Disease name standardization method and device

Abstract

The present application relates to artificial intelligence, and provides a method and device for standardizing disease names, the method comprising: obtaining a target dictionary, a current diagnosis text, and a preset ICD standard disease name set, performing a word segmentation operation on the current diagnosis text based on the target dictionary, obtaining the disease name to be standardized, and constructing a target dictionary tree based on the preset ICD standard disease name set; based on the target dictionary tree, matching the disease name to be standardized with multiple preset ICD standard disease names in the preset ICD standard disease name set to obtain multiple first matching degrees, and when there is a target first matching degree that meets the preset conditions among the multiple first matching degrees, obtaining the target preset ICD standard disease name corresponding to the target first matching degree, and determining the target preset ICD standard disease name as the conversion result of the disease name to be standardized, so as to improve the conversion efficiency and accuracy. In addition, the present invention also relates to blockchain technology, and data can be stored in blockchain nodes.

Description

Technical Field

[0001] The present application relates to the technical field of disease name standardization based on artificial intelligence, and specifically to a disease name standardization method and device. Background Art

[0002] In recent years, with the vigorous development of smart medical care, smart medical technology based on big data has higher and higher requirements for data quality, and the name of the diagnosed disease, as an important feature, plays an important role in the field of medical research. However, different doctors in the hospital have different writing habits, and it is often difficult to reach a unified name for the same disease. Therefore, how to quickly and effectively extract the doctor's diagnosed disease name from the medical record has become a problem that needs to be solved. Summary of the invention

[0003] The embodiments of the present application provide a method and device for standardizing disease names, which are beneficial to improving the efficiency of disease name standardization.

[0004] The first aspect of the embodiment of the present application provides a disease name standardization method, which is applied to a server and includes:

[0005] Acquire a target dictionary, a current diagnosis text, and a preset ICD (International Classification of Diseases) standard disease name set, wherein the preset ICD standard disease name set includes a plurality of preset ICD standard disease names;

[0006] Based on the target dictionary, a word segmentation operation is performed on the current diagnosis text to obtain the disease name to be standardized contained in the current diagnosis text;

[0007] Based on the preset ICD standard disease name set, construct a target dictionary tree;

[0008] Based on the target dictionary tree, matching the disease name to be standardized with the multiple preset ICD standard disease names in the preset ICD standard disease name set to obtain multiple first matching degrees;

[0009] When there is a target first matching degree that meets the preset conditions among the multiple first matching degrees, the target preset ICD standard disease name corresponding to the target first matching degree is obtained, and the target preset ICD standard disease name is determined as the conversion result of the disease name to be standardized.

[0010] The second aspect of the embodiment of the present application provides a disease name standardization device, which is applied to a server. The device includes: an acquisition unit, a word segmentation unit, a construction unit, a matching unit and a determination unit, wherein:

[0011] The acquisition unit is used to acquire a target dictionary, a current diagnosis text, and a preset ICD standard disease name set, wherein the preset ICD standard disease name set includes a plurality of preset ICD standard disease names;

[0012] The word segmentation unit is used to perform a word segmentation operation on the current diagnosis text based on the target dictionary to obtain the disease name to be standardized contained in the current diagnosis text;

[0013] The construction unit is used to construct a target dictionary tree based on the preset ICD standard disease name set;

[0014] The matching unit is used to match the disease name to be standardized with the multiple preset ICD standard disease names in the preset ICD standard disease name set based on the target dictionary tree to obtain multiple first matching degrees;

[0015] The determination unit is used to obtain the target preset ICD standard disease name corresponding to the target first matching degree when there is a target first matching degree that meets the preset conditions among the multiple first matching degrees, and determine the target preset ICD standard disease name as the conversion result of the disease name to be standardized.

[0016] A third aspect of an embodiment of the present application provides a server, comprising a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method described in the first aspect of the embodiment of the present application.

[0017] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, comprising a data storage area and a program storage area, the data storage area stores data created according to the use of a blockchain node, and the program storage area stores a computer program, wherein the computer program includes program instructions, and the program instructions, when executed by a processor, perform some or all of the steps described in the first aspect of the embodiment of the present application.

[0018] A fifth aspect of the embodiments of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package.

[0019] Implementing the embodiments of the present application has at least the following beneficial effects:

[0020] Through the embodiment of the present application, the method is applied to a server, and includes: obtaining a target dictionary, a current diagnosis text, and a preset ICD standard disease name set, wherein the preset ICD standard disease name set includes multiple preset ICD standard disease names, performing a word segmentation operation on the current diagnosis text based on the target dictionary to obtain the disease name to be standardized contained in the current diagnosis text, and constructing a target dictionary tree based on the preset ICD standard disease name set, and matching the disease name to be standardized with multiple preset ICD standard disease names in the preset ICD standard disease name set based on the target dictionary tree to obtain multiple first matching degrees, and when there is a target first matching degree that meets the preset conditions among the multiple first matching degrees, obtaining the target preset ICD standard disease name corresponding to the target first matching degree, and determining the target preset ICD standard disease name as the conversion result of the disease name to be standardized. In this way, the current diagnosis text can be segmented through the target dictionary to reduce the problems of colloquialism, typos, omissions, abbreviations, etc. existing in the current diagnosis text. In addition, based on the target dictionary tree constructed based on the preset ICD standard disease name set, multiple preset ICD standard disease names are matched with the names to be standardized to obtain a conversion structure, which is conducive to improving conversion efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1A A structural schematic diagram of a disease name standardization method is provided for an embodiment of the present application;

[0023] Figure 1B A flowchart of a disease name standardization method is provided for an embodiment of the present application;

[0024] Figure 1C A structural schematic diagram of a method for extracting disease names to be standardized is provided for an embodiment of the present application;

[0025] Figure 1D A schematic diagram of the structure of a target dictionary tree is provided for an embodiment of the present application;

[0026] Figure 2 A flowchart of a disease name standardization method is provided for an embodiment of the present application;

[0027] Figure 3 A flowchart of a disease name standardization method is provided for an embodiment of the present application;

[0028] Figure 4 A schematic diagram of the structure of a server is provided for an embodiment of the present application;

[0029] Figure 5 A structural schematic diagram of a disease name standardization device is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0031] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0032] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0033] In order to better understand the embodiments of the present application, the method of applying the embodiments of the present application will be introduced below.

[0034] The disease name standardization system mentioned in the embodiments of the present application may include but is not limited to a background server, a component server, a cloud server, a service system server or a software server, etc. The above are only examples and not exhaustive, including but not limited to the above devices.

[0035] See also Figure 1A , Figure 1AIt is a structural diagram of a disease name standardization method provided in an embodiment of the present application. Based on the structural diagram, a target dictionary, a current diagnosis text and a preset ICD standard disease name set can be obtained. The preset ICD standard disease name set includes multiple preset ICD standard disease names. Then, based on the target dictionary, a word segmentation operation can be performed on the current diagnosis text to obtain the disease name to be standardized contained in the current diagnosis text, and based on the preset ICD standard disease name set, a target dictionary tree is constructed. Based on the target dictionary tree, the disease name to be standardized is matched with multiple preset ICD standard disease names in the preset ICD standard disease name set to obtain multiple first matching degrees. Finally, when there is a target first matching degree that meets the preset conditions among the multiple first matching degrees, the target preset ICD standard disease name corresponding to the target first matching degree is obtained, and the target preset ICD standard disease name is determined as the conversion result of the disease name to be standardized.

[0036] It can be seen that through a disease name standardization method provided in an embodiment of the present application, the current diagnosis text can be segmented through the target dictionary to reduce the problems of colloquialism, typos, omissions, abbreviations, etc. existing in the current diagnosis text. In addition, a target dictionary tree constructed based on a preset ICD standard disease name set matches multiple preset ICD standard disease names with the names to be standardized to obtain a conversion structure, which is conducive to improving conversion efficiency and accuracy.

[0037] See also Figure 1B , Figure 1B : is a flow chart of a disease name standardization method provided in an embodiment of the present application, which is applied to a server. The method comprises the following steps:

[0038] 101. Obtain a target dictionary, a current diagnosis text, and a preset ICD standard disease name set, wherein the preset ICD standard disease name set includes a plurality of preset ICD standard disease names.

[0039] The embodiment of the present application can be applied to a server, which may include: Figure 1A In the disease name standardization system shown, the above-mentioned target dictionary can be obtained by data processing of multiple historical disease diagnosis cases of multiple patients stored in the historical disease case library, and the target dictionary may include multiple historical disease names; the above-mentioned preset ICD standard disease name set can be set by the user or by system default, and the preset ICD standard disease name set may include multiple preset ICD standard disease names. The above-mentioned current diagnosis text may refer to the diagnosis text corresponding to the construction of any new disease case mentioned above or the diagnosis text that needs to be standardized for the disease name. The current diagnosis text may include at least one of the following: prescription information, diagnosis information, symptom description information, discharge summary information, hospital information, department information, patient information, etc., which are not limited here.

[0040] In a possible example, before the above step 101, before obtaining the target dictionary, the following steps may also be included:

[0041] A1. Extract historical diagnosis text information from the historical medical case database;

[0042] A2. Perform data cleaning on the historical diagnosis text information to obtain a historical disease name set;

[0043] A3. Process the historical disease name set and the preset ICD standard disease name set to obtain the target dictionary.

[0044] Among them, the above-mentioned historical medical case library can store multiple historical medical diagnosis cases of multiple patients, and the historical diagnosis cases may include at least one of the following: admission diagnosis information and discharge diagnosis information, etc., which are not limited here. In addition, the admission diagnosis information and the discharge diagnosis information may include at least one of the following: prescription information, diagnosis information, symptom description information, discharge summary information, hospital information, department information, patient information, etc., which are not limited here; the above-mentioned prescription information may include at least one of the following: disease name, disease symptoms, drug name, drug dosage, etc., which are not limited here.

[0045] In a specific implementation, multiple historical case diagnosis cases can be extracted from the historical medical case library, and historical diagnosis text information can be extracted therefrom. After obtaining the historical diagnosis text information, the historical diagnosis text information can be cleaned according to preset rules to obtain a historical disease name set. In addition, the preset rules can be set by the user or by system default, and are not limited here. For example, the above historical diagnosis text information can be eliminated to eliminate unnecessary fields (for example, fields that are not disease names). Then, the missing fields in the above historical diagnosis text information can be supplemented or modified based on empirical knowledge. Finally, a historical disease name set can be obtained. The historical disease name set may include multiple disease names corresponding to multiple historical medical diagnosis cases. Further, the historical disease name set and the preset ICD standard disease name set can be processed. In this way, an expanded target dictionary can be obtained, which may include multiple disease names. Using preset preset rules to clean the data is conducive to alleviating the inaccuracy and incompleteness of the extraction using rules. In addition, the extracted disease names do not need to be manually corrected, which is conducive to saving labor costs.

[0046] In a possible example, the above step A2, performing data cleaning on the historical diagnosis text information to obtain a historical disease name set, may include the following steps:

[0047] A21. Obtain multiple preset regular expressions for multiple preset disease names, wherein each preset disease name corresponds to a preset regular expression;

[0048] A22, matching the historical diagnosis text information with each of the plurality of preset regular expressions respectively to obtain a plurality of second matching degrees, each of the preset regular expressions corresponding to a second matching degree;

[0049] A23. Determine at least one preset disease name corresponding to at least one second matching degree that exceeds the first preset threshold among the multiple second matching degrees, and use the at least one preset disease name as the disease name set.

[0050] Among them, the above-mentioned first preset threshold can be set by the user or by the system default, which is not limited here. A plurality of preset disease names can be pre-stored in the server, and a regular expression can be preset for each preset disease name. The above-mentioned preset regular expression can be composed of ordinary characters and metacharacters. The preset regular expression can reflect the logical relationship between each character of the corresponding preset disease name. Since the above-mentioned historical diagnosis text information may contain a large number of colloquial, repetitive names or some abbreviations and typos, different preset regular expressions can be pre-set according to the characteristics of the word formation corresponding to the medical terms. For example, it can be formulated according to the separators contained in the corresponding disease names in practice, such as "(%s\s*\d+)|(%s\s*(\s*\d+)", etc. In this way, the above-mentioned diagnosis text information can be cleaned according to the preset regular expression, and meaningless characters and repeated names in the data can be eliminated to obtain a disease name set containing complete disease names.

[0051] In a specific implementation, the historical diagnostic text information can be matched with each preset regular expression respectively to perform logical filtering on the historical diagnostic text information to obtain multiple second matching degrees. Each preset regular expression can correspond to a second matching degree. Then, at least one preset disease name corresponding to at least one second matching degree greater than the first preset threshold can be screened out from the multiple second matching degrees, and the at least one preset disease name can be used as a disease name set. In this way, a complete and reliable disease name set can be obtained.

[0052] In a possible example, the above step A3, performing data processing on the historical disease name set and the preset ICD standard disease name set to obtain a target dictionary, may include the following steps:

[0053] A31, merging the disease name set with the preset ICD standard disease name set to obtain a first dictionary, wherein the first dictionary includes a plurality of first disease names;

[0054] A32. Remove duplicates from the multiple first disease names to obtain the target dictionary.

[0055] Among them, the above-mentioned preset ICD standard disease name set can be set by the user or by system default. The preset ICD standard disease name set may include multiple preset ICD standard disease names. The representation method of the preset ICD standard disease name can be determined based on certain characteristics of multiple diseases. For example, diseases can be classified according to certain rules, and the disease names can be represented by coding methods. In order to expand the dictionary corresponding to the disease names and provide more practical data, the above-mentioned disease name set and the preset ICD standard disease name set can be processed to obtain the expanded target dictionary. The target dictionary can still include multiple preset ICD standard disease names. This is also conducive to improving the accuracy of word segmentation of the new diagnostic text (current diagnostic text).

[0056] In a specific implementation, the above-mentioned disease name set can be merged with the above-mentioned preset ICD standard disease name set to obtain a first dictionary, and then the same and repeated first disease names in the first dictionary are removed to finally obtain the above-mentioned target dictionary.

[0057] like Figure 1C The figure is a structural diagram of a method for extracting disease names to be standardized. As shown in the figure, historical diagnosis text information can be extracted from the historical medical case library, and the historical diagnosis text information can be cleaned to obtain a historical disease name set. The historical disease name set and the preset ICD standard disease name set are processed to obtain a target dictionary, and the current diagnosis text is obtained. Based on the target dictionary, the current diagnosis text is segmented to obtain the disease names to be standardized contained in the current diagnosis text. In this way, the current diagnosis text can be segmented through the target dictionary to reduce the problems of colloquialism, typos, omissions, abbreviations, etc. in the current diagnosis text. The extracted disease names do not need to be manually corrected, which is conducive to saving labor costs.

[0058] 102. Based on the target dictionary, perform a word segmentation operation on the current diagnosis text to obtain the disease names to be standardized contained in the current diagnosis text.

[0059] Among them, since there may be a large number of colloquial, repetitive names or some abbreviated names in the current diagnosis text, the current diagnosis text can be segmented based on the target dictionary obtained by processing the historical diagnosis information in the historical medical case library to obtain the disease name to be standardized contained in the current diagnosis text. The current diagnosis text can be any new diagnosis text. In this way, based on the target dictionary, the disease name can be extracted from the current diagnosis text more quickly, which can effectively solve the inaccuracy and incompleteness of the extraction using rules. In this way, the extracted disease name does not need to be manually corrected, which is conducive to improving efficiency.

[0060] In a specific implementation, based on the target dictionary, the current diagnostic text is segmented, and obtaining the disease name to be standardized contained in the current diagnostic text may include the following steps: based on the above-mentioned target dictionary, statistics can be performed with the corresponding words in the target dictionary as units, and the frequency of occurrence of each word in the current diagnostic text can be counted. That is to say, when any sentence to be segmented appears in the current diagnostic text, all possible segmentation results are counted, and the segmentation result with the highest probability is used as the above-mentioned disease name to be standardized.

[0061] 103. Construct a target dictionary tree based on the preset ICD standard disease name set.

[0062] Among them, the above-mentioned preset ICD standard disease name set may include multiple preset ICD standard disease names. When a new diagnostic text appears, in order to facilitate matching with the text information in the target dictionary, or to find the preset ICD standard disease name in the preset ICD standard disease name set, the server can construct a target dictionary tree based on the above-mentioned preset ICD standard disease name set. The target dictionary tree can be understood as a dictionary tree constructed by any one or more character strings, which is used to store the character strings in the above-mentioned preset ICD standard disease name set.

[0063] In a possible example, the above step 103, constructing a target dictionary tree based on the preset ICD standard disease name set, may include the following steps:

[0064] 31. Based on the preset ICD standard disease name set, determine a first sequence corresponding to each preset ICD standard disease name in a plurality of preset ICD standard disease names in the preset ICD standard disease name set to obtain a plurality of first sequences, wherein each first sequence includes at least one character;

[0065] 32. Obtain a preset dictionary tree, wherein the preset dictionary tree includes a plurality of nodes;

[0066] 33. Traverse the multiple first sequences, match each of the first sequences with multiple nodes corresponding to the preset dictionary tree, and obtain multiple third matching degrees;

[0067] 34. Calculate the average of the plurality of third matching degrees;

[0068] 35. If the mean is greater than a second preset threshold, the preset dictionary tree is not updated, and the preset dictionary tree is used as the target dictionary tree;

[0069] 36. If the mean is less than or equal to the second preset threshold, update the preset dictionary tree to obtain the target dictionary tree.

[0070] Among them, the above-mentioned second preset threshold can be set by the user or by the system default, which is not limited here. The above-mentioned preset dictionary tree can be set by the user or by the system default, which is not limited here. The preset dictionary tree can be understood as the initial dictionary tree, which is a dictionary tree that has not yet stored multiple character strings in the preset ICD standard disease name set. The preset dictionary tree may include multiple nodes, each node may correspond to a character. When constructing the preset dictionary tree, it can be generated based on the International Classification of Diseases ICD code. For example, the preset dictionary tree can be a two-layer structure, the first layer is the major disease category, such as A00. (cholera), and the second layer is the disease name contained in the major category, such as A00.0 (typical cholera) and so on.

[0071] In a specific implementation, the first sequence corresponding to each preset ICD standard disease name in the corresponding multiple preset ICD standard disease names can be determined according to the preset ICD standard disease name set to obtain multiple first sequences, wherein each first sequence includes at least one character, which may include two types of text characters and special characters; further, based on the preset dictionary tree, each first sequence corresponding to the above multiple first sequences can be traversed, and the above multiple first sequences can be matched one by one with the multiple nodes corresponding to the above preset dictionary tree. If the match is successful, the above preset dictionary tree will not be updated. If the match fails, the above preset dictionary tree will be updated to obtain the target dictionary tree. In this way, the above preset dictionary tree can be expanded step by step to convert the preset ICD standard disease name set into the target dictionary tree, which is conducive to improving the efficiency of subsequent disease name standardization. It should be noted that the target dictionary tree can also be constructed in advance based on the preset ICD standard disease name set. In this way, when the server obtains the current diagnosis text, the subsequent disease name standardization steps can be directly performed based on the target dictionary tree.

[0072] Furthermore, when traversing each of the multiple first sequences, multiple third matching degrees can be obtained, and the average of the multiple third matching degrees can be calculated. If the average is greater than the second preset threshold, the match is considered to be successful and the above-mentioned preset dictionary tree is not updated. On the contrary, if the average is less than or equal to the second preset threshold, the match is considered to have failed, and the above-mentioned preset dictionary tree can be updated to obtain the target dictionary tree.

[0073] In addition, the step of gradually updating the preset dictionary tree can also be performed during the traversal process. A third preset threshold can be preset in the server, and the third preset threshold can be set by the user or by the system default. If the third matching degree is greater than the third preset threshold, it can be considered that the corresponding first sequence matches the node in the preset dictionary tree successfully, that is, if the match is successful, the preset dictionary tree will not be updated. If the third matching degree is less than or equal to the third preset threshold, it can be considered that the corresponding first sequence matches the node in the preset dictionary tree unsuccessfully, and the preset dictionary tree can be updated based on the corresponding first node. In this way, the above-mentioned first sequence is traversed step by step, and the above-mentioned method is used cyclically to gradually update the above-mentioned preset dictionary tree to obtain the target dictionary tree.

[0074] In a possible example, the above step 36, updating the preset dictionary tree to obtain the target dictionary tree, may include the following steps:

[0075] 361. Based on the preset dictionary tree, determine the initial mappings corresponding to the multiple nodes in the preset dictionary tree;

[0076] 362. If a character i corresponding to the first sequence i does not exist in the initial mapping, add a new mapping i, save the character i in the mapping i, and update the initial mapping to the mapping i, wherein the first sequence i is any one of the multiple first sequences, and the character i is any one of the first sequences;

[0077] 363. Based on the mapping i, update the preset dictionary tree to the target dictionary tree.

[0078] Among them, since the above steps are based on the average of multiple third matching degrees corresponding to multiple first sequences to determine whether the preset dictionary tree needs to be updated, it is not clear which specific node of the preset dictionary tree needs to be updated. Therefore, when updating, a judgment can be made based on each first sequence to gradually update the above preset dictionary tree. This is conducive to improving the accuracy of constructing the target dictionary tree.

[0079] In a specific implementation, the server may determine the initial mapping corresponding to the preset dictionary tree based on the preset dictionary tree. The initial mapping may be the initial path corresponding to the preset dictionary tree. The initial path indicates the mapping relationship between every two nodes in the preset dictionary tree, and also reflects the mapping relationship between each node in the preset dictionary tree and the corresponding stored information. If there is a situation where any character i corresponding to the first sequence i does not exist in the initial mapping corresponding to the above multiple nodes, then based on the above initial mapping, a new mapping i is added to save the character i. At this time, the preset dictionary tree is updated to the first dictionary tree. At the same time, based on the mapping i, the above initial mapping can also be updated to the first mapping including the mapping i, wherein the character i is any character in the above first sequence, and the above first sequence i is any one of multiple first sequences. In this way, the above steps can be repeated for other characters in the first sequence to gradually update the first mapping. Finally, the above steps can be performed for all first sequences to gradually update the first mapping. When all the characters in the first sequence are traversed, the target dictionary tree can be obtained.

[0080] as follows Figure 1D As shown, it is a structural schematic diagram of a target dictionary tree, which can be constructed based on a preset ICD standard disease name set. As shown in the figure, the target dictionary tree shown in the figure can be constructed based on preset ICD standard disease names such as "amoebic enteritis", "amoebiasis", "amoebic dysentery", "Addison's disease" and "Alzheimer's disease". The solid circle represents the end node of a disease name path.

[0081] 104. Based on the target dictionary tree, the disease name to be standardized is matched with the multiple preset ICD standard disease names in the preset ICD standard disease name set to obtain multiple first matching degrees.

[0082] Among them, after obtaining the name of the disease to be standardized, the disease name to be standardized can be matched and searched based on the above-mentioned target dictionary tree to obtain the ICD standard disease name corresponding to the disease name to be standardized. That is to say, the disease name to be standardized can be matched with multiple preset ICD standard disease names in the preset ICD standard disease name set to obtain multiple first matching degrees, and the conversion result of the disease name to be standardized can be obtained based on the multiple first matching degrees.

[0083] In a possible example, the above step 104, matching the disease name to be standardized with the multiple preset ICD standard disease names in the preset ICD standard disease name set to obtain multiple first matching degrees, may include the following steps:

[0084] 41. Determine a target mapping table corresponding to the target dictionary tree, wherein the target mapping table contains a plurality of preset paths, and each disease name in the target dictionary tree corresponds to a preset path;

[0085] 42. Based on the target dictionary tree, starting from character j, search downward in sequence according to the head node corresponding to the target dictionary tree to obtain the path j to be matched and the preset path j corresponding to the path to be matched in the target mapping table, wherein the character j is the first character in the disease name to be standardized;

[0086] 43. Match the to-be-matched path j with the preset path j to obtain a first matching degree j of the character j.

[0087] Among them, the server can determine the target mapping table corresponding to the target dictionary tree, which may include a preset path corresponding to each disease name in the target dictionary tree. Furthermore, based on the target dictionary tree, starting from the first character j of the disease name to be standardized, the server can search downward from the head node corresponding to the above target dictionary tree in sequence to obtain the path j to be matched and the preset path j corresponding to the path to be matched in the mapping table, and match the path j to be matched with the preset path j to obtain a first matching degree, and so on, until each character corresponding to the disease name to be standardized has completed the cycle in each path corresponding to the above target dictionary tree, and multiple first matching degrees are obtained.

[0088] 105. When there is a target first matching degree that meets the preset conditions among the multiple first matching degrees, obtain the target preset ICD standard disease name corresponding to the target first matching degree, and determine the target preset ICD standard disease name as the conversion result of the disease name to be standardized.

[0089] Among them, the above-mentioned preset conditions can be set by the user or by system default, and are not limited here. For example, it can be set that when the first matching degree is 100%, it can be determined that the match is successful. When the match is successful, the preset ICD standard disease name corresponding to the target first matching degree that meets the preset conditions is determined to be the conversion result of the disease name to be standardized, otherwise the match fails.

[0090] Optionally, if the disease name to be standardized is matched with multiple preset ICD standard disease names in the preset ICD standard disease name set based on the above-mentioned target dictionary tree, if the characters corresponding to the disease name to be standardized cannot be completely matched in the above-mentioned target dictionary tree, that is, the above-mentioned preset conditions are not met, the server may match the disease name to be standardized with multiple preset ICD standard disease names in the above-mentioned preset ICD standard disease name set based on the path similarity and semantic similarity of the target dictionary tree to obtain the conversion result of the disease name to be standardized. In this way, when the characters corresponding to the disease name to be standardized are not completely matched in the above-mentioned target dictionary tree, the conversion of the disease name to be standardized can still be achieved, which is conducive to improving the matching accuracy.

[0091] In a specific implementation, the target dictionary tree may include a root node, and the second sequence corresponding to the disease name to be standardized can be determined; traversal is started with the root node corresponding to the target dictionary tree as the starting point to obtain multiple second paths matched by the second sequence in the target dictionary tree; the semantic similarities corresponding to the multiple second paths are calculated to obtain multiple semantic similarities; the second path corresponding to the maximum value of the multiple semantic similarities is selected as the target path; and the character corresponding to the target path in the target dictionary tree is determined to be the conversion result of the disease name to be standardized.

[0092] The calculation of the semantic similarities corresponding to the plurality of second paths may be performed using the following formula:

[0093] X = a × X1 + b × X2;

[0094]

[0095] Among them, wi=(a1,a2,…,an), wj=(b1,b2,…,bn), n is the word vector dimension. The above X1 represents the path length corresponding to each second path, which can also be understood as the depth of each traversal. The above a and b are real numbers, and the weights of X1 and X2 in calculating semantic similarity can be adjusted by adjusting the values ​​of a and b.

[0096] In addition, when traversing from the root node corresponding to the above-mentioned target dictionary tree as the starting point, and obtaining multiple second paths matched by the above-mentioned second sequence in the above-mentioned target dictionary tree, the following steps may be included: taking the root node as the starting point, selecting a path m (m is a positive integer) as the current subtree, and the path m is any path starting from the root node; searching for the first character corresponding to the above-mentioned disease name to be standardized in any layer corresponding to the current subtree, if the character is found, then searching for the second character corresponding to the above-mentioned disease name to be standardized in the next layer of the above-mentioned any layer, and thus, repeating the search for the third character corresponding to the above-mentioned disease name to be standardized, if the third character is not found in the above-mentioned current subtree, then selecting another path except the path m to repeat the above steps for traversal, and thus, multiple second paths may be obtained, and the second path may or may not completely include all the characters corresponding to the above-mentioned disease name to be standardized. In this way, the matching method that combines path similarity and semantic similarity through the above-mentioned method is conducive to improving the matching accuracy, so as to quickly convert the disease name to be standardized into a standardized disease name.

[0097] It can be seen that the disease name standardization method described in the embodiment of the present application is applied to the server, and the present invention can be applied to the field of smart medical care, thereby promoting the construction of smart cities. The above method includes: obtaining a target dictionary, a current diagnosis text and a preset ICD standard disease name set, the preset ICD standard disease name set includes multiple preset ICD standard disease names, based on the target dictionary, performing a word segmentation operation on the current diagnosis text to obtain the disease name to be standardized contained in the current diagnosis text, based on the preset ICD standard disease name set, constructing a target dictionary tree, based on the target dictionary tree, matching the disease name to be standardized with multiple preset ICD standard disease names in the preset ICD standard disease name set to obtain multiple first matching degrees, when there is a target first matching degree that meets the preset conditions among the multiple first matching degrees, obtaining the target preset ICD standard disease name corresponding to the target first matching degree, and determining the target preset ICD standard disease name as the conversion result of the disease name to be standardized. In this way, the current diagnosis text can be segmented through the target dictionary to reduce the problems of colloquialism, typos, omissions, abbreviations, etc. existing in the current diagnosis text. In addition, based on the target dictionary tree constructed by the preset ICD standard disease name set, multiple preset ICD standard disease names are matched with the names to be standardized to obtain a conversion structure, which is conducive to improving conversion efficiency and accuracy.

[0098] Consistent with the above, see Figure 2 , Figure 2 This is a flow chart of a disease name standardization method disclosed in an embodiment of the present application, which is applied to a server. The disease name standardization method may include the following steps:

[0099] 201. Obtain a preset ICD standard disease name set, wherein the preset ICD standard disease name set includes multiple preset ICD standard disease names.

[0100] 202. Extract historical diagnosis text information from the historical medical case library.

[0101] 203. Perform data cleaning on the historical diagnosis text information to obtain a historical disease name set.

[0102] 204. Perform data processing on the historical disease name set and the preset ICD standard disease name set to obtain the target dictionary.

[0103] 205. Get the current diagnosis text.

[0104] 206. Based on the target dictionary, perform a word segmentation operation on the current diagnosis text to obtain the disease names to be standardized contained in the current diagnosis text.

[0105] 207. Construct a target dictionary tree based on the preset ICD standard disease name set.

[0106] 208. Based on the target dictionary tree, match the disease name to be standardized with the multiple preset ICD standard disease names in the preset ICD standard disease name set to obtain multiple first matching degrees.

[0107] 209. When there is a target first matching degree that meets the preset conditions among the multiple first matching degrees, obtain the target preset ICD standard disease name corresponding to the target first matching degree, and determine the target preset ICD standard disease name as the conversion result of the disease name to be standardized.

[0108] The disease name standardization method described in the above steps 201 to 209 can be referred to Figure 1B Corresponding steps of the described disease name standardization method.

[0109] It can be seen that the disease name standardization method described in the embodiment of the present application obtains a preset ICD standard disease name set, the preset ICD standard disease name set includes multiple preset ICD standard disease names, extracts historical diagnosis text information from a historical medical case library, performs data cleaning on the historical diagnosis text information, obtains a historical disease name set, performs data processing on the historical disease name set and the preset ICD standard disease name set to obtain a target dictionary, obtains the current diagnosis text, performs a word segmentation operation on the current diagnosis text based on the target dictionary, obtains the disease name to be standardized contained in the current diagnosis text, constructs a target dictionary tree based on the preset ICD standard disease name set, and matches the disease name to be standardized with multiple preset ICD standard disease names in the preset ICD standard disease name set based on the target dictionary tree. Matching is performed to obtain multiple first matching degrees. When there is a target first matching degree that meets the preset conditions among the multiple first matching degrees, the target preset ICD standard disease name corresponding to the target first matching degree is obtained, and the target preset ICD standard disease name is determined as the conversion result of the disease name to be standardized. In this way, the historical diagnosis text in the historical medical condition library can be subjected to a series of processing to obtain an expanded target dictionary that is more suitable for practical applications, and the current diagnosis text is segmented through the target dictionary to reduce the problems of colloquialism, typos, omissions, abbreviations, etc. in the current diagnosis text. In addition, based on the target dictionary tree constructed based on the preset ICD standard disease name set, multiple preset ICD standard disease names are matched with the names to be standardized to obtain a conversion structure, which is conducive to improving conversion efficiency and accuracy.

[0110] Consistent with the above, see Figure 3 , Figure 3 This is a flow chart of a disease name standardization method disclosed in an embodiment of the present application, which is applied to a server. The disease name standardization method may include the following steps:

[0111] 301. Obtain a target dictionary, a current diagnosis text, and a preset ICD standard disease name set, wherein the preset ICD standard disease name set includes a plurality of preset ICD standard disease names;

[0112] 302. Based on the target dictionary, perform a word segmentation operation on the current diagnosis text to obtain the disease names to be standardized contained in the current diagnosis text.

[0113] 303. Based on the preset ICD standard disease name set, determine a first sequence corresponding to each preset ICD standard disease name in a plurality of preset ICD standard disease names in the preset ICD standard disease name set to obtain a plurality of first sequences, wherein each first sequence includes at least one character.

[0114] 304. Obtain a preset dictionary tree, where the preset dictionary tree includes multiple nodes.

[0115] 305. Traverse the multiple first sequences, match each of the first sequences with multiple nodes corresponding to the preset dictionary tree, and obtain multiple third matching degrees.

[0116] 306. Calculate an average of the multiple third matching degrees.

[0117] 307. If the mean is greater than a second preset threshold, the preset dictionary tree is not updated, and the preset dictionary tree is used as the target dictionary tree.

[0118] 308. If the mean is less than or equal to the second preset threshold, update the preset dictionary tree to obtain the target dictionary tree.

[0119] 309. Based on the target dictionary tree, the disease name to be standardized is matched with the multiple preset ICD standard disease names in the preset ICD standard disease name set to obtain multiple first matching degrees.

[0120] 310. When there is a target first matching degree that meets the preset conditions among the multiple first matching degrees, obtain the target preset ICD standard disease name corresponding to the target first matching degree, and determine the target preset ICD standard disease name as the conversion result of the disease name to be standardized.

[0121] The disease name standardization method described in the above steps 301 to 310 can be referred to Figure 1B Corresponding steps of the described disease name standardization method.

[0122] It can be seen that in the disease name standardization method described in the embodiment of the present application, the server can obtain a target dictionary, a current diagnosis text and a preset ICD standard disease name set, the preset ICD standard disease name set includes multiple preset ICD standard disease names, based on the target dictionary, perform a word segmentation operation on the current diagnosis text to obtain the disease name to be standardized contained in the current diagnosis text, based on the preset ICD standard disease name set, determine the first sequence corresponding to each preset ICD standard disease name in the multiple preset ICD standard disease names in the preset ICD standard disease name set, and obtain multiple first sequences, wherein each first sequence includes at least one character, obtain a preset dictionary tree, the preset dictionary tree includes multiple nodes, traverse the multiple first sequences, match each first sequence with multiple nodes corresponding to the preset dictionary tree, obtain multiple third matching degrees, calculate the average of the multiple third matching degrees, if the average is greater than the second preset threshold value, do not update the preset dictionary tree, and use the preset dictionary tree as The target dictionary tree, if the mean is less than or equal to the second preset threshold, updates the preset dictionary tree to obtain the target dictionary tree, based on the target dictionary tree, matches the disease name to be standardized with multiple preset ICD standard disease names in the preset ICD standard disease name set to obtain multiple first matching degrees, when there is a target first matching degree that meets the preset conditions among the multiple first matching degrees, obtains the target preset ICD standard disease name corresponding to the target first matching degree, and determines the target preset ICD standard disease name as the conversion result of the disease name to be standardized. In this way, the current diagnostic text can be segmented through the target dictionary to reduce the problems of colloquialism, typos, omissions, abbreviations, etc. in the current diagnostic text, and the preset ICD standard disease name set under the international standard is processed to obtain the target dictionary tree, based on the target dictionary tree, the disease name to be standardized is processed to obtain the conversion result of the disease name to be standardized, which is conducive to improving the conversion accuracy.

[0123] Consistent with the above, see Figure 4 , Figure 4 A schematic diagram of the structure of a server provided in an embodiment of the present application, such as Figure 4 As shown, it includes a processor, a communication interface, a memory and one or more programs, wherein the processor, the communication interface and the memory are connected to each other, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions, and the one or more programs include instructions for performing the following steps:

[0124] Acquire a target dictionary, a current diagnosis text, and a preset ICD standard disease name set, wherein the preset ICD standard disease name set includes a plurality of preset ICD standard disease names;

[0125] Based on the target dictionary, a word segmentation operation is performed on the current diagnosis text to obtain the disease name to be standardized contained in the current diagnosis text;

[0126] Based on the preset ICD standard disease name set, construct a target dictionary tree;

[0127] Based on the target dictionary tree, matching the disease name to be standardized with the multiple preset ICD standard disease names in the preset ICD standard disease name set to obtain multiple first matching degrees;

[0128] When there is a target first matching degree that meets the preset conditions among the multiple first matching degrees, the target preset ICD standard disease name corresponding to the target first matching degree is obtained, and the target preset ICD standard disease name is determined as the conversion result of the disease name to be standardized.

[0129] It can be seen that the server described in the embodiment of the present application can obtain a target dictionary, a current diagnosis text and a preset ICD standard disease name set, the preset ICD standard disease name set includes multiple preset ICD standard disease names, based on the target dictionary, the current diagnosis text is segmented to obtain the disease name to be standardized contained in the current diagnosis text, based on the preset ICD standard disease name set, a target dictionary tree is constructed, based on the target dictionary tree, the disease name to be standardized is matched with multiple preset ICD standard disease names in the preset ICD standard disease name set to obtain multiple first matching degrees, when there is a target first matching degree that meets the preset conditions among the multiple first matching degrees, the target preset ICD standard disease name corresponding to the target first matching degree is obtained, and the target preset ICD standard disease name is determined as the conversion result of the disease name to be standardized. In this way, the current diagnosis text can be segmented through the target dictionary to reduce the problems of colloquialism, typos, omissions, abbreviations, etc. in the current diagnosis text. In addition, based on the target dictionary tree constructed based on the preset ICD standard disease name set, multiple preset ICD standard disease names are matched with the names to be standardized to obtain a conversion structure, which is conducive to improving conversion efficiency and accuracy.

[0130] In a possible example, before obtaining the target dictionary, the processor is further configured to:

[0131] Extract historical diagnosis text information from the historical medical case database;

[0132] Performing data cleaning on the historical diagnosis text information to obtain a historical disease name set;

[0133] The historical disease name set and the preset ICD standard disease name set are processed to obtain the target dictionary.

[0134] In a possible example, in the aspect of performing data cleaning on the historical diagnosis text information to obtain a historical disease name set, the processor is specifically used to:

[0135] Obtain multiple preset regular expressions for multiple preset disease names, wherein each preset disease name corresponds to a preset regular expression;

[0136] Matching the historical diagnosis text information with each of the plurality of preset regular expressions respectively to obtain a plurality of second matching degrees, each of the preset regular expressions corresponding to a second matching degree;

[0137] At least one preset disease name corresponding to at least one second matching degree exceeding a first preset threshold among the plurality of second matching degrees is determined, and the at least one preset disease name is used as the disease name set.

[0138] In a possible example, in the aspect of performing data processing on the historical disease name set and the preset ICD standard disease name set to obtain a target dictionary, the processor is specifically used to:

[0139] Merging the disease name set with the preset ICD standard disease name set to obtain a first dictionary, wherein the first dictionary includes a plurality of first disease names;

[0140] The plurality of first disease names are deduplicated to obtain the target dictionary.

[0141] In a possible example, in the aspect of constructing the target dictionary tree based on the preset ICD standard disease name set, the processor is specifically used to:

[0142] Based on the preset ICD standard disease name set, determining a first sequence corresponding to each preset ICD standard disease name in a plurality of preset ICD standard disease names in the preset ICD standard disease name set, and obtaining a plurality of first sequences, wherein each first sequence includes at least one character;

[0143] Obtain a preset dictionary tree, wherein the preset dictionary tree includes a plurality of nodes;

[0144] Traversing the multiple first sequences, matching each of the first sequences with multiple nodes corresponding to the preset dictionary tree, and obtaining multiple third matching degrees;

[0145] Calculating the average of the plurality of third matching degrees;

[0146] If the mean is greater than a second preset threshold, the preset dictionary tree is not updated, and the preset dictionary tree is used as the target dictionary tree;

[0147] If the mean is less than or equal to the second preset threshold, the preset dictionary tree is updated to obtain the target dictionary tree.

[0148] In a possible example, in the updating of the preset dictionary tree to obtain the target dictionary tree, the processor is specifically configured to:

[0149] Based on the preset dictionary tree, determining initial mappings corresponding to the plurality of nodes in the preset dictionary tree;

[0150] If a character i corresponding to the first sequence i does not exist in the initial mapping, a new mapping i is added, and the character i is stored in the mapping i, wherein the first sequence i is any one of the multiple first sequences, the character i is any one of the first sequences, and i is a positive integer;

[0151] Based on the mapping i, the preset dictionary tree is updated to be the target dictionary tree.

[0152] In a possible example, in the aspect of matching the disease name to be standardized with the plurality of preset ICD standard disease names in the preset ICD standard disease name set to obtain a plurality of first matching degrees, the processor is specifically configured to:

[0153] Determine a target mapping table corresponding to the target dictionary tree, wherein the target mapping table has a plurality of preset paths, and each disease name in the target dictionary tree corresponds to a preset path;

[0154] Based on the target dictionary tree, starting from character j, searching downward in sequence according to the head node corresponding to the target dictionary tree, obtaining the path j to be matched and the preset path j corresponding to the path to be matched in the target mapping table, wherein the character j is the first character in the disease name to be standardized;

[0155] The to-be-matched path j is matched with the preset path j to obtain a first matching degree j of the character j.

[0156] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that, in order to realize the above functions, the server includes a hardware structure and / or software module corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0157] The embodiment of the present application can divide the server into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0158] Consistent with the above, see Figure 5 , Figure 5 : is a structural diagram of a disease name standardization device disclosed in an embodiment of the present application, which is applied to a server. The device includes: an acquisition unit 501, a word segmentation unit 502, a construction unit 503, a matching unit 504 and a determination unit 505, wherein:

[0159] The acquisition unit 501 is used to acquire a target dictionary, a current diagnosis text and a preset ICD standard disease name set, wherein the preset ICD standard disease name set includes a plurality of preset ICD standard disease names;

[0160] The word segmentation unit 502 is used to perform a word segmentation operation on the current diagnosis text based on the target dictionary to obtain the disease name to be standardized contained in the current diagnosis text;

[0161] The construction unit 503 is used to construct a target dictionary tree based on the preset ICD standard disease name set;

[0162] The matching unit 504 is used to match the disease name to be standardized with the multiple preset ICD standard disease names in the preset ICD standard disease name set based on the target dictionary tree to obtain multiple first matching degrees;

[0163] The determination unit 505 is used to obtain a target preset ICD standard disease name corresponding to the target first matching degree when there is a target first matching degree that meets the preset conditions among the multiple first matching degrees, and determine the target preset ICD standard disease name as the conversion result of the disease name to be standardized.

[0164] It can be seen that the disease name standardization device described in the embodiment of the present application is applied to a server, and the device can obtain a target dictionary, a current diagnosis text, and a preset ICD standard disease name set, wherein the preset ICD standard disease name set includes multiple preset ICD standard disease names, and based on the target dictionary, a word segmentation operation is performed on the current diagnosis text to obtain the disease name to be standardized contained in the current diagnosis text, and based on the preset ICD standard disease name set, a target dictionary tree is constructed, and based on the target dictionary tree, the disease name to be standardized is matched with multiple preset ICD standard disease names in the preset ICD standard disease name set to obtain multiple first matching degree When there is a target first match degree that meets the preset conditions among multiple first match degrees, the target preset ICD standard disease name corresponding to the target first match degree is obtained, and the target preset ICD standard disease name is determined as the conversion result of the disease name to be standardized. In this way, the current diagnosis text can be segmented through the target dictionary to reduce the problems of colloquialism, typos, omissions, abbreviations, etc. in the current diagnosis text. In addition, based on the target dictionary tree constructed based on the preset ICD standard disease name set, multiple preset ICD standard disease names are matched with the names to be standardized to obtain a conversion structure, which is conducive to improving conversion efficiency and accuracy.

[0165] In a possible example, in the aspect of constructing the target dictionary tree based on the preset ICD standard disease name set, the construction unit 503 is specifically used for:

[0166] Based on the preset ICD standard disease name set, determining a first sequence corresponding to each preset ICD standard disease name in a plurality of preset ICD standard disease names in the preset ICD standard disease name set, and obtaining a plurality of first sequences, wherein each first sequence includes at least one character;

[0167] Obtain a preset dictionary tree, wherein the preset dictionary tree includes a plurality of nodes;

[0168] Traversing the multiple first sequences, matching each of the first sequences with multiple nodes corresponding to the preset dictionary tree, and obtaining multiple third matching degrees;

[0169] Calculating the average of the plurality of third matching degrees;

[0170] If the mean is greater than a second preset threshold, the preset dictionary tree is not updated, and the preset dictionary tree is used as the target dictionary tree;

[0171] If the mean is less than or equal to the second preset threshold, the preset dictionary tree is updated to obtain the target dictionary tree.

[0172] In a possible example, in the updating of the preset dictionary tree to obtain the target dictionary tree, the construction unit 503 is further configured to:

[0173] Based on the preset dictionary tree, determining initial mappings corresponding to the plurality of nodes in the preset dictionary tree;

[0174] If a character i corresponding to the first sequence i does not exist in the initial mapping, a new mapping i is added, and the character i is stored in the mapping i, wherein the first sequence i is any one of the multiple first sequences, the character i is any one of the first sequences, and i is a positive integer;

[0175] Based on the mapping i, the preset dictionary tree is updated to be the target dictionary tree.

[0176] In a possible example, in the aspect of matching the disease name to be standardized with the plurality of preset ICD standard disease names in the preset ICD standard disease name set to obtain a plurality of first matching degrees, the matching unit 504 is specifically used to:

[0177] Determine a target mapping table corresponding to the target dictionary tree, wherein the target mapping table has a plurality of preset paths, and each disease name in the target dictionary tree corresponds to a preset path;

[0178] Based on the target dictionary tree, starting from character j, searching downward in sequence according to the head node corresponding to the target dictionary tree, obtaining the path j to be matched and the preset path j corresponding to the path to be matched in the target mapping table, wherein the character j is the first character in the disease name to be standardized;

[0179] The to-be-matched path j is matched with the preset path j to obtain a first matching degree j of the character j.

[0180] An embodiment of the present application also provides a computer-readable storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any disease name standardization method recorded in the above method embodiments.

[0181] 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.

[0182] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any disease name standardization method recorded in the above method embodiments.

[0183] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0184] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0185] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0186] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0187] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of a software program module.

[0188] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program codes.

[0189] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing the relevant hardware through a program, and the program may be stored in a computer-readable memory, which may include a flash drive, ROM, RAM, a magnetic disk or an optical disk, etc.

[0190] The blockchain referred to in the present invention is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the blockchain underlying platform, platform product service layer, and application service layer.

[0191] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for standardizing disease names, characterized in that: Applicable to servers, including: Extract historical diagnosis text information from the historical medical case database; Performing data cleaning on the historical diagnosis text information to obtain a historical disease name set; Processing the historical disease name set and the preset ICD standard disease name set to obtain a target dictionary, wherein the preset ICD standard disease name set includes a plurality of preset ICD standard disease names, and the target dictionary includes a plurality of historical disease names; Get the current diagnostic text; Based on the target dictionary, a word segmentation operation is performed on the current diagnosis text to obtain the disease name to be standardized contained in the current diagnosis text; Based on the preset ICD standard disease name set, determining a first sequence corresponding to each preset ICD standard disease name in a plurality of preset ICD standard disease names in the preset ICD standard disease name set, and obtaining a plurality of first sequences, wherein each first sequence includes at least one character; Obtain a preset dictionary tree, wherein the preset dictionary tree includes a plurality of nodes; Traversing the multiple first sequences, matching each of the first sequences with multiple nodes corresponding to the preset dictionary tree, and obtaining multiple third matching degrees; Calculating the average of the plurality of third matching degrees; If the mean is greater than a second preset threshold, the preset dictionary tree is not updated, and the preset dictionary tree is used as the target dictionary tree; If the mean is less than or equal to the second preset threshold, updating the preset dictionary tree to obtain the target dictionary tree; Based on the target dictionary tree, matching the disease name to be standardized with the multiple preset ICD standard disease names in the preset ICD standard disease name set to obtain multiple first matching degrees; When there is a target first matching degree that meets the preset conditions among the multiple first matching degrees, the target preset ICD standard disease name corresponding to the target first matching degree is obtained, and the target preset ICD standard disease name is determined as the conversion result of the disease name to be standardized.

2. The method according to claim 1, characterized in that: The historical diagnosis text information is cleaned to obtain a historical disease name set, including: Obtain multiple preset regular expressions for multiple preset disease names, wherein each preset disease name corresponds to a preset regular expression; Matching the historical diagnosis text information with each of the plurality of preset regular expressions respectively to obtain a plurality of second matching degrees, each of the preset regular expressions corresponding to a second matching degree; At least one preset disease name corresponding to at least one second matching degree exceeding a first preset threshold among the plurality of second matching degrees is determined, and the at least one preset disease name is used as the disease name set.

3. The method according to claim 2, characterized in that The data processing of the historical disease name set and the preset ICD standard disease name set to obtain a target dictionary includes: Merging the disease name set with the preset ICD standard disease name set to obtain a first dictionary, wherein the first dictionary includes a plurality of first disease names; The plurality of first disease names are deduplicated to obtain the target dictionary.

4. The method according to claim 1, characterized in that The updating of the preset dictionary tree to obtain the target dictionary tree includes: Based on the preset dictionary tree, determining initial mappings corresponding to the plurality of nodes in the preset dictionary tree; If a character i corresponding to the first sequence i does not exist in the initial mapping, a new mapping i is added, and the character i is stored in the mapping i, wherein the first sequence i is any one of the multiple first sequences, the character i is any one of the first sequences, and i is a positive integer; Based on the mapping i, the preset dictionary tree is updated to be the target dictionary tree.

5. The method according to any one of claims 1 to 4, characterized in that: The step of matching the disease name to be standardized with the plurality of preset ICD standard disease names in the preset ICD standard disease name set to obtain a plurality of first matching degrees includes: Determine a target mapping table corresponding to the target dictionary tree, wherein the target mapping table has a plurality of preset paths, and each disease name in the target dictionary tree corresponds to a preset path; Based on the target dictionary tree, starting from character j, searching downward in sequence according to the head node corresponding to the target dictionary tree, obtaining the path j to be matched and the preset path j corresponding to the path to be matched in the target mapping table, wherein the character j is the first character in the disease name to be standardized; The to-be-matched path j is matched with the preset path j to obtain a first matching degree j of the character j.

6. A disease name standardization device, characterized in that: Applied to a server, the device is used to execute the disease name standardization method according to any one of claims 1 to 5, the device comprises: an acquisition unit, a word segmentation unit, a construction unit, a matching unit and a determination unit, wherein: The acquisition unit is used to acquire a target dictionary, a current diagnosis text, and a preset ICD standard disease name set, wherein the preset ICD standard disease name set includes a plurality of preset ICD standard disease names; The word segmentation unit is used to perform a word segmentation operation on the current diagnosis text based on the target dictionary to obtain the disease name to be standardized contained in the current diagnosis text; The construction unit is used to construct a target dictionary tree based on the preset ICD standard disease name set; The matching unit is used to match the disease name to be standardized with the multiple preset ICD standard disease names in the preset ICD standard disease name set based on the target dictionary tree to obtain multiple first matching degrees; The determination unit is used to obtain the target preset ICD standard disease name corresponding to the target first matching degree when there is a target first matching degree that meets the preset conditions among the multiple first matching degrees, and determine the target preset ICD standard disease name as the conversion result of the disease name to be standardized.

7. A server, characterized in that: The method comprises a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, comprising a data storage area and a program storage area, wherein the data storage area stores data created according to the use of a blockchain node, and the program storage area stores a computer program, characterized in that: The computer program comprises program instructions which, when executed by a processor, cause the processor to perform the method according to any one of claims 1 to 5.

Images