A mood intervention method and related apparatus

Abstract

This application discloses an emotion intervention method and related apparatus to reduce costs. The method is applied to the processing module of an emotion intervention device, which also includes an interaction module. The method includes: obtaining corresponding target emotional semantic information, target paralinguistic features, initial emotion, and target physiological neural state based on collected user voice data and user physiological indicator data; identifying the user's corresponding target emotion based on the initial emotion and target physiological neural state, and obtaining an emotion score for the target emotion based on the target emotional semantic information and target paralinguistic features; if the emotion score exceeds a preset score threshold, obtaining a first intervention method for the target emotion based on a preset relationship and at least one of the three: the type of target emotional semantic information, the target physiological neural state, and the initial emotion; and controlling the interaction module to execute the first intervention method.

Description

Technical Field

[0001] This application relates to the field of intelligent psychological counseling, and more particularly to an emotion intervention method and related apparatus. Background Technology

[0002] Cognitive behavioral therapy (CBT) is currently the most empirically proven and widely used method for changing cognition and behavior. Its core principle is that emotions are determined not by events themselves, but by how individuals perceive those events. CBT helps individuals correct skewed thinking, adjust negative emotions and inappropriate behaviors, and break the cycle of negative mental and physical health. It not only effectively relieves psychological stress and improves sleep quality but also provides a scientifically feasible solution for psychological and emotional intervention. Current intervention programs require professionals knowledgeable in CBT to provide intervention services to patients.

[0003] However, the existing solutions suffer from high labor costs due to the limited number of professionals knowledgeable in CBT compared to the large number of patients, which places a certain economic burden on patients. Summary of the Invention

[0004] To address the high labor costs in the background art, embodiments of this application provide an emotion intervention method and related apparatus to reduce costs.

[0005] The first aspect of this application provides an emotion intervention method applied to the processing module of an emotion intervention device, the device further including an interaction module, the method comprising: Based on the collected user voice data and user physiological index data, the corresponding target emotional semantic information, target paralinguistic features, initial emotion and target physiological neural state are obtained; The target emotion of the user is identified based on the initial emotion and the target physiological neural state, and the emotion score of the target emotion is obtained based on the target emotional semantic information and the target paralinguistic features. If the emotion score exceeds the preset score threshold, then based on the preset relationship between the first specified quantity and the emotion intervention method, the first intervention method for the target emotion is obtained according to at least one of the three factors: the type of target emotion semantic information, the target physiological and neural state, and the initial emotion. The first specified quantity includes at least one of the three factors: the type of emotion semantic information, the physiological and neural state, and the emotion. The control interaction module is used to execute the first intervention method.

[0006] Optionally, after obtaining the target emotion score based on the target sentiment semantic information and target paralinguistic features, the method further includes: Based on the preset relationship between the second specified quantity and the personalized intervention method, the second intervention method for the target emotion is determined according to the user's historical feedback information and / or the user's selection information. The second specified quantity includes historical feedback information and / or selection information. The control interaction module executes the first intervention method, including: The control interaction module is used to execute the first intervention method and the second intervention method.

[0007] Optionally, after the control interaction module performs the first intervention, the method further includes: The control and interaction module prompts the user to complete their homework and records and stores the homework content entered by the user and the homework completion time.

[0008] Optionally, after the control interaction module performs the first intervention, the method further includes: If the change in the target exceeds the preset threshold, the emotional intervention is considered complete. The change in the target is the change in the emotional score before and after the intervention. If the target change does not exceed the preset threshold and the current cumulative number of interventions does not exceed the preset number, then based on the preset relationship between the third specified quantity and the alternative intervention methods, a third intervention method for the target emotion is obtained according to at least one of the three factors: the type of target emotional semantic information, the target physiological neural state, and the initial emotion. After the interaction module is controlled to execute the third intervention method, the judgment is re-based on the target change and the current cumulative number of interventions. If the target change does not exceed the preset threshold, and the current cumulative number of interventions exceeds the preset number, the control interaction module will issue a suggestion for manual intervention.

[0009] Optionally, based on the collected user voice data and user physiological index data, corresponding target emotional semantic information, target paralinguistic features, initial emotion, and target physiological neural state are obtained, including: The collected user voice data is processed into text transcription to obtain the corresponding text data, and the text data is processed into emotional semantic extraction to obtain the corresponding target emotional semantic information. Feature extraction processing is performed on user voice data to obtain corresponding target sub-language features, which include fundamental frequency, energy, speech rate, and formants; Based on the pre-defined relationship between the third specified quantity and emotion, the corresponding initial emotion is obtained according to the target emotional semantic information and the target paralinguistic features. The third specified quantity includes emotional semantic information and paralinguistic features. The collected user physiological index data are processed to obtain the corresponding target physiological neural state.

[0010] Optionally, the collected user physiological index data can be processed to obtain the corresponding target physiological neural state, including: Real-time collection of user physiological data, including heart rate interval and target respiratory rate; The target standard deviation of all heartbeat intervals within the acquisition time period, the target root mean square of the difference between adjacent heartbeat intervals, and the target ratio of low-frequency power to high-frequency power are calculated based on the heartbeat intervals. Based on the preset relationship between the fourth specified quantity and the physiological and nervous state, the corresponding target physiological and nervous state is obtained according to the target respiratory rate, target standard deviation, target root mean square, and target ratio. The fourth specified quantity includes at least one of the following: respiratory rate, standard deviation of heartbeat intervals, root mean square of the difference between adjacent heartbeat intervals, and ratio of low-frequency power to high-frequency power. The physiological and nervous state represents the user's physiological stress level.

[0011] Optionally, an emotion score for the target emotion is obtained based on the target's emotional semantic information and target paralinguistic features, including: Based on the pre-defined relationship between emotional semantic information and the text score corresponding to the target emotion, the target text score is determined according to the target emotional semantic information; based on the pre-defined relationship between paralinguistic features and the acoustic score corresponding to the target emotion, the target acoustic score is determined according to the target paralinguistic features; and a weighted fusion calculation is performed based on the first pre-defined weight, the target text score, and the target acoustic score to obtain the speech score corresponding to the target emotion. The physiological score corresponding to the target emotion is obtained by weighted fusion calculation based on the second preset weight, target breathing rate, target standard deviation, target root mean square and target ratio. The signal-to-noise ratio of the user's voice data is determined as the voice signal quality value; the corresponding physiological signal quality value is obtained by weighted fusion calculation based on the mutation rate of the heartbeat interval, the coefficient of variation of the cycle corresponding to the target respiratory frequency, and the third preset weight. The comprehensive score corresponding to the target emotion is obtained by calculating the speech score, physiological score, speech signal quality value, and physiological signal quality value, and then the comprehensive score is normalized to obtain the corresponding emotion score.

[0012] A second aspect of this application provides an emotion intervention device, comprising: The processing unit is used to obtain the corresponding target emotional semantic information, target paralinguistic features, initial emotion and target physiological neural state based on the collected user voice data and user physiological index data. The recognition unit is used to identify the user's target emotion based on the initial emotion and the target's physiological and neural state, and to obtain the emotion score of the target emotion based on the target's emotional semantic information and target's paralinguistic features. The processing unit is also configured to, if the emotion score exceeds a preset score threshold, obtain a first intervention method for the target emotion based on a preset relationship between a first specified quantity and the emotion intervention method, according to at least one of the three factors: the type of the target emotion semantic information, the target physiological and neural state, and the initial emotion. The first specified quantity includes at least one of the three factors: the type of the emotion semantic information, the physiological and neural state, and the emotion. The interaction unit is used to execute the first intervention method.

[0013] A third aspect of this application provides an emotion intervention device, comprising: Central processing unit, memory, and input / output interfaces; The memory can be either temporary or permanent storage. The central processing unit is configured to communicate with the memory and execute instructions in the memory to perform the aforementioned method.

[0014] A fourth aspect of this application provides a computer-readable storage medium including instructions that, when executed on a computer, cause the computer to perform the aforementioned method.

[0015] As can be seen from the above technical solutions, the embodiments of this application have the following advantages: First, based on collected user voice data and user physiological index data, the corresponding target emotional semantic information, target paralinguistic features, initial emotion, and target physiological neural state are obtained. Then, based on the initial emotion and target physiological neural state, the user's corresponding target emotion is identified, and an emotion score is obtained based on the target emotional semantic information and target paralinguistic features. If the emotion score exceeds a preset score threshold, a first intervention method is obtained based on a preset relationship between a first specified quantity and an emotional intervention method, according to at least one of the three: the type of target emotional semantic information, the target physiological neural state, and the initial emotion. The first specified quantity includes at least one of the three: the type of emotional semantic information, the physiological neural state, and the emotion. Finally, the interaction module is controlled to execute the first intervention method. This application's method implements emotional intervention based on an emotion intervention device. This device is mass-producible, eliminating the need for users to frequently seek professional services, significantly reducing costs while achieving emotional intervention, and greatly alleviating the user's economic burden.

[0016] Additional aspects and advantages of embodiments of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of embodiments of this application. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of an embodiment of an emotion intervention method disclosed in this application; Figure 2 This is a schematic diagram of another embodiment of an emotion intervention method disclosed in this application; Figure 3 This is a schematic diagram of an embodiment of an emotion intervention device disclosed in this application; Figure 4 This is a schematic diagram of another embodiment of an emotion intervention device disclosed in this application.

[0019] The realization of the objectives, functional features and advantages of the embodiments of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0020] Cognitive Behavioral Therapy (CBT) is an important approach that can modify a person's cognitive behavior. To achieve patient health management, existing solutions require professionals skilled in CBT to provide intervention services. However, current solutions suffer from high labor costs due to a limited number of CBT professionals compared to the large number of patients, placing a financial burden on patients. Furthermore, human intervention is not always timely. To address these technical problems, this application provides an emotion intervention method and related device to reduce costs. The method utilizes an emotion intervention device that can be mass-produced, reducing costs and eliminating the need for frequent professional interventions. This significantly reduces costs while still achieving emotion intervention, greatly alleviating the financial burden on users.

[0021] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the embodiments of this application, and should not be construed as limiting the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the protection scope of the embodiments of this application.

[0022] In the description of the embodiments of this application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "circumferential", "radial", etc., indicating the orientation or positional relationship are based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the embodiments of this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of this application.

[0023] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "first," "second," "third," "fourth," etc., are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus. In the description of embodiments of this application, "a plurality of" means two or more, unless otherwise expressly specified.

[0024] In the embodiments of this application, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0025] In the embodiments of this application, unless otherwise expressly specified and limited, "above" or "below" the second feature can include direct contact between the first and second features, or contact between the first and second features through another feature between them. Furthermore, "above," "over," and "on top" of the second feature includes the first feature being directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature includes the first feature being directly below or diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.

[0026] The following describes one emotion intervention method proposed in this application. Please refer to... Figure 1 One embodiment of the emotion intervention method of this application is applied to the processing module of an emotion intervention device, the device further including an interaction module, the method comprising: 101. Based on the collected user voice data and user physiological index data, obtain the corresponding target emotional semantic information, target paralinguistic features, initial emotion, and target physiological neural state; Based on the collected user voice data and user physiological indicator data, corresponding target emotional semantic information, target paralinguistic features, initial emotion, and target physiological neural state are obtained. Specifically, user voice data includes the user's speech content and intonation, while user physiological indicator data refers to the user's specific physiological indicators. Target emotional semantic information consists of words or phrases containing emotion, target paralinguistic features include the user's acoustic characteristics, such as tone and energy level, initial emotion is the preliminary emotion judged based on the user's current situation, and target physiological neural state represents the user's physiological stress level.

[0027] 102. Identify the user's target emotion based on the initial emotion and the target's physiological neural state, and obtain the emotion score of the target emotion based on the target's emotional semantic information and target paralinguistic features; The system identifies the user's target emotion based on the initial emotion and the target physiological neural state, and obtains an emotion score for the target emotion based on the target emotional semantic information and target paralinguistic features. Specifically, the target emotion is the final emotion obtained by adjusting the initial emotion using the target physiological neural state, and the emotion score indicates the degree to which the user currently tends to be in the target emotion.

[0028] 103. If the emotion score exceeds the preset score threshold, then based on the preset relationship between the first specified quantity and the emotion intervention method, the first intervention method for the target emotion is obtained according to at least one of the three factors: the type of target emotion semantic information, the target physiological neural state, and the initial emotion. If the emotion score exceeds a preset scoring threshold, then based on a preset relationship between a first specified quantity and the emotion intervention method, a first intervention method for the target emotion is obtained according to at least one of the following three factors: the type of target emotional semantic information, the target physiological and neural state, and the initial emotion. The first specified quantity includes at least one of the three factors: the type of emotional semantic information, the physiological and neural state, and the emotion. The scoring threshold can be set according to actual needs, and the preset relationship can also be set according to actual circumstances; specific details are not limited here.

[0029] 104. Control the interaction module to execute the first intervention method.

[0030] The control interaction module executes the first intervention method. The processing module controls the interaction module based on the first intervention method. The first intervention method may include one or more specific operation steps, such as voice or light prompts, etc., which are not limited here.

[0031] In this embodiment, the corresponding target emotional semantic information, target paralinguistic features, initial emotion, and target physiological neural state are first obtained based on the collected user voice data and user physiological indicator data. Then, the user's target emotion is identified based on the initial emotion and target physiological neural state, and an emotion score is obtained based on the target emotional semantic information and target paralinguistic features. If the emotion score exceeds a preset score threshold, a first intervention method is obtained based on a preset relationship between a first specified quantity and an emotional intervention method, according to at least one of the three: the type of target emotional semantic information, the target physiological neural state, and the initial emotion. The first specified quantity includes at least one of the three: the type of emotional semantic information, the physiological neural state, and the emotion. Finally, the interaction module is controlled to execute the first intervention method. This method implements emotional intervention based on an emotion intervention device. The device is mass-producible, eliminating the need for users to frequently seek professional services, significantly reducing costs while achieving emotional intervention, and greatly alleviating the user's economic burden.

[0032] Please see Figure 2 Another embodiment of the emotion intervention method of this application is applied to the processing module of an emotion intervention device (taking an intelligent plush robot as an example in this embodiment). The device further includes an interaction module, and the method includes: 201. Based on the collected user voice data and user physiological index data, obtain the corresponding target emotional semantic information, target paralinguistic features, initial emotion, and target physiological neural state; In one implementation, the collected user voice data is first transcribed into text to obtain corresponding text data. Then, the text data undergoes sentiment semantic extraction to obtain the corresponding target sentiment semantic information. Specifically, the intelligent plush robot is equipped with a microphone array capable of collecting user voice data in real time, including daily conversations, self-talk, or interactive statements. The utterances in the collected user voice data can be transcribed into text to obtain corresponding text data. Then, target sentiment semantic information is extracted from the text data based on natural language processing algorithms. This sentiment semantic information is information carrying emotions, including emotional vocabulary (such as "worried," "afraid," and "hopeless"), affirmative and negative expressions (such as "good," "bad," and "no"), degree modifiers (such as "extremely worried" and "increasingly afraid"), expressions of uncertainty (such as "what to do" and "don't know if it will happen"), and expressions of catastrophic consequences (such as "definitely failed again" and "completely hopeless").

[0033] Next, feature extraction processing is performed on the user's voice data to obtain the corresponding target paralinguistic features, which include fundamental frequency, energy, speech rate, and formants. Specifically, fundamental frequency reflects the user's level of tension, energy reflects the user's level of repression, speech rate reflects the user's level of activation, and formants reflect the user's level of speech stability.

[0034] Then, based on the pre-defined relationship between the third specified quantity and emotion, the corresponding initial emotion is obtained according to the target emotional semantic information and target paralinguistic features. The third specified quantity includes emotional semantic information and paralinguistic features. Specifically, the pre-defined relationship between the third specified quantity and emotion can be set according to actual needs, and is not limited here. For example, the pre-defined relationship can be set as follows: when there are expressions of degree modification (such as "particularly worried" and "increasingly afraid") and / or expressions of uncertainty (such as "what to do" and "I don't know if it will happen"), and the speech rate is outside the specified normal range, the fundamental frequency fluctuates greatly, or the pauses increase, it is determined to be an anxious emotion; or when there are expressions of "hopelessness" and / or "very tired" and / or "don't want to talk", and the energy decreases, the speech rate slows down, and the long pauses increase, it is determined to be a depressed emotion; or when neither the text nor the paralinguistic features show obvious positive or negative features, it can be determined to be a calm state.

[0035] Finally, the collected user physiological data is processed to obtain the corresponding target physiological and neurological state. Specifically, the intelligent plush robot is equipped with a non-contact, non-invasive millimeter-wave radar sensor, which can collect user physiological data using the aforementioned sensor. This data is then further processed to obtain the corresponding target physiological and neurological state. The physiological and neurological state represents the user's level of physiological stress, which can be stress, relaxation, or calmness, etc., and is not specifically limited here.

[0036] The step of "processing the collected user physiological index data to obtain the corresponding target physiological neural state" has multiple implementation methods, which are not limited here. The following is an example of one implementation method.

[0037] In one implementation, user physiological data is collected in real time, including heart rate interval and target respiratory rate. It is understood that the user physiological data may also include other data, which can be set according to actual needs; no specific limitation is made here. This embodiment uses heart rate interval and target respiratory rate as examples.

[0038] Then, based on the heart rate intervals, the target standard deviation of all heart rate intervals within the data collection period, the target root mean square of the difference between adjacent heart rate intervals, and the target ratio of low-frequency power to high-frequency power are calculated. Based on the preset relationship between the fourth specified quantity and the physiological nervous state, the corresponding target physiological nervous state is obtained according to the target respiratory rate, target standard deviation, target root mean square, and target ratio. The fourth specified quantity includes at least one of the following: respiratory rate, standard deviation of heart rate intervals, root mean square of the difference between adjacent heart rate intervals, and the ratio of low-frequency power to high-frequency power. The physiological nervous state represents the user's physiological stress level. The preset relationship between the fourth specified quantity and the physiological nervous state can also be set according to actual needs. For example, if a significantly increased target ratio (sympathetic activation), decreased RMSSD (parasympathetic inhibition), and irregular and shallow respiratory rate occur, the physiological nervous state is determined to be a high-stress state.

[0039] 202. Identify the user's target emotion based on the initial emotion and the target's physiological and neural state, and obtain the emotion score of the target emotion based on the target's emotional semantic information and target's paralinguistic features; The step "Identify the user's target emotion based on the initial emotion and target physiological and neural state" specifically involves identifying the user's target emotion based on a preset relationship between the overall quantity and the identified emotion. The overall quantity includes both emotion and physiological and neural state. The preset relationship between the overall quantity and the identified emotion can be set according to actual needs and is not limited here. For example, if the initial emotion is "happy" and the target physiological and neural state is high stress, the target emotion is determined to be hidden anxiety or forced cheerfulness. Or, if the initial emotion is "depressed" and the target physiological and neural state is low stress, the target emotion is determined to be depression.

[0040] Specifically, the step of "obtaining the emotion score of the target emotion based on the target emotional semantic information and the target paralinguistic features" can be implemented in multiple ways, and no specific implementation is limited here. The following is an example of one implementation method.

[0041] In one implementation, after temporal alignment, the target text score is first determined based on a preset relationship between emotional semantic information and the text score corresponding to the target emotion. Then, based on a preset relationship between paralinguistic features and the acoustic score corresponding to the target emotion, the target acoustic score is determined based on the target paralinguistic features. Finally, a weighted fusion calculation is performed using a first preset weight, the target text score, and the target acoustic score to obtain the speech score corresponding to the target emotion. For example, for anxiety, the emotional semantic information "worry" can be given 6 points, while "no" can be given 4 points; the average is 5 points. As another example, for anxiety, if the energy in the paralinguistic features is higher than a preset value, the corresponding acoustic score is high (e.g., 8 points).

[0042] Next, a weighted fusion calculation is performed based on the second preset weight, target breathing rate, target standard deviation, target root mean square, and target ratio to obtain the physiological score corresponding to the target emotion. The second preset weight can be set according to actual needs; specific settings are not limited here.

[0043] Then, the signal-to-noise ratio of the user's voice data is determined as the voice signal quality value. A weighted fusion calculation is performed based on the mutation rate of the heartbeat interval, the coefficient of variation of the cycle corresponding to the target respiratory frequency, and a third preset weight to obtain the corresponding physiological signal quality value. The third preset weight can be set according to actual needs; no specific limitation is made here.

[0044] Finally, a comprehensive score corresponding to the target emotion is obtained based on the speech score, physiological score, speech signal quality value, and physiological signal quality value. This comprehensive score is then normalized to obtain the corresponding emotion rating. Specifically, there are multiple implementation methods, which are not limited here. For example, one method uses only the speech score and physiological score, along with their corresponding weights, for calculation.

[0045] 203. If the emotion score exceeds the preset score threshold, then based on the preset relationship between the first specified quantity and the emotion intervention method, the first intervention method for the target emotion is obtained according to at least one of the three factors: the type of target emotion semantic information, the target physiological neural state, and the initial emotion. If the emotion score exceeds a preset threshold, a first intervention method is determined based on the preset relationship between the first specified quantity and the emotion intervention method. This intervention method is chosen according to at least one of the following three factors: the type of the target emotion semantic information, the target physiological and neurological state, and the initial emotion. The first specified quantity includes at least one of the three factors: the type of emotion semantic information, the physiological and neurological state, and the emotion itself. The type of emotion semantic information can be catastrophic thinking, self-denial, avoidance, pre-sleep rumination, self-harm, or expression of despair. The preset relationship can be set according to actual needs and is not limited here. For example, if the first specified quantity is "catastrophic thinking," the corresponding emotion intervention method could be named "Socratic questioning." "High anxiety and decreased physiological indicators" could be "diaphragmatic breathing / mindfulness relaxation." "Depression and frequent negative automatic thoughts" could be "behavioral activation + thought recording sheet." "Self-denial" could be "self-compassion training + cognitive restructuring." "Avoidance" could be "progressive task decomposition." "Depression and decreased activity" could be "behavioral activation." "Pre-sleep rumination" could be "pre-sleep thought unloading + relaxation training." "Self-harm or expression of despair" could be "triggering a high-risk warning process."

[0046] 204. Based on the preset relationship between the second specified quantity and the personalized intervention method, determine the second intervention method for the target emotion according to the user's historical feedback information and / or the user's selection information; Based on the pre-defined relationship between the second specified quantity and the personalized intervention method, a second intervention method targeting the target emotion is determined according to the user's historical feedback information and / or the user's selection information. The second specified quantity includes historical feedback information and / or selection information; historical feedback information refers to the user's feedback based on previous interventions, and selection information refers to information actively chosen by the user. Personalized intervention methods include "empathy + gentle guidance" or "rational guidance," etc., without specific limitations here.

[0047] 205. The control interaction module executes the first intervention method and the second intervention method; 206. The control interaction module prompts the user to complete their homework and records and stores the homework content entered by the user and the homework completion time; For example, a smart plush robot can use voice prompts to remind users which homework they need to complete and record the user's progress.

[0048] 207. If the change in the target exceeds the preset threshold, the emotional intervention is considered complete. The change in the target is the change in the emotional score before and after the intervention. If the change in the target exceeds the preset threshold, the emotional intervention is considered complete. The target change is the change in emotional rating before and after the intervention. The preset threshold is the dividing point between whether or not intervention is needed. If the change in the target exceeds the preset threshold, the intervention is considered effective. If the change in the target does not exceed the preset threshold, the intervention is considered ineffective.

[0049] 208. If the target change does not exceed the preset threshold and the current cumulative number of interventions does not exceed the preset number, then based on the preset relationship between the third specified quantity and the alternative intervention methods, a third intervention method for the target emotion is obtained according to at least one of the three factors: the type of target emotional semantic information, the target physiological neural state, and the initial emotion. After the interaction module is controlled to execute the third intervention method, the judgment is re-based on the target change and the current cumulative number of interventions. Specifically, if the current intervention is ineffective, it is determined whether the cumulative number of interventions has exceeded the preset limit. If it has not exceeded the preset limit, a third intervention method is derived based on at least one of the following three factors: the type of target emotional semantic information, the target's physiological and neurological state, and the initial emotion. The effectiveness of the third intervention method is then assessed; if not, intervention continues until the process proceeds to step 207 or step 209. Alternative intervention methods can be other intervention methods set according to actual needs; specific details are not limited here.

[0050] 209. If the target change does not exceed the preset threshold, and the current cumulative number of interventions exceeds the preset number, the control interaction module will issue a suggestion for manual intervention.

[0051] Specifically, if there is still no significant effect after the preset number of interventions, it indicates that manual intervention is required. The control interaction module will issue a prompt suggesting manual intervention to remind the user to seek help from professionals in a timely manner.

[0052] The following example illustrates this implementation. One evening, Ms. L said to the robot, "I had two more injections of ovulation-inducing drugs today, and my stomach feels bloated. I think there might be no hope again; the last time, such a good embryo didn't develop..." After assessment, the robot obtained the initial emotion (moderate to severe anxiety), the type of emotional semantic information was catastrophic thinking, and the target physiological and neurological state was a state of high stress. Based on weighted fusion calculation, the emotion score given was 7.5, exceeding the preset scoring threshold of 5, requiring emotional intervention. Through analysis, the first intervention method corresponding to "catastrophic thinking + high stress" is "Socratic questioning + relaxation training," while Ms. L chose the second intervention method "empathy + gentle guidance." Subsequently, the second intervention method can be implemented first, followed by the first intervention method.

[0053] For example, the robot says: "It sounds like today's injections were tiring and worrying for you. Many mothers undergoing IVF treatment have the thought of 'what if it doesn't work again,' which is very normal. Would you like to spend a few minutes with me and see if this thought is entirely correct?" Next, the robot says, "You said, 'This time it might be hopeless again.' Shall we look for some evidence? What were the reasons for the last failed transfer? Did the doctor mention any adjustments to the treatment plan this time?" Ms. L replies (voice interaction): "Last time the endometrium wasn't good enough... This time the doctor added medication, and the endometrium seems to be a little thicker." The robot says, "Hmm, that's one piece of evidence that 'it might be successful.' Shall we look for other evidence? For example, your embryo quality score this time is a little higher than last time, right?" After 3-5 rounds of dialogue, the robot guides the patient to conclude that "it's not entirely hopeless."

[0054] Then, based on Ms. L's real-time breathing rate (radar monitoring showed shallow and rapid breathing), the robot proactively guided her: "I can feel that your breathing is a little rapid. Shall we take three deep breaths together? I will guide you with lights and sounds." The robot emitted a soft and slow guiding voice, while the LED light on its chest gradually increased in brightness with each inhalation and exhalation for 2 minutes.

[0055] The robot assigns homework: "To help you sleep better tonight, let's give ourselves a little task: write down 'one progress' and 'one thing that made me feel a little bit at ease' today, and share them with me at this time tomorrow, okay? You can do it by speaking or typing." After the intervention, the target change in mood score was achieved, decreasing to 4.2, indicating significant relief. Relevant information was recorded and stored. If the intervention is ineffective for three consecutive days, a notification can be sent to a professional.

[0056] This embodiment introduces an emotion level (the emotion level can be determined based on a preset relationship between scores and levels, according to the emotion score) to increase the accuracy of the assessment and the effectiveness of the intervention. In the above implementation, the emotion level is reflected in the initial emotion or the target emotion. For example, "mild anxiety," "moderate anxiety," "moderate to severe anxiety," and "severe anxiety" are four different emotions with corresponding intervention methods of different degrees, to reflect graded intervention. It can be understood that in another implementation, the emotion level can be evaluated separately, and the relationship between the target emotion and the intervention method can be viewed as described above. Simply put, if the emotion level is "mild," then there is only a corresponding intervention method; if the emotion level is "moderate" or "moderate to severe," then not only is there a corresponding intervention method, but a dynamic psychological and emotional assessment report can also be automatically generated, including a 7-day emotion trend chart, abnormal fluctuation time points (such as the injection day, the day before egg retrieval, etc.), and specific suggestions; if the emotion level is "severe," then in addition to intervention based on specific intervention methods, an alert must be immediately sent to the patient's pre-registered emergency contact person and the reproductive center's psychological clinic to facilitate the emergency contact person or medical staff to refer the patient to the hospital's psychology department. All of the above reflects graded intervention. For example, for "moderate to severe anxiety", the corresponding intervention method is "Socratic questioning + relaxation training", and a dynamic assessment report should be generated for reference. If the "moderate to severe anxiety" changes to "severe anxiety", in addition to "Socratic questioning + relaxation training" and generating an assessment report, the emergency contact person or medical staff should be notified to refer the patient to the hospital's psychology department to ensure the patient's mental health.

[0057] In this embodiment, the method utilizes an emotion intervention device to achieve emotional intervention. This device is mass-producible, eliminating the need for users to frequently seek professional services, significantly reducing costs and alleviating the financial burden on users while still providing emotional intervention. Furthermore, the robot can detect emotional peaks at key time points such as the injection date, before egg retrieval, and after embryo transfer, automatically increasing the frequency of CBT intervention without requiring the patient to actively seek help. This reduces the risk of miscarriage, is safe and non-invasive, and implements personalized intervention methods based on historical data or individual choices. It is non-contact and non-invasive, requiring no human intervention and significantly reducing feelings of shame.

[0058] The above describes an emotion intervention method according to an embodiment of this application. The following describes an emotion intervention device according to an embodiment of this application. Please refer to... Figure 3 One embodiment of an emotion intervention device in this application includes: Processing unit 301 is used to obtain corresponding target emotional semantic information, target paralinguistic features, initial emotion and target physiological neural state based on the collected user voice data and user physiological index data; The recognition unit 302 is used to identify the target emotion corresponding to the user based on the initial emotion and the target physiological neural state, and to obtain the emotion score of the target emotion based on the target emotional semantic information and the target paralinguistic features. The processing unit 301 is further configured to, if the emotion score exceeds a preset score threshold, obtain a first intervention method for the target emotion based on a preset relationship between a first specified quantity and an emotion intervention method, according to at least one of the three factors: the type of target emotion semantic information, the target physiological and neural state, and the initial emotion. The first specified quantity includes at least one of the three factors: the type of emotion semantic information, the physiological and neural state, and the emotion. Interaction unit 303 is used to execute the first intervention method.

[0059] In this embodiment, the processing unit 301 first obtains the corresponding target emotional semantic information, target paralinguistic features, initial emotion, and target physiological neural state based on the collected user voice data and user physiological indicator data. Then, the recognition unit 302 identifies the user's corresponding target emotion based on the initial emotion and target physiological neural state, and obtains an emotion score for the target emotion based on the target emotional semantic information and target paralinguistic features. If the emotion score exceeds a preset score threshold, a first intervention method is obtained based on a preset relationship between a first specified quantity and an emotional intervention method, according to at least one of the three: the type of target emotional semantic information, the target physiological neural state, and the initial emotion. The first specified quantity includes at least one of the three: the type of emotional semantic information, the physiological neural state, and the emotion. Finally, the interaction unit 303 controls the interaction module to execute the first intervention method. The method of this application implements emotional intervention based on an emotion intervention device. This device can be mass-produced, eliminating the need for users to frequently seek professional services, significantly reducing costs while achieving emotional intervention, and greatly alleviating the economic burden on users.

[0060] The following is a detailed description of an emotion intervention device according to an embodiment of this application. Based on the above embodiments, another embodiment of the emotion intervention device according to an embodiment of this application further includes: Furthermore, the device also includes a determining unit for: Based on the preset relationship between the second specified quantity and the personalized intervention method, the second intervention method for the target emotion is determined according to the user's historical feedback information and / or the user's selection information. The second specified quantity includes historical feedback information and / or selection information. The interactive unit is specifically used for: The control interaction module is used to execute the first intervention method and the second intervention method.

[0061] Furthermore, the device also includes a working unit for: The control and interaction module prompts the user to complete their homework and records and stores the homework content entered by the user and the homework completion time.

[0062] Furthermore, the device also includes a judgment unit for: If the change in the target exceeds the preset threshold, the emotional intervention is considered complete. The change in the target is the change in the emotional score before and after the intervention. If the target change does not exceed the preset threshold and the current cumulative number of interventions does not exceed the preset number, then based on the preset relationship between the third specified quantity and the alternative intervention methods, a third intervention method for the target emotion is obtained according to at least one of the three factors: the type of target emotional semantic information, the target physiological neural state, and the initial emotion. After the interaction module is controlled to execute the third intervention method, the judgment is re-based on the target change and the current cumulative number of interventions. If the target change does not exceed the preset threshold, and the current cumulative number of interventions exceeds the preset number, the control interaction module will issue a suggestion for manual intervention.

[0063] Furthermore, the processing unit is specifically used for: The collected user voice data is processed into text transcription to obtain the corresponding text data, and the text data is processed into emotional semantic extraction to obtain the corresponding target emotional semantic information. Feature extraction processing is performed on user voice data to obtain corresponding target sub-language features, which include fundamental frequency, energy, speech rate, and formants; Based on the pre-defined relationship between the third specified quantity and emotion, the corresponding initial emotion is obtained according to the target emotional semantic information and the target paralinguistic features. The third specified quantity includes emotional semantic information and paralinguistic features. The collected user physiological index data are processed to obtain the corresponding target physiological neural state.

[0064] Furthermore, the processing unit is specifically used for: Real-time collection of user physiological data, including heart rate interval and target respiratory rate; The target standard deviation of all heartbeat intervals within the acquisition time period, the target root mean square of the difference between adjacent heartbeat intervals, and the target ratio of low-frequency power to high-frequency power are calculated based on the heartbeat intervals. Based on the preset relationship between the fourth specified quantity and the physiological and nervous state, the corresponding target physiological and nervous state is obtained according to the target respiratory rate, target standard deviation, target root mean square, and target ratio. The fourth specified quantity includes at least one of the following: respiratory rate, standard deviation of heartbeat intervals, root mean square of the difference between adjacent heartbeat intervals, and ratio of low-frequency power to high-frequency power. The physiological and nervous state represents the user's physiological stress level.

[0065] Furthermore, the identification unit is specifically used for: Based on the pre-defined relationship between emotional semantic information and the text score corresponding to the target emotion, the target text score is determined according to the target emotional semantic information; based on the pre-defined relationship between paralinguistic features and the acoustic score corresponding to the target emotion, the target acoustic score is determined according to the target paralinguistic features; and a weighted fusion calculation is performed based on the first pre-defined weight, the target text score, and the target acoustic score to obtain the speech score corresponding to the target emotion. The physiological score corresponding to the target emotion is obtained by weighted fusion calculation based on the second preset weight, target breathing rate, target standard deviation, target root mean square and target ratio. The signal-to-noise ratio of the user's voice data is determined as the voice signal quality value; the corresponding physiological signal quality value is obtained by weighted fusion calculation based on the mutation rate of the heartbeat interval, the coefficient of variation of the cycle corresponding to the target respiratory frequency, and the third preset weight. The comprehensive score corresponding to the target emotion is obtained by calculating the speech score, physiological score, speech signal quality value, and physiological signal quality value, and then the comprehensive score is normalized to obtain the corresponding emotion score.

[0066] The functions and processes performed by each unit in the emotion intervention device of this embodiment are the same as those described above. Figures 1 to 2 The functions and procedures performed by the emotional intervention device are similar, and will not be described in detail here.

[0067] Figure 4 This is a schematic diagram of the structure of an emotion intervention device provided in an embodiment of this application. The emotion intervention device 400 may include one or more central processing units (CPUs) 401 and a memory 405, in which one or more applications or data are stored.

[0068] The memory 405 can be volatile or persistent storage. The program stored in the memory 405 can include one or more modules, each module including a series of instruction operations on the emotion intervention device 400. Furthermore, the central processing unit 401 can be configured to communicate with the memory 405 and execute the series of instruction operations stored in the memory 405 on the emotion intervention device 400.

[0069] The emotion intervention device 400 may also include one or more power supplies 402, one or more wired or wireless network interfaces 403, one or more input / output interfaces 404, and / or one or more operating systems, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0070] The central processing unit 401 can perform the aforementioned... Figures 1 to 2The specific operations performed by the emotion intervention device in the illustrated embodiment will not be described in detail here.

[0071] This application also provides a computer-readable storage medium including instructions that, when executed on a computer, cause the computer to perform the methods described in the foregoing embodiments.

[0072] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0073] It should be noted that although the steps in the flowcharts of the various embodiments are drawn sequentially according to the arrows, unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the various embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps.

[0074] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the embodiments of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0075] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0076] The above are merely preferred embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structural transformations made using the description and drawings of the present application under the inventive concept of the present application, or direct / indirect applications in other related technical fields, are included within the patent protection scope of the present application.

Claims

1. An emotion intervention method, characterized in that, A processing module for use in an emotion intervention device, the device further including an interaction module, the method comprising: Based on the collected user voice data and user physiological index data, the corresponding target emotional semantic information, target paralinguistic features, initial emotion and target physiological neural state are obtained; The target emotion corresponding to the user is identified based on the initial emotion and the target physiological neural state, and the emotion score of the target emotion is obtained based on the target emotional semantic information and the target paralinguistic features. If the emotion score exceeds a preset score threshold, then based on the preset relationship between the first specified quantity and the emotion intervention method, a first intervention method for the target emotion is obtained according to at least one of the three factors: the type of the target emotion semantic information, the target physiological neural state, and the initial emotion. The first specified quantity includes at least one of the three factors: the type of emotion semantic information, the physiological neural state, and the emotion. Control the interaction module to execute the first intervention method.

2. The emotion intervention method according to claim 1, characterized in that, After obtaining the emotion score of the target emotion based on the target emotional semantic information and the target paralinguistic features, the method further includes: Based on the preset relationship between the second specified quantity and the personalized intervention method, a second intervention method for the target emotion is determined according to the user's historical feedback information and / or the user's selection information. The second specified quantity includes historical feedback information and / or selection information. The control of the interaction module to execute the first intervention method includes: The control interaction module executes the first intervention method and the second intervention method.

3. The emotion intervention method according to claim 1, characterized in that, After controlling the interaction module to execute the first intervention method, the method further includes: The control module prompts the user to complete their homework and records and stores the homework content entered by the user and the homework completion time.

4. The emotion intervention method according to claim 1, characterized in that, After controlling the interaction module to execute the first intervention method, the method further includes: If the target change exceeds a preset threshold, the emotional intervention is considered complete. The target change refers to the change in the emotional score before and after the intervention. If the target change amount does not exceed the preset threshold and the current cumulative number of interventions does not exceed the preset number, then based on the preset relationship between the third specified amount and the alternative intervention methods, a third intervention method for the target emotion is obtained according to at least one of the three factors: the type of the target emotional semantic information, the target physiological neural state, and the initial emotion. After the interaction module is controlled to execute the third intervention method, the judgment is re-based on the target change amount and the current cumulative number of interventions. If the target change does not exceed a preset threshold, and the current cumulative number of interventions exceeds a preset number, then the interaction module is controlled to issue a suggestion for manual intervention.

5. The emotion intervention method according to claim 1, characterized in that, The process of obtaining corresponding target emotional semantic information, target paralinguistic features, initial emotion, and target physiological neural state based on collected user voice data and user physiological index data includes: The collected user voice data is processed by text transcription to obtain the corresponding text data, and the text data is processed by emotional semantic extraction to obtain the corresponding target emotional semantic information. The user voice data is subjected to feature extraction processing to obtain corresponding target sub-language features, which include fundamental frequency, energy, speech rate and formants; Based on the preset relationship between the third specified quantity and emotion, the corresponding initial emotion is obtained according to the target emotional semantic information and the target paralinguistic features. The third specified quantity includes emotional semantic information and paralinguistic features. The collected user physiological index data are processed to obtain the corresponding target physiological neural state.

6. The emotion intervention method according to claim 5, characterized in that, The process of processing the collected user physiological index data to obtain the corresponding target physiological neural state includes: Real-time collection of user physiological data, including heart rate interval and target respiratory rate; The target standard deviation of all heartbeat intervals within the acquisition time period, the target root mean square of the difference between adjacent heartbeat intervals, and the target ratio of low-frequency power to high-frequency power are calculated based on the heartbeat intervals. Based on the preset relationship between the fourth specified quantity and the physiological nervous state, the corresponding target physiological nervous state is obtained according to the target respiratory rate, the target standard deviation, the target root mean square, and the target ratio. The fourth specified quantity includes at least one of the following: respiratory rate, standard deviation of heartbeat intervals, root mean square of the difference between adjacent heartbeat intervals, and ratio of low-frequency power to high-frequency power. The physiological nervous state represents the user's physiological stress level.

7. The emotion intervention method according to claim 6, characterized in that, The step of obtaining the emotion score of the target emotion based on the target emotional semantic information and the target paralinguistic features includes: Based on a preset relationship between emotional semantic information and the text score corresponding to the target emotion, the corresponding target text score is determined according to the target emotional semantic information; based on a preset relationship between paralinguistic features and the acoustic score corresponding to the target emotion, the corresponding target acoustic score is determined according to the target paralinguistic features; and a weighted fusion calculation is performed according to a first preset weight, the target text score, and the target acoustic score to obtain the speech score corresponding to the target emotion. The physiological score corresponding to the target emotion is obtained by weighted fusion calculation based on the second preset weight, the target breathing rate, the target standard deviation, the target root mean square, and the target ratio. The signal-to-noise ratio of the user's voice data is determined as the voice signal quality value; the corresponding physiological signal quality value is obtained by weighted fusion calculation based on the mutation rate of the heartbeat interval, the coefficient of variation of the period corresponding to the target respiratory frequency, and the third preset weight. The comprehensive score corresponding to the target emotion is obtained based on the speech score, the physiological score, the speech signal quality value, and the physiological signal quality value, and the comprehensive score is normalized to obtain the corresponding emotion score.

8. An emotion intervention device, characterized in that, include: The processing unit is used to obtain the corresponding target emotional semantic information, target paralinguistic features, initial emotion and target physiological neural state based on the collected user voice data and user physiological index data. The identification unit is used to identify the target emotion corresponding to the user based on the initial emotion and the target physiological neural state, and to obtain the emotion score of the target emotion based on the target emotional semantic information and the target paralinguistic features; The processing unit is further configured to, if the emotion score exceeds a preset score threshold, obtain a first intervention method for the target emotion based on a preset relationship between a first specified quantity and an emotion intervention method, according to at least one of the three factors: the type of the target emotion semantic information, the target physiological neural state, and the initial emotion. The first specified quantity includes at least one of the three factors: the type of emotion semantic information, the physiological neural state, and the emotion. An interaction unit is used to execute the first intervention method.

9. An emotion intervention device, characterized in that, include: Central processing unit, memory, and input / output interfaces; The memory is either a short-term storage memory or a persistent storage memory; The central processing unit is configured to communicate with the memory and execute instructions in the memory to perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Includes instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1 to 7.

Images