Medical element processing method, device, equipment and computer readable storage medium

Abstract

The application provides a medical element processing method, device and equipment and a computer readable storage medium. According to the medical element to be processed, at least one element attribute of the medical element to be processed is obtained, and then at least one candidate normalized medical element of the medical element to be processed is obtained according to at least one of each element attribute and a relationship attribute of the element attribute, so that a standard normalized medical element of the medical element to be processed can be obtained according to the at least one candidate normalized medical element, thereby realizing the unification of medical elements on various carriers into standard medical elements.

Description

TECHNICAL FIELD

[0001] The present application relates to the medical technology field, and in particular, to a medical element processing method, device, equipment and computer readable storage medium.

BACKGROUND

[0002] Medical element refers to necessary content for describing medical related conditions in the medical field, such as diagnosis element, disease element, drug element, etc. Generally, there are many diversified expressions of medical elements, such as a little stomach ache, slight abdominal pain, abdominal pain, etc. Although the expression of these medical elements is different, they all represent the same meaning.

[0003] Therefore, in order to facilitate viewing and further analysis, it is necessary to provide a medical element processing method for unifying medical elements appearing on various carriers (such as patient cases, diagnosis certificates, etc.) into standard medical elements.

SUMMARY

[0004] Aspects of the present application provide a medical element processing method, device, equipment and computer readable storage medium for unifying medical elements appearing on various carriers into standard medical elements.

[0005] In an aspect of the present application, a medical element processing method is provided, comprising:

[0006] According to the to-be-processed medical element, obtaining at least one element attribute of the to-be-processed medical element;

[0007] According to at least one of each element attribute and the relationship attribute of the element attribute in the at least one element attribute, obtaining at least one candidate normalized medical element of the to-be-processed medical element;

[0008] According to the at least one candidate normalized medical element, obtaining a standard normalized medical element of the to-be-processed medical element.

[0009] In another aspect of the present application, a medical element processing device is provided, comprising:

[0010] An attribute unit is configured to obtain at least one element attribute of the to-be-processed medical element according to the to-be-processed medical element;

[0011] A normalization unit is configured to obtain at least one candidate normalized medical element of the to-be-processed medical element according to at least one of each element attribute and the relationship attribute of the element attribute in the at least one element attribute;

[0012] a screening unit configured to obtain a standard normalized medical element of the medical element to be processed according to the at least one candidate normalized medical element.

[0013] In another aspect of the present application, a device is provided, the device comprising:

[0014] one or more processors;

[0015] a storage configured to store one or more programs,

[0016] when the one or more programs are executed by the one or more processors, the one or more processors implement the medical element processing method as provided in the above aspect.

[0017] In another aspect of the present application, a computer readable storage medium is provided, the computer readable storage medium storing a computer program, the computer program being executed by a processor to implement the medical element processing method as provided in the above aspect.

[0018] According to the above technical solution, the embodiment of the present application obtains at least one element attribute of the medical element to be processed according to the medical element to be processed, and then obtains at least one candidate normalized medical element of the medical element to be processed according to at least one of each element attribute and a relationship attribute of the element attribute, so that the standard normalized medical element of the medical element to be processed can be obtained according to the at least one candidate normalized medical element, thereby realizing the unification of medical elements on various carriers into standard medical elements.

[0019] In addition, by using semantic learning based on a feature model, the technical solution provided by the present application can provide more candidate normalized medical elements, thereby effectively improving the reliability of medical element processing.

[0020] In addition, the technical solution provided by the present application does not require manual operation, is simple to operate, and has high accuracy, thereby effectively improving the efficiency and reliability of medical element processing.

[0021] In addition, the technical solution provided by the present application can effectively improve the user experience.

DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.Figure 1 A flowchart of a medical element processing method according to an embodiment of the present application is shown in FIG. 1.

[0024] Figure 2 A structural diagram of a medical element processing device according to another embodiment of the present application is shown in FIG. 2.

[0025] Figure 3 A block diagram of an exemplary computer system / server 12 suitable for implementing embodiments of the present application is shown in FIG. 3.

DETAILED DESCRIPTION

[0026] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0027] It should be noted that the terminal involved in the embodiments of the present application can include but is not limited to a mobile phone, a personal digital assistant (PDA), a wireless handheld device, a tablet computer, a personal computer (PC), an MP3 player, an MP4 player, a wearable device (for example, smart glasses, a smart watch, a smart bracelet, etc.), and the like.

[0028] In addition, the term "and / or" in the present document is only used to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone. In addition, the character " / " in the present document generally represents an "or" relationship between the front and rear associated objects.

[0029] As described in the background, some medical elements have different expressions, but they all represent the same meaning. In the prior art, a large amount of knowledge can be accumulated by manual arrangement to form a knowledge base, and a standard medical element is obtained through traditional knowledge query. If the query fails, the user can only unify the medical elements with the same meaning but different expressions into a standard medical element according to the specific content of the medical element and by himself inducing the standard element name represented by the medical element from massive data. This method has the following disadvantages:

[0030] 1. High time cost and labor cost

[0031] A large number of knowledge bases need to be constructed by experts, and each time a new expression appears, an expert needs to make a judgment, which consumes a lot of manpower and time.

[0032] 2. Low influence and recall rate

[0033] In the medical field, medical elements have the characteristics of serious oralization and diversified expression, and simple knowledge accumulation cannot cover various expression modes, which will inevitably lead to low influence and recall rate.

[0034] Therefore, the present application provides a medical element processing method for unifying medical elements on various carriers into standard medical elements.

[0035] Figure 1 The flowchart of the medical element processing method provided by an embodiment of the present application is shown in Figure 1 .

[0036] 101. Obtaining at least one element attribute of the to-be-processed medical element according to the to-be-processed medical element.

[0037] 102. Obtaining at least one candidate normalized medical element of the to-be-processed medical element according to at least one of each element attribute in the at least one element attribute and the relationship attribute of the element attribute.

[0038] 103. Obtaining a standard normalized medical element of the to-be-processed medical element according to the at least one candidate normalized medical element.

[0039] It should be noted that part or all of the execution subjects of 101-103 can be an application located in a local terminal, or can also be a plug-in or a software development kit (SDK) and the like functional units arranged in the application located in the local terminal, or can also be a processing engine located in a network side server, or can also be a distributed system located in the network side, and the present embodiment does not particularly limit this.

[0040] It can be understood that the application can be a native program (native App) installed on the terminal, or can also be a web program (web App) of a browser on the terminal, and the present embodiment does not particularly limit this.

[0041] In this way, by obtaining at least one element attribute of the to-be-processed medical element according to the to-be-processed medical element, and then obtaining at least one candidate normalized medical element of the to-be-processed medical element according to at least one of each element attribute in the at least one element attribute and a relationship attribute of the element attribute, the standard normalized medical element of the to-be-processed medical element can be obtained according to the at least one candidate normalized medical element, so that the medical elements appearing on various carriers are unified into standard medical elements.

[0042] Optionally, in one possible implementation of the embodiment, in 101, the attribute extraction model constructed in advance can be used to perform attribute extraction processing on the to-be-processed medical element to obtain at least one element attribute of the to-be-processed medical element.

[0043] Optionally, in one possible implementation of the embodiment, in 101, the element type to which the to-be-processed medical element belongs can be obtained according to the to-be-processed medical element, and then at least one element attribute of the to-be-processed medical element can be obtained according to the element type and the to-be-processed medical element.

[0044] The element type can include but is not limited to at least one of the following:

[0045] A disease element, for example, bilateral ovarian cysts, etc.;

[0046] A surgery element, for example, lung transplantation, etc.;

[0047] A symptom element, for example, upper abdominal pain, etc.;

[0048] A sign element, for example, abdominal mass, etc.;

[0049] An examination element, for example, blood routine, etc.; and

[0050] A drug element, for example, cold granules, etc.

[0051] In this implementation, different attribute extraction rules can be set for different element types, so as to perform attribute extraction processing on the to-be-processed medical element according to the attribute extraction rules to obtain at least one element attribute of the to-be-processed medical element.

[0052] For example, the attribute extraction rule of the disease element can be

people

symptom description

human body part attribute

symptom description attribute

disease name attribute

disease stage attribute

[0053] For example, the attribute extraction rule of the surgery element can be

human body part attribute

operation name attribute

[0054] Or, for example, the attribute extraction rule of the symptom element can be

human body part attribute

symptom description attribute

[0055] Or, for example, the attribute extraction rule of the drug element can be

drug name attribute

[0056] It should be noted that the "attribute" in the present application is used to represent the relevant content of the attribute, which can include but is not limited to attribute name and attribute value.

[0057] For example, the medical element "mild pain in the upper abdomen" has a corresponding attribute extraction rule of

human body part attribute

symptom description attribute

[0058] Optionally, in one possible implementation of the present embodiment, in 102, a standard element attribute list can be obtained, and then the standard element attribute list can be used to normalize each element attribute in the at least one element attribute, to obtain at least one candidate normalized medical element of the medical element to be processed.

[0059] The standard element attribute list is an offline attribute list used to accumulate some common knowledge, which includes not only some common synonyms. For example, the synonym "eye blindness" of "blindness" in the disease element. Or, for example, the synonym "pain" of

symptom description attribute

[0060] In a specific implementation process, the standard element attribute list can include but is not limited to at least one of expert-annotated high-frequency words, common synonyms and newly-added synonyms, which are not particularly limited in the present embodiment.

[0061] For example, in actual application scenarios, some medical elements frequently appear, which can be called high-frequency words. Through expert annotation, the standard medical elements of these high-frequency words can be obtained and accumulated in the standard element attribute list.

[0062] Or, for example, in actual application scenarios, common synonyms in the medical field can be obtained through mining from professional books and sorting by medical experts, and accumulated in the standard element attribute list.

[0063] Or, for example, in actual application scenarios, new synonyms are continuously accumulated and expanded to the standard element attribute list.

[0064] After obtaining the normalized element attribute, at least one candidate normalized medical element of the medical element to be processed can be obtained according to the normalized element attribute by using a matching algorithm, for example, an inverted index algorithm.

[0065] The inverted index algorithm is taken as an example below to illustrate how to establish the inverted index of the standard medical element.

[0066] Firstly, the element type to which the standard medical element "abdominal pain" belongs can be obtained according to the standard medical element "abdominal pain", which is a symptom element. Then, two element attributes of the standard medical element can be obtained according to the element type and the standard medical element, one of which is an attribute name "human body part attribute" and an attribute value "abdomen", and the other of which is an attribute name "symptom description attribute" and an attribute value "pain". Next, the relationship attribute of each element attribute can be obtained by performing synonym processing on each element attribute according to the two element attributes, the relationship attribute of which is an attribute name "human body part attribute" and "symptom description attribute", and the corresponding attribute values of which are "abdominal pain" and "pain", respectively. Finally, the inverted index of the standard medical element "abdominal pain" can be established by using the relationship attribute of the element attribute, that is, relationship attribute→standard medical element.

[0067] Suppose the attribute name of the obtained normalized element attribute is "human body part attribute" and "symptom description attribute", and the corresponding attribute values thereof are "abdominal pain" and "pain", respectively. Based on the established inverted index of the standard medical element "abdominal pain", the standard medical element "abdominal pain" can be pointed to as a candidate normalized medical element.

[0068] It can be understood that based on the established inverted index, a plurality of other standard medical elements can be further pointed to as a plurality of candidate normalized medical elements.

[0069] Optionally, in one possible implementation manner of the embodiment, the modification processing can be performed on the at least one element attribute according to each element attribute in the at least one element attribute in 102, to obtain at least one candidate normalized medical element of the medical element to be processed.

[0070] The modification processing can include, but is not limited to, at least one of the adding processing and the deleting processing, and the embodiment does not particularly limit the modification processing.

[0071] For example, the modifier "three days ago" in the element attribute "three days ago with a cold" can be deleted, and then the candidate normalized medical element "cold" is obtained.

[0072] Or, for another example, the suffix word "disease" can be added to the element attribute "AIDS" to obtain the candidate normalized medical element "AIDS disease".

[0073] Or, for another example, the suffix word "disease" in the element attribute "AIDS disease" can be deleted to obtain the candidate normalized medical element "AIDS".

[0074] After obtaining the element attribute of the modification processing, at least one candidate normalized medical element of the medical element to be processed can be obtained according to the element attribute of the modification processing by using a matching algorithm, for example, an inverted index algorithm.

[0075] After obtaining the element attribute of the modification processing, at least one candidate normalized medical element of the medical element to be processed can be obtained according to the element attribute of the modification processing by using a matching algorithm, for example, an inverted index algorithm.

[0076] Optionally, in one possible implementation manner of the embodiment, in 102, the conversion processing can be performed on each of the at least one element attribute according to each of the at least one element attribute to obtain the relationship attribute of the element attribute, and then at least one candidate normalized medical element of the medical element to be processed can be obtained according to the relationship attribute of each of the element attribute.

[0077] The conversion processing can include but is not limited to at least one of synonym processing and hypernym processing, which is not particularly limited in the embodiment.

[0078] The detailed content of the implementation manner will be illustrated below by taking the medical element "slight pain in the upper abdomen" as an example. The attribute extraction rule corresponding to the medical element "slight pain in the upper abdomen" can be

human body part attribute

symptom description attribute

human body part attribute

symptom description attribute

[0079] For example, after obtaining the element attribute

human body part attribute

symptom description attribute

human body part attribute

symptom description attribute

[0080] Or, for another example, after obtaining the element attribute

human body part attribute

symptom description attribute

human body part attribute

symptom description attribute

[0081] Or, for another example, after obtaining the element attribute

human body part attribute

symptom description attribute

human body part attribute

symptom description attribute

[0082] After obtaining the element attribute processed by the conversion processing, at least one candidate normalized medical element of the medical element to be processed can be obtained by using a matching algorithm, such as an inverted index algorithm, according to the element attribute processed by the conversion processing.

[0083] Optionally, in one possible implementation manner of the embodiment, before 103, more candidate normalized medical elements can be further obtained.

[0084] Specifically, the medical element to be processed can be input into a pre-constructed feature model to obtain a vector representation of the medical element to be processed. Then, a similarity parameter between each standard normalized medical element and the medical element to be processed can be obtained according to the vector representation of each standard normalized medical element and the vector representation of the medical element to be processed. At least one candidate normalized medical element of the medical element to be processed can be obtained according to the similarity parameter between each standard normalized medical element and the medical element to be processed.

[0085] Further, before the medical element to be processed is input into a pre-constructed feature model to obtain a vector representation of the medical element to be processed, various model training methods can be used to construct the feature model, which is not particularly limited in the embodiment.

[0086] For example, the feature model can be constructed by using a supervised learning method. Specifically, the feature model can be constructed by using a model training process with labeled standard medical elements. The vector representation of the medical element to be processed can be obtained by using the constructed feature model with the medical element to be processed as input.

[0087] Alternatively, for another example, the feature model can be constructed by using an unsupervised learning method. Specifically, the Skip-thoughts model can be used, which is an open-source sentence encoder-decoder model of Google, used to learn to encode the input sentence into a fixed-dimensional vector representation. The encoder can use a neural network to encode the current sentence, and the decoder can reconstruct the encoding of the sentence around the input sentence. The input medical element to be processed can be encoded into a vector representation by using the Skip-thoughs model, and the vector representation is matched with the vector representation of all standard medical elements to obtain the vector representation of the standard medical element with high semantic relevance.

[0088] Alternatively, for another example, the feature model can be constructed by using a semi-supervised learning method. Specifically, the model training method in the first two examples can be used to construct the feature model.

[0089] In a specific implementation process, a similarity threshold can be set, and the standard normalized medical element with a similarity parameter greater than or equal to the similarity threshold can be set as the candidate normalized medical element of the medical element to be processed, otherwise, the processing is discarded.

[0090] Optionally, in one possible implementation of the embodiment, in 103, if multiple candidate normalized medical elements are obtained, the at least one candidate normalized medical element can be screened by using a screening rule to obtain the standard normalized medical element of the medical element to be processed.

[0091] In a specific implementation process, the screening rule can be to screen the candidate normalized medical element with the highest priority as the standard normalized medical element of the medical element to be processed.

[0092] Specifically, the priority of the medical element can be set according to a preset rule. For example, the priority of the medical element containing the superordinate element attribute is higher than the priority of the medical element containing the subordinate element attribute, the priority of the medical element containing the modifier element attribute is higher than the priority of the medical element not containing the modifier element attribute, the priority of the medical element containing the suffix element attribute is higher than the priority of the medical element not containing the suffix element attribute, and the like.

[0093] In another specific implementation process, the screening principle can be to screen out a candidate normalized medical element containing the most features as the standard normalized medical element of the medical element to be processed.

[0094] For example, the candidate normalized medical element "child cold" contains more features than the candidate normalized medical element "cold".

[0095] In actual application, after obtaining the standard normalized medical element of the medical element to be processed, the next step of auxiliary diagnosis can be performed, for example, to determine the relevant department and the corresponding treatment scheme.

[0096] In this embodiment, by obtaining at least one element attribute of the medical element to be processed according to the medical element to be processed, and then obtaining at least one candidate normalized medical element of the medical element to be processed according to at least one of each element attribute and the relationship attribute of the element attribute, the standard normalized medical element of the medical element to be processed can be obtained according to the at least one candidate normalized medical element, so that various medical elements appearing on various carriers can be unified into standard medical elements.

[0097] In addition, by using semantic learning based on a feature model, the technical solution provided by the present application can provide more candidate normalized medical elements, thereby effectively improving the reliability of medical element processing.

[0098] In addition, the technical solution provided by the present application does not require manual operation, is simple to operate, and has high accuracy, and can effectively improve the efficiency and reliability of medical element processing.

[0099] In addition, the technical solution provided by the present application can effectively improve the user experience.

[0100] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the action sequence described, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily necessary for the present application.

[0101] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0102] Figure 2 The structural schematic diagram of the medical element processing device provided by another embodiment of the present application is shown in FIG. 2.Figure 2 The processing apparatus of medical elements in this embodiment can include an attribute unit 21, a normalization unit 22, and a screening unit 23. The attribute unit 21 is configured to obtain at least one element attribute of a medical element to be processed according to the medical element to be processed. The normalization unit 22 is configured to obtain at least one candidate normalized medical element of the medical element to be processed according to at least one of each element attribute in the at least one element attribute and a relationship attribute of the element attribute. The screening unit 23 is configured to obtain a standard normalized medical element of the medical element to be processed according to the at least one candidate normalized medical element.

[0103] It should be noted that part or all of the processing apparatus of medical elements provided in this embodiment can be an application located in a local terminal, or can also be a plug-in or a software development kit (SDK) and the like functional units arranged in the application located in the local terminal, or can also be a search engine located in a network side server, or can also be a distributed system located in the network side, and this embodiment does not make a special limitation.

[0104] It can be understood that the application can be a native application (nativeApp) installed on the terminal, or can also be a web application (webApp) of a browser on the terminal, and this embodiment does not make a special limitation.

[0105] Optionally, in a possible implementation manner of this embodiment, the attribute unit 21 can be specifically configured to obtain an element type to which the medical element to be processed belongs according to the medical element to be processed, and obtain at least one element attribute of the medical element to be processed according to the element type and the medical element to be processed.

[0106] Optionally, in a possible implementation manner of this embodiment, the normalization unit 22 can be specifically configured to obtain a standard element attribute list, and perform normalization processing on each element attribute in the at least one element attribute by using the standard element attribute list to obtain at least one candidate normalized medical element of the medical element to be processed.

[0107] Optionally, in a possible implementation manner of this embodiment, the normalization unit 22 can be specifically configured to perform modification processing on the at least one element attribute according to each element attribute in the at least one element attribute to obtain at least one candidate normalized medical element of the medical element to be processed.

[0108] The modification processing can include, but is not limited to, at least one of an addition processing and a deletion processing, and this embodiment does not make a special limitation.

[0109] Optionally, in a possible implementation of the embodiment, the normalization unit 22 can be specifically configured to: perform conversion processing on each of the at least one element attribute according to each of the at least one element attribute, to obtain a relationship attribute of the element attribute; and obtain at least one candidate normalized medical element of the medical element to be processed according to the relationship attribute of each of the element attribute.

[0110] The conversion processing can include, but is not limited to, at least one of synonym processing and hypernym processing, and the embodiment is not particularly limited in this regard.

[0111] Optionally, in a possible implementation of the embodiment, the normalization unit 22 can be further configured to: input the medical element to be processed into a pre-constructed feature model, to obtain a vector representation of the medical element to be processed; obtain a similarity parameter between each of the at least one standard normalized medical element and the medical element to be processed according to the vector representation of each of the at least one standard normalized medical element and the vector representation of the medical element to be processed; and obtain at least one candidate normalized medical element of the medical element to be processed according to the similarity parameter between each of the at least one standard normalized medical element and the medical element to be processed.

[0112] Further, the normalization unit 22 can be further configured to: construct the feature model by using a supervised learning method; or construct the feature model by using an unsupervised learning method; or construct the feature model by using a semi-supervised learning method.

[0113] In a specific implementation process, the normalization unit 22 can be specifically configured to: take a standard normalized medical element with a similarity parameter greater than or equal to a similarity threshold as a candidate normalized medical element of the medical element to be processed.

[0114] It should be noted that, Figure 1 The method in the corresponding embodiment can be implemented by the medical element processing apparatus provided in the embodiment. The detailed description can be referred to in the description of the medical element processing apparatus. Figure 1 The related content in the corresponding embodiment will not be described here again.

[0115] In the embodiment, the attribute unit obtains at least one element attribute of the to-be-processed medical element according to the to-be-processed medical element, and then the normalization unit obtains at least one candidate normalized medical element of the to-be-processed medical element according to at least one of each element attribute in the at least one element attribute and a relationship attribute of the element attribute, so that the screening unit can obtain a standard normalized medical element of the to-be-processed medical element according to the at least one candidate normalized medical element, thereby realizing the unification of medical elements on various carriers into standard medical elements.

[0116] In addition, by using the semantic learning based on the feature model, the technical solution provided by the present application can provide more candidate normalized medical elements, thereby effectively improving the reliability of medical element processing.

[0117] In addition, the technical solution provided by the present application does not require manual operation, is simple to operate, has high accuracy, and can effectively improve the efficiency and reliability of medical element processing.

[0118] In addition, the technical solution provided by the present application can effectively improve the user experience.

[0119] Figure 3 A block diagram of an exemplary computer system / server 12 suitable for implementing embodiments of the present application is shown. Figure 3 The computer system / server 12 shown is only one example of a computer system / server and should not be taken as limiting the generality of the embodiments of the present application.

[0120] As shown in Figure 3 The computer system / server 12 is shown in the form of a general-purpose computing device. The components of the computer system / server 12 can include, but are not limited to, one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 to the processing unit 16.

[0121] The bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or local bus using any of a variety of bus architectures including Industry Standard Architecture (ISA), Micro Channel Architecture (MAC), Enhanced ISA (EISA), Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0122] Computer system / server 12 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by computer system / server 12 and includes both

[0123] The system memory 28 can include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Computer system / server 12 can further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, a storage system 34 can be provided for reading from and writing to non-removable, non-volatile magnetic media (e.g., a "hard drive"). Figure 3 Although not shown, a magnetic disk drive can also be utilized in some embodiments to access magnetic on-removable, non-volatile magnetic media for reading and writing, such as a Figure 3 In these instances, each drive can be connected to the bus 18 by one or more data media interfaces. The system memory 28 can include at least one program product having a set (e.g., at least one) of program modules that configure machine 10 to perform the functions of the embodiments of the application.

[0124] A program / utility 40, having a set (at least one) of program modules 42, can be stored in system memory 28 by way of example, such programs can include an operating system, one or more application programs, other program modules, and program data, each of or a combination of which

[0125] Computer system / server 12 can also communicate with one or more external devices 14 such as a keyboard, a pointing device, a display 25, etc.; one or more devices that enable a user to interact with computer system / server 12; and / or any devices (e.g., network card, modem, etc.) that enable computer system / server 12 to communicate with one or more other computing devices. Such communication can occur via Input / Output (I / O) interfaces 44. Still yet, computer system / server 12 can communicate with one or more networks such as a local area network (LAN), a general wide area network (WAN), and / or a public network (e.g., the Internet) via network adapter 20. As depicted, network adapter 20 communicates with the other components of computer system / server 12 via bus 18. It should be appreciated that although not shown, other hardware and / or software

[0126] Processing unit 16 performs various Figure 1 processing methods of medical elements provided by the corresponding embodiments.

[0127] Another embodiment of the present application further provides a computer readable storage medium, having stored thereon a computer program, which when executed by a processor, implements the processing method of medical elements provided by the corresponding embodiments. Figure 1 processing methods of medical elements provided by the corresponding embodiments.

[0128] Specifically, any combination of one or more computer readable medium can be employed. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, the computer readable storage medium can be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0129] A computer readable signal medium can include a propagated data signal with computer executable code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated signal can take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium can be any computer readable medium that can be involved in

[0130] The code can be transmitted in any form, including, but not limited to, radio frequency, electrical, optical, acoustical, or any form of propagation medium. Further, it should be appreciated that a computing entity includes computing devices as well as apparatus that have more limited scope, such as devices that are capable of reading instructions from a combination of media, or a device that is capable of reading instructions from only a limited number of media (e.g., a device that is capable of reading instructions from memory but not from a computer bus).

[0131] The computer program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, application specific circuitry, or field programmable gate array (FPGA) circuitry can execute the computer program code.

[0132] Those skilled in the art will clearly understand that, for the sake of brevity and conciseness, the specific working processes of the systems, apparatuses and units described above can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0133] In several embodiments provided by the present application, it should be understood that the disclosed system, apparatus and method can be implemented by other ways. For example, the apparatus embodiments described above are merely schematic, for example, the division of the units is merely a logical function division, and actual implementation can have another division manner, for example, a plurality of units or page components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interfaces, apparatuses or units, and can be electrical, mechanical or other forms.

[0134] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0135] In addition, each functional unit in each embodiment of the application can be integrated in one processing unit, or each unit can be physically present alone, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional unit.

[0136] The integrated unit realized in the form of software functional unit can be stored in a computer readable storage medium. The software functional unit stored in a storage medium includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute part of the steps of the method described in each embodiment of the application. The foregoing storage medium includes a variety of program code storage media such as a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0137] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the application, and not to limit them; although the application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the application.

Claims

1. A medical element processing method characterized by, The method comprises the following steps: obtaining at least one element attribute of the to-be-processed medical element based on an attribute extraction rule according to the to-be-processed medical element; wherein the attribute extraction rule is determined according to a medical element type; the element attribute comprises an attribute name and an attribute value; the to-be-processed medical element is a medical element obtained from various carriers; obtaining at least one candidate normalized medical element of the to-be-processed medical element according to at least one of each element attribute in the at least one element attribute and a relationship attribute of the element attribute; selecting a candidate normalized medical element with the highest priority or the most characteristics from the at least one candidate normalized medical element as a standard normalized medical element of the to-be-processed medical element; the step of obtaining at least one element attribute of the to-be-processed medical element based on an attribute extraction rule according to the to-be-processed medical element comprises: performing attribute extraction processing on the to-be-processed medical element based on the attribute extraction rule to obtain at least one element attribute of the to-be-processed medical element.

2. The method of claim 1, wherein, the step of obtaining at least one element attribute of the to-be-processed medical element according to the to-be-processed medical element comprises: obtaining an element type to which the to-be-processed medical element belongs according to the to-be-processed medical element; obtaining at least one element attribute of the to-be-processed medical element according to the element type and the to-be-processed medical element.

3. The method of claim 1, wherein, the step of obtaining at least one candidate normalized medical element of the to-be-processed medical element according to each element attribute in the at least one element attribute comprises: obtaining a standard element attribute list; performing normalization processing on each element attribute in the at least one element attribute by using the standard element attribute list to obtain at least one candidate normalized medical element of the to-be-processed medical element.

4. The method of claim 1, wherein, the step of obtaining at least one candidate normalized medical element of the to-be-processed medical element according to each element attribute in the at least one element attribute comprises: performing modification processing on the at least one element attribute according to each element attribute in the at least one element attribute to obtain at least one candidate normalized medical element of the to-be-processed medical element.

5. The method of claim 4, wherein, the modification processing comprises at least one of an addition processing and a deletion processing.

6. The method of claim 1, wherein, the step of obtaining at least one candidate normalized medical element of the to-be-processed medical element according to a relationship attribute of each element attribute in the at least one element attribute comprises: performing conversion processing on each element attribute in the at least one element attribute according to the element attribute to obtain a relationship attribute of the element attribute; obtaining at least one candidate normalized medical element of the to-be-processed medical element according to the relationship attribute of each element attribute.

7. The method of claim 6, wherein, the conversion processing comprises at least one of a synonym processing and a hypernym processing.

8. The method according to any one of claims 1 to 7, characterized in that, before the step of obtaining a standard normalized medical element of the to-be-processed medical element according to the at least one candidate normalized medical element, the method further comprises: inputting the to-be-processed medical element into a pre-constructed feature model to obtain a vector representation of the to-be-processed medical element; normalizing each of the standard normalized medical elements according to at least one criterion, and obtaining a similarity parameter between each of the standard normalized medical elements and the medical element to be processed; obtaining at least one candidate normalized medical element of the medical element to be processed according to the similarity parameter between each of the standard normalized medical elements and the medical element to be processed.

9. The method of claim 8, wherein, Before the inputting the medical element to be processed into the pre-constructed feature model to obtain the vector representation of the medical element to be processed, the method further comprises: constructing the feature model by using a supervised learning method; or constructing the feature model by using an unsupervised learning method; or constructing the feature model by using a semi-supervised learning method.

10. The method of claim 8, wherein, The obtaining at least one candidate normalized medical element of the medical element to be processed according to the similarity parameter between each of the standard normalized medical elements and the medical element to be processed comprises: taking a standard normalized medical element with a similarity parameter greater than or equal to a similarity threshold as a candidate normalized medical element of the medical element to be processed.

11. A medical element processing apparatus characterized by comprising: comprises: an attribute unit configured to obtain at least one element attribute of the medical element to be processed based on an attribute extraction rule according to the medical element to be processed, wherein the attribute extraction rule is determined according to a medical element type, and the element attribute comprises an attribute name and an attribute value; the medical element to be processed is a medical element obtained from various carriers; a normalization unit configured to obtain at least one candidate normalized medical element of the medical element to be processed according to at least one of each of the at least one element attribute and a relationship attribute of the element attribute; a screening unit configured to screen out a candidate normalized medical element with the highest priority or the most features from the at least one candidate normalized medical element as a standard normalized medical element of the medical element to be processed; the attribute unit is configured to perform attribute extraction processing on the medical element to be processed based on the attribute extraction rule to obtain at least one element attribute of the medical element to be processed.

12. The apparatus of claim 11, wherein, The attribute unit is specifically configured to obtain an element type to which the medical element to be processed belongs according to the medical element to be processed; and obtain at least one element attribute of the medical element to be processed according to the element type and the medical element to be processed. The normalization unit is specifically configured to 13. The apparatus of claim 11, wherein, obtain a standard element attribute list; and perform normalization processing on each of the at least one element attribute by using the standard element attribute list to obtain at least one candidate normalized medical element of the medical element to be processed. The normalization unit is specifically configured to 14. The apparatus of claim 11, wherein, perform modification processing on the at least one element attribute according to each of the at least one element attribute to obtain at least one candidate normalized medical element of the medical element to be processed. The modification processing comprises at least one of an adding processing and a deleting processing.

15. The apparatus of claim 14, wherein, The normalization unit is specifically configured to 16. The apparatus of claim 11, wherein, ​ According to each of the at least one element attribute, a conversion process is performed on each of the at least one element attribute to obtain a relationship attribute of the element attribute; and According to the relationship attribute of each of the element attributes, at least one candidate normalized medical element of the medical element to be processed is obtained.

17. The apparatus of claim 16, wherein, The conversion process includes at least one of synonym processing and hypernym processing.

18. The apparatus of any of claims 11-17, wherein, The normalization unit is further configured to input the medical element to be processed into a pre-constructed feature model to obtain a vector representation of the medical element to be processed; obtain a similarity parameter between each of the at least one standard normalized medical element and the medical element to be processed according to the vector representation of each of the at least one standard normalized medical element and the vector representation of the medical element to be processed; and and obtain at least one candidate normalized medical element of the medical element to be processed according to the similarity parameter between each of the at least one standard normalized medical element and the medical element to be processed.

19. The apparatus of claim 18, wherein, The normalization unit is further configured to construct the feature model by using a supervised learning method; or construct the feature model by using an unsupervised learning method; or construct the feature model by using a semi-supervised learning method.

20. The apparatus of claim 18, wherein, The normalization unit is specifically configured to select a standard normalized medical element with a similarity parameter greater than or equal to a similarity threshold as a candidate normalized medical element of the medical element to be processed.

21. An apparatus, comprising: The device comprises: one or more processors; a storage device configured to store one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1-10.

22. A computer readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the method according to any one of claims 1-10.

Images