Disease name standardization method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of artificial intelligence and data processing, and discloses a disease name standardization method and device, computer equipment and a storage medium. According to the method, the to-be-standardized disease name is obtained, the target standard disease name matched with the to-be-standardized disease name is found out from the ICD code directory, and the to-be-standardized disease name is associated with the target standard disease name and the corresponding code, so that the to-be-standardized disease name can be standardized according to the ICD code directory; standardization and unification of disease names are realized; in the risk prevention of the insurance industry, a disease name standardization method is utilized to convert a non-standard disease name into a standard disease name, and an effective risk tag is mined from the standard disease name, so that an insurance enterprise risk prevention system can be optimized, complex non-structured disease data can be completely structured, and a corresponding disease risk can be mapped; the risk prevention effect is greatly improved, and a risk prevention team is assisted to break the bottleneck.

Description

Technical Field

[0001] The present invention relates to the fields of artificial intelligence and data processing technology, and in particular to a disease name standardization method, device, computer equipment and storage medium. Background Art

[0002] Risk prevention has always been a key task in the financial industry, especially in the insurance industry. Insurance companies are ultimately risk-based companies, and a complete risk prevention system is the key to high-quality development of the insurance industry. It can be said that risk prevention has always been the bottom line and cornerstone of the development of the insurance industry.

[0003] However, as the data capabilities of insurance companies improve, the insurance industry faces increasing challenges in improving risk prevention effectiveness: first, the information density of structured data is low, and risk prevention models often rely on hundreds or thousands of features. Strong rule features have long been mined, and the remaining structured features have extremely low information density, and repeated adjustments to mining are of little significance; second, the degree of standardization of unstructured data is low. Considering that the biggest risk in the insurance industry is disease risk, but disease risk is often stored in unstructured text data, in traditional medical and insurance industries, the standardization of medical data is extremely dependent on the professionalism and work efficiency of coders.

[0004] Based on this, improving the standardization of disease names and discovering effective risk labels have become the key to optimizing the risk prevention system of various insurance companies. Therefore, how to achieve the standardization of disease names has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a disease name standardization method, device, computer equipment and storage medium to solve the technical problem of how to achieve disease name standardization.

[0006] In the first aspect, a method for standardizing disease names is provided, comprising:

[0007] Get the name of the disease to be standardized;

[0008] In the ICD code directory, search for the target standardized disease name that completely matches the disease name to be standardized;

[0009] If the target standard disease name that completely matches the disease name to be standardized is not found in the ICD code directory, the disease name to be standardized is replaced with a synonym using the synonym replacement library, and then the target standard disease name that completely matches the disease name to be standardized after the synonym replacement is found in the ICD code directory;

[0010] If the target standard disease name that completely matches the disease name to be standardized after synonym replacement is not found in the ICD code directory, the disease name to be standardized is converted into a synonym using the synonym conversion library, and then the target standard disease name that completely matches the disease name to be standardized after synonym conversion is found in the ICD code directory;

[0011] If the target standard disease name that completely matches the disease name to be standardized after synonym conversion is not found in the ICD coding directory, the disease name to be standardized after synonym conversion is matched with the standard disease name in the ICD coding directory in an unordered manner, and the matching degree between each standard disease name in the ICD coding directory and the disease name to be standardized after synonym conversion is calculated, and the standard disease name with the highest matching degree is determined as the target standard disease name;

[0012] The disease name to be standardized is associated with the target standard disease name and its corresponding code.

[0013] In a second aspect, a disease name standardization device is provided, comprising:

[0014] An acquisition module is used to obtain the name of the disease to be standardized;

[0015] The first matching module is used to search the ICD code catalog for a target standardized disease name that completely matches the disease name to be standardized;

[0016] The second matching module is used to replace the disease name to be standardized with a synonym using a synonym replacement library if a target standard disease name that completely matches the disease name to be standardized is not found in the ICD code directory, and then search the ICD code directory for a target standard disease name that completely matches the disease name to be standardized after the synonym replacement;

[0017] The third matching module is used to perform synonym conversion on the disease name to be standardized using the synonym conversion library if the target standard disease name that completely matches the disease name to be standardized after the synonym replacement is not found in the ICD code directory, and then search for the target standard disease name that completely matches the disease name to be standardized after the synonym replacement in the ICD code directory;

[0018] The fourth matching module is used for, if a target standard disease name that completely matches the disease name to be standardized after synonym conversion is not found in the ICD coding directory, to match the disease name to be standardized after synonym conversion with the standard disease name in the ICD coding directory in an unordered manner, and to calculate the matching degree between each standard disease name in the ICD coding directory and the disease name to be standardized after synonym conversion, and to determine the standard disease name with the highest matching degree as the target standard disease name;

[0019] A mapping association module is used to associate the disease name to be standardized with the target standard disease name and its corresponding code.

[0020] In a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned disease name standardization method when executing the computer program.

[0021] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned disease name standardization method are implemented.

[0022] The above-mentioned disease name standardization, application method, device, computer equipment and storage medium obtain the disease name to be standardized, find the target standard disease name that matches the disease name to be standardized from the ICD coding directory, and associate the disease name to be standardized with the target standard disease name and its corresponding code, so that the disease name to be standardized can be standardized according to the ICD coding directory, thereby realizing the standardization and consistency of disease names; and when finding the target standard disease name that matches the disease name to be standardized from the ICD coding directory, first match the disease name to be standardized with the standard disease name in the ICD coding directory. If there is no match, the disease name to be standardized is replaced with a synonym and converted to a synonym, and then further matched with the standard disease name. If there is still no match, the disease name to be standardized after the synonym conversion is matched with the standard disease name in the ICD coding directory in an unordered manner, and the standard disease name with the highest matching degree is determined as the target standard disease name. Through multiple matching processes, the precision and accuracy of disease name standardization are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0024] Figure 1 is an exemplary system architecture diagram in which the present invention can be applied;

[0025] Figure 2 is a flow chart of a disease name standardization method in one embodiment of the present invention;

[0026] Figure 3 is a structural schematic diagram of a disease name standardization device in one embodiment of the present invention;

[0027] Figure 4 It is a structural diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0028] 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 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] like Figure 1 As shown, the system architecture includes a client, a network, and a server. The network is used to provide a medium for a communication link between the client and the server, that is, the client can communicate with the server through the network. The network includes various connection types, such as wired, wireless communication links or fiber optic cables, etc. Users can use the client to interact with the server through the network to receive or send messages, etc. Various communication client applications can be installed on the client, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc. The server can be a server that provides various services, such as a background server that supports the pages displayed on the client.

[0030] The embodiments of the present application provide a method, device, computer equipment and storage medium for standardizing disease names. Among them, the disease name standardization method can be applied to a server. The client can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers and portable wearable devices. The server can be implemented with an independent server or a server cluster composed of multiple servers. The present invention is described in detail below through specific embodiments. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0031] Figure 2 A flow chart of a disease name standardization method provided by an embodiment of the present invention is as follows: Figure 2As shown, the disease name standardization method includes steps S10 to S60:

[0032] S10: Obtain the name of the disease to be standardized.

[0033] There are a large amount of medical records and physical examination data in the CDC database, medical center database and the diagnosis and treatment database of each hospital. Due to the different personal experiences and diagnosis and treatment habits of different doctors, the disease names entered into the database may contain qualifiers or colloquialisms, that is, the disease names entered into the database are non-standardized disease names.

[0034] In this step, by processing the medical records and physical examination data, key information can be extracted to obtain the name of the disease to be standardized. For example, the text information of the paper medical records and physical examination data can be converted into a computer-readable digital format using OCR technology, and then the key information such as the disease name can be identified and extracted using LLM technology to obtain the disease name to be standardized.

[0035] S20: In the ICD code directory, search for a target standard disease name that completely matches the disease name to be standardized.

[0036] The step S20 includes steps S21 to S24:

[0037] S21: Perform random matching of the disease name to be standardized with each standard disease name in the ICD coding directory, and search for a standard disease name that completely matches the disease name to be standardized.

[0038] The ICD coding directory includes multiple standard disease names and their corresponding codes. In this step, the disease name to be standardized and the standard disease name are first shuffled into disordered forms, and then the disordered disease name to be standardized is matched with the standard disease name in disorder. The complete match described in this step does not only mean that the disease name to be standardized is completely consistent with the standard disease name in the ICD coding directory. In addition, as long as all the characters in the disease name to be standardized can be found in the standard disease name in the ICD coding directory, or all the characters in the standard disease name in the ICD coding directory can be found in the disease name to be standardized, they all belong to the category of complete matching. For example, "type I diabetes" in the disease name to be standardized and "type I diabetes" in the standard disease name belong to the category of complete matching; "type I diabetes" in the disease name to be standardized and "type I diabetes" in the standard disease name also belong to the category of complete matching; "respiratory tract infection" in the disease name to be standardized and "acute respiratory tract infection" in the standard disease name also belong to the category of complete matching; "acute respiratory tract infection" in the disease name to be standardized and "respiratory tract infection" in the standard disease name also belong to the category of complete matching. The matching of the disease name to be standardized with each standard disease name in the ICD coding catalogue is realized in the form of unordered matching, which can provide matching accuracy and thus improve the precision and accuracy of the disease name standardization system.

[0039] S22: Determine whether the number of standard disease names that completely match the disease name to be standardized is unique.

[0040] The process of disease name standardization is a process of matching the standard disease name and the corresponding code that matches the disease name to be standardized from the ICD code directory. Based on the limitation of the complete match category in step S21, in the process of disorderly matching the disease name to be standardized with the standard disease name, there may be multiple standard disease names that completely match the disease name to be standardized. For this situation, different processing is required according to the number of standard disease names that completely match the disease name to be standardized.

[0041] S23: If the number of standard disease names that completely match the disease name to be standardized is unique, the unique standard disease name that completely matches the disease name to be standardized is determined as the target standard disease name.

[0042] S24: If the number of standard disease names that completely match the disease name to be standardized is not unique, a standard disease name with the longest coding digit is selected from multiple standard disease names that completely match the disease name to be standardized and determined as the target standard disease name.

[0043] For step S24, when there are multiple standard disease names that completely match the disease name to be standardized, the standard disease name with the longest number of coding bits is selected from the multiple standard disease names that completely match the disease name to be standardized and determined as the target standard disease name; if there are multiple standard disease names that completely match the disease name to be standardized and have the longest number of coding bits, the multiple standard disease names that completely match the disease name to be standardized and have the longest number of coding bits are simultaneously determined as the target standard disease name.

[0044] S30: If the target standard disease name that completely matches the disease name to be standardized is not found in the ICD coding directory, the disease name to be standardized is replaced with a synonym using the synonym replacement library, and then the target standard disease name that completely matches the disease name to be standardized after the synonym replacement is found in the ICD coding directory.

[0045] Since there may be multiple synonyms for disease names, such as "cancer" and "malignant tumor", "Roman numerals" and "Arab numerals", etc., it is necessary to establish a synonym replacement library to collect and organize these synonyms. This synonym replacement library can be constructed by collecting medical data on a daily basis and mining and analyzing the standard mapping library. The synonym replacement library includes multiple groups of synonyms related to disease names.

[0046] Because the disease name may have synonyms, therefore, when the target standard disease name that completely matches the disease name to be standardized is not found in the ICD coding directory, after the disease name to be standardized is replaced with a synonym using the synonym replacement library, the target standard disease name that completely matches the disease name to be standardized after the synonym replacement may be found in the ICD coding directory. Among them, the specific process of searching for the target standard disease name that completely matches the disease name to be standardized after the synonym replacement in the ICD coding directory can refer to the above steps S21 to S24, which will not be repeated here.

[0047] For step S30, whether it is possible to quickly and accurately find the target standard disease name that completely matches the disease name to be standardized after synonym replacement in the ICD coding directory depends on the comprehensiveness and accuracy of the data in the synonym replacement library. Therefore, how to expand the synonym replacement library becomes the key.

[0048] In the embodiment of the present invention, the synonym replacement library is expanded through steps S31 to S33:

[0049] S31: Extract information from the disease corpus to obtain synonym key-value pairs.

[0050] The data stored in the disease corpus are derived from medical records and physical examination data in the CDC database, the medical center database, and the diagnosis and treatment databases of various hospitals, including text-intensive image materials and non-text-intensive image materials.

[0051] For text-intensive image materials, OCR (Optical Character Recognition) technology and LLM (Large Language Model) technology are used to process the text-intensive image materials, and information is extracted from the text-intensive image materials to obtain synonym key-value pairs. The synonym key-value pairs are a pair of disease names that are synonyms of each other.

[0052] For non-text-intensive image materials, VLM (Visual Language Model) technology is used to process the non-text-intensive image materials, and information is extracted from the non-text-intensive image materials to obtain synonym key-value pairs.

[0053] S32: Calculate the confidence of the synonym key-value pair.

[0054] For the synonym key-value pairs extracted from the disease corpus, a confidence algorithm module is set to score the confidence of the synonym key-value pairs. Specifically, setting the confidence algorithm module to score the confidence of the synonym key-value pairs can be achieved through existing technologies, and the specific process is not repeated here.

[0055] S33: directly adding synonym key-value pairs with a confidence level higher than a preset value to the synonym replacement library, and determining whether to add synonym key-value pairs with a confidence level lower than a preset value to the synonym replacement library according to manual review results.

[0056] For synonym key-value pairs with a confidence level higher than a preset value, manual review is not required and they are directly added to the synonym replacement library; for synonym key-value pairs with a confidence level lower than a preset value, they need to undergo a simple manual review. If the review is passed, they are added to the synonym replacement library. If the review is not passed, they are left to be determined and further proofread by professionals with a medical background.

[0057] For steps S31 to S33, OCR technology and LLM technology are used to extract information from text-intensive materials to obtain synonym key-value pairs, while VLM technology is used to extract information from non-text-intensive materials to obtain synonym key-value pairs. The accuracy of information extraction is much higher than that of traditional algorithms, and the data mining accuracy of the disease corpus is improved by more than 15%. A confidence algorithm module is set to score the confidence of the information extraction results. Synonymous key-value pairs with high confidence are exempted from manual review and are directly stored in the database. Synonymous key-value pairs with low confidence are stored in the database after simple manual review, which improves efficiency by more than 80%.

[0058] S40: If the target standard disease name that completely matches the disease name to be standardized after synonym replacement is not found in the ICD coding directory, the disease name to be standardized is converted into a synonym using the synonym conversion library, and then the target standard disease name that completely matches the disease name to be standardized after synonym conversion is found in the ICD coding directory.

[0059] Due to the personal experience and treatment habits of different doctors, the same disease may be described using different words. For example, cold and acute nasopharyngitis, ectopic pregnancy and ectopic pregnancy, AFP and alpha-fetoprotein are all different descriptions of the same disease. The core of synonym conversion is to use the synonym conversion library to convert the complete disease description to obtain another description of the same disease. The construction of the synonym conversion library relies on the accumulation of the CDC database, the medical center database, and the standardization of daily medical data. Each disease name in the synonym conversion library is associated with multiple different description statements.

[0060] Because the same disease may be described using different words, when the target standard disease name that completely matches the disease name to be standardized after synonym replacement is not found in the ICD coding directory, after the disease name to be standardized is converted into a synonym using the synonym conversion library, the target standard disease name that completely matches the disease name to be standardized after synonym conversion may be found in the ICD coding directory. Among them, the specific process of searching for the target standard disease name that completely matches the disease name to be standardized after synonym conversion in the ICD coding directory can refer to the above steps S21 to S24, which will not be repeated here.

[0061] For step S40, whether it is possible to quickly and accurately find the target standard disease name that completely matches the disease name to be standardized after synonym conversion in the ICD coding directory depends on the comprehensiveness and accuracy of the data in the synonym conversion library. Therefore, how to expand the synonym conversion library becomes the key.

[0062] In the embodiment of the present invention, the synonym conversion library is expanded through steps S41 to S43:

[0063] S41: Build corresponding prompt template based on ICD coding group.

[0064] Prompt engineering refers to a technique that helps the model generate the desired output by adding prompt information to the model input text. Here, building a corresponding prompt template based on the ICD code group actually edits the prompt information related to the ICD code group to guide the knowledge extraction model to extract information related to the disease name, disease code, etc.

[0065] S42: Import the prompt template into the knowledge extraction model. The knowledge extraction model completes the knowledge extraction of the disease corpus under the guidance of the prompt template, and uses the knowledge extraction results to construct corresponding synonym conversion key-value pairs.

[0066] Importing the prompt template into the knowledge extraction model can guide the knowledge extraction model to extract relevant information such as disease name and disease code, and then associate different descriptions of the same disease to obtain corresponding synonym conversion key-value pairs.

[0067] S43: Add the synonym conversion key-value pair to the synonym conversion library.

[0068] For steps S41 to S43, the synonym conversion library is expanded using large model technology, which greatly improves work efficiency.

[0069] S50: If the target standard disease name that completely matches the disease name to be standardized after synonym conversion is not found in the ICD coding directory, the disease name to be standardized after synonym conversion is matched with the standard disease name in the ICD coding directory in an unordered manner, and the matching degree between each standard disease name in the ICD coding directory and the disease name to be standardized after synonym conversion is calculated, and the standard disease name with the highest matching degree is determined as the target standard disease name.

[0070] For step S50, the names of diseases to be standardized after synonym conversion and the standard disease names in the ICD coding directory are first split and disordered, for example, "malignant tumor" is disordered to "tumor malignant tumor", and then a certain character in the names of diseases to be standardized after synonym conversion is matched with the characters of the standard disease name one by one. If a character identical to a certain character in the names of diseases to be standardized after synonym conversion is found in the standard disease name, it means a match. Then calculate the ratio of the number of matched characters to the total number of characters in the standard disease name. The higher the ratio, the higher the matching degree between the corresponding standard disease name and the names of diseases to be standardized after synonym conversion. Finally, the standard disease name with the highest matching degree is determined as the target standard disease name.

[0071] Since the number of standard disease names with the highest matching degree with the disease name to be standardized after the synonym conversion may be more than one, we further determine the standard disease name with the highest matching degree as the target standard disease name through steps S51 to S53:

[0072] S51: Determine whether the number of standard disease names that have the highest matching degree with the disease name to be standardized after the synonym conversion is unique;

[0073] S52: If the number of standard disease names with the highest matching degree with the to-be-standardized disease name after the synonym conversion is unique, the unique standard disease name with the highest matching degree with the to-be-standardized disease name after the synonym conversion is determined as the target standard disease name;

[0074] S53: If the number of standard disease names that have the highest matching degree with the disease name to be standardized after synonym conversion is not unique, then the standard disease name with the shortest length is selected from multiple standard disease names that have the highest matching degree with the disease name to be standardized after synonym conversion, and determined as the target standard disease name.

[0075] Since there may be more than one standard disease name with the highest matching degree and the shortest length with the disease name to be standardized after the synonym conversion, we further select the shortest standard disease name from multiple standard disease names with the highest matching degree with the disease name to be standardized after the synonym conversion through steps S531 to S533, and determine it as the target standard disease name:

[0076] S531: Determine whether the number of standard disease names that have the highest matching degree and the shortest length with the disease name to be standardized after the synonym conversion is unique;

[0077] S532: If the number of standard disease names with the highest matching degree and the shortest length with the disease name to be standardized after the synonym conversion is unique, then the unique standard disease name with the highest matching degree and the shortest length with the disease name to be standardized after the synonym conversion is determined as the target standard disease name;

[0078] S533: If the number of standard disease names that have the highest matching degree and the shortest length with the disease name to be standardized after synonym conversion is not unique, all standard disease names that have the highest matching degree and the shortest length with the disease name to be standardized after synonym conversion are determined as the target standard disease names.

[0079] S60: Associating the disease name to be standardized with the target standard disease name and its corresponding code.

[0080] By obtaining the name of the disease to be standardized, finding the target standard disease name that matches the disease name to be standardized from the ICD coding directory, and associating the disease name to be standardized with the target standard disease name and its corresponding code, it is possible to standardize the disease name to be standardized according to the ICD coding directory, thereby achieving standardization and consistency of disease names.

[0081] The disease name standardization method provided by the present invention can be applied to various application scenarios. For example, in the risk prevention of the insurance industry, the disease name standardization method is used to convert non-standard disease names into standard disease names, and then effective risk labels are mined from the standard disease names. This can optimize the risk prevention system of insurance companies, and can completely structure complex unstructured disease data and map the corresponding disease risks, greatly improving the risk prevention effect and helping the risk prevention team break the bottleneck. For another example, in the diagnosis and treatment of the disease, the disease name standardization method can be used to quickly determine the standardized disease name and risk level corresponding to the customer's disease description, speed up the time to determine the treatment plan, and improve the treatment experience.

[0082] The disease name standardization method provided in the embodiment of the present invention obtains the disease name to be standardized, finds the target standard disease name that matches the disease name to be standardized from the ICD coding directory, and associates the disease name to be standardized with the target standard disease name and its corresponding code, so that the disease name to be standardized can be standardized according to the ICD coding directory, thereby achieving standardization and consistency of disease names; and when the target standard disease name that matches the disease name to be standardized is found from the ICD coding directory, the disease name to be standardized is first matched with the standard disease name in the ICD coding directory. If there is no match, the disease name to be standardized is replaced with a synonym and converted to a synonym, and then further matched with the standard disease name. If there is still no match, the disease name to be standardized after the synonym conversion is matched with the standard disease name in the ICD coding directory in an unordered manner, and the standard disease name with the highest matching degree is determined as the target standard disease name. Through multiple matching processes, the precision and accuracy of disease name standardization are improved.

[0083] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0084] In one embodiment, a disease name standardization device is provided, which corresponds one-to-one to the disease name standardization method in the above embodiment. Figure 3 As shown, the disease name standardization device includes an acquisition module 10, a first matching module 20, a second matching module 30, a third matching module 40, a fourth matching module 50 and a mapping association module 60. The functional modules are described in detail as follows:

[0085] The acquisition module 10 is used to execute step S10 in the disease name standardization method in the above embodiment, that is, to acquire the disease name to be standardized.

[0086] The first matching module 20 is used to execute step S20 in the disease name standardization method in the above embodiment, that is, to search the ICD code directory for a target standard disease name that completely matches the disease name to be standardized.

[0087] The second matching module 30 is used to execute step S30 in the disease name standardization method in the above embodiment, that is, if a target standard disease name that completely matches the disease name to be standardized is not found in the ICD code directory, the disease name to be standardized is replaced with a synonym using a synonym replacement library, and then the target standard disease name that completely matches the disease name to be standardized after the synonym replacement is found in the ICD code directory.

[0088] The third matching module 40 is used to execute step S40 in the disease name standardization method in the above embodiment, that is, if a target standard disease name that completely matches the disease name to be standardized after synonym replacement is not found in the ICD code directory, the disease name to be standardized is converted into a synonym using the synonym conversion library, and then the target standard disease name that completely matches the disease name to be standardized after synonym conversion is searched in the ICD code directory.

[0089] The fourth matching module 50 is used to execute step S50 in the disease name standardization method in the above embodiment, that is, if the target standard disease name that completely matches the disease name to be standardized after synonym conversion is not found in the ICD coding directory, the disease name to be standardized after synonym conversion is matched in an unordered manner with the standard disease name in the ICD coding directory, and the matching degree between each standard disease name in the ICD coding directory and the disease name to be standardized after synonym conversion is calculated, and the standard disease name with the highest matching degree is determined as the target standard disease name.

[0090] The mapping association module 60 is used to execute step S60 in the disease name standardization method in the above embodiment, that is, to associate the disease name to be standardized with the target standard disease name and its corresponding code.

[0091] In one embodiment, the first matching module 20 is specifically configured to:

[0092] Performing random matching of the disease name to be standardized with each standard disease name in the ICD coding directory, and searching for a standard disease name that completely matches the disease name to be standardized;

[0093] Determining whether the number of standard disease names that completely match the disease name to be standardized is unique;

[0094] If the number of standard disease names that completely match the disease name to be standardized is unique, the unique standard disease name that completely matches the disease name to be standardized is determined as the target standard disease name;

[0095] If the number of standard disease names that completely match the disease name to be standardized is not unique, the standard disease name with the longest coding digit is selected from multiple standard disease names that completely match the disease name to be standardized and determined as the target standard disease name.

[0096] In one embodiment, the fourth matching module 50 is further configured to:

[0097] Determine whether the number of standard disease names that have the highest matching degree with the disease name to be standardized after the synonym conversion is unique;

[0098] If the number of standard disease names with the highest matching degree with the to-be-standardized disease name after the synonym conversion is unique, the unique standard disease name with the highest matching degree with the to-be-standardized disease name after the synonym conversion is determined as the target standard disease name;

[0099] If the number of standard disease names that have the highest matching degree with the disease name to be standardized after synonym conversion is not unique, the standard disease name with the shortest length is selected from multiple standard disease names that have the highest matching degree with the disease name to be standardized after synonym conversion and determined as the target standard disease name.

[0100] In one embodiment, the fourth matching module 50 is further configured to:

[0101] Determine whether the number of standard disease names that have the highest matching degree and the shortest length with the disease name to be standardized after synonym conversion is unique;

[0102] If the number of standard disease names with the highest matching degree and the shortest length with the disease name to be standardized after the synonym conversion is unique, then the unique standard disease name with the highest matching degree and the shortest length with the disease name to be standardized after the synonym conversion is determined as the target standard disease name;

[0103] If the number of standard disease names with the highest matching degree and the shortest length with the disease name to be standardized after synonym conversion is not unique, all standard disease names with the highest matching degree and the shortest length with the disease name to be standardized after synonym conversion are determined as the target standard disease names.

[0104] The disease name standardization device provided in the embodiment of the present invention obtains the disease name to be standardized, finds the target standard disease name that matches the disease name to be standardized from the ICD code directory, and associates the disease name to be standardized with the target standard disease name and its corresponding code, so that the disease name to be standardized can be standardized according to the ICD code directory, thereby realizing the standardization and consistency of the disease name; and when the target standard disease name that matches the disease name to be standardized is found from the ICD code directory, the disease name to be standardized is first matched with the standard disease name in the ICD code directory. If there is no match, the disease name to be standardized is replaced with a synonym and converted to a synonym, and then further matched with the standard disease name. If there is still no match, the disease name to be standardized after the synonym conversion is matched with the standard disease name in the ICD code directory in an unordered manner, and the standard disease name with the highest matching degree is determined as the target standard disease name. Through multiple matching processes, the precision and accuracy of disease name standardization are improved.

[0105] For the specific definition of the disease name standardization device, please refer to the definition of the disease name standardization method above, which will not be repeated here. Each module in the above-mentioned disease name standardization device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0106] In one embodiment, a computer device is provided, whose internal structure diagram can be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with other external electronic devices via a network connection. When the computer program is executed by the processor, the functions or steps of the above-mentioned disease name standardization method are implemented.

[0107] In one embodiment, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the functions or steps of the above-mentioned disease name standardization method are implemented.

[0108] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0109] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0110] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for standardizing disease names, characterized in that: include: Get the name of the disease to be standardized; In the ICD code directory, search for the target standardized disease name that completely matches the disease name to be standardized; If the target standard disease name that completely matches the disease name to be standardized is not found in the ICD code directory, the disease name to be standardized is replaced with a synonym using the synonym replacement library, and then the target standard disease name that completely matches the disease name to be standardized after the synonym replacement is found in the ICD code directory; If the target standard disease name that completely matches the disease name to be standardized after synonym replacement is not found in the ICD code directory, the disease name to be standardized is converted into a synonym using the synonym conversion library, and then the target standard disease name that completely matches the disease name to be standardized after synonym conversion is found in the ICD code directory; If the target standard disease name that completely matches the disease name to be standardized after synonym conversion is not found in the ICD coding directory, the disease name to be standardized after synonym conversion is matched with the standard disease name in the ICD coding directory in an unordered manner, and the matching degree between each standard disease name in the ICD coding directory and the disease name to be standardized after synonym conversion is calculated, and the standard disease name with the highest matching degree is determined as the target standard disease name; The disease name to be standardized is associated with the target standard disease name and its corresponding code.

2. The method for standardizing disease names according to claim 1, characterized in that: In the ICD code directory, search for the target standardized disease name that fully matches the disease name to be standardized, including: Performing random matching of the disease name to be standardized with each standard disease name in the ICD coding directory, and searching for a standard disease name that completely matches the disease name to be standardized; Determining whether the number of standard disease names that completely match the disease name to be standardized is unique; If the number of standard disease names that completely match the disease name to be standardized is unique, the unique standard disease name that completely matches the disease name to be standardized is determined as the target standard disease name; If the number of standard disease names that completely match the disease name to be standardized is not unique, the standard disease name with the longest coding digit is selected from multiple standard disease names that completely match the disease name to be standardized and determined as the target standard disease name.

3. The disease name standardization method according to claim 1, characterized in that: The method for expanding the synonym replacement library includes: Extract information from the disease corpus to obtain synonym key-value pairs; Calculate the confidence of synonym key-value pairs; The synonym key-value pairs with a confidence level higher than a preset value are directly added to the synonym replacement library, and it is determined whether to add the synonym key-value pairs with a confidence level lower than a preset value to the synonym replacement library according to the manual review result.

4. The method for standardizing disease names according to claim 3, characterized in that: The data stored in the disease corpus include text-intensive image materials and non-text-intensive image materials. The information extracted from the disease corpus to obtain synonym key-value pairs includes: Use OCR technology and LLM technology to process text-intensive image materials, extract information from text-intensive image materials to obtain synonym key-value pairs; The VLM technology is used to process non-text-intensive image materials, and information is extracted from the non-text-intensive image materials to obtain synonym key-value pairs.

5. The disease name standardization method according to claim 1, characterized in that: The method for expanding the synonym conversion library includes: Build corresponding prompt templates based on ICD coding groups; Import the prompt template into the knowledge extraction model. Under the guidance of the prompt template, the knowledge extraction model completes the knowledge extraction of the disease corpus and uses the knowledge extraction results to construct the corresponding synonym conversion key-value pairs. The synonym conversion key-value pair is added to the synonym conversion library.

6. The method for standardizing disease names according to claim 1, wherein: The step of determining the standard disease name with the highest matching degree as the target standard disease name includes: Determine whether the number of standard disease names that have the highest matching degree with the disease name to be standardized after the synonym conversion is unique; If the number of standard disease names with the highest matching degree with the to-be-standardized disease name after the synonym conversion is unique, the unique standard disease name with the highest matching degree with the to-be-standardized disease name after the synonym conversion is determined as the target standard disease name; If the number of standard disease names that have the highest matching degree with the disease name to be standardized after synonym conversion is not unique, the standard disease name with the shortest length is selected from multiple standard disease names that have the highest matching degree with the disease name to be standardized after synonym conversion and determined as the target standard disease name.

7. The method for standardizing disease names according to claim 6, characterized in that: The step of selecting the shortest standard disease name from among the plurality of standard disease names that have the highest matching degree with the disease name to be standardized after the synonym conversion, and determining the shortest standard disease name as the target standard disease name, includes: Determine whether the number of standard disease names that have the highest matching degree and the shortest length with the disease name to be standardized after synonym conversion is unique; If the number of standard disease names with the highest matching degree and the shortest length with the disease name to be standardized after the synonym conversion is unique, then the unique standard disease name with the highest matching degree and the shortest length with the disease name to be standardized after the synonym conversion is determined as the target standard disease name; If the number of standard disease names with the highest matching degree and the shortest length with the disease name to be standardized after synonym conversion is not unique, all standard disease names with the highest matching degree and the shortest length with the disease name to be standardized after synonym conversion are determined as the target standard disease names.

8. A disease name standardization device, characterized in that: include: An acquisition module is used to obtain the name of the disease to be standardized; The first matching module is used to search the ICD code catalog for a target standardized disease name that completely matches the disease name to be standardized; The second matching module is used to replace the disease name to be standardized with a synonym using a synonym replacement library if a target standard disease name that completely matches the disease name to be standardized is not found in the ICD code directory, and then search the ICD code directory for a target standard disease name that completely matches the disease name to be standardized after the synonym replacement; The third matching module is used to perform synonym conversion on the disease name to be standardized using the synonym conversion library if the target standard disease name that completely matches the disease name to be standardized after the synonym replacement is not found in the ICD code directory, and then search for the target standard disease name that completely matches the disease name to be standardized after the synonym replacement in the ICD code directory; The fourth matching module is used for, if a target standard disease name that completely matches the disease name to be standardized after synonym conversion is not found in the ICD coding directory, to match the disease name to be standardized after synonym conversion with the standard disease name in the ICD coding directory in an unordered manner, and to calculate the matching degree between each standard disease name in the ICD coding directory and the disease name to be standardized after synonym conversion, and to determine the standard disease name with the highest matching degree as the target standard disease name; A mapping association module is used to associate the disease name to be standardized with the target standard disease name and its corresponding code.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the disease name standardization method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, characterized in that: When the computer program is executed by a processor, the steps of the disease name standardization method as described in any one of claims 1 to 7 are implemented.

Images