Medical electronic invoice detail acquisition method, electronic equipment and storage medium

Abstract

The invention provides a detail acquisition method of a medical electronic invoice, electronic equipment and a storage medium. The method comprises the following steps: acquiring character string data in medical electronic invoice data; matching the character string data with project library data, and determining whether the character string data is detail level data or not; if the character string data is detail level data, obtaining a region directory library corresponding to the medical electronic invoice data; matching the character string data with a region directory library, and if the character string data cannot be matched in the region directory library, performing data cleaning on the character string data for multiple times; and matching the target character string obtained after each time of data cleaning with the region directory library again until data details corresponding to the target character string are obtained from the region directory library. According to the scheme, on the basis that the character string data are matched with the project library and the region directory library, the character string data are cleaned and matched for multiple times, and the accuracy of finally obtaining the corresponding data details is further improved.

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to a method for obtaining details of a medical electronic invoice, an electronic device, and a storage medium. Background Art

[0002] The medical electronic invoice system needs to be connected with multiple departments and platforms, including the financial system, medical insurance center, etc. By matching data, seamless connection and information sharing between different systems can be achieved, promoting business collaboration and data integration.

[0003] At present, the bill information is collected and matched through the test project management system (TPA production input system). In order to save the cost of manpower collection and improve the collection efficiency, the IRS bill verification interface is introduced to verify the authenticity of the bill. For the data of the real bill, the IRS will return the bill information and additional list details.

[0004] However, in the list details returned by the State Taxation Bureau, the details of the real drug invoices may be confusing and may not match the data in the enterprise's drug diagnosis and treatment database. In addition, the detailed hierarchical data in some regions is not consistent with the enterprise catalog data, resulting in inaccurate list details. In view of this situation, the rules for matching the list information with the drug diagnosis and treatment database are designed and implemented to improve the success rate of detail bring-out. Summary of the invention

[0005] The embodiment of the present application provides a method for obtaining the details of medical electronic invoices, which is used to solve the problem that the list detail level data and the regional directory library cannot be perfectly matched, and the accuracy of the list detail level data.

[0006] The present application embodiment provides a method for obtaining details of a medical electronic invoice, including:

[0007] Get string data from medical electronic invoice data;

[0008] Matching the string data with the project library data to determine whether the string data is detail level data;

[0009] If the string data is detailed level data, obtain the regional directory library corresponding to the medical electronic invoice data;

[0010] Matching the string data with the regional directory library, and if the string data cannot be matched in the regional directory library, performing multiple data cleaning on the string data;

[0011] The target character string obtained after each data cleaning is used to match the regional directory library again until the data details corresponding to the target character string are obtained from the regional directory library.

[0012] In one embodiment, matching the string data with the project library data to determine whether the string data is detail level data includes:

[0013] Matching the string data with the project library data, and if the string data matches the project library data, determining that the string data is project-level data;

[0014] If the string data does not match the project library data, the string data is matched with the project mapping library data. If they do not match, the string data is determined to be detail level data; if they match, the string data is determined to be project level data.

[0015] In one embodiment, the performing multiple data cleaning on the string data includes:

[0016] The Chinese symbols in the character string data are replaced with English symbols.

[0017] In one embodiment, the performing multiple data cleaning on the string data includes:

[0018] The preset special characters contained in the character string data are removed.

[0019] In one embodiment, the performing multiple data cleaning on the string data includes:

[0020] The preset special brackets contained in the character string data are replaced with designated brackets.

[0021] In one embodiment, the performing multiple data cleaning on the string data includes:

[0022] The unit data in the character string data is removed to obtain continuous Chinese characters between preset special symbols.

[0023] In one embodiment, the performing multiple data cleaning on the string data includes:

[0024] A preset keyword is obtained, and the preset keyword in the character string data is deleted or replaced.

[0025] In one embodiment, after acquiring the data details corresponding to the target character string from the regional directory library, the method further includes:

[0026] The data details are compared with the face information corresponding to the target character string in the medical electronic invoice, and the final output data content is determined according to the priority.

[0027] The present application also provides an electronic device, the electronic device comprising:

[0028] processor;

[0029] a memory for storing processor-executable instructions;

[0030] Wherein, the processor is configured to execute the above-mentioned method for obtaining details of medical electronic invoices.

[0031] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. The computer program can be executed by a processor to complete any of the above-mentioned methods for obtaining details of medical electronic invoices.

[0032] The technical solution provided by the above embodiment of the present application matches the string data with the project library, determines that it is detailed level data, and then matches it with the corresponding regional directory library. The string data that cannot be matched with the regional directory library is cleaned and matched multiple times, and finally the data details corresponding to the target string are obtained. This solution further improves the accuracy of the obtained detailed level data by cleaning and matching the string data multiple times. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solution of the embodiments of the present application, the drawings required for use in the embodiments of the present application are briefly introduced below.

[0034] Figure 1 A flowchart of a method for obtaining details of a medical electronic invoice provided in an embodiment of the present application;

[0035] Figure 2 A data cleaning flow chart provided for an embodiment of the present application;

[0036] Figure 3 A flowchart of a method for obtaining details of medical electronic invoices provided in one embodiment of the present application. DETAILED DESCRIPTION

[0037] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0038] Similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0039] Figure 1 A flowchart of a method for obtaining details of a medical electronic invoice provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method for obtaining the details of medical electronic invoices provided in the embodiment of the present application includes:

[0040] Step 1: Obtain string data from medical electronic invoice data;

[0041] Among them, medical electronic invoice data is a payment voucher issued and collected in the form of data telegrams, including but not limited to: payee, amount received, receiving unit, charging items and other detailed information.

[0042] String data refers to the rows of data in the list details of the medical electronic invoice. For example, medical expenses are a string of data, and aspirin is a string.

[0043] Step 2: Match the string data with the project library data to determine whether the string data is detailed level data;

[0044] Among them, the project library data refers to the collection of various medical items, such as Western medicine fees, treatment fees, examination fees, Chinese medicine fees, nursing fees, laboratory fees, etc.

[0045] Detailed level data refers to more specific medical names under a certain medical item, such as electrocardiogram fees, magnetic resonance imaging fees, CT fees, etc. under the examination fees.

[0046] In one embodiment, the string data is matched with the project library data, and if the string data matches the project library data, the string data is the project library data. If the string data does not match the project library data, the string data is the detail layer data.

[0047] Step 3: If the string data is detailed level data, then obtain the regional directory library corresponding to the medical electronic invoice data;

[0048] The regional directory library corresponding to medical electronic invoice data refers to the database used to store and manage medical electronic invoice data established in different regions according to their respective business needs and management needs. These directory libraries usually include multiple classified data resources for easy positioning, search and utilization.

[0049] The method to obtain the corresponding regional directory library is: through the configuration reading when the medical electronic invoice is submitted, or according to the hospital information returned by the invoice information to match the hospital library, determine the province, city or district to which the hospital belongs, and then obtain the corresponding regional directory library (such as Zhejiang directory library, Chongqing directory library, etc.) through the province, city or district.

[0050] Step 4: Match the string data with the regional directory library. If the string data cannot be matched in the regional directory library, perform multiple data cleansing on the string data.

[0051] Among them, data cleaning refers to cleaning the string according to customized rules, such as replacing all Chinese symbols in the string data with English symbols.

[0052] Step 5: Use the target string obtained after each data cleaning to match it with the regional directory library again until the data details corresponding to the target string are obtained from the regional directory library.

[0053] It should be noted that after the string data is cleaned once, the cleaned target string is used to match the regional directory library. If the match fails, the string data is cleaned again, and then the cleaned target string is used to match the regional directory library again. If the match is successful, the data details corresponding to the target string are obtained from the regional directory library. If the match fails, it is cleaned and matched again.

[0054] The data details refer to the detail ID (identification), generic name, cost level, self-pay ratio, drug quantity, remarks and other data corresponding to the string data.

[0055] The technical solution provided in the above-mentioned embodiments of the present application further improves the accuracy of the corresponding data details finally obtained by cleaning and matching the string data multiple times on the basis of matching the string data with the regional directory library.

[0056] In one embodiment, the above step 2 matches the string data with the project library data to determine whether the string data is detailed level data, specifically including: matching the string data with the project library data, if the string data matches the project library data, determining that the string data is project level data; if the string data does not match the project library data, matching the string data with the project mapping library data, if they do not match, determining that the string data is detailed level data; if they match, determining that the string data is project level data.

[0057] Among them, the project mapping library data records other names of each medical item in the project library data. For example, the medical expenses in the project library data can be recorded in the project mapping library data and can also be called treatment fees, diagnosis fees, examination fees, etc.

[0058] To improve efficiency, you can first match the string data with the project library data. When the string data does not appear in the project library data, it is considered that the string data does not match the project library data. Otherwise, it is considered to match. When the string data does not match the project library data, the string data is matched with the project mapping library data. If the string data appears in the project mapping library, it is considered that the string data is project-level data. Otherwise, it is considered that the string data is detail-level data. Among them, project-level data includes Western medicine fees, Chinese medicine fees, etc. Detail-level data includes sodium chloride injection and vitamin C tablets.

[0059] In one embodiment, Figure 2 A data cleaning flow chart provided in an embodiment of the present application is as follows: Figure 2 As shown, the present application performs multiple data cleaning on the string data, including:

[0060] Step 6: Use English symbols to replace Chinese symbols in the string data.

[0061] Among them, since the symbols in the regional directory library are all English symbols, it is necessary to replace the Chinese symbols in the string data with English symbols. The method of replacing Chinese symbols with English symbols is, for example, replacing the English format "(" with the Chinese format "(", etc. After the replacement is completed, the target string data obtained after the replacement is matched with the regional directory library again.

[0062] Part of the code for this step is:

[0063]

[0064] Step 7: Use regular expressions to remove the preset special characters contained in the string data.

[0065] Among them, the regular expression method is, for example, to specify to remove other special symbols such as "[\\\\s~·`!!√▼①②③④⑤⑥⑦⑧⑨⑩□○G◎■◇⊙@#￥$%^……&*◆⊙★▲●※O☆△\\\\-——\\\\-_\\-=+

\\[\\]

[0066] Part of the code for this step is:

[0067]

[0068] Step 8: Use regular expressions to replace the preset special brackets contained in the string data with specified brackets.

[0069] The designated brackets may be "(" in English format, and the preset special brackets may be book title marks, curly brackets, etc. For example, "《" is replaced with the designated "(", "﹛" is replaced with the designated "(", and "{" is replaced with the designated "(". Then, if the string data contains "《", "》", "﹛", "﹜", "{", "}", it will be replaced with the designated corresponding brackets. After the special brackets in the string data containing the preset special brackets are successfully replaced with the designated brackets through regular expressions, the target string is obtained, and the target string is matched with the regional directory library again. In one embodiment, if the match fails, the content in the brackets can be directly deleted and matched again.

[0070] Part of the code for this step is:

[0071]

[0072]

[0073] Step 9: Use regular expressions to remove unit data from string data.

[0074] The unit data is, for example, "100 g / box", "1 mg*10", etc. The target string data obtained by deleting the unit data contained in the string data through regular expression is matched with the regional directory library again.

[0075] Step 10: Get the continuous Chinese characters between the preset special symbols through regular expressions.

[0076] Among them, if the string data contains "||urea cream||", the Chinese characters "urea cream" are obtained. The target string data of the continuous Chinese characters between the preset special symbols obtained by regular expression is matched with the regional directory library again. Part of the code of this step is:

[0077]

[0078]

[0079] Step 11: Delete or replace the preset keyword in the character string data by obtaining the preset keyword.

[0080] For example, if the preset keyword is "urea cream", when the string data is also "urea cream", delete "cream" or delete "milk". For example, "urea cream" can also be replaced with "urea cream". The target string data obtained by keyword filtering is matched with the regional directory library again.

[0081] The above method of multiple data cleaning of string data can be performed in sequence according to the above cleaning steps, or the string data can be cleaned in a random order, but each step is only performed once. For example, after the original string data "replaces all Chinese symbols with English symbols", it cannot be matched with the regional directory library, then the string data can be cleaned through the remaining other cleaning steps, but it is not necessary to go through the step of "replace all Chinese symbols with English symbols" again.

[0082] In one embodiment, Figure 3 The detailed acquisition method flow chart of the medical electronic invoice provided for this application is as follows: Figure 3 As shown, if the data in the regional directory library cannot be matched after the above steps, the data will be saved, and a dedicated person will organize and map the data later, and compile new rules for cleaning the data, or directly map the data to the data in the correct regional directory library.

[0083] Figure 3 The detailed acquisition method flow chart of the medical electronic invoice provided for this application is as follows: Figure 3 As shown, in one embodiment, the above steps can use ES query to match the string data with the regional directory library, and the word segmenter used is IK word segmenter. IK word segmenter is an open source Chinese word segmentation plug-in, which provides support for Chinese for Elasticsearch. IK word segmenter supports user-defined dictionaries and stop words to provide more accurate word segmentation effects. For example, the drug base (A) urea cream will be processed into base urea cream and base and passed to the ES server. ES will divide the data into urea cream and base according to the algorithm logic, and then query all the data that meets the data, and then use the proportion of the word segmentation in the entire data and the full calculation score, and finally return the data with the highest score. In this way, the final matching data can be obtained.

[0084] In one embodiment, after obtaining the data details corresponding to the target string from the regional directory library, the method further includes: comparing the data details with the face information corresponding to the target string in the medical electronic invoice, and determining the final output data content according to the priority.

[0085] The data details are obtained through the above cleaning steps. The data details may include detail ID, generic name, cost level, self-pay ratio, drug quantity, remarks and other data. These data details are compared with the face value information corresponding to the target string in the medical electronic invoice and the data is output.

[0086] It should be noted that due to regional reasons, the proportion of drug details may vary. Some insurance companies require the proportion to be based on the face value information, while others require the proportion to be based on the regional catalog library. Therefore, after obtaining the data details of the regional catalog library, customization is made according to the region and insurance company, and the final output data content is determined based on the priority between the face value information and the data details of the regional catalog library that are determined in advance. For example, when the face value information of a drug is inconsistent with the data details of the regional catalog library, if the face value information has a higher priority, the face value information will be used as the basis for output.

[0087] The embodiment of the present application also provides an electronic device, which includes a processor and a memory for storing instructions executable by the processor, and the processor is configured to execute the method for obtaining the details of medical electronic invoices described in the above embodiment of the present application. The electronic device can be a smart terminal such as a smart phone, a tablet computer, a server, a desktop computer, etc.

[0088] The embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and the computer program can be executed by a processor to complete the detailed acquisition method of medical electronic invoices described in the above embodiment. The computer-readable storage medium can be implemented as various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

Claims

1. A method for obtaining details of medical electronic invoices. It is characterized in that include: Get string data from medical electronic invoice data; Matching the string data with the project library data to determine whether the string data is detail level data; If the string data is detailed level data, obtain the regional directory library corresponding to the medical electronic invoice data; Matching the string data with the regional directory library, and if the string data cannot be matched in the regional directory library, performing multiple data cleaning on the string data; The target character string obtained after each data cleaning is used to match the regional directory library again until the data details corresponding to the target character string are obtained from the regional directory library.

2. The method according to claim 1, It is characterized in that The matching of the character string data with the project library data to determine whether the character string data is detail level data includes: Matching the string data with the project library data, and if the string data matches the project library data, determining that the string data is project-level data; If the string data does not match the project library data, the string data is matched with the project mapping library data. If they do not match, the string data is determined to be detail level data; if they match, the string data is determined to be project level data.

3. The method according to claim 1, It is characterized in that The performing multiple data cleaning on the string data includes: The Chinese symbols in the character string data are replaced with English symbols.

4. The method according to claim 1, It is characterized in that The performing multiple data cleaning on the string data includes: The preset special characters contained in the character string data are removed.

5. The method according to claim 1, It is characterized in that The performing multiple data cleaning on the string data includes: The preset special brackets contained in the character string data are replaced with designated brackets.

6. The method according to claim 1, It is characterized in that The performing multiple data cleaning on the string data includes: The unit data in the character string data is removed to obtain continuous Chinese characters between preset special symbols.

7. The method according to claim 1, It is characterized in that The performing multiple data cleaning on the string data includes: A preset keyword is obtained, and the preset keyword in the character string data is deleted or replaced.

8. The method according to claim 1, It is characterized in that After acquiring the data details corresponding to the target character string from the regional directory library, the method further includes: The data details are compared with the face information corresponding to the target character string in the medical electronic invoice, and the final output data content is determined according to the priority.

9. An electronic device, It is characterized in that The electronic device comprises: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to execute the method for obtaining details of medical electronic invoices as described in any one of claims 1-9.

10. A computer-readable storage medium, It is characterized in that The storage medium stores a computer program, and the computer program can be executed by a processor to complete the method for obtaining details of medical electronic invoices as described in any one of claims 1-9.

Images