CN112035120B - Logic code acquisition method and device based on medical data and computer equipment - Google Patents
Logic code acquisition method and device based on medical data and computer equipment Download PDFInfo
- Publication number
- CN112035120B CN112035120B CN202010897805.6A CN202010897805A CN112035120B CN 112035120 B CN112035120 B CN 112035120B CN 202010897805 A CN202010897805 A CN 202010897805A CN 112035120 B CN112035120 B CN 112035120B
- Authority
- CN
- China
- Prior art keywords
- information
- logic
- target
- medical data
- medical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/40—Transformation of program code
- G06F8/41—Compilation
- G06F8/44—Encoding
- G06F8/447—Target code generation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to the field of digital medical treatment, and provides a method, a device and computer equipment for acquiring logic codes based on medical data, wherein the method comprises the following steps: acquiring a plurality of pieces of medical data information in a medical database according to the medical item information; selecting a preset number of pieces of target medical data information, and acquiring main key information and external key information which are associated among the pieces of target medical data information; calculating in a logic processing model to obtain various target operation logics; and acquiring a corresponding logic code according to the target operation logic. The invention has the beneficial effects that: the corresponding logic codes are automatically generated based on the incidence relation among the medical data information, so that repeated and tedious workload of developers is relieved, and the development efficiency is better improved.
Description
Technical Field
The invention relates to the field of digital medical treatment, in particular to a method and a device for acquiring logic codes based on medical data and computer equipment.
Background
At present, when a medical project is developed, because each piece of medical data information (for example, a patient list, a drug list, and a medical record list) has a correlation, some basic logic codes need to be set for the correlation information among each piece of medical data information to facilitate the operation of a user, and many code generation tools are available on the market, which can quickly generate simple operations of adding, deleting, modifying, inquiring and the like for single medical data information, but only logic codes which can be generated for single medical data information lack correlation codes among the medical data information, developers still need to write basic codes among the medical data information, the repeated and tedious workload of the developers is increased, therefore, a method for acquiring logic codes based on medical data based on the relationship between medical data information is needed.
Disclosure of Invention
The invention mainly aims to provide a method, a device and computer equipment for acquiring logic codes based on medical data, and aims to solve the problem that developers need to write basic codes among medical data information.
The invention provides a medical data-based logic code acquisition method, which comprises the following steps:
acquiring a plurality of pieces of medical data information in a medical database according to the medical item information;
selecting a preset number of target medical data information from the plurality of medical data information, and acquiring main key information and external key information which are associated among the target medical data information according to the associated information among the target medical data information;
inputting the main key information, the external key information and the medical item information into a logic processing model for calculation to obtain various target operation logics; the logic processing model is trained on the basis of different combinations of primary key information and foreign key information and sample data consisting of processing codes generated according to the combinations;
and acquiring a corresponding logic code according to the target operation logic.
Further, before the step of selecting a preset number of pieces of target medical data information from the plurality of pieces of medical data information and acquiring the primary key information and the foreign key information associated with the target medical data information according to the associated information between the pieces of target medical data information, the method further includes:
judging whether the medical database has the associated information among the target medical data information or not;
if the target medical data information does not have the associated information, converting the content in the target medical data information into a text string, wherein the text string is composed of a plurality of character strings according to the positions of the character strings in the target medical data information;
extracting key character strings from the character string corresponding to the main key information of one of the target medical data information, and performing feature matching on the character strings corresponding to each foreign key information of other target medical data information through a BM algorithm;
and establishing the associated information of the main key and the foreign key between the target medical data information according to the matching result.
Further, the step of inputting the primary key information, the foreign key information, and the medical item information into a logic processing model for calculation to obtain a plurality of target calculation logics includes:
calculating the primary key information and the external key information to obtain a preliminary operation logic;
by the formula
Calculating a first matching degree of each preliminary operation logic and the medical item information;
judging whether the first matching degree corresponding to each preliminary operation logic reaches a first preset matching degree value or not;
and taking the preliminary operation logic reaching the first preset matching degree value as the target operation logic.
Further, the step of calculating the primary key information and the foreign key information to obtain a preliminary operation logic includes:
vectorizing the main key information and the foreign key information respectively to obtain respective corresponding n-dimensional vectors;
carrying out weighted calculation on the n-dimensional vectors corresponding to the primary key information and the foreign key information respectively to obtain n-dimensional target vectors which are x-dimensional target vectors respectively 1 ，x 2 ，...，x n ；
By G (t) ═ softmax [ vf (t)]Calculating to obtain a plurality of preliminary operation logics; wherein f (t) ═ g [ Ux t +Wf(t-1)+b]G (t) is the preliminary operation logic obtained by inputting the t-th target vector, x t The t-th target vector is shown, f (t) shows an intermediate function obtained by inputting the t-th target vector, and V, U, W, b are all preset parameters.
Further, the step of acquiring a plurality of pieces of medical data information in the medical database according to the medical item information includes:
acquiring the correspondence of the medical item information according to the medical item informationN feature vectors of (a), wherein the n feature vectors are y respectively 1 ，y 2 ，...，y n ；
By the formula
Calculating a second matching degree of the characteristic vector and a pre-stored vector of each piece of medical data information in a medical database; wherein, z is i Represents the ith pre-stored vector, said H (y) i ，z i ) Representing the similarity function of the ith pre-stored vector and the ith eigenvector, w i Representing the weight of the ith pre-stored vector in the medical item information;
judging whether the second matching degree corresponding to each piece of medical data information reaches a second preset matching degree or not;
and extracting the medical data information reaching the second preset matching degree to serve as the target medical data information.
Further, the step of obtaining the corresponding logic code according to the target operation logic includes:
obtaining a plurality of target feature vectors of the target operational logic;
by the formula
Calculating similarity values of the target feature vectors and code vectors corresponding to the logic codes; wherein M represents a set of a plurality of target feature vectors, and N represents a set of code vectors corresponding to one of the logic codes;
judging whether the similarity value is larger than a preset similarity value or not;
if so, taking the corresponding logic code larger than the preset similarity value as the code of the target operation logic.
Further, after the step of obtaining the corresponding logic code according to the target operation logic, the method includes:
acquiring the characteristic value of the logic code, and comparing the characteristic value with the similarity of the special values of various categories in a preset menu;
and programming the logic code into the category with the highest similarity in the preset menu.
The invention also provides a logic code acquisition device based on medical data, which comprises:
the medical data information acquisition module is used for acquiring a plurality of pieces of medical data information in the medical database according to the medical item information;
the relevant information acquisition module is used for selecting a preset number of pieces of target medical data information from the plurality of pieces of medical data information and acquiring main key information and external key information which are relevant among the pieces of target medical data information according to the relevant information among the pieces of target medical data information;
the operation logic calculation module is used for inputting the main key information, the external key information and the medical item information into a logic processing model for calculation to obtain various target operation logics; the logic processing model is trained on the basis of different combinations of primary key information and foreign key information and sample data consisting of processing codes generated according to the combinations;
and the logic code generation module is used for acquiring the corresponding logic code according to the target operation logic.
The invention also provides a computer device comprising a memory storing a computer program and a processor implementing the steps of any of the above methods when the processor executes the computer program.
The invention also provides a computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the method of any of the above.
The invention has the beneficial effects that: the corresponding medical data information in the medical database is obtained through the medical project information, then the associated main key information and the associated foreign key information are obtained according to the selected medical data information, the corresponding target calculation logic is obtained through the logic processing model, and finally the corresponding codes are generated according to the target calculation logic, so that the corresponding logic codes can be automatically generated based on the association relationship between the medical data information, the repeated and tedious workload of developers is relieved, and the development efficiency is better improved.
Drawings
FIG. 1 is a flow chart illustrating a method for obtaining logic code based on medical data according to an embodiment of the present invention;
FIG. 2 is a block diagram schematically illustrating a structure of a medical data-based logic code acquisition apparatus according to an embodiment of the present invention;
fig. 3 is a block diagram illustrating a structure of a computer device according to an embodiment of the present application.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that all directional indicators (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship between the components, the motion situation, etc. in a specific posture (as shown in the drawings), and if the specific posture is changed, the directional indicator is changed accordingly, and the connection may be a direct connection or an indirect connection.
The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and B, may mean: a exists alone, A and B exist simultaneously, and B exists alone.
In addition, descriptions such as "first", "second", etc. in the present invention are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
Referring to fig. 1, the present invention provides a method for acquiring a logic code based on medical data, including:
s1: acquiring a plurality of pieces of medical data information in a medical database according to the medical item information;
s2: selecting a preset number of target medical data information from the plurality of medical data information, and acquiring main key information and external key information which are associated among the target medical data information according to the associated information among the target medical data information;
s3: inputting the main key information, the external key information and the medical item information into a logic processing model for calculation to obtain various target operation logics; the logic processing model is trained on the basis of different combinations of primary key information and foreign key information and sample data consisting of processing codes generated according to the combinations;
s4: and acquiring a corresponding logic code according to the target operation logic.
As described in step S1, a plurality of pieces of medical data information are obtained from the medical database according to the medical item information, where the obtaining manner may be to configure, in a configuration file, connection IP addresses of the medical database, names of instances of the medical database, login accounts, passwords, and other related connection information, and a root directory path of the current item, and the medical database connection configuration may support connections of a plurality of types of medical databases, such as MySql, Oracle, PostgreSQL, SqlServer, and the like; and then acquiring corresponding medical data information according to the requirement of the medical item information.
As described in the above step S2, according to the target medical data information selected by the user and the associated information between the corresponding target medical data information, where the associated information exists only between the primary key information of one of the medical data information and the foreign key information of the other medical data information, the corresponding primary key information and foreign key information may be obtained according to the associated information.
As described in step S3, the operation logic between the primary key information, the foreign key information, and the medical item information can be inferred according to the obtained primary key information, the foreign key information, and the medical item information, for example, the primary key information is a patient list, and the foreign key information is corresponding medical record information, so that the operation logic between the primary key information and the foreign key information can be considered as finding medical record information corresponding to a patient, the operation logic is capturing data, and the like, and the operation logic can also be obtained by adding, modifying, reducing, and the like, to the medical record information, which can be obtained according to the primary key information, the foreign key information, and the medical item information, and thus the operation logic can be input into the logic processing model to obtain a plurality of corresponding target operation logics.
As described in step S4, after the target operation logic is obtained, the logic code corresponding to the target operation logic may be searched in the code medical database, or the corresponding logic code may be automatically generated based on the target operation logic for standby, thereby relieving the repeated and tedious workload of developers and improving the development efficiency.
In one embodiment, before the step S2 of selecting a preset number of pieces of target medical data information from the plurality of pieces of medical data information and acquiring primary key information and foreign key information associated with the pieces of target medical data information according to association information between the pieces of target medical data information, the method further includes:
s101: detecting whether the medical database has correlation information among the target medical data information;
s102: if the target medical data information does not have the associated information, converting the content in the target medical data information into a text string, wherein the text string is composed of a plurality of character strings according to the positions of the character strings in the target medical data information;
s103: extracting key character strings from the character string corresponding to the main key information of one of the target medical data information, and performing feature matching on the character strings corresponding to each foreign key information of other target medical data information through a BM algorithm;
s104: and establishing the associated information of the main key and the foreign key between the target medical data information according to the matching result.
As described in steps S101 to S104, since some medical data information is not associated with other medical data information before being entered into the medical database, and therefore does not have associated information, and it is not possible to subsequently acquire the foreign key information and the primary key information based on the associated information, it is possible to detect whether the selected target medical data information has associated information in the medical database, and when there is no associated information between the medical data information, it is possible to establish an association relationship between the target data as the associated information between the target medical databases. The specific establishing mode is that the content in the target medical data information is converted into individual character strings, then key character strings in the character strings are extracted according to a machine learning model based on natural language processing, then the characteristic matching between the primary key information and the foreign key information is calculated through a BM (Boyer-Moore) algorithm, and the associated information of the primary key and the foreign key between the foreign key information and the primary key information meeting the matching requirement is established. It should be noted that, in general, each piece of medical data information has complex related information, and only relatively simple related information can be established by the above method.
In one embodiment, the step S3 of inputting the primary key information, the foreign key information, and the medical item information into a logic processing model for calculation to obtain a plurality of target calculation logics includes:
s301: calculating the primary key information and the external key information to obtain a preliminary operation logic;
s302: by the formula
Calculate eachA first degree of match of the preliminary operational logic and the medical item information; wherein
Represents any one of the preliminary operation logics described,
representing medical item information;
s303: judging whether the first matching degree corresponding to each preliminary operation logic reaches a first preset matching degree value or not;
s304: and taking the preliminary operation logic reaching the first preset matching degree value as the target operation logic.
As described in steps S301 to S304, in the case of not considering medical item information, all corresponding preliminary operation logics may be obtained by calculation according to the primary key information and the foreign key information, the calculation method may be training according to big data, the training sample data is generated by combining different primary key information and foreign key information and operation logics constructed based on different primary key information and foreign key information, and the sample data may be obtained by the big data. In order to simplify the number of generated preliminary operation logics, the preliminary operation logics irrelevant to the item can be eliminated, specifically, a first matching degree of each preliminary operation logic and the medical item information can be calculated through a formula, when the first matching degree reaches a first preset matching degree value, the corresponding preliminary operation logic can be used as a target operation logic, wherein the first preset matching degree is a preset value, and the algorithm of the matching degree can be any algorithm, such as a WMD (world mover's distance) algorithm, a simhash algorithm, an algorithm based on cosine similarity, an SVM (support vector machine) vector model and the like, preferably, the method is implemented through the steps of
Performing calculation, wherein the preliminary operation logic is more related to the medical item information when the calculation result approaches 1, and the preliminary operation logic is less related to the medical item information when the calculation result approaches 0, and the calculation result is up toThe preliminary operation logic of the first preset matching degree is used as the target operation logic and participates in subsequent calculation analysis, so that the preliminary operation logic which is not the target operation logic can be omitted, the preliminary operation logic does not need to participate in the subsequent operation process, the operation time is saved, and the subsequently generated code is related to the project.
In one embodiment, the step S301 of calculating the primary key information and the foreign key information to obtain a preliminary operation logic includes:
s3011: vectorizing the main key information and the foreign key information respectively to obtain respective corresponding n-dimensional vectors;
s3012: carrying out weighted calculation on the n-dimensional vectors corresponding to the primary key information and the foreign key information respectively to obtain n-dimensional target vectors which are x-dimensional target vectors respectively 1 ，x 2 ，...，x n ；
S3013: by G (t) ═ softmax [ vf (t)]Calculating to obtain a plurality of preliminary operation logics; wherein f (t) ═ g [ Ux t +Wf(t-1)+b]G (t) is the preliminary operation logic obtained by inputting the t-th target vector, x t The t-th target vector is shown, f (t) shows an intermediate function obtained by inputting the t-th target vector, and V, U, W, b are all preset parameters.
As described in the above steps S3011-S3013, the specific formula for obtaining the preliminary operation logic may be that the primary key information and the foreign key information are vectorized, and then weighted calculation is performed, where the weighted calculation may be performed by obtaining a mathematical average or a geometric average, or by assigning different weight coefficients to the primary key information and the foreign key information, and then adding the weighted coefficients, that is, the primary key information and the foreign key information are integrated, so that the generated n-dimensional target vector integrates the contents of the primary key information and the foreign key information, the weighting budget is not limited, and may be used to integrate the information of the primary key information and the foreign key information, and then a plurality of preliminary operation logics are calculated according to a formula g (t) ═ softmax [ vf (t) ], where the number of dimensions of the preliminary operation logics is related to the vector, that is, the more the primary key information and the foreign key information are complex, the number of the generated preliminary operation logics is increased, in addition, V, U, W, b are all trained parameter values, and when the t-th target vector is input, the t-th operation logic can be obtained.
In one embodiment, the step S1 of obtaining a plurality of medical data information in the medical database according to the medical item information includes:
s111: acquiring n corresponding feature vectors according to the medical item information, wherein the n feature vectors are y respectively 1 ，y 2 ，...，y n ；
S112: by the formula
Calculating a second matching degree of the characteristic vector and a pre-stored vector of each piece of medical data information in a medical database; wherein, z is i Represents the ith pre-stored vector, said H (y) i ，z i ) Representing the similarity function of the ith pre-stored vector and the ith eigenvector, w i Representing the weight of the ith pre-stored vector in the medical item information;
s113: judging whether the second matching degree corresponding to each piece of medical data information reaches a second preset matching degree;
s114: and extracting the medical data information reaching the second preset matching degree to serve as the target medical data information.
As described in the foregoing steps S111 to S114, a specific way of extracting the plurality of medical data information from the medical database is to first obtain a plurality of feature vectors according to the medical item information, where the plurality of feature vectors can be used to represent features of the medical item information through the vectors obtained by the medical item information, then calculate a second matching degree of the feature vectors and the pre-stored vectors corresponding to each piece of medical data information, and then determine whether the second matching degree reaches a second preset matching degree, where when the second matching degree reaches the second preset matching degree, it can be considered that the piece of medical data information is the target medical data information required by the medical item information, where the second preset matching degree is a preset value. In addition, because different feature vectors have different degrees of influence on the items, a weight can be given to the value calculated by the feature vector of each item, and then the final second matching degree can be obtained by accumulation.
In one embodiment, the step S4 of generating corresponding logic codes according to the target operation logic includes:
s401: obtaining a plurality of target feature vectors of the target operational logic;
s402: by the formula
Calculating similarity values of the target feature vectors and code vectors corresponding to the logic codes; wherein M represents a set of a plurality of target feature vectors, and N represents a set of code vectors corresponding to one of the logic codes;
s403: judging whether the similarity value is larger than a preset similarity value or not;
s404: if so, taking the corresponding logic code larger than the preset similarity value as the code of the target operation logic.
As described in steps S401 to S404, since the target arithmetic logic has a plurality of similar arithmetic codes, a matching logical code can be found for the target arithmetic logic based on the target feature vector of the target arithmetic logic, and therefore, the similarity calculation can be performed between the plurality of target feature vectors and the code vectors of the respective logical codes, and the formula of the calculation can be that
When the calculation result is close to 1, the target eigenvector is more relevant to the logic code, when the calculation result is close to 0, the target eigenvector is more irrelevant to the logic code, wherein M comprises a plurality of target eigenvectors, the target eigenvector is generated based on target operation logic, and the elements in the set N are eigenvectors generated for each logic code, and the specific generation mode can be that the target operation logic or the logic code is input into a specified vector machine, then whether the similarity value is larger than a preset similarity value is judged, and when the similarity value is larger than the similarity value, the logic code can be considered to be the logic codeThe edit code can be used as the corresponding logic code of the target arithmetic logic, thereby realizing the acquisition of the logic code.
In one embodiment, after the step S4 of obtaining the corresponding logic code according to the target operation logic, the method includes:
s501: acquiring the characteristic value of the logic code, and comparing the characteristic value with the similarity of the special values of various categories in a preset menu;
s502: and programming the logic code into the category with the highest similarity in the preset menu.
As described in the foregoing steps S501 to S502, since the developer may not use all the logic codes, and may use the logic codes repeatedly, in order to facilitate the developer to search for the corresponding logic codes, the logic codes may be programmed into the menu, and considering that the number of the logic codes may be large, the logic codes may be classified according to the category of the logic codes, the logic codes are programmed into the category with the highest similarity in the preset menu, and the subsequent developer only needs to search for the logic codes at the corresponding positions, thereby saving the time for the developer to search for or write the logic codes.
Referring to fig. 2, the present invention also provides a medical data-based logic code acquisition apparatus, including:
a medical data information acquisition module 10, configured to acquire a plurality of pieces of medical data information in a medical database according to the medical item information;
the associated information acquiring module 20 is configured to select a preset number of pieces of target medical data information from the plurality of pieces of medical data information, and acquire, according to associated information between the pieces of target medical data information, primary key information and external key information associated between the pieces of target medical data information;
the operation logic calculation module 30 is used for inputting the main key information, the external key information and the medical item information into a logic processing model for calculation to obtain various target operation logics; the logic processing model is trained on the basis of different combinations of primary key information and foreign key information and sample data consisting of processing codes generated according to the combinations;
and the logic code generation module 40 is configured to obtain a corresponding logic code according to the target operation logic.
Acquiring a plurality of pieces of medical data information from a medical database according to the medical project information, wherein the acquiring mode can be that a connection IP address, a medical database instance name, a login account number, a password and other related connection information of the medical database and a root directory path of a current project are configured in a configuration file, and the connection configuration of the medical database can support the connection of various medical database types, such as MySql, Oracle, PostgreSQL, SqlServer and the like; and then acquiring corresponding medical data information according to the requirement of the medical item information.
According to the target medical data information selected by the user and the associated information between the corresponding target medical data information, wherein the associated information only exists between the main key information of one piece of medical data information and the external key information of the other piece of medical data information, and the corresponding main key information and the external key information can be obtained according to the associated information.
The operational logic between the primary key information and the foreign key information can be inferred according to the acquired primary key information, the foreign key information and the medical item information, for example, the primary key information is a patient list, the foreign key information is corresponding medical record information, the operational logic between the primary key information and the foreign key information can be considered to be the medical record information corresponding to the patient, the operational logic is the capture of data and the like, the operational logic can also be the logic of adding, modifying, reducing and the like to the medical record information, which can be obtained according to the primary key information, the foreign key information and the medical item information, and therefore, the operational logic can be input into a logic processing model to obtain a plurality of corresponding target operational logics.
After the target operational logic is obtained, the logic code corresponding to the target operational logic can be searched in the code medical database, or the corresponding logic code is automatically generated based on the target operational logic for standby, so that repeated and tedious workload of developers is relieved, and development efficiency is improved.
In one embodiment, the medical data based logic code obtaining apparatus further comprises:
the relevant information detection module is used for detecting whether the medical database has relevant information among the target medical data information;
the text string conversion module is used for converting the content in the target medical data information into a text string if the target medical data information does not have the associated information, wherein the text string is composed of a plurality of character strings according to the positions of the character strings in the target medical data information;
the key character string extraction module is used for extracting a key character string from a character string corresponding to the main key information of one of the target medical data information, and performing feature matching on the character string corresponding to each foreign key information of other target medical data information through a BM algorithm;
and the associated information establishing module is used for establishing the associated information of the main key and the external key between the target medical data information according to the matching result.
Because some medical data information is not associated with other medical data information before being input into the medical database, the medical data information also does not have associated information, so that the external key information and the main key information cannot be acquired based on the associated information subsequently, whether the selected target medical data information has the associated information or not can be detected in the medical database, and when no associated information exists among the medical data information, an association relation can be established among the target data as the associated information among the target medical databases. The specific establishing mode is that the content in the target medical data information is converted into individual character strings, then key character strings in the character strings are extracted according to a machine learning model based on natural language processing, then the characteristic matching between the primary key information and the foreign key information is calculated through a BM (Boyer-Moore) algorithm, and the associated information of the primary key and the foreign key between the foreign key information and the primary key information meeting the matching requirement is established. It should be noted that, in general, each piece of medical data information has complex related information, and only relatively simple related information can be established by the above method.
In one embodiment, the arithmetic logic computation module 30 includes:
the preliminary operation logic calculation submodule is used for calculating the main key information and the external key information to obtain preliminary operation logic;
a first matching degree operator module for passing the formula
Calculating a first matching degree of each preliminary operation logic and the medical item information; wherein
Represents any one of the preliminary operation logics described,
representing medical item information;
a first matching degree judging submodule, configured to judge whether the first matching degree corresponding to each of the preliminary operation logics reaches a first preset matching degree value;
and the target calculation logic judgment submodule is used for taking the preliminary operation logic reaching the first preset matching degree value as the target operation logic.
Under the condition of not considering medical item information, all corresponding preliminary operational logics can be obtained through calculation according to the primary key information and the foreign key information, the calculation method can be that training is carried out according to big data, training sample data is generated by different primary key information and foreign key information combinations and operational logics constructed on the basis of different primary key information and foreign key information, and the sample data can be obtained through the big data. In order to simplify the number of generated preliminary operation logics, the preliminary operation logics irrelevant to the item can be eliminated, specifically, the first matching degree of each preliminary operation logic and the medical item information can be calculated through a formula, and when the first matching degree reaches a first preset matching degree value, the corresponding preliminary operation can be carried outThe logic is used as a target operation logic, wherein the first preset matching degree is a preset value, and the algorithm of the matching degree can be any algorithm, such as a WMD algorithm (word mover's distance), a simhash algorithm, an algorithm based on cosine similarity, an SVM vector model and the like, preferably by using a method of calculating a vector quantity (SVM) model
And calculating, wherein the preliminary operation logic is more related to the medical item information when the calculation result approaches 1, the preliminary operation logic is more unrelated to the medical item information when the calculation result approaches 0, and the preliminary operation logic of which the calculation result reaches the first preset matching degree is used as the target operation logic to participate in subsequent calculation analysis, so that the preliminary operation logic which is not the target operation logic can be omitted, the subsequent operation process is not required to be participated, the operation time is saved, and the subsequently generated code is related to the item.
In one embodiment, the preliminary operation logic computation submodule includes:
the vectorization unit is used for respectively vectorizing the main key information and the external key information to obtain respective corresponding n-dimensional vectors;
a weighting calculation unit for performing weighting calculation on the n-dimensional vectors corresponding to the primary key information and the foreign key information to obtain n-dimensional target vectors, each x-dimensional target vector 1 ，x 2 ，...，x n ；
A preliminary operation logic calculation unit for passing G (t) ═ softmax [ vf (t)]Calculating to obtain a plurality of preliminary operation logics; wherein f (t) ═ g [ Ux t +Wf(t-1)+b]G (t) is the preliminary operation logic obtained by inputting the t-th target vector, x t The t-th target vector is shown, f (t) shows an intermediate function obtained by inputting the t-th target vector, and V, U, W, b are all preset parameters.
The specific formula for obtaining the preliminary operation logic may be that the primary key information and the foreign key information are vectorized, and then weighted calculation is performed, wherein the weighted calculation may be performed by obtaining a mathematical average or a geometric average, or by assigning different weight coefficients to the primary key information and the foreign key information, and then adding is performed, that is, the primary key information and the foreign key information are integrated, so that the generated n-dimensional target vector integrates the contents of the primary key information and the foreign key information, the weighted budget is not limited, and may be used for integrating the information of the primary key information and the foreign key information, and then a plurality of preliminary operation logics are calculated by using a formula g (t) ═ somax [ vf (t) ], wherein the preliminary operation logics are related to the dimensionality of the vector, that is, the more complicated the primary key information and the foreign key information are, the more the number of the generated preliminary operation logics are generated, and V, f, and f, U, W, b are all trained parameter values, when the t-th target vector is input, the t-th operation logic can be obtained.
In one embodiment, the medical data information acquisition module 10 includes:
a feature vector obtaining submodule, configured to obtain n corresponding feature vectors according to the medical item information, where the n feature vectors are y respectively 1 ，y 2 ，...，y n ；
A second matchmeter operator module for passing the formula
Calculating a second matching degree of the characteristic vector and a pre-stored vector of each piece of medical data information in a medical database; wherein, z is i Represents the ith pre-stored vector, said H (y) i ，z i ) Representing the similarity function of the ith pre-stored vector and the ith eigenvector, w i Representing the weight of the ith pre-stored vector in the medical item information;
the second matching degree judging submodule is used for judging whether the second matching degree corresponding to each piece of medical data information reaches a second preset matching degree or not;
and the target medical data information extraction submodule is used for extracting the medical data information reaching the second preset matching degree to serve as the target medical data information.
The specific extraction method for extracting the plurality of pieces of medical data information from the medical database is that a plurality of feature vectors are obtained according to the medical item information, wherein the vectors obtained by the plurality of feature vectors through the medical item information can be used for representing the features of the medical item information, then a second matching degree of the feature vectors and pre-stored vectors corresponding to each piece of medical data information is calculated, whether the second matching degree reaches a second preset matching degree is judged, when the second matching degree reaches the second preset matching degree, the piece of medical data information can be considered to be target medical data information required by the medical item information, and the second preset matching degree is a preset value. In addition, because different feature vectors have different influence degrees on the items, a weight can be given to the value obtained by calculating the feature vector of each item, and then the final second matching degree can be obtained by accumulation.
In one embodiment, the logic code generation module 40 includes:
a target feature vector obtaining submodule for obtaining a plurality of target feature vectors of the target arithmetic logic;
a similarity value calculation submodule for passing through the formula
Calculating similarity values of the target feature vectors and code vectors corresponding to the logic codes; wherein M represents a set of a plurality of target feature vectors, and N represents a set of code vectors corresponding to one of the logic codes;
the similarity value judgment submodule is used for judging whether the similarity value is greater than a preset similarity value or not;
and the code acquisition module is used for taking the corresponding logic code larger than the preset similarity value as the code of the target operation logic if the similarity value is larger than the preset similarity value.
Because the target arithmetic logic has a plurality of similar arithmetic codes, a matched logic code can be found for the target arithmetic logic based on the target characteristic vector of the target arithmetic logic, and therefore, a plurality of targets can be usedSimilarity calculation is carried out between the target feature vector and the code vectors of the logic codes, and the calculation formula can be
When the calculation result approaches 1, it indicates that the target feature vector is more relevant to the logic code, and when the calculation result approaches 0, it indicates that the target feature vector is more irrelevant to the logic code, where M includes a plurality of target feature vectors, the target feature vectors are generated based on target operation logic, and the elements in the set N are feature vectors generated for each logic code, and the specific generation manner may be to input the target operation logic or the logic code into a specified vector machine, and then determine whether the similarity value is greater than a preset similarity value, and when the similarity value is greater than the similarity value, it may be considered that the logic code may be a corresponding logic code of the target operation logic, thereby implementing the acquisition of the logic code.
In one embodiment, a medical data based logic code acquisition apparatus, comprises:
the characteristic value acquisition module is used for acquiring the characteristic value of the logic code and comparing the characteristic value with the similarity of the special values of various categories in a preset menu;
and the logic code compiling module is used for compiling the logic code into the category with the highest similarity in the preset menu.
Since the logic codes are not necessarily used by the developer completely and may be used repeatedly, in order to facilitate the developer to search for the corresponding logic codes, the logic codes may be programmed into the menu, and considering that the number of the logic codes may be large, the logic codes may be classified according to the categories of the logic codes, the logic codes are programmed into the categories with the highest similarity in the preset menu, and the subsequent developer only needs to search for the logic codes at the corresponding positions, thereby saving the time for the developer to search for or write the logic codes.
The invention has the beneficial effects that: the corresponding medical data information in the medical database is obtained through the medical project information, then the associated main key information and the associated foreign key information are obtained according to the selected medical data information, the corresponding target calculation logic is obtained through the logic processing model, and finally the corresponding codes are generated according to the target calculation logic, so that the corresponding logic codes can be automatically generated based on the association relationship between the medical data information, the repeated and tedious workload of developers is relieved, and the development efficiency is better improved.
Referring to fig. 3, a computer device, which may be a server and whose internal structure may be as shown in fig. 3, is also provided in the embodiment of the present application. The computer device includes a processor, a memory, a network interface, and a medical database connected by a system bus. Wherein the computer designed processor is used to provide computational and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a medical database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The medical database of the computer device is used for storing various medical data information and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program may be executed by a processor to implement the method for acquiring logic code based on medical data according to any of the above embodiments.
Those skilled in the art will appreciate that the architecture shown in fig. 3 is only a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects may be applied.
The embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method for acquiring logic codes based on medical data according to any of the above embodiments may be implemented.
It will be understood by those skilled in the art that all or part of the processes of the methods of the above embodiments may be implemented by hardware associated with instructions of a computer program, which may be stored on a non-volatile computer-readable storage medium, and when executed, may include processes of the above embodiments of the methods. Any reference to memory, storage, medical databases, or other media provided herein and used in the examples may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (8)
1. A method for obtaining a logic code based on medical data, comprising:
acquiring a plurality of pieces of medical data information in a medical database according to the medical item information;
selecting a preset number of target medical data information from the plurality of medical data information, and acquiring main key information and external key information which are associated among the target medical data information according to the associated information among the target medical data information;
inputting the main key information, the external key information and the medical item information into a logic processing model for calculation to obtain various target operation logics; the logic processing model is trained on the basis of different combinations of primary key information and foreign key information and sample data consisting of processing codes generated according to the combinations;
acquiring a corresponding logic code according to the target operation logic;
the step of inputting the primary key information, the foreign key information and the medical item information into a logic processing model for calculation to obtain various target operation logics includes:
calculating the primary key information and the external key information to obtain a preliminary operation logic;
by the formula
Calculating a first matching degree of each preliminary operation logic and the medical item information, wherein
Represents any one of the preliminary operation logics described,
representing medical item information;
judging whether the first matching degree corresponding to each preliminary operation logic reaches a first preset matching degree value or not;
taking the preliminary operation logic reaching the first preset matching degree value as the target operation logic;
the step of obtaining the corresponding logic code according to the target operation logic includes:
obtaining a plurality of target feature vectors of the target operational logic;
by the formula
Calculating similarity values of the target feature vectors and code vectors corresponding to the logic codes; wherein M represents a set of a plurality of target feature vectors, and N represents a set of code vectors corresponding to one of the logic codes;
judging whether the similarity value is larger than a preset similarity value or not;
if so, taking the corresponding logic code larger than the preset similarity value as the code of the target operation logic.
2. The method for acquiring logic code based on medical data according to claim 1, wherein the step of selecting a preset number of pieces of target medical data information from the plurality of pieces of medical data information and acquiring the primary key information and the foreign key information associated with each other between the pieces of target medical data information according to the associated information between the pieces of target medical data information further comprises:
judging whether the medical database has the associated information among the target medical data information or not;
if the target medical data information does not have the associated information, converting the content in the target medical data information into a text string, wherein the text string is composed of a plurality of character strings according to the positions of the character strings in the target medical data information;
extracting key character strings from the character string corresponding to the main key information of one of the target medical data information, and performing feature matching on the character strings corresponding to each foreign key information of other target medical data information through a BM algorithm;
and establishing the associated information of the main key and the foreign key between the target medical data information according to the matching result.
3. The method for obtaining a logic code based on medical data according to claim 1, wherein the step of calculating the primary key information and the foreign key information to obtain a preliminary operation logic includes:
vectorizing the main key information and the foreign key information respectively to obtain respective corresponding n-dimensional vectors;
carrying out weighted calculation on the n-dimensional vectors corresponding to the primary key information and the foreign key information respectively to obtain n-dimensional target vectors which are x-dimensional target vectors respectively 1 ，x 2 ，…，x n ；
By G (t) ═ softmax [ vf (t)]Calculating to obtain a plurality of preliminary operation logics; wherein f (t) ═ g [ Ux t +Wf(t-1)+b]G (t) is the preliminary operation logic obtained by inputting the t-th target vector, x t The t-th target vector is shown, f (t) shows an intermediate function obtained by inputting the t-th target vector, and V, U, W, b are all preset parameters.
4. The medical data-based logic code acquisition method according to claim 1, wherein the step of acquiring a plurality of medical data information in a medical database according to medical item information comprises:
acquiring n corresponding feature vectors according to the medical item information, wherein the n feature vectors are y respectively 1 ，y 2 ，…，y n ；
By the formula
Calculating a second matching degree of the characteristic vector and a pre-stored vector of each piece of medical data information in a medical database; wherein, z is i Represents the ith pre-stored vector, said H (y) i ，z i ) Representing the similarity function of the ith pre-stored vector and the ith eigenvector, w i Representing the weight of the ith pre-stored vector in the medical item information;
judging whether the second matching degree corresponding to each piece of medical data information reaches a second preset matching degree;
and extracting the medical data information reaching the second preset matching degree to serve as the target medical data information.
5. The method for obtaining logic code based on medical data according to claim 1, wherein the step of obtaining corresponding logic code according to the target operation logic is followed by:
acquiring the characteristic value of the logic code, and comparing the characteristic value with the similarity of the special values of various categories in a preset menu;
and programming the logic code into the category with the highest similarity in the preset menu.
6. A medical data-based logic code acquisition apparatus, comprising:
the medical data information acquisition module is used for acquiring a plurality of pieces of medical data information in the medical database according to the medical item information;
the relevant information acquisition module is used for selecting a preset number of pieces of target medical data information from the plurality of pieces of medical data information and acquiring main key information and external key information which are relevant among the pieces of target medical data information according to the relevant information among the pieces of target medical data information;
the operation logic calculation module is used for inputting the main key information, the external key information and the medical item information into a logic processing model for calculation to obtain various target operation logics; the logic processing model is trained on the basis of different combinations of primary key information and foreign key information and sample data consisting of processing codes generated according to the combinations;
the logic code generating module is used for acquiring a corresponding logic code according to the target operation logic;
the arithmetic logic computation module comprises:
the preliminary operation logic calculation submodule is used for calculating the main key information and the external key information to obtain preliminary operation logic;
a first matching degree operator module for passing the formula
Calculating a first matching degree of each preliminary operation logic and the medical item information; wherein
Representing any one of said preliminary operational logics,
representing medical item information;
a first matching degree judging submodule, configured to judge whether the first matching degree corresponding to each of the preliminary operation logics reaches a first preset matching degree value;
a target calculation logic decision submodule for taking the preliminary operation logic reaching the first preset matching degree value as the target operation logic;
the logic code generation module comprises:
a target feature vector obtaining submodule for obtaining a plurality of target feature vectors of the target arithmetic logic;
similarity value calculation submodule for passing through the formula
Calculating similarity values of the target feature vectors and code vectors corresponding to the logic codes; wherein M represents a set of a plurality of target feature vectors, and N represents a set of code vectors corresponding to one of the logic codes;
the similarity value judgment submodule is used for judging whether the similarity value is greater than a preset similarity value or not;
and the code acquisition module is used for taking the corresponding logic code larger than the preset similarity value as the code of the target operation logic if the similarity value is larger than the preset similarity value.
7. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 5 when executing the computer program.
8. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010897805.6A CN112035120B (en) | 2020-08-31 | 2020-08-31 | Logic code acquisition method and device based on medical data and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010897805.6A CN112035120B (en) | 2020-08-31 | 2020-08-31 | Logic code acquisition method and device based on medical data and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112035120A CN112035120A (en) | 2020-12-04 |
| CN112035120B true CN112035120B (en) | 2022-09-20 |
Family
ID=73587415
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010897805.6A Active CN112035120B (en) | 2020-08-31 | 2020-08-31 | Logic code acquisition method and device based on medical data and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112035120B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113159208B (en) * | 2021-04-29 | 2022-09-27 | 上海德衡数据科技有限公司 | Cloud edge fog computing-based medical information fusion method, system, equipment and medium |
| CN113569996B (en) * | 2021-08-30 | 2024-05-07 | 平安医疗健康管理股份有限公司 | Method, device, equipment and storage medium for classifying medical records information |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109688953A (en) * | 2016-07-15 | 2019-04-26 | 伊西康有限责任公司 | The device code and generator code of pairing |
| CN110785736A (en) * | 2018-02-12 | 2020-02-11 | 甲骨文国际公司 | Automatic code generation |
| CN110837356A (en) * | 2018-08-15 | 2020-02-25 | 北京京东尚科信息技术有限公司 | Data processing method and device |
| CN110853715A (en) * | 2019-09-23 | 2020-02-28 | 万达信息股份有限公司 | Medical data visualization processing method and system, storage medium and electronic device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8566598B2 (en) * | 2005-09-02 | 2013-10-22 | Goodman Consulting Group | Method for article authentication using an article's authentication code and a second code provided by the party requesting authentication |
-
2020
- 2020-08-31 CN CN202010897805.6A patent/CN112035120B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109688953A (en) * | 2016-07-15 | 2019-04-26 | 伊西康有限责任公司 | The device code and generator code of pairing |
| CN110785736A (en) * | 2018-02-12 | 2020-02-11 | 甲骨文国际公司 | Automatic code generation |
| CN110837356A (en) * | 2018-08-15 | 2020-02-25 | 北京京东尚科信息技术有限公司 | Data processing method and device |
| CN110853715A (en) * | 2019-09-23 | 2020-02-28 | 万达信息股份有限公司 | Medical data visualization processing method and system, storage medium and electronic device |
Non-Patent Citations (1)
| Title |
|---|
| 一种代码生成器框架研究;许丽花;《南京工业职业技术学院学报》;20150707;第1-4页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112035120A (en) | 2020-12-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108304882B (en) | Image classification method and device, server, user terminal and storage medium | |
| CN111737458A (en) | Intention identification method, device and equipment based on attention mechanism and storage medium | |
| CN111898758A (en) | User abnormal behavior identification method and device and computer readable storage medium | |
| CN112035120B (en) | Logic code acquisition method and device based on medical data and computer equipment | |
| CN112966271B (en) | Malicious software detection method based on graph convolution network | |
| CN113901327A (en) | Target recommendation model training method, recommendation device and electronic equipment | |
| CN111859986A (en) | Semantic matching method, device, equipment and medium based on multitask twin network | |
| CN111797078A (en) | Data cleaning method, model training method, device, storage medium and equipment | |
| CN112837069A (en) | Block chain and big data based secure payment method and cloud platform system | |
| CN112231033A (en) | Software interface element matching method and device combining RPA and AI | |
| CN112182384A (en) | Content recommendation method and device based on counterstudy and computer equipment | |
| CN108062474B (en) | File detection method and device | |
| CN113204968A (en) | Concept recognition method, device, equipment and storage medium of medical entity | |
| CN111626346A (en) | Data classification method, device, storage medium and device | |
| CN112836061A (en) | Intelligent recommendation method and device and computer equipment | |
| CN112784998A (en) | Data processing method and device and computing equipment | |
| CN111400340A (en) | Natural language processing method and device, computer equipment and storage medium | |
| KR20190064129A (en) | Method for inputing information to computing apparatus and computing apparatus thereof | |
| CN115098857A (en) | Visual malicious software classification method and device | |
| CN113343711A (en) | Work order generation method, device, equipment and storage medium | |
| CN112070086A (en) | Method for optimizing text recognition system, computer device, and storage medium | |
| KR20210147771A (en) | Method and apparatus for increasing knowledge based on uncertainty in neural networks | |
| CN110705603A (en) | Method and system for dynamically judging similarity of user request data | |
| CN112989022B (en) | Intelligent virtual text selection method and device and computer equipment | |
| Dwivedi et al. | Applying software metrics for the mining of design pattern |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220527 Address after: 518000 China Aviation Center 2901, No. 1018, Huafu Road, Huahang community, Huaqiang North Street, Futian District, Shenzhen, Guangdong Province Applicant after: Shenzhen Ping An medical and Health Technology Service Co.,Ltd. Address before: Room 12G, Block H, 666 Beijing East Road, Huangpu District, Shanghai 200000 Applicant before: PING AN MEDICAL AND HEALTHCARE MANAGEMENT Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |