Online consultation intelligent interaction method and system

Abstract

The invention provides an online consultation intelligent interaction method and system, and relates to the technical field of online consultation interaction.The online consultation intelligent interaction method comprises the steps that consultation reservation data is obtained, consultation nodes are determined, consultation record information is packaged and stored in a segmented mode, a consultation storage data packet is obtained, and feature extraction and feature category labeling are carried out; classifying the consultation storage data packet, obtaining a stage consultation report and a comprehensive consultation report, carrying out fusion comparison, obtaining a report comparison result, carrying out node consultation data labeling on the current comprehensive consultation report, and generating a consultation data trend chart; calculating a patient consultation weight factor and a patient consultation dynamic variable factor, further calculating a patient consultation coefficient, performing consultation parameter adjustment on the patient according to the patient consultation coefficient, and obtaining patient consultation adjustment data. Intelligent interaction and management of online consultation are achieved, consultation efficiency and quality are improved, medical resource configuration is optimized, and patient experience is enhanced.

Description

Technical Field

[0001] The present invention proposes an online consultation intelligent interaction method and system, which relate to the field of intelligent interaction technology, and specifically to the field of online consultation intelligent interaction technology. Background Art

[0002] In today's medical process, the consultation method has gradually changed from offline to online. Although traditional online consultation is already possible, online consultation management still faces many technical problems. The traditional online consultation application and appointment process is cumbersome, and it is difficult to monitor and adjust changes in real time. At the same time, there is a lack of personalized consultation management based on data analysis. When the doctor withdraws from the consultation due to emergency or special circumstances during the consultation, the consultation records are difficult to retrieve, analyze and manage in a targeted manner. It is also difficult for traditional online consultations to intelligently adjust the patient's future consultation parameters based on the consultation situation. Summary of the invention

[0003] The present invention provides an online consultation intelligent interaction method and system to solve the above problems:

[0004] The present invention provides an online consultation intelligent interaction method and system, the method comprising:

[0005] S1. Obtain consultation application information, make an appointment for consultation, obtain real-time data information during the consultation process and dynamic variable information of the consultation appointment information, pre-process and record the real-time data information, and obtain consultation record information;

[0006] S2, obtaining consultation appointment data, determining consultation nodes, segmenting and packaging the consultation record information and storing it, obtaining consultation storage data packets, performing feature extraction and feature category labeling, and then classifying the consultation storage data packets to obtain feature category data groups;

[0007] S3. Acquire the phase consultation report and the comprehensive consultation report according to the consultation storage data packet, perform fusion comparison, obtain the report comparison result, annotate the node consultation data of the current comprehensive consultation report, and then generate a consultation data trend chart;

[0008] S4. Calculate the patient consultation weight factor and the patient consultation dynamic variable factor, and then calculate the patient consultation coefficient, adjust the patient consultation parameters according to the patient consultation coefficient, and obtain patient consultation adjustment data.

[0009] Furthermore, the S1 includes:

[0010] Obtain consultation application information, determine the information of participants based on the consultation application information, and then determine the consultation appointment information;

[0011] Conduct a consultation according to the consultation appointment information and obtain real-time data information during the consultation process;

[0012] Acquire consultation appointment status change information, and acquire dynamic variable information of the consultation appointment information by combining the consultation appointment status change information with real-time data information during the consultation process;

[0013] Preprocessing the real-time data information to obtain preprocessed real-time data information;

[0014] The pre-processed real-time data information is stored to obtain consultation record information.

[0015] Further, the S2 includes:

[0016] Obtain consultation appointment data, and determine a consultation node according to the consultation appointment data;

[0017] The consultation record information is segmented and packaged according to the consultation node information to obtain consultation data packets of multiple stages;

[0018] The consultation data packets of each stage are stored to obtain the consultation storage data packets of each stage;

[0019] Obtaining preset consultation indicator types, and then obtaining characteristic keywords for each preset consultation indicator type;

[0020] Extracting features of the consultation storage data packets at each stage according to the feature keywords to obtain feature extraction data of the consultation storage data packets at each stage;

[0021] Marking the consultation storage data packets of each stage with feature categories according to the feature extraction data to obtain the marking information of the consultation storage data packets of each stage;

[0022] The consultation storage data packets of each stage are classified according to the types of annotation information to obtain feature category data groups.

[0023] Further, the S3 includes:

[0024] Obtain the doctor's consultation report data of each stage of the consultation storage data package to obtain the stage consultation report;

[0025] Sort the consultation reports of each stage according to the order of the stages and generate a comprehensive consultation report;

[0026] Extract features from the consultation report of each stage according to the feature keywords, and obtain feature extraction data of the consultation report of each stage;

[0027] Integrate the feature extraction data of each stage to obtain feature integration extraction data;

[0028] Obtain the patient's historical comprehensive consultation report, merge and compare the report data of the historical comprehensive consultation report with the report data of the current comprehensive consultation report, and obtain a report comparison result;

[0029] Perform node consultation data annotation on the current comprehensive consultation report according to the report comparison result; the node consultation data annotation includes difference data between the current comprehensive consultation report data and the average data of the historical comprehensive consultation report data;

[0030] Obtain the node consultation data annotation of each historical comprehensive consultation report and generate a consultation data trend chart.

[0031] Further, the S4 includes:

[0032] Acquire new information of consultation data according to the consultation data trend chart, and calculate the patient consultation weight factor according to the new information of consultation data;

[0033] Acquire dynamic variable information of each historical comprehensive consultation report, and calculate the patient consultation dynamic variable factor according to the dynamic variable information;

[0034] The patient consultation coefficient is calculated based on the patient consultation weight factor combined with the patient consultation dynamic factor;

[0035] The duration or frequency of the patient's next consultation is adjusted according to the patient consultation coefficient to obtain patient consultation adjustment data.

[0036] Furthermore, the interactive system comprises:

[0037] The consultation reservation record module is used to obtain consultation application information, make an appointment for consultation, obtain real-time data information during the consultation process and dynamic variable information of the consultation reservation information, pre-process and record the real-time data information, and obtain consultation record information;

[0038] The consultation record packaging and classification module is used to obtain consultation appointment data, determine the consultation node, segment and package the consultation record information and store it, obtain consultation storage data packets, perform feature extraction and feature category labeling, and then classify the consultation storage data packets to obtain feature category data groups;

[0039] The data fusion comparison module is used to obtain the phase consultation report and the comprehensive consultation report according to the consultation storage data packet, perform fusion comparison, obtain the report comparison result, annotate the node consultation data of the current comprehensive consultation report, and then generate a consultation data trend chart;

[0040] The consultation calculation and adjustment module is used to calculate the patient consultation weight factor and the patient consultation dynamic variable factor, and then calculate the patient consultation coefficient, adjust the patient consultation parameters according to the patient consultation coefficient, and obtain patient consultation adjustment data.

[0041] Furthermore, the consultation appointment record module includes:

[0042] The consultation appointment module is used to obtain consultation application information, determine the information of participants according to the consultation application information, and then determine the consultation appointment information;

[0043] Conduct a consultation according to the consultation appointment information and obtain real-time data information during the consultation process;

[0044] A variable acquisition module is used to acquire consultation appointment status change information, and acquire dynamic variable information of the consultation appointment information by combining the consultation appointment status change information with real-time data information during the consultation process;

[0045] Preprocessing the real-time data information to obtain preprocessed real-time data information;

[0046] The record storage module is used to store the pre-processed real-time data information to obtain consultation record information.

[0047] Furthermore, the consultation record packaging and classification module includes:

[0048] A node packaging module, used to obtain consultation appointment data and determine the consultation node according to the consultation appointment data;

[0049] The consultation record information is segmented and packaged according to the consultation node information to obtain consultation data packets of multiple stages;

[0050] A packaging storage module is used to store the consultation data packets of each stage and obtain the consultation storage data packets of each stage;

[0051] A feature extraction module is used to obtain the preset consultation indicator types, and then obtain the characteristic keywords of each preset consultation indicator type;

[0052] Extracting features of the consultation storage data packets at each stage according to the feature keywords to obtain feature extraction data of the consultation storage data packets at each stage;

[0053] A feature classification module is used to mark the consultation storage data packets of each stage with feature categories according to the feature extraction data, and obtain the marking information of the consultation storage data packets of each stage;

[0054] The consultation storage data packets of each stage are classified according to the types of annotation information to obtain feature category data groups.

[0055] Furthermore, the data fusion comparison module includes:

[0056] A comprehensive generation module is used to obtain the consultation report data of the doctor's consultation storage data package for each stage and obtain the stage consultation report;

[0057] Sort the consultation reports of each stage according to the order of the stages and generate a comprehensive consultation report;

[0058] An integrated extraction module is used to extract features from the consultation report of each stage according to feature keywords, and obtain feature extraction data of the consultation report of each stage;

[0059] Integrate the feature extraction data of each stage to obtain feature integration extraction data;

[0060] A comparison and annotation module is used to obtain the patient's historical comprehensive consultation report, merge and compare the report data of the historical comprehensive consultation report with the report data of the current comprehensive consultation report, and obtain a report comparison result;

[0061] Perform node consultation data annotation on the current comprehensive consultation report according to the report comparison result; the node consultation data annotation includes difference data between the current comprehensive consultation report data and the average data of the historical comprehensive consultation report data;

[0062] The trend chart generation module is used to obtain the node consultation data annotations of each historical comprehensive consultation report and generate a consultation data trend chart.

[0063] Furthermore, the consultation calculation adjustment module includes:

[0064] A weight calculation module, used to obtain new information of consultation data according to the consultation data trend chart, and calculate the patient consultation weight factor according to the new information of consultation data;

[0065] A dynamic calculation module, used to obtain dynamic variable information of each historical comprehensive consultation report, and calculate the patient consultation dynamic variable factor according to the dynamic variable information;

[0066] A consultation adjustment module, used to calculate a patient consultation coefficient based on a patient consultation weight factor combined with a patient consultation dynamic factor;

[0067] The duration or frequency of the patient's next consultation is adjusted according to the patient consultation coefficient to obtain patient consultation adjustment data.

[0068] Beneficial effects of the present invention: Through online intelligent interaction, the time consumed in consultation is saved and the consultation efficiency is improved. The consultation resources are dynamically adjusted according to the consultation data to ensure the rational allocation and efficient use of medical resources. Real-time data recording and dynamic analysis improve the accuracy and comprehensiveness of the consultation process and the accuracy of diagnosis. Personalized consultation reports and trend charts are provided. The present invention solves the problem that the traditional online consultation application and appointment process is cumbersome and difficult to monitor and adjust changes in real time. At the same time, it also solves the lack of personalized consultation management based on data analysis. When the doctor withdraws from the consultation midway due to emergency or special circumstances during the consultation, the consultation records are difficult to retrieve, analyze and manage in a targeted manner. The technical effect of intelligently adjusting the patient's future consultation parameters according to the consultation situation is achieved.

[0069] Figure 1 A schematic diagram of an intelligent interactive method for online consultation;

[0070] Figure 2 This is a schematic diagram of the consultation data trend chart. DETAILED DESCRIPTION

[0071] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0072] In one embodiment of the present invention, an online consultation intelligent interaction method and system are proposed by the present invention, and the method includes:

[0073] S1. Obtain consultation application information, make an appointment for consultation, obtain real-time data information during the consultation process and dynamic variable information of the consultation appointment information, pre-process and record the real-time data information, and obtain consultation record information;

[0074] S2, obtaining consultation appointment data, determining consultation nodes, segmenting and packaging the consultation record information and storing it, obtaining consultation storage data packets, performing feature extraction and feature category labeling, and then classifying the consultation storage data packets to obtain feature category data groups;

[0075] S3. Acquire the phase consultation report and the comprehensive consultation report according to the consultation storage data packet, perform fusion comparison, obtain the report comparison result, annotate the node consultation data of the current comprehensive consultation report, and then generate a consultation data trend chart;

[0076] S4, calculating the patient consultation weight factor and the patient consultation dynamic variable factor, and then calculating the patient consultation coefficient, adjusting the patient consultation parameters according to the patient consultation coefficient, and obtaining the patient consultation adjustment data, such as Figure 1 shown.

[0077] The working principle of the above technical solution is as follows: by collecting the consultation application information of the patient, including basic information, medical history, current symptoms, etc. Make an appointment for consultation according to the application information, and capture the data information and dynamic changes of the appointment information in the consultation process (such as consultation time adjustment, doctor change, etc.) in real time. Preprocess the real-time data information (such as data cleaning and formatting) to ensure data quality and generate detailed consultation record information. The system segments and packages the consultation record information according to the progress and key nodes of the consultation to form a consultation storage data packet. Extract features from the data packet, classify the data packet according to the marked feature category, form a feature category data group, and use the classified data packet to generate a stage consultation report and a comprehensive consultation report. The two reports are fused and compared, and the changes and differences in the consultation process are analyzed to obtain the report comparison results. In the comprehensive consultation report, the consultation data of the current node is annotated, and the consultation data trend chart is generated through data visualization technology to facilitate the visualization of the data. The system calculates the patient consultation weight factor and dynamic variable factor based on the patient's consultation record, feature category data, and dynamic variables in the consultation process. Combining these factors, the patient consultation coefficient is calculated, which can reflect the patient's overall consultation data. According to the patient consultation coefficient, the system automatically adjusts the patient's consultation parameters.

[0078] The technical effects of the above technical solutions are: saving time consumed in consultation and improving consultation efficiency through online intelligent interaction. Dynamically adjusting consultation resources according to consultation data to ensure the rational allocation and efficient use of medical resources. Real-time data recording and dynamic analysis improve the accuracy and comprehensiveness of the consultation process and the accuracy of diagnosis. Provide personalized consultation reports and trend charts. The present invention solves the problem that the traditional online consultation application and appointment process is cumbersome and difficult to monitor and adjust changes in real time. At the same time, it also solves the lack of personalized consultation management based on data analysis. When the doctor withdraws from the consultation midway due to emergency or special circumstances during the consultation, the consultation records are difficult to retrieve, analyze and manage in a targeted manner. The technical effect of intelligently adjusting the patient's future consultation parameters according to the consultation situation is achieved.

[0079] In one embodiment of the present invention, the S1 includes:

[0080] Obtain consultation application information, determine the information of participants according to the consultation application information, and then determine the consultation appointment information; the consultation appointment information includes consultation time information, consultation personnel and consultation purpose, etc.;

[0081] A consultation is conducted according to the consultation appointment information, and real-time data information during the consultation process is obtained; the real-time data information includes consultation communication information and interactive file information, etc.

[0082] Obtain consultation appointment status change information, and obtain dynamic variable information of the consultation appointment information by combining the consultation appointment status change information with real-time data information during the consultation process; the dynamic variable information includes changes in consultation personnel, time and purpose, etc.;

[0083] Preprocessing the real-time data information to obtain preprocessed real-time data information;

[0084] The pre-processed real-time data information is stored to obtain consultation record information.

[0085] The working principle of the above technical solution is as follows: the present invention collects consultation application information from patients or medical institutions, and automatically or manually assists in determining the information of participants, including attending physicians, experts in relevant departments, and appointment time, etc. After determining the participants, detailed consultation appointment information is generated, including consultation time, location, list of participants and their respective roles, consultation purpose, etc. According to the consultation appointment information, online consultation invitation information is sent to relevant personnel of the organization for online consultation. During the consultation process, the system captures and records consultation communication information in real time, such as text chat, voice call, video call, etc. During or before the consultation, changes in appointment status may occur, such as time adjustment, personnel replacement, purpose change, etc. By obtaining these appointment status change information and combining real-time consultation data information, dynamic variable information of consultation appointment information is generated. The captured real-time data information is preprocessed, including data cleaning (removing useless or erroneous data), formatting (unifying data format and standards), etc. The preprocessed real-time data information is stored as consultation record information.

[0086] The technical effects of the above technical solutions are: through the online process, the communication costs and time delays in traditional consultations are reduced, and the consultation efficiency is improved. Real-time data recording and storage ensure the traceability and transparency of the consultation process. The system can capture and process changes in appointment status in real time, making the consultation plan more flexible and adaptable to actual conditions. The pre-processed real-time data provides strong data support for medical decision-making and reduces the occurrence of errors or mistakes. Based on real-time data and dynamic variable information, the system can allocate medical resources more accurately, such as reasonably allocating expert time and optimizing inspection processes. Patients can participate in the consultation process more conveniently and understand their condition and treatment plan in real time.

[0087] In one embodiment of the present invention, S2 includes:

[0088] Obtain consultation appointment data, and determine consultation nodes according to the consultation appointment data; consultation nodes may be personnel entry and exit time nodes, communication information nodes, etc.;

[0089] The consultation record information is segmented and packaged according to the consultation node information to obtain consultation data packets of multiple stages;

[0090] The consultation data packets of each stage are stored to obtain the consultation storage data packets of each stage;

[0091] Obtaining preset consultation indicator types, and then obtaining characteristic keywords for each preset consultation indicator type;

[0092] Feature extraction is performed on the consultation storage data packets of each stage according to the feature keywords to obtain feature extraction data of the consultation storage data packets of each stage; the feature extraction data includes data of the consultation storage data packets containing the feature keywords.

[0093] The consultation storage data packets of each stage are annotated with feature categories according to the feature extraction data to obtain the annotation information of the consultation storage data packets of each stage; the annotation information includes feature keywords of the consultation storage data packets.

[0094] The consultation storage data packets of each stage are classified according to the type of the marked information to obtain feature category data groups. Each feature category data group includes a plurality of data packets of the same feature category.

[0095] The working principle of the above technical solution is: obtain consultation appointment data from the database, which contains detailed arrangements for the consultation, such as participants, time, location, etc. According to the appointment data, key time nodes and communication information nodes can be identified, such as personnel entry and exit time, important discussion time period, etc. According to the identified consultation node information, the continuous consultation record information is segmented, and each segment corresponds to a specific node or time period. The segmented record information is packaged into consultation data packets of multiple stages, and each data packet contains all relevant information in the stage. The consultation data packets of each stage are stored independently to ensure the integrity and accessibility of the data. During the storage process, security measures such as data compression and encryption may also be included to improve storage efficiency and data security. The system presets a variety of consultation indicator types. For each type of consultation indicator, the system defines corresponding feature keywords, and identifies specific information content through these keywords. Using the preset feature keywords, feature extraction is performed on the consultation storage data packets of each stage. The content in the data packet that meets the description of the feature keywords is identified. The extracted feature data is annotated, and the annotation information includes the feature keywords and their specific location or context information in the data packet. According to the type of annotation information, the system classifies the consultation storage data packets of each stage. The classification is based on the type of characteristic keywords contained in the data packets. The classification results form multiple characteristic category data groups, each of which contains all data packets with the same characteristic keywords.

[0096] The technical effect of the above technical solution is: through segmentation packaging and feature extraction, the original, unstructured consultation record data is converted into a structured data set that is conducive to query and analysis. The formation of feature category data groups allows data analysts to locate the data set of interest more quickly, thereby improving analysis efficiency. The preset consultation indicator types and feature keywords help improve the recognition efficiency of specific fields and specific events. Security measures taken during data storage, such as compression and encryption, enhance data security and privacy protection.

[0097] In one embodiment of the present invention, S3 includes:

[0098] Obtain the doctor's consultation report data of each stage of the consultation storage data package to obtain the stage consultation report;

[0099] Sort the consultation reports of each stage according to the order of the stages and generate a comprehensive consultation report;

[0100] Extract features from the consultation report of each stage according to the feature keywords, and obtain feature extraction data of the consultation report of each stage;

[0101] The feature extraction data of each stage are integrated to obtain feature integrated extraction data; the above scheme can flexibly integrate the consultation data of each feature, so as to facilitate data analysis of each feature of the consultation.

[0102] Obtain the patient's historical comprehensive consultation report, fuse and compare the report data of the historical comprehensive consultation report with the report data of the current comprehensive consultation report to obtain a report comparison result; the fusion comparison includes obtaining the current data of each category and comparing the different data of the same category in the history.

[0103] The node consultation data of the current comprehensive consultation report is annotated according to the report comparison result; the node consultation data annotation includes annotating the node consultation data of the current comprehensive consultation report according to the difference data between the current comprehensive consultation report data and the average data of the historical comprehensive consultation report data.

[0104] Obtain the node consultation data annotation of each historical comprehensive consultation report and generate a consultation data trend chart, such as Figure 2 shown.

[0105] The working principle of the above technical solution is: obtain the consultation report data written by the doctor for the consultation storage data package of each stage to form a stage consultation report. Sort these stage consultation reports in chronological or logical order, and finally generate a complete comprehensive consultation report. Perform feature extraction on the consultation report of each stage, and identify the key information points in the report based on the preset feature keywords. Integrate the feature extraction data of all stages to form feature integration extraction data. Obtain the patient's historical comprehensive consultation reports, which record the patient's past consultation situation and the doctor's advice. Fusion and comparison of the report data of the current comprehensive consultation report with the historical data, and identify the difference between the current data and the historical data through difference comparison. According to the report comparison results, the system annotates the node consultation data of the current comprehensive consultation report. The basis for annotation is the degree of difference between the current data and the historical average data. Through annotation, the doctor can intuitively see which nodes or time periods have the most significant data changes. Obtain the node consultation data annotation of each historical comprehensive consultation report, and generate a consultation data trend chart in combination with the annotation information of the current report. This chart uses time as the horizontal axis and data changes as the vertical axis, intuitively showing the long-term change trends and short-term fluctuations in patient consultation data.

[0106] The technical effect of the above technical solution is: by generating comprehensive consultation reports and extracting data through feature integration, doctors can more easily obtain comprehensive information and key features of the consultation, and improve the readability and usability of the report. Fusion and comparison of current data with historical data can help doctors understand the evolution of the patient's condition and the changing trend of treatment effects, so as to make more scientific and reasonable decisions. Through node consultation data annotation and consultation data trend charts, doctors can identify time periods and patient groups that need to be focused on, and optimize the allocation and utilization efficiency of medical resources. Through detailed consultation reports and intuitive data trend charts, patients can have a clearer understanding of their condition and treatment. The integration, comparison and analysis results of consultation data can provide valuable data support for medical research.

[0107] In one embodiment of the present invention, the S4 includes:

[0108] The newly added information of the consultation data is obtained according to the consultation data trend chart, and the patient consultation weight factor is calculated according to the newly added information of the consultation data; the newly added information is the difference data of each of the above nodes, and the difference between the current data and the average value of the historical data.

[0109] The calculation formula of the patient consultation weight factor is:

[0110]

[0111] Among them, Y qz is the patient consultation weight factor, j is the total number of stages, ΔSd Add information to the current stage of consultation data, ΔS d-1 Add information to the consultation data of the previous stage of the current stage, ΔS i Add information to the consultation data of the i-th stage, ΔS i-1 is the new information added to the consultation data of the i-1th stage, m is the total number of characteristic keywords corresponding to the i-th stage, E ik is the preset enhancement factor of the kth feature keyword in the i-th stage, E maxik is the preset maximum possible value of the kth feature keyword in the i-th stage, α ik is the preset feature keyword weight parameter, C i To preset a specific state correction factor;

[0112] pass Assigning an enhancement factor to each feature keyword and comparing it with the maximum possible value can enhance the impact of these feature keywords in the evaluation. ik Approaching or reaching E maxik , the value of this part will increase significantly.

[0113] λij is used as a weight parameter to adjust the relative importance of different events or features in the evaluation. By assigning different weight parameters to different events or features, the model can be made to reflect the actual situation more flexibly.

[0114] Acquire dynamic variable information of each historical comprehensive consultation report, and calculate the patient consultation dynamic variable factor according to the dynamic variable information;

[0115] The calculation formula of the patient consultation dynamic variable factor is:

[0116]

[0117] Among them, D bl is the patient consultation dynamic variable factor, z is the total number of comprehensive consultation reports, m is the number of preset consultation indicator types, △L ob is the data of the bth preset consultation indicator type in the oth comprehensive consultation report, △L o-1b The data of the bth preset consultation indicator type of the o-1th comprehensive consultation report;

[0118] The patient consultation coefficient is calculated based on the patient consultation weight factor combined with the patient consultation dynamic factor;

[0119] The calculation formula of the patient consultation coefficient is:

[0120]

[0121] Among them, HZ is the patient consultation coefficient;

[0122] Compare the patient consultation coefficient with the preset coefficient threshold to obtain the coefficient comparison result. When the patient consultation coefficient is greater than the preset coefficient threshold, increase the adjustment. Otherwise, decrease the adjustment.

[0123] The duration or frequency of the patient's next consultation is adjusted according to the patient consultation coefficient to obtain patient consultation adjustment data.

[0124] The working principle of the above technical solution is: identify new information points or trend changes from the consultation data trend chart, which may represent new progress in the patient's condition or new situations in the treatment response. According to these new information, the weight factor of the patient consultation is calculated. The size of the weight factor reflects the importance and influence of the new information on the overall consultation situation of the patient. Obtain each historical comprehensive consultation report and extract the dynamic variable information therein, such as changes in the consultation personnel, changes in time, changes in purpose, etc. Analyze the dynamic variable information and calculate the dynamic variable factor of the patient consultation. The dynamic variable factor reflects the changes and influence of unstable factors in the patient consultation process. Combine the patient consultation weight factor with the patient consultation dynamic variable factor to calculate the patient consultation coefficient. The patient consultation coefficient is a comprehensive indicator that takes into account both the importance of the new information and the influence of historical dynamic variables, and is used to evaluate the comprehensive complexity and urgency of the patient's current consultation situation. According to the size of the patient consultation coefficient, the system automatically adjusts the duration or frequency of the patient's next consultation. If the patient consultation coefficient is high, it means that the patient's condition is complicated or changes rapidly, requiring more frequent consultations and longer consultation times; otherwise, the number of consultations can be appropriately reduced or the consultation time can be shortened.

[0125] The technical effect of the above technical solution is: by calculating the patient consultation coefficient and adjusting the consultation duration or frequency accordingly, personalized management of patient consultation is achieved, which is more in line with the actual needs of patients and improves the pertinence and effectiveness of consultation. Reasonable consultation duration and frequency arrangement help optimize the utilization of medical resources. For patients who need frequent consultations, it can ensure that they receive timely and effective treatment; for patients with relatively stable conditions, the number of unnecessary consultations can be reduced to avoid waste of medical resources. Personalized consultation management can better meet the needs of patients. Through in-depth analysis and utilization of consultation data, medical institutions can continuously improve and optimize consultation processes and service quality.

[0126] In one embodiment of the present invention, the interactive system comprises:

[0127] The consultation reservation record module is used to obtain consultation application information, make an appointment for consultation, obtain real-time data information during the consultation process and dynamic variable information of the consultation reservation information, pre-process and record the real-time data information, and obtain consultation record information;

[0128] The consultation record packaging and classification module is used to obtain consultation appointment data, determine the consultation node, segment and package the consultation record information and store it, obtain consultation storage data packets, perform feature extraction and feature category labeling, and then classify the consultation storage data packets to obtain feature category data groups;

[0129] The data fusion comparison module is used to obtain the phase consultation report and the comprehensive consultation report according to the consultation storage data packet, perform fusion comparison, obtain the report comparison result, annotate the node consultation data of the current comprehensive consultation report, and then generate a consultation data trend chart;

[0130] The consultation calculation and adjustment module is used to calculate the patient consultation weight factor and the patient consultation dynamic variable factor, and then calculate the patient consultation coefficient, adjust the patient consultation parameters according to the patient consultation coefficient, and obtain patient consultation adjustment data.

[0131] The working principle of the above technical solution is as follows: by collecting the consultation application information of the patient, including basic information, medical history, current symptoms, etc. Make an appointment for consultation according to the application information, and capture the data information and dynamic changes of the appointment information in the consultation process (such as consultation time adjustment, doctor change, etc.) in real time. Preprocess the real-time data information (such as data cleaning and formatting) to ensure data quality and generate detailed consultation record information. The system segments and packages the consultation record information according to the progress and key nodes of the consultation to form a consultation storage data packet. Extract features from the data packet, classify the data packet according to the marked feature category, form a feature category data group, and use the classified data packet to generate a stage consultation report and a comprehensive consultation report. The two reports are fused and compared, and the changes and differences in the consultation process are analyzed to obtain the report comparison results. In the comprehensive consultation report, the consultation data of the current node is annotated, and the consultation data trend chart is generated through data visualization technology to facilitate the visualization of the data. The system calculates the patient consultation weight factor and dynamic variable factor based on the patient's consultation record, feature category data, and dynamic variables in the consultation process. Combining these factors, the patient consultation coefficient is calculated, which can reflect the patient's overall consultation data. According to the patient consultation coefficient, the system automatically adjusts the patient's consultation parameters.

[0132] The technical effects of the above technical solutions are: saving time consumed in consultation and improving consultation efficiency through online intelligent interaction. Dynamically adjusting consultation resources according to consultation data to ensure the rational allocation and efficient use of medical resources. Real-time data recording and dynamic analysis improve the accuracy and comprehensiveness of the consultation process and the accuracy of diagnosis. Provide personalized consultation reports and trend charts. The present invention solves the problem that the traditional online consultation application and appointment process is cumbersome and difficult to monitor and adjust changes in real time. At the same time, it also solves the lack of personalized consultation management based on data analysis. When the doctor withdraws from the consultation midway due to emergency or special circumstances during the consultation, the consultation records are difficult to retrieve, analyze and manage in a targeted manner. The technical effect of intelligently adjusting the patient's future consultation parameters according to the consultation situation is achieved.

[0133] In one embodiment of the present invention, the consultation appointment recording module includes:

[0134] The consultation appointment module is used to obtain consultation application information, determine the information of the participants according to the consultation application information, and then determine the consultation appointment information; the consultation appointment information includes consultation time information, consultation personnel and consultation purpose, etc.;

[0135] A consultation is conducted according to the consultation appointment information, and real-time data information during the consultation process is obtained; the real-time data information includes consultation communication information and interactive file information, etc.

[0136] The variable acquisition module is used to obtain the consultation appointment status change information, and obtain the dynamic variable information of the consultation appointment information by combining the consultation appointment status change information with the real-time data information during the consultation process; the dynamic variable information includes the change of the consultation personnel, the change of time and the change of purpose, etc.;

[0137] Preprocessing the real-time data information to obtain preprocessed real-time data information;

[0138] The record storage module is used to store the pre-processed real-time data information to obtain consultation record information.

[0139] The working principle of the above technical solution is as follows: the present invention collects consultation application information from patients or medical institutions, and automatically or manually assists in determining the information of participants, including attending physicians, experts in relevant departments, and appointment time, etc. After determining the participants, detailed consultation appointment information is generated, including consultation time, location, list of participants and their respective roles, consultation purpose, etc. According to the consultation appointment information, online consultation invitation information is sent to relevant personnel of the organization for online consultation. During the consultation process, the system captures and records consultation communication information in real time, such as text chat, voice call, video call, etc. During or before the consultation, changes in appointment status may occur, such as time adjustment, personnel replacement, purpose change, etc. By obtaining these appointment status change information and combining real-time consultation data information, dynamic variable information of consultation appointment information is generated. The captured real-time data information is preprocessed, including data cleaning (removing useless or erroneous data), formatting (unifying data format and standards), etc. The preprocessed real-time data information is stored as consultation record information.

[0140] The technical effects of the above technical solutions are: through the online process, the communication costs and time delays in traditional consultations are reduced, and the consultation efficiency is improved. Real-time data recording and storage ensure the traceability and transparency of the consultation process. The system can capture and process changes in appointment status in real time, making the consultation plan more flexible and adaptable to actual conditions. The pre-processed real-time data provides strong data support for medical decision-making and reduces the occurrence of errors or mistakes. Based on real-time data and dynamic variable information, the system can allocate medical resources more accurately, such as reasonably allocating expert time and optimizing inspection processes. Patients can participate in the consultation process more conveniently and understand their condition and treatment plan in real time.

[0141] In one embodiment of the present invention, the consultation record packaging and classification module includes:

[0142] A node packaging module is used to obtain consultation appointment data and determine consultation nodes according to the consultation appointment data; consultation nodes can be personnel entry and exit time nodes, communication information nodes, etc.;

[0143] The consultation record information is segmented and packaged according to the consultation node information to obtain consultation data packets of multiple stages;

[0144] A packaging storage module is used to store the consultation data packets of each stage and obtain the consultation storage data packets of each stage;

[0145] A feature extraction module is used to obtain the preset consultation indicator types, and then obtain the characteristic keywords of each preset consultation indicator type;

[0146] Feature extraction is performed on the consultation storage data packets of each stage according to the feature keywords to obtain feature extraction data of the consultation storage data packets of each stage; the feature extraction data includes data of the consultation storage data packets containing the feature keywords.

[0147] The feature classification module is used to mark the consultation storage data packets of each stage with feature categories according to the feature extraction data, and obtain the marking information of the consultation storage data packets of each stage; the marking information includes the feature keywords of the consultation storage data packets.

[0148] The consultation storage data packets of each stage are classified according to the type of the marked information to obtain feature category data groups. Each feature category data group includes a plurality of data packets of the same feature category.

[0149] The working principle of the above technical solution is: obtain consultation appointment data from the database, which contains detailed arrangements for the consultation, such as participants, time, location, etc. According to the appointment data, key time nodes and communication information nodes can be identified, such as personnel entry and exit time, important discussion time period, etc. According to the identified consultation node information, the continuous consultation record information is segmented, and each segment corresponds to a specific node or time period. The segmented record information is packaged into consultation data packets of multiple stages, and each data packet contains all relevant information in the stage. The consultation data packets of each stage are stored independently to ensure the integrity and accessibility of the data. During the storage process, security measures such as data compression and encryption may also be included to improve storage efficiency and data security. The system presets a variety of consultation indicator types. For each type of consultation indicator, the system defines corresponding feature keywords, and identifies specific information content through these keywords. Using the preset feature keywords, feature extraction is performed on the consultation storage data packets of each stage. The content in the data packet that meets the description of the feature keywords is identified. The extracted feature data is annotated, and the annotation information includes the feature keywords and their specific location or context information in the data packet. According to the type of annotation information, the system classifies the consultation storage data packets of each stage. The classification is based on the type of characteristic keywords contained in the data packets. The classification results form multiple characteristic category data groups, each of which contains all data packets with the same characteristic keywords.

[0150] The technical effect of the above technical solution is: through segmentation packaging and feature extraction, the original, unstructured consultation record data is converted into a structured data set that is conducive to query and analysis. The formation of feature category data groups allows data analysts to locate the data set of interest more quickly, thereby improving analysis efficiency. The preset consultation indicator types and feature keywords help improve the recognition efficiency of specific fields and specific events. Security measures taken during data storage, such as compression and encryption, enhance data security and privacy protection.

[0151] In one embodiment of the present invention, the data fusion comparison module includes:

[0152] A comprehensive generation module is used to obtain the consultation report data of the doctor's consultation storage data package for each stage and obtain the stage consultation report;

[0153] Sort the consultation reports of each stage according to the order of the stages and generate a comprehensive consultation report;

[0154] An integrated extraction module is used to extract features from the consultation report of each stage according to feature keywords, and obtain feature extraction data of the consultation report of each stage;

[0155] The feature extraction data of each stage are integrated to obtain feature integrated extraction data; the above scheme can flexibly integrate the consultation data of each feature, so as to facilitate data analysis of each feature of the consultation.

[0156] The comparison and annotation module is used to obtain the patient's historical comprehensive consultation report, fuse and compare the report data of the historical comprehensive consultation report with the report data of the current comprehensive consultation report, and obtain the report comparison result; the fusion comparison includes obtaining the current data of each category and comparing the different data of the same category in the history.

[0157] The node consultation data of the current comprehensive consultation report is annotated according to the report comparison result; the node consultation data annotation includes annotating the node consultation data of the current comprehensive consultation report according to the difference data between the current comprehensive consultation report data and the average data of the historical comprehensive consultation report data.

[0158] The trend chart generation module is used to obtain the node consultation data annotations of each historical comprehensive consultation report and generate a consultation data trend chart.

[0159] The working principle of the above technical solution is: obtain the consultation report data written by the doctor for the consultation storage data package of each stage to form a stage consultation report. Sort these stage consultation reports in chronological or logical order, and finally generate a complete comprehensive consultation report. Perform feature extraction on the consultation report of each stage, and identify the key information points in the report based on the preset feature keywords. Integrate the feature extraction data of all stages to form feature integration extraction data. Obtain the patient's historical comprehensive consultation reports, which record the patient's past consultation situation and the doctor's advice. Fusion and comparison of the report data of the current comprehensive consultation report with the historical data, and identify the difference between the current data and the historical data through difference comparison. According to the report comparison results, the system annotates the node consultation data of the current comprehensive consultation report. The basis for annotation is the degree of difference between the current data and the historical average data. Through annotation, the doctor can intuitively see which nodes or time periods have the most significant data changes. Obtain the node consultation data annotation of each historical comprehensive consultation report, and generate a consultation data trend chart in combination with the annotation information of the current report. This chart uses time as the horizontal axis and data changes as the vertical axis, intuitively showing the long-term change trends and short-term fluctuations in patient consultation data.

[0160] The technical effect of the above technical solution is: by generating comprehensive consultation reports and extracting data through feature integration, doctors can more easily obtain comprehensive information and key features of the consultation, and improve the readability and usability of the report. Fusion and comparison of current data with historical data can help doctors understand the evolution of the patient's condition and the changing trend of treatment effects, so as to make more scientific and reasonable decisions. Through node consultation data annotation and consultation data trend charts, doctors can identify time periods and patient groups that need to be focused on, and optimize the allocation and utilization efficiency of medical resources. Through detailed consultation reports and intuitive data trend charts, patients can have a clearer understanding of their condition and treatment. The integration, comparison and analysis results of consultation data can provide valuable data support for medical research.

[0161] In one embodiment of the present invention, the consultation calculation adjustment module includes:

[0162] A weight calculation module, used to obtain new information of consultation data according to the consultation data trend chart, and calculate the patient consultation weight factor according to the new information of consultation data;

[0163] The calculation formula of the patient consultation weight factor is:

[0164]

[0165] Among them, Y qz is the patient consultation weight factor, j is the total number of stages, ΔS dAdd information to the current stage of consultation data, ΔS d-1 Add information to the consultation data of the previous stage of the current stage, ΔS i Add information to the consultation data of the i-th stage, ΔS i-1 is the new information added to the consultation data of the i-1th stage, m is the total number of characteristic keywords corresponding to the i-th stage, E ik is the preset enhancement factor of the kth feature keyword in the i-th stage, E maxik is the preset maximum possible value of the kth feature keyword in the i-th stage, α ik is the preset feature keyword weight parameter, C i To preset a specific state correction factor;

[0166] A dynamic calculation module, used to obtain dynamic variable information of each historical comprehensive consultation report, and calculate the patient consultation dynamic variable factor according to the dynamic variable information;

[0167] The calculation formula of the patient consultation dynamic variable factor is:

[0168]

[0169] Among them, D bl is the patient consultation dynamic variable factor, z is the total number of comprehensive consultation reports, m is the number of preset consultation indicator types, △L ob is the data of the bth preset consultation indicator type in the oth comprehensive consultation report, △L o-1b The data of the bth preset consultation indicator type of the o-1th comprehensive consultation report;

[0170] The consultation adjustment module is used to calculate the patient consultation coefficient according to the patient consultation weight factor combined with the patient consultation dynamic factor; the calculation formula of the patient consultation coefficient is:

[0171]

[0172] Among them, HZ is the patient consultation coefficient;

[0173] The duration or frequency of the patient's next consultation is adjusted according to the patient consultation coefficient to obtain patient consultation adjustment data.

[0174] The working principle of the above technical solution is: identify new information points or trend changes from the consultation data trend chart, which may represent new progress in the patient's condition or new situations in the treatment response. According to these new information, the weight factor of the patient consultation is calculated. The size of the weight factor reflects the importance and influence of the new information on the overall consultation situation of the patient. Obtain each historical comprehensive consultation report and extract the dynamic variable information therein, such as changes in the consultation personnel, changes in time, changes in purpose, etc. Analyze the dynamic variable information and calculate the dynamic variable factor of the patient consultation. The dynamic variable factor reflects the changes and influence of unstable factors in the patient consultation process. Combine the patient consultation weight factor with the patient consultation dynamic variable factor to calculate the patient consultation coefficient. The patient consultation coefficient is a comprehensive indicator that takes into account both the importance of the new information and the influence of historical dynamic variables, and is used to evaluate the comprehensive complexity and urgency of the patient's current consultation situation. According to the size of the patient consultation coefficient, the system automatically adjusts the duration or frequency of the patient's next consultation. If the patient consultation coefficient is high, it means that the patient's condition is complicated or changes rapidly, requiring more frequent consultations and longer consultation times; otherwise, the number of consultations can be appropriately reduced or the consultation time can be shortened.

[0175] The technical effect of the above technical solution is: by calculating the patient consultation coefficient and adjusting the consultation duration or frequency accordingly, personalized management of patient consultation is achieved, which is more in line with the actual needs of patients and improves the pertinence and effectiveness of consultation. Reasonable consultation duration and frequency arrangement help optimize the utilization of medical resources. For patients who need frequent consultations, it can ensure that they receive timely and effective treatment; for patients with relatively stable conditions, the number of unnecessary consultations can be reduced to avoid waste of medical resources. Personalized consultation management can better meet the needs of patients. Through in-depth analysis and utilization of consultation data, medical institutions can continuously improve and optimize consultation processes and service quality.

[0176] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An online consultation intelligent interaction method, characterized in that: The method comprises: S1. Obtain consultation application information, make an appointment for consultation, obtain real-time data information during the consultation process and dynamic variable information of the consultation appointment information, pre-process and record the real-time data information, and obtain consultation record information; S2, obtaining consultation appointment data, determining consultation nodes, segmenting and packaging the consultation record information and storing it, obtaining consultation storage data packets, performing feature extraction and feature category labeling, and then classifying the consultation storage data packets to obtain feature category data groups; S3. Acquire the phase consultation report and the comprehensive consultation report according to the consultation storage data packet, perform fusion comparison, obtain the report comparison result, annotate the node consultation data of the current comprehensive consultation report, and then generate a consultation data trend chart; S4. Calculate the patient consultation weight factor and the patient consultation dynamic variable factor, and then calculate the patient consultation coefficient, adjust the patient consultation parameters according to the patient consultation coefficient, and obtain patient consultation adjustment data.

2. According to claim 1, an online consultation intelligent interaction method is characterized in that: The S1 includes: Obtain consultation application information, determine the information of participants based on the consultation application information, and then determine the consultation appointment information; Conduct a consultation according to the consultation appointment information and obtain real-time data information during the consultation process; Acquire consultation appointment status change information, and acquire dynamic variable information of the consultation appointment information by combining the consultation appointment status change information with real-time data information during the consultation process; Preprocessing the real-time data information to obtain preprocessed real-time data information; The pre-processed real-time data information is stored to obtain consultation record information.

3. According to claim 1, an online consultation intelligent interaction method is characterized in that: The S2 includes: Obtain consultation appointment data, and determine a consultation node according to the consultation appointment data; The consultation record information is segmented and packaged according to the consultation node information to obtain consultation data packets of multiple stages; The consultation data packets of each stage are stored to obtain the consultation storage data packets of each stage; Obtaining preset consultation indicator types, and then obtaining characteristic keywords for each preset consultation indicator type; Extracting features of the consultation storage data packets at each stage according to the feature keywords to obtain feature extraction data of the consultation storage data packets at each stage; Marking the consultation storage data packets of each stage with feature categories according to the feature extraction data to obtain the marking information of the consultation storage data packets of each stage; The consultation storage data packets of each stage are classified according to the types of annotation information to obtain feature category data groups.

4. According to claim 1, an online consultation intelligent interaction method is characterized in that: The S3 includes: Obtain the doctor's consultation report data of each stage of the consultation storage data package to obtain the stage consultation report; Sort the consultation reports of each stage according to the order of the stages and generate a comprehensive consultation report; Extract features from the consultation report of each stage according to the feature keywords, and obtain feature extraction data of the consultation report of each stage; Integrate the feature extraction data of each stage to obtain feature integration extraction data; Obtain the patient's historical comprehensive consultation report, merge and compare the report data of the historical comprehensive consultation report with the report data of the current comprehensive consultation report, and obtain a report comparison result; Mark the node consultation data of the current comprehensive consultation report according to the report comparison results; Obtain the node consultation data annotation of each historical comprehensive consultation report and generate a consultation data trend chart.

5. According to claim 1, the online consultation intelligent interaction method is characterized in that: The S4 includes: Acquire new information of consultation data according to the consultation data trend chart, and calculate the patient consultation weight factor according to the new information of consultation data; Acquire dynamic variable information of each historical comprehensive consultation report, and calculate the patient consultation dynamic variable factor according to the dynamic variable information; The patient consultation coefficient is calculated based on the patient consultation weight factor combined with the patient consultation dynamic factor; The duration or frequency of the patient's next consultation is adjusted according to the patient consultation coefficient to obtain patient consultation adjustment data.

6. An online consultation intelligent interactive system, characterized in that: The interactive system comprises: The consultation reservation record module is used to obtain consultation application information, make an appointment for consultation, obtain real-time data information during the consultation process and dynamic variable information of the consultation reservation information, pre-process and record the real-time data information, and obtain consultation record information; The consultation record packaging and classification module is used to obtain consultation appointment data, determine the consultation node, segment and package the consultation record information and store it, obtain consultation storage data packets, perform feature extraction and feature category labeling, and then classify the consultation storage data packets to obtain feature category data groups; The data fusion comparison module is used to obtain the phase consultation report and the comprehensive consultation report according to the consultation storage data packet, perform fusion comparison, obtain the report comparison result, annotate the node consultation data of the current comprehensive consultation report, and then generate a consultation data trend chart; The consultation calculation and adjustment module is used to calculate the patient consultation weight factor and the patient consultation dynamic variable factor, and then calculate the patient consultation coefficient, adjust the patient consultation parameters according to the patient consultation coefficient, and obtain patient consultation adjustment data.

7. The online consultation intelligent interactive system according to claim 6, characterized in that: The consultation appointment record module includes: The consultation appointment module is used to obtain consultation application information, determine the information of participants according to the consultation application information, and then determine the consultation appointment information; Conduct a consultation according to the consultation appointment information and obtain real-time data information during the consultation process; A variable acquisition module is used to acquire consultation appointment status change information, and acquire dynamic variable information of the consultation appointment information by combining the consultation appointment status change information with real-time data information during the consultation process; Preprocessing the real-time data information to obtain preprocessed real-time data information; The record storage module is used to store the pre-processed real-time data information to obtain consultation record information.

8. The online consultation intelligent interactive system according to claim 6, characterized in that: The consultation record packaging and classification module includes: A node packaging module, used to obtain consultation appointment data and determine the consultation node according to the consultation appointment data; The consultation record information is segmented and packaged according to the consultation node information to obtain consultation data packets of multiple stages; A packaging storage module is used to store the consultation data packets of each stage and obtain the consultation storage data packets of each stage; A feature extraction module is used to obtain the preset consultation indicator types, and then obtain the characteristic keywords of each preset consultation indicator type; Extracting features of the consultation storage data packets at each stage according to the feature keywords to obtain feature extraction data of the consultation storage data packets at each stage; A feature classification module is used to mark the consultation storage data packets of each stage with feature categories according to the feature extraction data, and obtain the marking information of the consultation storage data packets of each stage; The consultation storage data packets of each stage are classified according to the types of annotation information to obtain feature category data groups.

9. The online consultation intelligent interactive system according to claim 6, characterized in that: The data fusion comparison module includes: A comprehensive generation module is used to obtain the consultation report data of the doctor's consultation storage data package for each stage and obtain the stage consultation report; Sort the consultation reports of each stage according to the order of the stages and generate a comprehensive consultation report; An integrated extraction module is used to extract features from the consultation report of each stage according to feature keywords, and obtain feature extraction data of the consultation report of each stage; Integrate the feature extraction data of each stage to obtain feature integration extraction data; A comparison and annotation module is used to obtain the patient's historical comprehensive consultation report, merge and compare the report data of the historical comprehensive consultation report with the report data of the current comprehensive consultation report, and obtain a report comparison result; Perform node consultation data annotation on the current comprehensive consultation report according to the report comparison result; the node consultation data annotation includes difference data between the current comprehensive consultation report data and the average data of the historical comprehensive consultation report data; The trend chart generation module is used to obtain the node consultation data annotations of each historical comprehensive consultation report and generate a consultation data trend chart.

10. The online consultation intelligent interactive system according to claim 6, characterized in that: The consultation calculation and adjustment module includes: A weight calculation module, used to obtain new information of consultation data according to the consultation data trend chart, and calculate the patient consultation weight factor according to the new information of consultation data; A dynamic calculation module, used to obtain dynamic variable information of each historical comprehensive consultation report, and calculate the patient consultation dynamic variable factor according to the dynamic variable information; A consultation adjustment module, used to calculate a patient consultation coefficient based on a patient consultation weight factor combined with a patient consultation dynamic factor; The duration or frequency of the patient's next consultation is adjusted according to the patient consultation coefficient to obtain patient consultation adjustment data.

Images