A method and system for replying to conversation scripts in online psychological counseling

Abstract

The present invention relates to the technical field of online psychological counseling, and specifically to a method and system for replying to conversation techniques in online psychological counseling, including the following steps: Based on the original data of emotional states and psychological counseling needs, symbols are assigned to different states and needs, and the data is subjected to initialization coding processing to generate an initial framework of the symbol set. In the present invention, by initializing coding and optimizing symbols to accurately map conversation strategies, losses during the information transmission process are effectively avoided, making the information exchange during the counseling process smoother and more accurate. Continuous analysis and iterative adjustment of the information transmission efficiency contribute to continuously optimizing the reply strategy and improving the overall counseling quality. By simulating the psychological impacts of different conversation strategies and drawing impact maps, potential psychological risks can be accurately predicted and avoided, ensuring that the counseling service can better meet the actual needs of the seekers, strengthening the implementation of personalized services, and promoting the mental health of users.

Description

Technical Field

[0001] The present invention relates to the technical field of online psychological counseling, and particularly to a method and system for replying to conversation words in online psychological counseling. Background Art

[0002] The technical field of online psychological counseling involves using Internet technologies to provide mental health services and support, including psychotherapy and counseling services through video conferencing, instant messaging software, email, and web platforms. The application of the technology allows professionals to remotely reach out to clients, breaking geographical and time limitations and providing more flexible and accessible mental health resources. With the development and popularization of Internet technologies, online psychological counseling has become an important means to improve public mental health levels, especially in densely populated or remote areas. This includes the development of related software and tools aimed at enhancing counseling efficiency and quality, such as using artificial intelligence to analyze user emotions or provide initial mental health assessments.

[0003] Among them, the method for replying to conversation words in online psychological counseling refers to a specific communication technique or strategy used during online psychological counseling. This method aims to enhance the communication effect, improve the responsiveness and personalization of counseling through carefully designed reply words. The purpose is to more effectively support and guide clients, help them feel understood and supported in a virtual environment, and promote psychological recovery and health improvement. It not only helps improve the work efficiency of counselors but also enhances the security and privacy of services, and is an important part of modern online psychological counseling services.

[0004] Existing online psychological counseling technologies provide flexible and extensive access methods, but they have deficiencies in personalized services and responsiveness. Existing technologies rely on standardized replies and procedures, lacking in-depth analysis of individual differences and immediate emotional changes of clients, resulting in insufficient personalization and precision in counseling. The information transmission efficiency has not been finely optimized, leading to the actual needs of clients not being fully understood and met, affecting the effectiveness of counseling and the satisfaction of clients. The deficiencies in existing technologies are particularly significant when dealing with complex emotions and psychological states, resulting in misunderstandings and information transmission errors during the counseling process, affecting the trust of clients and the overall quality of counseling. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art, and to propose a method and system for replying to conversation words in online psychological counseling.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions. A method for replying to conversation words in online psychological counseling includes the following steps:

[0007] S1: Based on the original data of emotional states and psychological counseling needs, assign symbols to different states and needs, and perform initial encoding processing on the data to generate an initial framework of the symbol set;

[0008] S2: Using the initial framework of the symbol set, analyze the representativeness and distinctiveness of each symbol in the symbol set, divide and merge the symbols to optimize the uniqueness of the symbols, and obtain an optimized symbol set;

[0009] S3: Through the optimized symbol set, construct the mapping relationship from symbols to conversation strategies, integrate the symbols and corresponding conversations, and generate an encoding mapping table through item-by-item verification;

[0010] S4: Using the encoding mapping table, analyze the information transmission efficiency of conversation responses, and avoid information loss by iteratively adjusting the mapping relationship in the mapping table to generate an analysis result of information transmission efficiency;

[0011] S5: Using the analysis result of information transmission efficiency, simulate the psychological impact of different conversation strategies according to conversation data and psychological risk assessment indicators, draw a psychological impact map, and obtain a psychological impact prediction model;

[0012] S6: Through the psychological impact prediction model, analyze the psychological risks of conversation strategies, compare the prediction results with the risk acceptance threshold, adjust the conversation strategies in the mapping table, avoid psychological risks, and generate a strategy adjustment result.

[0013] As a further solution of the present invention, the initial framework of the symbol set includes emoji based on different emotions, descriptive labels of psychological needs, and associated initial encodings. The optimized symbol set includes symbols that distinguish different psychological states, hierarchical symbols of emotions, and optimized behavior indication symbols. The encoding mapping table includes the degree of association between symbols and conversations, the classification of application scenarios of conversations, and the expected feedback types of conversation effects. The analysis result of information transmission efficiency includes the response time of conversations, information coverage rate, and customer satisfaction indicators. The psychological impact prediction model includes an emotion change prediction map, a psychological stability index, and a predicted user behavior response pattern. The strategy adjustment result includes modified conversation coping strategies, risk threshold adjustment parameters, and newly introduced warning mechanisms.

[0014] As a further solution of the present invention, the steps of assigning symbols to different states and needs and performing initial encoding processing on the data based on the original data of emotional states and psychological counseling needs to generate an initial framework of the symbol set are specifically as follows:

[0015] S101: Collect the original data of emotional states and psychological counseling needs, assign unique identifiers to data items, record the source and timestamp, and generate a data identification framework;

[0016] S102: Based on the data recognition framework, identify the key variables in the data, including emotional fluctuations and consultation frequencies, perform frequency and pattern analysis on the variables, extract key features, and generate a key feature index;

[0017] S103: Using the key feature index, assign symbols to different emotional states and psychological needs, mark and classify the data, and generate an initial framework of the symbol set.

[0018] As a further solution of the present invention, the steps of using the initial framework of the symbol set to analyze the representativeness and distinctiveness of each symbol in the symbol set, divide and merge the symbols, and optimize the uniqueness of the symbols to obtain the optimized symbol set are specifically as follows:

[0019] S201: Using the initial framework of the symbol set, perform statistical analysis on the frequency and distribution of each symbol, record the number of symbols and rare symbols, analyze the application of the symbols in different emotional states and psychological needs, and generate a symbol analysis result;

[0020] S202: Based on the symbol analysis result, evaluate the representativeness and distinctiveness of the symbols, merge the symbols with low distinctiveness, divide the symbols with high frequency but low representativeness, and check that each symbol has a definite and unique representational meaning, and generate a symbol optimization plan;

[0021] S203: Implement the symbol optimization plan, readjust and encode the symbol set, and through iterative data encoding and symbol adjustment, check the emotional state and psychological counseling needs of each symbol for the target, and generate an optimized symbol set.

[0022] As a further solution of the present invention, the steps of constructing a mapping relationship from symbols to conversation strategies through the optimized symbol set, integrating symbols and corresponding conversations, and checking item by item to generate a coding mapping table are specifically as follows:

[0023] S301: Using the optimized symbol set, associate each symbol with the target conversation strategy, and the conversation strategy is customized according to the emotional state and psychological needs represented by the symbol, and verify that each symbol has a corresponding response conversation, and generate an initial mapping relationship;

[0024] S302: Integrate and optimize the initial mapping relationship, pair the symbols and corresponding conversations according to the real-time application scenario and logical relationship, check and solve the existing conflicts, and verify the practicality of the mapping relationship, and generate a verified mapping relationship;

[0025] S303: According to the verified mapping relationship, record each symbol and the corresponding conversation strategy, and perform verification and adjustment, including the definition of each symbol and the paired conversation, and generate a coding mapping table.

[0026] As a further solution of the present invention, using the encoding mapping table, analyzing the information transmission efficiency of the conversation reply, and generating the information transmission efficiency analysis result by iteratively adjusting the mapping relationship in the mapping table to avoid information loss, the specific steps are as follows:

[0027] S401: Based on the encoding mapping table, implement an initial information transmission efficiency test. By simulating scenarios and user feedback, evaluate the reply speed and user parsing degree of different conversation strategies, identify delays and ambiguity points in information transmission, and generate an initial efficiency analysis result;

[0028] S402: According to the initial efficiency analysis result, iteratively adjust the mapping relationship from symbols to conversation strategies in the mapping table, optimize the conversation strategies that cause information delays and misunderstandings, and adjust the conversation content through real-time data and user behavior analysis to generate an adjusted mapping relationship;

[0029] S403: Apply the adjusted mapping relationship, perform the information transmission efficiency test again, compare the improvement effects before and after, verify information loss and optimize the efficiency of conversation replies, and generate an information transmission efficiency analysis result.

[0030] As a further solution of the present invention, adopting the information transmission efficiency analysis result, according to conversation data and psychological risk assessment indicators, simulating the psychological impact of different conversation strategies, and drawing a psychological impact map to obtain the specific steps of the psychological impact prediction model are as follows:

[0031] S501: Use the information transmission efficiency analysis result, combine conversation data and psychological risk assessment indicators, set simulation parameters to evaluate the psychological impact caused by different conversation strategies in real-time scenarios, including anxiety caused by comfort level and incentive effect, and generate initial simulation data of psychological impact;

[0032] S502: Based on the initial simulation data of psychological impact, use data visualization tools to evaluate the psychological impacts corresponding to multiple conversation strategies, analyze the intensity and scope of the psychological impacts corresponding to different conversation strategies, and check the psychological effects of each strategy to generate a psychological impact map;

[0033] S503: According to the psychological impact map, analyze the relationship between conversation strategies and psychological reactions, predict the psychological impacts of different conversation strategies, verify the real-time adjustment and optimization of the model for conversations, match the psychological state of users, and generate a psychological impact prediction model.

[0034] As a further solution of the present invention, through the psychological impact prediction model, analyzing the psychological risks of conversation strategies, comparing the prediction results with the risk acceptance threshold, adjusting the conversation strategies in the mapping table, avoiding psychological risks, and generating the specific steps of the strategy adjustment result are as follows:

[0035] S601: Using the described psychological impact prediction model and the multiple linear regression algorithm, evaluate the psychological risks of the differentiated conversation strategy, including quantifying the changes in emotional instability and sense of stress, and generate the risk assessment result of the conversation strategy;

[0036] S602: Compare the predicted risk value in the risk assessment result of the conversation strategy with the pre-set risk acceptance threshold, identify the conversation strategies that exceed the threshold, analyze the risk sources and impact degrees of the strategies, and generate the analysis result of the conversation strategies with excessive risks;

[0037] S603: Based on the analysis result of the conversation strategies with excessive risks, adjust the conversation strategies in the mapping table, optimize and replace the conversations that cause psychological risks, avoid potential negative impacts, rebalance the relationship between the conversation strategy and the user's psychological safety, and generate the strategy adjustment result.

[0038] As a further solution of the present invention, the formula of the multiple linear regression algorithm is as follows:

[0039]

[0040] Among them, R is the psychological risk score value, β0 represents the intercept of the regression model, β1 represents the weight parameter of emotional instability, E represents the measured value of emotional instability, β2 represents the weight parameter of the change in sense of stress, S represents the change amount of sense of stress, T represents the conversation duration, β3 represents the weight parameter of the complexity of the conversation strategy, and C represents the complexity of the conversation strategy.

[0041] A conversation reply system for online psychological counseling, the conversation reply system for online psychological counseling is used to execute the above-mentioned conversation reply method for online psychological counseling, and the system includes:

[0042] The data encoding module collects the data of psychological counseling needs and emotional states, encodes the data, assigns target symbols, and generates the initial framework of the symbol set;

[0043] The symbol mapping module analyzes the representativeness and distinguishability of the differentiated symbols based on the initial framework of the symbol set, combines the same type of symbols and divides the different symbols, and obtains the optimized symbol set;

[0044] The conversation strategy module uses the optimized symbol set to establish the mapping relationship from symbols to conversation strategies, verifies the mapping relationship item by item, checks the adaptability of the conversations, and constructs the conversation mapping table;

[0045] The transmission efficiency processing module analyzes the information transmission efficiency through the conversation mapping table, iteratively adjusts the mapping table, verifies the speed and efficiency of information transmission through data analysis, and generates the information efficiency analysis result;

[0046] Based on the information efficiency analysis results, the psychological risk assessment module combines the conversation script data and psychological risk assessment indicators, simulates the psychological impact of different conversation script strategies, and generates strategy adjustment results.

[0047] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0048] In the present invention, by refining and encoding the emotional states and needs in psychological counseling, the uniqueness of symbols is optimized, significantly improving the pertinence and efficiency of conversation script responses. By initializing the encoding and symbol optimization to accurately map the conversation script strategies, the loss during the information transmission process is effectively avoided, making the information exchange during the counseling process smoother and more accurate. The continuous analysis and iterative adjustment of the information transmission efficiency contribute to continuously optimizing the response strategies and improving the overall counseling quality. By simulating the psychological impact of different conversation script strategies and drawing the impact map, potential psychological risks can be accurately predicted and avoided, enhancing the security of the service. The adjustment and optimization process of the system ensure that the counseling service can better meet the actual needs of the applicants seeking help, strengthen the implementation of personalized services, and promote the mental health of users. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 is a schematic diagram of the working process of the present invention;

[0050] Figure 2 is a detailed flowchart of S1 of the present invention;

[0051] Figure 3 is a detailed flowchart of S2 of the present invention;

[0052] Figure 4 is a detailed flowchart of S3 of the present invention;

[0053] Figure 5 is a detailed flowchart of S4 of the present invention;

[0054] Figure 6 is a detailed flowchart of S5 of the present invention;

[0055] Figure 7 is a detailed flowchart of S6 of the present invention;

[0056] Figure 8 is a system flowchart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0058] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by terms such as "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more, unless otherwise specifically defined.

[0059] Please refer to Figure 1 , the present invention provides a technical solution, a method for replying to conversation words in online psychological counseling, including the following steps:

[0060] S1: Based on the original data of emotional state and psychological counseling needs, assign symbols to the differential states and needs, and perform initialization encoding processing on the data to generate an initial framework of the symbol set;

[0061] S2: Adopt the initial framework of the symbol set, analyze the representativeness and distinctiveness of each symbol in the symbol set, divide and merge the symbols, optimize the uniqueness of the symbols, and obtain an optimized symbol set;

[0062] S3: Through the optimized symbol set, construct a mapping relationship from symbols to conversation strategies, integrate symbols and corresponding conversation words, and check item by item to generate a coding mapping table;

[0063] S4: Utilize the coding mapping table to analyze the information transmission efficiency of the conversation reply, and avoid information loss by iteratively adjusting the mapping relationship in the mapping table to generate an information transmission efficiency analysis result;

[0064] S5: Adopt the information transmission efficiency analysis result, simulate the psychological impact of differential conversation strategies according to conversation data and psychological risk assessment indicators, draw a psychological impact map, and obtain a psychological impact prediction model;

[0065] S6: Through the psychological impact prediction model, analyze the psychological risks of the conversation strategies, compare the prediction results with the risk acceptance threshold, adjust the conversation strategies in the mapping table, avoid psychological risks, and generate a strategy adjustment result.

[0066] The initial framework of the symbol set includes emojis based on differentiated emotions, descriptive labels of psychological needs, and associated initialization codes. The optimized symbol set includes symbols for differentiating psychological states, hierarchical symbols of emotions, and optimized behavior indication symbols. The coding mapping table includes the degree of association between symbols and speech, the classification of application scenarios of speech, and the expected feedback type of speech effects. The analysis results of information transmission efficiency include the response time of speech, information coverage rate, and customer satisfaction indicators. The psychological impact prediction model includes an emotion change prediction map, a psychological stability index, and a predicted user behavior response pattern. The strategy adjustment results include modified speech coping strategies, risk threshold adjustment parameters, and newly introduced warning mechanisms.

[0067] Please refer to Figure 2 , based on the original data of emotional states and psychological counseling needs, allocate symbols for differentiated states and needs, and perform initialization coding processing on the data. The specific steps for generating the initial framework of the symbol set are as follows:

[0068] S101: Collect the original data of emotional states and psychological counseling needs, assign a unique identifier to each data item, record the source and timestamp, and the execution process for generating the data identification framework is as follows;

[0069] During the process of collecting the original data of emotional states and psychological counseling needs, it is necessary to determine the source and type of the data. For example, obtain data through questionnaires, online platform interactions, or direct face-to-face counseling sessions. Classify the collected data in detail according to the specific content of emotional states and counseling needs, assign a unique identifier for future tracking and analysis, and recording the timestamp of the data is crucial because it can help researchers identify the specific time point of data collection, analyze the changing trend of emotional states, or the timeliness of psychological counseling. The process involves formatting and standardizing the data output to ensure that the data can be correctly recognized and utilized by the system in subsequent processing. The accuracy of data identification and classification directly affects the quality of data analysis and the effectiveness of data-driven decision-making, generating a data identification framework.

[0070] S102: Based on the data identification framework, identify the key variables in the data, including emotional fluctuations and counseling frequencies, perform frequency and pattern analysis on the variables, and extract key features. The execution process for generating the key feature index is as follows;

[0071] Identify the key variables in the data and calculate the variance of emotional fluctuations according to the formula where x i represents the emotional state value recorded in a single counseling session, represents the average emotional state value, and N represents the total number of counseling sessions.

[0072] Detailed formula explanation and formula calculation derivation process: Considering that the recognition of emotional fluctuations and consultation frequency is achieved by analyzing the fluctuation patterns in time series data, the variance formula can be used to measure the degree of emotional state fluctuations. By collecting emotional state data within a certain time period, such as daily emotional records within a week, if there are seven records, then N = 7. Let the emotional state of each record be x1, x2,..., x7, and calculate the average value each x i Subtract The sum of the squared differences after subtraction is then divided by N to obtain the variance F of emotional fluctuations.

[0073] For example, if the emotional records within a week are 4, 5, 3, 4, 4, 5, 3, then the average value is The variance F is calculated as follows:

[0074]

[0075] The results show that the emotional state is relatively stable within this week and the volatility is not large.

[0076] S103: Adopt key feature indexing, assign symbols to differentiated emotional states and psychological needs, mark and classify the data, and the execution process of generating the initial framework of the symbol set is as follows;

[0077] Assign symbols to differentiated emotional states and psychological needs. By symbolically marking each category of data, the efficiency and accuracy of data processing can be improved, including the identification of each category of emotional state and psychological need. During the process, various data classification techniques will be used, such as cluster analysis, to ensure that each emotional state and need is properly identified and classified. The symbols assigned to each emotional state and psychological need need to have a certain logic and recognizability to facilitate subsequent data analysis and application. The classified data will be sorted according to the symbol set and stored in the database. When conducting subsequent data query and analysis, relevant data can be directly retrieved through symbols, accelerating the data processing speed and improving work efficiency, thus generating the initial framework of the symbol set.

[0078] Please refer to Figure 3 and adopt the initial framework of the symbol set. The steps to analyze the representativeness and distinctiveness of each symbol in the symbol set, divide and merge the symbols, and optimize the uniqueness of the symbols to obtain the optimized symbol set are as follows:

[0079] S201: Use the initial framework of the symbol set to conduct statistical analysis on the frequency and distribution of each symbol, record the number of symbols and rare symbols, analyze the application of symbols in differentiated emotional states and psychological needs, and the execution process of generating the symbol analysis results is as follows;

[0080] Using the initial framework of the symbol set, statistical analysis of the frequency and distribution of each symbol is carried out. The process includes collecting the number of times each symbol appears in the database and its distribution in different emotional states and psychological needs. Symbols with high frequency but low representativeness or unclear specific meaning can be identified, and rare but significant symbols can also be discovered. The results of the statistical analysis will record the total number of symbols and the specific quantity of each symbol, providing decision-making support for subsequent symbol optimization to more accurately reflect different emotional states and psychological needs. The statistical analysis of symbols not only helps to understand the distribution characteristics of the data but also provides a basis for further data processing and analysis. For example, in subsequent processing, the structure of the data set can be adjusted according to the distribution and frequency of symbols to enhance the representativeness and discrimination of the data set, resulting in an optimized symbol set.

[0081] S202: Based on the symbol analysis results, evaluate the representativeness and discrimination of symbols, merge symbols with low discrimination, divide symbols with high frequency but low representativeness, and check that each symbol has a definite and unique representational meaning. The execution process of generating the symbol optimization plan is as follows;

[0082] Based on the symbol analysis results, optimize the symbols, including merging symbols with low discrimination and splitting symbols with high frequency but low representativeness, to ensure that each symbol can accurately represent a specific emotional state or psychological need. The steps involve evaluating the functionality and practicality of the symbols. In this way, the efficiency and practicality of the symbol set can be improved. During the evaluation process, special attention will be paid to symbols that frequently appear in multiple categories but have ambiguous meanings. If symbols cannot effectively distinguish different situations, it will lead to misunderstandings in data analysis, including redefining or adjusting the symbols to ensure that each symbol can play its due role in the analysis, improving the accuracy and efficiency of data processing, and generating a symbol optimization plan.

[0083] S203: Implement the symbol optimization plan, readjust and encode the symbol set. Through iterative data encoding and symbol adjustment, check the emotional state and psychological counseling needs of each symbol for the target. The execution process of generating the optimized symbol set is as follows;

[0084] Implement a symbol optimization solution. By readjusting and encoding the existing symbol set, ensure that each symbol can more accurately reflect the represented emotional state or psychological need. The process includes iterative data encoding and symbol adjustment, and ensuring that each adjustment can improve the utility of the symbol set through testing and verification. It will serve the needs analysis of emotional states and psychological counseling more precisely and effectively. The technologies involved in the re-encoded symbol set include data classification, cluster analysis, and pattern recognition, etc. The adjustment of each symbol is based on its performance in actual applications and the matching degree with the emotional states and psychological needs of the target group. The optimization process ensures that each symbol has a unique and definite representational meaning, improves the performance and reliability of the entire data analysis system, and generates an optimized symbol set.

[0085] Please refer to Figure 4 , through the optimized symbol set, construct the mapping relationship from symbols to conversation strategies, integrate symbols and corresponding conversations, and verify item by item. The specific steps for generating the coding mapping table are as follows:

[0086] S301: Adopt the optimized symbol set, associate each symbol with the target conversation strategy. The conversation strategy is customized according to the emotional state and psychological need represented by the symbol. Verify that each symbol has a corresponding response conversation. The execution process for generating the initial mapping relationship is as follows;

[0087] Adopt the optimized symbol set, associate a customized conversation strategy with each symbol. The strategy is carefully designed according to the emotional state and psychological need represented by the symbol to ensure that each symbol has an appropriate response conversation. The process includes the compilation of conversation content and the corresponding setting of symbols. The verification process ensures that the matching between each symbol and the conversation is accurate, provides a preliminary link framework from symbols to conversations, and the framework provides a basis for subsequent optimization and application. The generation of the initial mapping is a dynamic process, involving repeated testing and adjustment to ensure that the conversation can effectively reflect the emotions and needs represented by the symbol. Such a matching is crucial for interactions and user satisfaction in actual applications, and generates the initial mapping relationship.

[0088] S302: Integrate and optimize the initial mapping relationship, pair the symbols and corresponding conversations according to the real-time application scenario and logical relationship, check and resolve existing conflicts, and verify the practicality of the mapping relationship. The execution process for generating the verified mapping relationship is as follows;

[0089] Integrate and optimize the initialized mapping relationship. The steps involve effectively pairing symbols with corresponding discourse strategies according to real-time application scenarios and logical relationships, checking and resolving existing conflicts to ensure the mapping relationship remains consistent and practical in various application scenarios. During the optimization process, special attention is paid to adjusting the discourse that performs poorly due to changes in scenarios, ensuring that the discourse for each symbol can work effectively in different situations. Systematic checking and adjustment help improve the adaptability of the entire system and the quality of user interaction. It is a confirmation of the relationship between symbols and discourse, ensuring that the relationship can achieve the best effect in actual use, and generating a verified mapping relationship.

[0090] S303: According to the verified mapping relationship, record each symbol and its corresponding discourse strategy, and perform verification and adjustment, including the definition of each symbol and the paired discourse. The execution process of generating the coding mapping table is as follows;

[0091] According to the verified mapping relationship, record and adjust each symbol and its corresponding discourse strategy, including the detailed definition of the symbol and the compilation of the discourse content. The adjustment process ensures that the definition of each symbol is accurate and that each discourse can effectively express the meaning of the symbol and meet the needs of users. It is used to guide future applications and system development. It not only records the corresponding relationship between each symbol and discourse, but also includes the usage instructions of the symbol and discourse in different situations. Recording and adjustment are to ensure that the system can efficiently and accurately reflect the emotions and needs of users during actual operation, improve the user experience and the application value of the system, and generate a coding mapping table.

[0092] Please refer to Figure 5 , using the coding mapping table, analyze the information transfer efficiency of the discourse reply. By iteratively adjusting the mapping relationship in the mapping table to avoid information loss, the steps for generating the information transfer efficiency analysis result are specifically as follows:

[0093] S401: Based on the coding mapping table, implement an initial information transfer efficiency test. By simulating scenarios and user feedback, evaluate the reply speed and user parsing degree of different discourse strategies, identify delays and ambiguity points in information transfer, and the execution process of generating the initial efficiency analysis result is as follows;

[0094] Based on the coding mapping table, conduct an initial information transfer efficiency test, including testing the response time of each symbol and conversation strategy and the user's understanding level in a simulated scenario. During the evaluation, special attention will be paid to identifying factors that cause information delay and ambiguity. The test process evaluates the actual effect of the conversation strategy by simulating the interaction between the user and the system, and details of the problems and reasons found during the test will be recorded to provide a basis for subsequent adjustments. The efficiency test is a crucial step to help determine that the conversation strategy needs further optimization in actual application to improve the speed and accuracy of information transfer, which not only relates to the user experience but also directly affects the operation efficiency of the system, and generate the initial efficiency analysis result.

[0095] S402: According to the initial efficiency analysis result, iteratively adjust the mapping relationship from symbols to conversations in the mapping table, optimize the conversation strategies that cause information delay and misunderstanding. Through real-time data and user behavior analysis, adjust the conversation content. The execution process of generating the adjusted mapping relationship is as follows;

[0096] According to the initial efficiency analysis result, iteratively adjust the mapping relationship from symbols to conversations in the mapping table, including analyzing the specific conversation strategies that cause information delay and misunderstanding, and optimizing based on in-depth analysis of real-time data and user behavior. The adjustment process not only focuses on improving the clarity and precision of the conversation but also includes adjusting the structure and expression of the conversation content to adapt to different interaction scenarios and user needs, ensuring that information transfer is more efficient and unambiguous. The data-based iterative adjustment is a key link to ensure the adaptability and flexibility of the system. Through adjustment, the system can better serve users, improve the naturalness of interaction and user satisfaction, and generate the adjusted mapping relationship.

[0097] S403: Apply the adjusted mapping relationship and conduct the information transfer efficiency test again, compare the improvement effects before and after, verify information loss and optimize the efficiency of the conversation reply. The execution process of generating the information transfer efficiency analysis result is as follows;

[0098] Apply the adjusted mapping relationship and conduct the information transfer efficiency test again, compare the information transfer efficiency and the user's understanding level before and after the adjustment. This step aims to verify the actual effect of the adjustment measures and ensure that the optimization of the conversation strategy can effectively reduce information loss and improve the response speed. The test is conducted by simulating the user interaction scenario again. The evaluation results will detail the specific effects of the improvement of each conversation strategy, including the reduction of response time and the improvement of user satisfaction, provide proof of the effectiveness of the adjustment measures, and ensure that each optimization is based on actual user feedback and data analysis. The iterative process is a key method to improve the overall performance of the system and the user experience, and generate the information transfer efficiency analysis result.

[0099] Please refer to Figure 6, using the analysis results of information transmission efficiency, according to the conversation data and psychological risk assessment indicators, simulating the psychological impact of different conversation strategies, and drawing a psychological impact map, the steps to obtain a psychological impact prediction model are as follows:

[0100] S501: Use the analysis results of information transmission efficiency, combine the conversation data and psychological risk assessment indicators, set simulation parameters to evaluate the psychological impact caused by different conversation strategies in real-time scenarios, including the anxiety caused by the comfort level and incentive effect, and the execution process of generating initial simulation data of psychological impact is as follows;

[0101] Use the analysis results of information transmission efficiency, combine the conversation data and psychological risk assessment indicators, set simulation parameters to evaluate the psychological impact caused by different conversation strategies in real-time scenarios, including the anxiety or psychological reaction caused by the conversation strategy when providing comfort or incentive. The process of setting simulation parameters takes into account the characteristics of various conversation strategies and the psychological characteristics of the target user group, provides a basic data framework for further analysis and optimization. The data set is an important tool for understanding the actual psychological impact of conversation strategies, helps analysts and decision-makers foresee the specific psychological effects that different conversation strategies may bring, and more accurately adjust the conversation content in actual applications to meet the actual needs of users, generating initial simulation data of psychological impact.

[0102] S502: Based on the initial simulation data of psychological impact, use data visualization tools to evaluate the psychological impact corresponding to multiple conversation strategies, analyze the intensity and scope of the psychological impact corresponding to different conversation strategies, and check the psychological effects of each strategy. The execution process of generating a psychological impact map is as follows;

[0103] Based on the initial simulation data of psychological impact, use data visualization tools to evaluate the psychological impact corresponding to different conversation strategies, display the intensity and scope of the psychological impact of different conversation strategies through graphs and charts, analyze to help identify which conversation strategies are more effective in actual applications, and at the same time point out that the strategies need further adjustment or improvement, display the specific impact of various conversation strategies on the user's psychological state. The map makes the design and optimization process of conversation strategies more data-driven, ensures that decisions are based on the actual psychological reactions of users, and improves the overall effectiveness and applicability of conversation strategies, generating a psychological impact map.

[0104] S503: According to the psychological impact map, analyze the relationship between the conversation strategy and the psychological reaction, predict the psychological impact of different conversation strategies, verify the real-time adjustment and optimization of the model for the conversation, match the user's psychological state, and the execution process of generating a psychological impact prediction model is as follows;

[0105] According to the psychological influence map, analyze the relationship between the conversation strategy and the psychological reaction, predict the psychological influence of different conversation strategies. The process covers all stages from data to decision-making. Using the data in the psychological influence map, researchers can deeply understand how different conversation strategies interact with the user's psychological state. Based on the actual user feedback and psychological assessment data, provide a scientific basis for the real-time adjustment and optimization of the conversation strategy, ensure that the conversation strategy can effectively match the user's psychological state in actual application, and be used to guide the future design of the conversation strategy, ensure that the conversation content not only meets the situational needs, but also has a positive impact on the user's mental health and overall experience, and generate a psychological influence prediction model.

[0106] Please refer to Figure 7 , through the psychological influence prediction model, analyze the psychological risks of the conversation strategy, compare the prediction results with the risk acceptance threshold, adjust the conversation strategy in the mapping table, and avoid psychological risks. The specific steps to generate the strategy adjustment result are as follows:

[0107] S601: Adopt the psychological influence prediction model and use the multiple linear regression algorithm to evaluate the psychological risks of different conversation strategies, including quantifying the changes in emotional instability and stress. The execution process to generate the risk assessment result of the conversation strategy is as follows;

[0108] The formula of the multiple linear regression algorithm is as follows:

[0109]

[0110] Among them, R is the psychological risk score value, β0 represents the intercept of the regression model, β1 represents the weight parameter of emotional instability, E represents the measured value of emotional instability, β2 represents the weight parameter of the change in stress, S represents the change in stress, T represents the conversation duration, β3 represents the weight parameter of the complexity of the conversation strategy, and C represents the complexity of the conversation strategy.

[0111] Detailed explanation of the formula and the derivation process of the formula calculation:

[0112] 1. Parameter definition and data acquisition:

[0113] β0 (intercept): Obtained by analyzing historical data through a linear regression model, set to 2.5. The value represents the basic psychological risk score without a conversation strategy.

[0114] β1 (weight of emotional instability): Based on the correlation analysis between emotion and psychological risk, set to 1.2. The parameter varies greatly with emotional fluctuations.

[0115] β2 (weight of stress change): Reflects the impact of stress change on psychological risk, set to 0.8. The coefficient takes into account the adjustment effect of the logical function form on the stress change.

[0116] β3 (Weight of speech complexity): Set to 0.5 with reference to the actual effect of complexity on psychological impact.

[0117] 2. Quantification process of parameters:

[0118] E (Measurement value of emotional instability): Collected by an emotion monitoring device, and the emotional fluctuation index is set to 30 (average daily fluctuation frequency for quantifying emotional stability).

[0119] S (Change in sense of pressure): Measured by a psychological stress monitor, set to 20 in this example (referring to the change value of the pressure index over a period of time).

[0120] T (Duration of speech): In the calculation of parameters, in minutes, set to 10 minutes in this example.

[0121] C (Complexity of speech strategy): The quantification method is to count the number of variables and turning points in the implementation of the speech, set to 4 in this example.

[0122] 3. Formula calculation and derivation process:

[0123]

[0124] Calculate As the value of T increases, e -T approaches 0, and the logistic function approaches 1. Therefore, this part of the calculation is

[0125] Calculate Calculated to be

[0126] Comprehensive formula calculation: R = 2.5 + 36 + 16 + 1.41 = 55.91.

[0127] The results show that based on the currently set emotional instability, change in sense of pressure, duration of speech, and complexity of speech strategy, the calculated psychological risk score is 55.91. The value indicates that under the current speech strategy, the subject faces a medium or higher psychological risk. Through quantitative assessment, the strategy formulator can adjust the speech strategy for high-risk scores to reduce potential adverse psychological impacts.

[0128] S602: Compare the predicted risk value in the speech strategy risk assessment result with the pre-set risk acceptance threshold, identify the speech strategies that exceed the threshold, analyze the risk sources and impact degrees of the strategies, and the execution process for generating the analysis result of speech strategies with excessive risks is as follows;

[0129] Compare the predicted risk values in the risk assessment results of the conversation strategy with the pre-set risk acceptance threshold to identify conversation strategies that exceed the threshold. The steps are to ensure that all conversation strategies are within an acceptable risk range. The conversation strategies that exceed the standard need to be analyzed in detail to determine the source of the risk and the degree of impact, including the specific situation of each conversation strategy that exceeds the standard and the recommended handling measures. This is a crucial security guarantee step to ensure that the conversation strategies do not affect the mental health of users or cause adverse reactions due to excessive risks. In this way, the system can timely adjust or eliminate the conversation strategies that cause discomfort or negative effects to users and generate the analysis results of conversation strategies that exceed the standard.

[0130] S603: Based on the analysis results of conversation strategies that exceed the standard, adjust the conversation strategies in the mapping table, optimize and replace the conversation strategies that cause psychological risks, avoid potential negative impacts, and rebalance the relationship between the conversation strategies and user psychological safety. The execution process of generating the strategy adjustment results is as follows;

[0131] Based on the analysis results of conversation strategies that exceed the standard, adjust the conversation strategies in the mapping table, optimize and replace the conversation strategies that cause psychological risks, and rebalance the relationship between the conversation strategies and user psychological safety. The process involves the re-design of the conversation content to ensure that all conversations can effectively convey information while protecting the mental health of users, including the adjustment details and expected effects of each conversation strategy. The adjustment is based on actual user feedback and professional psychological evaluations, aiming to ensure that the conversation strategies can maintain the psychological well-being of users while achieving their functions and avoid any negative impacts. Through optimization measures, both the security of the system and user satisfaction will be improved, and the strategy adjustment results will be generated.

[0132] Please refer to Figure 8 , a conversation reply system for online psychological counseling. The conversation reply system for online psychological counseling is used to execute the above-mentioned conversation reply method for online psychological counseling. The system includes:

[0133] The data encoding module collects data on psychological counseling needs and emotional states, encodes the data, assigns target symbols, and generates the initial framework of the symbol set;

[0134] The symbol mapping module analyzes the representativeness and distinguishability of different symbols based on the initial framework of the symbol set, combines similar symbols and divides distinguishable symbols to obtain the optimized symbol set;

[0135] The conversation strategy module uses the optimized symbol set to establish the mapping relationship from symbols to conversation strategies, verifies each mapping relationship item by item, checks the adaptability of the conversations, and constructs the conversation mapping table;

[0136] The transfer efficiency processing module analyzes the information transfer efficiency through the conversation mapping table, iteratively adjusts the mapping table, verifies the information transfer speed and efficiency through data analysis, and generates the information efficiency analysis result;

[0137] Based on the information efficiency analysis result, the psychological risk assessment module combines the conversation data and the psychological risk assessment indicators, simulates the psychological impact of different conversation strategies, and generates the strategy adjustment result.

[0138] The above are only the preferred embodiments of the present invention, and do not limit the present invention in other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as the technical solution content of the present invention is not departed from, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still belong to the protection scope of the technical solution of the present invention.

Claims

1. A method for responding to online psychological consultation, characterized in that: The following steps are involved: Based on the original data of emotional state and psychological counseling needs, symbols are assigned to differentiated states and needs, and the data is initialized and coded to generate the initial framework of the symbol set; Using the initial framework of the symbol set, analyzing the representativeness and distinctiveness of each symbol in the symbol set, dividing and merging the symbols, optimizing the uniqueness of the symbols, and obtaining an optimized symbol set; Through the optimized symbol set, a mapping relationship between symbols and speech strategies is constructed, symbols and corresponding speech strategies are integrated, and a coding mapping table is generated by checking each item one by one; Utilize the coding mapping table to analyze the information transmission efficiency of the speech reply, avoid information loss by iteratively adjusting the mapping relationship in the mapping table, and generate the information transmission efficiency analysis result; Using the information transmission efficiency analysis results, based on the speech data and psychological risk assessment indicators, simulate the psychological impact of the differentiated speech strategy, draw a psychological impact map, and obtain a psychological impact prediction model; By using the psychological impact prediction model, the psychological risk of the speech strategy is analyzed, the prediction result is compared with the risk acceptance threshold, the speech strategy in the mapping table is adjusted to avoid psychological risks, and the strategy adjustment result is generated; Among them, based on the original data of emotional state and psychological counseling needs, symbols are assigned to differentiated states and needs, and the data is initialized and encoded. The steps of generating the initial framework of the symbol set are as follows: Collect raw data on emotional states and psychological counseling needs, assign unique identifiers to data items, record sources and timestamps, and generate a data identification framework; Based on the data identification framework, identify key variables in the data, including mood swings and consultation frequency, perform frequency and pattern analysis on the variables, extract key features, and generate a key feature index; Using the key feature index, assigning symbols to differentiated emotional states and psychological needs, labeling and classifying the data, and generating an initial framework of symbol sets; The steps of constructing a mapping relationship between symbols and speech strategies through the optimized symbol set, integrating symbols and corresponding speech strategies, and verifying them one by one to generate a coding mapping table are as follows: Using the optimized symbol set, each symbol is associated with a target speech strategy, the speech strategy is customized according to the emotional state and psychological needs represented by the symbol, and each symbol is verified to have a corresponding response speech, and an initialization mapping relationship is generated; Integrate and optimize the initialization mapping relationship, pair the symbols with the corresponding words according to the real-time application scenario and logical relationship, check and resolve existing conflicts, verify the practicality of the mapping relationship, and generate a verified mapping relationship; According to the verified mapping relationship, each symbol and the corresponding speech strategy are recorded, and verification and adjustment are performed, including the definition and matching speech of each symbol, to generate a coding mapping table.

2. The online psychological consultation speech reply method according to claim 1 is characterized in that: The initial framework of the symbol set includes emoticons based on differentiated emotions, descriptive labels of psychological needs and associated initialization codes; the optimized symbol set includes symbols for distinguishing differentiated psychological states, hierarchical symbols of emotions and optimized behavioral indication symbols; the coding mapping table includes the degree of association between symbols and speech, the classification of application scenarios of speech and the expected feedback type of speech effects; the information transmission efficiency analysis results include the response time of speech, information coverage and customer satisfaction indicators; the psychological impact prediction model includes an emotion change prediction map, a psychological stability index and a predicted user behavior response pattern; the strategy adjustment results include a modified speech response strategy, risk threshold adjustment parameters and a newly introduced early warning mechanism.

3. The online psychological consultation speech reply method according to claim 1 is characterized in that: The steps of adopting the initial framework of the symbol set, analyzing the representativeness and distinctiveness of each symbol in the symbol set, dividing and merging the symbols, optimizing the uniqueness of the symbols, and obtaining the optimized symbol set are as follows: Using the initial framework of the symbol set, statistically analyze the frequency and distribution of each symbol, record the number of symbols and rare symbols, analyze the application of symbols in differentiated emotional states and psychological needs, and generate symbol analysis results; Based on the symbol analysis results, evaluate the representativeness and discrimination of the symbols, merge the symbols with low discrimination, divide the high-frequency but low-representative symbols, check that each symbol has a definite and unique representational meaning, and generate a symbol optimization plan; The symbol optimization scheme is implemented, the symbol set is readjusted and encoded, and through iterative data encoding and symbol adjustment, each symbol is checked for the target's emotional state and psychological counseling needs, and an optimized symbol set is generated.

4. The online psychological consultation speech reply method according to claim 1 is characterized in that: The steps of using the coding mapping table to analyze the information transmission efficiency of the speech reply, iteratively adjusting the mapping relationship in the mapping table to avoid information loss, and generating the information transmission efficiency analysis result are as follows: Based on the coding mapping table, an initial information transmission efficiency test is performed to evaluate the response speed and user analysis degree of the differentiated speech strategy through simulation scenarios and user feedback, identify delays and ambiguous points in information transmission, and generate initial efficiency analysis results; According to the initialization efficiency analysis result, the mapping relationship between symbols and speech in the mapping table is iteratively adjusted to optimize the speech strategy that causes information delay and misunderstanding, and the speech content is adjusted through real-time data and user behavior analysis to generate an adjusted mapping relationship; Apply the adjusted mapping relationship, perform the information transfer efficiency test again, compare the improvement effects before and after, verify the information loss and optimize the efficiency of the speech reply, and generate the information transfer efficiency analysis results.

5. The online psychological consultation speech reply method according to claim 1 is characterized in that: The steps of using the information transmission efficiency analysis results, simulating the psychological impact of differentiated speech strategies according to speech data and psychological risk assessment indicators, drawing a psychological impact map, and obtaining a psychological impact prediction model are as follows: Using the information transmission efficiency analysis results, combined with the speech data and psychological risk assessment indicators, setting simulation parameters to evaluate the psychological impact of differentiated speech strategies in real-time scenarios, including the anxiety caused by comfort and incentive effects, and generating psychological impact initialization simulation data; Based on the psychological impact initialization simulation data, using data visualization tools, evaluate the psychological impact corresponding to a variety of speech strategies, analyze the intensity and range of psychological impact corresponding to differentiated speech, check the psychological effect of each strategy, and generate a psychological impact map; According to the psychological impact map, the relationship between speech strategies and psychological reactions is analyzed, the psychological impact of differentiated speech strategies is predicted, the real-time adjustment and optimization of the dialogue by the verification model is carried out, the psychological state of the user is matched, and a psychological impact prediction model is generated.

6. The online psychological consultation speech reply method according to claim 1, characterized in that: The psychological risk of the speech strategy is analyzed by the psychological impact prediction model, the prediction result is compared with the risk acceptance threshold, the speech strategy in the mapping table is adjusted to avoid psychological risks, and the steps of generating the strategy adjustment result are as follows: The psychological impact prediction model is used to evaluate the psychological risks of differentiated speech strategies using a multivariate linear regression algorithm, including quantifying changes in emotional instability and stress, and generating speech strategy risk assessment results; Compare the predicted risk value in the risk assessment result of the speech strategy with the pre-set risk acceptance threshold, identify the speech strategy that exceeds the threshold, analyze the risk source and impact of the strategy, and generate the analysis result of the speech strategy that exceeds the risk limit; Based on the analysis results of the risk-exceeding speech, the speech strategies in the mapping table are adjusted, the speech that causes psychological risks is optimized and replaced, potential negative impacts are avoided, the relationship between the speech strategy and the user's psychological safety is rebalanced, and the strategy adjustment results are generated.

7. The online psychological consultation speech reply method according to claim 6 is characterized in that: The formula of the multivariate linear regression algorithm is as follows: ， in, is the psychological risk score, represents the intercept of the regression model, The weight parameter representing emotional instability, represents a measure of emotional instability, The weight parameter representing the change in pressure sensation, Represents the change in pressure. Represents the duration of the speech. The weight parameter representing the complexity of the speech strategy, Represents the complexity of the speech strategy.

8. A speech response system for online psychological consultation, characterized in that: According to the online psychological consultation speech reply method according to any one of claims 1 to 7, the system comprises: The data coding module collects data on psychological counseling needs and emotional states, encodes the data, assigns target symbols, and generates an initial framework of symbol sets; The symbol mapping module analyzes the representativeness and discrimination of the differentiated symbols based on the initial framework of the symbol set, merges the symbols of the same type and divides the symbols of different types, and obtains an optimized symbol set; The speech strategy module uses the optimized symbol set to establish a mapping relationship from symbols to speech strategies, verifies the mapping relationship one by one, checks the adaptability of the speech, and constructs a speech mapping table; The transmission efficiency processing module analyzes the efficiency of information transmission through the speech mapping table, iteratively adjusts the mapping table, verifies the speed and efficiency of information transmission through data analysis, and generates information efficiency analysis results; The psychological risk assessment module simulates the psychological impact of differentiated speech strategies based on the information efficiency analysis results, combined with speech data and psychological risk assessment indicators, and generates strategy adjustment results.

Images