Insurance information intelligent data monitoring system and method

Abstract

The invention discloses an insurance information intelligent data monitoring system and method, and belongs to the technical field of intelligent data monitoring, and the method comprises the following steps: dividing clients into different groups; analyzing the claim settlement frequency of each group in each time period; analyzing the moving average value of the claim settlement frequency of each group in each time period, and analyzing the claim settlement period characteristics of each group; analyzing a differential value and a periodic influence value of each group in each time period; analyzing the predicted difference value of each group in each time period; obtaining the predicted claim settlement frequency of each group in each time period; judging the claim settlement abnormity of each group; according to the method, the accurate claim settlement change trend is predicted for the to-be-monitored company, the predicted data and the actual data are analyzed, and a prompt is made in time when the claim settlement is abnormal, so that the decision of the insurance company has accurate data support, and appropriate countermeasures are taken to avoid loss.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent data monitoring, and specifically to an insurance information intelligent data monitoring system and method. Background Art

[0002] With the continuous development of the insurance industry and the rapid progress of data technology and informatization, insurance companies have begun to use technologies such as big data analysis and artificial intelligence to improve the operational efficiency and service quality of their core businesses. Especially in the field of claims management, insurance companies are facing growing customer demand and market competition pressure;

[0003] At present, the monitoring system of insurance companies in claims management lacks effective analysis of claims data, cannot provide accurate claims change trends, and cannot promptly remind when claims are abnormal. As a result, insurance companies lack accurate data support for their decisions, and thus take inappropriate response measures, resulting in losses.

[0004] Therefore, people are in urgent need of an intelligent insurance information data monitoring system to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent insurance information data monitoring system to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] An intelligent insurance information data monitoring method, the method comprising the following steps:

[0008] S1. Collect the ages of customers in the monitored companies and divide them into different groups; collect the historical claims data of the monitored companies and analyze the claims frequency of each group in each time period;

[0009] S2. Analyze the moving average of the claim frequency of each group in each time period and analyze the claim cycle characteristics of each group according to the claim frequency of each group in each time period;

[0010] S3. Analyze the difference value and cycle impact value of each group in each time period based on the claim frequency and claim cycle characteristics of each group in each time period;

[0011] S4. Analyze the predicted difference value of each group in each time period according to the difference value and periodic impact value of each group in each time period; obtain the predicted claim frequency of each group in each time period according to the predicted difference value of each group in each time period;

[0012] S5. Determine the claim abnormality of each group based on the predicted claim frequency of each group in each time period and the actual claim frequency of each group in each time period.

[0013] According to the above technical solution, the specific process of step S1 is as follows:

[0014] S1-1. Collect the ages of customers in the company to be monitored and obtain the maximum age, recorded as A max ; Get the minimum age, recorded as A min ; A max -A min The value of is used as the age span; the age span is divided into A1 parts, where the length of each part is (A max -A min ) / A1, A1 is a positive integer; the customer's age is A min +(a-1)×(A max -A min ) / A1 to A min +a×(A max -A min ) / A1 are divided into the same group, where a∈[1,A1];

[0015] Divide customer groups by age. Customers of the same age group have strong similarities in insurance needs. At the same time, customers of different age groups have significant differences in health status, risk tolerance, insurance needs, etc. Divide by age to more accurately predict the insurance claims status of customers and conduct precise analysis.

[0016] S1-2. Collect historical claims data of the company to be monitored, including claim date, claim event and customer age;

[0017] Match the customer to the corresponding group based on their age; set the unit time and divide it into different time periods based on the claim date; match the claim events with each time period to obtain the number of claim events for each group in each time period; take the ratio of the number of claim events for each group in each time period to the unit time as the claim frequency of each group in each time period;

[0018] The claim frequency of the i-th group in the j-th time period is denoted as B i，j .

[0019] According to the above technical solution, the specific process of step S2 is as follows:

[0020] S2-1. Set a sliding window to process the claim frequency of each group in each time period; the sliding window moves in the order of time periods, and each movement of the sliding window is from the time period where the sliding window is located to the next adjacent time period; each time the sliding window is moved, the claim frequency corresponding to the corresponding group in the time period window where the sliding window is located is covered, and the claim frequency corresponding to the corresponding group in the time period window where the sliding window is located is calculated to obtain the moving average of the claim frequency of each group in each time period;

[0021] The size of the sliding window is recorded as b; the claim frequency corresponding to the i-th group in the j-th time period of the sliding window is calculated to obtain the moving average of the claim frequency of the i-th group in the j-th time period, recorded as C i，j ;

[0022] C i，j The specific calculation formula is as follows:

[0023]

[0024] Among them, B i，c represents the claim frequency of the i-th group in the c-th time period;

[0025] Use a sliding window to calculate the moving average of the frequency of claims for each group in each time period, thereby smoothing the data and eliminating short-term fluctuations in the data;

[0026] S2-2. According to the time period sequence, obtain the moving average of the claim frequency of each group in each time period, and compare the i-th group with C i，j The moving average of the claim frequency in the adjacent previous time period is denoted by C i，j-1 ; Combine the ith group with C i，j The moving average of the claim frequency in the adjacent subsequent time period is denoted by C i，j+1 ;

[0027] Filter out the products that meet C i，j-1 <C i，j And C i，j >C i，j+1 C i，j , as the peak value of the i-th group; take the average of all peak values ​​of the i-th group as the claim cycle characteristic of the i-th group, denoted by D i ;

[0028] By analyzing the moving average of the claims frequency of each group in each time period, the claims cycle characteristics of the corresponding group are obtained. The claims cycle characteristics reflect the long-term change characteristics of the claims of the corresponding group.

[0029] According to the above technical solution, the specific process of step S3 is as follows:

[0030] S3-1. Based on the claim frequency B of the i-th group in the j-th time period i，j , and the i-th group is combined with B i，j The claim frequency in the previous time period is denoted as B i，j-1 ;B i，j and B i，j-1 , calculate the difference value of the i-th group in each time period. The specific calculation formula is ΔE1 i，j =B i，j -B i，j-1 ; Among them, ΔE1 i，j represents the difference value of the i-th group in the j-th time period; obtain B i，j The difference value of the previous i-th group in each time period, and the average of all the difference values ​​is taken as the comprehensive difference value of the i-th group in the j-th time period, recorded as ΔE2 i，j ;

[0031] S3-2. Based on the claim frequency B of the i-th group in the j-th time period i，j and the claim cycle characteristics D of the i-th group i , calculate the periodic impact value of the i-th group in each time period. The specific calculation formula is ΔE3 i，j =B i，j -D i ; Among them, ΔE3 i，j It represents the periodic impact value of the i-th group in the j-th time period;

[0032] The differential value reflects the short-term changing trend of the claims of the corresponding group, and the periodic impact value reflects the long-term changing trend of the claims of the corresponding group. Using the differential value and the periodic impact value as the basic data parameters for prediction improves the reliability and accuracy of the prediction.

[0033] According to the above technical solution, the specific process of step S4 is as follows:

[0034] S4-1, taking the next time period adjacent to the j-th time period corresponding to the i-th group as the j+1-th time period corresponding to the i-th group;

[0035] S4-2. The predicted difference value of the i-th group in the j+1-th time period is recorded as ΔF1 i，j+1 ;

[0036] According to the comprehensive difference value ΔE2 of the i-th group in the j-th time period i，j and the periodic impact value ΔE3 of the i-th group in the j-th time period i，j , for ΔF1 i，j+1 For prediction, the prediction model is as follows: ΔF1i，j+1 =α0+α1×ΔE2 i，j +α2×ΔE3 i，j +α3; where α0 represents the constant term; α1 represents the differential coefficient; α2 represents the periodic coefficient; α3 represents the error term;

[0037] The constant term, differential coefficient, periodic coefficient and error term in the prediction model are obtained by training the prediction model with the system historical data. And through the continuous accumulation of data, the constant term, differential coefficient, periodic coefficient and error term are continuously adjusted to improve the prediction model, thereby improving the reliability and accuracy of the prediction.

[0038] S4-3. Based on the claim frequency B of the i-th group in the j-th time period i，j and the predicted difference value ΔF1 of the i-th group in the j+1th time period i，j+1 , calculate the predicted claim frequency of the i-th group in the j+1-th time period. The specific calculation formula is B1 i，j+1 =B i，j +ΔF1 i，j+1 Among them, B1 i，j+1 It represents the predicted claim frequency of the i-th group in the j+1-th time period.

[0039] According to the above technical solution, the specific process of step S5 is as follows:

[0040] S5-1. The actual claim frequency of the i-th group in the j+1th time period is recorded as B i，j+1 ; Based on the predicted claim frequency B1 of the i-th group in the j+1th time period i，j+1 , calculate the deviation between the predicted claim frequency and the actual claim frequency of the i-th group in the j+1th time period. The specific calculation formula is H i，j+1 =|B i，j+1 -B1 i，j+1 |; Among them, H i，j+1 It represents the deviation between the predicted claim frequency and the actual claim frequency of the i-th group in the j+1-th time period;

[0041] S5-2. Take the average of the deviations between the predicted claim frequency and the actual claim frequency of the i-th group in each time period before the j+1th time period, and record it as H1 i ;

[0042] Take the standard deviation of the predicted claim frequency and the actual claim frequency of the i-th group in each time period before the j+1th time period, and record it as H2 i ;

[0043] If H i，j+1 Satisfy H i，j+1≤H1 i +β×H2 i , it means that the claims of the i-th group are normal; where β represents the adjustment coefficient;

[0044] If H i，j+1 Satisfy H i，j+1 >H1 i +β×H2 i , it means that the claim settlement of the i-th group is abnormal, and the system issues a reminder message.

[0045] An intelligent insurance information data monitoring system, the system includes an information collection module, an information processing module and an execution module;

[0046] The information acquisition module is used to acquire the information required by the system; the information processing module is used to store, analyze and transmit the information of each module; and the execution module is used to execute the information of the information processing module.

[0047] According to the above technical solution, the information collection module includes a historical information unit and a real-time information unit;

[0048] The historical information unit is used to collect historical data information of claims settlement in the company to be monitored; the real-time information unit is used to collect real-time data information of claims settlement in the company to be monitored.

[0049] According to the above technical solution, the information processing module includes an information storage unit, an information analysis unit and an information transmission unit;

[0050] The information storage unit is used to store the information acquired by the information acquisition module; the information analysis unit is used to analyze the information acquired by the information acquisition module; and the information transmission unit is used for information transmission of each module in the system.

[0051] According to the above technical solution, the execution module includes a display unit and a reminder unit;

[0052] The display unit is used to provide a visual display of the claims of the company to be monitored, and to view the changes in the claims of the company to be monitored in real time; the reminder unit is used to issue a reminder when the claims of the company to be monitored are abnormal.

[0053] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0054] The present invention collects and analyzes the data of claims settlement in the monitored company to obtain the claims frequencies corresponding to different groups of the monitored company, analyzes the claims frequencies corresponding to different groups, predicts the claims frequencies corresponding to different groups, and judges the claims abnormalities of each group based on the predicted claims frequencies and actual claims frequencies corresponding to different groups. Not only can the accurate claims change trend be predicted for the monitored company through effective analysis of the claims settlement data in the monitored company, but also timely reminders can be made when claims abnormalities are detected based on analysis of the predicted data and actual data, so that the insurance company's decision-making has accurate data support, so that appropriate countermeasures can be taken to avoid losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0056] Figure 1 It is a flow chart of an intelligent insurance information data monitoring method of the present invention;

[0057] Figure 2 It is a structural schematic diagram of an insurance information intelligent data monitoring system of the present invention. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] See also Figure 1 , the present invention provides a technical solution:

[0060] An intelligent insurance information data monitoring method, the method comprising the following steps:

[0061] S1. Collect the ages of customers in the monitored companies and divide them into different groups; collect the historical claims data of the monitored companies and analyze the claims frequency of each group in each time period;

[0062] According to the above technical solution, the specific process of step S1 is as follows:

[0063] S1-1. Collect the ages of customers in the company to be monitored and obtain the maximum age, recorded as A max ; Get the minimum age, recorded as A min ; A max -Amin The value of is used as the age span; the age span is divided into A1 parts, where the length of each part is (A max -A min ) / A1, A1 is a positive integer; the customer's age is A min +(a-1)×(A max -A min ) / A1 to A min +a×(A max -A min ) / A1 are divided into the same group, where a∈[1,A1];

[0064] Divide customer groups by age. Customers of the same age group have strong similarities in insurance needs. At the same time, customers of different age groups have significant differences in health status, risk tolerance, insurance needs, etc. Divide by age to more accurately predict the insurance claims status of customers and conduct precise analysis.

[0065] S1-2. Collect historical claims data of the company to be monitored, including claim date, claim event and customer age;

[0066] Match the customer to the corresponding group based on their age; set the unit time and divide it into different time periods based on the claim date; match the claim events with each time period to obtain the number of claim events for each group in each time period; take the ratio of the number of claim events for each group in each time period to the unit time as the claim frequency of each group in each time period;

[0067] The claim frequency of the i-th group in the j-th time period is denoted as B i，j .

[0068] S2. Analyze the moving average of the claim frequency of each group in each time period and analyze the claim cycle characteristics of each group according to the claim frequency of each group in each time period;

[0069] According to the above technical solution, the specific process of step S2 is as follows:

[0070] S2-1. Set a sliding window to process the claim frequency of each group in each time period; the sliding window moves in the order of time periods, and each movement of the sliding window is from the time period where the sliding window is located to the next adjacent time period; each time the sliding window is moved, the claim frequency corresponding to the corresponding group in the time period window where the sliding window is located is covered, and the claim frequency corresponding to the corresponding group in the time period window where the sliding window is located is calculated to obtain the moving average of the claim frequency of each group in each time period;

[0071] The size of the sliding window is recorded as b; the claim frequency corresponding to the i-th group in the j-th time period of the sliding window is calculated to obtain the moving average of the claim frequency of the i-th group in the j-th time period, recorded as C i，j ;

[0072] C i，j The specific calculation formula is as follows:

[0073]

[0074] Among them, B i，c represents the claim frequency of the i-th group in the c-th time period;

[0075] For example:

[0076] It is known that the size of the sliding window is b = 3; the claim frequencies corresponding to the i-th group in the j = 5th time period window of the sliding window are B i，j＝5 =60, B i，j-1＝4 =55, B i，j-b+1＝3 =50;

[0077] C i，j The specific calculation formula is as follows:

[0078]

[0079] Get C i，j＝5 =55;

[0080] Use a sliding window to calculate the moving average of the frequency of claims for each group in each time period, thereby smoothing the data and eliminating short-term fluctuations in the data;

[0081] S2-2. According to the time period sequence, obtain the moving average of the claim frequency of each group in each time period, and compare the i-th group with C i，j The moving average of the claim frequency in the adjacent previous time period is denoted by C i，j-1 ; Combine the ith group with C i，j The moving average of the claim frequency in the adjacent subsequent time period is denoted by C i，j+1 ;

[0082] Filter out the products that meet C i，j-1 <C i，j And C i，j >C i，j+1 C i，j , as the peak value of the i-th group; take the average of all peak values ​​of the i-th group as the claim cycle characteristic of the i-th group, denoted by D i ;

[0083] By analyzing the moving average of the claims frequency of each group in each time period, the claims cycle characteristics of the corresponding group are obtained. The claims cycle characteristics reflect the long-term change characteristics of the claims of the corresponding group.

[0084] S3. Analyze the difference value and cycle impact value of each group in each time period based on the claim frequency and claim cycle characteristics of each group in each time period;

[0085] According to the above technical solution, the specific process of step S3 is as follows:

[0086] S3-1. Based on the claim frequency B of the i-th group in the j-th time period i，j , and the i-th group is combined with B i，j The claim frequency in the previous time period is denoted as B i，j-1 ;B i，j and B i，j-1 , calculate the difference value of the i-th group in each time period. The specific calculation formula is ΔE1 i，j =B i，j -B i，j-1 ; Among them, ΔE1 i，j represents the difference value of the i-th group in the j-th time period; obtain B i，j The difference value of the previous i-th group in each time period, and the average of all the difference values ​​is taken as the comprehensive difference value of the i-th group in the j-th time period, recorded as ΔE2 i，j ;

[0087] S3-2. Based on the claim frequency B of the i-th group in the j-th time period i，j and the claim cycle characteristics D of the i-th group i , calculate the periodic impact value of the i-th group in each time period. The specific calculation formula is ΔE3 i，j =B i，j -D i ; Among them, ΔE3 i，j It represents the periodic impact value of the i-th group in the j-th time period;

[0088] The differential value reflects the short-term changing trend of the claims of the corresponding group, and the periodic impact value reflects the long-term changing trend of the claims of the corresponding group. Using the differential value and the periodic impact value as the basic data parameters for prediction improves the reliability and accuracy of the prediction.

[0089] S4. Analyze the predicted difference value of each group in each time period according to the difference value and periodic impact value of each group in each time period; obtain the predicted claim frequency of each group in each time period according to the predicted difference value of each group in each time period;

[0090] According to the above technical solution, the specific process of step S4 is as follows:

[0091] S4-1, taking the next time period adjacent to the j-th time period corresponding to the i-th group as the j+1-th time period corresponding to the i-th group;

[0092] S4-2. The predicted difference value of the i-th group in the j+1-th time period is recorded as ΔF1 i，j+1 ;

[0093] According to the comprehensive difference value ΔE2 of the i-th group in the j-th time period i，j and the periodic impact value ΔE3 of the i-th group in the j-th time period i，j , for ΔF1 i，j+1 For prediction, the prediction model is as follows: ΔF1 i，j+1 =α0+α1×ΔE2 i，j +α2×ΔE3 i，j +α3; where α0 represents the constant term; α1 represents the differential coefficient; α2 represents the periodic coefficient; α3 represents the error term;

[0094] The constant term, differential coefficient, periodic coefficient and error term in the prediction model are obtained by training the prediction model with the system historical data. And through the continuous accumulation of data, the constant term, differential coefficient, periodic coefficient and error term are continuously adjusted to improve the prediction model, thereby improving the reliability and accuracy of the prediction.

[0095] S4-3. Based on the claim frequency B of the i-th group in the j-th time period i，j and the predicted difference value ΔF1 of the i-th group in the j+1th time period i，j+1 , calculate the predicted claim frequency of the i-th group in the j+1-th time period. The specific calculation formula is B1 i，j+1 =B i，j +ΔF1 i，j+1 Among them, B1 i，j+1 It represents the predicted claim frequency of the i-th group in the j+1-th time period.

[0096] S5. Determine the abnormality of claims for each group based on the predicted claims frequency of each group in each time period and the actual claims frequency of each group in each time period;

[0097] According to the above technical solution, the specific process of step S5 is as follows:

[0098] S5-1. The actual claim frequency of the i-th group in the j+1th time period is recorded as B i，j+1 ; Based on the predicted claim frequency B1 of the i-th group in the j+1th time period i，j+1, calculate the deviation between the predicted claim frequency and the actual claim frequency of the i-th group in the j+1th time period. The specific calculation formula is H i，j+1 =|B i，j+1 -B1 i，j+1 |; Among them, H i，j+1 It represents the deviation between the predicted claim frequency and the actual claim frequency of the i-th group in the j+1-th time period;

[0099] S5-2. Take the average of the deviations between the predicted claim frequency and the actual claim frequency of the i-th group in each time period before the j+1th time period, and record it as H1 i ;

[0100] Take the standard deviation of the predicted claim frequency and the actual claim frequency of the i-th group in each time period before the j+1th time period, and record it as H2 i ;

[0101] If H i，j+1 Satisfy H i，j+1 ≤H1 i +β×H2 i , it means that the claims of the i-th group are normal; where β represents the adjustment coefficient;

[0102] If H i，j+1 Satisfy H i，j+1 >H1 i +β×H2 i , it means that the claim settlement of the i-th group is abnormal, and the system issues a reminder message.

[0103] See also Figure 2 , an intelligent data monitoring system for insurance information, the system includes an information collection module, an information processing module and an execution module;

[0104] The information acquisition module is used to acquire the information required by the system; the information processing module is used to store, analyze and transmit the information of each module; and the execution module is used to execute the information of the information processing module.

[0105] According to the above technical solution, the information collection module includes a historical information unit and a real-time information unit;

[0106] The historical information unit is used to collect historical data information of claims settlement in the company to be monitored; the real-time information unit is used to collect real-time data information of claims settlement in the company to be monitored.

[0107] According to the above technical solution, the information processing module includes an information storage unit, an information analysis unit and an information transmission unit;

[0108] The information storage unit is used to store the information acquired by the information acquisition module; the information analysis unit is used to analyze the information acquired by the information acquisition module; and the information transmission unit is used for information transmission of each module in the system.

[0109] According to the above technical solution, the execution module includes a display unit and a reminder unit;

[0110] The display unit is used to provide a visual display of the claims of the company to be monitored, and to view the changes in the claims of the company to be monitored in real time; the reminder unit is used to issue a reminder when the claims of the company to be monitored are abnormal.

[0111] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions recorded in the aforementioned embodiments, or to replace some of the technical features therein by equivalents. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent insurance information data monitoring method, characterized in that: The method comprises the following steps: S1. Collect the ages of customers in the monitored companies and divide them into different groups; collect the historical claims data of the monitored companies and analyze the claims frequency of each group in each time period; S2. Analyze the moving average of the claim frequency of each group in each time period and analyze the claim cycle characteristics of each group according to the claim frequency of each group in each time period; S3. Analyze the difference value and cycle impact value of each group in each time period based on the claim frequency and claim cycle characteristics of each group in each time period; S4. Analyze the predicted difference value of each group in each time period according to the difference value and periodic impact value of each group in each time period; obtain the predicted claim frequency of each group in each time period according to the predicted difference value of each group in each time period; S5. Determine the claim abnormality of each group based on the predicted claim frequency of each group in each time period and the actual claim frequency of each group in each time period.

2. The intelligent insurance information data monitoring method according to claim 1, characterized in that: The specific process of step S1 is as follows: S1-1. Collect the ages of customers in the company to be monitored and obtain the maximum age, recorded as A max ; Get the minimum age, recorded as A min ; A max -A min The value of is used as the age span; the age span is divided into A1 parts, where the length of each part is (A max -A min ) / A1, A1 is a positive integer; the customer's age is A min +(a-1)×(A max -A min ) / A1 to A min +a×(A max -A min ) / A1 are divided into the same group, where a∈[1,A1]; S1-2. Collect historical claims data of the company to be monitored, including claim date, claim event and customer age; Match the customer to the corresponding group based on their age; set the unit time and divide it into different time periods based on the claim date; match the claim events with each time period to obtain the number of claim events for each group in each time period; take the ratio of the number of claim events for each group in each time period to the unit time as the claim frequency of each group in each time period; The claim frequency of the i-th group in the j-th time period is denoted as B i，j .

3. The intelligent insurance information data monitoring method according to claim 2, characterized in that: The specific process of step S2 is as follows: S2-1. Set a sliding window to process the claim frequency of each group in each time period; the sliding window moves in the order of time periods, and each movement of the sliding window is from the time period where the sliding window is located to the next adjacent time period; each time the sliding window is moved, the claim frequency corresponding to the corresponding group in the time period window where the sliding window is located is covered, and the claim frequency corresponding to the corresponding group in the time period window where the sliding window is located is calculated to obtain the moving average of the claim frequency of each group in each time period; The size of the sliding window is recorded as b; the claim frequency corresponding to the i-th group in the j-th time period of the sliding window is calculated to obtain the moving average of the claim frequency of the i-th group in the j-th time period, recorded as C i，j ; C i，j The specific calculation formula is as follows: Among them, B i，c represents the claim frequency of the i-th group in the c-th time period; S2-2. According to the time period sequence, obtain the moving average of the claim frequency of each group in each time period, and compare the i-th group with C i，j The moving average of the claim frequency in the adjacent previous time period is denoted by C i，j-1 ; Combine the ith group with C i，j The moving average of the claim frequency in the adjacent subsequent time period is denoted by C i，j+1 ; Filter out the products that meet C i，j-1 <C i，j And C i，j >C i，j+1 C i，j , as the peak value of the i-th group; take the average of all peak values ​​of the i-th group as the claim cycle characteristic of the i-th group, denoted by D i .

4. The intelligent insurance information data monitoring method according to claim 3 is characterized by: The specific process of step S3 is as follows: S3-1. Based on the claim frequency B of the i-th group in the j-th time period i，j , and the i-th group is combined with B i，j The claim frequency in the previous time period is recorded as B i，j-1 ; by B i，j and B i，j-1 , calculate the difference value of the i-th group in each time period. The specific calculation formula is ΔE1 i，j =B i，j -B i，j-1 ; Among them, ΔE1 i，j represents the difference value of the i-th group in the j-th time period; obtain B i，j The difference value of the previous i-th group in each time period, and the average of all the difference values ​​is taken as the comprehensive difference value of the i-th group in the j-th time period, recorded as ΔE2 i，j ; S3-2. Based on the claim frequency B of the i-th group in the j-th time period i，j and the claim cycle characteristics D of the i-th group i , calculate the periodic impact value of the i-th group in each time period. The specific calculation formula is ΔE3 i，j =B i，j -D i ; Among them, ΔE3 i，j It represents the periodic impact value of the i-th group in the j-th time period.

5. The intelligent insurance information data monitoring method according to claim 4, characterized in that: The specific process of step S4 is as follows: S4-1, taking the next time period adjacent to the j-th time period corresponding to the i-th group as the j+1-th time period corresponding to the i-th group; S4-2. The predicted difference value of the i-th group in the j+1-th time period is recorded as ΔF1 i，j+1 ; According to the comprehensive difference value ΔE2 of the i-th group in the j-th time period i，j and the periodic impact value ΔE3 of the i-th group in the j-th time period i，j , for ΔF1 i，j+1 For prediction, the prediction model is as follows: ΔF1 i，j+1 =α0+α1×ΔE2 i，j +α2×ΔE3 i，j +α3; where α0 represents the constant term; α1 represents the differential coefficient; α2 represents the periodic coefficient; α3 represents the error term; S4-3. Based on the claim frequency B of the i-th group in the j-th time period i，j and the predicted difference value ΔF1 of the i-th group in the j+1th time period i，j+1 , calculate the predicted claim frequency of the i-th group in the j+1-th time period. The specific calculation formula is B1 i，j+1 =B i，j +ΔF1 i，j+1 Among them, B1 i，j+1 It represents the predicted claim frequency of the i-th group in the j+1-th time period.

6. The intelligent insurance information data monitoring method according to claim 5, characterized in that: The specific process of step S5 is as follows: S5-1. The actual claim frequency of the i-th group in the j+1th time period is recorded as B i，j+1 ; Based on the predicted claim frequency B1 of the i-th group in the j+1th time period i，j+1 , calculate the deviation between the predicted claim frequency and the actual claim frequency of the i-th group in the j+1th time period. The specific calculation formula is H i，j+1 =|B i，j+1 -B1 i，j+1 |; Among them, H i，j+1 It represents the deviation between the predicted claim frequency and the actual claim frequency of the i-th group in the j+1-th time period; S5-2. Take the average of the deviations between the predicted claim frequency and the actual claim frequency of the i-th group in each time period before the j+1th time period, and record it as H1 i ; Take the standard deviation of the predicted claim frequency and the actual claim frequency of the i-th group in each time period before the j+1th time period, and record it as H2 i ; If H i，j+1 Satisfy H i，j+1 ≤H1 i +β×H2 i , it means that the claims of the i-th group are normal; where β represents the adjustment coefficient; If H i，j+1 Satisfy H i，j+1 >H1 i +β×H2 i , it means that the claim settlement of the i-th group is abnormal, and the system issues a reminder message.

7. An insurance information intelligent data monitoring system, such as using an insurance information intelligent data monitoring method according to any one of claims 1 to 6, characterized in that: The system includes an information collection module, an information processing module and an execution module; The information acquisition module is used to acquire the information required by the system; the information processing module is used to store, analyze and transmit the information of each module; and the execution module is used to execute the information of the information processing module.

8. An intelligent insurance information data monitoring system according to claim 7, characterized in that: The information collection module includes a historical information unit and a real-time information unit; The historical information unit is used to collect historical data information of claims settlement in the company to be monitored; the real-time information unit is used to collect real-time data information of claims settlement in the company to be monitored.

9. The intelligent insurance information data monitoring system according to claim 7, characterized in that: The information processing module includes an information storage unit, an information analysis unit and an information transmission unit; The information storage unit is used to store the information acquired by the information acquisition module; the information analysis unit is used to analyze the information acquired by the information acquisition module; and the information transmission unit is used for information transmission of each module in the system.

10. An intelligent insurance information data monitoring system according to claim 7, characterized in that: The execution module includes a display unit and a reminder unit; The display unit is used to provide a visual display of the claims of the company to be monitored, and to view the changes in the claims of the company to be monitored in real time; the reminder unit is used to issue a reminder when the claims of the company to be monitored are abnormal.

Images