information filled in by the person without a psychological disorder; The third calculation unit is used to calculate the proportion of the selected first option in all the first sub-scale information to obtain the first calculation result; The fourth calculation unit is used to calculate the proportion of the selected first option in all the second sub-scale information to obtain the second calculation result; The fifth calculation unit is used to calculate according to the selected first option and all the first scale information to obtain the third calculation result; A sixth computing unit, configured to perform calculations based on the first calculation result, the second calculation result, and the third calculation result to obtain the importance degree of the first option; The specific process of calculating the importance degree of the first option is as follows: ； In the above formula, represents the proportion of the selected first option Xi in all the first sub-scale information; represents the proportion of the selected first option Xi in all the second sub-scale information; N represents the number of all the first scales, represents the number of the first scales in which the first option is selected. By calculating with the above formula, the importance degree of the first option can be quantified.

5. The psychological disorder prediction device according to claim 4, wherein The third processing module includes: A fourth processing unit, configured to perform calculations based on the prediction result and the actual result of the trained first psychological disorder prediction model to obtain a matching degree value; A fifth processing unit, configured to adjust the fitness function of the BP neural network according to the matching degree value; A sixth processing unit, configured to calculate the fitness function of each particle and determine the individual optimal position and the particle swarm optimal position of the first iteration; An iteration unit, configured to iteratively update the individual optimal position and the particle swarm optimal position until the optimal particle position is found; A seventh processing unit, configured to obtain an initial connection weight and a threshold according to the optimal particle position; An eighth processing unit, configured to learn from the training set according to the initial connection weight and the threshold to establish an optimal first psychological disorder prediction model.

6. The psychological disorder prediction device according to claim 4, wherein After the third processing module, it further includes: A second acquisition module, configured to acquire a sampling interval period; A fourth processing module, configured to repeatedly sample the emotional regulation strategy tendency scale information of the person to be evaluated according to the sampling interval period to obtain sample data; A fifth processing module, configured to divide the sample data according to the sampling interval period to obtain the divided sample data; A sixth processing module, configured to construct a training set according to the psychological disorder label and at least one of the divided sample data; A seventh processing module, configured to train a second psychological disorder prediction model using the training set to obtain a trained second psychological disorder prediction model, where the second psychological disorder prediction model is used to predict psychological disorders after the current moment.

7. A psychological disorder prediction device, characterized in that, It includes: A memory, configured to store a computer program; A processor, configured to implement the steps of the psychological disorder prediction method according to any one of claims 1 to 3 when executing the computer program.

8. A readable storage medium, characterized in that: A computer program is stored on the readable storage medium, and when the computer program is executed by the processor, it implements the steps of the psychological disorder prediction method according to any one of claims 1 to 3.

Images