Insurance fund expenditure prediction method for disaster events, electronic equipment and storage medium

Abstract

The present invention relates to the technical field of insurance business, and provides a method, electronic device and storage medium for predicting insurance fund expenditure for disaster events, including: determining similar historical disaster events according to disaster information of a target disaster event; determining a predicted expenditure amount of the target disaster event on the i-th day after the occurrence time according to the compensation information of similar historical disaster events; determining the proportion of all events that complete claims settlement on the i-th day between the occurrence time and the maximum compensation time, and a revised compensation amount corresponding to the target disaster event according to the group basic characteristics and group compensation characteristics of similar historical disaster events, and the group basic characteristics of the target disaster event; determining the expenditure amount of the target disaster event on the i-th day after the occurrence time according to the predicted expenditure amount, the revised compensation amount and the event proportion, so as to realize reasonable improvement of the compensation of the event from multiple dimensions, which is conducive to the smooth progress and planning of the compensation business.

Description

Technical Field

[0001] The present invention relates to the technical field of insurance business, and in particular to a method for predicting insurance fund expenditure for disaster events, electronic equipment and storage medium. Background Art

[0002] After a disaster event occurs, it is necessary to predict the claims applications related to the disaster event in order to predict the payment amount at any number of days after the disaster event occurs, so as to ensure that the insurance claims business can be handled normally.

[0003] When commonly used time series algorithms are used to predict the daily expenditure amount of insurance companies' cash flows, when encountering sudden disaster events, the prediction results of the prediction model will show obvious deviations due to insufficient estimation of compensation, and there is a lack of means to assess the intensity of the subsequent impact of sudden disaster events. Summary of the invention

[0004] In view of the problems existing in the prior art, the present invention provides a method for predicting insurance fund expenditures for disaster events, an electronic device and a storage medium.

[0005] In a first aspect, the present invention provides a method for predicting insurance fund expenditures for disaster events, comprising:

[0006] Based on the disaster information of the target disaster event, similar historical disaster events are identified;

[0007] Determine the forecast amount of expenditure on the i-th day after the target disaster event occurs based on the compensation information of similar historical disaster events;

[0008] According to the basic group characteristics and group compensation characteristics of similar historical disaster events, as well as the basic group characteristics of the target disaster event, determine the proportion of all events that complete claims settlement on the i-th day between the occurrence time and the maximum compensation time, and the modified compensation amount corresponding to the target disaster event;

[0009] The expenditure amount of the target disaster event on the i-th day after the occurrence time is determined based on the expenditure forecast amount, the modified compensation amount and the event ratio.

[0010] In one embodiment, based on the basic group characteristics and group compensation characteristics of similar historical disaster events and the basic group characteristics of the target disaster event, determining the modified compensation amount corresponding to the target disaster event includes:

[0011] Determine the impact of the target disaster event according to the basic characteristics of the group of the target disaster event and the basic characteristics of the group of similar historical disaster events;

[0012] Determine the average compensation amount and the number of compensation claims based on the group compensation characteristics of similar historical disaster events;

[0013] The revised compensation amount shall be determined based on the average compensation amount of each case, the number of compensation claims and the degree of impact.

[0014] In one embodiment, determining similar historical disaster events based on the disaster information of the target disaster event includes:

[0015] Determine first information in the disaster information, and determine the disaster category of the target disaster event according to the first information;

[0016] When it is determined that the disaster category is at least two, determining second information in the disaster event;

[0017] When it is determined according to the second information that the disaster category of the target disaster event is one, all historical disaster events in the disaster category are selected as similar historical disaster events.

[0018] In one embodiment, determining the expenditure amount of the target disaster event on the i-th day after the occurrence time according to the expenditure forecast amount, the modified compensation amount and the event ratio includes:

[0019] Determine the revised compensation amount on the i-th day after the occurrence of the target disaster event according to the revised compensation amount and the event ratio;

[0020] The expenditure amount of the target disaster event on the i-th day after the occurrence time is determined based on the forecast expenditure amount and the revised amount.

[0021] In a second aspect, the present invention provides a device for predicting insurance fund expenditures for disaster events, comprising:

[0022] A matching module is used to determine similar historical disaster events based on the disaster information of the target disaster event;

[0023] A prediction module, used to determine the predicted amount of expenditure on the i-th day after the occurrence of the target disaster event based on the compensation information of similar historical disaster events;

[0024] An analysis module, for determining the proportion of all events that complete claims settlement on the i-th day between the occurrence time and the maximum compensation time, and the modified compensation amount corresponding to the target disaster event, based on the group basic characteristics and group compensation characteristics of similar historical disaster events and the group basic characteristics of the target disaster event;

[0025] A processing module is used to determine the expenditure amount of the target disaster event on the i-th day after the occurrence time according to the expenditure forecast amount, the modified compensation amount and the event ratio.

[0026] In one embodiment, the analysis module, in the process of determining the revised compensation amount, is specifically used to:

[0027] Determine the impact of the target disaster event according to the basic characteristics of the group of the target disaster event and the basic characteristics of the group of similar historical disaster events;

[0028] Determine the average compensation amount and the number of compensation claims based on the group compensation characteristics of similar historical disaster events;

[0029] The revised compensation amount shall be determined based on the average compensation amount of each case, the number of compensation claims and the degree of impact.

[0030] In one embodiment, the matching module is specifically used for:

[0031] Determine first information in the disaster information, and determine the disaster category of the target disaster event according to the first information;

[0032] When it is determined that the disaster category is at least two, determining second information in the disaster event;

[0033] When it is determined according to the second information that the disaster category of the target disaster event is one, all historical disaster events in the disaster category are selected as similar historical disaster events.

[0034] In one embodiment, the processing module is specifically used to:

[0035] Determine the revised compensation amount on the i-th day after the occurrence of the target disaster event according to the revised compensation amount and the event ratio;

[0036] The expenditure amount of the target disaster event on the i-th day after the occurrence time is determined based on the forecast expenditure amount and the revised amount.

[0037] In a third aspect, the present invention provides an electronic device comprising a memory and a memory storing a computer program, wherein when the processor executes the program, the steps of the method for predicting insurance fund expenditure for disaster events described in the first aspect are implemented.

[0038] In a fourth aspect, the present invention provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, wherein the computer program is used to enable the processor to execute the steps of the method for predicting insurance fund expenditures for disaster events described in the first aspect.

[0039] The insurance fund expenditure prediction method, electronic device and storage medium for disaster events provided by the present invention obtain the expenditure prediction amount, revised compensation amount and the proportion of events for which claims are completed after the event occurs that meet the target disaster event through compensation information and feature analysis of historical disaster events similar to the target disaster event. The expenditure prediction amount, revised compensation amount and event proportion are then used to determine the expenditure amount at any number of days after the event occurs, thereby achieving reasonable improvement in the compensation of the event from multiple dimensions, reflecting a more accurate expenditure amount, and facilitating the smooth progress and planning of the compensation business. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 It is a flow chart of the insurance fund expenditure prediction method for disaster events provided by the present invention;

[0042] Figure 2 It is a schematic diagram of the structure of the insurance fund expenditure prediction device for disaster events provided by the present invention;

[0043] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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.

[0045] Figure 1 A schematic diagram showing a method for predicting insurance fund expenditures for disaster events provided by the present invention is shown in FIG. Figure 1 , the method comprising:

[0046] 11. Determine similar historical disaster events based on the disaster information of the target disaster event;

[0047] 12. Based on the compensation information of similar historical disaster events, determine the forecast amount of expenditure on the i-th day after the target disaster event occurs;

[0048] 13. Based on the basic group characteristics and group compensation characteristics of similar historical disaster events, as well as the basic group characteristics of the target disaster event, determine the proportion of all events that complete claims settlement on the i-th day between the time of occurrence and the maximum compensation time, and the revised compensation amount corresponding to the target disaster event;

[0049] 14. Determine the expenditure amount of the target disaster event on the i-th day after the occurrence time based on the expenditure forecast amount, the revised compensation amount and the event ratio.

[0050] Regarding steps 11 to 14, it should be noted that in the present invention, after a disaster event occurs, it is necessary to predict the claim applications related to the disaster event in order to predict the payment amount at any number of days after the disaster event occurs, so as to ensure that the insurance claim business can be processed normally.

[0051] In the present invention, the insurance agent will select the specific disaster type of the target disaster event through the system interface, such as heavy rain, flood, typhoon, earthquake, fire, blizzard, etc., and fill in the disaster information such as geographical location, occurrence time, and estimated number of victims. At this time, based on the above disaster information, multiple historical disaster events similar to the target disaster event can be screened out from the historical disaster events.

[0052] In the present invention, a disaster analysis model may be configured, which may take disaster information of a target disaster event as input and then output similar historical disaster events.

[0053] In the present invention, historical claims records are extracted and sorted, disaster events are marked, data are processed and processed, and disaster information such as the date of disaster, time of disaster, area of ​​disaster, type of disaster, number of victims, risky products, compensation amount, number of reports, maximum claims cycle, average compensation duration, etc. are generated. The disaster information is used to train a disaster analysis model through clustering algorithms such as K-Means / hierarchical clustering to obtain the ability to output multiple disaster category results, each of which contains one or more historical disaster events.

[0054] Furthermore, first information in the disaster information is determined, and a disaster category of the target disaster event is determined based on the first information;

[0055] When it is determined that there are at least two disaster categories, second information in the disaster event is determined;

[0056] When it is determined according to the second information that the disaster category of the target disaster event is one, all historical disaster events in the disaster category are selected as similar historical disaster events.

[0057] In this regard, it should be noted that some input disaster information (i.e., the first information) is used as input to the disaster analysis model to calculate the similarity with each disaster category to obtain one or more disaster category results. If it is a single disaster category result, there is no need to supplement other information. If it is multiple disaster category results, the system interface will further prompt you to supplement other disaster information (i.e., the second information). For example, when the disaster type is heavy rain, you may need to supplement the precipitation. When the disaster type is an earthquake, you may need to supplement the earthquake intensity, etc., until a disaster category result is finally output.

[0058] In the present invention, similar historical disaster events have corresponding compensation information. The compensation information includes daily expenditure data such as salary expenditure and cost expenditure. Since these historical disaster events are similar to the target disaster event, based on the compensation information of similar historical disaster events, the expenditure forecast amount of the target disaster event on the i-th day after the occurrence time can be predicted.

[0059] The prediction process can be achieved by inputting the compensation information of similar historical disaster events into the expenditure amount prediction model, and the expenditure amount prediction model outputs the corresponding expenditure prediction amount for the i-th day.

[0060] In the present invention, the daily expenditure data such as salary expenditure and cost expenditure of multiple historical disaster events are used as sample data, and dirty data such as data anomalies and classification anomalies are eliminated. The data are summarized on a daily basis according to expenditure categories such as compensation, salary, and expenses. The total amount of each category is used as the sequence value of the time series, and the data is divided according to different time periods and put into XGBoost / LSTM model training. The optimal time period for different expenditure categories is found through the mean error between the actual value and the estimated value, and an insurance fund expenditure amount prediction model is established to output the expenditure forecast amount for the i-th day.

[0061] In the present invention, there will be a certain number of compensation claims from the occurrence to the end of each historical disaster event. Therefore, each historical disaster event is a group compensation event. To this end, it is necessary to obtain the basic group characteristics and group compensation characteristics of similar historical disaster events. It is also necessary to obtain the basic group characteristics of the target disaster event (input configuration is required by the insurance agent).

[0062] In the present invention, the basic characteristics of the group include the center latitude Center_lat, the center longitude Center_lng, the number of days since the disaster occurred Days_pass, the number of victims Disater_victims, etc. The group payment characteristics include the average amount of compensation Paid_amount, the number of reports Regist_count, the claim period Claim_period, the maximum claim duration Max_claim_days, etc.

[0063] In the present invention, the difference between the basic characteristics of the group of the target disaster event and the basic characteristics of the group of similar historical disaster events (such as latitude difference, longitude difference, time difference, number of people difference, etc.) is calculated, and the sum of the difference values ​​is taken as the impact degree of the target disaster event.

[0064] The impact of cases with more recent history will be higher, and the impact of cases with longer history will be lower. The impact of cases with close geographical locations will be higher, and the impact of cases with far geographical locations will be lower. The impact of the estimated number of disaster victims is greater than the number of disaster victims in the category, and the impact of the estimated number of disaster victims is lower than the number of disaster victims in the category.

[0065] In the present invention, the average compensation amount and the number of compensation claims are determined based on the group compensation characteristics of similar historical disaster events;

[0066] Multiply the average compensation amount and the number of claims, and add the impact to get the revised compensation amount.

[0067] In the present invention, group claim characteristics also include the average claim period Claim_period, the maximum claim duration Max_claim_days, etc. Experience and statistical results show that the claim period of insurance cases follows a skewed distribution with a center to the left. Therefore, Claim_period represents the claim period of most cases in the same category, and Max_claim_days represents the maximum duration of continuous payment. The proportion of events in which claims are completed on any i-th day between 0 and Max_claim_days can be extracted based on the distribution.

[0068] In the present invention, the expenditure amount of the target disaster event on the i-th day after the occurrence time is determined according to the expenditure forecast amount, the revised compensation amount and the event ratio. That is, the revised compensation amount and the event ratio are multiplied to obtain the revised amount of the target disaster event on the i-th day after the occurrence time, and then the expenditure forecast amount and the revised amount are summed to obtain the expenditure amount of the target disaster event on the i-th day after the occurrence time.

[0069] The method for predicting insurance fund expenditure for disaster events provided by the present invention obtains the expenditure forecast amount, revised compensation amount and the proportion of events for which claims are completed after the occurrence of the target disaster event through compensation information and feature analysis of historical disaster events similar to the target disaster event. The expenditure forecast amount, revised compensation amount and event proportion are then used to determine the expenditure amount at any number of days after the occurrence of the event, thereby achieving reasonable improvement of the compensation for the event from multiple dimensions, reflecting a more accurate expenditure amount, and facilitating the smooth progress and planning of the compensation business.

[0070] The following is a description of the insurance fund expenditure prediction device for disaster events provided by the present invention. The insurance fund expenditure prediction device for disaster events described below and the insurance fund expenditure prediction method for disaster events described above can be referenced to each other.

[0071] Figure 2 A schematic diagram showing a flow chart of a device for predicting insurance fund expenditures for disaster events provided by the present invention is shown in FIG. Figure 2 The device comprises a matching module 21, a prediction module 22, an analysis module 23 and a processing module 24, wherein:

[0072] A matching module 21 is used to determine similar historical disaster events based on the disaster information of the target disaster event;

[0073] The prediction module 22 is used to determine the predicted expenditure amount of the target disaster event on the i-th day after the occurrence time based on the compensation information of similar historical disaster events;

[0074] The analysis module 23 is used to determine the proportion of all events that complete claims settlement on the i-th day between the occurrence time and the maximum compensation time, and the modified compensation amount corresponding to the target disaster event based on the group basic characteristics and group compensation characteristics of similar historical disaster events and the group basic characteristics of the target disaster event;

[0075] The processing module 24 is used to determine the expenditure amount of the target disaster event on the i-th day after the occurrence time according to the expenditure forecast amount, the modified compensation amount and the event ratio.

[0076] In a further embodiment of the above device, the analysis module is specifically used to:

[0077] Determine the impact of the target disaster event based on the basic group characteristics of the target disaster event and the basic group characteristics of similar historical disaster events;

[0078] Determine the average compensation amount and the number of compensation claims based on the group compensation characteristics of similar historical disaster events;

[0079] The revised compensation amount is determined based on the average compensation amount per case, the number of compensation claims and the degree of impact.

[0080] In a further device of the above device, the matching module is specifically used for:

[0081] Determine first information in the disaster information, and determine the disaster category of the target disaster event according to the first information;

[0082] When it is determined that there are at least two disaster categories, second information in the disaster event is determined;

[0083] When it is determined according to the second information that the disaster category of the target disaster event is one, all historical disaster events in the disaster category are selected as similar historical disaster events.

[0084] In a further device of the above device, the processing module is specifically used for:

[0085] Determine the revised compensation amount on the ith day after the occurrence of the target disaster event according to the revised compensation amount and the event ratio;

[0086] Based on the forecast and revised expenditure amounts, determine the expenditure amount for the target disaster event on the i-th day after it occurs.

[0087] Since the principle of the device described in the embodiment of the present invention is the same as that of the method described in the above embodiment, a more detailed explanation will not be repeated here.

[0088] It should be noted that, in the embodiment of the present invention, the relevant functional modules can be implemented by a hardware processor.

[0089] The insurance fund expenditure prediction device for disaster events provided by the present invention obtains the expenditure prediction amount, revised compensation amount and the proportion of events for which claims are completed after the occurrence of the target disaster event through compensation information and feature analysis of historical disaster events similar to the target disaster event. The expenditure prediction amount, revised compensation amount and event proportion are then used to determine the expenditure amount at any number of days after the occurrence of the event, thereby achieving reasonable improvement of the compensation for the event from multiple dimensions, reflecting a more accurate expenditure amount, and facilitating the smooth progress and planning of the compensation business.

[0090] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3As shown, the electronic device may include: a processor 31, a communication interface 32, a memory 33 and a communication bus 34, wherein the processor 31, the communication interface 32 and the memory 33 communicate with each other through the communication bus 34. The processor 31 may call a computer program in the memory 33 to execute the steps of the insurance fund expenditure prediction method for disaster events, for example, including: determining similar historical disaster events according to the disaster information of the target disaster event; determining the expenditure prediction amount of the target disaster event on the i-th day after the occurrence time according to the compensation information of similar historical disaster events; determining the proportion of all events that complete the claim settlement on the i-th day between the occurrence time and the maximum compensation time according to the group basic characteristics and group compensation characteristics of similar historical disaster events and the group basic characteristics of the target disaster event, and the modified compensation amount corresponding to the target disaster event; determining the expenditure amount of the target disaster event on the i-th day after the occurrence time according to the expenditure prediction amount, the modified compensation amount and the event proportion.

[0091] In addition, the logic instructions in the above-mentioned memory 33 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0092] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the steps of a method for predicting insurance fund expenditures for disaster events, for example including: determining similar historical disaster events based on disaster information of a target disaster event; determining a forecast expenditure amount for the target disaster event on the i-th day after the occurrence time based on compensation information of similar historical disaster events; determining the proportion of events in which claims are completed on the i-th day between the occurrence time and the maximum compensation time among all events based on the basic group characteristics and group compensation characteristics of similar historical disaster events, as well as the basic group characteristics of the target disaster event; determining the expenditure amount of the target disaster event on the i-th day after the occurrence time based on the expenditure forecast amount, the revised compensation amount and the event proportion.

[0093] On the other hand, an embodiment of the present invention also provides a processor-readable storage medium, which stores a computer program, and the computer program is used to enable the processor to execute the steps of a method for predicting insurance fund expenditures for disaster events, for example including: determining similar historical disaster events based on disaster information of a target disaster event; determining a predicted expenditure amount for the target disaster event on the i-th day after the occurrence time based on compensation information of similar historical disaster events; determining the proportion of events among all events that complete claims settlement on the i-th day between the occurrence time and the maximum compensation time, and a revised compensation amount corresponding to the target disaster event, based on the basic group characteristics and group compensation characteristics of similar historical disaster events, as well as the basic group characteristics of the target disaster event; determining the expenditure amount of the target disaster event on the i-th day after the occurrence time based on the predicted expenditure amount, the revised compensation amount and the event proportion.

[0094] The processor-readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD)), etc.

[0095] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0096] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting insurance fund expenditures for disaster events, characterized in that: include: Determine similar historical disaster events based on the disaster information of the target disaster event; wherein a disaster analysis model is configured, the model takes the disaster information of the target disaster event as input, and then outputs similar historical disaster events; Determine the forecast amount of expenditure on the i-th day after the target disaster event occurs based on the compensation information of similar historical disaster events; According to the basic group characteristics and group compensation characteristics of similar historical disaster events, as well as the basic group characteristics of the target disaster event, determine the proportion of all events that complete claims settlement on the i-th day between the occurrence time and the maximum compensation time, and the modified compensation amount corresponding to the target disaster event; The expenditure amount of the target disaster event on the i-th day after the occurrence time is determined based on the expenditure forecast amount, the modified compensation amount and the event ratio.

2. The method for predicting insurance fund expenditures for disaster events according to claim 1, characterized in that: According to the basic group characteristics and group compensation characteristics of similar historical disaster events, as well as the basic group characteristics of the target disaster event, the modified compensation amount corresponding to the target disaster event is determined, including: Determine the impact of the target disaster event according to the basic characteristics of the group of the target disaster event and the basic characteristics of the group of similar historical disaster events; Determine the average compensation amount and the number of compensation claims based on the group compensation characteristics of similar historical disaster events; The revised compensation amount shall be determined based on the average compensation amount of each case, the number of compensation claims and the degree of impact.

3. The method for predicting insurance fund expenditures for disaster events according to claim 1, characterized in that: Determining similar historical disaster events based on the disaster information of the target disaster event includes: Determine first information in the disaster information, and determine the disaster category of the target disaster event according to the first information; When it is determined that the disaster category is at least two, determining second information in the disaster event; When it is determined according to the second information that the disaster category of the target disaster event is one, all historical disaster events in the disaster category are selected as similar historical disaster events.

4. The method for predicting insurance fund expenditures for disaster events according to claim 1, characterized in that: Determine the expenditure amount of the target disaster event on the i-th day after the occurrence time according to the expenditure forecast amount, the modified compensation amount and the event ratio, including: Determine the revised compensation amount on the i-th day after the occurrence of the target disaster event according to the revised compensation amount and the event ratio; The expenditure amount of the target disaster event on the i-th day after the occurrence time is determined based on the forecast expenditure amount and the revised amount.

5. A device for predicting insurance fund expenditures for disaster events, characterized in that: include: A matching module is used to determine similar historical disaster events based on the disaster information of the target disaster event; wherein a disaster analysis model is configured, the model takes the disaster information of the target disaster event as input, and then outputs similar historical disaster events; A prediction module, used to determine the predicted amount of expenditure on the i-th day after the occurrence of the target disaster event based on the compensation information of similar historical disaster events; An analysis module, for determining the proportion of all events that complete claims settlement on the i-th day between the occurrence time and the maximum compensation time, and the modified compensation amount corresponding to the target disaster event, based on the group basic characteristics and group compensation characteristics of similar historical disaster events and the group basic characteristics of the target disaster event; A processing module is used to determine the expenditure amount of the target disaster event on the i-th day after the occurrence time according to the expenditure forecast amount, the modified compensation amount and the event ratio.

6. The insurance fund expenditure prediction device for disaster events according to claim 5, characterized in that: The analysis module is specifically used in the process of determining the revised compensation amount: Determine the impact of the target disaster event according to the basic characteristics of the group of the target disaster event and the basic characteristics of the group of similar historical disaster events; Determine the average compensation amount and the number of compensation claims based on the group compensation characteristics of similar historical disaster events; The revised compensation amount shall be determined based on the average compensation amount of each case, the number of compensation claims and the degree of impact.

7. The insurance fund expenditure prediction device for disaster events according to claim 5, characterized in that: The matching module is specifically used for: Determine first information in the disaster information, and determine the disaster category of the target disaster event according to the first information; When it is determined that the disaster category is at least two, determining second information in the disaster event; When it is determined according to the second information that the disaster category of the target disaster event is one, all historical disaster events in the disaster category are selected as similar historical disaster events.

8. The insurance fund expenditure prediction device for disaster events according to claim 5, characterized in that: The processing module is specifically used for: Determine the revised compensation amount on the i-th day after the occurrence of the target disaster event according to the revised compensation amount and the event ratio; The expenditure amount of the target disaster event on the i-th day after the occurrence time is determined based on the forecast expenditure amount and the revised amount.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method for predicting insurance fund expenditure for disaster events as described in any one of claims 1 to 4 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for predicting insurance fund expenditure for disaster events as claimed in any one of claims 1 to 4 are implemented.

Images