Medical data processing method, device, equipment and computer-readable storage medium

Abstract

In the field of medical data processing technology, the present application provides a medical data processing method, apparatus, device and computer-readable storage medium, the method comprising: obtaining billing data of each medical data type; determining the correlation scores between each medical data type based on the billing data of each medical data type; clustering each medical data type based on the correlation scores between each medical data type to obtain multiple medical data type groups; determining whether the multiple medical data type groups meet the preset conditions; when it is determined that the multiple medical data type groups meet the preset conditions, sending the multiple medical data type groups to the terminal device of the insured person, so that the insured person can reimburse the billing data according to the multiple medical data type groups. This solution improves the efficiency and accuracy of the insured person in reimbursement of billing data. The present application also relates to the fields of blockchain technology and artificial intelligence technology, and the billing data can be stored in the blockchain.

Description

Technical Field

[0001] The present application relates to the field of medical data processing technology, and in particular to a medical data processing method, apparatus, device and computer-readable storage medium. Background Art

[0002] Medical insurance generally refers to basic medical insurance, a social insurance system established to compensate workers for economic losses caused by illness. When insured individuals incur medical expenses, they receive financial compensation from the medical insurance provider. Currently, the types of illnesses are numerous and complex. If insured individuals wish to claim reimbursement for multiple disease policies, they must file for each policy individually, resulting in relatively low reimbursement efficiency. Therefore, how to effectively process medical data to improve the efficiency and accuracy of medical reimbursement for insured individuals is a pressing issue. Summary of the Invention

[0003] The main purpose of this application is to provide a medical data processing method, device, equipment and computer-readable storage medium, aiming to improve the efficiency and accuracy of medical data processing.

[0004] In a first aspect, the present application provides a medical data processing method, the medical data processing method comprising the following steps:

[0005] Obtain billing data for each medical data type;

[0006] Determining, based on the bill data of each of the medical data types, a correlation score between the medical data types;

[0007] Clustering the medical data types according to the correlation scores between the medical data types to obtain multiple medical data type groups;

[0008] determining whether a plurality of medical data type groups meet a preset condition;

[0009] When it is determined that the plurality of medical data type groups meet the preset conditions, the plurality of medical data type groups are sent to the terminal device of the insured person, so that the insured person can claim reimbursement of bill data according to the plurality of medical data type groups.

[0010] In a second aspect, the present application further provides a medical data processing device, the medical data processing device comprising an acquisition module, a determination module, a generation module, and a sending module, wherein:

[0011] The acquisition module is used to obtain bill data of various medical data types;

[0012] The determining module is configured to determine a correlation score between each of the medical data types based on the bill data of each of the medical data types;

[0013] The generating module is configured to cluster the medical data types according to the correlation scores between the medical data types to obtain a plurality of medical data type groups;

[0014] The determination module is further configured to determine whether the plurality of medical data type groups meet preset conditions;

[0015] The sending module is used to send the multiple medical data type groups to the terminal device of the insured person when it is determined that the multiple medical data type groups meet the preset conditions, so that the insured person can reimburse the bill data according to the multiple medical data type groups.

[0016] In a third aspect, the present application also provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the medical data processing method as described above are implemented.

[0017] In a fourth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the medical data processing method as described above are implemented.

[0018] The present application provides a medical data processing method, apparatus, device, and computer-readable storage medium. The present application obtains billing data of various medical data types; determines the correlation scores between the various medical data types based on the billing data of the various medical data types; clusters the various medical data types based on the correlation scores between the various medical data types to obtain multiple medical data type groups; determines whether the multiple medical data type groups meet preset conditions; and when it is determined that the multiple medical data type groups meet the preset conditions, sends the multiple medical data type groups to the terminal device of the insured person, so that the insured person can claim reimbursement for the billing data based on the multiple medical data type groups. By clustering medical data types with high correlation scores into groups, the efficiency and accuracy of medical data processing are improved, thereby improving the efficiency and accuracy of the insured person's billing data reimbursement. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0020] Figure 1 A flowchart of a medical data processing method provided in an embodiment of the present application;

[0021] Figure 2 for Figure 1 A schematic flow chart of sub-steps of a medical data processing method in FIG.

[0022] Figure 3 A schematic block diagram of a medical data processing device provided in an embodiment of the present application;

[0023] Figure 4 for Figure 3 A schematic block diagram of submodules of a medical data processing device;

[0024] Figure 5 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present application.

[0025] The realization of the objectives, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0027] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0028] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0029] Fundamental AI technologies generally include sensors, specialized AI chips, cloud computing, distributed storage, healthcare insurance reimbursement technology, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0030] The embodiments of the present application provide a medical data processing method, apparatus, device, and computer-readable storage medium. The medical data processing method can be applied to a terminal device, which can be an electronic device such as a mobile phone, tablet computer, laptop computer, desktop computer, personal digital assistant, and wearable device. For example, the terminal device is a laptop computer, which obtains billing data of each medical data type; determines the correlation score between each medical data type based on the billing data of each medical data type; clusters each medical data type based on the correlation score between each medical data type to obtain multiple medical data type groups; determines whether the multiple medical data type groups meet the preset conditions; and when it is determined that the multiple medical data type groups meet the preset conditions, sends the multiple medical data type groups to the terminal device of the insured person, so that the insured person can reimburse the billing data based on the multiple medical data type groups.

[0031] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0032] Please refer to Figure 1 , Figure 1 A flowchart of a medical data processing method provided in an embodiment of the present application.

[0033] like Figure 1 As shown, the medical data processing method includes steps S101 to S105.

[0034] Step S101: Obtain bill data of various medical data types.

[0035] The medical data type refers to the types of various diseases. The types of diseases can be determined according to actual conditions and are not specifically limited in this embodiment. For example, the diseases can be rheumatism, heart disease, hypertension, gastroenteritis, etc. The bill data refers to the bill data of the patient's medical expenses for disease treatment.

[0036] In one embodiment, billing data for insured persons after medical treatment is obtained to obtain billing data for various medical types. For example, the billing data for insured person A after medical treatment includes billing data for heart disease of 3,000 yuan and billing data for hypertension of 1,500 yuan. The billing data for insured person B after medical treatment includes billing data for gastroenteritis of 150 yuan and billing data for fever of 80 yuan.

[0037] Step S102: Determine the correlation scores between the various medical data types based on the bill data of the various medical data types.

[0038] The correlation score refers to the similarity of the medical data types. If the correlation score between two medical data types is larger, it indicates that the two medical data types are more similar.

[0039] In one embodiment, billing data for each medical data type is subjected to normal distribution processing to obtain a normal distribution function for the billing data of each medical data type. The function parameters of the normal distribution function for the billing data of each medical data type are estimated using the maximum likelihood method to obtain a billing data function for each medical data type. Correlation is then calculated for the billing data functions for each medical data type to obtain correlation scores between the medical data types. By subjecting the billing data to normal distribution processing, the accuracy of the correlation score calculation can be improved.

[0040] In one embodiment, a correlation calculation is performed on the billing data functions of each medical data type to obtain a correlation score between the medical data types. This may be performed by sequentially performing relative entropy calculations on the billing data functions of two medical data types to obtain the relative entropies of the billing data functions of the two medical data types, sequentially performing JS divergence calculations on the relative entropies of the billing data functions of the two medical data types to obtain a dispersion score between the billing data functions of the medical data types, and determining the correlation score between the medical data types based on the dispersion score between the billing data functions of the medical data types. By determining the relative entropies of the billing data functions and using the relative entropies, the correlation scores between the medical data types can be accurately obtained.

[0041] In one embodiment, the relative entropy of the billing data functions of the two medical data types is calculated in sequence. The relative entropy of the billing data functions of the two medical data types can be obtained by obtaining a preset relative entropy formula, wherein the preset relative entropy formula is P(x) is the first billing data function, and Q(x) is the second billing data function. Based on the preset relative entropy formula, the two billing data functions are sequentially substituted into the preset relative entropy formula to obtain the relative entropy of the two billing data functions. By substituting the two billing data functions into the preset relative entropy formula, the relative entropy of the two billing data functions can be accurately obtained.

[0042] In one embodiment, the relative entropy of the billing data functions of two medical data types is sequentially calculated by JS divergence, and the dispersion score between the billing data functions of each medical data type is obtained by obtaining a preset JS divergence formula, which is: Among them, KLp||p+q2 and KLq||p+q2 are relative entropies calculated based on the first bill data function and the second bill data function. The relative entropy can be determined according to the above relative entropy calculation process, which will not be described in detail. Based on the preset JS divergence formula, and the relative entropy of the first bill data function and the second bill data function is substituted into the preset JS divergence formula, the discreteness score between the bill data functions is obtained. By calculating the relative entropy of the bill data function in turn through the preset JS divergence formula, the discreteness score between each bill data function can be accurately obtained.

[0043] In one embodiment, the correlation scores between the various medical data types can be determined based on the discreteness scores between the billing data functions of each medical data type by obtaining a mapping table between discreteness scores and correlation scores, querying the mapping table for the correlation scores corresponding to the discreteness scores between the billing data functions of each medical data type, and obtaining the correlation scores between the various medical data types. The mapping table is pre-established based on the discreteness scores and correlation scores between the billing data functions of each medical data type. The establishment of the mapping table can be based on actual circumstances and is not specifically limited in this embodiment. Based on the mapping table, the correlation scores between the various medical data types can be accurately queried.

[0044] Step S103: clustering the medical data types according to the correlation scores between the medical data types to obtain a plurality of medical data type groups.

[0045] Among them, the medical data type group is obtained by clustering multiple medical data types with high similarity. The number of medical data types in the medical data type group can be determined according to actual conditions. This embodiment does not make specific limitations on this. For example, the medical data type includes medical data type 1, medical data type 2, medical data type 3, medical data type 4 and medical data type 5. Clustering is performed according to the correlation scores between each medical data type to obtain medical data type group 1 and medical data type group 2, wherein medical data type group 1 includes medical data type 1 and medical data type 4, and medical data type group 1 includes medical data type 2, medical data type 3 and medical data type 5.

[0046] In one embodiment, if Figure 2 As shown, step S103 includes sub-steps S1031 to S1033.

[0047] Sub-step S1031 : obtaining a preset number of medical data type groups, and selecting a preset number of target medical data types from the plurality of medical data types.

[0048] Among them, the preset number of medical data type groups can be set according to actual conditions, and this embodiment does not make specific restrictions on this. For example, when there are 50 medical data types, the preset number of medical data type groups can be set to 5.

[0049] In one embodiment, a preset number of medical data type groups is obtained, and a preset number of medical data types are selected from multiple medical data types based on the preset number of medical data type groups as target medical data types. It should be noted that the method for selecting the preset number of medical data types from the multiple medical data types can be selected based on actual circumstances and is not specifically limited in this embodiment. For example, a preset number of medical data types may be randomly selected from the multiple medical data types, or one medical data type may be selected from every other medical data type as the medical data type until the preset number of medical data types is obtained.

[0050] Exemplarily, the medical data types include medical data type 1, medical data type 2, medical data type 3, medical data type 4, medical data type 5, medical data type 6, medical data type 7, medical data type 8, medical data type 9 and medical data type 10. Three medical data types are randomly selected from medical data type 1, medical data type 2, medical data type 3, medical data type 4, medical data type 5, medical data type 6, medical data type 7, medical data type 8, medical data type 9 and medical data type 10 as target medical data types, and the target medical data types include medical data type 2, medical data type 5 and 10.

[0051] Exemplarily, the medical data types include medical data type 1, medical data type 2, medical data type 3, medical data type 4, medical data type 5, medical data type 6, medical data type 7, medical data type 8, medical data type 9 and medical data type 10. One medical data type is selected as the target medical data type every two medical data types from medical data type 1, medical data type 2, medical data type 3, medical data type 4, medical data type 5, medical data type 6, medical data type 7, medical data type 8, medical data type 9 and medical data type 10, and the target medical data types include medical data type 1, medical data type 4 and medical data type 7.

[0052] Sub-step S1032: taking each target medical data type as the first member of each medical data type group, wherein one medical data type group corresponds to one target medical data type.

[0053] After determining the target medical data type, the target medical data type is assigned as the first member of a medical data type group, thereby obtaining the target medical data type corresponding to each medical data type group. The allocation rules for assigning target medical data types to medical data type groups can be selected based on practical circumstances and are not specifically limited in this embodiment. For example, the target medical data types can be randomly assigned to medical data type groups.

[0054] Exemplarily, the target medical data type includes medical data type 1, target medical data type 2, and target medical data type 3, the medical data type group includes medical data type group 1 and medical data type group 2, the target medical data type 1 is used as the first member of medical data type group 1, the target medical data type 2 is used as the first member of medical data type group 3, and the target medical data type 2 is used as the first member of medical data type 3.

[0055] Sub-step S1033: clustering each medical data type according to the correlation score between the first member of each medical data type group and each medical data type to obtain a plurality of medical data type groups.

[0056] Based on the correlation scores between each medical data type and the first member of each medical data type group, each medical data type is clustered into the medical data type group corresponding to the first member with the highest correlation score, thereby obtaining multiple medical data type groups. By clustering each medical data type into the medical data type group corresponding to the first member with the highest correlation score, the medical data type group with the most similar medical data types can be accurately found.

[0057] Exemplarily, the medical data type group includes medical data type group 1 and medical data type group 2, wherein the medical data types include medical data type 1, medical data type 2, medical data type 3, medical data type 4 and medical data type 5, medical data type 1 is the first member of medical data type group 1, medical data type 2 is the first member of medical data type group 2, the correlation score between medical data type 1 and medical data type 3 is 0.3, the correlation score between medical data type 1 and medical data type 4 is 0.5, the correlation score between medical data type 1 and medical data type 5 is 0.1, the correlation score between medical data type 2 and medical data type 3 is 0.6, the correlation score between medical data type 2 and medical data type 4 is 0.1, and the correlation score between medical data type 2 and medical data type 5 is 0.7. Therefore, the correlation score between medical data type 3 and medical data type 1 is less than the correlation score between medical data type 2 and medical data type 2, and medical data type 3 is clustered into medical data type group 2. The correlation score between medical data type 4 and medical data type 1 is greater than the correlation score between medical data type 4 and medical data type 2, and medical data type 4 is clustered into medical data type group 1. The correlation score between medical data type 5 and medical data type 1 is less than the correlation score between medical data type 5 and medical data type 2, and medical data type 5 is clustered into medical data type group 2. That is, medical data type group 1 includes medical data type 1 and medical data type 4, and the medical data type group includes medical data type 2, medical data type 4, and medical data type 5.

[0058] In one embodiment, each medical data type is considered a medical data type group. Clustering is performed on each medical data type group based on correlation scores between the medical data types. Clustering is terminated when a preset number of medical data type groups has been reached, resulting in multiple medical data type groups. Clustering each medical data type as a medical data type group eliminates the need to determine the first member of a medical data type group, improving the efficiency of medical data type clustering.

[0059] Exemplarily, the medical data types include medical data type 1, medical data type 2, medical data type 3, medical data type 4 and medical data type 5, with medical data type 1 being the first member of medical data type group 1, medical data type 2 being the first member of medical data type group 2, medical data type 3 being the first member of medical data type group 3, medical data type 4 being the first member of medical data type group 4 and medical data type 5 being the first member of medical data type group 5, the correlation scores of medical data type 1 with medical data type 2, medical data type 3, medical data type 4 and medical data type 5 being 0.2, 0.4, 0.5 and 0.8 respectively, the correlation scores of medical data type 2 with medical data type 3, medical data type 4 and medical data type 5 being 0.1, 0.4 and 0.7 respectively, the correlation scores of medical data type 3 with medical data type 4 and medical data type 5 being 0.2 and 0.6 respectively, the correlation scores of medical data type 4 with medical data type 5 being The correlation score is 0.2, and the preset number of medical data type groups is 3. The medical data type 1 of medical data type group 1 and the medical data type 5 of medical data type group 5 are clustered into one medical data type group to obtain the updated medical data type group 1. The medical data type 2 of medical data type group 2 and the medical data type 4 of medical data type group 4 are clustered into one medical data type group to obtain the updated medical data type group 2. Based on the above correlation score calculation method, the correlation score of medical data type 3 with the medical data type 1 and medical data type 5 of the updated medical data type group 1 is 0.5, and the dispersion score of medical data type 3 with the medical data type 2 and medical data type 4 of the updated medical data type group 2 is 0.3. Then medical data type 3 is clustered into medical data type group 1, and medical data type group 1 includes medical data type 1, medical data type 3, and medical data type 3, and medical data type group 2 includes medical data type 2 and medical data type 4.

[0060] Step S104: Determine whether the plurality of medical data type groups meet preset conditions.

[0061] In one embodiment, silhouette coefficients are determined for multiple medical data type groups; based on the silhouette coefficients, whether the multiple medical data type groups meet preset conditions is determined. Using the silhouette coefficients of the medical data type groups, whether the clustered groupings of the medical data types meet the conditions is determined, greatly improving the accuracy of the medical data type groupings.

[0062] In one embodiment, the method for determining the silhouette coefficients of multiple medical data type groups may be: obtaining a silhouette coefficient formula, which is: Among them, S is the silhouette coefficient, N is the number of medical data types, bi The mean of the correlation scores between the medical data type and other medical data types in the medical data type group is determined, and the mean of the correlation scores between the medical data type and other medical data types in the medical data type groups other than the medical data type group is obtained. The minimum mean is taken as a i , based on the silhouette coefficient formula, and the a of each medical data type i and b i By substituting this silhouette coefficient formula, the silhouette coefficients of multiple medical data type groups can be accurately obtained.

[0063] In one embodiment, based on the silhouette coefficients of multiple medical data type groups, determining whether the multiple medical data type groups meet preset conditions can be performed by: determining whether the silhouette coefficients are greater than or equal to a preset threshold; if the silhouette coefficients are greater than or equal to the preset threshold, determining that the multiple medical data type groups meet the preset conditions; and if the silhouette coefficients are less than the preset threshold, determining that the multiple medical data type groups do not meet the preset conditions. The preset threshold can be set based on actual conditions, and this embodiment can be set based on actual conditions. Based on whether the silhouette coefficients are greater than or equal to the preset threshold, it is possible to accurately determine whether the clustering of multiple medical data type groups meets the conditions, greatly improving the accuracy of medical data type clustering.

[0064] In one embodiment, if multiple medical data type groups do not meet a preset condition, a preset first number of medical data type groups is re-determined; each medical data type is clustered based on the correlation scores between the medical data types to obtain the preset first number of medical data type groups. When the clustering of medical data types does not meet the condition, the number of medical data type groups is re-determined and the medical data types are re-clustered, thereby improving the accuracy of medical data type merging.

[0065] Step S105: When it is determined that the plurality of medical data type groups meet the preset conditions, the plurality of medical data type groups are sent to the terminal device of the insured person, so that the insured person can claim reimbursement of bill data according to the plurality of medical data type groups.

[0066] When multiple medical data type groups are determined to meet pre-set conditions, the multiple medical data type groups are sent to the insured person's terminal device. The insured person then merges the multiple medical data types based on the multiple medical data type groups and submits the merged bill data for unified reimbursement. The terminal device can be selected based on actual circumstances, and this embodiment does not impose specific limitations on this. For example, the terminal device can be a mobile phone. By clustering multiple medical data types, insured persons can submit bill data reimbursement based on the medical data type groups, significantly improving the accuracy and efficiency of bill data reimbursement.

[0067] Exemplarily, the medical data type includes medical data type 1, medical data type 2, medical data type 3, medical data type 4, and medical data type 5, medical data type group 1 includes medical data type 1, medical data type 2, and medical data type 4, and medical data type group 2 includes medical data type 3 and medical data type 5. The billing data of medical data type 1, medical data type 2, and medical data type 4 are merged, and the billing data of medical data type 3 and medical data type 5 are merged, and the merged billing data are reimbursed separately.

[0068] The medical data processing method provided in the above embodiment obtains billing data for each medical data type; determines correlation scores between the medical data types based on the billing data for each medical data type; clusters the medical data types based on the correlation scores to obtain multiple medical data type groups; determines whether the multiple medical data type groups meet preset conditions; and, if it is determined that the multiple medical data type groups meet the preset conditions, sends the multiple medical data type groups to the insured person's terminal device, allowing the insured person to claim reimbursement for the billing data based on the multiple medical data type groups. By clustering medical data types with high correlation scores into groups, the efficiency and accuracy of medical data processing are improved, thereby improving the efficiency and accuracy of billing data reimbursement for the insured person.

[0069] See 3, Figure 3 A schematic block diagram of a medical data processing device provided in an embodiment of the present application.

[0070] like Figure 3 As shown, the medical data processing device 200 includes an acquisition module 210, a determination module 220, a generation module 230 and a sending module 240, wherein:

[0071] The acquisition module 210 is used to obtain bill data of various medical data types;

[0072] The determining module 220 is configured to determine a correlation score between each of the medical data types based on the bill data of each of the medical data types;

[0073] The generating module 230 is configured to cluster the medical data types according to the correlation scores between the medical data types to obtain a plurality of medical data type groups;

[0074] The determination module 220 is further configured to determine whether the plurality of medical data type groups meet a preset condition;

[0075] The sending module 240 is used to send the multiple medical data type groups to the terminal device of the insured person when it is determined that the multiple medical data type groups meet the preset conditions, so that the insured person can reimburse the bill data according to the multiple medical data type groups.

[0076] In one embodiment, if Figure 4 As shown, the generation module 230 includes an acquisition submodule 231, a determination submodule 232 and a generation submodule 233, wherein:

[0077] The acquisition submodule 231 is configured to acquire a preset number of medical data type groups and select a preset number of target medical data types from the plurality of medical data types;

[0078] The determining submodule 232 is configured to use each target medical data type as a first member of each medical data type group, wherein one medical data type group corresponds to one target medical data type;

[0079] The generating submodule 233 is configured to cluster each medical data type according to the correlation score between the first member of each medical data type group and each medical data type to obtain a plurality of medical data type groups.

[0080] In one embodiment, the generating submodule 233 is further configured to:

[0081] According to the correlation scores between each medical data type and the first member of each medical data type group, each medical data type is clustered into the medical data type group corresponding to the first member with the largest correlation score, to obtain multiple medical data type groups.

[0082] In one embodiment, the generating module 230 is further configured to:

[0083] Each medical data type is regarded as a medical data type group, and each medical data type group is clustered according to the correlation scores between each medical data type. The medical data type group clustering is stopped when the number of medical data type groups reaches a preset number, and multiple medical data type groups are obtained.

[0084] In one embodiment, the generating module 230 is further configured to:

[0085] determining silhouette coefficients for a plurality of said groups of medical data types;

[0086] It is determined whether the plurality of medical data type groups meet preset conditions according to the silhouette coefficients of the plurality of medical data type groups.

[0087] In one embodiment, the generating module 230 is further configured to:

[0088] Determining whether the silhouette coefficient is greater than or equal to a preset threshold;

[0089] If the silhouette coefficient is greater than or equal to a preset threshold, it is determined that the plurality of medical data type groups meet the preset conditions;

[0090] If the silhouette coefficient is less than a preset threshold, it is determined that the plurality of medical data type groups do not meet the preset conditions.

[0091] In one embodiment, the generating module 230 is further configured to:

[0092] If the plurality of medical data type groups do not meet the preset condition, reacquiring a preset first number of medical data type groups;

[0093] The medical data types are clustered based on the correlation scores between the medical data types to obtain a preset first number of medical data type groups.

[0094] It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the above-mentioned medical data processing device can refer to the corresponding process in the aforementioned medical data processing method embodiment, and will not be repeated here.

[0095] See also Figure 5 , Figure 5 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present application.

[0096] like Figure 5 As shown, the terminal device includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a storage medium and an internal memory.

[0097] The storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any medical data processing method.

[0098] The processor is used to provide computing and control capabilities to support the operation of the entire terminal device.

[0099] The internal memory provides an environment for the operation of the computer program in the storage medium. When the computer program is executed by the processor, the processor can execute any medical data processing method.

[0100] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the terminal device to which the solution of the present application is applied. The specific terminal device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0101] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0102] In one embodiment, the processor is configured to execute a computer program stored in the memory to implement the following steps:

[0103] Obtain billing data for each medical data type;

[0104] Determining, based on the bill data of each of the medical data types, a correlation score between the medical data types;

[0105] Clustering the medical data types according to the correlation scores between the medical data types to obtain multiple medical data type groups;

[0106] determining whether a plurality of medical data type groups meet a preset condition;

[0107] When it is determined that the plurality of medical data type groups meet the preset conditions, the plurality of medical data type groups are sent to the terminal device of the insured person, so that the insured person can claim reimbursement of bill data according to the plurality of medical data type groups.

[0108] In one embodiment, when clustering the medical data types according to the correlation scores between the medical data types to obtain multiple medical data type groups, the processor is configured to implement:

[0109] Obtaining a preset number of medical data type groups, and selecting a preset number of target medical data types from a plurality of the medical data types;

[0110] taking each target medical data type as the first member of each medical data type group, wherein one medical data type group corresponds to one target medical data type;

[0111] The medical data types are clustered according to the correlation scores between the first members of the medical data type groups and the medical data types to obtain a plurality of medical data type groups.

[0112] In one embodiment, when the processor implements clustering each medical data type according to the correlation score between the first member of each medical data type group and each medical data type to obtain a plurality of medical data type groups, it is configured to implement:

[0113] According to the correlation scores between each medical data type and the first member of each medical data type group, each medical data type is clustered into the medical data type group corresponding to the first member with the largest correlation score, to obtain multiple medical data type groups.

[0114] In one embodiment, when clustering the medical data types according to the correlation scores between the medical data types to obtain multiple medical data type groups, the processor is configured to implement:

[0115] Each medical data type is regarded as a medical data type group, and each medical data type group is clustered according to the correlation scores between each medical data type. The medical data type group clustering is stopped when the number of medical data type groups reaches a preset number, and multiple medical data type groups are obtained.

[0116] In one embodiment, the processor, when determining whether the plurality of medical data type groups meet a preset condition, is configured to:

[0117] determining silhouette coefficients for a plurality of said groups of medical data types;

[0118] It is determined whether the plurality of medical data type groups meet preset conditions according to the silhouette coefficients of the plurality of medical data type groups.

[0119] In one embodiment, when the processor determines whether the plurality of medical data type groups meet a preset condition based on the silhouette coefficients of the plurality of medical data type groups, the processor is configured to implement:

[0120] Determining whether the silhouette coefficient is greater than or equal to a preset threshold;

[0121] If the silhouette coefficient is greater than or equal to a preset threshold, it is determined that the plurality of medical data type groups meet the preset conditions;

[0122] If the silhouette coefficient is less than a preset threshold, it is determined that the plurality of medical data type groups do not meet the preset conditions.

[0123] In one embodiment, after determining whether the plurality of medical data type groups meet a preset condition based on the silhouette coefficients of the plurality of medical data type groups, the processor is further configured to:

[0124] If the plurality of medical data type groups do not meet the preset condition, reacquiring a preset first number of medical data type groups;

[0125] The medical data types are clustered based on the correlation scores between the medical data types to obtain a preset first number of medical data type groups.

[0126] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the terminal device described above can refer to the corresponding process in the aforementioned medical data processing method embodiment, and will not be repeated here.

[0127] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions. The method implemented when the program instructions are executed can refer to the various embodiments of the medical data processing method of the present application.

[0128] The computer-readable storage medium may be an internal storage unit of the terminal device described in the aforementioned embodiment, such as a hard disk or memory of the terminal device. The computer-readable storage medium may be non-volatile or volatile. The computer-readable storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash memory card, etc., equipped on the terminal device.

[0129] 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.

[0130] Blockchain, as used in this article, refers to a novel application model for computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Blockchain is essentially a decentralized database, a series of data blocks generated using cryptographic methods. Each block contains information about a batch of online transactions, used to verify the validity of this information (to prevent counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, the platform product service layer, and the application service layer.

[0131] It should be understood that the terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0132] It should also be understood that the term "and / or" used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements that are inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system that includes the element.

[0133] The serial numbers of the embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments. The above description is only a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A medical data processing method, characterized in that: include: Obtain bill data for each medical data type, where the medical data type is the type of each disease; Determining, based on the bill data of each of the medical data types, a correlation score between the medical data types; Clustering the medical data types according to the correlation scores between the medical data types to obtain multiple medical data type groups; determining whether a plurality of medical data type groups meet a preset condition; When it is determined that the plurality of medical data type groups meet the preset conditions, the plurality of medical data type groups are sent to the terminal device of the insured person, so that the insured person can apply for reimbursement of bill data according to the plurality of medical data type groups; The step of determining the correlation scores between the medical data types based on the bill data of the medical data types includes: performing normal distribution processing on the billing data of each medical data type to obtain a normal distribution function of the billing data of each medical data type, estimating function parameters of the normal distribution function of the billing data of each medical data type using the maximum likelihood method to obtain a billing data function of each medical data type, performing correlation calculation on the billing data function of each medical data type to obtain a correlation score between the medical data types; Among them, the method of performing correlation calculation on the billing data functions of each medical data type to obtain the correlation score between each medical data type is: performing relative entropy calculation on two billing data functions of the medical data type in turn to obtain the relative entropy of the two billing data functions of the medical data type, performing JS divergence calculation on the relative entropy of the two billing data functions of the medical data type in turn to obtain the dispersion score between the billing data functions of each medical data type, and determining the correlation score between each medical data type based on the dispersion score between the billing data functions of each medical data type.

2. The medical data processing method according to claim 1, wherein: The clustering of the medical data types according to the correlation scores between the medical data types to obtain multiple medical data type groups includes: Obtaining a preset number of medical data type groups, and selecting a preset number of target medical data types from a plurality of the medical data types; taking each target medical data type as the first member of each medical data type group, wherein one medical data type group corresponds to one target medical data type; The medical data types are clustered according to the correlation scores between the first members of the medical data type groups and the medical data types to obtain a plurality of medical data type groups.

3. The medical data processing method according to claim 2, wherein: The clustering of each medical data type according to the correlation score between the first member of each medical data type group and each medical data type to obtain a plurality of medical data type groups includes: According to the correlation scores between each medical data type and the first member of each medical data type group, each medical data type is clustered into the medical data type group corresponding to the first member with the largest correlation score, to obtain multiple medical data type groups.

4. The medical data processing method according to claim 1, wherein: The clustering of the medical data types according to the correlation scores between the medical data types to obtain multiple medical data type groups includes: Each medical data type is regarded as a medical data type group, and each medical data type group is clustered according to the correlation scores between each medical data type. The medical data type group clustering is stopped when the number of medical data type groups reaches a preset number, and multiple medical data type groups are obtained.

5. The medical data processing method according to claim 1, wherein: Determining whether the plurality of medical data type groups meet preset conditions includes: determining silhouette coefficients for a plurality of said groups of medical data types; It is determined whether the plurality of medical data type groups meet preset conditions according to the silhouette coefficients of the plurality of medical data type groups.

6. The medical data processing method according to claim 5, wherein: The determining, based on the silhouette coefficients of the plurality of medical data type groups, whether the plurality of medical data type groups meet a preset condition comprises: Determining whether the silhouette coefficient is greater than or equal to a preset threshold; If the silhouette coefficient is greater than or equal to a preset threshold, it is determined that the plurality of medical data type groups meet the preset conditions; If the silhouette coefficient is less than a preset threshold, it is determined that the plurality of medical data type groups do not meet the preset conditions.

7. The medical data processing method according to claim 5, wherein: After determining whether the plurality of medical data type groups meet preset conditions based on the contour coefficients of the plurality of medical data type groups, the method further includes: If the plurality of medical data type groups do not meet the preset condition, reacquiring a preset first number of medical data type groups; The medical data types are clustered based on the correlation scores between the medical data types to obtain a preset first number of medical data type groups.

8. A medical data processing device, characterized in that: The medical data processing device includes an acquisition module, a determination module, a generation module and a sending module, wherein: The acquisition module is used to acquire bill data of various medical data types, wherein the medical data types are types of various diseases; The determining module is configured to determine a correlation score between each of the medical data types based on the bill data of each of the medical data types; The generating module is configured to cluster the medical data types according to the correlation scores between the medical data types to obtain a plurality of medical data type groups; The determination module is further configured to determine whether the plurality of medical data type groups meet preset conditions; The sending module is used to send the plurality of medical data type groups to the terminal device of the insured person when it is determined that the plurality of medical data type groups meet the preset conditions, so that the insured person can apply for reimbursement of bill data according to the plurality of medical data type groups. The step of determining the correlation scores between the medical data types based on the bill data of the medical data types includes: performing normal distribution processing on the billing data of each medical data type to obtain a normal distribution function of the billing data of each medical data type, estimating function parameters of the normal distribution function of the billing data of each medical data type using the maximum likelihood method to obtain a billing data function of each medical data type, performing correlation calculation on the billing data function of each medical data type to obtain a correlation score between the medical data types; Among them, the method of performing correlation calculation on the billing data functions of each medical data type to obtain the correlation score between each medical data type is: performing relative entropy calculation on two billing data functions of the medical data type in turn to obtain the relative entropy of the two billing data functions of the medical data type, performing JS divergence calculation on the relative entropy of the two billing data functions of the medical data type in turn to obtain the dispersion score between the billing data functions of each medical data type, and determining the correlation score between each medical data type based on the dispersion score between the billing data functions of each medical data type.

9. A terminal device, characterized in that: The terminal device includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the medical data processing method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the medical data processing method according to any one of claims 1 to 7 are implemented.

Images