Standardization methods, systems, equipment and media for names of medical information data items

Abstract

The present invention relates to data standardization of medical data sources, specifically to a method, system, device and medium for standardizing names of medical information data items, which can automatically standardize data of multiple data sources from a literal description level, have reasonable design, simple processing, strong adaptability, greatly liberate manpower and improve efficiency; the method comprises the following steps: unifying and removing duplicates of initial data item names of multiple medical information data sources obtained at a character level to obtain data items with different names; constructing an n-gram feature set of each data item according to the number of characters in the name of each data item; obtaining the name similarity between every two data items based on the character level according to the n-gram feature set of each data item, and constructing a similarity matrix; clustering data items in the similarity matrix that are greater than a similarity threshold, and assigning the same standardized name to all data items in each cluster for standardization.

Description

Technical Field

[0001] The present invention relates to data standardization of medical data sources, and specifically to a method, system, device and medium for standardizing the names of medical information data items. Background Art

[0002] With the advancement of information construction in various industries, massive amounts of data are stored in electronic form. For example, in the medical industry, more and more medical institutions use hospital information management systems (HIS systems) to manage the collected data. This type of information system improves the ability to collect and manage data, but it also brings about the problem of data standardization from different data sources.

[0003] Each medical institution's HIS system has a set of data standard methods. However, the data standard methods of different medical institutions are usually different, and it is very difficult to promote data standardization in multiple medical institutions in practice. For example, in medical insurance reimbursement, it is necessary to standardize the names of charges of different medical institutions so as to conduct a unified review of medical insurance reimbursement. Each medical institution represents a data source. Since each data source corresponds to a different data standardization method, the names of the same data item in different data sources are not exactly the same. More specifically, the names of data items are similar but not exactly the same. This brings difficulties to the integration of data from multiple data sources. The unified standardization of data from multiple data sources requires a lot of manpower, which is time-consuming and labor-intensive. The existing standardization method, on the one hand, will vectorize the name and then compare it, which has a large amount of calculation, and different vectorizations will lead to deviations in the results, which cannot be unified, and standard adjustment is also difficult. On the other hand, a standard library will be established and then compared and standardized, which has poor adaptability, high requirements for original data, and slow updates. It is easy to encounter problems that cannot be matched, resulting in incomplete standardization. Summary of the invention

[0004] In view of the practical problems existing in the prior art regarding the development of hospital informatization construction and the different data standardizations among multiple medical institutions (i.e., multiple data sources), the present invention provides a method, system, equipment, and medium for standardizing the names of medical information data items, which can automatically standardize data from multiple data sources at the literal description level. It has a reasonable design, simple processing, and strong adaptability, which greatly liberates manpower and improves efficiency.

[0005] The present invention is achieved through the following technical solutions:

[0006] A standardized method for naming medical information data items, including,

[0007] Unify and remove duplicates of initial data item names of multiple medical information data sources at the character level to obtain data items with different names;

[0008] According to the number of characters in the name of each data item, construct an n-gram feature set for each data item;

[0009] Based on the n-gram feature set of each data item, the name similarity between every two data items based on the character level is calculated to construct a similarity matrix;

[0010] The data items in the similarity matrix whose similarity is greater than the similarity threshold are clustered, and all the data items in each cluster are assigned the same standardized name for standardization.

[0011] Optionally, the unification and deduplication at the character level may include:

[0012] Keep the Chinese characters and numeric characters in the initial data project name, unify the English characters into lowercase, and remove all characters except Chinese, numeric and English characters.

[0013] Optionally, the n-gram feature set of each data item is constructed according to the number of characters in the name of each data item, including:

[0014] Calculate the number of characters in each data item name to obtain the length of each data item name;

[0015] Calculate the average length m of all data item names, and construct m n-gram feature sets for each data item; the feature set that cannot be constructed is an empty set.

[0016] Optionally, the name similarity between every two data items based on the character level is obtained according to the n-gram feature set of each data item, including:

[0017] Calculate the Jacquard coefficient between the n-gram feature sets corresponding to each two data items;

[0018] The Jaccard coefficients of all n-gram feature sets are combined to obtain the similarity between the two data items for which the Jaccard coefficient is calculated.

[0019] Optionally, the similarity between the two data items is expressed as follows:

[0020] sim(A,B)=(e 1 *J-Index(A 1-gram ,B 1-gram )+e 2 *J-Index(A 2-gram ,B2-gram )+……+e m *J-Index(A m-gram ,B m-gram )) / (e 1 +e 2 +……+e m );

[0021] Among them, sim(A,B) is the similarity between data items A and B, A i-gram is the n-gram feature set of data item A, B i-gram is the n-gram feature set of data item B, i = 1, 2, ..., m, m is the average length of all data item names, J-Index (A i-gram ,B i-gram ) is the Jacquard coefficient between the n-gram feature sets corresponding to data items A and B, and e is a natural constant.

[0022] Optionally, clustering items in the similarity matrix whose data similarity is greater than a threshold value includes:

[0023] Each data item with a similarity less than the threshold value is treated as a cluster separately;

[0024] For each data item whose similarity is not less than the similarity threshold, select the data item with the highest similarity and aggregate them, and cluster the multiple data items that have intersections after aggregation.

[0025] Optionally, the step of assigning the same standardized name to all data items in each cluster for standardization includes:

[0026] In a cluster including a single data item, the name of the data item is used as a standardized name of the cluster for standardization;

[0027] In a cluster including multiple data items, the average value of similarity between each data item in the cluster and other data items in the cluster is calculated, and the name of the data item with the largest average value is used as the standardized name of the cluster for standardization.

[0028] A standardized system for naming items of medical information data, including,

[0029] A preprocessing module, used to unify and remove duplicates of initial data item names of multiple medical information data sources obtained at the character level to obtain data items with different names;

[0030] A feature construction module is used to construct an n-gram feature set for each data item according to the number of characters in the name of each data item;

[0031] A similarity matrix construction module is used to obtain the name similarity between every two data items based on the character level according to the n-gram feature set of each data item, and construct a similarity matrix;

[0032] The name standardization module is used to cluster the data items with a similarity greater than a threshold in the similarity matrix, and to assign the same standardized name to all the data items in each cluster for standardization.

[0033] A computer device comprises: a memory for storing a computer program; and a processor for implementing the method for standardizing the names of medical information data items as described in any one of the above items when executing the computer program.

[0034] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method for standardizing the names of medical information data items as described in any one of the above items.

[0035] Compared with the prior art, the present invention has the following beneficial technical effects:

[0036] The present invention first unifies and removes duplicates at the character level as required, pre-processes the initial data, reduces the amount of calculation for subsequent standardization, extracts a combination of multiple characters in the project name using n-gram features, and uses the feature to compare similarities, so that the name similarity between two data projects can be judged from the character combination at the character level, and the relationship between the two can be more accurately reflected; and then, clustering is performed after threshold division, and standardization is performed according to the clustering, which not only simplifies the amount of calculation for standardization, but also has strong adaptability, and can perform simple standardization operations on data of different quantities and sources, and adjust the scale of standardization by setting the threshold to meet different needs and systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 Schematic diagram of the process of standardizing the names of medical information data items in an example of the present invention.

[0038] Figure 2 This is a standardized system structure block diagram of the medical information data item names described in the example of the present invention.

[0039] Figure 3 This is a structural block diagram of the preprocessing module of the standardization system described in the example of the present invention.

[0040] Figure 4 It is a structural block diagram of the characteristic construction module of the standardization system described in the example of the present invention.

[0041] Figure 5It is a structural block diagram of the similarity matrix construction module of the standardization system described in the example of the present invention.

[0042] Figure 6 This is a structural block diagram of the name standardization module of the standardization system described in the example of the present invention. DETAILED DESCRIPTION

[0043] The present invention is further described in detail below in conjunction with specific embodiments, which are intended to explain the present invention rather than to limit it.

[0044] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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.

[0045] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application may be combined with each other.

[0046] The present invention may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communications network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0047] In the present invention, "module", "device", "system" and the like refer to related entities applied to computers, such as hardware, a combination of hardware and software, software or software in execution, etc. In detail, for example, an element can be, but is not limited to, a process, a processor, an object, an executable element, an execution thread, a program and / or a computer running on a processor. In addition, an application or script program running on a server, a server can all be an element. One or more elements can be in an execution process and / or thread, and an element can be localized on a computer and / or distributed between two or more computers, and can be operated by various computer-readable media. An element can also communicate through local and / or remote processes according to a signal with one or more data packets, for example, a signal from a data that interacts with another element in a local system, a distributed system, and / or a network on the Internet through a signal to interact with other systems.

[0048] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include" and "comprise" include not only those elements, but also other elements that are not explicitly listed, or also include elements inherent to such processes, methods, articles or equipment. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the existence of other identical elements in the process, method, article or equipment that includes the elements.

[0049] The method for standardizing the names of medical information data items of the present invention is as follows: Figure 1 As shown, including,

[0050] S1 unifies and removes duplicates of initial data item names of multiple medical information data sources at the character level to obtain data items with different names;

[0051] This step is a preprocessing step for the initial data item names of multiple data sources. Each data item name is unified at the character level, that is, at the literal description level. On the one hand, it makes them have the same character format. On the other hand, it avoids recognition differences caused by character differences for the same name, making it easier to remove data duplication and prepare for subsequent calculations.

[0052] S2 constructs an n-gram feature set for each data item based on the number of characters in the name of each data item;

[0053] Among them, n-gram is an existing algorithm based on statistical language model. Its basic idea is to perform a sliding window operation of size N on the content of the text according to bytes, forming a sequence of byte segments of length N, where N can be set according to requirements. Each byte segment is called a gram, and the occurrence frequency of all grams is counted and filtered according to a pre-set threshold to form a key gram list, which is the feature space of the text. Each gram in the list is a feature dimension, forming the corresponding n-gram feature set.

[0054] In the present invention, each characterized data item name is used as the object for sliding window operation, and features are selected based on characters as basic units. The above method is used to construct an n-gram feature set for each data item.

[0055] S3 calculates the name similarity between every two data items based on the character level according to the n-gram feature set of each data item to construct a similarity matrix;

[0056] This step is to filter the names of data items that are actually one data item but cannot be completely matched due to inconsistent standards of different data sources by calculating similarity. For example, Dimension C and Vitamin C, as well as Vitamin C, etc., can reflect the similarities between them through similarity calculation, which lays the foundation for whether they can be standardized.

[0057] S4 clusters the data items in the similarity matrix whose similarity is greater than the similarity threshold, and assigns the same standardized name to all the data items in each cluster for standardization.

[0058] Among them, by setting the threshold, the names of the items can be screened by similarity, so that the names that are essentially the same can be clustered, for example, Vitamin C and Vitamin C, and Vitamin C, etc., and then a standardized name is assigned to each category. In the above example, for example, Vitamin C is assigned, thereby achieving the standardization of the names of medical information data items.

[0059] In a preferred embodiment of the present invention, the unification and deduplication at the character level includes retaining the Chinese characters and numeric characters in the initial data item names, unifying the English characters into lowercase, and removing other characters except Chinese, numeric and English characters. Then, deduplication is performed on the updated data item names to obtain n data items with different names. And the above preprocessing steps can be automatically implemented by code.

[0060] The following example illustrates the specific process of preprocessing. For example, there are four data items, namely "C-reactive protein", "C-reactive protein", "c-reactive protein", and "C-reactive protein". According to the above preprocessing steps, all characters except English and Chinese are removed, and English characters are unified into lowercase. These four data items are preprocessed into "c-reactive protein". After deduplication, only the data item "c-reactive protein" needs to be retained.

[0061] In a preferred embodiment of the present invention, the n-gram feature set of each data item is constructed according to the number of characters in the name of each data item, including:

[0062] Calculate the number of characters in each data item name to obtain the length of each data item name;

[0063] Calculate the average length m of all data item names, and construct m n-gram feature sets for each data item; the feature set that cannot be constructed is an empty set. That is, construct 1-gram, 2-gram, ..., m-gram features for each data item, and there are m feature sets for each data item. If the name length of the data item is less than m, the feature set that cannot be constructed is an empty set.

[0064] The following example illustrates the process of constructing n-gram features. For example, there are three data items (assuming there are only three data items in total, the actual number of data items is thousands or tens of thousands), namely "ibuprofen", "aspirin", and "acetaminophen". The average length of the names of these n = 3 data items is m = 4, so 1-gram, 2-gram, 3-gram, and 4-gram are constructed for these three data items, a total of 4 n-gram features, as shown in Table 1:

[0065] Table 1 is the n-gram feature table constructed from three data items.

[0066]

[0067] The above features are all screened and determined through sliding windows, rather than randomly combining and splicing characters, thereby ensuring the consistency of the data item names in the features.

[0068] In a preferred embodiment of the present invention, the name similarity between each two data items based on the n-gram feature set of each data item is obtained based on the character level, including:

[0069] Calculate the Jacquard coefficient between the n-gram feature sets corresponding to each two data items;

[0070] The Jaccard coefficients of all n-gram feature sets are combined to obtain the similarity between the two data items for which the Jaccard coefficients are calculated.

[0071] Among them, the Jaccard coefficient is used to compare the similarity and diversity of sample sets, which is defined as the ratio between the size of the intersection and the size of the union of two sets; for example, if two sets have 2 common entities and 4 different entities, then the Jaccard coefficient is 2 / 4=0.5.

[0072] The similarity calculation based on the Jacquard coefficient in the present invention is specifically as follows:

[0073] First, the Jacquard coefficient is calculated between the n-gram feature sets i-gram (i = 1, 2, ..., m) corresponding to each two data items, as shown in the following formula:

[0074] J-Index(A i-gram ,B i-gram )=|A i-gram ∩B i-gram | / |A i-gram ∪B i-gram |

[0075] Among them, J-Index(Ai-gram ,B i-gram ) is the Jacquard coefficient between the n-gram feature sets corresponding to data items A and B, A i-gram is the n-gram feature set of data item A, B i-gram is the n-gram feature set of data item B, i=1, 2, ..., m, and m is the average length of all data item names.

[0076] Then combine the Jacquard coefficients of all i-grams to get the similarity sim between the two data items:

[0077] sim(A,B)=(e 1 *J-Index(A 1-gram ,B 1-gram )+e 2 *J-Index(A 2-gram ,B 2-gram )+……+e m *J-Index(A m-gram ,B m-gram )) / (e 1 +e 2 +……+e m );

[0078] Among them, sim(A,B) is the similarity between data items A and B, A i-gram is the n-gram feature set of data item A, B i-gram is the n-gram feature set of data item B, i = 1, 2, ..., m, m is the average length of all data item names, J-Index (A i-gram ,B i-gram ) is the Jacquard coefficient between the n-gram feature sets corresponding to data items A and B, and e is a natural constant.

[0079] The similarity calculated by applying the similarity between each two data item names is used to construct a similarity matrix. The similarity matrix is ​​a symmetric matrix, that is, a matrix symmetric with the diagonal as the axis. The matrix element e ij =e ji The elements on the diagonal represent the similarity of the data items themselves, that is, e ii = 1. Specifically, the similarity matrix obtained in the example described in the present invention is shown in Table 2.

[0080] Table 2 is the similarity matrix constructed from the six items.

[0081]

[0082] Due to the symmetry of the similarity matrix and the exclusion of project standardization, we only focus on the values ​​in the upper right part of the similarity matrix, and no longer pay attention to other values ​​of the similarity matrix. For example, the gray part of the similarity matrix in Table 2 has the project names on the vertical and horizontal axes, and the values ​​in the middle are the similarities between the projects themselves.

[0083] In a preferred embodiment of the present invention, clustering items in a similarity matrix that are greater than a threshold value of data similarity includes:

[0084] Each data item with a similarity less than the threshold value is treated as a cluster separately;

[0085] For each data item whose similarity is not less than the similarity threshold, select the data item with the highest similarity and aggregate them, and cluster the multiple data items that have intersections after aggregation.

[0086] Specifically, on the similarity matrix shown in Table 2 obtained in the above steps, data items with a similarity greater than a threshold value are clustered, and one or more data items obtained from each cluster are standardized as having the same name.

[0087] For the obtained similarity matrix, first, the data items are screened according to the threshold value, as shown in Table 2. The threshold value is set to 0.5, and data item 6 is removed in the figure. The removed data item indicates that the similarity between the item and other items is low, so the data item is taken as a standard data item alone. If there are multiple data items that do not meet the threshold value, each data item is taken as a standard data item alone; then, among the retained data items, each data item selects the item with the highest similarity and aggregates the data items. For example, in Table 2, the highest similarity between item 1 and item 2 is 0.9, the highest similarity between item 1 and item 3 is 0.8, and the highest similarity between item 4 and item 5 is 0.9; therefore, item 1, item 2 and item 3 are aggregated together, item 4 and item 5 are aggregated together, and item 6 below the threshold is taken as a cluster alone. Finally, three standardized data item clusters are obtained to complete data standardization.

[0088] In another preferred embodiment of the present invention, the step of assigning a same standardized name to all data items in each cluster for standardization includes:

[0089] In a cluster including a single data item, the name of the data item is used as a standardized name of the cluster for standardization;

[0090] In a cluster including multiple data items, the average value of similarity between each data item in the cluster and other data items in the cluster is calculated, and the name of the data item with the largest average value is used as the standardized name of the cluster for standardization.

[0091] Specifically, in each cluster, the average value of the similarity between each data item and other data items in the cluster is calculated, and the data item with the largest average value is used as the standardized name of the cluster.

[0092] For example, there are three data items A, B, and C in a cluster. The similarities between these three data items are shown in Table 3 below.

[0093] Table 3 is a similarity table of three data items A, B, and C in a cluster.

[0094]

[0095]

[0096] From the above matrix, we can know the similarity between any two data items. Next, we calculate the average similarity between each data item and other data items:

[0097] For data item A: (sim(A,B)+sim(A,C)) / 2=(0.90+0.95) / 2=0.925

[0098] For data item B: (sim(A,B)+sim(B,C)) / 2=(0.90+0.85) / 2=0.875

[0099] For data item C: (sim(A,C)+sim(B,C)) / 2=(0.95+0.85) / 2=0.900

[0100] From the above, we can see that the value corresponding to data item A is the largest, so in this cluster, data item A is used to represent the item name of this cluster, thereby completing standardization.

[0101] The present invention corresponds to the above method and also provides a standardized system for the names of medical information data items, such as Figure 2 As shown, including,

[0102] The preprocessing module 201 is used to unify and remove duplicates of the initial data item names of the acquired multiple medical information data sources at the character level to obtain data items with different names;

[0103] A feature construction module 202, for constructing an n-gram feature set for each data item according to the number of characters in the name of each data item;

[0104] A similarity matrix construction module 203 is used to calculate the name similarity between every two data items based on the character level according to the n-gram feature set of each data item to construct a similarity matrix;

[0105] The name standardization module 204 is used to cluster the data items in the similarity matrix that are greater than a similarity threshold, and to assign the same standardized name to all the data items in each cluster for standardization.

[0106] Among them, in the preprocessing module 201, as Figure 3 As shown, including

[0107] The conversion unit is used to retain the Chinese characters and numeric characters in the initial data item name and unify the English characters into lowercase.

[0108] The removal unit is used to remove characters other than Chinese, numbers and English characters based on the output of the conversion unit.

[0109] In the feature construction module 202, as Figure 4 As shown, including

[0110] The length unit is used to calculate the number of characters in each data item name to obtain the length of each data item name;

[0111] The construction unit is used to calculate the average length m of all data item names and construct m n-gram feature sets for each data item; the feature set that cannot be constructed is an empty set.

[0112] In the similarity matrix construction module 203, as Figure 5 As shown, including

[0113] The Jacquard coefficient unit is used to calculate the Jacquard coefficient between the n-gram feature sets corresponding to every two data items;

[0114] The similarity unit is used to fuse the Jaccard coefficients of all n-gram feature sets to obtain the similarity between the two data items for calculating the Jaccard coefficient.

[0115] In the name standardization module 204, as Figure 6 As shown, including

[0116] The clustering unit is used to treat each data item less than the similarity threshold as a separate cluster; for each data item not less than the similarity threshold, select the data item with the highest similarity for aggregation, and cluster multiple data items that have intersections after aggregation.

[0117] A designated unit is used to, in a cluster including a single data item, use the name of the data item as the standardized name of the cluster for standardization; in a cluster including multiple data items, calculate the average value of the similarity between each data item in the cluster and other data items in the cluster to which it belongs, and use the name of the data item with the largest average value as the standardized name of the cluster for standardization.

[0118] In general, the standardization method, system, device and medium for the name of medical information data items based on literal description provided by the present invention is an innovation that can automatically standardize data; it solves the problem that different medical institutions have different data standardization methods. Compared with manual data standardization, the automated data standardization method for different data sources proposed by the present invention greatly liberates manpower and improves work efficiency; the data standardization method proposed by the present invention has a wide range of applications. In addition to medical information management systems, it can be applied to information management systems in multiple industry fields when there are multiple data standardization requirements for different data sources.

[0119] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0120] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0121] The server can be a stand-alone server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), as well as big data and artificial intelligence platforms.

[0122] The present invention also provides a computer device, which may include a memory and a processor, wherein a computer program is stored on the memory, and when the computer program is executed by the processor, the method for standardizing the names of medical information data items as in the above example is implemented. It is understood that the electronic device may also include an input / output (I / O) interface and a communication component.

[0123] The processor is used to execute all or part of the steps in the method for standardizing the names of medical information data items in the above example. The memory is used to store various types of data, which may include instructions of any application or method in the electronic device, as well as data related to the application.

[0124] The processor can be an application specific integrated circuit (ASIC), a digital signal processor (DSP), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components to execute the standardized method of medical information data item names as in the above example.

[0125] The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0126] This embodiment also provides a computer-readable storage medium. Each functional unit in each embodiment of the present invention may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. If the function is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium.

[0127] Based on such understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0128] The aforementioned storage media include: flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, server, APP application mall, etc. Various media that can store program check codes, on which a computer program is stored, and when the computer program is executed by a processor, the following method steps can be implemented:

[0129] S1 unifies and removes duplicates of initial data item names of multiple medical information data sources at the character level to obtain data items with different names;

[0130] S2 constructs an n-gram feature set for each data item based on the number of characters in the name of each data item;

[0131] S3 calculates the name similarity between every two data items based on the character level according to the n-gram feature set of each data item to construct a similarity matrix;

[0132] S4 clusters the data items in the similarity matrix whose similarity is greater than the similarity threshold, and assigns the same standardized name to all the data items in each cluster for standardization.

[0133] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0134] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0135] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0136] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0137] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for standardizing names of medical information data items, characterized in that: include, Unify and remove duplicates of initial data item names of multiple medical information data sources at the character level to obtain data items with different names; According to the number of characters in the name of each data item, construct an n-gram feature set for each data item; Based on the n-gram feature set of each data item, the name similarity between every two data items based on the character level is calculated to construct a similarity matrix; Clustering the data items in the similarity matrix whose similarity is greater than the similarity threshold, and assigning the same standardized name to all the data items in each cluster for standardization; The name similarity between each two data items based on the character level is obtained according to the n-gram feature set of each data item, including: Calculate the Jacquard coefficient between the n-gram feature sets corresponding to each two data items; The Jaccard coefficients of all n-gram feature sets are combined to obtain the similarity between the two data items for which the Jaccard coefficient is calculated; The similarity between the two data items is expressed as follows: sim(A, B) = ( e 1 * J-Index(A 1-gram , B 1-gram ) + e 2 * J-Index(A 2-gram , B 2-gram ) +…… + e m * J-Index(A m-gram , B m-gram ) ) / (e 1 + e 2 + …… + e m ); Among them, sim(A, B) is the similarity between data items A and B, A i-gram is the n-gram feature set of data item A, B i-gram is the n-gram feature set of data item B, i=1, 2, ..., m, m is the average length of all data item names, J-Index(A i-gram , B i-gram ) is the Jacquard coefficient between the n-gram feature sets corresponding to data items A and B, and e is a natural constant.

2. The method for standardizing the names of medical information data items according to claim 1, characterized in that: The unification and deduplication at the character level include: Keep the Chinese characters and numeric characters in the initial data project name, unify the English characters into lowercase, and remove all characters except Chinese, numeric and English characters.

3. The method for standardizing the names of medical information data items according to claim 1, characterized in that: According to the number of characters in the name of each data item, an n-gram feature set of each data item is constructed. include, Calculate the number of characters in each data item name to obtain the length of each data item name; Calculate the average length m of all data item names, and construct m n-gram feature sets for each data item; the feature set that cannot be constructed is an empty set.

4. The method for standardizing the names of medical information data items according to claim 1, characterized in that: The clustering is performed on the items in the similarity matrix that are greater than the threshold value of data similarity. include, Each data item with a similarity less than the threshold value is treated as a cluster separately; For each data item whose similarity is not less than the similarity threshold, select the data item with the highest similarity and aggregate them, and cluster the multiple data items that have intersections after aggregation.

5. The method for standardizing the names of medical information data items according to claim 4, characterized in that: The standardization of all data items in each cluster by specifying the same standardized name includes: In a cluster including a single data item, the name of the data item is used as a standardized name of the cluster for standardization; In a cluster including multiple data items, the average value of similarity between each data item in the cluster and other data items in the cluster is calculated, and the name of the data item with the largest average value is used as the standardized name of the cluster for standardization.

6. A system for standardizing names of medical information data items, characterized in that: include, A preprocessing module, used to unify and remove duplicates of initial data item names of multiple medical information data sources obtained at the character level to obtain data items with different names; A feature construction module is used to construct an n-gram feature set for each data item according to the number of characters in the name of each data item; A similarity matrix construction module is used to obtain the name similarity between every two data items based on the character level according to the n-gram feature set of each data item, and construct a similarity matrix; The name similarity between each two data items based on the character level is obtained according to the n-gram feature set of each data item, including: Calculate the Jacquard coefficient between the n-gram feature sets corresponding to each two data items; The Jaccard coefficients of all n-gram feature sets are combined to obtain the similarity between the two data items for which the Jaccard coefficient is calculated; The similarity between the two data items is expressed as follows: sim(A, B) = ( e 1 * J-Index(A 1-gram , B 1-gram ) + e 2 * J-Index(A 2-gram , B 2-gram ) +…… + e m * J-Index(A m-gram , B m-gram ) ) / (e 1 + e 2 + …… + e m ); Among them, sim(A, B) is the similarity between data items A and B, A i-gram is the n-gram feature set of data item A, B i-gram is the n-gram feature set of data item B, i=1, 2, ..., m, m is the average length of all data item names, J-Index(A i-gram , B i-gram ) is the Jacquard coefficient between the n-gram feature sets corresponding to data items A and B, and e is a natural constant; The name standardization module is used to cluster the data items with a similarity greater than a threshold in the similarity matrix, and to assign the same standardized name to all the data items in each cluster for standardization.

7. A computer device, characterized in that: include: Memory for storing computer programs; A processor, used to implement the method for standardizing the names of medical information data items as described in any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the method for standardizing the names of medical information data items according to any one of claims 1 to 5.

Images