A data processing system based on group coding

Abstract

The present invention relates to the field of data processing, and in particular to a data processing system based on group coding. When a computer program is executed by a processor, the following steps are implemented: matching a medical record data combination set with a target group coding set to obtain a group category set and a first group set, obtaining a corresponding reporting degree according to a group subcategory corresponding to any coding data combination in the first group set, judging a corresponding reporting information category according to the reporting degree and a preset first reporting degree threshold, thereby obtaining first reporting data, grouping the coding data combinations, and measuring the reporting degree of each coding data combination in the first group set, obtaining a reporting information category to obtain the first reporting data, thereby improving the accuracy of the first reporting data, thereby optimizing the guiding effect on doctors modifying diagnosis data and surgery and operation data, on medical insurance bureaus and hospitals settling expenses, and on updating and reforming DRG grouping.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a data processing system based on group coding. Background Art

[0002] DRG (Diagnosis Related Groups) is a classification method used in medical management and payment systems. Patients are divided into several diagnosis groups for management based on factors such as their diagnostic data and surgical operation data. Medical insurance payers will formulate payment standards based on the diagnosis groups and conduct direct settlement with hospitals. The patient's own payment method, reimbursement ratio, etc. will not change, thereby improving the ability to control medical expenses as well as the capacity and efficiency of medical services.

[0003] In the process of grouping patients into diagnostic groups, when errors occur in filling out the patient's diagnostic data and surgical operation data, or when some diseases are not included in the DRG grouping system, errors will occur in the judgment of the diagnostic group, thus affecting the accuracy of the fee settlement of the medical insurance bureau and the hospital. Therefore, grouping patients according to their diagnostic data and surgical operation data, and reporting the corresponding information based on the grouping results, has guiding significance for doctors to fill in diagnostic data and surgical operation data, medical insurance bureaus and hospitals to settle fees, and for the update and reform of DRG grouping.

[0004] Therefore, how to improve the accuracy of reported information and thus optimize the guidance effect on hospitals, medical insurance bureaus and DRG grouping rules has become an urgent problem to be solved. Summary of the invention

[0005] In view of the above technical problems, the technical solution adopted by the present invention is a data processing system based on group coding, wherein the data processing system based on group coding includes a processor and a memory storing a computer program, and the memory also stores a coded data combination set A={A1, A2, ..., A i , ..., A m}、Target group coding set B = {B1, B2, ..., B j , ..., B n}, the total number of diagnosis codes P, the total number of operation codes Q, the total number of operations Z1 and the total number of diagnoses Z2 corresponding to the target object, the i-th coding data combination A i ={A i 1 , A i 2}, A i 1 refers to the diagnostic code in the ith coding data combination, A i 2refers to the operation code in the i-th coded data combination, B j Refers to the jth target group code, and the memory also stores A i 1 The corresponding association operation encoding set D i , A i 1 The corresponding number of diagnoses, A i 2 The corresponding associated diagnosis code set R i and A i 2 The corresponding number of operations, D i Included with A i 1 The associated p i Operation code, R i Included with A i 2 Associated q i diagnostic codes, wherein i=1, 2, ..., m, m refers to the total number of coded data combinations, j=1, 2, ..., n, n refers to the total number of target group codes, and when the computer program is executed by a processor, the following steps are implemented:

[0006] S1, match A and B, and obtain the grouping category set C corresponding to A = {C1, C2, ..., C i , ..., C m}, where C i A i The corresponding grouping categories include complete match, partial mismatch and complete mismatch. The corresponding grouping subcategories of partial mismatch include operation code mismatch and diagnosis code mismatch.

[0007] S2, grouping all the coded data combinations according to C to obtain a first grouping set QY, wherein QY includes all the coded data combinations with a grouping category of partial mismatch.

[0008] S3, for any coded data combination QY in QY 0 , according to QY 0 Corresponding group sub-category, get QY 0 The corresponding reporting level W 0 , S3 specifically includes the following steps:

[0009] S31, if QY 0 The corresponding group subcategory is the operation code does not match, then according to QY 0 The associated diagnosis code set R corresponding to the operation code 0 , the corresponding operation times S1, P and Z1, get QY 0The corresponding reporting level W 0 =α1×q 0 / P+α2×S1 / Z1, where α1 refers to the preset first priority, α2 refers to the preset second priority, q 0 Refers to R 0 The total number of diagnostic codes in the .

[0010] S32, if QY 0 The corresponding grouping subcategory is a mismatch in diagnosis code, then according to QY 0 The associated operation code set D corresponding to the diagnosis code 0 , the corresponding diagnosis times S2, Q and Z2, get QY 0 The corresponding reporting level W 0 =α3×p 0 / Q+α4×S2 / Z2, where α3 refers to the preset third priority, α4 refers to the preset fourth priority, and p 0 It means D 0 The total number of operation codes in .

[0011] S4, according to W 0 and the preset first reporting level threshold Y1, judge QY 0 Corresponding reporting information category.

[0012] S5, traverse all the coded data combinations in QY and obtain the first reporting data, wherein the first reporting data includes all the coded data combinations in QY and the reporting information category corresponding to each coded data combination in QY.

[0013] The present invention has at least the following beneficial effects: matching A and B, obtaining a grouping category set C corresponding to A, grouping all coded data combinations according to C, obtaining a first grouping set QY, and for any coded data combination QY in QY 0 , according to QY 0 Corresponding group sub-category, get QY 0 The corresponding reporting level W 0 , according to W 0 and the preset first reporting level threshold Y1, judge QY 0 The corresponding reporting information category is traversed through all the coded data combinations in QY to obtain the first reporting data. It can be seen that by grouping the coded data combinations and measuring the reporting degree of each coded data combination in the first grouping set, the reporting information category is obtained to obtain the first reporting data, which improves the accuracy of the first reporting data, thereby optimizing the guidance effect on doctors modifying diagnosis data and operation data, medical insurance bureaus and hospitals settling expenses, and updating and reforming DRG grouping. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0015] Figure 1 A flowchart of a processor of a data processing system based on block coding implementing a computer program is provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0017] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0018] The first embodiment provides a data processing system based on group coding, the data processing system based on group coding includes a processor and a memory storing a computer program, the memory also stores a target object coding data combination set A={A1, A2, . . . , A i , ..., A m}、Target group coding set B = {B1, B2, ..., B j , ..., B n}, the total number of diagnosis codes P, the total number of operation codes Q, the total number of operations Z1 and the total number of diagnoses Z2 corresponding to the target object, the i-th coding data combination A i ={A i 1 , A i 2}, Ai 1 refers to the diagnostic code in the ith coding data combination, A i 2 refers to the operation code in the i-th coded data combination, B j Refers to the jth target group code, and the memory also stores A i 1 The corresponding association operation encoding set D i , A i 1 The corresponding number of diagnoses, A i 2 The corresponding associated diagnosis code set R i and A i 2 The corresponding number of operations, D i Included with A i 1 The associated p i Operation code, R i Included with A i 2 Associated q i diagnostic codes, wherein i=1, 2, ..., m, m refers to the total number of coding data combinations, j=1, 2, ..., n, n refers to the total number of group codes, and when the computer program is executed by the processor, the following steps are implemented, such as Figure 1 As shown:

[0019] S1, match A and B, and obtain the grouping category set C corresponding to A = {C1, C2, ..., C i , ..., C m}, where C i A i The corresponding grouping categories include complete match, partial mismatch and complete mismatch. The corresponding grouping subcategories of partial mismatch include operation code mismatch and diagnosis code mismatch.

[0020] The target object may refer to the medical records of several patients, and several diagnosis codes and operation codes corresponding to several surgeries and operations of the patients are extracted from the medical records, and then several coding data combinations are obtained to form a coding data combination set A. The coding data combination includes the corresponding diagnosis code and operation code, which serves as the basis for data analysis.

[0021] The target group code may refer to a DRG (Diagnosis Related Groups) code.

[0022] The total number of diagnostic codes P may refer to the total number of categories of diagnostic codes extracted from the target object, the total number of operation codes Q may refer to the total number of categories of operation codes extracted from the target object, the total number of operations Z1 may refer to the total number of surgical operations extracted from the target object, and the total number of diagnoses Z2 may refer to the total number of diagnostic results extracted from the target object.

[0023] Each diagnosis code A i 1 It also corresponds to an associated operation encoding set D i , D i Included in the diagnosis code A i 1 The associated p i operation code, that is, when the diagnosis result corresponds to the diagnosis code A i 1 The possible surgical procedures and operation codes corresponding to the procedures. i 1 The corresponding diagnosis number may refer to the diagnosis code A extracted from the diagnosis result data of the target object. i 1 The number of times.

[0024] Each operation is coded as A i 2 There is also an associated diagnostic code set R i , R i Included in the operation code A i 2 Related q i A diagnosis code, that is, including the surgery and operation corresponding to the operation code A i 2 The possible diagnosis results correspond to the diagnosis code. Operation code A i 2 The corresponding operation number may refer to the operation code A extracted from the surgery and operation data of the target object. i 2 The number of times.

[0025] The grouping categories include complete match, partial mismatch and complete mismatch. Further, the grouping subcategories corresponding to partial mismatch include operation code mismatch and diagnosis code mismatch.

[0026] Therefore, this embodiment first matches A and B to determine the grouping category corresponding to each coded data combination, thereby obtaining the grouping category set C corresponding to A as the basis for data analysis.

[0027] In a specific implementation, S1 further includes the following steps:

[0028] S11, for A i Match with B and get A i Corresponding group category C i , S11 further includes the following steps:

[0029] S111, if A exists in B i 1 The corresponding code does not exist in A i 2 The corresponding code is determined by A i Corresponding group category C i is a partial mismatch, and A i The corresponding grouping subcategory is Operation Code Mismatch;

[0030] S112, if A does not exist in B i 1 The corresponding code exists A i 2 The corresponding code is determined by A i Corresponding group category C i is a partial mismatch, and A i The corresponding grouping subcategories were diagnosis code mismatch;

[0031] S12, traverse all the coded data combinations in A, and obtain the grouping category set C={C1, C2, ..., C i , ..., C m}.

[0032] In the above, A and B are matched to obtain the grouping category set C corresponding to A = {C1, C2, ..., C i , ..., C m}, determines the grouping category of each coded data combination, and provides a data basis for reporting information.

[0033] S2, grouping all the coded data combinations according to C to obtain a first grouping set QY, wherein QY includes all the coded data combinations with a grouping category of partial mismatch.

[0034] Among them, all the coded data combinations with the grouping category of partial mismatch are grouped into the same set to obtain a first grouping set QY.

[0035] S3, for any coded data combination QY in QY 0 , according to QY 0 Corresponding group sub-category, get QY 0 The corresponding reporting level W 0 , S3 specifically includes the following steps:

[0036] Among them, the partial mismatch between the coding data combination and the grouping code may be caused by errors made by doctors in filling in the diagnosis data, surgery and operation data, or the corresponding diagnosis data and disease data are not included in the DRG grouping rule system. Therefore, it is necessary to judge the above two reasons in order to find the correct reason to improve the accuracy of the reported information.

[0037] Specifically, this embodiment combines QY according to any coded data in QY 0 Corresponding group sub-category, get QY 0 The corresponding reporting level W 0 .

[0038] S31, if QY 0 The corresponding group subcategory is the operation code does not match, then according to QY 0 The associated diagnosis code set R corresponding to the operation code 0 , the corresponding operation times S1, P and Z1, get QY 0 The corresponding reporting level W 0 =α1×q 0 / P+α2×S1 / Z1, where α1 refers to the preset first priority, α2 refers to the preset second priority, q 0 Refers to R 0 The total number of diagnostic codes in the .

[0039] Among them, if QY 0 The corresponding group subcategory is the operation code does not match, then according to QY 0 The associated diagnosis code set R corresponding to the operation code 0 The proportion of the total number of diagnostic codes in the total number of diagnostic codes corresponding to the target object, and QY 0 The proportion of the corresponding operation times S1 in the total operation times Z1 of the target object is used to measure QY 0 The probability of occurrence in the coded data combination to determine QY 0 The classification as a partial mismatch in the match with the target grouping code set B is due to incorrect information filling or a loophole in the grouping rules.

[0040] The specific values ​​of α1 and α2 can be set by the implementer according to actual conditions.

[0041] S32, if QY 0 The corresponding grouping subcategory is a mismatch in diagnosis code, then according to QY 0 The associated operation code set D corresponding to the diagnosis code 0 , the corresponding diagnosis times S2, Q and Z2, get QY 0 The corresponding reporting level W 0=α3×p 0 / Q+α4×S2 / Z2, where α3 refers to the preset third priority, α4 refers to the preset fourth priority, and p 0 It means D 0 The total number of operation codes in .

[0042] Among them, if QY 0 The corresponding grouping subcategory is a mismatch in diagnosis code, then according to QY 0 The associated operation code set D corresponding to the diagnosis code 0 The total number of operation codes in the target object corresponds to the total number of operation codes Q, and QY 0 The proportion of the corresponding diagnosis number S2 in the total diagnosis number Z2 of the target object is used to measure QY 0 The probability of occurrence in the coded data combination to determine QY 0 The classification as a partial mismatch in the match with the target grouping code set B is due to incorrect information filling or a loophole in the grouping rules.

[0043] The specific values ​​of α3 and α4 can be set by the implementer according to actual conditions.

[0044] As mentioned above, according to any coded data combination QY in QY 0 Corresponding group sub-category, get QY 0 The corresponding reporting level W 0 , to characterize QY 0 The probability of occurrence in the coded data combination is used to determine QY 0 The reasons for being classified as partial mismatch in the match with the target group coding set B provide data support and improve the accuracy of the judgment result.

[0045] S4, according to W 0 and the preset first reporting level threshold Y1, judge QY 0 Corresponding reporting information category.

[0046] In a specific implementation, S4 further includes the following steps:

[0047] S41, if W 0 <Y1, then judge QY 0 The corresponding reporting information category is information filling error;

[0048] S42, if W 0 ≥Y1, then judge QY 0 The corresponding reporting information category is grouping rule vulnerability.

[0049] Among them, if W 0 <Y1, indicating QY0 The probability of appearing in the coded data combination is small, QY 0 The appearance of this coded data combination may be accidental, so it is judged that QY 0 The corresponding reporting information category is information filling error.

[0050] If W 0 ≥Y1, indicating QY 0 The probability of appearing in the coded data combination is relatively high, QY 0 If this combination of coded data appears more often, then QY 0 The corresponding reporting information category is grouping rule vulnerability.

[0051] According to W 0 and the preset first reporting level threshold Y1, judge QY 0 The corresponding reported information categories improve the accuracy of the reported information categories, thereby improving the accuracy of the reported information.

[0052] S5, traverse all the coded data combinations in QY and obtain the first reporting data, wherein the first reporting data includes all the coded data combinations in QY and the reporting information category corresponding to each coded data combination in QY.

[0053] Among them, all the coding data combinations in QY and the reporting information categories corresponding to each coding data combination in QY are combined into the first reporting data, which is reported as reporting information, and then provides guidance and suggestions for doctors to modify diagnosis data, surgery and operation data, and update and reform DRG grouping.

[0054] In a specific embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0055] If A exists in B i 1 The corresponding code exists A i 2 The corresponding code is determined by A i Corresponding group category C i is an exact match.

[0056] In a specific implementation, the memory also stores the resource consumption level and historical reimbursement ratio corresponding to each operation. When the computer program is executed by the processor, the following steps are also implemented:

[0057] S6, grouping all the coded data combinations according to C to obtain a second grouping set G, wherein G includes all the coded data combinations whose grouping category is complete match;

[0058] S7, for any coded data combination G in G0 , according to G 0 Corresponding resource consumption level F 0 and historical reimbursement ratio H 0 , get G 0 The corresponding recommended priority X 0 =exp(F 0 ×H 0 ), where exp() refers to the natural exponential function;

[0059] S8, traverse all the coding data combinations in G, and obtain the recommendation priority corresponding to each coding data combination in G;

[0060] S9, sort all the coded data combinations in G according to the recommended priority, and obtain the third grouping set G 1 ;

[0061] S10, for G 1 The first reported data is combined with the first reported data to obtain the second reported data.

[0062] Among them, all the coded data combinations with the grouping category of complete match are grouped into the same set to obtain a second grouping set G.

[0063] The resource consumption level can represent the level of resources consumed by the corresponding coding data combination. The higher the resource consumption level, the more resources the corresponding coding data combination consumes, and the degree of consideration for the coding data combination is higher when reimbursement and fee settlement are performed.

[0064] The specific value and form of the resource consumption level may be set by the implementer according to actual conditions. For example, the resource consumption level may be an integer such as one, two, three, etc.

[0065] In this embodiment, according to any coded data combination G in G 0 Corresponding resource consumption level F 0 and historical reimbursement ratio H 0 , get G 0 The corresponding recommended priority X 0 =exp(F 0 ×H 0 ), used to represent the coded data combination G 0 The priority for making recommendations.

[0066] Specifically, the second reported data includes a third group set G 1 and first reported data.

[0067] In a specific embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0068] If A does not exist in B i 1 The corresponding code does not exist in A i 2 The corresponding code is determined by A i Corresponding group category C i Is completely mismatched.

[0069] In a specific embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0070] S100, grouping all the coded data combinations according to C to obtain a fourth grouping set E, wherein E includes all the coded data combinations whose grouping category is completely mismatched;

[0071] S200, for any coded data combination E in E 0 , according to E 0 The associated diagnosis code set R corresponding to the operation code 1 、E 0 The number of operations corresponding to the operation code S3, P, Z1, E 0 The associated operation code set D corresponding to the diagnosis code 1 、E 0 The number of diagnoses corresponding to the diagnosis codes S4, Q and Z2 in E 0 The corresponding reporting level W 1 =β1×(α1×q 1 / P+α2×S3 / Z1)+β2×(α3×p 1 / Q+α4×S2 / Z2), where β1 refers to the preset fifth priority, β2 refers to the preset sixth priority, and q 1 Refers to R 1 The total number of diagnostic codes in 1 It means D 1 The total number of operation codes in ;

[0072] S300, according to W 1 and the preset second reporting level threshold Y2, judging E 0 The corresponding reporting information category;

[0073] S400, traversing all the coded data combinations in E, and respectively obtaining the reporting information category corresponding to each coded data combination in E;

[0074] S500, obtain the third reporting data according to the reporting information categories corresponding to all the coded data combinations in E and the first reporting data, wherein the third reporting data includes the first reporting data, and all the coded data combinations in E and the reporting information categories corresponding to each coded data combination in E.

[0075] Among them, all the coded data combinations with the grouping category of completely mismatching are grouped into the same set to obtain a fourth grouping set E. Similarly, it is necessary to find out the correct reason why each coded data combination in E is classified as completely mismatching to improve the accuracy of the reported information.

[0076] Specifically, according to any coded data combination E in E 0 The associated diagnosis code set R corresponding to the operation code 1 The proportion of the total number of diagnostic codes in the target object corresponding to the total number of diagnostic codes P, E 0 The proportion of the number of operations S3 corresponding to the operation code in the total number of operations Z1 corresponding to the target object, E 0 The associated operation code set D corresponding to the diagnosis code 1 The proportion of the total number of operation codes in the total number of operation codes corresponding to the target object, Q, and E 0 The proportion of the number of diagnoses S4 corresponding to the diagnostic code in the total number of diagnoses Z2 corresponding to the target object is used to measure E 0 The probability of occurrence in the coded data combination is used to determine E 0 The classification as a complete mismatch in the match with the target grouping code set B is due to incorrect information filling or a loophole in the grouping rules.

[0077] As mentioned above, according to any coded data combination E in E 0 Corresponding diagnostic data and operation data are obtained from E 0 The corresponding reporting level W 1 , to characterize E 0 The probability of occurrence in the coded data combination is used to determine E 0 The reasons for being classified as completely mismatched in the match with the target group coding set B provide data support and improve the accuracy of the judgment result.

[0078] In a specific implementation, S300 further includes the following steps:

[0079] S301, if W 1 <Y2, then judge E 0 The corresponding reporting information category is information filling error;

[0080] S302, if W 1 ≥Y2, then judge E 0 The corresponding reporting information category is grouping rule vulnerability.

[0081] In one specific embodiment, Y2>Y1.

[0082] Among them, QY 0The corresponding grouping category is partial mismatch, and E 0 The corresponding grouping category is completely mismatched, then E 0 The reason why it is classified as completely mismatched in the match with the target group code set B is the possibility of incorrect information filling. 0 The reason why the matching with the target group coding set B is classified as a complete mismatch is that the possibility of incorrect information filling is smaller.

[0083] Therefore, in this embodiment, Y2>Y1 is set, and W 0 When ≥Y1, QY can be judged 0 The corresponding reporting information category is grouping rule vulnerability, but only in W 1 ≥Y2, then judge E 0 The corresponding reporting information category is grouping rule loopholes, thereby improving the accuracy of the judgment results and further improving the accuracy of the reported information.

[0084] In a specific implementation, according to the reporting information category corresponding to all the coded data combinations in E and the second reporting data, the fourth reporting data is obtained, wherein the fourth reporting data includes all the coded data combinations in QY, the reporting information category corresponding to each coded data combination in QY, the third grouping set G 1 As well as all the coded data combinations in E and the reporting information categories corresponding to each coded data combination in E.

[0085] In the above, A and B are matched to obtain the grouping category set C corresponding to A, and all the coded data combinations are grouped according to C to obtain the first grouping set QY. For any coded data combination QY in QY 0 , according to QY 0 Corresponding group sub-category, get QY 0 The corresponding reporting level W 0 , according to W 0 and the preset first reporting level threshold Y1, judge QY 0 The corresponding reporting information category is traversed through all the coded data combinations in QY to obtain the first reporting data. It can be seen that by grouping the coded data combinations and measuring the reporting degree of each coded data combination in the first grouping set, the reporting information category is obtained to obtain the first reporting data, which improves the accuracy of the first reporting data, thereby optimizing the guidance effect on doctors modifying diagnostic data and surgical and operation data, medical insurance bureaus and hospitals settling expenses, and updating and reforming DRG grouping.

[0086] Although some specific embodiments of the present invention have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It should also be understood by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. A data processing system based on block coding, characterized in that: The data processing system based on group coding comprises a processor and a memory storing a computer program, wherein the memory also stores a coding data combination set A={A1, A2, . . . , A i , ..., A m }、Target group coding set B = {B1, B2, ..., B j , ..., B n }, the total number of diagnosis codes P, the total number of operation codes Q, the total number of operations Z1, the total number of diagnoses Z2, the resource consumption level and historical reimbursement ratio corresponding to each operation, the i-th coding data combination A i ={A i 1 , A i 2 }, A i 1 refers to the diagnostic code in the ith coding data combination, A i 2 refers to the operation code in the i-th coded data combination, B j refers to the jth target group code, and the memory also stores A i 1 The corresponding association operation encoding set D i , A i 1 The corresponding number of diagnoses, A i 2 The corresponding associated diagnosis code set R i and A i 2 The corresponding number of operations, D i Included with A i 1 The associated p i Operation code, R i Included with A i 2 Associated q i diagnostic codes, wherein i=1, 2, ..., m, m refers to the total number of coded data combinations, j=1, 2, ..., n, n refers to the total number of target group codes, and when the computer program is executed by a processor, the following steps are implemented: S1, match A and B, and obtain the grouping category set C corresponding to A = {C1, C2, ..., C i , ..., C m }, where C i A i corresponding grouping categories, the grouping categories including complete match, partial mismatch and complete mismatch, the grouping subcategories corresponding to the partial mismatch including operation code mismatch and diagnosis code mismatch; S2, grouping all the coded data combinations according to C to obtain a first grouping set QY, wherein QY includes all the coded data combinations whose grouping category is partially mismatched; S3, for any coded data combination QY in QY 0 , according to QY 0 Corresponding group sub-category, get QY 0 The corresponding reporting level W 0 , S3 specifically includes the following steps: S31, if QY 0 The corresponding group subcategory is the operation code does not match, then according to QY 0 The associated diagnosis code set R corresponding to the operation code 0 , the corresponding operation times S1, P and Z1, get QY 0 The corresponding reporting level W 0 =α1×q 0 / P+α2×S1 / Z1, where α1 refers to the preset first priority, α2 refers to the preset second priority, q 0 Refers to R 0 The total number of diagnostic codes in S32, if QY 0 The corresponding grouping subcategory is a mismatch in diagnosis code, then according to QY 0 The associated operation code set D corresponding to the diagnosis code 0 , the corresponding diagnosis times S2, Q and Z2, get QY 0 The corresponding reporting level W 0 =α3×p 0 / Q+α4×S2 / Z2, where α3 refers to the preset third priority, α4 refers to the preset fourth priority, and p 0 It means D 0 The total number of operation codes in ; S4, according to W 0 and the preset first reporting level threshold Y1, judge QY 0 The corresponding reporting information category; S5, traversing all the coded data combinations in QY to obtain first reporting data, wherein the first reporting data includes all the coded data combinations in QY and the reporting information category corresponding to each coded data combination in QY; When the computer program is executed by a processor, the following steps are also implemented: If A exists in B i 1 The corresponding code exists A i 2 The corresponding code is determined by A i Corresponding group category C i is an exact match; S6, grouping all the coded data combinations according to C to obtain a second grouping set G, wherein G includes all the coded data combinations whose grouping category is complete match; S7, for any coded data combination G in G 0 , according to G 0 Corresponding resource consumption level F 0 and historical reimbursement ratio H 0 , get G 0 The corresponding recommended priority X 0 =exp(F 0 ×H 0 ), where exp() refers to the natural exponential function; S8, traverse all the coding data combinations in G, and obtain the recommendation priority corresponding to each coding data combination in G; S9, sort all the coded data combinations in G according to the recommended priority, and obtain the third grouping set G 1 ; S10, for G 1 and the first reported data to obtain second reported data; If A does not exist in B i 1 The corresponding code does not exist in A i 2 The corresponding code is determined by A i Corresponding group category C i is completely mismatched; S100, grouping all the coded data combinations according to C to obtain a fourth grouping set E, wherein E includes all the coded data combinations whose grouping category is completely mismatched; S200, for any coded data combination E in E 0 , according to E 0 The associated diagnosis code set R corresponding to the operation code 1 、E 0 The number of operations corresponding to the operation code S3, P, Z1, E 0 The associated operation code set D corresponding to the diagnosis code 1 、E 0 The number of diagnoses corresponding to the diagnosis codes in E4, Q and Z2 is obtained. 0 The corresponding reporting level W 1 =β1×(α1×q 1 / P+α2×S3 / Z1)+β2×(α3×p 1 / Q+α4×S2 / Z2), where β1 refers to the preset fifth priority, β2 refers to the preset sixth priority, and q 1 Refers to R 1 The total number of diagnostic codes in 1 It means D 1 The total number of operation codes in ; S300, according to W 1 and the preset second reporting level threshold Y2, judging E 0 The corresponding reporting information category; S400, traversing all the coded data combinations in E, and respectively obtaining the reporting information category corresponding to each coded data combination in E; S500, obtain third reporting data according to the reporting information categories corresponding to all the coded data combinations in E and the first reporting data, wherein the third reporting data includes the first reporting data, all the coded data combinations in E and the reporting information categories corresponding to each coded data combination in E.

2. The data processing system based on group coding according to claim 1, characterized in that: S1 also includes the following steps: S11, for A i Match with B and get A i Corresponding group category C i , S11 further includes the following steps: S111, if A exists in B i 1 The corresponding code does not exist in A i 2 The corresponding code is determined by A i Corresponding group category C i is a partial mismatch, and A i The corresponding grouping subcategory is Operation Code Mismatch; S112, if A does not exist in B i 1 The corresponding code exists A i 2 The corresponding code is determined by A i Corresponding group category C i is a partial mismatch, and A i The corresponding grouping subcategories were diagnosis code mismatch; S12, traverse all the coded data combinations in A, and obtain the grouping category set C={C1, C2, ..., C i , ..., C m }.

3. The data processing system based on block coding according to claim 1, characterized in that: S4 also includes the following steps: S41, if W 0 <Y1, then judge QY 0 The corresponding reporting information category is information filling error; S42, if W 0 ≥Y1, then judge QY 0 The corresponding reporting information category is grouping rule vulnerability.

4. The data processing system based on group coding according to claim 1, characterized in that: S300 also includes the following steps: S301, if W 1 <Y2, then judge E 0 The corresponding reporting information category is information filling error; S302, if W 1 ≥Y2, then judge E 0 The corresponding reporting information category is grouping rule vulnerability.

5. The data processing system based on block coding according to claim 1, characterized in that: Y2>Y1.

Images