A medical insurance intelligent management method and system based on data fusion
By analyzing the data fusion deviations of medical insurance data channels and adopting appropriate detection strategies for anomaly detection channel data processing, the reliability and accuracy issues of data in existing technologies have been resolved, ensuring the reliability and accuracy of medical insurance data and achieving the desired data reliability and accuracy.
Patent Information
- Application Number
- CN202510460975.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-14
- Publication Date
- 2025-12-16
- Estimated Expiration
- 2045-04-14
AI Technical Summary
The reliability of the medical insurance data resource pool is difficult to meet the requirements, resulting in problems such as data format mismatch or interface mismatch during data interaction, which affects the monitoring and analysis of medical insurance data and the timely detection of anomalies.
By analyzing the data fusion deviations from different channels, the channels with fusion deviations are identified. Based on the analysis results of medical data of related medical insurance users, the types of fusion processing needs are determined, and appropriate detection strategies are adopted to detect anomalies and ensure data reliability.
It ensures the accuracy and reliability of medical insurance data, and improves the reliability and accuracy of data fusion processing by handling the differences in data fusion needs from different channels through differentiated detection strategies.
Smart Images
Figure CN120296673B_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The application belongs to the technical field of data processing, and particularly relates to a medical insurance intelligent management method and system based on data fusion. BACKGROUND
[0002] The medical insurance system involves a large number of people, and therefore, in order to realize data management of medical insurance data, data needs to be collected from multiple channels such as medical insurance systems, medical institutions, health departments, civil affairs systems and tax systems, covering insurance information, medical consumption records, drug use conditions, disease diagnosis results, health archives and the like, to form a comprehensive medical insurance data resource pool.
[0003] However, in actual operation, due to the existence of a certain degree of deviation in information systems and data interfaces of different channels, it may cause data format mismatch or data interface mismatch during data interaction, so that the data reliability of the medical insurance data resource pool cannot meet the requirements, and therefore, how to monitor and analyze the medical insurance data to timely and effectively find abnormal conditions and potential risks becomes a technical problem to be solved.
[0004] To solve the above technical problems, the application provides a medical insurance intelligent management method and system based on data fusion. SUMMARY
[0005] To achieve the object of the application, the application adopts the following technical solutions:
[0006] Specifically, in a first aspect, the application provides a medical insurance intelligent management method based on data fusion, which specifically comprises:
[0007] S1 determining a fusion deviation channel of the channel by using the fusion deviation condition of the associated data of different channels between different medical insurance users and other channels;
[0008] S2 determining an associated medical insurance user of the channel based on the associated data of the medical insurance user of the channel, and determining a fusion processing demand type of the associated medical insurance user based on the analysis result of the medical data of the associated medical insurance user;
[0009] S3 acquiring constituent data of the associated medical insurance user of different fusion processing demand types of the channel, and determining that the channel does not need to be detected and analyzed by using a preset strategy, and entering the next step in combination with the associated data of the fusion deviation channel of different associated medical insurance users;
[0010] S4 acquiring a response abnormal condition of the channel during data fusion processing of different associated medical insurance users in a preset period of time, and determining an abnormal detection method of the channel based on distributed discrete data of the response abnormality between the associated channels of the associated medical insurance users.
[0011] The beneficial effects of the present application are:
[0012] Based on the analysis result of the medical data of the associated medical insurance user, the fusion processing demand type of the associated medical insurance user is determined, so as to realize the determination of the disease type of the associated medical insurance user from the analysis result of the medical data of the associated medical insurance user, and further realize the difference of the re-consultation demand of the associated medical insurance user caused by the difference of the disease type, and further realize the difference of the data fusion processing demand of the medical insurance data of different channels, and generate a differentiated channel data port detection strategy according to the difference of the data fusion demand of the associated medical insurance user, and lay a foundation for ensuring the data reliability of the channel.
[0013] According to the response abnormality of the channel in the data fusion processing of different associated medical insurance users in a preset period, and the distribution discrete data of the response abnormality of the associated channels of the associated medical insurance users, the abnormality detection method of the channel is determined, which not only considers the response abnormality of the channel in the data fusion processing, but also considers the response abnormality of the associated channels of the associated medical insurance users, realizes the determination of the abnormality detection method of the channel from the perspective of ensuring the reliability of the data fusion processing of the associated medical insurance users, ensures the data reliability and accuracy of the medical insurance database, and also ensures the reliability of the data fusion processing between different channels.
[0014] The further technical scheme is that the channel includes a drugstore, a medical insurance system, a medical institution, a health and health department, a civil affairs system and a tax system.
[0015] The further technical scheme is that the fusion deviation situation is according to the fusion failure number of different fusion failure types in the fusion processing process of the channel and other channels.
[0016] The further technical scheme is that the fusion failure type includes response delay abnormality, data loss and data format error.
[0017] The further technical scheme is that the determination method of the fusion deviation channel of the channel is:
[0018] According to the fusion deviation situation of the channel and other channels in the fusion processing process, the fusion failure number of different medical insurance users is determined.
[0019] According to the fusion failure number of different medical insurance users, the fusion failure user in the medical insurance user is determined.
[0020] Based on the number of the fusion failure user, it is determined whether the other channel is the fusion deviation channel of the channel.
[0021] The further technical solution is that the fusion failure user is a medical insurance user whose fusion failure times are not in a preset failure times interval.
[0022] The further technical solution is that when the number of fusion failure users of the other channel and the channel is greater than a preset failure user number threshold, it is determined that the other channel is a fusion deviation channel of the channel.
[0023] The further technical solution is that the determined method of the channel anomaly detection method is:
[0024] The response anomaly of the channel in the preset period is determined by the data fusion processing of the different associated medical insurance users, and the associated medical insurance user is determined as a response anomaly user.
[0025] According to the distribution of the response anomaly of the associated channel of the associated medical insurance user, it is determined that the different associated channels have response anomaly medical insurance users, and the associated channel response anomaly coefficient is determined by the coincidence of the response anomaly medical insurance users of the different associated channels and the response anomaly medical insurance users.
[0026] Based on the associated channel response anomaly coefficient and the number of response anomaly users of the channel, the anomaly detection method of the channel is determined.
[0027] The further technical solution is that based on the associated channel response anomaly coefficient and the number of response anomaly users of the channel, the anomaly detection method of the channel is determined, specifically including:
[0028] The associated channel response anomaly coefficient and the number of response anomaly users of the channel are multiplied to determine the response anomaly factor of the channel.
[0029] When the response anomaly factor is greater than a preset anomaly factor threshold, a preset detection strategy is used for anomaly detection processing of the channel.
[0030] When the response anomaly factor is not greater than the preset anomaly factor threshold, a second preset detection strategy is used for anomaly detection processing of the channel.
[0031] The further technical solution is that the preset detection strategy is to perform real-time detection processing of the network delay of the data port of the channel.
[0032] The further technical solution is that the second preset detection strategy is to perform detection processing of the data port of the channel when there is a response anomaly.
[0033] In a second aspect, the present application provides a computer system comprising a memory and a processor connected in communication, and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to implement the above-mentioned medical insurance intelligent management method based on data fusion.
[0034] Other features and advantages will be set forth in the accompanying description, and in part will become apparent to those skilled in the art upon examination of the following or can be learned by practice of the application. The objects and advantages of the application can be realized and attained by means of the instrumentalities and combinations particularly pointed out in the description and appended claims.
[0035] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the following preferred embodiments are specifically described in detail below, and the accompanying drawings are described as follows. BRIEF DESCRIPTION OF DRAWINGS
[0036] The above-mentioned and other features and advantages of the present application will become more apparent by describing in detail example embodiments thereof with reference to the attached drawings.
[0037] Figure 1 is a flowchart of a medical insurance intelligent management method based on data fusion;
[0038] Figure 2 is a flowchart of a method for determining the fusion deviation channel of the channel;
[0039] Figure 3 is a flowchart of a method for determining the fusion processing demand type of the associated medical insurance user;
[0040] Figure 4 is a flowchart of a method for determining the abnormality detection method of the channel. DETAILED DESCRIPTION
[0041] In order to make the technical personnel in the art better understand the technical solutions in the present specification, the technical solutions in the present specification will be described in detail below with reference to the drawings in the present specification. Obviously, the described embodiments are only a part of the embodiments of the present specification, not all. Based on the embodiments of the present specification, all other embodiments obtained by those skilled in the art without creative labor should belong to the protection scope of the present specification.
[0042] Embodiment 1
[0043] As shown in Figure 1 , the present application provides a medical insurance intelligent management method based on data fusion, which specifically comprises:
[0044] S1 determines the fusion deviation channel of the channel by using the fusion deviation of different channels in the association data between different medical insurance users and other channels;
[0045] Further, the fusion deviation channel is other channels whose sum of fusion failure times of the medical insurance users of the channels is greater than a preset fusion failure time threshold.
[0046] S2 determines the associated medical insurance user of the channel based on the association data of the medical insurance user of the channel, and determines the fusion processing demand type of the associated medical insurance user based on the analysis result of the medical data of the associated medical insurance user.
[0047] It should be noted that the diagnosis disease type of the associated user is determined based on the analysis result of the medical data of the associated user, and the preset demand type corresponding to the diagnosis disease type is used as the fusion processing demand type of the associated medical insurance user.
[0048] S3 obtains the composition data of the associated medical insurance user of different fusion processing demand types of the channel, and determines that the channel does not need to use a preset strategy for detection analysis when the association data of the fusion deviation channel of the different associated medical insurance users is combined.
[0049] It can be understood that the associated medical insurance user of a type of processing demand type of the channel is determined based on the composition data of the associated medical insurance user of different fusion processing demand types of the channel, and is used as a screened medical insurance user. The number of screened medical insurance users in different fusion deviation channels is determined based on the association data of the fusion deviation channel of the screened medical insurance user, and when the number of screened medical insurance users of the fusion deviation channel is greater than a preset screened user number threshold, it is determined that the channel needs to use a preset strategy for detection analysis.
[0050] S4 obtains the response abnormality of the channel in the data fusion processing of different associated medical insurance users in a preset time period, and determines the abnormality detection method of the channel based on the distribution discrete data of the response abnormality between the associated channels of the associated medical insurance users.
[0051] It should be noted that the associated medical insurance user of the channel exists response abnormality is determined as the response abnormality user of the channel based on the response abnormality of the channel in the data fusion processing of different associated medical insurance users in a preset time period, and the distribution discrete coefficient of different associated channels is determined based on the proportion of the number of response abnormality medical insurance users of different associated channels that do not exist in the other associated channels, and the average value of the distribution discrete coefficient of different associated channels and the average value of the proportion of the number of response abnormality users of the channel in the associated medical insurance users of the channel in the data fusion processing in a preset time period. The abnormality detection coefficient is determined based on the average value, and when the abnormality detection coefficient is greater than a preset abnormality detection coefficient threshold, a preset detection strategy is used for abnormality detection processing of the channel, and when the abnormality detection coefficient is not greater than a preset detection coefficient threshold, a second preset detection strategy is used for abnormality detection processing of the channel.
[0052] Further, the channels include pharmacies, medical insurance systems, medical institutions, health departments, civil affairs systems, and tax systems.
[0053] Specifically, the fusion deviation situation is determined according to the fusion failure numbers of the channel and other channels in different fusion failure types in the fusion processing.
[0054] It can be understood that the fusion failure types include response delay exceptions, data missing, and data format errors.
[0055] Specifically, as shown in the following table, the method for determining the fusion deviation channels of the channel is as follows: Figure 2
[0056] According to the fusion deviation situation of the channel and other channels in the fusion processing, the fusion failure numbers of different medical insurance users are determined.
[0057] According to the fusion failure numbers of different medical insurance users, the fusion failure users in the medical insurance users are determined.
[0058] Based on the number of the fusion failure users, it is determined whether the other channels are the fusion deviation channels of the channel.
[0059] Further, the fusion failure users are medical insurance users whose fusion failure numbers are not within a preset failure number interval.
[0060] It can be understood that when the number of the fusion failure users of the other channels and the channel is greater than a preset failure user number threshold, it is determined that the other channels are the fusion deviation channels of the channel.
[0061] Further, when the channel does not exist a fusion failure channel, it is directly transferred to step S4 to determine the abnormality detection method of the channel.
[0062] It needs to be further explained that when the number of the fusion deviation channels of the channel does not meet the requirements, it is directly determined that a preset strategy is used for detection and analysis.
[0063] Optionally, the method for determining the fusion deviation channels of the channel is as follows:
[0064] According to the fusion deviation situation of the channel and other channels in the fusion processing, the fusion failure numbers of different medical insurance users are determined.
[0065] According to the proportion of the number of medical insurance users with fusion failure numbers in different dates, the fusion failure coefficients in different dates are determined.
[0066] determine whether the other channel is a fusion deviation channel of the channel based on an average of the fusion failure coefficients in different dates.
[0067] Further, when the average of the fusion failure coefficients in different dates is greater than a preset fusion failure coefficient threshold, it is determined that the other channel is a fusion deviation channel of the channel.
[0068] Optionally, the method for determining the fusion deviation channel of the channel is:
[0069] determine the fusion failure times of different medical insurance users based on the fusion deviation of the channel and the other channel in the fusion process, and when the total fusion failure times of the channel and the other channel do not meet the requirements, it is determined that the other channel is a fusion deviation channel of the channel.
[0070] When the total fusion failure times of the channel and the other channel meet the requirements:
[0071] determine the fusion failure users in the medical insurance users based on the fusion failure times of different medical insurance users, and when the number of the fusion failure users does not meet the requirements, it is determined that the other channel is a fusion deviation channel of the channel.
[0072] When the number of the fusion failure users meets the requirements:
[0073] take the same associated medical insurance users of the channel and the other channel as the same users, and when the proportion of the number of medical insurance users with fusion failure times in the same users does not meet the requirements, it is determined that the other channel is a fusion deviation channel of the channel.
[0074] When the proportion of the number of medical insurance users with fusion failure times in the same users meets the requirements:
[0075] determine the fusion failure coefficients in different dates based on the proportion of the number of medical insurance users with fusion failure times in different dates of the channel, and when the average of the fusion failure coefficients in different dates does not meet the requirements, it is determined that the other channel is a fusion deviation channel of the channel.
[0076] When the average of the fusion failure coefficients in different dates meets the requirements:
[0077] determine a preset threshold of the fusion failure coefficient under the number of the same users based on the number of the same users, obtain the proportion of the number of dates with fusion failure coefficients greater than the preset threshold, and when the proportion of the number of dates with fusion failure coefficients greater than the preset threshold does not meet the requirements, it is determined that the other channel is a fusion deviation channel of the channel.
[0078] When the proportion of the number of dates when the fusion failure coefficient is greater than the preset threshold value meets the requirement:
[0079] The number of the same users is obtained, and the fusion deviation value is determined in combination with the fusion failure coefficient and the number of fusion failure users in different dates. Whether the other channel is a fusion deviation channel of the channel is determined based on the fusion deviation value.
[0080] Further, when the fusion deviation value is greater than a preset fusion deviation threshold value, it is determined that the other channel is a fusion deviation channel of the channel.
[0081] Specifically, as shown in Figure 3 The method for determining the fusion processing requirement type of the associated medical insurance user is:
[0082] The diagnosis disease type of the associated user is determined based on the analysis result of the medical data of the associated user.
[0083] Based on the diagnosis disease type, the number of re-visits of the associated user in a future preset time period is determined.
[0084] The fusion processing requirement type of the associated medical insurance user is determined according to the number of re-visits.
[0085] Further, the fusion processing requirement type of the associated medical insurance user is determined according to the number of re-visits, specifically including:
[0086] The fusion processing requirement type of the associated medical insurance user is determined according to the preset requirement type corresponding to the number of re-visits.
[0087] It can be understood that the fusion processing requirement type includes a first processing requirement type, a second processing requirement type, and a third processing requirement type.
[0088] Specifically, the constituent data of the associated medical insurance user includes the number of associated medical insurance users of different fusion processing requirement types.
[0089] It should be noted that the association data of the fusion deviation channel of the associated medical insurance user includes the number of fusion deviation channels of different associated medical insurance users.
[0090] It can be understood that the channel does not need to be detected and analyzed by a preset strategy, specifically including:
[0091] The associated medical insurance users of the first processing requirement type of the channel are determined based on the constituent data of the associated medical insurance users of different fusion processing requirement types of the channel, and are used as screened medical insurance users.
[0092] According to the association data of the screened medical insurance user of the fusion deviation channel, the number of the screened medical insurance user of the fusion deviation channel is determined;
[0093] Based on the number of the screened medical insurance user of the fusion deviation channel, it is determined whether the channel needs to be detected and analyzed by using the preset strategy.
[0094] Further, when the number of the screened medical insurance user of the fusion deviation channel is greater than the preset screened user number threshold, it is determined that the channel needs to be detected and analyzed by using the preset strategy.
[0095] Optionally, it is determined that the channel does not need to be detected and analyzed by using the preset strategy, specifically including:
[0096] The association data of the screened medical insurance user of the fusion deviation channel is determined according to the different fusion processing demand types of the channel, and the association medical insurance user of the channel is determined as a screened medical insurance user;
[0097] According to the association data of the screened medical insurance user of the fusion deviation channel, the number of the screened medical insurance user in different fusion deviation channels is determined;
[0098] Based on the number of the screened medical insurance user in different fusion deviation channels, it is determined whether the channel needs to be detected and analyzed by using the preset strategy.
[0099] Specifically, when the number of the screened medical insurance user in the fusion deviation channel does not meet the requirement, it is determined that the channel needs to be detected and analyzed by using the preset strategy.
[0100] It should be noted that the fusion processing demand of the first type of processing demand is greater than the second type of processing demand, and the second type of processing demand is greater than the third type of processing demand.
[0101] Optionally, it is determined that the channel does not need to be detected and analyzed by using the preset strategy, specifically including:
[0102] S31 determines the different fusion processing demand types of the association medical insurance user of the channel according to the composition data of the different fusion processing demand types of the association medical insurance user of the channel, and determines the preset processing demand coefficient of the different association medical insurance users based on the different fusion processing demand types of the association medical insurance users.
[0103] S32 determines the number of the fusion deviation channel of the different association medical insurance users according to the association data of the fusion deviation channel of the association medical insurance user, and combines the preset processing demand coefficient of the different association medical insurance users to determine the fusion deviation demand value of the different association medical insurance users.
[0104] S33 determine a comprehensive fusion deviation demand value based on different associated medical insurance user fusion deviation demand values, and determine whether the channel needs to use a preset strategy for detection analysis by using the comprehensive fusion deviation demand value.
[0105] Further, when the comprehensive fusion deviation demand value is greater than a preset deviation demand threshold value, it is determined that the channel needs to use a preset strategy for detection analysis.
[0106] Optionally, the step S31 includes the following content:
[0107] S311 determine the number of different fusion processing demand type associated medical insurance users in the channel based on the composition data of different fusion processing demand type associated medical insurance users in the channel, when the number of associated medical insurance users in the channel does not meet the requirement, it is determined that the channel needs to use a preset strategy for detection analysis, when the number of associated medical insurance users in the channel meets the requirement, go to step S312;
[0108] S312 when the number of associated medical insurance users in the channel is less than a preset associated user number threshold value, it is determined that the channel does not need to use a preset strategy for detection analysis, when the number of associated medical insurance users in the channel is not less than a preset associated user number threshold value, go to step S313;
[0109] S313 determine the number of associated medical insurance users of a type of processing demand type, when the number of associated medical insurance users of a type of processing demand type does not meet the requirement, it is determined that the channel needs to use a preset strategy for detection analysis, when the number of associated medical insurance users of a type of processing demand type meets the requirement, go to step S314;
[0110] S314 determine different associated medical insurance user preset processing demand coefficients based on different associated medical insurance user fusion processing demand types, when the sum of different associated medical insurance user preset processing demand coefficients does not meet the requirement, it is determined that the channel needs to use a preset strategy for detection analysis, when the sum of different associated medical insurance user preset processing demand coefficients meets the requirement, go to step S32.
[0111] Optionally, the step S32 includes the following content:
[0112] S321 determine the number of different associated medical insurance user fusion deviation channels based on the associated data of the associated medical insurance user fusion deviation channel, when the sum of the number of different associated medical insurance user fusion deviation channels does not meet the requirement, it is determined that the channel needs to use a preset strategy for detection analysis, when the sum of the number of different associated medical insurance user fusion deviation channels meets the requirement, go to step S322;
[0113] S322When there is an associated medical insurance user whose number of fusion deviation channels is greater than the preset deviation channel number threshold, step S323 is entered; when there is no associated medical insurance user whose number of fusion deviation channels is greater than the preset deviation channel number threshold, step S324 is entered;
[0114] S323When the number of associated medical insurance users whose number of fusion deviation channels is greater than the preset deviation channel number threshold does not meet the requirement, it is determined that the channel needs to be detected and analyzed using a preset strategy; when the number of associated medical insurance users whose number of fusion deviation channels is greater than the preset deviation channel number threshold meets the requirement, step S324 is entered;
[0115] S324The number of fusion deviation channels of different associated medical insurance users is determined, and the fusion deviation demand value of different associated medical insurance users is determined in combination with the preset processing demand coefficient of different associated medical insurance users; when the average value of the fusion deviation demand value of different associated medical insurance users does not meet the requirement, it is determined that the channel needs to be detected and analyzed using a preset strategy; when the average value of the fusion deviation demand value of different associated medical insurance users meets the requirement, step S33 is entered.
[0116] Specifically, as shown in Figure 4 the method for determining the abnormality detection method of the channel is:
[0117] determine the associated medical insurance users whose response is abnormal based on the response abnormality distribution discrete data between the associated channels of the associated medical insurance users, and take them as response abnormality users of the associated channels;
[0118] determine the associated medical insurance users whose response is abnormal based on the response abnormality distribution discrete data between the associated channels of the associated medical insurance users, and take them as response abnormality users of the associated channels;
[0119] determine the abnormality detection method of the channel based on the associated channel response abnormality coefficient and the number of response abnormality users of the channel.
[0120] Further, the method for determining the associated channel response abnormality coefficient is:
[0121] determine the number of associated channels whose response is abnormal in different response abnormality medical insurance users based on the coincidence of the response abnormality medical insurance users of different associated channels;
[0122] determine the preset coincidence coefficient of different response abnormality medical insurance users according to the number of associated channels whose response is abnormal in different response abnormality medical insurance users.
[0123] Determine a preset response abnormality coefficient at the number of the response abnormal medical insurance users based on different associated channels, and determine the associated channel response abnormality coefficient based on the ratio of the preset response abnormality coefficient to the average of the preset coincidence coefficient.
[0124] It can be understood that the preset coincidence coefficient and the preset response abnormality coefficient are determined according to a preset corresponding relationship between the number of associated channels with response abnormalities in different response abnormal medical insurance users and the number of response abnormal medical insurance users of different associated channels, respectively.
[0125] Further, the response abnormality includes response delay greater than a preset time length and no response.
[0126] It should be noted that the channel abnormality detection method is determined based on the associated channel response abnormality coefficient and the number of response abnormal users of the channel, and specifically includes:
[0127] The response abnormality factor of the channel is determined by the product of the associated channel response abnormality coefficient and the number of response abnormal users of the channel.
[0128] When the response abnormality factor is greater than a preset abnormality factor threshold, a preset detection strategy is used for abnormality detection processing of the channel.
[0129] When the response abnormality factor is not greater than the preset abnormality factor threshold, a second preset detection strategy is used for abnormality detection processing of the channel.
[0130] Further, the preset detection strategy is to perform detection processing of the network delay of the data port of the channel in real time.
[0131] It can be understood that the second preset detection strategy is to perform detection processing of the data port of the channel when there is a response abnormality.
[0132] Embodiment 2
[0133] In a second aspect, the present application provides a computer system, comprising a memory and a processor connected in communication, and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to perform the above-mentioned medical insurance intelligent governance method based on data fusion.
[0134] Optionally, the method for determining the channel abnormality detection method is:
[0135] determine, according to the response abnormality distribution discrete data between the associated channels of the associated medical insurance users, that different associated channels have medical insurance users with response abnormality, and take the medical insurance users with response abnormality as response abnormality users of the associated channels; when the number of the response abnormality users does not meet the requirement, perform the abnormality detection processing of the channel by using the preset detection strategy;
[0136] when the channel has associated medical insurance users with response abnormality:
[0137] take the associated medical insurance users with response abnormality as response abnormality users, and when the number of the response abnormality users does not meet the requirement, perform the abnormality detection processing of the channel by using the preset detection strategy;
[0138] when the number of the response abnormality users meets the requirement:
[0139] determine, according to the response abnormality distribution discrete data between the associated channels of the associated medical insurance users, that different associated channels have medical insurance users with response abnormality, and take the medical insurance users with response abnormality as response abnormality users of the associated channels; when the number of the response abnormality users does not meet the requirement, perform the abnormality detection processing of the channel by using the preset detection strategy;
[0140] when there is no associated channel whose number of response abnormality users does not meet the requirement:
[0141] when the sum of the number of the response abnormality users of the associated channels and the number of the response abnormality users of the channel does not meet the requirement, perform the abnormality detection processing of the channel by using the preset detection strategy;
[0142] when the sum of the number of the response abnormality users of the associated channels and the number of the response abnormality users of the channel meets the requirement:
[0143] determine, according to the response abnormality users of the different associated channels and the coincidence of the response abnormality users, an associated channel response abnormality coefficient, and when the associated channel response abnormality coefficient does not meet the requirement, perform the abnormality detection processing of the channel by using the preset detection strategy;
[0144] when the associated channel response abnormality coefficient meets the requirement:
[0145] determine, according to the product of the associated channel response abnormality coefficient and the number of the response abnormality users of the channel, a response abnormality factor of the channel, and determine the abnormality detection method of the channel by using the response abnormality factor.
[0146] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.
[0147] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.
[0148] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.
Claims
1. A data fusion-based intelligent governance method for medical insurance, characterized in that, Specifically, it includes: By utilizing the fusion deviation of data from different medical insurance users and other channels, the fusion deviation channels are determined. Based on the associated data of medical insurance users in the aforementioned channels, the associated medical insurance users in the aforementioned channels are identified, and the fusion processing requirement type of the associated medical insurance users is determined based on the analysis results of the medical data of the associated medical insurance users. Obtain the composition data of associated medical insurance users with different fusion processing requirements of the channel, and when it is determined that the channel does not need to be detected and analyzed using a preset strategy, combine the fusion deviation data of different associated medical insurance users with the associated data of the channel, proceed to the next step. The method for detecting anomalies in the channels during data fusion processing of different associated medical insurance users within a preset time period is determined by analyzing the discrete distribution data of response anomalies between associated channels of the associated medical insurance users. The method for determining the fusion deviation of the channel is as follows: The number of fusion failures for different medical insurance users is determined based on the fusion deviation between the aforementioned channels and other channels during the fusion processing. The users who failed to merge were identified among the medical insurance users based on the number of merging failures among different medical insurance users. Based on the number of users whose fusion failed, determine whether the other channels are fusion deviation channels of the channel; The method for determining the anomaly detection method for the channel is as follows: Based on the abnormal response of the channel during the data fusion processing of different associated medical insurance users within a preset time period, the associated medical insurance users with abnormal response of the channel are identified and identified as users with abnormal response. Based on the discrete distribution data of response anomalies among the associated channels of the associated medical insurance users, medical insurance users with response anomalies in different associated channels are identified and regarded as medical insurance users with response anomalies in the associated channels. The response anomaly coefficient of the associated channels is determined by using the medical insurance users with response anomalies in different associated channels and the overlap of medical insurance users with response anomalies. Based on the anomaly coefficient of the associated channel and the number of users with abnormal responses in the channel, the anomaly detection method for the channel is determined.
2. The intelligent medical insurance governance method based on data fusion as described in claim 1, characterized in that, The channels mentioned include pharmacies, medical insurance systems, medical institutions, health departments, civil affairs systems, and tax systems.
3. The intelligent medical insurance governance method based on data fusion as described in claim 1, characterized in that, The fusion deviation is determined based on the number of fusion failures of the channel and other channels under different fusion failure types during the fusion processing.
4. The intelligent medical insurance governance method based on data fusion as described in claim 3, characterized in that, The types of fusion failures include abnormal response delays, missing data, and incorrect data formats.
5. The intelligent medical insurance governance method based on data fusion as described in claim 1, characterized in that, When the number of users who failed to merge with the channel from the other channels exceeds a preset threshold for the number of failed users, the other channels are determined to be channels with fusion deviations from the channel.
6. The intelligent medical insurance governance method based on data fusion as described in claim 1, characterized in that, When the number of channels with fusion deviation does not meet the requirements, a preset strategy is directly adopted for detection and analysis.
7. The intelligent medical insurance governance method based on data fusion as described in claim 1, characterized in that, Based on the anomaly coefficient of the associated channel and the number of users with abnormal responses in the channel, the anomaly detection method for the channel is determined, specifically including: The response anomaly factor of the channel is determined by multiplying the response anomaly coefficient of the associated channel by the number of users with response anomalies in the channel. When the response anomaly factor is greater than the preset anomaly factor threshold, the preset detection strategy is used to perform anomaly detection processing on the channel. When the response anomaly factor is not greater than the preset anomaly factor threshold, the second preset detection strategy is used to perform anomaly detection processing on the channel.
8. A computer system, comprising: A memory and processor connected by communication, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it executes a data fusion-based intelligent medical insurance governance method as described in any one of claims 1-7.
Citation Information
Patent Citations
Distributed channel automatic switching method and storage medium
CN114928563A
Multi-channel data cross validation payment method, system and device and medium
CN119359312A