An interactive-based psychological counseling session system

Abstract

The present invention relates to the technical field of psychological counseling, and specifically to an interactive psychological counseling conversation system, including: a dialogue management module for receiving the consultation information of the current user and determining the context process and sequence during the user's consultation; a language processing module for analyzing the consultation information and understanding the emotional tendency expressed by the current user; a consultation knowledge module for obtaining the historical data of the user's consultation and determining the emotional pattern and consultation degree information of the user's consultation in combination with the emotional tendency of the consultation information; a consultation recommendation module for determining the user's preference according to the emotional pattern and consultation degree information of the user's consultation; and recommending a consultation plan according to the user's preference; achieving a more personalized and appropriate consultation service and improving the efficiency and accuracy of the user's psychological counseling.

Description

Technical Field

[0001] The present invention relates to the technical field of psychological counseling, and specifically, to an interactive psychological counseling session system. Background Art

[0002] Psychological counseling is the main professional way to maintain the mental health of the public. Different from biomedicine, psychological counseling mainly plays a role through good interpersonal communication between counselors and clients. Therefore, evaluating the ability of clients to participate in psychological counseling and evaluating and selecting appropriate counseling methods and counselors for them (hereinafter referred to as "psychological counseling decision-making evaluation") directly affects the counseling effect and is the core element of psychological counseling. Psychological counseling decision-making evaluation is beneficial for counseling institutions to select the most suitable psychological counselor for specific clients, beneficial for psychological counselors to select the most suitable counseling methods and counseling styles for clients, and also avoids iatrogenic harm caused by the mismatch between counselors and / or counseling methods, which damages the counseling effectiveness. Psychological counseling decision-making evaluation is also an important support means for carrying out mental health services in the era of precision medicine.

[0003] For example, Chinese Patent Publication No. CN112885433A discloses a psychological counseling service matching method, system, device and storage medium. The method includes: obtaining the first information of the user, and obtaining the psychological counseling suitability index of the user according to the first information; if it is determined that the user is suitable for psychological counseling services according to the psychological counseling suitability index, then obtaining the second information of the user, and matching the first psychological counseling method in a preset psychological counseling method library according to the second information; obtaining the third information of the user, and matching the first psychological counselor in a preset psychological counselor library according to the third information.

[0004] However, when selecting a counselor according to the corresponding indicators, it is also necessary to determine the changes in the relevant intentions and the changes in the relevant emotional tendencies of the user during the consultation, and also to adjust the set plan according to the different habits of each person to improve the accuracy of the consultation. Summary of the Invention

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: an interactive psychological counseling session system, including: a dialogue management module, configured to receive the consultation information of the current user and determine the context process and sequence during the user's consultation.

[0006] A language processing module, configured to analyze the consultation information and understand the emotional tendency expressed by the current user.

[0007] A consultation knowledge module, configured to obtain the historical data of the user's consultation, and combine the emotional tendency of the consultation information to determine the emotional pattern and consultation degree information of the user's consultation.

[0008] A consultation recommendation module, which is used to determine user preferences according to the emotional pattern and consultation degree information of the user's consultation, and recommend consultation solutions according to the user preferences.

[0009] A consultation feedback module, which is used to obtain the consultation feedback after the implementation of the consultation solution, extract the consultation stage of the current user from the consultation solution, and combine the consultation solution and consultation feedback of each consultation stage to obtain the feedback evaluation solution of the current user.

[0010] The beneficial effects of the present invention are as follows: First, by real-time monitoring factors such as the change of the user's consultation intention, emotional state and time, the present invention ensures that the consultation session system has stronger context awareness ability, so as to provide more personalized and appropriate consultation services.

[0011] Second, through in-depth analysis of the user's consultation information, the system of the present invention can accurately identify the user's emotional tendency and recommend more suitable consultation solutions accordingly.

[0012] Third, by using the user's historical consultation data, the system of the present invention can identify the user's emotional pattern and consultation degree information, and then provide consultation suggestions that more meet the user's needs.

[0013] Fourth, by comprehensively considering the user's emotional pattern and consultation degree information, the system of the present invention can determine the user's preferences and recommend the most suitable consultation solution for the current user accordingly.

[0014] Fifth, the present invention not only provides consultation services, but also can evaluate the effect of the consultation solution by collecting consultation feedback, and continuously optimize the consultation services accordingly. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention will be further described below in conjunction with the drawings and embodiments.

[0016] Figure 1 is a system framework diagram of an interactive psychological consultation session system.

[0017] Figure 2 is a system schematic diagram of an interactive psychological consultation session system.

[0018] Figure 3 is a process schematic diagram of the consultation feedback module of an interactive psychological consultation session system. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] The embodiments of the present invention will be described in detail below. The following described embodiments are exemplary and are only used to explain the present invention, and should not be construed as a limitation to the present invention. For those not specified in the embodiments, the techniques or conditions described in the literature in the field or according to the product specifications are followed.

[0020] Refer toFigure 1 , Figure 2 , an interactive psychological counseling session system, comprising: a dialogue management module, a language processing module, a counseling knowledge module, a counseling recommendation module, and a counseling feedback module.

[0021] The dialogue management module receives the counseling information of the user; the dialogue management module passes the counseling information of the user and its context to the language processing module for further analysis; the language processing module analyzes the counseling information of the user, understands the emotional tendency expressed by the user, and passes the emotional tendency analysis result to the counseling knowledge module for further determining the emotional pattern; the counseling knowledge module obtains the historical data of the user's counseling, and passes the emotional pattern and counseling degree information to the counseling recommendation module for recommending a counseling plan according to the user's preference; the counseling recommendation module determines the recommended counseling plan and passes the recommended counseling plan to the counseling feedback module for collecting the feedback after implementation; the counseling feedback module obtains the counseling feedback after the implementation of the counseling plan. The feedback evaluation plan is passed back to the dialogue management module or other relevant modules for further optimizing the counseling process.

[0022] The dialogue management module is used to receive the counseling information of the current user and determine the context process and sequence during the user's counseling.

[0023] The language processing module is used to analyze the counseling information and understand the emotional tendency expressed by the current user.

[0024] The counseling knowledge module is used to obtain the historical data of the user's counseling and determine the emotional pattern and counseling degree information of the user's counseling in combination with the emotional tendency of the counseling information.

[0025] The counseling recommendation module is used to determine the user's preference according to the emotional pattern and counseling degree information of the user's counseling; recommend a counseling plan according to the user's preference.

[0026] The counseling feedback module is used to obtain the counseling feedback after the implementation of the counseling plan, extract the counseling stage of the current user from the counseling plan, and obtain the feedback evaluation plan of the current user in combination with the counseling plan and counseling feedback of each counseling stage.

[0027] During normal psychological counseling, since the problems to be consulted will contain various complex elements, and whether the counselor can accurately express the current psychological problems, and after determining the psychological problems expressed by the counselor, how to qualitatively analyze the current emerging psychological problems, and judge what kind of plan should be adopted to intervene in the current psychological problems, it is necessary to qualitatively analyze the counselor's plan according to the corresponding situation, and conduct a separate analysis of each problem, so as to determine whether the verified psychological problems of the counselor and the psychological problems expressed by the counselor are the same problem, and how the related problems are generated, and how to reduce the impact of psychological problems on the counselor, so as to select a suitable plan to guide the counselor.

[0028] At this time, when conducting a psychological counseling session with the user, the user will first be required to conduct a specific simulation test to verify whether the user has psychological diseases such as mania and autism. The corresponding scales used will be initial tested with scales such as the Minnesota Multiphasic Personality Inventory and the Beck Depression Inventory, and then the counseling information sent by the user will be received, and the progress of the session will be gradually tracked, and this part of the tracked information will be input into the language processing module.

[0029] That is, the implementation methods for determining the context process and sequence during the user's consultation also include: monitoring the intention changes of each round of dialogue during the user's consultation, and recording the occurrence scenario of the dialogue, the user's emotional state and time.

[0030] The intention changes of each round of dialogue can be obtained through the recognition content of the consultation knowledge module, and the user's emotional state is analyzed through the language processing module for the consultation information, so as to continuously record and track the user's session record.

[0031] The following are some scales used in psychological counseling. When using these scales, a part of them will be selected for testing according to the current diagnostic methods, and combined with the form of communication to determine the possible psychological problems of the current user.

[0032] Minnesota Multiphasic Personality Inventory (MMPI): This is a widely used adult personality test, used to evaluate a variety of psychological disorders and personality traits.

[0033] Beck Depression Inventory (BDI): Used to evaluate the degree of depression in patients with depression.

[0034] Hamilton Anxiety Rating Scale (HAM-A): Used to evaluate the severity of anxiety symptoms.

[0035] Generalized Anxiety Disorder Scale (GAD-7): This is a short self-report scale, used to screen for generalized anxiety disorder.

[0036] Patient Health Questionnaire (PHQ-9): This is a self-report questionnaire that assesses symptoms of depression.

[0037] Young Mania Rating Scale (YMRS): Used to assess the severity of manic symptoms in patients with bipolar disorder.

[0038] Brief Psychiatric Rating Scale (BPRS): Used to assess the severity of symptoms in patients with psychosis, particularly schizophrenia.

[0039] Child Behavior Checklist (CBCL): This is a tool used to assess behavioral, emotional, and social problems in children and adolescents.

[0040] Eysenck Personality Questionnaire (EPQ): Used to assess personality traits such as neuroticism, introversion, extroversion, and psychoticism.

[0041] Stanford-Binet Intelligence Scale (SBIS): This is an intelligence test used to assess an individual's cognitive abilities and IQ level.

[0042] The language processing module analyzes the consulting information and understands the emotional tendency expressed by the current user in the following manner: obtain the user's preliminary verification information, and determine the user's psychological counseling index based on the preliminary verification information; extract the first key information from the consulting information based on the obtained preliminary verification information, and determine the user's corresponding confession preference index based on the first key information; determine the user's related symptom matching index based on the confession preference index, and the symptom matching index is used to indicate the degree of the current user's symptom and the specific manifestation type of the symptom; translate the current user's consulting information based on the obtained symptom matching index to obtain the emotional tendency expressed by the user; the purpose of translation here is to verify the illogical behavior of the current user before and after the consultation, as well as the problems in the preliminary verification, so as to select the processing method that best suits the current user.

[0043] Initial verification information usually refers to the basic information provided by the user when they first contact the psychological counseling service. This information may include the user's age, gender, occupation, educational background, family status, personal medical history, current major problems or concerns, etc. This information helps the psychological counselor to form a preliminary understanding and assessment of the user.

[0044] The first key information is the core points extracted and analyzed from the preliminary verification information provided by the user. This information may include the user's most prominent psychological problems, emotional state, behavioral performance, thinking patterns, etc. The first key information is more focused and specific, and can directly reflect the user's current psychological state and need to confide.

[0045] The final obtained emotional tendency is that the counselor comprehensively applies professional knowledge, skills, and experience to transform the user's original expression (which may be vague, chaotic, or emotional) into a clearer, more specific, easier-to-understand, and operable form. It may include an elaboration on the nature, causes, and development process of the user's psychological problems, an explanation of the user's emotions, behaviors, and cognitive patterns, as well as the identification of the user's potential needs and expectations.

[0046] In the case where the psychological counseling indicators are represented as current preliminary verification information, the basic indicators corresponding to the current user, such as the psychological state classification, emotional classification, behavioral classification, environmental classification, etc. that the current user presents, at this time, the index values required in these classifications will be extracted from the obtained preliminary verification information. This index value is generally represented as a numerical value from 0 to 1 to quantify whether the corresponding situation exists for the current user. If the performance is normal, the corresponding numerical value is regarded as 0.

[0047] Psychological state classification: Depression: To judge whether the user shows depressive tendencies; Anxiety: To evaluate the user's anxiety level; Stress: To measure the degree of stress felt by the user; Self-efficacy: To evaluate the user's confidence level in coping with challenges; Stress response: To identify the user's response pattern when facing stress.

[0048] Emotional classification: Emotional stability: To evaluate the degree of the user's emotional fluctuations; Positive emotions: To evaluate the positive emotions expressed by the user; Negative emotions: To identify the negative emotions expressed by the user; Emotional expression ability: Whether the user can clearly express their emotions.

[0049] Behavioral classification: Coping mechanisms: The coping strategies adopted by the user when facing difficulties; Social interaction: The way the user interacts with others and the quality thereof; Lifestyle habits: Lifestyle habits such as diet and sleep; Behavioral patterns: The user's behavioral habits and their changing trends. Occupational status: Employed or not, job satisfaction.

[0050] Environmental classification: Living environment: Living conditions and their impact on emotions; Economic situation: Financial situation and the stress it brings; Major life events: Major changes or events experienced recently; Traumatic experiences: Whether there are signs of post-traumatic stress disorder (PTSD); Coping ability: Performance when facing recent challenges.

[0051] According to the obtained preliminary verification information, the method of extracting the first key information from the counseling information is as follows: In accordance with the obtained preliminary verification information, obtain the information corresponding to the preliminary verification information in the counseling information as the first key information; At this time, verify whether the classification of the counseling information is the same as the corresponding information in the preliminary verification information. When they are the same, verify the frequency of occurrence of the corresponding vocabulary in the counseling information, and sort the identified words according to the frequency of occurrence to form the first key information.

[0052] Based on the first key information, the implementation method of determining the user's corresponding confession bias index is to set the emotional tendency score, the help-seeking bias score, the information sharing tendency score, and the problem-oriented score according to the user's consulting information, and take the weighted average of the emotional tendency score, the help-seeking bias score, the information sharing tendency score, and the problem-oriented score as the output confession bias index.

[0053] Sentiment tendency score: indicates that users are more likely to express emotions during communication, whether positive or negative. Sentiment analysis technology can be used to score each message of the user, and then the overall sentiment tendency score can be summarized; the score range is: -1 to +1; -1 indicates extremely negative emotions, and +1 indicates extremely positive emotions.

[0054] Help-seeking tendency score: indicates that the user may be inclined to seek help, whether it is seeking solutions, emotional support or information query. Intent recognition technology can be used to determine how much help-seeking components are contained in the user's information; score range: 0 to 1; 0 means no intention to seek help at all, and 1 means completely seeking help.

[0055] Information Sharing Propensity Score: Indicates that users may be more willing to share their experiences, feelings, or ideas; content analysis can be used to determine the amount of information shared by users; score range: 0 to 1; 0 means almost no information sharing, and 1 means very willing to share.

[0056] Problem-oriented score: indicates that the user may be more inclined to talk about specific problems or concerns rather than general feelings or experiences; question type identification technology can be used to assess whether the user's information is focused on problem solving.

[0057] As for the method of obtaining the symptom matching index, the obtained confession bias index is matched with the preset symptom, and the index with the highest similarity after matching is used as the output symptom matching index. At this time, the matching method is to use the confession bias index as input and compare it with the corresponding data in the symptom, calculate the Pearson correlation coefficient, and use the symptom matching index corresponding to the maximum value of the Pearson correlation coefficient as the index with the highest similarity, thereby selecting the corresponding symptom matching index.

[0058] The symptom matching index can reflect the severity of the user's symptoms. For example, a higher index value may mean that the symptoms exhibited by the user are more consistent with the diagnostic criteria of a certain mental illness.

[0059] Translate the consultation information of the current user according to the obtained disease matching indicators to obtain the emotional tendency expressed by the user. In this case, the meaning conveyed by the user himself needs to be based on the user's emotional state and potential psychological condition; if the user shows a depressive tendency, then there may be more negative emotion weights in some language expressions of the user. At this time, more attention needs to be paid to the user's expressions in relevant languages when identifying the language.

[0060] That is, identify the consultation information of the current user, process the word with the highest confidence in the consultation information as the keyword for the current identification, determine the emotional tendency of the identified keyword in multiple scenarios, and use the group of emotional tendencies with the highest similarity between the emotional tendency and the disease matching indicators as the emotional tendency expressed by the current user.

[0061] At this time, the similarity between the selected emotional tendency and the disease matching indicators is obtained by comparing the emotional scores existing in the emotional tendency with the emotional score values corresponding to the disease matching indicators in the corresponding situation, and the one with the smallest difference between the two emotional scores is regarded as the highest similarity. At the same time, the emotional score is obtained by comparing the keyword with a pre-set emotional dictionary. Since the disease matching indicator represents the score of the current user in the corresponding symptom, the main emotional tendency of the user at the corresponding disease stage can be obtained at this time. At this time, the relevant indicators of the user can be obtained according to the disease matching indicators and some of them are quantified as emotional scores, so as to monitor the problems existing in the user in the corresponding consultation situation.

[0062] After obtaining the emotional tendency of the consultation information in the consultation knowledge module, combined with the historical data of the current user's previous consultations, the emotional pattern of the user's current consultation can be known. Identifying this obtained emotional pattern can know the current state of the user, and at the same time obtain other information of the consultation, such as the complexity, detail or urgency of the user's question, to judge the expected effect that can be achieved by answering the user's consultation at this time, so as to quantify the corresponding consultation degree information.

[0063] The implementation method of determining the emotional pattern of the user's consultation is to compare the emotional tendency of the consultation information with the historical data, determine the correlation between the emotional tendencies, and determine the change trend of the emotional tendency over time; according to the correlation between the emotional tendencies and the change trend of the emotional tendency, identify the emotional pattern corresponding to the current emotional tendency; use the identified emotional pattern as the output emotional pattern.

[0064] The method of determining the correlation between the emotional tendencies needs to convert the currently identified emotional tendency into an emotional score, calculate the correlation coefficient corresponding to the current emotional tendency according to the current emotional score and the emotional scores in the historical data, and use the calculated correlation coefficient as the correlation between the emotional tendencies.

[0065] ; where, represents the correlation coefficient corresponding to the current emotional tendency, represents the quantity of the current emotional score, , due to the situation of emotional tendency fluctuations during normal consultations, at this time, the values of each emotional score during the emotional tendency fluctuations are recorded, so as to judge the correlation coefficient corresponding to the corresponding score of the current emotional tendency, represents the current i-th emotional score, represents the i-th emotional score in the historical data, represents the average value of the current emotional scores, represents the average value of the emotional scores in the historical data.

[0066] For the average value of the current emotional scores selected at this time, by identifying multiple emotional scores after the transformation of the current emotional tendency, and then calculating the corresponding average value at this time; for the average value of the emotional scores selected from the historical data, it is determined based on the situation of the user's historical consultations, by averaging the emotional scores set for the user in history. If the user has never participated in psychological counseling, the average value of the emotional scores in the historical data selected at this time is the average value of the emotional scores obtained from the overall historical data corresponding to the current user's symptoms; to quantify the display situation of the user under different symptoms.

[0067] At this time, through the correlation coefficient, it is possible to judge a change in the user's own emotional tendency during the current interactive psychological counseling, as well as the corresponding correlation under this emotional tendency change, to determine whether the current user's state is the same as the historical data previously identified, and to assist in selecting the counseling method for the current user.

[0068] When identifying the change trend of the emotional tendency, what is mainly identified is the change in the emotional scores corresponding to the emotional tendency, so as to determine the change in the emotional tendency; first, identify the turning points when the emotional tendency changes, as well as the difference between the maximum and minimum values of the emotional scores corresponding to the emotional tendency within a fixed time. This difference is regarded as the basic difference, and the basic difference needs to be less than the size of the preset difference. The purpose of setting the basic difference is to judge the fluctuating change of the emotional tendency within a fixed time, so as to determine the stability of the emotions of the current consulting user; the range of this fixed time is set to 10 minutes, 30 minutes, 1 hour, and the specific selected range can also be adjusted according to the needs of the current user, to quantify the accuracy of the current user's processing.

[0069] Determine the change value of the emotional scores between the identified turning points of the emotional tendency. According to the change value of the emotional scores, determine the emotional pattern corresponding to the turning points, and take the emotional pattern with the highest occurrence probability in the emotional pattern as the emotional pattern output at this time.

[0070] The emotional pattern with the highest occurrence probability usually has a high representativeness and can better reflect the mainstream trend of the user's emotional state; the emotional pattern with the highest occurrence probability usually has a high representativeness and can better reflect the mainstream trend of the user's emotional state; at this time, it is necessary to focus on dealing with the user's emotional changes in the short term, so as to make timely processing according to the user's emotional changes in the short term.

[0071] Suppose the change trend of the user's emotional tendency is as follows: Turning point 1: Emotional score is -0.5; Turning point 2: Emotional score is -0.4; Turning point 3: Emotional score is -0.7 (the lowest point); Turning point 4: Emotional score is -0.6; Turning point 5: Emotional score is -0.3 (the highest point); Turning point 6: Emotional score is -0.5.

[0072] According to the above emotional scores, the following emotional patterns can be identified: Downward pattern: From turning point 1 to turning point 3, the emotional score drops from -0.5 to -0.7.

[0073] Upward pattern: From turning point 3 to turning point 5, the emotional score rises from -0.7 to -0.3.

[0074] Fluctuation pattern: From turning point 3 to turning point 6, the emotional score fluctuates between -0.7 and -0.5.

[0075] The implementation method of the consultation degree information is to extract the consultation questions of the current consultation information, and take the probability distribution of the user's consultation questions, the consultation time, and the level of the consultation questions as the consultation degree information.

[0076] The probability distribution of the user's consultation questions is obtained by calculating the proportion of the type corresponding to the current consultation question in the total consultation questions; the consultation time is to record the duration of the current user's consultation to determine how long the current user needs to communicate to complete a process of psychological consultation; the level of the consultation question indicates the level to which the current consultation question can be decomposed, and this level is used to refine the current consultation question enough to determine the essence of the consultation question. For example, the consultation question is disassembled into three levels, or more levels. The first level is the original question, the second level represents the main aspects in the consultation question, and the third level is the details and action steps corresponding to the main aspects. If the decomposition exceeds three levels, the first two levels are the same, and the third level is converted into a component of the main aspect. The fourth level can be the details in the component; if it is decomposed into two levels, the second level is the details in the original question, and so on. The number of levels currently selected will be adjusted according to the complexity of the consultation question.

[0077] Obtain the consultation plan. According to the emotional pattern and consultation degree information of the user's consultation, determine the user's preferences, classify the user's preferences; set priorities for various types of user preferences, and select the user's consultation plan based on the priorities within the user's preferences.

[0078] The implementation method of determining the user's preferences and classifying the user's preferences is as follows: Use the probability distribution of the user's consultation questions, consultation time, and the level of consultation questions in the consultation degree information as the classification basis to obtain the first classification list, and use the emotional pattern as the classification basis to obtain the second classification list; Compare the first classification list and the second classification list, compare the data in the first classification list with the data in the second classification list. At this time, the values of the data after classifying the emotional pattern and consultation degree information according to different situations are calculated. The comparison method is to calculate the Pearson correlation coefficient for these data, and use the classification list with the largest Pearson correlation coefficient value after comparison as the output classification list, and set priorities according to the comparison classification list. The set priorities are set according to the weighted average of the probability distribution of the user's consultation questions, consultation time, the level of consultation questions, and the corresponding weights of the emotional pattern in the classification list. At this time, a classification list will be obtained. Obtain the consultation plan corresponding to the output classification list, and select the consultation plan with the highest priority as the output consultation plan.

[0079] As Figure 3 shown, when obtaining the feedback evaluation plan, use the sum of the cosine features of the consultation plans in all consultation stages as the basic evaluation condition for the current feedback evaluation; when the basic evaluation condition meets the preset conditions, record the key factors that change during the consultation stage, perform component analysis on the key factors, obtain three groups of consultation plans, and splice the three groups of consultation plans to obtain the current feedback evaluation plan.

[0080] Consultation feedback is represented in the form of the achievement of the user's consultation goal, user satisfaction, behavior change, etc. in this plan. At this time, when dealing with the user in combination with the consultation feedback, the consultation plan with the changed consultation feedback will be used as the plan for processing at this time to determine what plan should be adopted for feedback after the user has made corresponding changes, so as to improve the targeted processing effect for different users.

[0081] The key factors that change during the consultation stage mainly include the change in the emotional pattern corresponding to each consultation stage of the user, and the change in the content of the questions the user wants to consult. At this time, the change in the emotion corresponding to the user's each consultation will be recorded, and the content most relevant to the emotion change will be used as the key factor identified at this time; that is to say, the key factor is the corresponding change in the following content.

[0082] Changes in the content of the consultation: the transfer of the consultation theme; the impact of specific events: major events or experiences that occur in life; changes in the emotional pattern: changing from one emotional pattern to another; adjustment of the consultation strategy: the counselor adjusts the consultation method according to the user's situation; use these contents as the analysis data for the feedback evaluation of the consultation plan implemented in all consultation stages.

[0083] The first group of consultation plans is reconstructed according to the dimensions of each consultation plan, and the first group of consultation plans is obtained recursively.

[0084] At this time, define the initial set of consultation plans, and subdivide each dimension. Generate new consultation plans according to the subdivided dimensions until the required consultation plans are reached.

[0085] Suppose the initial set of consultation plans is: short-term consultation, high-frequency problems, intermediate problems, stable mode; medium-term consultation, medium-frequency problems, intermediate problems, declining mode; long-term consultation, low-frequency problems, intermediate problems, rising mode.

[0086] Refine each dimension: consultation time: short-term -> short-term 1, short-term 2; medium-term -> medium-term 1, medium-term 2; long-term -> long-term 1, long-term 2.

[0087] Probability distribution of consultation problems: high-frequency -> high-frequency 1, high-frequency 2; medium-frequency -> medium-frequency 1, medium-frequency 2; low-frequency -> low-frequency 1, low-frequency 2.

[0088] Level of consultation problems: intermediate -> intermediate 1, intermediate 2; basic -> basic 1, basic 2; advanced -> advanced 1, advanced 2.

[0089] Emotional pattern: stable -> stable 1, stable 2; declining -> declining 1, declining 2; rising -> rising 1, rising 2; fluctuating -> fluctuating 1, fluctuating 2.

[0090] Generate new plans by combination: short-term 1, high-frequency 1, intermediate 1, stable 1; short-term 2, high-frequency 2, intermediate 2, stable 2; medium-term 1, medium-frequency 1, intermediate 1, declining 1; medium-term 2, medium-frequency 2, intermediate 2, declining 2; long-term 1, low-frequency 1, intermediate 1, rising 1; long-term 2, low-frequency 2, intermediate 2, rising 2.

[0091] Repeat the above process until each dimension is fully subdivided to form the first group of consultation plans.

[0092] The second group of consultation plans is reconstructed and recursively obtained according to the probability of the key factors appearing in each consultation plan.

[0093] At this time, define the initial set of consultation plans, and then count the probability of each key factor appearing. Screen according to the obtained key factors until the calculation indexes of each key factor reach the target values.

[0094] Suppose the initial set of consultation plans is: short-term consultation, high-frequency problems, medium-level problems, stable mode.

[0095] Medium-term consultation, medium-frequency problems, medium-level problems, declining mode.

[0096] Long-term consultation, low-frequency problems, medium-level problems, rising mode.

[0097] Calculate the probabilities of key factors: Specific events: family conflict 0.3, work pressure 0.5, interpersonal relationship 0.2.

[0098] Consultation topics: mental health 0.6, academic tutoring 0.3, career planning 0.1.

[0099] Emotional patterns: stable mode 0.4, declining mode 0.3, rising mode 0.2, fluctuating mode 0.1.

[0100] Filter out the consultation plans most relevant to the key factors according to the probabilities, such as: related to work pressure: medium-term consultation, high-frequency problems, medium-level problems, declining mode.

[0101] Related to mental health: long-term consultation, low-frequency problems, medium-level problems, stable mode.

[0102] Repeat the above process until each key factor is fully filtered and reconstructed to form the second set of consultation plans.

[0103] At this time, the way to require that the calculation indicators of each key factor reach the target value is to calculate the filtered consultation plans with the standard plans, and determine that the Pearson correlation coefficient between the index values corresponding to the components in the selected plans at this time and the index values of the standard plans can take the maximum value, and iterate in turn until all the consultation plans are reconstructed.

[0104] Extract the key components from the first set of consultation plans and the second set of consultation plans for the third set of consultation plans, map the obtained key components, and determine the influence range corresponding to each mapped key component; set the consultation plans whose influence range meets the initial set range as the third set of consultation plans.

[0105] At this time, define the initial set of consultation plans, extract the key components from the first set of consultation plans and the second set of consultation plans, determine the influence range according to the key components, and filter out the consultation plans whose influence range meets the initial set range.

[0106] Suppose the key components are: consultation time: short-term, medium-term, long-term.

[0107] Probability distribution of consultation problems: high-frequency, medium-frequency, low-frequency.

[0108] Levels of consultation questions: basic, intermediate, advanced.

[0109] Emotional patterns: stable, decreasing, increasing, fluctuating.

[0110] Determine the scope of influence: Consultation time: short-term (≤1 month), medium-term (1 - 6 months), long-term (>6 months).

[0111] Probability distribution of consultation questions: high-frequency (≥50%), medium-frequency (20% - 50%), low-frequency (<20%).

[0112] Levels of consultation questions: basic (simple), intermediate (medium), advanced (complex).

[0113] Emotional patterns: stable (fluctuation ≤ ±0.2), decreasing (fluctuation ≤ -0.5), increasing (fluctuation ≥ +0.5), fluctuating (fluctuation ≥ ±0.5).

[0114] Filter out eligible consultation plans according to the scope of influence, such as: short-term consultation (≤1 month), high-frequency questions (≥50%), intermediate questions (medium), stable pattern (fluctuation ≤ ±0.2); finally form the third group of consultation plans.

[0115] Convert the obtained first group of consultation plans, second group of consultation plans, and third group of consultation plans into feature vectors, and take the plan with the shortest distance between the feature vectors in the three groups of consultation plans as the feedback evaluation plan for the final output.

[0116] At this time, calculate the mutual distance between the transformed feature vectors, and calculate the distance d1 between the feature vectors of the first group of consultation plans and the second group of consultation plans, the distance d2 between the feature vectors of the second group of consultation plans and the third group of consultation plans, and the distance d3 between the feature vectors of the first group of consultation plans and the third group of consultation plans. Output the consultation plan corresponding to the feature vector when the sum of the distances d1, d2, and d3 takes the minimum value to obtain the final feedback evaluation plan.

[0117] This final plan can combine the changes of users in different consultation stages to generate a more comprehensive and more suitable consultation plan for users to adjust themselves, improve the effect of user consultation, and guide users and adjust their mental state in a timely manner during the interaction with users.

[0118] The cosine feature sum of the consultation plans in all consultation stages is to convert the consultation plans set in all consultation stages into vectors, calculate the cosine similarity of each vector. At this time, each consultation plan will convert the consultation features in the consultation plan into multiple vectors, calculate the cosine similarity between the current consultation plan and the vectors of the standard consultation plan one by one, and after summing up the calculated cosine similarities, the cosine feature sum of the consultation plan can be obtained.

[0119] The preset conditions set for the basic evaluation conditions require the cosine features of the consultation plan and can be greater than the values set in the preset conditions. For example, obtain the vector of the consultation time , the vector of the probability distribution of the consultation questions , the vector of the levels of the consultation questions , the vector of the emotional patterns ; Calculate the cosine similarities corresponding to these four vectors in sequence.

[0120] ; Among them, represents the cosine similarity of the consultation time, represents the standard vector of the consultation time.

[0121] The calculation methods of the cosine similarities for the probability distribution of the consultation questions, the levels of the consultation questions, and the emotional patterns are the same as the above formula, and will not be listed one by one here; after calculating these four cosine similarities, sum them to obtain the corresponding cosine feature sum. At the same time, for the preset conditions set at this time, each cosine similarity to be calculated must be greater than 0.6, and the cosine feature sum must be greater than 2.8 to verify whether the consultation plan used in each stage meets the requirements.

[0122] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention, and still be covered by the protection scope of the present invention.

Claims

1. An interactive psychological consultation conversation system, characterized in that: include: The dialogue management module is used to receive the current user's consultation information and determine the context flow and sequence of the user's consultation; The language processing module is used to analyze the consultation information and understand the emotional tendency expressed by the current user; The consultation knowledge module is used to obtain the historical data of user consultations and determine the emotional pattern and consultation degree information of the user consultations in combination with the emotional tendency of the consultation information; Determining the sentiment pattern of user consultation includes: comparing the sentiment tendency of consultation information with historical data, determining the correlation between sentiment tendencies, and determining the changing trend of sentiment tendencies over time; Determining the correlation between sentiment tendencies includes: converting the currently identified sentiment tendency into a sentiment score, and calculating the Pearson correlation coefficient corresponding to the current sentiment tendency based on the current sentiment score and the sentiment score in the historical data. ,Will As a correlation between emotional tendencies: When identifying the changing trend of the emotional tendency, first identify the turning point when the emotional tendency changes, and the extreme difference value of the emotional score corresponding to the emotional tendency within a fixed time, and the difference value is less than the preset difference value; determine the change value of the emotional score between the identified turning points of the emotional tendency, and determine the emotional pattern corresponding to the turning point according to the change value of the emotional score, and use the emotional pattern with the highest probability of appearing in the emotional pattern as the emotional pattern output at this time; The consultation degree information includes the probability distribution of users’ consultation questions, consultation time and the level of consultation questions; The consultation recommendation module uses the probability distribution of the user's consultation questions, the consultation time, and the level of the consultation questions as the classification basis to obtain the first classification list, and uses the emotional pattern as the classification basis to obtain the second classification list; compares the data in the first classification list with the data in the second classification list, and uses the classification list with the largest Pearson correlation coefficient after comparison as the output classification list, and sets the priority according to the compared classification list. The set priority is set according to the weighted average of the corresponding weights of the probability distribution of the user's consultation questions, the consultation time, the level of the consultation questions, and the emotional pattern in the classification list, obtains the consultation plan corresponding to the output classification list, and selects the consultation plan with the largest priority as the output consultation plan; The consultation feedback module is used to obtain consultation feedback after the implementation of the consultation plan, and extract the consultation stage of the current user from the consultation plan, and combine the consultation plan and consultation feedback of each consultation stage to obtain the feedback evaluation plan of the current user.

2. The interactive psychological consultation conversation system according to claim 1, characterized in that: The implementation method of determining the context flow and sequence of user consultation also includes: monitoring the changes in the intention of each round of dialogue during user consultation, and recording the scene of the conversation, the user's emotional state and time.

3. The interactive psychological consultation conversation system according to claim 1, characterized in that: The language processing module analyzes the consulting information and understands the emotional tendency expressed by the current user in the following manner: obtaining the user's preliminary verification information, and determining the user's psychological counseling index based on the preliminary verification information; extracting the first key information from the consulting information based on the obtained preliminary verification information, and determining the user's corresponding confession bias index based on the first key information; determining the user's related symptom matching index based on the confession bias index; and translating the current user's consulting information based on the obtained symptom matching index to obtain the emotional tendency expressed by the user.

4. The interactive psychological consultation conversation system according to claim 3 is characterized in that: The method of extracting the first key information from the consulting information according to the obtained preliminary verification information is to obtain information in the consulting information corresponding to the preliminary verification information as the first key information according to the obtained preliminary verification information; Verify whether the classification of the consulting information is the same as that of the corresponding information in the preliminary verification information. If they are the same, verify the frequency of occurrence of the corresponding words in the consulting information, and sort the recognized words according to the frequency of occurrence of the words to form the first key information; Based on the first key information, the implementation method of determining the user's corresponding confession bias index is to set the emotional tendency score, the help-seeking bias score, the information sharing tendency score, and the problem-oriented score according to the user's consulting information, and take the weighted average of the emotional tendency score, the help-seeking bias score, the information sharing tendency score, and the problem-oriented score as the output confession bias index.

5. The interactive psychological consultation conversation system according to claim 1, characterized in that: The Pearson correlation coefficient corresponding to the current sentiment tendency is calculated as follows: ； represents the number of current sentiment scores, , represents the current i-th sentiment score, represents the i-th sentiment score in the historical data, represents the average value of the current sentiment score, Represents the average of sentiment scores in historical data.

6. The interactive psychological consultation conversation system according to claim 1, characterized in that: Feedback evaluation plans can be obtained by: The sum of the cosine characteristics of the consulting solutions in all consulting stages is used as the basic evaluation condition for the feedback evaluation at this time; when the basic evaluation condition meets the preset conditions, the key factors that have changed in the consulting stage are recorded, and the key factors are analyzed for components to obtain three groups of consulting solutions. The consulting solution after splicing the three groups of consulting solutions is obtained to obtain the current feedback evaluation solution; The first set of consulting solutions is reconstructed according to the dimensions of each consulting solution, and the first set of consulting solutions is obtained recursively; The second group of consulting solutions is reconstructed recursively according to the probability of the key factors appearing in each consulting solution, and the second group of consulting solutions is obtained; The third group of consulting solutions extracts key components from the first and second groups of consulting solutions, maps the obtained key components, and determines the impact range corresponding to each mapped key component; and sets the consulting solutions whose impact ranges meet the initially set range as the third group of consulting solutions; The first, second and third consulting solutions are converted into feature vectors, and the solution with the shortest feature vector distance among the three consulting solutions is used as the final output feedback evaluation solution.

Images