Medical insurance medicine purchase fault prediction processing method and device

Abstract

The invention discloses a medical insurance medicine purchasing fault prediction processing method and device, and relates to the technical field of e-commerce platforms and medicine supply chains. A specific embodiment of the method comprises the steps of receiving monitoring data of a monitoring target in a medical insurance server; determining prediction delay information of the monitoring target in the prediction time period according to the monitoring data; determining a target delay threshold value corresponding to the monitoring scene; and according to the monitoring scene, the prediction delay information and a target delay threshold value, determining prediction fault information of the monitoring target in the medical insurance server. According to the embodiment, when the medical insurance server does not have a fault, the fault information possibly appearing in the medical insurance server can be predicted. Through early warning in advance, system faults can be checked in time, normal completion of medical insurance service processing is guaranteed, and smoothness and high efficiency of the medical insurance service processing process are improved.

Description

Technical Field

[0001] This invention relates to the fields of e-commerce platforms and pharmaceutical supply chain technology, and in particular to a method and apparatus for predicting and handling medical insurance drug purchase failures. Background Technology

[0002] The medical insurance server deploys medical insurance business services. External terminals or servers interact with the medical insurance server to complete medical insurance business processing, such as online and offline drug purchase processing. Typically, the monitoring system can only detect and issue alarms when the medical insurance server malfunctions. By this time, the fault has already occurred, and medical insurance business processing often cannot be completed, such as users being unable to purchase medicines normally, affecting the smoothness and efficiency of the medical insurance business processing. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method and apparatus for predicting and handling medical insurance drug purchase failures, which can predict the failure information of the medical insurance server when the server itself is not malfunctioning. By providing early warnings, medical insurance system failures can be promptly identified and resolved, ensuring the normal completion of medical insurance business processing and improving the smoothness and efficiency of the medical insurance business processing.

[0004] In a first aspect, embodiments of the present invention provide a method for predicting and handling medical insurance drug purchase failures, applied in a predictive analysis server deployed on the external network of the medical insurance server. The method includes:

[0005] Receive monitoring data from the medical insurance server for the monitored targets;

[0006] Based on the monitoring data, determine the prediction delay information of the monitored target during the prediction period;

[0007] Determine the target latency threshold corresponding to the monitoring scenario;

[0008] Based on the monitoring scenario, predicted latency information, and target latency threshold, the predicted fault information of the monitored target in the medical insurance server is determined.

[0009] Optionally, the target latency threshold corresponding to the monitoring scenario is determined, including:

[0010] In response to the monitoring scenario being single-server monitoring, a first latency threshold is determined as the target latency threshold; wherein, the first monitoring threshold is determined based on the historical monitoring data of the monitoring target in the medical insurance server;

[0011] In response to the monitoring scenario being regional monitoring, a second latency threshold is determined as the target latency threshold; wherein, the second monitoring threshold is determined based on historical monitoring data of the monitoring target in multiple regional medical insurance servers in the target region; the target region is the geographical region where the medical insurance server is located.

[0012] Optionally, based on the monitoring scenario, predicted latency information, and target latency threshold, predicted fault information of the monitored target in the medical insurance server is determined, including:

[0013] In response to the monitoring scenario being single-server monitoring, and the monitoring target in the medical insurance server experiencing delay within the predicted time period, the effective delay count of the monitoring target in the medical insurance server is determined based on the predicted delay information and the target delay threshold; in response to the effective delay count not exceeding the count threshold, the predicted fault information is determined to be a single-server operation fault targeting the monitoring target, and the fault level is the first preset level.

[0014] In response to the scenario of single-server monitoring, and the monitoring target in the medical insurance server experiencing delay within the predicted time period, the effective delay count of the monitoring target in the medical insurance server is determined based on the predicted delay information and the target delay threshold; in response to the effective delay count exceeding the threshold, the predicted fault information is determined to be a single-server operation fault targeting the monitoring target, and the fault level is the second preset level.

[0015] In response to the monitoring scenario being regional monitoring, the system determines whether the regional medical insurance server is a delayed server based on the predicted latency information and target latency threshold corresponding to the regional medical insurance server in the target area. In response to the proportion of delayed servers in the target area exceeding the proportion threshold, the system determines that the predicted fault information is a regional operational fault targeting the monitoring target, and the fault level is the third preset level.

[0016] Optionally, after determining the predicted fault information of the monitored target in the medical insurance server based on the monitoring scenario, predicted latency information, and target latency threshold, the method further includes:

[0017] In response to a fault level of the first preset level, the operation and maintenance strategy is determined to execute the automatic recovery script corresponding to the monitoring target;

[0018] In response to the rule level being the second preset level, the operation and maintenance policy is determined to stop the medical insurance server from providing external services, and an alarm message is sent.

[0019] In response to a fault level of the third preset level, the execution strategy is determined to switch the target area to the disaster recovery link and an alarm message is sent.

[0020] Optionally, the monitoring data is sent by a relay server;

[0021] The method also includes:

[0022] Send the target latency threshold for single-server monitoring scenarios to the relay server.

[0023] Optionally, the method further includes: in response to receiving an abnormal alarm for a drug purchase order, determining the pharmacy that placed the order; determining the target medical insurance server and the drug purchase area corresponding to the pharmacy; in response to the existence of first predicted fault information corresponding to the target medical insurance server, determining the first monitoring target corresponding to the first predicted fault information; generating fault information for the drug purchase order based on the target medical insurance server and the first monitoring target; in response to the existence of second predicted fault information corresponding to the drug purchase area, determining the second monitoring target corresponding to the second predicted fault information; and generating fault information for the drug purchase order based on the drug purchase area and the second monitoring target.

[0024] Secondly, embodiments of the present invention provide a method for sending monitoring data, applied in an intranet data collection server. The intranet data collection server is deployed on the intranet where the medical insurance server is located. The intranet data collection server only opens a first port. The method includes:

[0025] Collect monitoring data of the targets monitored in the medical insurance server;

[0026] The monitoring data is encrypted to obtain encrypted monitoring data;

[0027] The encrypted monitoring data is sent to the relay server through the first port; the relay server then sends the decrypted monitoring data to the predictive analysis server; the predictive analysis server determines the predicted delay information of the monitored target based on the monitoring data, and determines the predicted fault information of the monitored target based on the monitoring scenario and the predicted delay information.

[0028] Thirdly, embodiments of the present invention provide a method for forwarding monitoring data, applied in a relay server deployed on the external network of the medical insurance server, wherein the relay server only opens a second port, and the method includes:

[0029] The encrypted monitoring data sent by the intranet data collection server is received through the second port.

[0030] Decrypt the encrypted monitoring data;

[0031] In response to the decrypted monitoring data passing data verification, the decrypted monitoring data is sent to the predictive analysis server through the second port; the predictive analysis server determines the predicted latency information of the monitored target based on the monitoring data, and determines the predicted fault information of the monitored target based on the monitoring scenario and the predicted latency information.

[0032] Optionally, it also includes:

[0033] Receive the target latency threshold for a single-server monitoring scenario sent by the predictive analytics server;

[0034] Based on the decrypted monitoring data, determine the duration of delay for the monitored target;

[0035] In response to a delay duration exceeding the target delay threshold, a delay alarm message is sent for the monitored target.

[0036] Fourthly, embodiments of the present invention provide a medical insurance drug purchase failure prediction and processing device, applied in a prediction analysis server, the prediction analysis server being deployed on the external network of the medical insurance server, the device comprising:

[0037] The data receiving module is used to receive monitoring data from the monitored targets in the medical insurance server;

[0038] The delay prediction module is used to determine the predicted delay information of the monitored target during the prediction period based on the monitoring data.

[0039] The threshold determination module is used to determine the target latency threshold corresponding to the monitoring scenario;

[0040] The fault prediction module is used to determine the predicted fault information of the monitored targets in the medical insurance server based on the monitoring scenario, predicted latency information, and target latency threshold.

[0041] Fifthly, embodiments of the present invention provide a monitoring data transmission device applied in an intranet data collection server. The intranet data collection server is deployed in the intranet where the medical insurance server is located. The intranet data collection server only opens a first port. The device includes:

[0042] The data acquisition module is used to collect monitoring data of the monitored targets in the medical insurance server;

[0043] The encryption module is used to encrypt the monitoring data to obtain encrypted monitoring data;

[0044] The data sending module is used to send encrypted monitoring data to the relay server through the first port; the relay server then sends the decrypted monitoring data to the predictive analysis server; the predictive analysis server determines the predicted delay information of the monitored target based on the monitoring data, and determines the predicted fault information of the monitored target based on the monitoring scenario and the predicted delay information.

[0045] Sixthly, embodiments of the present invention provide a monitoring data forwarding device, applied in a relay server deployed on the external network of the medical insurance server, the relay server only opening a second port, the device comprising:

[0046] The data receiving module is used to receive encrypted monitoring data sent by the intranet data collection server through the second port;

[0047] The decryption module is used to decrypt the encrypted monitoring data.

[0048] The data sending module is used to send the decrypted monitoring data to the predictive analysis server through the second port in response to the data verification of the decrypted monitoring data. The predictive analysis server determines the predicted delay information of the monitored target based on the monitoring data, and determines the predicted fault information of the monitored target based on the monitoring scenario and the predicted delay information.

[0049] In a seventh aspect, embodiments of the present invention provide an electronic device, comprising:

[0050] One or more processors;

[0051] A storage device for storing one or more programs that, when executed by one or more processors, cause the one or more processors to implement the methods of any of the above embodiments.

[0052] Eighthly, embodiments of the present invention provide a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the method of any of the above embodiments.

[0053] Ninthly, embodiments of the present invention provide a computer program product, including a computer program, wherein the computer program, when executed by a processor, implements the method of any of the above embodiments.

[0054] One embodiment of the above invention has the following advantages or beneficial effects: the monitoring target can be: service port, functional service, business application, and hardware devices such as card reader and printer. Based on the monitoring scenario, predicted latency information, and target latency threshold, predicted fault information of the monitored target in the medical insurance server is determined. It can predict the fault information of the medical insurance server even when no fault occurs. Through early warning, system faults can be investigated in a timely manner, ensuring the normal completion of medical insurance business processing and improving the smoothness and efficiency of the medical insurance business processing process.

[0055] Furthermore, the intranet data collection server is deployed within the intranet where the medical insurance server resides. The relay server and predictive analysis server are deployed on the external network of the medical insurance server. The intranet data collection server only opens its first port. The intranet data collection server sends encrypted monitoring data to the relay server through the first port. The relay server only opens its second port. The relay server receives encrypted monitoring data sent by the intranet data collection server through the second port, and sends decrypted monitoring data to the predictive analysis server. This embodiment of the invention enables fault prediction of monitored targets on the medical insurance server while also reducing the risk of medical insurance data leakage within the intranet, thus improving the security of medical insurance data.

[0056] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0057] The accompanying drawings are provided to better understand the invention and are not intended to unduly limit the scope of the invention. Wherein:

[0058] Figure 1 This is a schematic diagram of the architecture of a medical insurance fault prediction system provided in one embodiment of the present invention;

[0059] Figure 2 This is a schematic diagram of the process of a medical insurance drug purchase failure prediction and handling method provided in an embodiment of the present invention;

[0060] Figure 3 This is a schematic diagram of the process of a medical insurance drug purchase failure prediction and handling method provided in another embodiment of the present invention;

[0061] Figure 4 This is a schematic diagram illustrating the interaction between an intranet data collection server and a relay server, provided in one embodiment of the present invention.

[0062] Figure 5 This is a schematic diagram of the flow of a monitoring data transmission method provided in an embodiment of the present invention;

[0063] Figure 6 This is a schematic diagram of the flow of a monitoring data forwarding method provided in an embodiment of the present invention;

[0064] Figure 7 This is a schematic diagram of the structure of a medical insurance drug purchase failure prediction and processing device provided in one embodiment of the present invention;

[0065] Figure 8 This is a schematic diagram of the structure of a monitoring data transmission device provided in one embodiment of the present invention;

[0066] Figure 9 This is a schematic diagram of the structure of a monitoring data forwarding device provided in one embodiment of the present invention;

[0067] Figure 10 This is a schematic diagram of the structure of a computer system suitable for implementing terminal devices or servers of the present invention. Detailed Implementation

[0068] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0069] It should be noted that the acquisition, storage, use, and processing of data in the technical solutions of this invention comply with the relevant provisions of national laws and regulations.

[0070] The solution of this invention constructs a complete fault prediction system through technical features such as dual-machine physical isolation architecture, encrypted one-way data transmission mechanism and intelligent analysis. Figure 1 This is a schematic diagram of the architecture of a medical insurance fault prediction system provided in one embodiment of the present invention. Figure 1 As shown, the architecture of the fault prediction system includes: an intranet data acquisition server, a relay server, and a predictive analysis server.

[0071] The intranet data collection server is deployed within the intranet where the medical insurance server is located, and only the first port is open. The intranet data collection server collects monitoring data from the targets monitored on the medical insurance server; it encrypts the monitoring data to obtain encrypted monitoring data; and it sends the encrypted monitoring data to the relay server through the first port.

[0072] The relay server is deployed on the external network of the medical insurance server, and only the second port is open. Through the second port, it receives encrypted monitoring data sent by the internal network data collection server; decrypts the encrypted monitoring data; and in response to the decrypted monitoring data passing data verification, sends the decrypted monitoring data to the predictive analysis server through the second port.

[0073] The internal data collection server and the relay server are physically isolated by a firewall to ensure that the medical insurance server is not exposed to the external network. A whitelist policy can be used to restrict communication ports, so that the data collection server only opens the first port, which is a one-way data transmission port.

[0074] The relay server does not store sensitive data. The internal network data collection server sends encrypted monitoring data to the relay server using encryption algorithms to prevent data leakage and reverse penetration. The relay server sends decrypted monitoring data to the predictive analysis server at preset intervals and supports resuming interrupted downloads.

[0075] The predictive analytics server is deployed on the external network of the medical insurance server. The predictive analytics server receives monitoring data from the monitored targets on the medical insurance server; based on the monitoring data, it determines the predicted latency information of the monitored targets during the predicted time period; it determines the target latency threshold corresponding to the monitoring scenario; and based on the monitoring scenario, predicted latency information, and target latency threshold, it determines the predicted fault information of the monitored targets on the medical insurance server.

[0076] Figure 2 This is a schematic diagram illustrating the flow of a method for predicting and handling medical insurance drug purchase failures, provided by an embodiment of the present invention. This method is applied to a predictive analysis server, which is deployed on the external network of the medical insurance server. Figure 2 As shown, the method includes:

[0077] Step 201: Receive monitoring data from the monitored targets in the medical insurance server.

[0078] A medical insurance server is a server that processes medical insurance-related business. For example, a medical insurance server receives online or offline drug purchase orders, performs identity verification and medical insurance settlement processing on these orders, enabling users to purchase drugs using medical insurance.

[0079] Monitoring targets can be set according to the needs of medical insurance operations. Monitoring targets may include: service ports, functional services, business applications, and hardware devices such as card readers and printers. Monitoring data may include: heart rate monitoring data, connectivity status, etc.

[0080] Based on a preset scanning frequency, multiple monitoring time points are determined. At each monitoring time point, it is monitored whether the target is normally connected or providing services. If the target is normally connected or providing services, the monitoring data at that time point is designated as the first flag. If the target is not connected or unable to provide services, the monitoring data at that time point is designated as the second flag. The monitoring data from each time point are combined sequentially to generate the target's heartbeat detection data.

[0081] Step 202: Based on the monitoring data, determine the predicted delay information of the monitored target during the predicted period.

[0082] The prediction period can be set according to the needs of medical insurance operations. The prediction period can be the next 5 minutes, the next 10 minutes, the next day, the next week, etc. Prediction delay information refers to the predicted delay information of the monitored target within the prediction period. Prediction delay information may include: whether the monitored target experiences a delay within the prediction period, the time when the monitored target experiences a delay within the prediction period, and the duration of each delay within the prediction period.

[0083] Historical monitoring data of the monitored targets in the medical insurance server are input into the prediction model. Based on the output of the prediction model, the prediction delay information of the monitored targets in the prediction period is determined.

[0084] The regional medical insurance server is a server that provides the same services as the medical insurance server. Historical monitoring data of the monitored targets in the regional medical insurance server are input into the prediction model. Based on the output of the prediction model, the prediction delay information of the monitored targets in the regional medical insurance server during the prediction period is determined.

[0085] Step 203: Determine the target latency threshold corresponding to the monitoring scenario.

[0086] If the monitoring scenario is single-server monitoring, the first latency threshold is determined as the target latency threshold; whereby the first monitoring threshold is determined based on the historical monitoring data of the monitoring target in the medical insurance server.

[0087] Historical monitoring data refers to the monitoring data of the monitored targets in the medical insurance server over historical time periods. Historical time periods can include the past 10 minutes, past 1 hour, past 10 hours, past 1 day, past 1 week, past 6 months, etc. Specifically, based on the historical monitoring data, the historical latency duration of the monitored target in each latency instance within the historical time period is determined. The mean, mode, and median of each historical latency duration of the monitored target can be used as the target latency threshold.

[0088] For example, the target monitored by the medical insurance system experienced two delays within a historical period, with historical delay durations of 5 seconds and 7 seconds respectively. The average of these historical delay durations, 6 seconds, can be used as the target delay threshold.

[0089] Alternatively, the first latency threshold, i.e. the target latency threshold corresponding to a single-service monitoring scenario, can be calculated using the following formula:

[0090] µ1+n1*δ1

[0091] Where µ1 is the mean of the historical latency of each monitored target in the medical insurance server. n1 is a positive integer, a negative integer, or 0. δ1 is the standard deviation of the historical latency of each monitored target in the medical insurance server.

[0092] If the monitoring scenario is regional monitoring, the second latency threshold is determined as the target latency threshold; whereby the second monitoring threshold is determined based on historical monitoring data of the monitored target in multiple regional medical insurance servers within the target region. The target region is the geographical area where the medical insurance server is located.

[0093] Historical monitoring data refers to the monitoring data of the monitored targets in the regional medical insurance server over historical time periods. Historical time periods can include the past 10 minutes, past 1 hour, past 10 hours, past 1 day, past 1 week, past 6 months, etc. Specifically, for each regional medical insurance server, based on the historical monitoring data of the monitored targets in the regional medical insurance server, the historical latency duration of the monitored targets in each historical time period is determined. The mean, mode, and median of the historical latency durations of the monitored targets in each regional medical insurance server can be used as target latency thresholds.

[0094] For example, the target region includes Regional Server 1 and Regional Server 2. The monitored target on Regional Server 1 experienced three delays during the historical time period, with historical delay durations of 5 seconds, 7 seconds, and 10 seconds, respectively. The monitored target on Regional Server 2 experienced one delay during the historical time period, with a historical delay duration of 10 seconds. The average historical delay duration of 8 seconds for the monitored targets across all regional medical insurance servers can be used as the target delay threshold.

[0095] Alternatively, the second latency threshold, i.e., the target latency threshold corresponding to the area monitoring scenario, can be calculated using the following formula:

[0096] µ2+n2*δ2

[0097] Where µ2 is the mean of the historical latency of the monitored targets in each regional medical insurance server. n2 is a positive integer, a negative integer, or 0. δ2 is the standard deviation of the historical latency of the monitored targets in each regional medical insurance server.

[0098] Step 204: Based on the monitoring scenario, predicted latency information, and target latency threshold, determine the predicted fault information of the monitoring target in the medical insurance server.

[0099] The predicted fault information may include: whether the monitored target will experience delays during the predicted period, the number of effective delays of the monitored target during the predicted period, the duration of delays of the monitored target during the predicted period, and the fault level.

[0100] In this embodiment of the invention, the predicted delay information of the monitored target during the predicted time period is determined based on the monitoring data of the monitored target in the medical insurance server. Based on the monitoring scenario, the predicted delay information, and the target delay threshold, the predicted fault information of the monitored target in the medical insurance server is determined. This allows for the prediction of fault information of the medical insurance server even when no fault occurs. Through early warning, system faults can be promptly identified and investigated, ensuring the normal completion of medical insurance business processing and improving the smoothness and efficiency of the medical insurance business processing.

[0101] Furthermore, the intranet data collection server is deployed within the intranet where the medical insurance server resides. The intranet data collection server only opens its first port. Through the first port, the intranet data collection server sends encrypted monitoring data to the relay server. The relay server is deployed on the external network of the medical insurance server. The relay server only opens its second port. Through the second port, the relay server receives the encrypted monitoring data sent by the intranet data collection server and sends the decrypted monitoring data to the predictive analysis server. The predictive analysis server is deployed on the external network of the medical insurance server. This embodiment of the invention enables fault prediction of monitored targets on the medical insurance server while also reducing the risk of medical insurance data leakage on the external network, thus improving the security of data on the medical insurance server.

[0102] Figure 3 This is a schematic diagram of a method for predicting and handling medical insurance drug purchase failures, provided by another embodiment of the present invention. This method is applied in a predictive analysis server. Figure 3 As shown, the method includes:

[0103] Step 301: Receive monitoring data from the monitored targets in the medical insurance server.

[0104] Step 302: Based on the monitoring data, determine the predicted delay information of the monitored target during the predicted period.

[0105] Step 303: Determine the target latency threshold corresponding to the monitoring scenario.

[0106] If the monitoring scenario is single-server monitoring, proceed to step 304. If the monitoring scenario is area monitoring, proceed to step 309.

[0107] Step 304: Determine whether the monitoring target in the medical insurance server experiences a delay within the predicted time period.

[0108] If the monitored target in the medical insurance server experiences a delay during the predicted period, proceed to step 305. If the monitored target in the medical insurance server does not experience a delay during the predicted period, proceed to step 308.

[0109] Step 305: Based on the predicted latency information and the target latency threshold, determine the effective latency count of the monitoring target in the medical insurance server.

[0110] The predicted latency information includes the latency duration corresponding to multiple delays. If the latency duration of the monitored target in a single delay exceeds the target latency threshold, that single delay is determined to be a valid latency.

[0111] The initial effective delay count is 0. For each delay duration in the predicted delay information, if the delay duration exceeds the target delay threshold, the effective delay count is incremented by 1. The final effective delay count is determined as the effective delay count of the monitoring target in the medical insurance server.

[0112] Step 306: In response to the fact that the number of effective delays has not exceeded the threshold, the predicted fault information is determined to be a single server operation fault targeting the monitoring target, and the fault level is the first preset level.

[0113] The higher the fault level, the more severe the problems it can cause. When the number of effective delays does not exceed the threshold, the predicted fault information is determined to be a single-server operational fault targeting the monitored object, and the fault level is the first preset level. The predicted fault information corresponding to the first preset level includes: the medical insurance server identifier, the monitored object identifier, and the fault level.

[0114] Step 307: In response to the effective delay count exceeding the threshold, determine that the predicted fault information is a single server operation fault targeting the monitored target, and the fault level is the second preset level.

[0115] The predicted fault information corresponding to the second preset fault level includes: medical insurance server identifier, monitoring target identifier, and fault level.

[0116] Step 308: Determine that there are no operational faults in the monitoring targets in the medical insurance server.

[0117] Step 309: Determine whether the regional medical insurance server is a delay server based on the predicted delay information and target delay threshold corresponding to the regional medical insurance server in the target area.

[0118] The predicted fault information corresponding to the third preset fault level includes: area identifier, monitoring target identifier, and fault level.

[0119] For each regional medical insurance server, the initial effective latency count is 0. For each latency duration in the predicted latency information corresponding to the regional medical insurance server, if the latency duration exceeds the target latency threshold, the effective latency count is incremented by 1; the final effective latency count is determined as the effective latency count of the monitoring target in the regional medical insurance server.

[0120] If the number of valid delays for a monitored target in the regional medical insurance server exceeds the regional threshold, then the regional medical insurance server is identified as a delay server.

[0121] Step 310: In response to the proportion of delayed servers in the target area exceeding the proportion threshold, the predicted fault information is determined to be a regional operational fault targeting the monitored target, and the fault level is the third preset level.

[0122] The solution in this embodiment of the invention sets three fault levels. These are, in ascending order of severity, a first preset level, a second preset level, and a third preset level. Different processing procedures and alarm methods are set for different fault levels to ensure that faults of different levels are handled in accordance with business needs, reducing the adverse impact of faults on the medical insurance system.

[0123] For example, for predicted faults at the first preset level, alarm information can be sent to the medical insurance server maintenance personnel via SMS or email. For predicted faults at the second preset level, alarm information can be sent to the medical insurance server maintenance personnel via telephone. For predicted faults at the third preset level, alarm information can be sent to the regional head and maintenance personnel of the medical insurance system via telephone.

[0124] In this embodiment of the invention, the monitoring scenario is divided into single-server monitoring and regional monitoring. Different fault conditions and fault levels are set for single-server monitoring and regional monitoring respectively, which enables technicians to quickly understand the fault situation and formulate corresponding troubleshooting strategies to reduce losses caused by the fault.

[0125] In one embodiment of the present invention, after determining the predicted fault information of the monitored target in the medical insurance server based on the monitoring scenario, predicted latency information, and target latency threshold, the method further includes: in response to a fault level of a first preset level, determining the operation and maintenance strategy to execute the automatic recovery script corresponding to the monitored target; in response to a rule level of a second preset level, determining the operation and maintenance strategy to stop the medical insurance server from providing external services and sending alarm information; and in response to a fault level of a third preset level, determining the execution strategy to switch the target area to the disaster recovery link and sending alarm information. By formulating different operation and maintenance strategies for different fault levels, targeted recovery processing of system faults can be carried out efficiently and effectively, enabling the medical insurance system to return to normal operation as soon as possible.

[0126] The solution of this invention involves the following servers: a medical insurance server, an intranet data collection server, a relay server, and a predictive analysis server. The medical insurance server is used to process medical insurance business. The intranet data collection server is deployed within the intranet where the medical insurance server resides. The intranet data collection server collects monitoring data from the monitored targets within the medical insurance server and sends the encrypted monitoring data to the relay server. The relay server is deployed on the external network of the medical insurance server, receives the encrypted monitoring data sent by the intranet data collection server, and sends the decrypted monitoring data to the predictive analysis server. The predictive analysis server determines the predicted delay information of the monitored targets based on the monitoring data, and determines the predicted fault information of the monitored targets based on the monitoring scenario and the predicted delay information.

[0127] The solution in this invention predicts fault information in the medical insurance system through information interaction between the aforementioned servers. By providing early warnings, system faults can be identified and addressed promptly, ensuring the normal completion of medical insurance business processing and improving the smoothness and efficiency of the process.

[0128] In one embodiment of the present invention, the monitoring data is sent by a relay server; the method further includes sending the target latency threshold under a single-server monitoring scenario to the relay server.

[0129] After receiving the target latency threshold for a single-server monitoring scenario from the predictive analytics server, the relay server can dynamically modify its high-alarm threshold based on the target latency threshold. The relay server receives encrypted monitoring data from the intranet data collection server and decrypts it to obtain the decrypted monitoring data. If the decrypted monitoring data meets the alarm conditions corresponding to the alarm threshold, an alarm is issued to quickly detect potential system failures in the medical insurance system.

[0130] The medical insurance drug purchase failure prediction and processing method provided in this embodiment of the invention further includes: in response to receiving an abnormal alarm for a drug purchase order, determining the pharmacy that placed the order; determining the target medical insurance server and the drug purchase area corresponding to the pharmacy; in response to the existence of first predicted failure information corresponding to the target medical insurance server, determining the first monitoring target corresponding to the first predicted failure information; generating failure information for the drug purchase order based on the target medical insurance server and the first monitoring target; in response to the existence of second predicted failure information corresponding to the drug purchase area, determining the second monitoring target corresponding to the second predicted failure information; and generating failure information for the drug purchase order based on the drug purchase area and the second monitoring target.

[0131] The target health insurance server is used to process medication orders placed by pharmacies. The medication purchase area is the geographical region where the pharmacy is located.

[0132] The medical insurance server identifier in the first predicted fault information is the identifier of the target medical insurance server. If first predicted fault information corresponding to the target medical insurance server exists, the first monitoring target corresponding to the first predicted fault information is determined. Based on the target medical insurance server and the first monitoring target, fault information for the drug purchase order is generated. The fault information includes: the identifier of the target medical insurance server and the identifier of the first monitoring target.

[0133] The region identifier in the second predicted fault information is the identifier of the drug purchase area. If second predicted fault information corresponding to a drug purchase area exists, the second monitoring target corresponding to the second predicted fault information is determined. Based on the drug purchase area and the second monitoring target, fault information for the drug purchase order is generated. The fault information includes: the identifier of the drug purchase area and the identifier of the second monitoring target.

[0134] If an anomaly alarm is received during the online or offline drug purchase process, the solution in this invention can be used to determine the fault information of the drug purchase order. Based on the fault information, technicians can then specifically troubleshoot the medical insurance system, efficiently resolve system faults, improve the user's drug purchase experience, and ensure the continuity of medical insurance services.

[0135] Figure 4 This is a schematic diagram illustrating the interaction between an intranet data collection server and a relay server, provided in one embodiment of the present invention. Figure 4 As shown, the intranet data acquisition server sends encrypted monitoring data to the relay server via an optical shutter device. The optical shutter device serves as a one-way transmission and reverse blocking mechanism. The optical shutter device uses a hardware-level one-way transmission module, allowing only the intranet data acquisition server to send data to the relay server, but disallowing the relay server from sending data to the intranet data acquisition server.

[0136] Configure firewall rules so that the internal network data collection server only opens port 1 and the relay server only opens port 2.

[0137] The internal network data collection server encapsulates the collected monitoring data into a preset format. It then encrypts the monitoring data using an encryption algorithm. The encryption key is stored in a hardware security module to prevent key leakage. Finally, it generates a hash value for the monitoring data and sends the hash value along with the encrypted monitoring data to the relay server.

[0138] The relay server is an independent external network server equipped with dual network cards. It connects to the internal network data acquisition server via an optical gateway device, supporting bidirectional information exchange with the predictive analysis server. The relay server decrypts the received encrypted monitoring data and verifies the hash value consistency. If the hash value does not match, the received encrypted data is discarded and a local alarm is triggered. If the hash value matches, the decrypted monitoring data is sent to the predictive analysis server at a preset frequency.

[0139] Figure 5 This is a schematic diagram illustrating the flow of a monitoring data transmission method according to an embodiment of the present invention. It is applied to an intranet data collection server, which is deployed within the intranet where the medical insurance server is located. The intranet data collection server only opens its first port. Figure 5 As shown, the method includes:

[0140] Step 501: Collect monitoring data of the monitored targets in the medical insurance server.

[0141] Monitoring targets can be set according to the needs of medical insurance operations. Monitoring targets may include: service ports, functional services, business applications, and hardware devices such as card readers and printers. Monitoring data may include: heart rate monitoring data, connectivity status, etc.

[0142] Based on a preset scanning frequency, multiple monitoring time points are determined. At each monitoring time point, the intranet data acquisition server monitors whether the monitored target is normally connected or providing services to the outside world. If the monitored target is normally connected or providing services to the outside world, the monitoring data at that time point is designated as the first flag. If the monitored target is not connected or cannot provide services to the outside world, the monitoring data at that time point is designated as the second flag. The monitoring data from each time point are combined sequentially to generate the heartbeat detection data of the monitored target.

[0143] Step 502: Encrypt the monitoring data to obtain encrypted monitoring data.

[0144] Step 503: Send the encrypted monitoring data to the relay server through the first port.

[0145] The relay server sends the decrypted monitoring data to the predictive analysis server. Based on the monitoring data, the predictive analysis server determines the predicted latency information of the monitored target, and based on the monitoring scenario and the predicted latency information, determines the predicted fault information of the monitored target. The predictive analysis server is used to execute the medical insurance drug purchase fault prediction processing method of any of the above embodiments.

[0146] In this embodiment of the invention, an intranet data collection server deployed within the intranet where the medical insurance server is located collects monitoring data of the monitored targets on the medical insurance server. The intranet data collection server then sends the encrypted monitoring data to a relay server. This solution can effectively prevent the risk of leakage of sensitive intranet data while ensuring the monitoring of the operation of the medical insurance server on the intranet.

[0147] Figure 6 This is a schematic diagram illustrating the flow of a monitoring data forwarding method according to an embodiment of the present invention. It is applied to a relay server deployed on the external network of the medical insurance server, and the relay server only has its second port open. Figure 6 As shown, the method includes:

[0148] Step 601: Receive encrypted monitoring data sent by the intranet data collection server through the second port.

[0149] Step 602: Decrypt the encrypted monitoring data.

[0150] Step 603: In response to the decrypted monitoring data passing data verification, the decrypted monitoring data is sent to the predictive analysis server through the second port.

[0151] The decrypted monitoring data is the monitoring data of the monitored target received by the predictive analysis server from the medical insurance server. Based on the monitoring data, the predictive analysis server determines the predicted delay information of the monitored target, and based on the monitoring scenario and the predicted delay information, determines the predicted fault information of the monitored target. The predictive analysis server is used to execute the medical insurance drug purchase fault prediction processing method of any of the above embodiments.

[0152] In this embodiment of the invention, a relay server deployed on the external network of the medical insurance server receives encrypted monitoring data sent by the internal network data collection server. If the decrypted monitoring data passes data verification, the relay server sends the decrypted monitoring data to the predictive analysis server. If the decrypted monitoring data fails data verification, the relay server sends an alarm message.

[0153] The relationship between the internal network data collection server and the relay server is one-to-many. That is, each internal network data collection server corresponds to a unique relay server. Each relay server can correspond to one or more internal network data collection servers.

[0154] Similarly, the relationship between relay servers and predictive analytics servers is one-to-many. That is, each relay server corresponds to a unique predictive analytics server. Each predictive analytics server can correspond to one or more relay servers. One predictive analytics server can be set up in each region, or one predictive analytics server can be set up in multiple regions.

[0155] Setting up a relay server between the intranet data collection server and the predictive analysis server can effectively ensure the security of the intranet where the medical insurance system is located. Furthermore, it can improve the efficiency of fault data collection and prediction, resulting in more timely fault information.

[0156] In one embodiment of the present invention, the method further includes: receiving a target latency threshold for a single-server monitoring scenario sent by a predictive analysis server; determining the latency duration of the monitored target based on the decrypted monitoring data; and sending a latency alarm message for the monitored target in response to the latency duration exceeding the target latency threshold.

[0157] After receiving the target latency threshold for a single-server monitoring scenario from the predictive analysis server, the relay server can dynamically modify the target latency threshold stored in the relay server based on this threshold. The existing latency duration is the historical latency duration of the monitored target in the medical insurance server. If the existing latency duration exceeds the target latency threshold, a latency alarm message is sent for the monitored target to promptly detect potential system failures in the medical insurance system.

[0158] Figure 7This is a schematic diagram of a medical insurance drug purchase failure prediction and processing device according to an embodiment of the present invention. It is applied in a predictive analysis server, which is deployed on the external network of the medical insurance server, such as... Figure 7 As shown, the device includes:

[0159] The data receiving module 701 is used to receive monitoring data of the monitored targets in the medical insurance server;

[0160] The delay prediction module 702 is used to determine the predicted delay information of the monitored target during the prediction period based on the monitoring data.

[0161] The threshold determination module 703 is used to determine the target delay threshold corresponding to the monitoring scenario.

[0162] The fault prediction module 704 is used to determine the predicted fault information of the monitored target in the medical insurance server based on the monitoring scenario, predicted delay information and target delay threshold.

[0163] Optionally, the threshold determination module 703 is specifically used for:

[0164] In response to the monitoring scenario being single-server monitoring, a first latency threshold is determined as the target latency threshold; wherein, the first monitoring threshold is determined based on the historical monitoring data of the monitoring target in the medical insurance server;

[0165] In response to the monitoring scenario being regional monitoring, a second latency threshold is determined as the target latency threshold; wherein, the second monitoring threshold is determined based on historical monitoring data of the monitoring target in multiple regional medical insurance servers in the target region; the target region is the geographical region where the medical insurance server is located.

[0166] Optionally, the fault prediction module 704 is specifically used for:

[0167] In response to the monitoring scenario being single-server monitoring, and the monitoring target in the medical insurance server experiencing delay within the predicted time period, the effective delay count of the monitoring target in the medical insurance server is determined based on the predicted delay information and the target delay threshold; in response to the effective delay count not exceeding the count threshold, the predicted fault information is determined to be a single-server operation fault targeting the monitoring target, and the fault level is the first preset level.

[0168] In response to the scenario of single-server monitoring, and the monitoring target in the medical insurance server experiencing delay within the predicted time period, the effective delay count of the monitoring target in the medical insurance server is determined based on the predicted delay information and the target delay threshold; in response to the effective delay count exceeding the threshold, the predicted fault information is determined to be a single-server operation fault targeting the monitoring target, and the fault level is the second preset level.

[0169] In response to the monitoring scenario being regional monitoring, the system determines whether the regional medical insurance server is a delayed server based on the predicted latency information and target latency threshold corresponding to the regional medical insurance server in the target area. In response to the proportion of delayed servers in the target area exceeding the proportion threshold, the system determines that the predicted fault information is a regional operational fault targeting the monitoring target, and the fault level is the third preset level.

[0170] Optionally, the fault prediction module 704 is also used for:

[0171] In response to a fault level of the first preset level, the operation and maintenance strategy is determined to execute the automatic recovery script corresponding to the monitoring target;

[0172] In response to the rule level being the second preset level, the operation and maintenance policy is determined to stop the medical insurance server from providing external services, and an alarm message is sent.

[0173] In response to a fault level of the third preset level, the execution strategy is determined to switch the target area to the disaster recovery link and an alarm message is sent.

[0174] Optionally, the monitoring data is sent by a relay server;

[0175] Also includes:

[0176] The threshold sending module is used to send the target latency threshold in a single-server monitoring scenario to the relay server.

[0177] Optionally, it also includes:

[0178] The fault determination module is used to determine the corresponding pharmacy when receiving an abnormal alarm for a medicine purchase order;

[0179] Determine the target medical insurance server and the drug purchase area corresponding to the pharmacy to which you are placing the order;

[0180] In response to the existence of first predicted fault information corresponding to the target medical insurance server, the first monitoring target corresponding to the first predicted fault information is determined.

[0181] Based on the target medical insurance server and the primary monitoring target, generate fault information for the drug purchase order;

[0182] In response to the second predicted fault information corresponding to the drug purchase area, the second monitoring target corresponding to the second predicted fault information is determined.

[0183] Based on the drug purchase area and the second monitoring target, generate fault information for the drug purchase order.

[0184] Figure 8This is a schematic diagram of a monitoring data transmission device according to an embodiment of the present invention. It is applied in an intranet data collection server, which is deployed within the intranet where the medical insurance server is located. The intranet data collection server only opens its first port, such as... Figure 8 As shown, the device includes:

[0185] The data acquisition module 801 is used to collect monitoring data of the monitored targets in the medical insurance server;

[0186] The encryption module 802 is used to encrypt the monitoring data to obtain encrypted monitoring data;

[0187] The data sending module 803 is used to send encrypted monitoring data to the relay server through the first port; the relay server sends the decrypted monitoring data to the predictive analysis server; the predictive analysis server determines the predicted delay information of the monitored target based on the monitoring data, and determines the predicted fault information of the monitored target based on the monitoring scenario and the predicted delay information.

[0188] Figure 9 This is a schematic diagram of a monitoring data forwarding device according to an embodiment of the present invention. It is applied in a relay server deployed on the external network of the medical insurance server. The relay server only opens its second port, such as... Figure 9 As shown, the device includes:

[0189] The data receiving module 901 is used to receive encrypted monitoring data sent by the intranet data collection server through the second port;

[0190] The decryption module 902 is used to decrypt the encrypted monitoring data;

[0191] The data sending module 903 is used to send the decrypted monitoring data to the predictive analysis server through the second port in response to the data verification of the decrypted monitoring data. The predictive analysis server determines the predicted delay information of the monitoring target based on the monitoring data, and determines the predicted fault information of the monitoring target based on the monitoring scenario and the predicted delay information.

[0192] Optionally, the data sending module 903 is also used to: receive the target latency threshold for a single-server monitoring scenario sent by the predictive analysis server;

[0193] In response to the decrypted monitoring data being verified, the delayed duration of the monitored target is determined based on the decrypted monitoring data.

[0194] In response to a delay duration exceeding the target delay threshold, a delay alarm message is sent for the monitored target;

[0195] The decrypted monitoring data is sent to the predictive analytics server via the second port.

[0196] This invention provides an electronic device, comprising:

[0197] One or more processors;

[0198] A storage device for storing one or more programs that, when executed by one or more processors, cause the one or more processors to implement the methods of any of the above embodiments.

[0199] This invention provides a computer program product, including a computer program that, when executed by a processor, implements the method of any of the above embodiments.

[0200] The following is for reference. Figure 10 It shows a schematic diagram of the structure of a computer system 1000 suitable for implementing a terminal device of the present invention. Figure 10 The terminal device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0201] like Figure 10 As shown, the computer system 1000 includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 1002 or programs loaded from storage section 1008 into random access memory (RAM) 1003. The RAM 1003 also stores various programs and data required for the operation of the system 1000. The CPU 1001, ROM 1002, and RAM 1003 are interconnected via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0202] The following components are connected to I / O interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to I / O interface 1005 as needed. A removable medium 1011, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 1010 as needed so that computer programs read from it can be installed into storage section 1008 as needed.

[0203] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1009, and / or installed from removable medium 1011. When the computer program is executed by central processing unit (CPU) 1001, it performs the functions defined above in the system of this invention.

[0204] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0205] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0206] The modules described in the embodiments of the present invention can be implemented in software or hardware. The described modules can also be housed in a processor, and for example, can be described as: a data receiving module, a delay prediction module, a threshold determination module, and a fault prediction module. The names of these modules do not necessarily limit the module itself; for example, the data receiving module can also be described as "a module that receives monitoring data from the monitored targets in the medical insurance server."

[0207] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, which, when executed by the device, cause the device to include:

[0208] Receive monitoring data from the medical insurance server for the monitored targets;

[0209] Based on the monitoring data, determine the prediction delay information of the monitored target during the prediction period;

[0210] Determine the target latency threshold corresponding to the monitoring scenario;

[0211] Based on the monitoring scenario, predicted latency information, and target latency threshold, the predicted fault information of the monitored target in the medical insurance server is determined.

[0212] According to the technical solution of this invention, the predicted latency information of the monitored targets in the medical insurance server is determined based on the monitoring data of the monitored targets during the predicted period. The monitored targets can be: ports, services, card readers, printers, etc. Based on the monitoring scenario, predicted latency information, and target latency threshold, the predicted fault information of the monitored targets in the medical insurance server is determined. This allows for the prediction of fault information of the medical insurance server even when no fault occurs. Through early warning, system faults can be promptly identified and investigated, ensuring the normal completion of medical insurance business processing and improving the smoothness and efficiency of the medical insurance business processing process.

[0213] Furthermore, the intranet data collection server is deployed within the intranet where the medical insurance server resides. The intranet data collection server only opens its first port. Through the first port, the intranet data collection server sends encrypted monitoring data to the relay server. The relay server is deployed on the external network of the medical insurance server. The relay server only opens its second port. Through the second port, the relay server receives the encrypted monitoring data sent by the intranet data collection server and sends the decrypted monitoring data to the predictive analysis server. The predictive analysis server is deployed on the external network of the medical insurance server. This embodiment of the invention enables fault prediction of monitored targets on the medical insurance server while also reducing the risk of medical insurance data being leaked to the external network, thus improving the security of data on the medical insurance server.

[0214] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for predicting and handling medical insurance drug purchase failures, characterized in that, The method is applied in a predictive analytics server, which is deployed on the external network of the medical insurance server, and includes: Receive monitoring data from the medical insurance server for the monitored targets; Based on the monitoring data, the prediction delay information of the monitored target during the prediction period is determined; Determine the target latency threshold corresponding to the monitoring scenario; Based on the monitoring scenario, the predicted delay information, and the target delay threshold, the predicted fault information of the monitoring target in the medical insurance server is determined.

2. The method according to claim 1, characterized in that, Determining the target latency threshold corresponding to the monitoring scenario includes: In response to the fact that the monitoring scenario is single-server monitoring, a first latency threshold is determined as the target latency threshold; wherein, the first monitoring threshold is determined based on the historical monitoring data of the monitoring target in the medical insurance server; In response to the monitoring scenario being regional monitoring, a second latency threshold is determined as the target latency threshold; wherein, the second monitoring threshold is determined based on historical monitoring data of the monitoring target in multiple regional medical insurance servers in the target region; the target region is the geographical region where the medical insurance server is located.

3. The method according to claim 1, characterized in that, The step of determining the predicted fault information of the monitored target in the medical insurance server based on the monitoring scenario, the predicted latency information, and the target latency threshold includes: In response to the monitoring scenario being single-server monitoring, and the monitoring target in the medical insurance server experiencing a delay within the predicted time period, the effective delay count of the monitoring target in the medical insurance server is determined based on the predicted delay information and the target delay threshold; in response to the effective delay count not exceeding the count threshold, the predicted fault information is determined to be a single-server operation fault targeting the monitoring target, and the fault level is a first preset level. In response to the monitoring scenario being single-server monitoring, and the monitoring target in the medical insurance server experiencing a delay within the predicted time period, the effective delay count of the monitoring target in the medical insurance server is determined based on the predicted delay information and the target delay threshold; in response to the effective delay count exceeding the count threshold, the predicted fault information is determined to be a single-server operation fault targeting the monitoring target, and the fault level is a second preset level. In response to the monitoring scenario being regional monitoring, based on the predicted latency information corresponding to the regional medical insurance server in the target region and the target latency threshold, it is determined whether the regional medical insurance server is a latency server; in response to the proportion of latency servers in the target region exceeding the proportion threshold, it is determined that the predicted fault information is a regional operational fault targeting the monitoring target, and the fault level is the third preset level.

4. The method according to claim 3, characterized in that, After determining the predicted fault information of the monitored target in the medical insurance server based on the monitoring scenario, the predicted delay information, and the target delay threshold, the method further includes: In response to the fault level being the first preset level, the operation and maintenance strategy is determined to be to execute the automatic recovery script corresponding to the monitoring target; In response to the rule level being the second preset level, the operation and maintenance strategy is determined to stop the medical insurance server from providing external services, and an alarm message is sent. In response to the fault level being the third preset level, the execution strategy is determined to switch the target area to the disaster recovery link and an alarm message is sent.

5. The method according to claim 1, characterized in that, The monitoring data is sent by a relay server; The method also includes: The target latency threshold for a single-server monitoring scenario is sent to the relay server.

6. The method according to claim 1, characterized in that, Also includes: In response to an abnormal alarm upon receiving a medication purchase order, the pharmacy corresponding to the medication purchase order is identified; Determine the target medical insurance server and the drug purchase area corresponding to the pharmacy where the order was placed; In response to the existence of first predicted fault information corresponding to the target medical insurance server, a first monitoring target corresponding to the first predicted fault information is determined. Based on the target medical insurance server and the first monitoring target, generate fault information for the drug purchase order; In response to the existence of second predicted fault information corresponding to the drug purchase area, a second monitoring target corresponding to the second predicted fault information is determined; based on the drug purchase area and the second monitoring target, fault information for the drug purchase order is generated.

7. A method for transmitting monitoring data, characterized in that, The method, applied to an intranet data collection server deployed within the intranet where the medical insurance server is located, and wherein the intranet data collection server only opens its first port, includes: Collect monitoring data of the monitored targets in the medical insurance server; The monitoring data is encrypted to obtain encrypted monitoring data; The encrypted monitoring data is sent to the relay server through the first port; the relay server then sends the decrypted monitoring data to the predictive analysis server; the predictive analysis server determines the predicted delay information of the monitored target based on the monitoring data, and determines the predicted fault information of the monitored target based on the monitoring scenario and the predicted delay information.

8. A method for forwarding monitoring data, characterized in that, The method is applied to a relay server deployed on the external network of the medical insurance server, wherein the relay server only opens a second port, and the method includes: The encrypted monitoring data sent by the intranet data collection server is received through the second port. The encrypted monitoring data is then decrypted. In response to the decrypted monitoring data passing data verification, the decrypted monitoring data is sent to the predictive analysis server through the second port; wherein, the predictive analysis server determines the predicted delay information of the monitored target based on the monitoring data, and determines the predicted fault information of the monitored target based on the monitoring scenario and the predicted delay information.

9. The method according to claim 8, characterized in that, Also includes: Receive the target latency threshold for a single-server monitoring scenario sent by the predictive analytics server; Based on the decrypted monitoring data, determine the duration of delay for the monitored target; In response to the delayed duration exceeding the target delay threshold, a delay alarm message is sent for the monitored target.

10. A medical insurance drug purchase failure prediction and processing device, characterized in that, The device is used in a predictive analytics server, which is deployed on the external network of the medical insurance server. The device includes: The data receiving module is used to receive monitoring data from the monitored targets in the medical insurance server; The delay prediction module is used to determine the predicted delay information of the monitored target during the prediction period based on the monitoring data. The threshold determination module is used to determine the target latency threshold corresponding to the monitoring scenario; The fault prediction module is used to determine the predicted fault information of the monitored target in the medical insurance server based on the monitoring scenario, the predicted delay information, and the target delay threshold.

11. A device for transmitting monitoring data, characterized in that, The device is used in an intranet data collection server, which is deployed on the intranet where the medical insurance server is located. The intranet data collection server only opens its first port. The device includes: The data acquisition module is used to collect monitoring data of the monitored targets in the medical insurance server; An encryption module is used to encrypt the monitoring data to obtain encrypted monitoring data; The data sending module is used to send the encrypted monitoring data to the relay server through the first port; wherein the relay server sends the decrypted monitoring data to the predictive analysis server; the predictive analysis server determines the predicted delay information of the monitoring target based on the monitoring data, and determines the predicted fault information of the monitoring target based on the monitoring scenario and the predicted delay information.

12. A monitoring data forwarding device, characterized in that, The device is used in a relay server deployed on the external network of the medical insurance server. The relay server only opens a second port. The device includes: The data receiving module is used to receive encrypted monitoring data sent by the intranet data collection server through the second port; The decryption module is used to decrypt the encrypted monitoring data; The data sending module is used to send the decrypted monitoring data to the predictive analysis server through the second port in response to the data verification of the decrypted monitoring data; wherein, the predictive analysis server determines the predicted delay information of the monitoring target based on the monitoring data, and determines the predicted fault information of the monitoring target based on the monitoring scenario and the predicted delay information.

13. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-9.

14. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-9.

15. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-9.

Images