Data verification method, device, computer equipment and readable storage medium

By acquiring and simulating case data, combining predictive models and similarity calculations, the problem of insufficient case sample data in the medical field is solved, and the data reliability and model performance are improved.

CN111739646BActive Publication Date: 2024-12-03SHENZHEN PING AN MEDICAL HEALTH TECHNOLOGY SERVICES CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202010574333.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-06-22
Publication Date
2024-12-03
Estimated Expiration
2040-06-22

AI Technical Summary

Technical Problem

In the medical field, insufficient data volume, difficulty in obtaining and poor quality of case samples, resulting in insufficient data during model training, affecting the stability and performance of the model.

Method used

By obtaining the sample case data of the set number of users for N consecutive years, using the data simulation model to simulate new case data, and predict the target index value through the prediction model, calculate the similarity value to determine the reliability of the simulation data. If the threshold is greater than the simulation data, otherwise it will not be used.

Benefits of technology

It improves the reliability and accuracy of simulated case data, ensures the quality and quantity of data during model training, and enhances the stability and performance of the model.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN111739646B_ABST
    Figure CN111739646B_ABST
Patent Text Reader

Abstract

The present invention relates to data processing and provides a data verification method, which comprises: obtaining sample case data of a set number of users for N consecutive years, and simulating simulated case data of each user in the N+1th year by using a data simulation model based on the sample case data; predicting a first indicator value of a target indicator of each user in the N+1th year based on the sample case data by using a prediction model; predicting a second indicator value of the target indicator of each user in the N+1th year by using the prediction model based on the simulated case data of each user in the N+1th year; calculating a similarity value between the first indicator value and the second indicator value by using a similarity calculation model; if the similarity value is greater than a preset threshold, using the data simulation model to simulate the case data; in addition, the present invention also relates to blockchain technology, and the simulation data can be stored in a blockchain node; the present invention ensures that the simulated case data has high reliability and accuracy.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a data verification method, device, computer equipment and readable storage medium. Background Art

[0002] With the continuous development of machine learning algorithms, machine learning algorithms can be used in various fields to train models for prediction, classification, and clustering. In the process of model training, a large amount of sample data is required to ensure the stability and high performance of the model. However, in the medical field, there are problems such as insufficient case sample data, difficulty in obtaining case samples, and poor quality of case samples. Therefore, how to use limited case sample data to fit more and better quality case sample data has become a technical problem that technical personnel in this field urgently need to solve. Summary of the invention

[0003] The object of the present invention is to provide a data verification method, device, computer equipment and readable storage medium, which can ensure that the simulated case data has high reliability and accuracy.

[0004] According to one aspect of the present invention, a data verification method is provided, which specifically comprises the following steps:

[0005] Obtaining N consecutive years of sample case data of a set number of users, and using a preset data simulation model to simulate the simulated case data of each user in the N+1th year based on the sample case data;

[0006] Using a preset prediction model, predicting the first indicator value of the target indicator for each user in the N+1th year based on the sample case data of the set number of users for N consecutive years;

[0007] According to the simulated case data of each user in the N+1th year, using the prediction model to predict the second indicator value of the target indicator of each user in the N+1th year;

[0008] Calculating a similarity value between the first index value and the second index value using a preset similarity calculation model;

[0009] If the similarity value is greater than a preset threshold, the data simulation model is used to simulate the case data; if the similarity value is less than the preset threshold, the data simulation model is not used to simulate the case data.

[0010] Optionally, the using a preset data simulation model to simulate the simulated case data of each user in the N+1th year according to the sample case data specifically includes:

[0011] Extract target sample data from each sample case data;

[0012] According to the preset classification rules, the target sample data of the same year is divided into a set number of sets, and the data volume of the target sample data in each set of the year is counted;

[0013] A conversion probability matrix is ​​formed according to the data volume of the target sample data in each set of different years; the conversion probability matrix is ​​used to predict the data volume distribution of the target sample data in each set of the next year according to the data volume distribution of the target sample data in each set of the previous year;

[0014] According to the sample case data of the Nth year and the conversion probability matrix, a preset data simulation model is used to simulate the simulated case data of the target sample data of the N+1th year.

[0015] Optionally, the method of using a preset prediction model to predict the first indicator value of the target indicator of each user in the N+1th year based on the sample case data of the set number of users for N consecutive years specifically includes:

[0016] Setting L indicator value intervals of the target indicator, and training a corresponding prediction model for each indicator value interval; the prediction model is used to predict the probability value of the indicator value of the target indicator within the corresponding indicator value interval;

[0017] For a user, using the user's N consecutive years of sample case data and various prediction models, obtain the prediction result value of each prediction model;

[0018] The index value interval corresponding to the prediction model with the largest prediction result value is used as the first index value of the user's target index in the N+1th year.

[0019] Optionally, predicting the second indicator value of the target indicator for each user in the N+1 year by using the prediction model according to the simulated case data of each user in the N+1 year specifically includes:

[0020] Obtaining prediction models for each indicator value interval corresponding to the target indicator;

[0021] For a user, using the simulated case data of the user in the N+1th year and various prediction models, the preset result values ​​of various preset models are obtained;

[0022] The index value interval corresponding to the prediction model with the largest preset result value is used as the second index value of the user's target index in the N+1th year.

[0023] Optionally, the calculating the similarity value between the first index value and the second index value by using a preset similarity calculation model specifically includes:

[0024] The first index values ​​of all users are formed into a first set, and the second index values ​​of all users are formed into a second set;

[0025] A preset similarity calculation model is used to calculate a similarity value between the first set and the second set.

[0026] According to another aspect of the present invention, a data verification device is also provided, which specifically includes the following components:

[0027] A simulation module is used to obtain sample case data of a set number of users for N consecutive years, and use a preset data simulation model to simulate the simulated case data of each user in the N+1th year based on the sample case data;

[0028] A first prediction module is used to predict the first indicator value of the target indicator of each user in the N+1th year based on the sample case data of the set number of users for N consecutive years by using a preset prediction model;

[0029] A second prediction module is used to predict the second indicator value of the target indicator of each user in the N+1 year by using the prediction model according to the simulated case data of each user in the N+1 year;

[0030] A calculation module, used to calculate the similarity value between the first index value and the second index value by using a preset similarity calculation model;

[0031] A judgment module is used to use the data simulation model to simulate the case data if the similarity value is greater than a preset threshold; if the similarity value is less than the preset threshold, not use the data simulation model to simulate the case data.

[0032] Optionally, the simulation module is specifically used for:

[0033] Extract target sample data from each sample case data;

[0034] According to the preset classification rules, the target sample data of the same year is divided into a set number of sets, and the data volume of the target sample data in each set of the year is counted;

[0035] A conversion probability matrix is ​​formed according to the data volume of the target sample data in each set of different years; the conversion probability matrix is ​​used to predict the data volume distribution of the target sample data in each set of the next year according to the data volume distribution of the target sample data in each set of the previous year;

[0036] According to the sample case data of the Nth year and the conversion probability matrix, a preset data simulation model is used to simulate the simulated case data of the target sample data of the N+1th year.

[0037] Optionally, the computing module is specifically used to:

[0038] The first index values ​​of all users are formed into a first set, and the second index values ​​of all users are formed into a second set;

[0039] A preset similarity calculation model is used to calculate a similarity value between the first set and the second set.

[0040] According to another aspect of the present invention, a computer device is provided, which specifically includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the above-mentioned data verification method when executing the program.

[0041] According to another aspect of the present invention, there is also provided a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the above-mentioned data verification method are implemented.

[0042] The data verification method, device, computer equipment and readable storage medium provided by the present invention utilize a data simulation model to simulate new case data based on historical case data. However, in order to verify the reliability of the simulated case data, the index value of the target index is predicted based on the historical case data and the simulated case data respectively. In the present invention, the first index value predicted based on the historical case data is used as true data, and the second index value predicted based on the simulated case data is used as false data. If the similarity between the first index value and the second index value is greater than a preset threshold, it means that the reliability of the simulated case data is good, that is, it means that the simulated false data is closer to the real data, and the simulated case data can be used. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0044] Figure 1 An optional flow chart of the data verification method provided in Example 1;

[0045] Figure 2 A schematic diagram of an optional program module of the data verification device provided in Example 2;

[0046] Figure 3 A schematic diagram of an optional hardware architecture of a computer device provided in Example 3. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical scheme and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0048] Embodiment 1

[0049] The embodiment of the present invention provides a data verification method, such as Figure 1 As shown, the method specifically comprises the following steps:

[0050] Step S101: Obtain sample case data of a set number of users for N consecutive years, and use a preset data simulation model to simulate the simulated case data of each user in the N+1th year based on the sample case data; wherein N is a positive integer.

[0051] Specifically, the data simulation model is a model for simulating case data based on the MCMC Markov Chain Monte Carlo algorithm.

[0052] For example, based on the sample case data of a set number of users for 5 consecutive years, the data simulation model constructed based on the MCMC Markov Chain Monte Carlo algorithm is used to simulate the simulated case data of each user in the 6th year. Preferably, the input to the data simulation model is the annual number of visits, annual drug expenses, and disease code of each user for 5 consecutive years, and the output of the data simulation model is the annual number of visits, annual drug expenses, and disease code of each user in the 6th year.

[0053] Furthermore, the method of using a preset data simulation model to simulate the simulated case data of each user in the N+1th year according to the sample case data specifically includes:

[0054] Step A1: extracting target sample data from each sample case data;

[0055] For example, if the target sample data is the number of annual visits, the data value of the number of annual visits is obtained from each sample case data.

[0056] Step A2: According to the preset classification rules, the target sample data of the same year is divided into a set number of sets, and the data volume of the target sample data in each set of the year is counted;

[0057] For example, the annual number of visits is divided into four intervals (for example, the four intervals are: less than three times, three to five times, five to ten times, and more than ten times) to form four sets; for the annual number of visits of all users in one year, the annual number of visits of all users is divided into four sets, and the number of annual visits in each set is counted.

[0058] Step A3: forming a conversion probability matrix according to the data volume of target sample data in each set of different years; the conversion probability matrix is ​​used to predict the data volume distribution of target sample data in each set of the next year according to the data volume distribution of target sample data in each set of the previous year;

[0059] Preferably, step A3 specifically includes:

[0060] Step A31: Calculate the total proportion of the data volume of each set in the first year, and calculate the total proportion of the data volume of each set in the second year;

[0061] The total proportion of the data volume of a set is equal to the data volume of the set divided by the total data volume of all sets;

[0062] Step A32: According to the total proportion of each set in the first year and the total proportion of each set in the second year, the Kolmogorov's Equation formula is used to calculate the conversion probability of a set in the first year being converted into each set in the second year, thereby forming a conversion probability matrix;

[0063] Among them, each row of the conversion probability matrix represents each set of the target sample data in the first year, each column of the conversion probability matrix represents each set of the target sample data in the second year, and each value of the conversion probability matrix represents the conversion probability of a set in the first year being converted into a set in the second year.

[0064] For example, among the 1 million users in the first year, the data volume of set 1 is 60,000, and the data volume of set 2 is 70,000. Then, in the first year, the total proportion of set 1 is 0.06, and the total proportion of set 2 is 0.07; among the 1 million users in the second year, the data volume of set 1 is 68,000, and the data volume of set 2 is 85,000. Then, in the second year, the total proportion of set 1 is 0.068, and the total proportion of set 2 is 0.085; Kolmogorov's Equation formula can be used to calculate the conversion probability that the annual number of visits of a user in the first year is in set 1 and the annual number of visits in the second year is also in set 1, and the conversion probability that the annual number of visits of a user in the first year is in set 1 and the annual number of visits in the second year is in set 2, and so on;

[0065] Step A33: According to the data amount of each set from the 2nd to the Nth year, the conversion probability matrix is ​​continuously adjusted in the manner of steps A31 to A32.

[0066] Step A4: Based on the sample case data of the Nth year and the conversion probability matrix, a preset data simulation model is used to simulate the simulated case data of the target sample data of the N+1th year.

[0067] According to the above steps A1 to A4, various types of simulation case data of the user in the N+1th year are simulated.

[0068] Step S102: using a preset prediction model to predict the first indicator value of the target indicator of each user in the N+1th year based on the sample case data of the set number of users for N consecutive years.

[0069] Specifically, the prediction model is a medical expense prediction model constructed based on CNN convolutional neural network and RNN recurrent neural network, and the target indicator is the annual total medical expense in the N+1th year; for example, for a user, based on the user's case sample data for 5 consecutive years, the medical expense prediction model is used to predict the user's annual total medical expense in the 6th year.

[0070] In this embodiment, the training set and the test set are divided in a ratio of 4:1; the training set is used to train the prediction model, and the test set is used to test the performance of the prediction model. The input of the prediction model is the number of annual visits, annual drug expenses, and disease codes for 5 consecutive years, and the output of the prediction model is the user's total annual medical expenses in the 6th year.

[0071] Further, step S102 includes:

[0072] Step B1: setting L indicator value intervals of the target indicator, and training a corresponding prediction model for each indicator value interval; the prediction model is used to predict the probability value of the indicator value of the target indicator within the corresponding indicator value interval, wherein L is a positive integer;

[0073] For example, when the target indicator is the annual total medical expenses, five indicator value intervals are set: less than 100 yuan, 100 to 500 yuan, 500 to 1,000 yuan, 1,000 to 5,000 yuan, and greater than 5,000 yuan, and a corresponding medical expense prediction model is set for each indicator value interval; the medical expense prediction model of less than 100 yuan is used to predict the probability value that the user's annual total medical expenses in the sixth year are less than 100 yuan; the medical expense prediction model of 100 to 500 yuan is used to predict the probability value that the user's annual total medical expenses in the sixth year are between 100 and 500 yuan.

[0074] Step B2: for a user, using the user's N consecutive years of sample case data and various prediction models, obtain the prediction result value of each prediction model;

[0075] Preferably, step B2 specifically includes:

[0076] For a prediction model, determining characteristic variables required by the prediction model;

[0077] Extracting the characteristic value of the characteristic variable from the sample case data of the user each year;

[0078] The average value of the characteristic value of the characteristic variable in N years is input into the prediction model to obtain the prediction result value of the prediction model.

[0079] Step B3: taking the index value interval corresponding to the prediction model with the largest prediction result value as the first index value of the user's target index in the N+1th year.

[0080] Step S103: Based on the simulated case data of each user in the N+1th year, the prediction model is used to predict the second indicator value of the target indicator of each user in the N+1th year.

[0081] For example, for a user, based on the simulated case data for the 6th year, the medical expense prediction model is used to predict the user's total annual medical expenses for the 6th year.

[0082] Specifically, step S103 includes:

[0083] Step C1: obtaining prediction models for each indicator value interval corresponding to the target indicator;

[0084] Step C2: for a user, using the simulated case data of the user in the N+1th year and various prediction models, obtaining preset result values ​​of various preset models;

[0085] Preferably, step C2 specifically includes:

[0086] For a prediction model, determining characteristic variables required by the prediction model;

[0087] Extracting the characteristic value of the characteristic variable from the simulated case data of the user in the N+1th year;

[0088] The feature value is input into the prediction model to obtain the prediction result value of the prediction model.

[0089] Step C3: Using the index value interval corresponding to the prediction model with the largest preset result value as the second index value of the user's target index in the N+1th year.

[0090] Step S104: Calculate the similarity value between the first index value and the second index value using a preset similarity calculation model.

[0091] In this embodiment, the performance of the prediction model is evaluated by calculating the distance between two index values ​​(ie, the similarity value); when the similarity value is high, it indicates that the prediction model is more reliable; preferably, the similarity calculation model adopts a log-likelihood ratio similarity algorithm.

[0092] Specifically, step S104 includes:

[0093] The first index values ​​of all users are formed into a first set, and the second index values ​​of all users are formed into a second set;

[0094] A preset similarity calculation model is used to calculate a similarity value between the first set and the second set.

[0095] In this embodiment, in order to improve the efficiency of verifying data, the first indicator value of each user is not compared with the second indicator value one by one. Instead, the first indicator values ​​of all users are taken as a set and compared with the second indicator values ​​of all users. By comparing the similarity of the two sets, it can be determined whether the simulation case data is reliable.

[0096] Preferably, step S104 specifically includes:

[0097] Step D1: The first index values ​​of all users are formed into a first set, and the second index values ​​of all users are formed into a second set;

[0098] Step D2: Determine k according to the first set and the second set 11 , k 12 , k 21 , k 22 The value of k 11 represents the number of identical index values ​​in the first set and the second set, k 12 represents the number of indicator values ​​that appear only in the first set, k 21 represents the number of index values ​​that appear only in the second set, k 22 Represents the number of all indicator values ​​that appear in the first set and the second set.

[0099] That is, k 11 is the number of intersections between the first set and the second set, k 12 is the number of items that belong to the first set and do not belong to the second set, k 21 is the number of items that belong to the second set but not to the first set, k 22 is the number of unions of the first set and the second set.

[0100] Step D3: According to k 11 , k 12 , k 21 , k 22 , calculate the travel entropy value according to the following formula:

[0101]

[0102] Step D4: According to k 11 , k 12 , k 21 , k 22 , calculate the column entropy value according to the following formula:

[0103]

[0104] Step D5: According to k 11 , k 12 , k 21 , k 22 , the matrix entropy value is calculated according to the following formula:

[0105]

[0106] Step D6: Calculate the similarity value according to the row entropy value, column entropy value and matrix entropy value according to the following formula:

[0107] Similarity value = 2×(matrixEntropy-rowEntropy-columEntropy).

[0108] Step S105: If the similarity value is greater than a preset threshold, the data simulation model is used to simulate the case data; if the similarity value is less than the preset threshold, the data simulation model is not used to simulate the case data.

[0109] Preferably, the preset threshold is set to 0.9.

[0110] In addition, the method further comprises:

[0111] The simulated case data simulated using the data simulation model is stored in the blockchain node.

[0112] In practical applications, the corresponding summary information is obtained based on the simulated case data. Specifically, the summary information is obtained by hashing the simulated case data, such as using the sha256s algorithm. Uploading the summary information to the blockchain can ensure its security and fairness and transparency to users. The user device can download the summary information from the blockchain to verify whether the simulated case data has been tampered with. The blockchain referred to in this example is a new application model of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. The blockchain can include the blockchain underlying platform, the platform product service layer, and the application service layer.

[0113] In this embodiment, a data simulation model is used to simulate new case data based on historical case data. However, in order to verify the reliability of the simulated case data, the index value of the target index is predicted based on the historical case data and the simulated case data respectively. In this embodiment, the first index value predicted based on the historical case data is used as true data, and the second index value predicted based on the simulated case data is used as false data. If the similarity between the first index value and the second index value is greater than the preset threshold, it means that the reliability of the simulated case data is good, that is, it means that the simulated false data is closer to the real data, and the simulated case data can be used. If the similarity between the first index value and the second index value is less than the preset threshold, it means that the data simulation model is poor, and the data simulation model needs to be adjusted until the similarity between the first index value and the second index value is greater than the preset threshold.

[0114] Embodiment 2

[0115] The embodiment of the present invention provides a data verification device, such as Figure 2 As shown, the device specifically includes the following components:

[0116] The simulation module 201 is used to obtain sample case data of a set number of users for N consecutive years, and use a preset data simulation model to simulate the simulated case data of each user in the N+1th year based on the sample case data;

[0117] The first prediction module 202 is used to predict the first indicator value of the target indicator of each user in the N+1th year based on the sample case data of the set number of users for N consecutive years by using a preset prediction model;

[0118] The second prediction module 203 is used to predict the second indicator value of the target indicator of each user in the N+1 year by using the prediction model according to the simulated case data of each user in the N+1 year;

[0119] A calculation module 204, configured to calculate a similarity value between the first index value and the second index value using a preset similarity calculation model;

[0120] The judgment module 205 is used to use the data simulation model to simulate the case data if the similarity value is greater than a preset threshold; if the similarity value is less than the preset threshold, not use the data simulation model to simulate the case data.

[0121] Specifically, the simulation module 201 is used for:

[0122] Extract target sample data from each sample case data;

[0123] According to the preset classification rules, the target sample data of the same year is divided into a set number of sets, and the data volume of the target sample data in each set of the year is counted;

[0124] A conversion probability matrix is ​​formed according to the data volume of the target sample data in each set of different years; the conversion probability matrix is ​​used to predict the data volume distribution of the target sample data in each set of the next year according to the data volume distribution of the target sample data in each set of the previous year;

[0125] According to the sample case data of the Nth year and the conversion probability matrix, a preset data simulation model is used to simulate the simulated case data of the target sample data of the N+1th year.

[0126] Furthermore, the first prediction module 202 is used to:

[0127] Setting L indicator value intervals of the target indicator, and training a corresponding prediction model for each indicator value interval; the prediction model is used to predict the probability value of the indicator value of the target indicator within the corresponding indicator value interval;

[0128] For a user, using the user's N consecutive years of sample case data and various prediction models, obtain the prediction result value of each prediction model;

[0129] The index value interval corresponding to the prediction model with the largest prediction result value is used as the first index value of the user's target index in the N+1th year.

[0130] Furthermore, the second prediction module 203 is used to:

[0131] Obtaining prediction models for each indicator value interval corresponding to the target indicator;

[0132] For a user, using the simulated case data of the user in the N+1th year and various prediction models, the preset result values ​​of various preset models are obtained;

[0133] The index value interval corresponding to the prediction model with the largest preset result value is used as the second index value of the user's target index in the N+1th year.

[0134] Furthermore, the calculation module 204 is used to:

[0135] The first index values ​​of all users are formed into a first set, and the second index values ​​of all users are formed into a second set;

[0136] A preset similarity calculation model is used to calculate a similarity value between the first set and the second set.

[0137] Embodiment 3

[0138] This embodiment also provides a computer device, such as a smart phone, tablet computer, laptop computer, desktop computer, rack server, blade server, tower server or cabinet server (including an independent server or a server cluster composed of multiple servers) that can execute programs. Figure 3 As shown, the computer device 30 of this embodiment includes at least but not limited to: a memory 301 and a processor 302 that can communicate with each other via a system bus. It should be noted that Figure 3 Only computer device 30 is shown with components 301 - 302 , but it should be understood that implementing all of the components shown is not a requirement, and more or fewer components may alternatively be implemented.

[0139] In this embodiment, the memory 301 (i.e., readable storage medium) includes flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 301 can be an internal storage unit of the computer device 30, such as a hard disk or memory of the computer device 30. In other embodiments, the memory 301 can also be an external storage device of the computer device 30, such as a plug-in hard disk equipped on the computer device 30, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 301 can also include both the internal storage unit of the computer device 30 and its external storage device. In this embodiment, the memory 301 is generally used to store the operating system and various application software installed on the computer device 30, such as the program code of the data verification device of the second embodiment. In addition, the memory 301 can also be used to temporarily store various types of data that have been output or are to be output.

[0140] In some embodiments, the processor 302 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips. The processor 302 is generally used to control the overall operation of the computer device 30 .

[0141] Specifically, in this embodiment, the processor 302 is used to execute a program of the data verification method stored in the processor 302, and the program of the data verification method implements the following steps when being executed:

[0142] Obtaining N consecutive years of sample case data of a set number of users, and using a preset data simulation model to simulate the simulated case data of each user in the N+1th year based on the sample case data;

[0143] Using a preset prediction model, predicting the first indicator value of the target indicator for each user in the N+1th year based on the sample case data of the set number of users for N consecutive years;

[0144] According to the simulated case data of each user in the N+1th year, using the prediction model to predict the second indicator value of the target indicator of each user in the N+1th year;

[0145] Calculating a similarity value between the first index value and the second index value using a preset similarity calculation model;

[0146] If the similarity value is greater than a preset threshold, the data simulation model is used to simulate the case data; if the similarity value is less than the preset threshold, the data simulation model is not used to simulate the case data.

[0147] The specific implementation process of the above method steps can be found in the first embodiment, and this embodiment will not be repeated here.

[0148] Embodiment 4

[0149] This embodiment also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a disk, an optical disk, a server, an App application store, etc., wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following method steps are implemented:

[0150] Obtaining N consecutive years of sample case data of a set number of users, and using a preset data simulation model to simulate the simulated case data of each user in the N+1th year based on the sample case data;

[0151] Using a preset prediction model, predicting the first indicator value of the target indicator for each user in the N+1th year based on the sample case data of the set number of users for N consecutive years;

[0152] According to the simulated case data of each user in the N+1th year, using the prediction model to predict the second indicator value of the target indicator of each user in the N+1th year;

[0153] Calculating a similarity value between the first index value and the second index value using a preset similarity calculation model;

[0154] If the similarity value is greater than a preset threshold, the data simulation model is used to simulate the case data; if the similarity value is less than the preset threshold, the data simulation model is not used to simulate the case data.

[0155] The specific implementation process of the above method steps can be found in the first embodiment, and this embodiment will not be repeated here.

[0156] Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the blockchain node, etc.

[0157] The blockchain referred to in this invention is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0158] It should be noted that, in this article, the terms "include", "comprises" or any other variations 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. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0159] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0160] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0161] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method.

[0162] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A data verification method, characterized in that: The method comprises: Obtaining N consecutive years of sample case data of a set number of users, and using a preset data simulation model to simulate the simulated case data of each user in the N+1th year based on the sample case data; Using a preset prediction model, predicting the first indicator value of the target indicator for each user in the N+1th year based on the sample case data of the set number of users for N consecutive years; According to the simulated case data of each user in the N+1th year, using the prediction model to predict the second indicator value of the target indicator of each user in the N+1th year; Calculating a similarity value between the first index value and the second index value using a preset similarity calculation model; If the similarity value is greater than a preset threshold, the data simulation model is used to simulate the case data; if the similarity value is less than the preset threshold, the data simulation model is not used to simulate the case data; The method of using a preset data simulation model to simulate the simulated case data of each user in the N+1th year according to the sample case data specifically includes: Extract target sample data from each sample case data; According to the preset classification rules, the target sample data of the same year is divided into a set number of sets, and the data volume of the target sample data in each set of the year is counted; A conversion probability matrix is ​​formed according to the data volume of the target sample data in each set of different years; the conversion probability matrix is ​​used to predict the data volume distribution of the target sample data in each set of the next year according to the data volume distribution of the target sample data in each set of the previous year; According to the sample case data of the Nth year and the conversion probability matrix, using a preset data simulation model to simulate the simulated case data of the target sample data of the N+1th year; The method of using a preset prediction model to predict the first indicator value of the target indicator for each user in the N+1th year based on the sample case data of the set number of users for N consecutive years specifically includes: Setting L indicator value intervals of the target indicator, and training a corresponding prediction model for each indicator value interval; the prediction model is used to predict the probability value of the indicator value of the target indicator within the corresponding indicator value interval; For a user, using the user's N consecutive years of sample case data and various prediction models, obtain the prediction result value of each prediction model; The index value interval corresponding to the prediction model with the largest prediction result value is used as the first index value of the user's target index in the N+1th year; The method of predicting the second indicator value of the target indicator for each user in the N+1 year by using the prediction model according to the simulated case data for each user in the N+1 year specifically includes: Obtaining prediction models for each indicator value interval corresponding to the target indicator; For a user, using the simulated case data of the user in the N+1th year and various prediction models, the preset result values ​​of various preset models are obtained; The index value interval corresponding to the prediction model with the largest preset result value is used as the second index value of the user's target index in the N+1th year.

2. The data verification method according to claim 1, characterized in that: The calculating the similarity value between the first index value and the second index value by using a preset similarity calculation model specifically includes: The first index values ​​of all users are formed into a first set, and the second index values ​​of all users are formed into a second set; A preset similarity calculation model is used to calculate a similarity value between the first set and the second set.

3. A data verification device, characterized in that: The device comprises: A simulation module is used to obtain sample case data of a set number of users for N consecutive years, and use a preset data simulation model to simulate the simulated case data of each user in the N+1th year based on the sample case data; A first prediction module is used to predict the first indicator value of the target indicator of each user in the N+1th year based on the sample case data of the set number of users for N consecutive years by using a preset prediction model; A second prediction module is used to predict the second indicator value of the target indicator of each user in the N+1 year by using the prediction model according to the simulated case data of each user in the N+1 year; A calculation module, used to calculate the similarity value between the first index value and the second index value by using a preset similarity calculation model; A judgment module, configured to use the data simulation model to simulate the case data if the similarity value is greater than a preset threshold; and not use the data simulation model to simulate the case data if the similarity value is less than the preset threshold; Wherein, the simulation module is specifically used for: Extract target sample data from each sample case data; According to the preset classification rules, the target sample data of the same year is divided into a set number of sets, and the data volume of the target sample data in each set of the year is counted; A conversion probability matrix is ​​formed according to the data volume of the target sample data in each set of different years; the conversion probability matrix is ​​used to predict the data volume distribution of the target sample data in each set of the next year according to the data volume distribution of the target sample data in each set of the previous year; According to the sample case data of the Nth year and the conversion probability matrix, using a preset data simulation model to simulate the simulated case data of the target sample data of the N+1th year; The first prediction module is specifically used for: Setting L indicator value intervals of the target indicator, and training a corresponding prediction model for each indicator value interval; the prediction model is used to predict the probability value of the indicator value of the target indicator within the corresponding indicator value interval; For a user, using the user's N consecutive years of sample case data and various prediction models, obtain the prediction result value of each prediction model; The index value interval corresponding to the prediction model with the largest prediction result value is used as the first index value of the user's target index in the N+1th year; The second prediction module is specifically used for: Obtaining prediction models for each indicator value interval corresponding to the target indicator; For a user, using the simulated case data of the user in the N+1th year and various prediction models, the preset result values ​​of various preset models are obtained; The index value interval corresponding to the prediction model with the largest preset result value is used as the second index value of the user's target index in the N+1th year.

4. The data verification device according to claim 3, characterized in that: The computing module is specifically used for: The first index values ​​of all users are formed into a first set, and the second index values ​​of all users are formed into a second set; A preset similarity calculation model is used to calculate a similarity value between the first set and the second set.

5. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 2 when executing the program.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 2 are implemented.

Citation Information

Patent Citations

  • Method and device for evaluating curative effect of chronic diseases

    CN108109700A

  • XGBoost disease probability predicting method, system and storage medium

    CN110111888A

  • Method and device for evaluating performance indicator

    CN110178123A

  • Method and device for predicting diabetes, storage medium, and computer device

    CN110197720A

  • Evaluation method and device for numerical similarity of equipment model

    CN111027190A