A visual government service data interaction risk monitoring system

Abstract

The present invention discloses a visual government service data interaction risk monitoring system, which relates to the field of risk management technology. The system includes: a monitoring record acquisition module for acquiring distributed monitoring records of medical insurance services; a service interaction timing acquisition module for acquiring a first service interaction timing; an interaction pattern clustering module for analyzing multiple interaction patterns and clustering them; a target service interaction extraction module for extracting a first target service interaction; an interaction risk assessment module for performing a risk assessment on the first target service interaction; and an early warning processing module for performing early warning processing. The present invention solves the technical problem in the prior art of low efficiency and accuracy of interaction risk monitoring due to the complexity of medical insurance service data, interaction platforms, and interaction patterns, and achieves the technical effect of improving the security and efficiency of medical insurance data interaction through distributed monitoring and clustered risk assessment of medical insurance service data.

Description

Technical Field

[0001] The present invention relates to the field of risk management technology, and in particular to a visual government service data interaction risk monitoring system. Background Art

[0002] With the in-depth development of the "Internet + Government Services" model, government services are shifting towards digitalization, networking, and intelligence. As an important component of government service data exchange, medical insurance service data exchange is of great significance for improving medical insurance service efficiency, optimizing the business environment, and enhancing user experience.

[0003] However, due to the complexity and diversity of medical insurance data, different service models and deployment models, and the complexity of the shared exchange platform environment, the difficulty of monitoring data interaction risks has increased. Existing monitoring technologies also have problems with low risk monitoring efficiency and low accuracy. Summary of the Invention

[0004] This application provides a visual government service data interaction risk monitoring system to solve the technical problems in the existing technology of low efficiency and accuracy of interaction risk monitoring due to the complexity of medical insurance service data, interaction platforms, and interaction modes.

[0005] The present application provides a visual government service data interaction risk monitoring system, the system comprising: a monitoring record acquisition module, the monitoring record acquisition module is used to interactively monitor medical insurance services through distributed risk monitoring equipment to obtain distributed monitoring records, the distributed monitoring records including multiple service interaction records with the identification of medical insurance service agencies; a service interaction timing acquisition module, the service interaction timing acquisition module is used to filter out a first service interaction record set of a first medical insurance user from the multiple service interaction records with the identification of medical insurance service agencies, and time-sequence the first service interaction record set to obtain a first service interaction timing; an interaction pattern clustering module, the interaction pattern clustering module is used to analyze and obtain multiple interaction patterns corresponding to multiple service interactions in the first service interaction timing, and combine the predetermined interaction patterns to obtain a first service interaction record set. An interaction pattern clustering strategy clusters the interaction patterns of the multiple service interactions to obtain a first clustering result; a target service interaction extraction module, the target service interaction extraction module is used to extract a first clustering cluster of the first interaction pattern in the first clustering result, and extract the first target service interaction in the first clustering cluster, the first interaction pattern being any one of the multiple interaction patterns; an interaction risk assessment module, the interaction risk assessment module is used to perform a risk assessment on the first target service interaction in combination with a first predetermined interaction benchmark of the first interaction pattern to obtain a first target risk index; an early warning processing module, the early warning processing module is used to issue an early warning instruction when the first target risk index reaches a first index limit, and perform early warning processing on the first target service interaction based on the early warning instruction.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The present application provides a visual government service data interaction risk monitoring system, which relates to the field of risk management technology. It uses distributed risk monitoring equipment to interactively monitor medical insurance services, obtains distributed monitoring records, and time-series service interaction record sets to obtain service interaction time sequences. It analyzes multiple interaction modes corresponding to multiple service interactions in the service interaction time sequences, conducts risk assessment according to predetermined interaction benchmarks, and performs early warning processing based on target risk indexes. It solves the technical problem of low efficiency and accuracy of interactive risk monitoring in the existing technology due to the complexity of medical insurance service data, interaction platforms, and interaction modes, and achieves the technical effect of improving the security and efficiency of medical insurance data interaction through distributed monitoring and clustered risk assessment of medical insurance service data. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A schematic diagram of the structure of a visual government service data interaction risk monitoring system provided in an embodiment of the present application;

[0010] Figure 2 A schematic diagram of a process for obtaining a target risk index in a visual government service data interaction risk monitoring system provided in an embodiment of the present application;

[0011] Figure 3 A flowchart of generating a target hierarchical visual graph in a visual government service data interaction risk monitoring system provided in an embodiment of the present application.

[0012] Explanation of the reference numerals: monitoring record acquisition module 11 , service interaction timing acquisition module 12 , interaction pattern clustering module 13 , target service interaction extraction module 14 , interaction risk assessment module 15 , early warning processing module 16 . DETAILED DESCRIPTION

[0013] This application provides a visual government service data interaction risk monitoring system to solve the technical problems in the existing technology of low efficiency and accuracy of interaction risk monitoring due to the complexity of medical insurance service data, interaction platforms, and interaction modes.

[0014] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0015] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices.

[0016] Example 1

[0017] like Figure 1 As shown, the present application provides a visual government service data interaction risk monitoring system, the system comprising:

[0018] The monitoring record acquisition module 11 is used to interactively monitor medical insurance services through distributed risk monitoring equipment to obtain distributed monitoring records, which include multiple service interaction records with the identification of medical insurance service agencies.

[0019] Specifically, the monitoring record acquisition module 11 of the present application has the main function of real-time monitoring and data collection of medical insurance services through distributed risk monitoring equipment. First, the module needs to establish a connection with multiple risk monitoring devices distributed in the medical insurance service system and perform necessary configurations. The risk monitoring equipment may include network monitoring equipment, database access interfaces, service log recording systems, etc., which together constitute a distributed risk monitoring network. After the connection is established, the monitoring record acquisition module 11 can collect distributed monitoring records from each device. The distributed monitoring records are mainly interaction records in the medical insurance service process. Each record contains the identification information of the medical insurance service agency, which can facilitate subsequent identification and classification, and provide data support for subsequent interaction pattern analysis.

[0020] During the data collection process, the monitoring record acquisition module 11 can also perform preliminary anomaly detection on the data. For example, if the frequency of a service interaction record is found to be abnormally high or low, or the interaction records of a service agency suddenly increase or decrease, the module can immediately issue an early warning, prompting the system administrator to check and handle the problem.

[0021] The service interaction timing acquisition module 12 is used to filter out the first service interaction record set of the first medical insurance user from the multiple service interaction records with the identification of the medical insurance service agency, and time-sequence the first service interaction record set to obtain a first service interaction timing.

[0022] It should be understood that the service interaction sequence acquisition module 12 of the present application is mainly responsible for screening out a set of service interaction records of a specific medical insurance user (e.g., the first medical insurance user) from multiple service interaction records with medical insurance service agency identification, and organizing these records into an ordered service interaction sequence based on their timestamps or occurrence order, i.e., the first service interaction sequence. This is the first visualization method in this solution, which uses time series charts, such as line charts or bar charts, to display trends and patterns of data interactions for data that changes over time.

[0023] Specifically, first retrieve all service interaction records about the first medical insurance user from the distributed monitoring records. These records may come from multiple different medical insurance service agencies, covering the user's interaction behaviors at different times and on different service channels. Furthermore, for the filtered service interaction record set of the first medical insurance user, sort them according to the timestamp or the order in which the interactions occurred. If some records lack timestamps or the time information is incomplete, use other information (such as service processing time, log recording time, etc.) to approximately determine the order in which they occurred, and then generate the first service interaction sequence. The first service interaction sequence not only records every interaction between the user and the service agency, but also clearly marks the time point and order of each interaction. It can be used to identify user behavior patterns, service usage habits, and possible risk points, and provide strong data support for subsequent risk assessment and early warning.

[0024] The interaction pattern clustering module 13 is used to analyze and obtain multiple interaction patterns corresponding to multiple service interactions in the first service interaction sequence, and cluster the interaction patterns of the multiple service interactions in combination with a predetermined interaction pattern clustering strategy to obtain a first clustering result.

[0025] Optionally, the interaction pattern clustering module 13 of the present application is responsible for analyzing multiple interaction patterns corresponding to multiple service interactions in the first service interaction sequence, and clustering the service interactions according to a predetermined interaction pattern clustering strategy. Specifically, first, the key features of each interaction are extracted from the first service interaction sequence. These features may include interaction media, interaction material type, interaction means, etc. Further, based on the extracted features, a machine learning algorithm or a statistical model is used to identify multiple interaction patterns corresponding to multiple service interactions. For example, sample feature data is collected based on different interaction patterns, and supervised training is performed in combination with a machine learning algorithm to obtain an interaction pattern recognition model, and the interaction pattern recognition model is used to identify multiple interaction patterns corresponding to multiple service interactions. The interaction patterns may include online service interactions, telephone consultation interactions, paper document interactions, email interactions, etc.

[0026] Furthermore, multiple service interaction tasks are clustered according to a predetermined interaction pattern clustering strategy. That is, the interaction pattern is used as the clustering target, and service interaction data with the same clustering pattern is clustered into one category. For example, all service interaction tasks through online service interaction can be grouped into one cluster, and all service interaction tasks through telephone consultation interaction can be grouped into another cluster through algorithms such as K-Means and hierarchical clustering. This achieves the purpose of classifying the number of interactions according to the interaction pattern, and obtains a first clustering result. The first clustering result includes multiple clusters, each cluster representing an interaction pattern and containing multiple service interaction records belonging to that pattern. This can be used to identify and classify different patterns in service interactions, providing strong support for subsequent risk assessment and early warning.

[0027] The target service interaction extraction module 14 is configured to extract a first cluster of a first interaction mode from the first clustering result and extract a first target service interaction from the first cluster, wherein the first interaction mode is any one of the plurality of interaction modes.

[0028] It should be understood that the target service interaction extraction module 14 of the present application is responsible for extracting service interaction records under a specific interaction mode (such as the first interaction mode) from the clustering results. Specifically, first identify the cluster corresponding to the first interaction mode from the first clustering result. Among them, the first interaction mode can be any one of a plurality of interaction modes, such as online service interaction, which can be determined according to system requirements or risk levels. Further, extract the first cluster corresponding to the first interaction mode, and the cluster contains all service interaction records belonging to the first interaction mode. Extract specific service interaction records from the first cluster as the first target service interaction, for example, extract any online service interaction record as the first target service interaction. These records will be the objects of subsequent risk assessment.

[0029] The interaction risk assessment module 15 is configured to perform a risk assessment on the first target service interaction in combination with a first predetermined interaction benchmark of the first interaction mode to obtain a first target risk index.

[0030] Further, such as Figure 2 As shown, the interactive risk assessment module 15 is further configured to perform the following steps:

[0031] P51: Reading predetermined interaction indicators, which include interaction mode, number of interactions, and interaction category;

[0032] P52: Collect interaction features of the first target service interaction corresponding to the first interaction mode based on the predetermined interaction indicator to obtain a target interaction indicator parameter;

[0033] P53: Compare the target interaction index parameter with the first predetermined interaction benchmark to obtain a target comparison deviation;

[0034] P54: The target comparison deviation after weighted normalization processing obtains the first target risk index.

[0035] Furthermore, step P53 of the embodiment of the present application further includes:

[0036] P53-1: Matching the first interaction feature parameter corresponding to the first interaction mode in the medical insurance interaction database to obtain the first predetermined interaction benchmark;

[0037] P53-2: In which, the medical insurance interaction database includes interaction feature data of predetermined medical insurance interaction modes, and the predetermined medical insurance interaction modes include at least online service interaction, telephone consultation interaction, paper document interaction, email interaction, three-party service interaction and face-to-face interaction.

[0038] Optionally, the interaction risk assessment module 15 of the present application is primarily responsible for performing a risk assessment on the first target service interaction based on a first predetermined interaction benchmark of the first interaction mode. Specifically, the module first reads predetermined interaction indicators, which typically include the interaction mode (e.g., online, telephone, face-to-face, etc.), the number of interactions (e.g., the number of user requests), and the interaction category (e.g., consultation, complaint, application, etc.).

[0039] Furthermore, based on the predetermined interaction indicator, relevant interaction feature data is collected from the first target service interaction corresponding to the first interaction mode, such as the user's actual interaction method, the actual number of interactions, and the specific interaction category, as target interaction indicator parameters. Furthermore, the collected target interaction indicator parameters are compared with the first predetermined interaction benchmark to identify the difference or deviation between the two, thereby obtaining a target comparison deviation, i.e., the deviation between the user's actual interaction indicator and the standard interaction indicator. For example, while an email interaction generally requires two interactions, if four interactions are actually recorded, the deviation from the predetermined number of interactions is significant, indicating a high interaction risk.

[0040] Among them, the first predetermined interaction benchmark is the standard interaction indicator value of each interaction mode, such as standard interaction duration, standard interaction platform, etc. In addition, the first interaction feature parameter corresponding to the first interaction mode can be matched in the medical insurance interaction database as the first predetermined interaction benchmark corresponding to the first interaction mode. The medical insurance interaction database is a database that stores interaction feature data of multiple predetermined medical insurance interaction modes. In addition, the predetermined medical insurance interaction modes may include multiple types such as online service interaction, telephone consultation interaction, and paper document interaction. The predetermined medical insurance interaction modes in the medical insurance interaction database show various interaction methods that may be adopted by medical insurance services. The selection of these methods is usually based on the nature of the service, user preferences and technical feasibility.

[0041] Furthermore, because different interaction indicators may have different importance and dimensions, the target comparison deviations need to be normalized to eliminate the impact of dimension, so that the individual comparison deviations can be directly added or subtracted numerically. Furthermore, based on historical data, expert experience, and business needs, weights are set for different interaction indicators, and the target comparison deviations of different interaction indicators are weighted according to the set weights to obtain the first target risk index, i.e., the risk index of the first target service interaction, which reflects the risk level of the first target service interaction relative to the predetermined interaction benchmark.

[0042] The early warning processing module 16 is configured to issue an early warning instruction when the first target risk index reaches a first index limit, and perform early warning processing on the first target service interaction based on the early warning instruction.

[0043] Furthermore, the warning processing module 16 is further configured to perform the following steps:

[0044] P61: Obtain historical medical insurance service interaction records, and extract the first historical record in the first interaction mode from the historical medical insurance service interaction records;

[0045] P62: Analyze the first historical records to obtain a first risk ratio of the first interaction mode, and set the first index limit based on the first risk ratio.

[0046] It should be understood that the early warning processing module 16 of the present application is responsible for issuing early warnings when possible risks are detected and taking appropriate early warning processing measures. Specifically, historical medical insurance service interaction records are first obtained. These records contain detailed data on medical insurance service interactions over a period of time, such as user behavior, interaction time, and interaction results. Furthermore, historical records related to the current first interaction mode are screened out from the historical medical insurance service interaction records, i.e., the first historical records.

[0047] Furthermore, by analyzing the interaction data in the first historical record, the ratio of risks (such as errors, anomalies, complaints, etc.) occurring in the first interaction mode is calculated, for example, by calculating the proportion of risk events to the total number of events, to obtain a first risk ratio. This ratio reflects the risk level of the interaction mode. Furthermore, based on the first risk ratio, the first index limit, i.e., the risk threshold corresponding to the first interaction mode, is set. The higher the first risk ratio, the smaller the corresponding risk threshold range.

[0048] When the first target risk index reaches or exceeds the first index limit, the early warning processing module 16 will immediately issue an early warning instruction. This instruction can be a notification, an alarm, or an automatically executed corrective action. Based on the early warning instruction, the system can take various early warning measures, such as suspending related services, notifying relevant personnel for processing, and automatically correcting errors. This reduces risks, protects user rights, and ensures the normal operation of medical insurance services.

[0049] Further, such as Figure 3 As shown, the embodiment of the present application further includes step P70, and step P70 further includes:

[0050] P71: Extracting first interaction data in the first target service interaction;

[0051] P72: Obtaining the first importance of the first interaction data based on the expert decision method;

[0052] P73: Generate a target hierarchical visualization graph of the interaction data in the first target service interaction based on the first importance.

[0053] Optionally, in order to further analyze and visualize the data in the first target service interaction, this application introduces a second visualization method, which is to stratify the data according to priority or importance, and prioritize the display of an overview of high-level data, gradually allowing users to drill down to more detailed levels. Specifically, the first interaction data in the first target service interaction is extracted from the service interaction records through log analysis, database query, etc., that is, the specific information generated during the first target service interaction process, which may include user input, system response, interaction time, interaction results, and other aspects.

[0054] Furthermore, the importance of the interaction data is assessed based on an expert decision-making method, which relies on expert experience and knowledge to determine data importance. By inviting experts in the field to analyze and evaluate the first interaction data, an importance score for each data item, namely, a first importance, can be obtained. This first importance can reflect the importance of each data item in the first interaction data. The importance of these data items may vary depending on factors such as their role in the service interaction process and their impact on the results.

[0055] Furthermore, based on the first importance score of the first interaction data, the individual data items in the first interaction data are sorted from high to low in importance and displayed in a target hierarchical visualization. Other interactive elements, such as connecting lines and annotations, can be added as needed to further explain the relationships and meanings between the data. The target hierarchical visualization is a visualization tool that displays data in layers according to importance. By reflecting the importance of data through visual elements such as color, size, and position, users can intuitively understand the relationships between data and differences in importance.

[0056] Generating the target hierarchical visualization helps users intuitively understand the relationships and importance differences between data. Furthermore, as service interactions progress, interaction data is constantly updated. Therefore, the target hierarchical visualization needs to be regularly updated to ensure that the data it reflects is current and accurate.

[0057] Furthermore, the embodiment of the present application further includes step P80, which further includes:

[0058] P81: Clustering the plurality of service interaction records having identifiers of the medical insurance service institutions based on a predetermined medical insurance service institution clustering strategy to obtain a second clustering result;

[0059] P82: extracting a second cluster of the first medical insurance service agency from the second clustering result, and extracting a second target service interaction from the second cluster;

[0060] P83: Record the average of the risk indexes of the second target service interactions as the second target risk index;

[0061] P84: When the second target risk index reaches the predetermined index limit, an early warning will be issued to the first medical insurance service agency.

[0062] The predetermined medical insurance service agency clustering strategy refers to clustering the medical insurance service agencies obtained by the monitoring components in the distributed risk monitoring device.

[0063] In a possible embodiment of the present application, different from the above-mentioned predetermined interaction pattern clustering strategy, the present application also provides a method for clustering analysis and early warning of service interaction records based on the predetermined medical insurance service agency clustering strategy. Specifically, first, the service interaction records that have the identification of the medical insurance service agency for multiple times are clustered based on the predetermined medical insurance service agency clustering strategy. The predetermined medical insurance service agency clustering strategy refers to clustering the medical insurance service agencies obtained by each monitoring component in the distributed risk monitoring device, that is, a strategy for clustering according to the characteristics and similarities of the medical insurance service agencies. For example, based on the geographical location, service scope, user group, service quality and other factors of the medical insurance service agency, a clustering algorithm (such as K-means, hierarchical clustering, etc.) can be used to cluster the service interaction records that have the identification of the medical insurance service agency for multiple times to obtain multiple clustering results, that is, the second clustering result.

[0064] Furthermore, a specific medical insurance service organization, i.e., the first medical insurance service organization, is selected or identified from the multiple clustering results. A cluster related to the first medical insurance service organization, i.e., the second cluster, is extracted from the second clustering results. Service interaction records related to the first medical insurance service organization are then extracted from the second cluster, i.e., the second target service interaction. Furthermore, the risk index of each service interaction record in the second target service interaction is statistically analyzed, and the mean is calculated to obtain the second target risk index. This mean reflects the average risk level of service interactions with the first medical insurance service organization over a specific time period.

[0065] Furthermore, referring to the method for setting the first index limit described above, interaction indicators for medical insurance service organizations are extracted, and risk index limits for medical insurance service organizations, i.e., predetermined index limits, are preset to determine whether the risk level of the medical insurance service organizations has reached a level requiring an early warning. When the second target risk index reaches or exceeds the predetermined index limit, indicating that the interaction risk of the first medical insurance service organization has exceeded the threshold, the system will issue an early warning instruction to the first medical insurance service organization and implement corresponding early warning measures, including notifying relevant personnel, suspending services, conducting risk investigations, etc., to mitigate the risks that may be posed by the medical insurance service organization.

[0066] In summary, the embodiments of the present application have at least the following technical effects:

[0067] This application interactively monitors medical insurance services through distributed risk monitoring equipment to obtain distributed monitoring records. By analyzing the record data of each institution, the medical insurance services of each institution are visualized, and the medical insurance service record data of each user across multiple institutions are integrated and analyzed to visualize the medical insurance services of each user. Furthermore, the medical insurance services of each user are clustered to achieve visual clustering analysis of similar medical insurance users, and risk assessment is performed according to a predetermined interactive benchmark, and early warning processing is performed according to the target risk index.

[0068] The technical effect of improving the security and efficiency of medical insurance data interaction has been achieved through distributed monitoring and clustered risk assessment of medical insurance service data.

[0069] Moreover, all the visualizations in this technical solution are based on the characteristics of the medical insurance service itself and are not suitable for all government services. It is mainly based on actual scenarios where there are multiple medical clinics, pharmacies and other places that can swipe medical insurance and provide medical insurance services. Other types of government services do not have this feature. Therefore, this technical solution can provide reference for other government service fields and cannot be transferred.

[0070] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0071] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0072] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A visual government service data interaction risk monitoring system, characterized by: include: A monitoring record acquisition module, the monitoring record acquisition module is used to interactively monitor medical insurance services through distributed risk monitoring equipment to obtain distributed monitoring records, the distributed monitoring records including multiple service interaction records with the identification of medical insurance service institutions; a service interaction time sequence acquisition module, the service interaction time sequence acquisition module being configured to filter out a first service interaction record set of a first medical insurance user from the plurality of service interaction records having an identifier of the medical insurance service institution, and time sequence the first service interaction record set to obtain a first service interaction time sequence; an interaction pattern clustering module, configured to analyze and obtain a plurality of interaction patterns corresponding to a plurality of service interactions in the first service interaction sequence, and cluster the interaction patterns of the plurality of service interactions according to a predetermined interaction pattern clustering strategy to obtain a first clustering result; a target service interaction extraction module, configured to extract a first cluster of a first interaction mode from the first clustering result, and extract a first target service interaction from the first cluster, wherein the first interaction mode is any one of the plurality of interaction modes; an interaction risk assessment module, configured to perform a risk assessment on the first target service interaction in combination with a first predetermined interaction benchmark of the first interaction mode to obtain a first target risk index; an early warning processing module, configured to issue an early warning instruction when the first target risk index reaches a first index limit, and perform early warning processing on the first target service interaction based on the early warning instruction; matching a first interaction feature parameter corresponding to the first interaction mode in a medical insurance interaction database to obtain the first predetermined interaction benchmark; The medical insurance interaction database includes interaction feature data of predetermined medical insurance interaction modes, wherein the predetermined medical insurance interaction modes include at least online service interaction, telephone consultation interaction, paper document interaction, email interaction, third-party service interaction, and face-to-face interaction; Acquire historical medical insurance service interaction records, and extract a first history record in the first interaction mode from the historical medical insurance service interaction records; analyzing the first historical records to obtain a first risk ratio of the first interaction mode, and setting the first index limit based on the first risk ratio; Reading predetermined interaction indicators; Based on the predetermined interaction indicator, interaction characteristics of the first target service interaction corresponding to the first interaction mode are collected to obtain a target interaction indicator parameter; Comparing the target interaction index parameter with the first predetermined interaction benchmark to obtain a target comparison deviation; The target comparison deviation after weighted normalization processing is used to obtain the first target risk index; Clustering the plurality of service interaction records having identifiers of medical insurance service agencies based on a predetermined medical insurance service agency clustering strategy to obtain a second clustering result, wherein the predetermined medical insurance service agency clustering strategy refers to clustering the medical insurance service agencies obtained by the monitoring components in the distributed risk monitoring device; Extracting a second cluster of the first medical insurance service agency from the second clustering result, and extracting a second target service interaction from the second cluster; Recording the average of the risk indexes of the second target service interactions as the second target risk index; When the second target risk index reaches a predetermined index limit, an early warning is issued to the first medical insurance service agency.

2. A visual government service data interaction risk monitoring system according to claim 1, characterized in that: The predetermined interaction indicators include interaction mode, interaction times and interaction category.

3. According to claim 1, a visual government service data interaction risk monitoring system is characterized in that: Also includes: Extracting first interaction data from the first target service interaction; Obtaining a first importance of the first interaction data based on an expert decision method; A target hierarchical visualization graph of interaction data in the first target service interaction is generated based on the first importance.

Images