Search

CN-122023027-A - Data prediction method and device based on artificial intelligence, computer equipment and medium

CN122023027ACN 122023027 ACN122023027 ACN 122023027ACN-122023027-A

Abstract

The application belongs to the technical field of artificial intelligence, and relates to a data prediction method, a device, computer equipment and a storage medium based on artificial intelligence, which comprise the steps of obtaining historical service data corresponding to a target service scene; the method comprises the steps of performing data cleaning processing on historical service data to obtain processed data, performing feature engineering on the processed data to obtain feature data, performing prediction processing on the feature data based on a target ensemble learning model to obtain a first service prediction result, performing prediction processing on the feature data based on a target neural network model to obtain a second service prediction result, performing result fusion on the first service prediction result and the second service prediction result to obtain a target service prediction result, and performing output processing on the target service prediction result. In addition, the application also relates to a blockchain technology, and target business prediction results can be stored in the blockchain. The method and the device can be applied to the service data prediction scene in the field of financial science and technology, and the generation accuracy of the target service prediction result is improved.

Inventors

  • CHEN ZHONGYU

Assignees

  • 中国平安财产保险股份有限公司

Dates

Publication Date
20260512
Application Date
20260114

Claims (10)

  1. 1. An artificial intelligence-based data prediction method is characterized by comprising the following steps: Acquiring historical service data corresponding to a target service scene; performing data cleaning treatment on the historical service data to obtain corresponding treatment data; carrying out characteristic engineering processing on the processing data to obtain corresponding characteristic data; Performing prediction processing on the characteristic data based on a trained target integrated learning model to obtain a corresponding first service prediction result; performing prediction processing on the characteristic data based on the trained target neural network model to obtain a corresponding second service prediction result; Performing result fusion processing on the first service prediction result and the second service prediction result to obtain a corresponding target service prediction result; And outputting the target service prediction result.
  2. 2. The artificial intelligence based data prediction method according to claim 1, wherein the step of performing feature engineering processing on the processed data to obtain corresponding feature data specifically comprises: performing feature construction on the processing data to obtain corresponding initial features; Acquiring a plurality of preset feature selection strategies; determining a target feature selection strategy from all the feature selection strategies; performing feature screening on the initial features based on the target feature selection strategy to obtain specified features associated with a preset prediction target; And taking the designated feature as the feature data.
  3. 3. The artificial intelligence-based data prediction method according to claim 1, wherein the step of performing result fusion processing on the first service prediction result and the second service prediction result to obtain a corresponding target service prediction result specifically comprises: Generating a first weight corresponding to the target ensemble learning model and a second weight corresponding to the target neural network model based on a preset weight generation strategy; Calling a preset fusion formula; calculating the first service prediction result, the second service prediction result, the first weight and the second weight based on the fusion formula to obtain corresponding calculation results; and taking the calculation result as the target service prediction result.
  4. 4. The method for predicting data based on artificial intelligence according to claim 3, wherein the step of generating the first weight corresponding to the target ensemble learning model based on a preset weight generation strategy specifically comprises: Acquiring risk preference information corresponding to the target service scene; performing weight mapping processing on the target ensemble learning model based on the risk preference information to obtain a corresponding first initial weight; Acquiring a preset weight adjustment rule; Performing weight adjustment processing on the first initial weight based on the weight adjustment rule to obtain a corresponding second initial weight; And taking the second initial weight as a first weight corresponding to the target ensemble learning model.
  5. 5. The artificial intelligence based data prediction method according to claim 1, wherein the step of performing data cleaning processing on the historical service data to obtain corresponding processed data specifically comprises: Performing abnormal value removal processing on the historical service data to obtain corresponding first processing data; performing missing value filling processing on the first processing data to obtain corresponding second processing data; performing data standardization processing on the second processing data to obtain corresponding third processing data; and taking the third processing data as the processing data.
  6. 6. The method for predicting data based on artificial intelligence according to claim 1, further comprising, before the step of predicting the feature data based on the trained target ensemble learning model to obtain the corresponding first business prediction result: collecting initial historical service data from a preset service system; cleaning and characteristic engineering processing are carried out on the initial historical service data to obtain corresponding sample data; Dividing the sample data into a training set and a testing set based on a preset dividing proportion; Calling a preset integrated learning model; Training the integrated learning model based on the training set to obtain a trained first generation model; Based on a preset optimization strategy, evaluating and optimizing the first generation model by using the test set to obtain a corresponding second generation model; and taking the second generated model as the target ensemble learning model.
  7. 7. The artificial intelligence based data prediction method according to claim 1, further comprising, after the step of performing output processing on the target traffic prediction result: Calling a preset encryption algorithm; Encrypting the target service prediction result based on the encryption algorithm to obtain a corresponding appointed service prediction result; Acquiring a preset data storage mode; And storing and processing the prediction result of the appointed service based on the data storage mode.
  8. 8. An artificial intelligence based data prediction apparatus, comprising: The first acquisition module is used for acquiring historical service data corresponding to the target service scene; the cleaning module is used for carrying out data cleaning processing on the historical service data to obtain corresponding processing data; the first processing module is used for carrying out characteristic engineering processing on the processing data to obtain corresponding characteristic data; The first prediction module is used for performing prediction processing on the characteristic data based on the trained target integrated learning model to obtain a corresponding first service prediction result; The second prediction module is used for performing prediction processing on the characteristic data based on the trained target neural network model to obtain a corresponding second service prediction result; the fusion module is used for carrying out result fusion processing on the first service prediction result and the second service prediction result to obtain a corresponding target service prediction result; and the output module is used for outputting and processing the target service prediction result.
  9. 9. A computer device comprising a memory having stored therein computer readable instructions which when executed implement the steps of the artificial intelligence based data prediction method of any of claims 1 to 7.
  10. 10. A computer readable storage medium having stored thereon computer readable instructions which when executed by a processor implement the steps of the artificial intelligence based data prediction method of any of claims 1 to 7.

Description

Data prediction method and device based on artificial intelligence, computer equipment and medium Technical Field The application relates to the technical field of artificial intelligence, and can be applied to the field of financial science and technology, in particular to a data prediction method, a data prediction device, computer equipment and a storage medium based on artificial intelligence. Background In the reinsurance business processing process in the financial field, surplus contracts play a key role as a common risk prevention, control and dispersion means. The core mechanism is that the reinsurance branch company determines the self-reservation amount and the line number according to the self-risk bearing capacity, and transfers the part exceeding the self-reservation amount of the insurance mark to the reinsurance company according to the established line number proportion, so that reasonable risk dispersion is realized. Traditionally, determining surplus contract lines is mainly based on experience judgment of business personnel, and is combined with the existing risk-producing and warranty system to upload EXCEL files for rough calculation. However, this method has significant drawbacks, since it relies on manual experience and the calculation method is relatively simple, resulting in extremely poor accuracy of the generated business result. For example, in the property insurance business in the financial field, for the comprehensive property insurance of a large manufacturing enterprise, the insurance standard covers complex factories, equipment, inventory and the like, and a plurality of related risk factors including natural disaster risks, accident risks and the like are involved. When the surplus contract line number is determined by using the traditional method, service personnel can estimate the contract line number only according to simple data and self experience of similar past projects, and the risk-producing reinsurance system can only perform preliminary analysis based on the uploaded limited EXCEL data, cannot comprehensively and accurately consider the influence of various risk factors on line number determination, so that the calculated surplus contract line number has larger deviation from the actual optimal line number, the effect of reinsurance service risk dispersion is affected, and potential economic loss can be brought to reinsurers and parties. Therefore, it is highly desirable to develop a method capable of improving the generation accuracy of surplus contract lines, which has important practical significance. Disclosure of Invention The embodiment of the application aims to provide a data prediction method, a device, computer equipment and a storage medium based on artificial intelligence, so as to solve the technical problem that the generated service result has extremely poor accuracy in the existing service processing mode for determining surplus contract line numbers. In a first aspect, there is provided an artificial intelligence based data prediction method, comprising: Acquiring historical service data corresponding to a target service scene; performing data cleaning treatment on the historical service data to obtain corresponding treatment data; carrying out characteristic engineering processing on the processing data to obtain corresponding characteristic data; Performing prediction processing on the characteristic data based on a trained target integrated learning model to obtain a corresponding first service prediction result; performing prediction processing on the characteristic data based on the trained target neural network model to obtain a corresponding second service prediction result; Performing result fusion processing on the first service prediction result and the second service prediction result to obtain a corresponding target service prediction result; And outputting the target service prediction result. In a second aspect, there is provided an artificial intelligence based data prediction apparatus comprising: The first acquisition module is used for acquiring historical service data corresponding to the target service scene; the cleaning module is used for carrying out data cleaning processing on the historical service data to obtain corresponding processing data; the first processing module is used for carrying out characteristic engineering processing on the processing data to obtain corresponding characteristic data; The first prediction module is used for performing prediction processing on the characteristic data based on the trained target integrated learning model to obtain a corresponding first service prediction result; The second prediction module is used for performing prediction processing on the characteristic data based on the trained target neural network model to obtain a corresponding second service prediction result; the fusion module is used for carrying out result fusion processing on the first service prediction result