CN117763207B

CN117763207B - Method and system for establishing skin-specialized two-class disease-specific database

Info

Publication number: CN117763207B
Application number: CN202410196958.6A
Authority: CN
Inventors: 蒋献; 陈思良; 刘绪; 杜丹; 张璐
Original assignee: West China Hospital of Sichuan University
Current assignee: West China Hospital of Sichuan University
Priority date: 2024-02-22
Filing date: 2024-02-22
Publication date: 2024-04-30
Anticipated expiration: 2044-02-22
Also published as: CN117763207A

Abstract

The invention relates to the technical field of databases, and discloses a method for establishing a skin professional two-class disease-specific database, which comprises the following steps: carrying out feature position calibration on project feature phrases to obtain an initial calibration hierarchical structure, and sequentially connecting a1 st calibration feature position, a 2 nd calibration feature position,And (3) the nth nominal feature position to obtain a feature phrase branch diameter, filling the current medical record disease name into a diagnosis disease name leaf node to obtain a feature phrase She Jing, obtaining an initial medical record index tree diagram if the current standard medical record is extracted, judging whether a novel standard medical record exists, and updating the target medical record index tree diagram if the novel standard medical record exists to obtain the target medical record index tree diagram. The invention also provides a system for establishing the skin professional two-class special disease database, electronic equipment and a computer readable storage medium. The invention can solve the problems that the current database for storing the skin medical data is not strong in storage structure and poor in data classification effect.

Description

Method and system for establishing skin-specialized two-class disease-specific database

Technical Field

The invention relates to the technical field of databases, in particular to a method, a system, electronic equipment and a computer readable storage medium for establishing a skin professional two-class disease database.

Background

Skin diseases are common frequently occurring diseases, and the treatment and nursing of the skin diseases need professional medical knowledge and abundant diagnosis and treatment experience. Since the relevant medical knowledge of skin diseases is rather bulky, in order to facilitate better learning and management of skin disease medical data, it is often possible to store skin disease medical data by means of constructing a database.

The current storage and management of the skin disease medical data are generally simple to store related data according to skin disease names, and the medical data belonging to different skin diseases are usually stored in the same storage node, so that the medical personnel can conveniently search, but the medical data storage mode has the advantages of simple structure classification and incapability of deeply mining hidden relations among the medical data, so that the database for storing the skin medical data at present has the problems of weak storage structure and poor data classification effect.

Disclosure of Invention

The invention provides a method, a system and a computer-readable storage medium for establishing a skin professional two-class special disease database, which mainly aim to solve the problems that the current database for storing skin medical data is not strong in storage structure and poor in data classification effect.

In order to achieve the above object, the present invention provides a method for establishing a database of skin-specific two-class specific diseases, comprising:

Acquiring a skin diagnosis and treatment item set and a skin disease name set, and sequentially extracting skin diagnosis and treatment items in the skin diagnosis and treatment item set, wherein the skin diagnosis and treatment item set comprises a cause item, a clinical manifestation item, a laboratory examination item, a treatment item and a prevention item;

Acquiring a project feature phrase set of the skin disease name set on a skin diagnosis and treatment project, and calibrating the feature position of each project feature phrase in the project feature phrase set to obtain an initial calibration hierarchical structure;

Sequentially extracting current standard medical records in a pre-constructed current standard medical record set, obtaining the current medical record disease name of the current standard medical record, identifying the 1 st project characteristic phrase, the 2 nd project characteristic phrase, the current standard medical record, An nth project feature phrase;

Identifying the 1 st project feature phrase, the 2 nd project feature phrase, The 1 st calibration feature position, the 2 nd calibration feature position and the/>, of the nth project feature phrase in the initial calibration hierarchical structureAn nth calibration feature position;

the 1 st calibration characteristic position, the 2 nd calibration characteristic position are connected in sequence, The nth calibration feature position is used for obtaining the feature phrase branch diameter of the current standard medical record;

Constructing and connecting diagnostic disease name leaf nodes at the nth calibration characteristic positions, and filling the current medical record disease names into the diagnostic disease name leaf nodes to obtain characteristic phrases She Jing of the current standard medical record;

Judging whether the current standard medical record is extracted;

if the current standard medical record is not extracted, returning to the step of sequentially extracting the current standard medical record in the pre-constructed current standard medical record set;

If the current standard medical record is extracted, obtaining an initial medical record index tree diagram;

judging whether a novel standard medical record exists;

if a new standard medical record exists, updating the initial medical record index tree diagram according to the new standard medical record to obtain a target medical record index tree diagram;

if no new standard medical record exists, the initial medical record index tree diagram is used as a target medical record index tree diagram, and the establishment of the skin major two-class special disease database is completed.

Optionally, the acquiring the item feature phrase set of the skin disease name set on the skin diagnosis and treatment item includes:

Sequentially extracting skin disease names from the skin disease name set;

Acquiring a disease name project phrase set of the skin disease name on the skin diagnosis and treatment project;

Summarizing the disease name project phrase sets of all skin disease names to obtain a plurality of groups of disease name project phrase sets;

and executing a union calculation operation on the plurality of groups of disease name project phrase sets by using a pre-constructed union formula to obtain the project feature phrase set.

Optionally, the union formula is as follows:

Wherein, Item feature phrase set representing the ith skin treatment item,/>A set of disease name project phrases representing the 1 st skin disease name,/>A set of disease name project phrases representing the 2 nd skin disease name,/>A set of patient item phrases representing the mth skin patient name.

Optionally, the performing feature location calibration on each item feature phrase in the item feature phrase set to obtain an initial calibration hierarchical structure includes:

acquiring the feature word frequency of each project feature phrase in the project feature phrase set;

constructing an item normal distribution map of the item feature phrase set in a pre-constructed normal coordinate system according to the feature word frequency, wherein an x axis of the normal coordinate system is an item feature phrase category, and a y axis is a feature word frequency;

Identifying phrase arrangement sequences of the project feature phrases in the project normal distribution diagram, and sorting the project feature phrases according to the phrase arrangement sequences to obtain a project feature phrase sequence;

And carrying out position calibration on the project feature phrases according to the serial number of each project feature phrase in the project feature phrase sequence to obtain the calibrated positions of the project feature phrases until the position calibration is completed on all the project feature phrases on the skin diagnosis and treatment project to obtain the initial calibration hierarchical structure.

Optionally, before the step of obtaining the set of skin disease names from the set of item feature phrases on the skin treatment item, the method further includes:

ordering the skin diagnosis and treatment items in the skin diagnosis and treatment item set to obtain a skin diagnosis and treatment item sequence;

Identifying the item serial number of each skin diagnosis and treatment item in the skin diagnosis and treatment item sequence, and determining the tree-shaped level of the skin diagnosis and treatment item according to the item serial number;

And superposing tree-shaped hierarchies of all the skin diagnosis and treatment projects according to the project serial numbers to obtain a diagnosis and treatment project hierarchy structure.

Optionally, before the current standard medical records are sequentially extracted from the pre-constructed current standard medical record set, the method further includes:

acquiring a history medical record set, and sequentially extracting history medical records from the history medical record set;

classifying medical record data of the historical medical record according to the skin diagnosis and treatment project to obtain a1 st project historical phrase, a2 nd project historical phrase, An nth project history phrase;

receiving the history phrase of the 1 st item, the history phrase of the 2 nd item, Standardized correction of the nth item history phrase to obtain a current standard medical record;

And summarizing all the current standard medical records to obtain the current standard medical record set.

Optionally, the identifying the 1 st item feature phrase, the 2 nd item feature phrase,The 1 st calibration feature position, the 2 nd calibration feature position and the/>, of the nth project feature phrase in the initial calibration hierarchical structureAn nth calibration feature location, comprising:

Identifying the 1 st project feature phrase, the 2 nd project feature phrase, Tree level 1, tree level 2, v/v of the nth item feature phraseAn nth tree level;

Extracting the characteristic phrase of the 1 st item, the characteristic phrase of the 2 nd item, The nth item feature phrase is at the 1 st tree level, the 2 nd tree level,/>The calibration positions in the nth tree level are obtained to obtain the 1 st calibration characteristic position, the 2 nd calibration characteristic position and the +/-And (5) the nth calibration characteristic position.

Optionally, the determining whether the new standard medical record exists includes:

Acquiring a current medical record set, classifying medical record data of the current medical record set according to the skin diagnosis and treatment project set to obtain a1 st project current phrase set, a 2 nd project current phrase set, a third project current phrase set and a fourth project current phrase set, An nth project current phrase set;

For the 1 st item current phrase set, the 2 nd item current phrase set, The current phrase set of the nth item is subjected to standardized correction to obtain a standard phrase set of the 1 st item, a standard phrase set of the 2 nd item and a/>An nth project standard phrase set;

Acquiring an initial project feature phrase set in the initial medical record index tree diagram;

judging the standard phrase set of the 1 st item, the standard phrase set of the 2 nd item, Whether the nth project standard phrase set is contained in the initial project characteristic phrase set in the initial medical record index tree diagram;

If the 1 st item standard phrase set, the 2 nd item standard phrase set, The n-th item standard phrase set is contained in the initial item characteristic phrase set in the initial medical record index tree diagram, and a novel standard medical record does not exist;

If the 1 st item standard phrase set, the 2 nd item standard phrase set, And if the n-th item standard phrase set is not included in the initial item characteristic phrase set in the initial medical record index tree diagram, a novel standard medical record exists.

Optionally, the updating the initial medical record index tree diagram according to the new standard medical record to obtain a target medical record index tree diagram includes:

Solving the 1 st item standard phrase set, the 2 nd item standard phrase set, A difference project standard phrase set of the nth project standard phrase set and the initial project characteristic phrase set;

Sequentially extracting the standard phrases of the difference project from the standard phrases set of the difference project;

Identifying a tree level of the differential project standard phrase;

filling the standard phrases of the difference project into the tree-shaped hierarchy, and calibrating the positions of the standard phrases to obtain a target calibration hierarchy structure;

Identifying the 1 st novel calibration position of each project feature phrase in the novel standard medical record in the target calibration hierarchical structure 2 nd new calibration position, An nth novel calibration position;

the 1 st novel calibration position, the 2 nd novel calibration position are connected in sequence, Obtaining a new phrase branch diameter of the new standard medical record at the nth new calibration position;

And identifying novel medical record disease names of the novel standard medical record, constructing and connecting diagnostic disease name leaf nodes at the nth novel calibration position, filling the novel medical record disease names into the diagnostic disease name leaf nodes, and obtaining a target medical record index tree-shaped chart.

Optionally, the step of obtaining the 1 st item standard phrase set, the 2 nd item standard phrase set,A set of difference project standard phrases of an nth project standard phrase set with the initial project feature phrase set, comprising:

the standard phrase set of the 1 st item, the standard phrase set of the 2 nd item, A difference project standard phrase set of the nth project standard phrase set and the initial project feature phrase set:

Wherein, Representing a standard phrase set of difference items,/>Representing an initial set of project feature phrases,/>Represents item 1 standard phrase set,/>Representing item 2 Standard phrase set,/>Representing the standard phrase set for the nth item.

In order to solve the above problems, the present invention further provides a system for establishing a skin-specific two-class disease database, the system comprising:

The initial calibration hierarchical structure construction module is used for acquiring a skin diagnosis and treatment item set and a skin disease name set, and sequentially extracting skin diagnosis and treatment items from the skin diagnosis and treatment item set, wherein the skin diagnosis and treatment item set comprises a cause item, a clinical manifestation item, a laboratory examination item, a treatment item and a prevention item; acquiring a project feature phrase set of the skin disease name set on a skin diagnosis and treatment project, and calibrating the feature position of each project feature phrase in the project feature phrase set to obtain an initial calibration hierarchical structure;

The project feature phrase extraction module is used for sequentially extracting current standard medical records in a pre-constructed current standard medical record set, obtaining the current medical record disease name of the current standard medical record, and identifying the 1 st project feature phrase, the 2 nd project feature phrase, the third project feature phrase and the fourth project feature phrase of the current standard medical record, An nth project feature phrase;

The initial medical record index tree diagram construction module is used for identifying the 1 st project feature phrase, the 2 nd project feature phrase, The 1 st calibration feature position, the 2 nd calibration feature position and the/>, of the nth project feature phrase in the initial calibration hierarchical structureAn nth calibration feature position; sequentially connecting the 1 st calibration characteristic position, the 2 nd calibration characteristic position and the/>The nth calibration feature position is used for obtaining the feature phrase branch diameter of the current standard medical record; constructing and connecting diagnostic disease name leaf nodes at the nth calibration characteristic positions, and filling the current medical record disease names into the diagnostic disease name leaf nodes to obtain characteristic phrases She Jing of the current standard medical record; judging whether the current standard medical record is extracted; if the current standard medical record is not extracted, returning to the step of sequentially extracting the current standard medical record in the pre-constructed current standard medical record set; if the current standard medical record is extracted, obtaining an initial medical record index tree diagram;

The initial medical record index tree diagram updating module is used for judging whether a novel standard medical record exists or not; if a new standard medical record exists, updating the initial medical record index tree diagram according to the new standard medical record to obtain a target medical record index tree diagram; and if the new standard medical record does not exist, taking the initial medical record index tree diagram as a target medical record index tree diagram.

In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:

at least one processor; and

A memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor to implement the method of skin-specific two-class disease database creation described above.

In order to solve the above-mentioned problems, the present invention also provides a computer-readable storage medium having stored therein at least one instruction that is executed by a processor in an electronic device to implement the method for creating the skin-specific two-class spot database described above.

Compared with the phenomenon described in the background art, the method is characterized in that the project feature phrase set is structurally stored in a mode of constructing the target medical record index tree diagram, firstly, a hierarchical structure of the target medical record index tree diagram, namely an initial calibration hierarchical structure, is required to be constructed, because different skin diagnosis and treatment projects usually correspond to different project feature phrase sets, skin diagnosis and treatment projects can be sequentially extracted in the skin diagnosis and treatment project set, each skin diagnosis and treatment project can independently represent a hierarchy, then, the project feature phrase set of the skin disease name set on the skin diagnosis and treatment project is acquired, finally, feature position calibration is carried out on each project feature phrase in the project feature phrase set to obtain an initial calibration hierarchical structure, at the moment, the current standard medical record needs to be sequentially extracted in a pre-constructed current standard medical record set, then, the current medical record disease name of the current standard medical record is acquired, the 1 st project feature phrase, the 2 nd project feature phrase of the current standard medical record are identified,Nth item feature phrase, due to 1 st item feature phrase, 2 nd item feature phrase,/>The nth item feature phrase has the relationship belonging to the same skin disease, so the relationship can be obtained through the 1 st item feature phrase, the 2 nd item feature phrase,/>The nth project feature phrase correlates project feature phrases in the initial calibration hierarchy, thus requiring identification of the 1 st project feature phrase, 2 nd project feature phrase,/>The 1 st calibration feature position, the 2 nd calibration feature position and the/>, of the nth project feature phrase in the initial calibration hierarchical structureThe nth calibration characteristic position is sequentially connected with the 1 st calibration characteristic position, the 2 nd calibration characteristic position and the/>And (3) an nth calibration feature position to obtain a feature phrase branch diameter of the current standard medical record, wherein each feature phrase branch diameter corresponds to a current medical record disease name, so that a diagnosis disease name leaf node is required to be constructed and connected at the nth calibration feature position, the current medical record disease name is filled into the diagnosis disease name leaf node to obtain a feature phrase She Jing of the current standard medical record, finally, whether the current standard medical record is extracted is judged, if the current standard medical record is not extracted, the extraction is continued, if the current standard medical record is extracted, an initial medical record index tree diagram is obtained, and finally, because a novel standard medical record possibly exists, in order to supplement data information of the novel standard medical record into the initial medical record index tree diagram, the initial medical record index tree diagram is required to be updated according to the novel standard medical record, and a target medical record index tree diagram is obtained, and if the novel standard medical record does not exist, the initial index tree diagram is directly used as the target index tree diagram. Therefore, the method, the system, the electronic equipment and the computer readable storage medium for establishing the skin professional two-class special disease database can solve the problems that the current database for storing skin medical data is not strong in storage structure and poor in data classification effect.

Drawings

FIG. 1 is a flow chart of a method for creating a database of skin-specific two-class specific diseases according to an embodiment of the present invention;

FIG. 2 is a functional block diagram of a system for creating a database of skin-specific two-class specific diseases according to an embodiment of the present invention;

fig. 3 is a schematic structural diagram of an electronic device for implementing the method for creating the skin-specific two-class disease database according to an embodiment of the present invention.

The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.

The embodiment of the application provides a method for establishing a database of skin-specific two-class special diseases. The execution subject of the method for establishing the skin professional two-class disease database comprises, but is not limited to, at least one of a server, a terminal and the like which can be configured to execute the method provided by the embodiment of the application. In other words, the method for building the skin-specific two-class disease database may be performed by software or hardware installed in a terminal device or a server device. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.

Example 1:

referring to fig. 1, a flow chart of a method for creating a database of skin-specific two-class specific diseases according to an embodiment of the invention is shown. In this embodiment, the method for establishing the skin-specific two-category disease database includes:

S1, acquiring a skin diagnosis and treatment item set and a skin disease name set, and sequentially extracting skin diagnosis and treatment items in the skin diagnosis and treatment item set, wherein the skin diagnosis and treatment item set comprises a cause item, a clinical manifestation item, a laboratory examination item, a treatment item and a prevention item.

The set of skin treatment items may be explained to refer to individual items of a patient with skin disease that are to be treated, for example: etiology item, clinical manifestation item, laboratory examination item, treatment item, prevention item, etc., the set of skin disease names refers to a set of skin disease names, such as: acne, flat wart, plantar wart, toe wart, callus, onychomycosis, tinea pedis, tinea corporis, seborrheic dermatitis, and dermatitis.

S2, acquiring a project feature phrase set of the skin disease name set on the skin diagnosis and treatment project, and calibrating the feature position of each project feature phrase in the project feature phrase set to obtain an initial calibration hierarchical structure.

It is understood that the term feature phrase set refers to a feature phrase set of a skin disease name on a specific skin treatment project, and that a skin disease typically has a plurality of feature phrases in a skin treatment project, for example: when the skin diagnosis and treatment project is a causative project and the skin disease is psoriasis, the project feature phrase set on the causative project can be: familial inheritance, immune abnormality, drug stimulation, etc.; when the skin diagnosis and treatment project is a causative project and the skin disease is seborrheic dermatitis, the project feature phrase set on the causative project may be: malassezia infection, endocrine dysfunction, digestive dysfunction, drug irritation, and the like; when the skin diagnosis and treatment project is a clinical manifestation project and the skin disease is psoriasis, the project feature phrase set on the etiology project can be: itching, erythema, scaling, etc.; when the skin diagnosis and treatment project is a clinical manifestation project and the skin disease is named mycosis fungoides, the project feature phrase set on the etiology project can be: white scales distributed in a sheet shape, evenly distributed punctiform blood vessels, dark red background of a dermatoscope and the like; when the skin diagnosis and treatment project is a clinical manifestation project and the skin disease is chronic eczema, the project feature phrase set on the etiology project can be as follows: unevenly distributed punctate blood vessels, spongy blisters, flaky/diffuse yellow scales, dark red background of the dermatoscope, etc. The project feature phrase needs to be determined according to a professional doctor to ensure the specificity and authority of naming, and is not described in detail herein.

It should be appreciated that the feature location calibration refers to hierarchical location calibration of the project feature phrase, for example: the etiology project is a first layer, the clinical manifestation project is a second layer, the laboratory examination project is a third layer, each layer should have a corresponding project characteristic phrase set, the first layer can be family genetics, immune abnormality, medicine stimulation, malassezia infection, endocrine dysfunctions, digestion dysfunctions and the like, and the second layer can be: skin itching, skin erythema, scaling, flaky distribution of white scaling, evenly distributed punctate blood vessels, dark red background of the dermatoscope, and the like. Familial inheritance, immune abnormalities, drug irritation, malassezia infection, endocrine dysfunction and digestive dysfunction in the first layer require targeting of the corresponding location, for example: the family inheritance of (a) is first layer first, immune abnormality is first layer second, drug stimulation is first layer third, and so on. The initial calibration hierarchical structure refers to a hierarchical structure in which all project feature phrase sets in each skin diagnosis project are calibrated in position.

In the embodiment of the present invention, before the step of obtaining the item feature phrase set of the skin disease name set on the skin diagnosis and treatment item, the method further includes:

The sequence of skin treatment items may be: etiology item-clinical manifestation item-laboratory examination item-treatment item-prevention item. The item number of the causative item is 1. The tree hierarchy refers to a hierarchy of the skin treatment project in a treatment project hierarchy, for example: the hierarchy of etiology items may be layer 1.

In the embodiment of the present invention, the obtaining the item feature phrase set of the skin disease name set on the skin diagnosis and treatment item includes:

Sequentially extracting skin disease names from the skin disease name set;

The term feature phrase set may be interpreted as referring to the union of the various sets of disease name term phrases, such as: when the project feature phrase sets of the two skin disease names are respectively: when the white scales, the uniformly distributed dot blood vessels, the dark red background of the dermatoscope and the uniformly distributed dot blood vessels, the spongy blisters, the yellow scales distributed in a sheet-like/diffuse manner and the dark red background of the dermatoscope are distributed in a sheet-like manner, the item feature phrase set can be the white scales distributed in a sheet-like manner, the uniformly distributed dot blood vessels, the dark red background of the dermatoscope, the uniformly distributed dot blood vessels, the spongy blisters and the yellow scales distributed in a sheet-like/diffuse manner. I.e. the dark red background of the dermatome needs to be removed.

In the embodiment of the invention, the union formula is as follows:

In the embodiment of the present invention, the performing feature location calibration on each item feature phrase in the item feature phrase set to obtain an initial calibration hierarchical structure includes:

Further, the feature word frequency refers to the frequency of occurrence of feature phrases of the project, for example: the feature word frequency was 0.7 when 700 out of 1000 medical records had a dark-red background of the dermatoscope. The term normal distribution map refers to a normal distribution map which uses an x axis as a term feature phrase category and uses a y axis as a feature word frequency and represents the feature word frequency distribution of the term feature phrase, wherein the larger the feature word frequency is, the closer the feature word frequency is to a middle position, the smaller the feature word frequency is, and the more the feature word frequency is deviated from the center position. In order to enable the obtained target medical record index tree diagram to present the middle dense specific, the project feature phrase with large feature word frequency is placed in the middle position.

S3, sequentially extracting current standard medical records in a pre-constructed current standard medical record set, obtaining the current medical record disease name of the current standard medical record, and identifying the 1 st project characteristic phrase, the 2 nd project characteristic phrase, the third project characteristic phrase, the fourth project characteristic phrase and the fourth project characteristic phrase of the current standard medical record,And (5) the nth project feature phrase.

As can be appreciated, the current standard medical record refers to a history of dermatological medical records modified by a practitioner. Since words in the history of the skin disease may come in and go out with the project feature phrase, corrections are required.

In the embodiment of the present invention, before the current standard medical records are sequentially extracted from the pre-constructed current standard medical record set, the method further includes:

Understandably, the 1 st project history phrase, the 2 nd project history phrase,The nth item history phrase refers to the skin disease diagnosis and treatment item belonging to the item number 1 and the skin disease diagnosis and treatment item of the item number 2 in the history medical record respectively,/>And the item feature phrase of the dermatological treatment item with the item serial number n.

S4, identifying the 1 st project feature phrase, the 2 nd project feature phrase,The 1 st calibration feature position, the 2 nd calibration feature position and the/>, of the nth project feature phrase in the initial calibration hierarchical structureAnd (5) the nth calibration characteristic position.

Further, the 1 st calibration characteristic position, the 2 nd calibration characteristic position,The nth calibration feature position refers to the 1 st project feature phrase, the 2 nd project feature phrase and the/>, respectivelyCalibration location of the nth item feature phrase in the initial calibration hierarchy, for example: the calibration position of immune abnormality is 1 st layer 1 st sequence number position, and the uniformly distributed punctiform blood vessels are 7 th sequence number position of the second layer.

In the embodiment of the invention, the 1 st project feature phrase, the 2 nd project feature phrase,The 1 st calibration feature position, the 2 nd calibration feature position and the/>, of the nth project feature phrase in the initial calibration hierarchical structureAn nth calibration feature location, comprising:

It can be appreciated that the 1 st tree level, the 2 nd tree level,The nth tree level refers to 1 item feature phrase, 2 item feature phrase and/or > respectivelyThe nth project feature phrase is hierarchical in the initial calibration hierarchy.

S5, sequentially connecting the 1 st calibration characteristic position, the 2 nd calibration characteristic position,And (5) calibrating the characteristic position by the nth time to obtain the characteristic phrase branch diameter of the current standard medical record.

The feature phrase branch path refers to a path of each item feature phrase in the current standard medical record after being sequentially connected in an initial calibration hierarchical structure.

And S6, constructing and connecting a diagnosis disease name leaf node at the nth calibration characteristic position, and filling the current medical record disease name into the diagnosis disease name leaf node to obtain a characteristic phrase She Jing of the current standard medical record.

It will be appreciated that the diagnostic disease name leaf node is only used to represent leaf nodes of skin disease names. The nth calibration feature position is the last item feature phrase of the current standard medical record, and all item feature phrases in the current standard medical record are extracted at the moment, so that a leaf node can be linked at the last nth calibration feature position, and the leaf node is used for indicating the skin disease name in the current standard medical record. The feature phrase She Jing refers to the feature phrase branch path that connects the diagnostic disease name leaf nodes.

And S7, judging whether the current standard medical record is extracted.

The data in the current standard medical record set can be interpreted to hide the connection between the feature phrases of each project, so that the current standard medical record in the current standard medical record set needs to be extracted until the current standard medical record is extracted.

And if the current standard medical record is not completely extracted, returning to the step of sequentially extracting the current standard medical record in the pre-constructed current standard medical record set.

And if the current standard medical record is completely extracted, executing S8 to obtain an initial medical record index tree diagram.

It can be appreciated that the initial medical record index tree graph refers to a tree graph constructed from links between project feature phrases of each current standard medical record in the current standard medical record set.

S9, judging whether a novel standard medical record exists.

Further, the new standard medical record refers to a modified medical record that contains a new dermatological disease name, a new project feature phrase, or a new association between project feature phrases.

In the embodiment of the invention, the judging whether the novel standard medical record exists comprises the following steps:

And if the new standard medical record exists, executing S10, and updating the initial medical record index tree diagram according to the new standard medical record to obtain a target medical record index tree diagram.

The target medical record index tree diagram can be explained to be a tree diagram after the initial medical record index tree diagram is updated by using project standard phrases in the novel standard medical record.

In the embodiment of the present invention, the updating the initial medical record index tree diagram according to the new standard medical record to obtain the target medical record index tree diagram includes:

Identifying a tree level of the differential project standard phrase;

It should be appreciated that the set of difference project standard phrases refers to the set of 1 st project standard phrases, the set of 2 nd project standard phrases,A set of project feature phrases that does not exist in the set of initial project feature phrases in the nth set of project standard phrases. Filling and calibrating the standard phrase type of the difference project can fill the standard phrase type of the difference project to the last position of the corresponding tree level. The 1 st novel calibration position, the 2 nd novel calibration position,/>And the nth new calibration position refers to the calibration position of each project standard phrase in each tree-shaped level in the new standard medical record.

In the embodiment of the invention, the 1 st project standard phrase set, the 2 nd project standard phrase set, the,A set of difference project standard phrases of an nth project standard phrase set with the initial project feature phrase set, comprising:

And if the new standard medical record does not exist, executing S11, and taking the initial medical record index tree diagram as a target medical record index tree diagram to complete the establishment of the skin major two-class special disease database.

Further, when the related project feature phrase set of the patient is obtained, the project feature phrase set can be utilized to compare in the target medical record index tree diagram, so that a path capable of outputting the skin disease names is gradually formed, and the leaf nodes of the path are identified, so that the classification diagnosis of the skin disease names of the patient can be realized, namely the skin disease names pointed by the path are changed into one type, and the other skin disease names are changed into the other type.

Example 2:

Fig. 2 is a functional block diagram of a system for creating a database of skin-specific two-class specific diseases according to an embodiment of the present invention.

The system 100 for establishing the skin-specific two-class disease database according to the present invention may be installed in an electronic device. Depending on the implementation, the system 100 for building a skin-specific two-category disease database may include an initial calibration hierarchy building module 101, a project feature phrase extraction module 102, an initial medical record index tree diagram building module 103, and an initial medical record index tree diagram updating module 104. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.

The initial calibration hierarchical structure construction module 101 is configured to obtain a skin diagnosis and treatment item set and a skin disease name set, and sequentially extract skin diagnosis and treatment items in the skin diagnosis and treatment item set, where the skin diagnosis and treatment item set includes a etiology item, a clinical manifestation item, a laboratory examination item, a treatment item and a prevention item; acquiring a project feature phrase set of the skin disease name set on a skin diagnosis and treatment project, and calibrating the feature position of each project feature phrase in the project feature phrase set to obtain an initial calibration hierarchical structure;

The project feature phrase extracting module 102 is configured to sequentially extract current standard medical records from a pre-constructed current standard medical record set, obtaining the current medical record disease name of the current standard medical record, identifying the 1 st project characteristic phrase, the 2 nd project characteristic phrase, the current standard medical record, An nth project feature phrase;

The initial medical record index tree diagram construction module 103 is configured to identify the 1 st item feature phrase, the 2 nd item feature phrase, The 1 st calibration feature position, the 2 nd calibration feature position and the/>, of the nth project feature phrase in the initial calibration hierarchical structureAn nth calibration feature position; sequentially connecting the 1 st calibration characteristic position, the 2 nd calibration characteristic position and the/>The nth calibration feature position is used for obtaining the feature phrase branch diameter of the current standard medical record; constructing and connecting diagnostic disease name leaf nodes at the nth calibration characteristic positions, and filling the current medical record disease names into the diagnostic disease name leaf nodes to obtain characteristic phrases She Jing of the current standard medical record; judging whether the current standard medical record is extracted; if the current standard medical record is not extracted, returning to the step of sequentially extracting the current standard medical record in the pre-constructed current standard medical record set; if the current standard medical record is extracted, obtaining an initial medical record index tree diagram;

The initial medical record index tree diagram updating module 104 is configured to determine whether a new standard medical record exists; if a new standard medical record exists, updating the initial medical record index tree diagram according to the new standard medical record to obtain a target medical record index tree diagram; and if the new standard medical record does not exist, taking the initial medical record index tree diagram as a target medical record index tree diagram.

In detail, the modules in the system 100 for establishing a skin specific two-class disease database in the embodiment of the present invention use the same technical means as the method for establishing a skin specific two-class disease database in fig. 1, and can produce the same technical effects, which are not described herein.

Example 3:

fig. 3 is a schematic structural diagram of an electronic device for implementing a method for creating a database of skin-specific two-class specific diseases according to an embodiment of the present invention.

The electronic device 1 may comprise a processor 10, a memory 11, a bus 12 and a communication interface 13, and may further comprise a computer program stored in the memory 11 and executable on the processor 10, such as a program built up in a skin professional two-class specific disease database.

The memory 11 includes at least one type of readable storage medium, including flash memory, a mobile hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may in other embodiments also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only for storing application software installed in the electronic device 1 and various types of data, such as codes of programs established in the skin-specific two-class disease database, but also for temporarily storing data that has been output or is to be output.

The processor 10 may be comprised of integrated circuits in some embodiments, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects the respective components of the entire electronic device using various interfaces and lines, executes or executes programs or modules (for example, programs established in a skin-specific two-class disease database, etc.) stored in the memory 11, and invokes data stored in the memory 11 to perform various functions of the electronic device 1 and process the data.

The bus may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus, or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc.

Fig. 3 shows only an electronic device with components, it being understood by a person skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or may be arranged in different components.

For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for supplying power to the respective components, and preferably, the power source may be logically connected to the at least one processor 10 through a power management system, so as to perform functions of charge management, discharge management, and power consumption management through the power management system. The power supply may also include one or more of any of a direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like. The electronic device 1 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which will not be described herein.

Further, the electronic device 1 may also comprise a network interface, optionally the network interface may comprise a wired interface and/or a wireless interface (e.g. WI-FI interface, bluetooth interface, etc.), typically used for establishing a communication connection between the electronic device 1 and other electronic devices.

The electronic device 1 may optionally further comprise a user interface, which may be a Display, an input unit, such as a Keyboard (Keyboard), or a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device 1 and for displaying a visual user interface.

It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.

The program created by the skin-specific two-class-specific database stored in the memory 11 of the electronic device 1 is a combination of instructions that, when executed in the processor 10, can implement:

Judging whether the current standard medical record is extracted;

judging whether a novel standard medical record exists;

Specifically, the specific implementation method of the above instruction by the processor 10 may refer to descriptions of related steps in the corresponding embodiments of fig. 1 to 2, which are not repeated herein.

Further, the modules/units integrated in the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. The computer readable storage medium may be volatile or nonvolatile. For example, the computer readable medium may include: any entity or system capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).

The present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, can implement:

Judging whether the current standard medical record is extracted;

judging whether a novel standard medical record exists;

In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus, system and method may be implemented in other manners. For example, the system embodiments described above are merely illustrative, e.g., the division of the modules is merely a logical function division, and other manners of division may be implemented in practice.

The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.

Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for building a skin-specific two-class disease database, the method comprising:

Sequentially extracting current standard medical records from a pre-constructed current standard medical record set, acquiring the current medical record disease name of the current standard medical record, and identifying the 1 st item feature phrase, the 2 nd item feature phrase, ⋯ th item feature phrase and the nth item feature phrase of the current standard medical record;

identifying a 1 st calibration feature position, a 2 nd calibration feature position, a ⋯ th calibration feature position and an n th calibration feature position of the 1 st project feature phrase, the 2 nd project feature phrase, ⋯ th project feature phrase and the n th project feature phrase in the initial calibration hierarchical structure;

Sequentially connecting the 1 st calibration characteristic position, the 2 nd calibration characteristic position, ⋯ th calibration characteristic position and the nth calibration characteristic position to obtain the characteristic phrase branch diameter of the current standard medical record;

Judging whether the current standard medical record is extracted;

judging whether a novel standard medical record exists;

2. The method for building a skin-specific two-category-specific database according to claim 1, wherein the obtaining the set of item feature phrases on the skin treatment item comprises:

Sequentially extracting skin disease names from the skin disease name set;

3. The method of creating a skin-specific two-class-specific database according to claim 2, wherein the union formula is as follows:

c_i=b_1∪b_2∪⋯∪b_m

Wherein c_i represents the item feature phrase set of the ith skin treatment item, b_1 represents the patient name item phrase set of the 1 st skin disease name, b_2 represents the patient name item phrase set of the 2 nd skin disease name, and b_m represents the patient name item phrase set of the m th skin disease name.

4. The method for building a skin-specific two-category disease database according to claim 2, wherein the performing feature location calibration on each item feature phrase in the set of item feature phrases to obtain an initial calibration hierarchy includes:

5. The method of claim 1, wherein prior to the step of obtaining the set of skin condition names from the set of project feature phrases on the skin treatment project, the method further comprises:

6. The method for creating the skin-specific two-category-specific database according to claim 1, wherein before the current standard medical records are sequentially extracted from the pre-constructed current standard medical record set, the method further comprises:

classifying medical record data of the historical medical record according to the skin diagnosis and treatment project to obtain a1 st project historical phrase, a 2 nd project historical phrase, ⋯ th project historical phrase and an nth project historical phrase;

Receiving standardized correction of the 1 st project history phrase, the 2 nd project history phrase, ⋯ th project history phrase and the nth project history phrase by a user to obtain a current standard medical record;

7. The method of claim 1-6, wherein identifying the 1 st item feature phrase, the 2 nd item feature phrase, the ⋯ nd item feature phrase, the 1 st calibration feature location, the 2 nd calibration feature location, the ⋯ nd calibration feature location in the initial calibration hierarchy comprises:

Identifying the 1 st item feature phrase, the 2 nd item feature phrase, ⋯, the 1 st tree level, the 2 nd tree level, ⋯, the n th tree level of the n-th item feature phrase;

and extracting the calibration positions of the 1 st item feature phrase, the 2 nd item feature phrase, ⋯ th item feature phrase and the n th item feature phrase in the 1 st tree-shaped level, the 2 nd tree-shaped level, ⋯ th tree-shaped level and the n th tree-shaped level to obtain a1 st calibration feature position, a2 nd calibration feature position, ⋯ th calibration feature position and an n th calibration feature position.

8. The method for creating a skin-specific two-category-specific database according to claim 1, wherein the determining whether a new standard medical record exists comprises:

acquiring a current medical record set, and classifying medical record data of the current medical record set according to the skin diagnosis and treatment project set to obtain a 1 st project current phrase set, a2 nd project current phrase set, ⋯ th project current phrase set and an n-th project current phrase set;

performing standardized correction on the 1 st item current phrase set, the 2 nd item current phrase set, ⋯ th item current phrase set and the n th item current phrase set to obtain a1 st item standard phrase set, a2 nd item standard phrase set, ⋯ th item standard phrase set and an n th item standard phrase set;

judging whether the 1 st item standard phrase set, the 2 nd item standard phrase set, ⋯ th item standard phrase set and the n-th item standard phrase set are contained in the initial item characteristic phrase set in the initial medical record index tree diagram;

if the 1 st item standard phrase set, the 2 nd item standard phrase set, ⋯ th item standard phrase set and the n-th item standard phrase set are contained in the initial item feature phrase set in the initial medical record index tree diagram, a novel standard medical record does not exist;

If the 1 st item standard phrase set, the 2 nd item standard phrase set, ⋯ th item standard phrase set, and the n-th item standard phrase set are not included in the initial item feature phrase set in the initial medical record index tree diagram, a new standard medical record exists.

9. The method for building a skin care two-category disease-specific database according to claim 8, wherein updating the initial medical record index tree graph according to the new standard medical record to obtain a target medical record index tree graph comprises:

solving a difference project standard phrase set of the 1 st project standard phrase set, the 2 nd project standard phrase set, ⋯ th project standard phrase set and the initial project characteristic phrase set;

Identifying a tree level of the differential project standard phrase;

Identifying a1 st novel calibration position, a2 nd novel calibration position, ⋯ th novel calibration position and an nth novel calibration position of each project feature phrase in the novel standard medical record in the target calibration hierarchical structure;

Sequentially connecting the 1 st novel calibration position, the 2 nd novel calibration position, ⋯ th novel calibration position and the nth novel calibration position to obtain novel phrase branch diameters of the novel standard medical record;

10. The method of claim 9, wherein said evaluating the set of 1 st item standard phrases, the set of 2 nd item standard phrases, ⋯, the set of n th item standard phrases against the set of initial item feature phrases comprises:

Solving a difference project standard phrase set of the 1 st project standard phrase set, the 2 nd project standard phrase set, ⋯ th project standard phrase set and the initial project characteristic phrase set by using the following steps:

X=(C_n∪d_1∪d_2∪⋯∪d_n )-(C_n∩d_1∩d_2∩⋯∩d_n )

Wherein X represents a difference project standard phrase set, C_n represents an initial project feature phrase set, d_1 represents a1 st project standard phrase set, d_2 represents a2 nd project standard phrase set, and d_n represents an nth project standard phrase set.

11. A system for building a skin-specific two-class disease-specific database, the system comprising:

The project feature phrase extraction module is used for sequentially extracting current standard medical records in a pre-constructed current standard medical record set, obtaining the current medical record disease name of the current standard medical record and identifying the 1 st project feature phrase, the 2 nd project feature phrase, the ⋯ nd project feature phrase and the n-th project feature phrase of the current standard medical record;

The initial medical record index tree diagram construction module is used for identifying the 1st item feature phrase, the 2 nd item feature phrase, ⋯ th item feature phrase and the nth item feature phrase in the 1st calibration feature position, the 2 nd calibration feature position, ⋯ th calibration feature position in the initial calibration hierarchical structure; sequentially connecting the 1st calibration characteristic position, the 2 nd calibration characteristic position, ⋯ th calibration characteristic position and the nth calibration characteristic position to obtain the characteristic phrase branch diameter of the current standard medical record; constructing and connecting diagnostic disease name leaf nodes at the nth calibration characteristic positions, and filling the current medical record disease names into the diagnostic disease name leaf nodes to obtain characteristic phrases She Jing of the current standard medical record; judging whether the current standard medical record is extracted; if the current standard medical record is not extracted, returning to the step of sequentially extracting the current standard medical record in the pre-constructed current standard medical record set; if the current standard medical record is extracted, obtaining an initial medical record index tree diagram;