Mental health guidance data processing method and system based on AI algorithm

Abstract

The invention discloses a psychological health guidance data processing method and system based on an AI algorithm. The method comprises the steps that user voice data and user parameters of a user to be guided are acquired; determining a corresponding guide strategy prediction model according to the user parameters; based on a preset voice emotion analysis algorithm, determining corresponding user emotion features and voice texts according to the user voice data; and inputting the user emotion features and the voice text into the guiding strategy prediction model to obtain a mental health guiding strategy corresponding to the to-be-guided user. Therefore, the method can fully combine the emotion features of the user with the guide strategy prediction model to accurately predict the guide strategy of the user, so as to achieve more intelligent and automatic psychological guidance, and improve the psychological health guidance effect.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and system for processing mental health guidance data based on an AI algorithm. Background Art

[0002] With people's increasing attention to mental health, technologies related to mental health guidance are rapidly developing. In particular, with the rise of artificial intelligence algorithms in recent years, more and more companies and institutions have begun to introduce AI algorithms into the field of mental health guidance, using them to implement intelligent and automated mental health counseling services. However, most existing technologies of this type only use language processing algorithms to guide users based on preset corpus or rules. They do not fully integrate users' diverse emotional characteristics and more intelligent multi-model architectures to achieve mental health guidance. Clearly, their mental health guidance effectiveness is poor, and they lack both intelligence and automation. Clearly, existing technologies have flaws that need to be addressed urgently. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a psychological health guidance data processing method and system based on AI algorithm, which can fully combine the user's emotional characteristics and guidance strategy prediction model to accurately predict the user's guidance strategy, so as to achieve more intelligent and automatic psychological guidance and improve the psychological health guidance effect.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a method for processing mental health guidance data based on an AI algorithm, the method comprising: Acquire user voice data and user parameters of the user to be guided; Determining a corresponding guidance strategy prediction model according to the user parameters; Based on a preset voice emotion analysis algorithm, determine corresponding user emotion characteristics and voice text according to the user voice data; The user's emotional characteristics and speech text are input into the guidance strategy prediction model to obtain a mental health guidance strategy corresponding to the user to be guided.

[0005] As an optional embodiment, in the first aspect of the present invention, the user parameters include at least one of user gender, user age, user mental consultation records, user medication records and user historical heart rate.

[0006] As an optional implementation manner, in the first aspect of the present invention, determining the corresponding guidance strategy prediction model according to the user parameters includes: For each candidate guidance strategy prediction model, obtain the historical training records and historical application records corresponding to the candidate guidance strategy prediction model; Calculating an average of similarities between the user parameter annotation in each training data in the historical training record and the user parameter to obtain a first similarity parameter; Calculating an average of similarities between the user parameter information of each application object in the historical application record and the user parameter to obtain a second similarity parameter; Calculating a weighted average of the first similarity parameter and the second similarity parameter to obtain an adaptation parameter corresponding to the candidate guidance strategy prediction model; The candidate guidance strategy prediction model with the highest adaptation parameter is determined as the guidance strategy prediction model corresponding to the user to be guided; the guidance strategy prediction model is obtained by training a training data set including multiple training user corpus texts and corresponding user emotion feature annotations and guidance strategy annotations.

[0007] As an optional embodiment, in the first aspect of the present invention, the user emotional characteristics include at least one of the degree of low mood, degree of extreme mood, degree of emotional fluctuation, degree of high mood, doubtful emotional characteristics and suspicious emotional characteristics.

[0008] As an optional embodiment, in the first aspect of the present invention, the preset voice emotion analysis algorithm determines the corresponding user emotion characteristics and voice text according to the user voice data, including: Inputting the user voice data into a speech recognition model to obtain corresponding voice text; Inputting the user voice data into an emotion feature pre-recognition model to obtain at least one possible emotion feature type corresponding to the user voice data; the possible emotion feature type is a degree of depression, a degree of extreme emotion, a degree of emotional fluctuation, a degree of high emotion, a doubtful emotion feature, or a suspicious emotion feature; For each of the possible emotion feature types, inputting the user voice data and the voice text into a feature prediction model corresponding to the possible emotion feature type to obtain feature parameters and prediction probabilities corresponding to the possible emotion feature; The characteristic parameters corresponding to all the possible emotion feature types whose predicted probabilities are greater than a preset probability threshold are determined as corresponding user emotion features.

[0009] As an optional embodiment, in the first aspect of the present invention, the emotion feature pre-recognition model is a CNN network, which is trained by a training data set including multiple training speech data and corresponding emotion feature type annotations; the feature prediction model is a CNN network, which is trained by a training data set including multiple corresponding possible emotion feature types of training speech data and corresponding text annotations and emotion degree parameter annotations.

[0010] As an optional embodiment, in the first aspect of the present invention, inputting the user's emotional characteristics and speech text into the guidance strategy prediction model to obtain a mental health guidance strategy corresponding to the user to be guided includes: For each emotion feature type in the user's emotion features, a contradiction parameter is calculated between the feature parameter corresponding to the emotion feature type and the feature parameter of any other emotion feature type; the contradiction parameter is determined by a preset contradiction numerical rule; the contradiction numerical rule is used to define the contradiction degree parameter corresponding to different feature parameters of different emotion feature types; the emotion feature type is a degree of low mood, a degree of extreme mood, a degree of emotional fluctuation, a degree of high mood, a doubtful emotion feature, or a suspicious emotion feature; Calculating an average value of all the contradiction parameters corresponding to the emotional feature type to obtain the degree of contradiction corresponding to the emotional feature type; Determining the emotion feature type whose contradiction degree is lower than a preset degree threshold as a target emotion feature type; For each target emotion feature type, the feature parameter corresponding to the target emotion feature type and the speech text are input as prediction data into the guidance strategy prediction model to obtain a guidance strategy corresponding to the target emotion feature type; the guidance strategy includes a plurality of guidance steps and guidance terms, guidance tones, and guidance prohibitions corresponding to each guidance step; Calculate the intersection of the guidance strategies corresponding to all the target emotional feature types to obtain the psychological health guidance strategy corresponding to the user to be guided; the psychological health guidance strategy includes multiple psychological guidance steps and the guidance terms, guidance tone and guidance prohibitions corresponding to each psychological guidance step.

[0011] As an optional embodiment, in the first aspect of the present invention, the method further comprises: According to the guidance words, guidance tone and guidance prohibited items corresponding to each psychological guidance step in the mental health guidance strategy, based on the preset first prompt word rule, a prompt word corresponding to each psychological guidance step is generated; In response to a psychological consultation request of the user to be guided, determining a psychological guidance stage corresponding to the user to be guided; Inputting the prompt words corresponding to the psychological guidance steps in the psychological guidance stage into the trained LLM model to obtain output question words and transition words; sending the question to the user to be guided for display, and sending the transitional words to the user to be guided for display upon receiving the answer from the user to be guided; Upon receiving answer data of the user to be guided to the question corresponding to any of the psychological guidance steps, combining the answer data and the prompt word corresponding to the psychological guidance step based on a preset second prompt word rule to obtain an answer prompt word; Inputting the answer prompt words into the LLM model to obtain the output answer words; The answering words are sent to the user to be guided after the transitional words are sent to the user to be guided.

[0012] A second aspect of an embodiment of the present invention discloses a mental health guidance data processing system based on an AI algorithm, the system comprising: An acquisition module, used to acquire user voice data and user parameters of the user to be guided; A determination module, configured to determine a corresponding guidance strategy prediction model based on the user parameters; An analysis module, configured to determine corresponding user emotion features and speech text according to the user speech data based on a preset speech emotion analysis algorithm; The guidance module is used to input the user's emotional characteristics and voice text into the guidance strategy prediction model to obtain the mental health guidance strategy corresponding to the user to be guided.

[0013] As an optional embodiment, in the second aspect of the present invention, the user parameters include at least one of user gender, user age, user mental consultation records, user medication records and user historical heart rate.

[0014] As an optional implementation, in the second aspect of the present invention, the specific manner in which the determination module determines the corresponding guidance strategy prediction model according to the user parameters includes: For each candidate guidance strategy prediction model, obtain the historical training records and historical application records corresponding to the candidate guidance strategy prediction model; Calculating an average of similarities between the user parameter annotation in each training data in the historical training record and the user parameter to obtain a first similarity parameter; Calculating an average of similarities between the user parameter information of each application object in the historical application record and the user parameter to obtain a second similarity parameter; Calculating a weighted average of the first similarity parameter and the second similarity parameter to obtain an adaptation parameter corresponding to the candidate guidance strategy prediction model; The candidate guidance strategy prediction model with the highest adaptation parameter is determined as the guidance strategy prediction model corresponding to the user to be guided; the guidance strategy prediction model is obtained by training a training data set including multiple training user corpus texts and corresponding user emotion feature annotations and guidance strategy annotations.

[0015] As an optional embodiment, in the second aspect of the present invention, the user emotional characteristics include at least one of the degree of low mood, degree of extreme mood, degree of emotional fluctuation, degree of high mood, doubtful emotional characteristics and suspicious emotional characteristics.

[0016] As an optional embodiment, in the second aspect of the present invention, the analysis module determines the corresponding user emotional features and speech text according to the user voice data based on a preset speech emotion analysis algorithm, including: Inputting the user voice data into a speech recognition model to obtain corresponding voice text; Inputting the user voice data into an emotion feature pre-recognition model to obtain at least one possible emotion feature type corresponding to the user voice data; the possible emotion feature type is a degree of depression, a degree of extreme emotion, a degree of emotional fluctuation, a degree of high emotion, a doubtful emotion feature, or a suspicious emotion feature; For each of the possible emotion feature types, inputting the user voice data and the voice text into a feature prediction model corresponding to the possible emotion feature type to obtain feature parameters and prediction probabilities corresponding to the possible emotion feature; The characteristic parameters corresponding to all the possible emotion feature types whose predicted probabilities are greater than a preset probability threshold are determined as corresponding user emotion features.

[0017] As an optional embodiment, in the second aspect of the present invention, the emotion feature pre-recognition model is a CNN network, which is trained by a training data set including multiple training speech data and corresponding emotion feature type annotations; the feature prediction model is a CNN network, which is trained by a training data set including multiple corresponding possible emotion feature types of training speech data and corresponding text annotations and emotion degree parameter annotations.

[0018] As an optional embodiment, in the second aspect of the present invention, the guidance module inputs the user's emotional characteristics and voice text into the guidance strategy prediction model to obtain a specific manner of the mental health guidance strategy corresponding to the user to be guided, including: For each emotion feature type in the user's emotion features, a contradiction parameter is calculated between the feature parameter corresponding to the emotion feature type and the feature parameter of any other emotion feature type; the contradiction parameter is determined by a preset contradiction numerical rule; the contradiction numerical rule is used to define the contradiction degree parameter corresponding to different feature parameters of different emotion feature types; the emotion feature type is a degree of low mood, a degree of extreme mood, a degree of emotional fluctuation, a degree of high mood, a doubtful emotion feature, or a suspicious emotion feature; Calculating an average value of all the contradiction parameters corresponding to the emotional feature type to obtain the degree of contradiction corresponding to the emotional feature type; Determining the emotion feature type whose contradiction degree is lower than a preset degree threshold as a target emotion feature type; For each target emotion feature type, the feature parameter corresponding to the target emotion feature type and the speech text are input as prediction data into the guidance strategy prediction model to obtain a guidance strategy corresponding to the target emotion feature type; the guidance strategy includes a plurality of guidance steps and guidance terms, guidance tones, and guidance prohibitions corresponding to each guidance step; Calculate the intersection of the guidance strategies corresponding to all the target emotional feature types to obtain the psychological health guidance strategy corresponding to the user to be guided; the psychological health guidance strategy includes multiple psychological guidance steps and the guidance terms, guidance tone and guidance prohibitions corresponding to each psychological guidance step.

[0019] As an optional embodiment, in the second aspect of the present invention, the system is further configured to perform the following steps: According to the guidance words, guidance tone and guidance prohibited items corresponding to each psychological guidance step in the mental health guidance strategy, based on the preset first prompt word rule, a prompt word corresponding to each psychological guidance step is generated; In response to a psychological consultation request of the user to be guided, determining a psychological guidance stage corresponding to the user to be guided; Inputting the prompt words corresponding to the psychological guidance steps in the psychological guidance stage into the trained LLM model to obtain output question words and transition words; sending the question to the user to be guided for display, and sending the transitional words to the user to be guided for display upon receiving the answer from the user to be guided; Upon receiving answer data of the user to be guided to the question corresponding to any of the psychological guidance steps, combining the answer data and the prompt word corresponding to the psychological guidance step based on a preset second prompt word rule to obtain an answer prompt word; Inputting the answer prompt words into the LLM model to obtain the output answer words; The answering words are sent to the user to be guided after the transitional words are sent to the user to be guided.

[0020] The third aspect of the present invention discloses another mental health guidance data processing system based on an AI algorithm, the system comprising: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute part or all of the steps in the mental health guidance data processing method based on AI algorithm disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the AI ​​algorithm-based mental health guidance data processing method disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: The present invention can determine the corresponding mental health guidance model according to user parameters, and then determine the user's emotional characteristics and voice text according to the user's voice data based on the voice emotion analysis algorithm, so as to input them into the mental health guidance model to obtain a more adaptive and accurate mental health guidance strategy, thereby being able to fully combine the user's emotional characteristics and the guidance strategy prediction model to accurately predict the user's guidance strategy, so as to achieve more intelligent and automatic psychological guidance and improve the mental health guidance effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 This is a flow chart of a method for processing mental health guidance data based on an AI algorithm disclosed in an embodiment of the present invention.

[0025] Figure 2 This is a structural diagram of a mental health guidance data processing system based on an AI algorithm disclosed in an embodiment of the present invention.

[0026] Figure 3This is a structural diagram of another AI algorithm-based mental health guidance data processing system disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0028] The terms "first," "second," and so on, in the description and claims of the present invention and the accompanying drawings are used to distinguish between different objects, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or device comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or device.

[0029] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0030] This invention discloses a mental health guidance data processing method and system based on an AI algorithm. This method can determine a corresponding mental health guidance model based on user parameters. It then uses a speech emotion analysis algorithm to determine user emotional characteristics and speech text from user speech data. These are then input into the mental health guidance model to generate a more adaptive and accurate mental health guidance strategy. This method can then fully combine user emotional characteristics with a guidance strategy prediction model to accurately predict the user's guidance strategy, achieving more intelligent and automated psychological guidance and improving the effectiveness of mental health guidance. These are described in detail below.

[0031] Example 1 See also Figure 1 , Figure 1 This is a flow chart of a method for processing mental health guidance data based on an AI algorithm disclosed in an embodiment of the present invention. Figure 1The described AI algorithm-based mental health guidance data processing method can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the mental health guidance data processing method based on the AI ​​algorithm may include the following operations: 101. Acquire user voice data and user parameters of the user to be guided.

[0032] 102. Determine a corresponding guidance strategy prediction model based on user parameters. 103. Based on the preset voice emotion analysis algorithm, determine the corresponding user emotion characteristics and voice text according to the user voice data. 104. Input the user's emotional features and voice text into the guidance strategy prediction model to obtain a corresponding mental health guidance strategy for the user to be guided.

[0033] It can be seen that the above-mentioned embodiment of the invention can determine the corresponding mental health guidance model according to user parameters, and then determine the user's emotional characteristics and voice text according to the user's voice data based on the voice emotion analysis algorithm, so as to input them into the mental health guidance model to obtain a more adaptive and accurate mental health guidance strategy, thereby being able to fully combine the user's emotional characteristics and the guidance strategy prediction model to accurately predict the user's guidance strategy, so as to achieve more intelligent and automatic psychological guidance and improve the mental health guidance effect.

[0034] As an optional embodiment, in the above steps, the user parameters include at least one of user gender, user age, user mental health consultation records, user medication records and user historical heart rate.

[0035] It can be seen that through the above optional embodiments, the content of user parameters is limited to comprehensively characterize the characteristics related to the user's mental health, so as to facilitate the subsequent accurate prediction of appropriate guidance strategies, and assist in fully combining the user's emotional characteristics and the guidance strategy prediction model to accurately predict the user's guidance strategy, so as to achieve more intelligent and automatic psychological guidance and improve the mental health guidance effect.

[0036] As an optional embodiment, in the above step, determining the corresponding guidance strategy prediction model according to the user parameters includes: For each candidate guidance strategy prediction model, obtain the historical training records and historical application records corresponding to the candidate guidance strategy prediction model; Calculating an average of similarities between the user parameter annotations and the user parameters in each training data in the historical training record to obtain a first similarity parameter; Calculating an average of the similarities between the user parameter information of each application object and the user parameters in the historical application records to obtain a second similarity parameter; Calculating a weighted average of the first similarity parameter and the second similarity parameter to obtain an adaptation parameter corresponding to the candidate guidance strategy prediction model; The candidate guidance strategy prediction model with the highest adaptation parameter is determined as the guidance strategy prediction model corresponding to the user to be guided; the guidance strategy prediction model is trained by a training data set including multiple training user corpus texts and corresponding user emotion feature annotations and guidance strategy annotations.

[0037] It can be seen that through the above optional embodiments, the adaptability of each candidate model can be measured based on the similarity calculation between the user information in the historical training records and historical application records of the candidate model and the current user parameters, so as to screen out the optimal prediction model, and subsequently accurately predict the appropriate guidance strategy, and assist in fully combining the user's emotional characteristics and the guidance strategy prediction model to accurately predict the user's guidance strategy, so as to achieve more intelligent and automatic psychological guidance and improve the effect of mental health guidance.

[0038] As an optional embodiment, in the above steps, the user's emotional characteristics include at least one of a low mood, an extreme mood, an emotional fluctuation, a high mood, a doubtful emotional characteristic, and a suspicious emotional characteristic.

[0039] It can be seen that through the above optional embodiments, the content of the user's emotional characteristics is limited to comprehensively characterize the emotional characteristics related to the user's mental health, so as to facilitate the subsequent accurate prediction of appropriate guidance strategies, and assist in fully combining the user's emotional characteristics and the guidance strategy prediction model to accurately predict the user's guidance strategy, so as to achieve more intelligent and automatic psychological guidance and improve the mental health guidance effect.

[0040] As an optional embodiment, in the above steps, based on a preset voice emotion analysis algorithm, determining corresponding user emotion features and voice text according to user voice data includes: Input the user's voice data into the speech recognition model to obtain the corresponding voice text; Inputting the user voice data into an emotion feature pre-recognition model to obtain at least one possible emotion feature type corresponding to the user voice data; optionally, the possible emotion feature type is a degree of depression, a degree of extreme emotion, a degree of emotional fluctuation, a degree of high emotion, a doubtful emotion feature, or a suspicious emotion feature; For each possible emotion feature type, input the user voice data and voice text into the feature prediction model corresponding to the possible emotion feature type to obtain the feature parameters and prediction probability corresponding to the possible emotion feature; The feature parameters corresponding to all possible emotion feature types whose predicted probabilities are greater than a preset probability threshold are determined as corresponding user emotion features.

[0041] It can be seen that through the above optional embodiments, it is possible to first identify possible emotional features based on the emotional feature pre-recognition model and then further combine the feature prediction model to predict accurate emotional features, so as to facilitate the subsequent accurate prediction of appropriate guidance strategies, and assist in fully combining user emotional features and guidance strategy prediction models to accurately predict user guidance strategies, so as to achieve more intelligent and automatic psychological guidance and improve the effect of mental health guidance.

[0042] As an optional embodiment, in the above steps, the emotion feature pre-recognition model is a CNN network, which is trained by a training data set including multiple training speech data and corresponding emotion feature type annotations; the feature prediction model is a CNN network, which is trained by a training data set including multiple corresponding possible emotion feature types of training speech data and corresponding text annotations and emotion degree parameter annotations.

[0043] It can be seen that through the above optional embodiments, the training details and network details of the emotion feature pre-recognition model and the feature prediction model are limited to accurately predict accurate emotion features, facilitate the subsequent accurate prediction of appropriate guidance strategies, and assist in fully combining user emotion features and guidance strategy prediction models to accurately predict user guidance strategies, so as to achieve more intelligent and automatic psychological guidance and improve the effect of mental health guidance.

[0044] As an optional embodiment, in the above steps, the user's emotional characteristics and speech text are input into the guidance strategy prediction model to obtain the mental health guidance strategy corresponding to the user to be guided, including: For each emotion feature type in the user's emotion features, calculate a contradiction parameter between a feature parameter corresponding to the emotion feature type and a feature parameter of any other emotion feature type; optionally, the contradiction parameter is determined by a preset contradiction numerical rule; the contradiction numerical rule is used to define a contradiction degree parameter corresponding to different feature parameters of different emotion feature types; the emotion feature type is a degree of low mood, a degree of extreme mood, a degree of emotional fluctuation, a degree of high mood, a doubtful emotion feature, or a suspicious emotion feature; Calculate the average value of all contradiction parameters corresponding to the emotional feature type to obtain the degree of contradiction corresponding to the emotional feature type; determining the emotional characteristic type whose contradiction degree is lower than a preset degree threshold as the target emotional characteristic type; For each target emotion feature type, the feature parameters and speech text corresponding to the target emotion feature type are input as prediction data into a guidance strategy prediction model to obtain a guidance strategy corresponding to the target emotion feature type; optionally, the guidance strategy includes multiple guidance steps and guidance terms, guidance tones, and guidance prohibitions corresponding to each guidance step; The intersection of the guidance strategies corresponding to all target emotional feature types is calculated to obtain the psychological health guidance strategy corresponding to the user to be guided; the psychological health guidance strategy includes multiple psychological guidance steps and the guidance terms, guidance tone and guidance prohibitions corresponding to each psychological guidance step.

[0045] It can be seen that through the above optional embodiments, it is possible to screen out target emotional features with higher probability based on the contradictory parameters between the characteristic parameters of the emotional feature types, and then determine a more accurate user mental health guidance strategy based on the strategy prediction and intersection calculation of each target emotional feature, so as to fully combine the user emotional features and the guidance strategy prediction model to accurately predict the user's guidance strategy, so as to achieve more intelligent and automatic psychological guidance and improve the mental health guidance effect.

[0046] As an optional embodiment, in the above steps, the method further includes: According to the guidance words, guidance tone and guidance prohibitions corresponding to each psychological guidance step in the mental health guidance strategy, based on the preset first prompt word rules, a prompt word corresponding to each psychological guidance step is generated; In response to a psychological consultation request from a user to be guided, determining a corresponding psychological guidance stage for the user to be guided; Input the prompt words corresponding to the psychological guidance steps in the psychological guidance stage into the trained LLM model to obtain the output question words and transition words; Send the question to the user to be guided for display, and when receiving the answer from the user to be guided, send the transition words to the user to be guided for display; When receiving the answer data of the user to be guided to the question corresponding to any psychological guidance step, the answer data and the prompt word corresponding to the psychological guidance step are combined based on the preset second prompt word rule to obtain the answer prompt word; Input the answer prompt words into the LLM model to obtain the output answer words; The answering words are sent to the user to be guided after the connecting words are sent to the user to be guided.

[0047] It can be seen that through the above optional embodiments, it is possible to provide consulting users with intelligent consulting services at the corresponding stage based on the prompt word rules based on the mental health guidance strategy and the trained LLM model, and to fully combine the user's emotional characteristics and the guidance strategy prediction model to accurately predict the user's guidance strategy, so as to achieve more intelligent and automatic psychological guidance and improve the mental health guidance effect.

[0048] Example 2 See also Figure 2 , Figure 2 This is a schematic diagram of the structure of a mental health guidance data processing system based on an AI algorithm disclosed in an embodiment of the present invention. Figure 2 The described AI algorithm-based mental health guidance data processing system can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the mental health guidance data processing system based on AI algorithm may include: The acquisition module 201 is used to acquire user voice data and user parameters of the user to be guided.

[0049] The determination module 202 is configured to determine a corresponding guidance strategy prediction model according to user parameters. The analysis module 203 is configured to determine corresponding user emotion features and speech text according to the user speech data based on a preset speech emotion analysis algorithm. The guidance module 204 is used to input the user's emotional characteristics and voice text into the guidance strategy prediction model to obtain a mental health guidance strategy corresponding to the user to be guided.

[0050] It can be seen that the above-mentioned embodiment of the invention can determine the corresponding mental health guidance model according to user parameters, and then determine the user's emotional characteristics and voice text according to the user's voice data based on the voice emotion analysis algorithm, so as to input them into the mental health guidance model to obtain a more adaptive and accurate mental health guidance strategy, thereby being able to fully combine the user's emotional characteristics and the guidance strategy prediction model to accurately predict the user's guidance strategy, so as to achieve more intelligent and automatic psychological guidance and improve the mental health guidance effect.

[0051] As an optional embodiment, the user parameters include at least one of user gender, user age, user mental consultation records, user medication records, and user historical heart rate.

[0052] It can be seen that through the above optional embodiments, the content of user parameters is limited to comprehensively characterize the characteristics related to the user's mental health, so as to facilitate the subsequent accurate prediction of appropriate guidance strategies, and assist in fully combining the user's emotional characteristics and the guidance strategy prediction model to accurately predict the user's guidance strategy, so as to achieve more intelligent and automatic psychological guidance and improve the mental health guidance effect.

[0053] As an optional embodiment, the specific manner in which the determination module determines the corresponding guidance strategy prediction model according to the user parameters includes: For each candidate guidance strategy prediction model, obtain the historical training records and historical application records corresponding to the candidate guidance strategy prediction model; Calculating an average of similarities between the user parameter annotations and the user parameters in each training data in the historical training record to obtain a first similarity parameter; Calculating an average of the similarities between the user parameter information of each application object and the user parameters in the historical application records to obtain a second similarity parameter; Calculating a weighted average of the first similarity parameter and the second similarity parameter to obtain an adaptation parameter corresponding to the candidate guidance strategy prediction model; The candidate guidance strategy prediction model with the highest adaptation parameter is determined as the guidance strategy prediction model corresponding to the user to be guided; the guidance strategy prediction model is trained by a training data set including multiple training user corpus texts and corresponding user emotion feature annotations and guidance strategy annotations.

[0054] It can be seen that through the above optional embodiments, the adaptability of each candidate model can be measured based on the similarity calculation between the user information in the historical training records and historical application records of the candidate model and the current user parameters, so as to screen out the optimal prediction model, and subsequently accurately predict the appropriate guidance strategy, and assist in fully combining the user's emotional characteristics and the guidance strategy prediction model to accurately predict the user's guidance strategy, so as to achieve more intelligent and automatic psychological guidance and improve the effect of mental health guidance.

[0055] As an optional embodiment, the user's emotional characteristics include at least one of a low mood, an extreme mood, an emotional fluctuation, a high mood, a doubtful emotional characteristic, and a suspicious emotional characteristic.

[0056] It can be seen that through the above optional embodiments, the content of the user's emotional characteristics is limited to comprehensively characterize the emotional characteristics related to the user's mental health, so as to facilitate the subsequent accurate prediction of appropriate guidance strategies, and assist in fully combining the user's emotional characteristics and the guidance strategy prediction model to accurately predict the user's guidance strategy, so as to achieve more intelligent and automatic psychological guidance and improve the mental health guidance effect.

[0057] As an optional embodiment, the analysis module determines the corresponding user emotion characteristics and speech text according to the user voice data based on a preset speech emotion analysis algorithm, including: Input the user's voice data into the speech recognition model to obtain the corresponding voice text; Inputting the user voice data into an emotion feature pre-recognition model to obtain at least one possible emotion feature type corresponding to the user voice data; optionally, the possible emotion feature type is a degree of depression, a degree of extreme emotion, a degree of emotional fluctuation, a degree of high emotion, a doubtful emotion feature, or a suspicious emotion feature; For each possible emotion feature type, input the user voice data and voice text into the feature prediction model corresponding to the possible emotion feature type to obtain the feature parameters and prediction probability corresponding to the possible emotion feature; The feature parameters corresponding to all possible emotion feature types whose predicted probabilities are greater than a preset probability threshold are determined as corresponding user emotion features.

[0058] It can be seen that through the above optional embodiments, it is possible to first identify possible emotional features based on the emotional feature pre-recognition model and then further combine the feature prediction model to predict accurate emotional features, so as to facilitate the subsequent accurate prediction of appropriate guidance strategies, and assist in fully combining user emotional features and guidance strategy prediction models to accurately predict user guidance strategies, so as to achieve more intelligent and automatic psychological guidance and improve the effect of mental health guidance.

[0059] As an optional embodiment, the emotion feature pre-recognition model is a CNN network, which is trained by a training data set including multiple training speech data and corresponding emotion feature type annotations; the feature prediction model is a CNN network, which is trained by a training data set including multiple corresponding possible emotion feature types of training speech data and corresponding text annotations and emotion degree parameter annotations.

[0060] It can be seen that through the above optional embodiments, the training details and network details of the emotion feature pre-recognition model and the feature prediction model are limited to accurately predict accurate emotion features, facilitate the subsequent accurate prediction of appropriate guidance strategies, and assist in fully combining user emotion features and guidance strategy prediction models to accurately predict user guidance strategies, so as to achieve more intelligent and automatic psychological guidance and improve the effect of mental health guidance.

[0061] As an optional embodiment, the guidance module inputs the user's emotional characteristics and voice text into the guidance strategy prediction model to obtain a specific method of the mental health guidance strategy corresponding to the user to be guided, including: For each emotion feature type in the user's emotion features, calculate a contradiction parameter between a feature parameter corresponding to the emotion feature type and a feature parameter of any other emotion feature type; optionally, the contradiction parameter is determined by a preset contradiction numerical rule; the contradiction numerical rule is used to define a contradiction degree parameter corresponding to different feature parameters of different emotion feature types; the emotion feature type is a degree of low mood, a degree of extreme mood, a degree of emotional fluctuation, a degree of high mood, a doubtful emotion feature, or a suspicious emotion feature; Calculate the average value of all contradiction parameters corresponding to the emotional feature type to obtain the degree of contradiction corresponding to the emotional feature type; determining the emotional characteristic type whose contradiction degree is lower than a preset degree threshold as the target emotional characteristic type; For each target emotion feature type, the feature parameters and speech text corresponding to the target emotion feature type are input as prediction data into a guidance strategy prediction model to obtain a guidance strategy corresponding to the target emotion feature type; optionally, the guidance strategy includes multiple guidance steps and guidance terms, guidance tones, and guidance prohibitions corresponding to each guidance step; The intersection of the guidance strategies corresponding to all target emotional feature types is calculated to obtain the psychological health guidance strategy corresponding to the user to be guided; the psychological health guidance strategy includes multiple psychological guidance steps and the guidance terms, guidance tone and guidance prohibitions corresponding to each psychological guidance step.

[0062] It can be seen that through the above optional embodiments, it is possible to screen out target emotional features with higher probability based on the contradictory parameters between the characteristic parameters of the emotional feature types, and then determine a more accurate user mental health guidance strategy based on the strategy prediction and intersection calculation of each target emotional feature, so as to fully combine the user emotional features and the guidance strategy prediction model to accurately predict the user's guidance strategy, so as to achieve more intelligent and automatic psychological guidance and improve the mental health guidance effect.

[0063] As an optional embodiment, the system is further configured to perform the following steps: According to the guidance words, guidance tone and guidance prohibitions corresponding to each psychological guidance step in the mental health guidance strategy, based on the preset first prompt word rules, a prompt word corresponding to each psychological guidance step is generated; In response to a psychological consultation request from a user to be guided, determining a corresponding psychological guidance stage for the user to be guided; Input the prompt words corresponding to the psychological guidance steps in the psychological guidance stage into the trained LLM model to obtain the output question words and transition words; Send the question to the user to be guided for display, and when receiving the answer from the user to be guided, send the transition words to the user to be guided for display; When receiving the answer data of the user to be guided to the question corresponding to any psychological guidance step, the answer data and the prompt word corresponding to the psychological guidance step are combined based on the preset second prompt word rule to obtain the answer prompt word; Input the answer prompt words into the LLM model to obtain the output answer words; The answering words are sent to the user to be guided after the connecting words are sent to the user to be guided.

[0064] It can be seen that through the above optional embodiments, it is possible to provide consulting users with intelligent consulting services at the corresponding stage based on the prompt word rules based on the mental health guidance strategy and the trained LLM model, and to fully combine the user's emotional characteristics and the guidance strategy prediction model to accurately predict the user's guidance strategy, so as to achieve more intelligent and automatic psychological guidance and improve the mental health guidance effect.

[0065] Example 3 See also Figure 3 , Figure 3 This is another mental health guidance data processing system based on AI algorithm disclosed in an embodiment of the present invention. Figure 3 The described AI algorithm-based mental health guidance data processing system is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the mental health guidance data processing system based on AI algorithm may include: A memory 301 storing executable program code; a processor 302 coupled to the memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the mental health guidance data processing method based on the AI ​​algorithm described in the first embodiment.

[0066] Example 4 An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the mental health guidance data processing method based on an AI algorithm described in the first embodiment.

[0067] Example 5 An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the mental health guidance data processing method based on the AI ​​algorithm described in Example 1.

[0068] The foregoing description of specific embodiments of the present disclosure is intended to illustrate a method for performing a multi-tasking process. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0069] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0070] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0071] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0072] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0073] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0075] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0076] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0077] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0078] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0079] This specification may be described in the general context of computer-executable instructions, such as program modules, executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media, including storage devices.

[0080] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0081] Finally, it should be noted that the mental health guidance data processing method and system based on AI algorithm disclosed in the embodiment of the present invention is only a preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the aforementioned embodiments, ordinary technicians in this field should understand that it is still possible to modify the technical solutions recorded in the aforementioned embodiments, or to replace some of the technical features therein by equivalents; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A mental health guidance data processing method based on AI algorithm, characterized in that: The method comprises: Acquire user voice data and user parameters of the user to be guided; Determining a corresponding guidance strategy prediction model according to the user parameters; Based on a preset voice emotion analysis algorithm, determine corresponding user emotion characteristics and voice text according to the user voice data; The user's emotional characteristics and speech text are input into the guidance strategy prediction model to obtain a mental health guidance strategy corresponding to the user to be guided.

2. The method for processing mental health guidance data based on AI algorithm according to claim 1, characterized in that: The user parameters include at least one of user gender, user age, user mental consultation records, user medication records and user historical heart rate.

3. The method for processing mental health guidance data based on AI algorithm according to claim 1, characterized in that: Determining a corresponding guidance strategy prediction model according to the user parameters includes: For each candidate guidance strategy prediction model, obtain the historical training records and historical application records corresponding to the candidate guidance strategy prediction model; Calculating an average of similarities between the user parameter annotation in each training data in the historical training record and the user parameter to obtain a first similarity parameter; Calculating an average of similarities between the user parameter information of each application object in the historical application record and the user parameter to obtain a second similarity parameter; Calculating a weighted average of the first similarity parameter and the second similarity parameter to obtain an adaptation parameter corresponding to the candidate guidance strategy prediction model; The candidate guidance strategy prediction model with the highest adaptation parameter is determined as the guidance strategy prediction model corresponding to the user to be guided; the guidance strategy prediction model is obtained by training a training data set including multiple training user corpus texts and corresponding user emotion feature annotations and guidance strategy annotations.

4. The method for processing mental health guidance data based on AI algorithm according to claim 1, characterized in that: The user emotional characteristics include at least one of a low mood, an extreme mood, an emotional fluctuation, a high mood, a doubtful emotional characteristic, and a suspicious emotional characteristic.

5. The method for processing mental health guidance data based on AI algorithm according to claim 1, characterized in that: The preset voice emotion analysis algorithm determines the corresponding user emotion characteristics and voice text according to the user voice data, including: Inputting the user voice data into a speech recognition model to obtain corresponding voice text; Inputting the user voice data into an emotion feature pre-recognition model to obtain at least one possible emotion feature type corresponding to the user voice data; the possible emotion feature type is a degree of depression, a degree of extreme emotion, a degree of emotional fluctuation, a degree of high emotion, a doubtful emotion feature, or a suspicious emotion feature; For each of the possible emotion feature types, inputting the user voice data and the voice text into a feature prediction model corresponding to the possible emotion feature type to obtain feature parameters and prediction probabilities corresponding to the possible emotion feature; The characteristic parameters corresponding to all the possible emotion feature types whose predicted probabilities are greater than a preset probability threshold are determined as corresponding user emotion features.

6. The method for processing mental health guidance data based on AI algorithm according to claim 5, characterized in that: The emotion feature pre-recognition model is a CNN network, which is trained by a training data set including multiple training speech data and corresponding emotion feature type annotations; the feature prediction model is a CNN network, which is trained by a training data set including multiple corresponding possible emotion feature types of training speech data and corresponding text annotations and emotion degree parameter annotations.

7. The method for processing mental health guidance data based on AI algorithm according to claim 5, characterized in that: The step of inputting the user's emotional characteristics and speech text into the guidance strategy prediction model to obtain a mental health guidance strategy corresponding to the user to be guided includes: For each emotion feature type in the user's emotion features, a contradiction parameter is calculated between the feature parameter corresponding to the emotion feature type and the feature parameter of any other emotion feature type; the contradiction parameter is determined by a preset contradiction numerical rule; the contradiction numerical rule is used to define the contradiction degree parameter corresponding to different feature parameters of different emotion feature types; the emotion feature type is a degree of low mood, a degree of extreme mood, a degree of emotional fluctuation, a degree of high mood, a doubtful emotion feature, or a suspicious emotion feature; Calculating an average value of all the contradiction parameters corresponding to the emotional feature type to obtain the degree of contradiction corresponding to the emotional feature type; Determining the emotion feature type whose contradiction degree is lower than a preset degree threshold as a target emotion feature type; For each target emotion feature type, the feature parameter corresponding to the target emotion feature type and the speech text are input as prediction data into the guidance strategy prediction model to obtain a guidance strategy corresponding to the target emotion feature type; the guidance strategy includes a plurality of guidance steps and guidance terms, guidance tones, and guidance prohibitions corresponding to each guidance step; Calculate the intersection of the guidance strategies corresponding to all the target emotional feature types to obtain the psychological health guidance strategy corresponding to the user to be guided; the psychological health guidance strategy includes multiple psychological guidance steps and the guidance terms, guidance tone and guidance prohibitions corresponding to each psychological guidance step.

8. The method for processing mental health guidance data based on AI algorithm according to claim 7, characterized in that: The method further comprises: According to the guidance words, guidance tone and guidance prohibited items corresponding to each psychological guidance step in the mental health guidance strategy, based on the preset first prompt word rule, a prompt word corresponding to each psychological guidance step is generated; In response to a psychological consultation request of the user to be guided, determining a psychological guidance stage corresponding to the user to be guided; Inputting the prompt words corresponding to the psychological guidance steps in the psychological guidance stage into the trained LLM model to obtain output question words and transition words; sending the question to the user to be guided for display, and sending the transitional words to the user to be guided for display upon receiving the answer from the user to be guided; Upon receiving answer data of the user to be guided to the question corresponding to any of the psychological guidance steps, combining the answer data and the prompt word corresponding to the psychological guidance step based on a preset second prompt word rule to obtain an answer prompt word; Inputting the answer prompt words into the LLM model to obtain the output answer words; The answering words are sent to the user to be guided after the transitional words are sent to the user to be guided.

9. A mental health guidance data processing system based on AI algorithm, characterized in that: The system comprises: An acquisition module, used to acquire user voice data and user parameters of the user to be guided; A determination module, configured to determine a corresponding guidance strategy prediction model based on the user parameters; An analysis module, configured to determine corresponding user emotion features and speech text according to the user speech data based on a preset speech emotion analysis algorithm; The guidance module is used to input the user's emotional characteristics and voice text into the guidance strategy prediction model to obtain the mental health guidance strategy corresponding to the user to be guided.

10. A mental health guidance data processing system based on AI algorithm, characterized in that: The system comprises: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the mental health guidance data processing method based on the AI ​​algorithm as described in any one of claims 1-8.

Images