CN114999599A - Data processing method and device, electronic equipment and computer readable storage medium - Google Patents

Data processing method and device, electronic equipment and computer readable storage medium Download PDF

Info

Publication number
CN114999599A
CN114999599A CN202210590350.2A CN202210590350A CN114999599A CN 114999599 A CN114999599 A CN 114999599A CN 202210590350 A CN202210590350 A CN 202210590350A CN 114999599 A CN114999599 A CN 114999599A
Authority
CN
China
Prior art keywords
diagnosis
treatment
target
path
model
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.)
Pending
Application number
CN202210590350.2A
Other languages
Chinese (zh)
Inventor
刘耀
张瑾
朱礼军
翟雨
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Institute Of Scientific And Technical Information Of China
Original Assignee
Institute Of Scientific And Technical Information Of China
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Institute Of Scientific And Technical Information Of China filed Critical Institute Of Scientific And Technical Information Of China
Priority to CN202210590350.2A priority Critical patent/CN114999599A/en
Publication of CN114999599A publication Critical patent/CN114999599A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/20Natural language analysis
    • G06F40/205Parsing
    • G06F40/216Parsing using statistical methods
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/20Natural language analysis
    • G06F40/279Recognition of textual entities
    • G06F40/289Phrasal analysis, e.g. finite state techniques or chunking
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/30Semantic analysis
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Public Health (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Artificial Intelligence (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • Primary Health Care (AREA)
  • Epidemiology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Pathology (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Medical Treatment And Welfare Office Work (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The embodiment of the application provides a data processing method and device, electronic equipment and a computer readable storage medium, and relates to the technical field of data processing. The method comprises the following steps: acquiring medical record data information of a target user, and determining basic diagnosis and treatment knowledge points in the medical record data information of the target user; acquiring a pre-established disease diagnosis and treatment model; marking basic diagnosis and treatment knowledge points in a disease diagnosis and treatment model, and converting the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points into data in a target format, wherein the target format comprises at least one of an image format, a matrix format and a text format; and inputting the data in the target format into a preset artificial intelligence algorithm to obtain at least one diagnosis and treatment path, and determining a target diagnosis and treatment path from the at least one diagnosis and treatment path. The compatibility between the current linear medical record recording mode and the artificial intelligence algorithm is effectively improved, the trial and error process in medical diagnosis is effectively reduced, and the waste of medical resources is effectively reduced.

Description

Data processing method and device, electronic equipment and computer readable storage medium
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a data processing method and apparatus, an electronic device, and a computer-readable storage medium.
Background
A large amount of clinical data such as electronic medical records, diagnosis records, prescription information and the like can be generated in the disease diagnosis and treatment process, and sufficient data support is provided for the development of medical informatization, modernization and intellectualization. However, the existing electronic medical record has linear recording mode, so that medical information data is numerous and complex, more redundant and interference information is accumulated in the recording process, and the compatibility and the adaptability with the current advanced algorithm are lacked. For example, the electronic medical records such as the current medical history, the past medical history, the current medical history and the physical examination are often long in length, the recording form is an unstructured natural language, and even if the subsequent processing such as structuring, information mining and displaying is carried out based on a deep learning algorithm, the processing result is still difficult to be applied to other algorithms and makes substantial contribution to disease diagnosis and treatment without a data representation mode of dimension reduction, unification and simplification.
Obviously, the existing linear recording mode of the electronic clinical data is numerous and complicated and redundant, so that the electronic clinical data lacks computability, is difficult to directly participate in efficient algorithm operation, and hinders the close relation between the existing medical diagnosis and treatment field data and the advanced artificial intelligence algorithm. If clinical data related to a disease diagnosis process cannot be treated in a reasonable form, a large amount of data accumulated in the diagnosis process can limit the use of an artificial intelligence algorithm in the field of intelligent medical diagnosis and treatment instead, so that huge logical calculation amount is caused, and the progress of medical informatization, modernization and intellectualization is hindered.
Disclosure of Invention
The embodiment of the application provides a data processing method and device, electronic equipment, a computer readable storage medium and a computer program product, which can solve the problem of effective application of an artificial intelligence algorithm in the field of disease diagnosis and treatment. The technical scheme is as follows:
according to a first aspect of embodiments of the present application, there is provided a data processing method, including:
acquiring medical record data information of a target user, and determining basic diagnosis and treatment knowledge points in the medical record data information of the target user;
acquiring a pre-established disease diagnosis and treatment model; the disease diagnosis and treatment model is a go chessboard type data model which is constructed based on medical record diagnosis samples and contains all diagnosis and treatment knowledge points in the medical record diagnosis samples; elements in the disease diagnosis and treatment model are diagnosis and treatment knowledge points of medical record diagnosis samples; each medical record diagnosis sample comprises medical record data information of a sample user and/or information of a diagnosis and treatment method which is performed and corresponds to the medical record;
marking basic diagnosis and treatment knowledge points in a disease diagnosis and treatment model, and converting the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points into data in a target format, wherein the target format comprises at least one of an image format, a matrix format and a text format;
inputting data in a target format into a preset artificial intelligence algorithm to obtain at least one diagnosis and treatment path output by the artificial intelligence algorithm, and determining a target diagnosis and treatment path from the at least one diagnosis and treatment path; and the nodes of the diagnosis and treatment path represent basic diagnosis and treatment knowledge points or target diagnosis and treatment knowledge points corresponding to the information of the subsequent diagnosis and treatment method.
In one possible implementation manner, converting the disease diagnosis and treatment model labeled with the basic diagnosis and treatment knowledge points into data in a target format includes:
if the target format is an image format, converting the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points into a target image; pixel points of the target image are elements of a disease diagnosis and treatment model;
if the target format is a matrix format, converting the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points into a target matrix; the elements of the target matrix are elements of a disease diagnosis and treatment model;
and if the target format is a text format, converting the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points into text contents, wherein each vocabulary in the text contents is an element of the disease diagnosis and treatment model.
In one possible implementation manner, the horizontal axis in the disease diagnosis and treatment model represents different attributes of diagnosis and treatment knowledge points, the disease diagnosis and treatment model comprises at least one attribute, elements in the same column belong to the same attribute, and the size of the disease diagnosis and treatment model is n x n; marking basic diagnosis and treatment knowledge points in a disease diagnosis and treatment model, and converting the disease diagnosis and treatment model marked with the basic diagnosis and treatment knowledge points into data in a target format, wherein the data comprises the following steps:
determining target attributes corresponding to the basic diagnosis and treatment knowledge points, marking elements corresponding to the target attributes in the disease diagnosis and treatment model, connecting the marked elements to form chess game data in the diagnosis and treatment process, and converting the chess game data into data in a target format.
In one possible implementation manner, determining a target diagnosis path from at least one diagnosis path includes:
calling a preset prior library, and determining the node value of each node in each diagnosis and treatment path based on the preset prior library; the node value represents the influence of the diagnosis and treatment knowledge point corresponding to the node on the target disease diagnosis;
determining the depth value of each diagnosis and treatment path;
and determining a target diagnosis and treatment path from the at least one diagnosis and treatment path according to the node value and the depth value, wherein the prior library is a library constructed based on a disease diagnosis and treatment manual.
In one possible implementation, determining a target clinical path from the at least one clinical path according to the node values and the depth values includes:
determining at least one reference path from the at least one clinical path; the total node value corresponding to the node of the reference path meets a first preset condition;
and determining the depth value of each reference path, and determining the target diagnosis and treatment path from the reference paths according to the depth values.
In one possible implementation, determining a target diagnosis path from the reference paths according to the depth values includes:
and determining the reference path with the minimum depth value as a target diagnosis and treatment path.
According to a second aspect of embodiments of the present application, there is provided a data processing apparatus, the apparatus including:
the basic diagnosis and treatment knowledge point determining module is used for acquiring case data information of a target user and determining basic diagnosis and treatment knowledge points in the case data information of the target user;
the disease diagnosis and treatment model acquisition module is used for acquiring a pre-established disease diagnosis and treatment model; the disease diagnosis and treatment model is a go chessboard type data model which is constructed based on medical record diagnosis samples and contains all diagnosis and treatment knowledge points in the medical record diagnosis samples; elements in the disease diagnosis and treatment model are diagnosis and treatment knowledge points of medical record diagnosis samples; each medical record diagnosis sample comprises medical record data information of a sample user and/or information of a diagnosis and treatment method which is performed and corresponds to the medical record;
the conversion module is used for marking basic diagnosis and treatment knowledge points in the disease diagnosis and treatment model and converting the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points into data in a target format, wherein the target format comprises at least one of an image format, a matrix format and a text format;
the diagnosis and treatment path determining module is used for inputting the data in the target format into a preset artificial intelligence algorithm to obtain at least one diagnosis and treatment path output by the artificial intelligence algorithm and determining a target diagnosis and treatment path from the at least one diagnosis and treatment path; and the nodes of the diagnosis and treatment path represent basic diagnosis and treatment knowledge points or target diagnosis and treatment knowledge points corresponding to the information of the subsequent diagnosis and treatment method.
In a third aspect of embodiments of the present application, an electronic device is provided, where the electronic device includes a memory, a processor, and a computer program stored in the memory, and the processor implements the steps of the method provided in the first aspect when executing the program.
According to a fourth aspect of embodiments herein, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method as provided by the first aspect.
According to a fifth aspect of embodiments herein, there is provided a computer program product comprising computer instructions stored in a computer-readable storage medium, which, when read by a processor of a computer device from the computer-readable storage medium, cause the processor to execute the computer instructions, so that the computer device performs the steps of implementing the method as provided in the first aspect.
The technical scheme provided by the embodiment of the application has the following beneficial effects: according to the embodiment of the application, a disease diagnosis and treatment model corresponding to a disease diagnosis sample is established, a diagnosis and treatment process sufficient list recorded by a large number of electronic medical records reaches the diagnosis and treatment model to form chess game data, important diagnosis and treatment steps related in a diagnosis and treatment manual become chess game nodes, complex logic calculation of diagnosis and treatment information participation is simplified, a target diagnosis and treatment path is determined, and a corresponding diagnosis and treatment method in the target diagnosis and treatment path is a maximum-possibility diagnosis and treatment method corresponding to case data information of a target user. The complexity of electronic medical record data in the diagnosis and treatment field is simplified, a data compatible entry is provided for application of algorithms such as counterstudy and the like in the diagnosis and treatment field, changes and rules in massive medical record information are effectively processed, a diagnosis and treatment path is formed by the rules, clinical diagnosis and treatment services are provided, the trial and error process in medical diagnosis is effectively reduced, and the waste of medical resources is effectively reduced.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments of the present application will be briefly described below.
Fig. 1 is a schematic flowchart of a data processing method according to an embodiment of the present application;
fig. 2 is a schematic diagram of a disease diagnosis and treatment model provided in an embodiment of the present application;
fig. 3 is a schematic diagram corresponding to the disease diagnosis and treatment model after marking the basic diagnosis and treatment knowledge points according to the embodiment of the present application;
fig. 4 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Embodiments of the present application are described below in conjunction with the drawings in the present application. It should be understood that the embodiments set forth below in connection with the drawings are exemplary descriptions for explaining technical solutions of the embodiments of the present application, and do not limit the technical solutions of the embodiments of the present application.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should be further understood that the terms "comprises" and/or "comprising," when used in this specification in connection with embodiments of the present application, specify the presence of stated features, information, data, steps, operations, elements, and/or components, but do not preclude the presence or addition of other features, information, data, steps, operations, elements, components, and/or groups thereof, as embodied in the art. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein indicates at least one of the items defined by the term, e.g., "a and/or B" may be implemented as "a", or as "B", or as "a and B".
To make the objects, technical solutions and advantages of the present application more clear, the following detailed description of the embodiments of the present application will be made with reference to the accompanying drawings.
The data processing method, the data processing device, the electronic equipment, the computer readable storage medium and the computer program product aim at solving the problem of effective application of algorithms in the artificial intelligence field such as counterstudy, Monte Carlo tree search, upper limit confidence coefficient and the like in the field of disease diagnosis and treatment.
The technical solutions of the embodiments of the present application and the technical effects produced by the technical solutions of the present application are explained below by describing several exemplary embodiments. It should be noted that the following embodiments may be referred to, referred to or combined with each other, and the description of the same terms, similar features, similar implementation steps and the like in different embodiments is not repeated.
An embodiment of the present application provides a data processing method, and as shown in fig. 1, the method includes:
step S101, acquiring case data information of a target user, and extracting basic diagnosis and treatment knowledge points in the case data information of the target user;
the target user of the embodiment of the application is a patient, and can be a patient with any type of disease, such as a skin disease patient, a cardiovascular disease patient and the like.
The case data information of the target user is determined from the medical record of the target user, the case of the target user is generally a text-type medical record, and can be a paper medical record or an electronic medical record, the case data information of the target user is extracted from the case of the target user and comprises information such as basic information of a patient, information of a performed disease diagnosis and treatment method, the basic information can be the name, the sex and the like of the target patient, and the disease diagnosis and treatment information can be external expressions of a disease changed by the patient, a condition queried by a doctor, a performed examination item or an operation item and the like.
The case data information is obtained from cases, generally has corresponding line and text rules or formats, and the line and text rules, sentence pattern characteristics, text semantics and the like of the case data information can be analyzed through a preset diagnosis and treatment knowledge point extraction algorithm to extract basic diagnosis and treatment knowledge points in the case data information of a target user, wherein the diagnosis and treatment knowledge points comprise patient information expression in a standard description or standard format, disease symptom description in a standard format, standard diagnosis and treatment method information expression and the like.
The diagnosis and treatment knowledge point extraction algorithm preset in the embodiment of the application comprises an LDA (Latent Dirichlet Allocation, document theme generation model), an LSTM (Long Short-Term Memory,
the method includes the steps of using algorithms such as a long-short Term memory network), a CRF (Conditional Random Field), a TF-IDF (Term Frequency-Inverse text Frequency index) and the like to deeply mine diagnosis and treatment knowledge points in case data information of a target user.
Of course, the basic diagnosis and treatment knowledge points can be directly extracted, and the category corresponding to the basic diagnosis and treatment knowledge points can also be determined, which is not limited in the embodiment of the present application.
Specifically, it is assumed that the characters in the case data information of the target user include "eczema is developed in a middle-aged man with age and sex, named after Zhangsan, and mainly appears on the upper limbs, and recently, a certain drug is taken, and the disease is initially determined to be allergy", the basic diagnosis and treatment knowledge point that can be determined for the case data information of the target user is "eczema and allergy upper limbs of the middle-aged man", and the basic diagnosis and treatment knowledge point reflects the content of the case data information of the target user.
Step S102, acquiring a pre-established disease diagnosis and treatment model; the disease diagnosis and treatment model is a go chessboard type data model which is constructed based on medical record diagnosis samples and contains all diagnosis and treatment knowledge points in the medical record diagnosis samples; elements in the disease diagnosis and treatment model are diagnosis and treatment knowledge points of a medical record diagnosis sample; each medical record diagnosis sample comprises medical record data information of a sample user and/or information of a diagnosis and treatment method which is performed and corresponds to the medical record.
The basic diagnosis and treatment knowledge points are extracted from the case data information of the target user, the number of the basic diagnosis and treatment knowledge points is limited, the diagnosis and treatment method of the disease cannot be directly determined only by the extracted basic diagnosis and treatment knowledge points, and the diagnosis and treatment method or the diagnosis and treatment path corresponding to the target user and having the highest possibility needs to be judged according to the extracted basic diagnosis and treatment knowledge points.
The diagnosis and treatment method information in the embodiment of the present application may be instruments, items, and treatment drugs after diagnosis, and the like, which is not limited in the embodiment of the present application.
The disease diagnosis and treatment model is constructed based on a preset and massive medical record sample and comprises all diagnosis and treatment knowledge points in the medical record diagnosis sample, and the construction method of the disease diagnosis and treatment model is as follows:
the method comprises the steps of taking massive medical record diagnosis samples in the target disease field, wherein the medical record diagnosis samples comprise medical record data information and diagnosis and treatment method information corresponding to medical records, performing word segmentation, stop word removal and accurate analysis on the structure and content characteristics of the medical record diagnosis samples on each medical record diagnosis sample, so that information such as basic information, disease diagnosis and treatment information and confirmed diseases of a patient is extracted, and an initial diagnosis and treatment model is constructed through the information.
According to the embodiment of the application, besides the diagnosis and treatment knowledge points in the massive medical record samples are extracted to construct the initial diagnosis and treatment model, the initial diagnosis and treatment model can be corrected and supplemented by means of expert field knowledge and disease diagnosis and treatment manuals in corresponding fields, and the disease diagnosis and treatment model is obtained. In addition, the disease diagnosis and treatment model can be a go-chess-board type data model with any size, such as 16 × 16, and can also be in other sizes.
As shown in fig. 2, the disease diagnosis and treatment model provided in the embodiment of the present application is exemplarily shown, and as shown in fig. 2, the disease diagnosis and treatment model corresponds to the dermatological field, and the disease diagnosis and treatment model includes attributes such as "age sex", "propagation and prevalence", "season", "course", "disease", "cause", "skin symptom", and "clinical examination and verification", where diagnosis and treatment knowledge points "male infant", "young male", "middle-aged female", "old male", "young female", and the like all belong to the attribute of "age sex", and diagnosis and treatment knowledge points included in other attributes are not exemplified.
Step S103, marking basic diagnosis and treatment knowledge points in the disease diagnosis and treatment model, and converting the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points into data in a target format, wherein the target format comprises at least one of an image format, a matrix format and a text format.
After the basic diagnosis and treatment knowledge points and the disease diagnosis and treatment model are determined, because each element on the disease diagnosis and treatment model is also a diagnosis and treatment knowledge point, the basic diagnosis and treatment knowledge points can be determined on the disease diagnosis and treatment model, and the basic diagnosis and treatment knowledge points are marked in the disease diagnosis and treatment model, as shown in fig. 3, the basic diagnosis and treatment knowledge points marked in the disease diagnosis and treatment model are exemplarily shown, wherein "o" in fig. 3 represents the basic diagnosis and treatment knowledge points, and an arrow represents a diagnosis and treatment sequence.
According to the embodiment of the application, the diagnosis and treatment knowledge points marked on the disease diagnosis and treatment model are equivalent to a chess game which is already carried out, after the basic diagnosis and treatment knowledge points are marked on the disease diagnosis and treatment model, the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points is converted into data in a target format, and the target format comprises at least one of an image format, a matrix format and a text format.
Specifically, the disease diagnosis and treatment model of the marked basic diagnosis and treatment knowledge points may be converted into a target image, the disease diagnosis and treatment model of the marked basic diagnosis and treatment knowledge points may be converted into a target matrix, and the disease diagnosis and treatment model of the marked basic diagnosis and treatment knowledge points may be converted into a common text format.
According to the embodiment of the application, the disease diagnosis and treatment model of the basic diagnosis and treatment knowledge points is converted into the data in the target format, so that the data in the target format can be applied to the relevant algorithm models in the fields of artificial intelligence and deep learning, and participate in subsequent calculation.
Step S104, inputting the data in the target format into a preset artificial intelligence algorithm to obtain at least one diagnosis and treatment path output by the artificial intelligence algorithm, and determining a target diagnosis and treatment path from the at least one diagnosis and treatment path; and the nodes of the diagnosis and treatment path represent basic diagnosis and treatment knowledge points or target diagnosis and treatment knowledge points corresponding to the information of the subsequent diagnosis and treatment method.
According to the embodiment of the application, after the data in the target format is obtained, the data in the target format is input into a preset artificial intelligence algorithm, at least one diagnosis and treatment path output by the artificial intelligence algorithm is obtained, the preset artificial intelligence algorithm takes the data in the target format generated after each case diagnosis sample is marked in a disease diagnosis and treatment model as a training sample, after the training sample is processed, the at least one diagnosis and treatment path can be output, and the diagnosis and treatment path comprises a basic diagnosis and treatment node and a target diagnosis and treatment node, namely, the node of the diagnosis and treatment path represents the basic diagnosis and treatment knowledge point or the target diagnosis and treatment knowledge point corresponding to subsequent diagnosis and treatment method information.
The artificial intelligence algorithm preset in the embodiment of the present application may be a pre-trained neural network model, or may be other algorithms, for example, an Upper Confidence Bound to Tree (UCT) algorithm, which is not limited in the embodiment of the present application.
For a specific embodiment, if the data in the target format is a target image, the corresponding pre-trained neural network model is an image processing model, the data in the target format is input into the pre-trained neural network model, so as to obtain at least one diagnosis and treatment path output by the preset neural network model, and a node corresponding to the diagnosis and treatment path represents the basic diagnosis and treatment knowledge point or a target diagnosis and treatment knowledge point corresponding to subsequent diagnosis and treatment method information, where the target diagnosis and treatment knowledge point may be a diagnosis and treatment method, a diagnosis and treatment item, or a diagnosis and treatment equipment to be performed subsequently, and in some cases, may be a diagnosis and treatment result, such as cure and death.
After the at least one diagnosis and treatment path is obtained, the target diagnosis and treatment path is determined from the at least one diagnosis and treatment path.
It can be understood that the medical data information of the target user is limited, the diagnosis and treatment path determined according to the medical data information of the target user may be multiple, a target diagnosis and treatment path needs to be further determined from the multiple diagnosis and treatment paths, and the diagnosis and treatment method in the target diagnosis and treatment path is the currently selectable optimal diagnosis and treatment method.
The target diagnosis and treatment knowledge point in the embodiment of the application is subsequent diagnosis and treatment method information, and may be items or treatment medicines and the like required for diagnosis and treatment, which is not limited in the embodiment of the application.
The embodiment of the present application provides a possible implementation manner, which converts a disease diagnosis and treatment model labeled with basic diagnosis and treatment knowledge points into data in a target format, including:
if the target format is an image format, converting the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points into a target image; pixel points of the target image are elements of a disease diagnosis and treatment model;
if the target format is a matrix format, converting the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points into a target matrix; the elements of the target matrix are elements of a disease diagnosis and treatment model;
and if the target format is a text format, converting the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points into text contents, wherein each vocabulary in the text contents is an element of the disease diagnosis and treatment model.
After obtaining a disease diagnosis and treatment model and basic diagnosis and treatment knowledge points corresponding to case data information of a target user, marking the basic diagnosis and treatment knowledge points on the disease diagnosis and treatment model, and converting the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points into data in a target format; if the target format is a matrix format, the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points is converted into a target matrix, elements of the target matrix are elements of the disease diagnosis and treatment model, if the target format is a text format, the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points is converted into text contents, and each vocabulary in the text contents is an element of the disease diagnosis and treatment model.
It can be understood that the content of the case data information of the target user is limited, and the doctor cannot accurately determine the disease of the target patient and the diagnosis and treatment method corresponding to the disease according to the diagnosis and treatment knowledge points extracted from the content of the case data information of the target user, and needs to determine the disease with the highest possibility and the corresponding diagnosis and treatment method according to the diagnosis and treatment knowledge points in the case data information of the target user, so as to reduce the possibility of determination errors.
The embodiment of the application provides a possible implementation mode, a transverse axis in a disease diagnosis and treatment model represents different attributes of diagnosis and treatment knowledge points, the disease diagnosis and treatment model comprises at least one attribute, elements in the same column belong to the same attribute, and the size of the disease diagnosis and treatment model is n x n; marking basic diagnosis and treatment knowledge points in a disease diagnosis and treatment model, and converting the disease diagnosis and treatment model marked with the basic diagnosis and treatment knowledge points into data in a target format, wherein the data comprises the following steps:
determining target attributes corresponding to the basic diagnosis and treatment knowledge points, marking elements corresponding to the target attributes in the disease diagnosis and treatment model, connecting the marked elements to form chess game data in the diagnosis and treatment process, and converting the chess game data into data in a target format.
The disease diagnosis and treatment model in the embodiment of the application may be any n × n diagnosis and treatment model, where n is a positive integer, such as 16 × 16, 32 × 32, and the like, and the disease diagnosis and treatment model may accommodate all diagnosis and treatment knowledge points in the field.
According to the method and the device, after the disease diagnosis and treatment model and the basic diagnosis and treatment knowledge points are determined, the basic diagnosis and treatment knowledge points are marked in the disease diagnosis and treatment model, a chess game formed by the basic diagnosis and treatment knowledge points is an already-processed chess game, the marked elements are connected to form chess game data in the diagnosis and treatment process, and the chess game data are converted into data in a target format.
The embodiment of the present application provides a possible implementation manner, and the determining of a target diagnosis and treatment path from at least one diagnosis and treatment path includes:
calling a preset prior library, and determining the node value of each node in each diagnosis and treatment path based on the preset prior library; the node value represents the influence of the diagnosis and treatment knowledge point corresponding to the node on the target disease diagnosis;
determining the depth value of each diagnosis and treatment path;
and determining a target diagnosis and treatment path from at least one diagnosis and treatment path according to the node value and the depth value, wherein the prior library is a library constructed based on a preset disease diagnosis and treatment manual.
The preset prior library is a library constructed based on a disease diagnosis and treatment manual, diagnosis and treatment knowledge points in the disease diagnosis and treatment manual are stored in the prior library, after a diagnosis and treatment path is determined, diagnosis and treatment knowledge points represented by all nodes in the diagnosis and treatment path are determined, and node values of all nodes in all diagnosis and treatment paths are determined by inquiring the preset prior library; the node value represents the influence of the diagnosis and treatment knowledge point corresponding to the node on the target disease diagnosis, and specifically, for example, if the diagnosis and treatment knowledge point corresponding to a certain node exists in the prior library, the node value of the node is high.
After the node value of each diagnosis and treatment path is determined, the depth information of each diagnosis and treatment path needs to be further determined, and the target diagnosis and treatment path is determined from at least one diagnosis and treatment path by combining the node value and the depth value.
The embodiment of the present application provides a possible implementation manner, wherein a target diagnosis and treatment path is determined from at least one diagnosis and treatment path according to a node value and a depth value, and the method includes:
determining at least one reference path from the at least one clinical path; the total node value corresponding to the node of the reference path meets a first preset condition;
and determining the depth value of each reference path, and determining the target diagnosis and treatment path from the reference paths according to the depth values.
It can be understood that at least one diagnosis and treatment path is obtained according to the basic diagnosis and treatment knowledge points, the diagnosis and treatment paths include the basic diagnosis and treatment knowledge points and the target diagnosis and treatment knowledge points, the diagnosis and treatment paths are not necessarily the optimal diagnosis and treatment path, and the target diagnosis and treatment path is determined from the at least one diagnosis and treatment path to be the optimal diagnosis and treatment path.
After at least one diagnosis and treatment path is determined, determining a total node value of nodes of each diagnosis and treatment path, determining a diagnosis and treatment path with the total node value meeting a first preset condition as a candidate path, for example, determining a diagnosis and treatment path with the total node value ranked 3 before as a candidate path, and after determining the candidate path, determining a candidate path with the minimum depth value from the candidate paths as a target diagnosis and treatment path.
The nodes in the target diagnosis and treatment path comprise nodes represented by basic diagnosis and treatment knowledge points and nodes represented by target diagnosis and treatment knowledge points corresponding to subsequent diagnosis and treatment method information.
The embodiment of the present application provides a possible implementation manner, and determining a target diagnosis and treatment path from a reference path according to a depth value includes:
and determining the reference path with the minimum depth value as a target diagnosis and treatment path.
The embodiment of the application provides a specific application scenario, wherein basic diagnosis and treatment knowledge points are marked in a disease diagnosis and treatment model, the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points is converted into a first target matrix, the first target matrix is input into a pre-established neural network model, the algorithm of the neural network model can be a Monte Carlo algorithm, and the neural network model carries out Monte Carlo tree search on the first target matrix marked with the basic diagnosis and treatment knowledge points to obtain at least one diagnosis and treatment path.
Determining a current node traversed by the current iteration in the iterative traversal process of Monte Carlo tree search; the first iteration traversal takes the root node as the current node;
determining at least one child node corresponding to the current node, determining an optimal child node from the at least one child node, if the depth corresponding to the optimal child node is determined to be smaller than the preset depth, determining an expanded optimal child node, and performing rolling simulation until the depth corresponding to the optimal child node is larger than the preset depth, or the optimal child node is a leaf node, or a path formed by the at least one child node does not exist in case data information of a target user;
and if the optimal child node is larger than the preset depth or the optimal child node is a leaf node, determining that the current iteration is finished, and traversing from the optimal child node to the root node in a reverse direction to obtain a candidate path corresponding to the current iteration.
The Monte Carlo tree search is carried out in continuous traversal, the first traversal takes the root node as the current node, and one basic diagnosis and treatment knowledge point can be selected as the root node according to the attribute of the basic diagnosis and treatment knowledge point.
In the current iteration process, a current node traversed by the current iteration is determined, at least one child node corresponding to the current node is determined, an optimal child node is determined from the at least one child node, the root node is taken as the root node in the first traversal, the child node of the root node is determined, the traversal times and the node value of each child node are determined, the total traversal times of the root node up to the current moment are determined, and the optimal child node is determined from the at least one child node according to the traversal times and the node value of each child node and the total traversal times of the root node.
Specifically, the best child node may be determined by the upper confidence interval UCT algorithm of the tree. In the UCT, I ∈ I is the set of nodes that can be reached from the current node p. The UCT selects a child node having the highest expectation value among the parent nodes p using the following equation. For any child node vi, determining the traversal times n (vi) of the child node, the times n (v) that the parent node of the child node is traversed, and the node value q (vi) of the child node to determine the UCT (vi, v) corresponding to the child node vi, and determining by the following formula:
Figure BDA0003664877090000131
wherein c is expectation, N represents the traversal times, vi represents a group of child nodes, v represents the current node, and Q (vi) represents the node value of the node.
The UCT is mainly divided into two components, the first one being: (Q (vi))/(N (vi)), also called an extension component, is a ratio representing success of a certain node, is a reward value of a node simulation success/total access times of the node, and in the search of a target diagnosis and treatment path, (Q (vi))/(N (vi)) represents the reward value of the node passing through the node and obtaining a correct shortest diagnosis and treatment path/total access times of the node. In case data information of a target user, n (vi) is mainly the width and depth of disease diagnosis and treatment, and q (vi) is mainly case data information of the target user and reward values of a path of "dermatology diagnosis and treatment routine", generally speaking, we prefer to traverse nodes with higher success rate, but in the monte carlo algorithm we cannot rely on such nodes only, that is, cannot rely on an extension component only, because this results in that nodes which are simulated as failures in the front are easily discarded in the simulation in the back, randomness and fairness are lost, and more simulation opportunities cannot be given to other nodes, resulting in overfitting. The second component in the UCT is the Exploration, in order to increase the search opportunities of all nodes and obtain the shortest diagnosis and treatment path, the subsequent Exploration component is required to be relied on, the component mainly traverses and explores unknown nodes, namely more diagnosis and treatment symptom nodes which are not traversed, the denominator values n (vi) of the nodes are lower, and the corresponding component values are larger, so that the nodes are easier to select.
After the UCT (vi, v) of each child node is determined, the numerical value of the UCT (vi, v) of each child node is compared, and the child node corresponding to the maximum value of the UCT (vi, v) is determined as the next target child node.
After the optimal child node is determined, if the depth corresponding to the optimal child node is determined to be smaller than the preset depth, the optimal child node is expanded, a walker is simulated until the depth corresponding to the optimal child node is larger than the preset depth, or a path formed by the node does not exist in a medical record, downward traversal cannot be continued, the preset depth is preset according to actual conditions, and the preset depth is larger than the number of basic diagnosis and treatment knowledge points.
If the optimal child node is larger than the preset depth or the optimal child node is a leaf node, the current iteration is determined to be completed, the optimal child node is traversed to the root node in a reverse direction, a diagnosis and treatment path corresponding to the current iteration is obtained, and a target diagnosis and treatment path needs to be further determined from at least one diagnosis and treatment path.
After determining the best child node from the at least one child node, the method further comprises:
adding 1 to the traversal times of the optimal child node;
backward traversal from the best child node to the root node, further comprising:
and in the reverse traversing process, adding 1 to the traversing times of each traversed node, and updating the node value corresponding to each traversed node into the sum of the node value of the current node and the node value corresponding to the child node.
After the optimal child node is determined, the traversal number of the optimal child node is added with 1, and the optimal child node is represented to be traversed.
In the embodiment of the application, in the process of determining that the optimal child node reversely traverses to the root node, 1 is added to the traversal times of each traversed node, and the node value corresponding to each traversed node is updated to be the sum of the node value of the current node and the node value corresponding to the child node, so that the node value is updated.
Determining a best child node from the at least one child node, comprising:
determining the traversal times and the node value of at least one child node corresponding to each child node;
determining an optimal child node from at least one child node according to the traversal times and the node value; the node value represents the influence of the diagnosis and treatment knowledge points corresponding to the node on the target disease diagnosis.
It is worth noting that each node in the monte carlo tree includes a node value and a node traversal number, and the node value represents the influence of the diagnosis and treatment knowledge point corresponding to the node on the target disease diagnosis.
The initial value of the node value is determined according to a second target matrix corresponding to the disease diagnosis and treatment knowledge point, and for any candidate diagnosis and treatment knowledge point or basic diagnosis and treatment knowledge point, the initial value of the node value corresponding to the candidate diagnosis and treatment knowledge point or basic diagnosis and treatment knowledge point is determined by determining the corresponding relation between the candidate diagnosis and treatment knowledge point or basic diagnosis and treatment knowledge point and the diagnosis and treatment knowledge point in the second target matrix. The corresponding relation comprises a restriction relation, an identity relation and other relations, if a basic diagnosis and treatment knowledge point or a candidate diagnosis and treatment knowledge point corresponding to a certain node has a restriction relation with a diagnosis and treatment knowledge point in a second target matrix, the initial value of the node corresponding to the node is relatively low, if the basic diagnosis and treatment knowledge point or the candidate diagnosis and treatment knowledge point corresponding to the certain node has an identity relation with the diagnosis and treatment knowledge point in the second target matrix, the initial value of the node corresponding to the node is relatively high, and at present, the corresponding relation between the basic diagnosis and treatment knowledge point or the candidate diagnosis and treatment knowledge point corresponding to the certain node and the diagnosis and treatment knowledge point in the second target matrix can also be other relations, and can be set according to actual conditions.
In the embodiment of the application, an optimal child node is determined from at least one child node through the traversal times and node values of the child nodes, specifically, the optimal child node can be determined through an upper confidence bound UCT algorithm of a tree, for any child node vi, the traversal times n (vi) of the child node, the traversal times n (v) of a parent node of the child node, and the node value q (vi) of the child node are determined to determine the UCT (vi, v) corresponding to the child node vi, and the optimal child node is determined through the following formula:
Figure BDA0003664877090000161
wherein c is a constant, N represents the traversal times, vi represents a group of nodes that the current node can reach, v represents the current node, and Q (vi) represents the node value of its child nodes.
After the UCT (vi, v) of each sub-node is determined, the numerical value of the UCT (vi, v) of each sub-node is compared, and the sub-node corresponding to the maximum value of the UCT (vi, v) is determined as a next target node.
After the at least one diagnosis and treatment path is determined, each candidate path needs to be further judged, and a target diagnosis and treatment path is determined from the at least one diagnosis and treatment path by combining the total node value and the depth value of each path.
After the reference path is determined, the target diagnosis and treatment path needs to be determined from the reference paths by further combining with the actual medical condition, for example, in order to save medical resources, the reference path with the minimum depth value is used as the target diagnosis and treatment path.
An embodiment of the present application provides a data processing apparatus 40, and as shown in fig. 4, the data processing apparatus 40 may include:
the basic diagnosis and treatment knowledge point determining module 410 is configured to acquire case data information of a target user and determine basic diagnosis and treatment knowledge points in the case data information of the target user;
a disease diagnosis and treatment model obtaining module 420, configured to obtain a pre-established disease diagnosis and treatment model; the disease diagnosis and treatment model is a go chessboard type data model which is constructed based on medical record diagnosis samples and contains all diagnosis and treatment knowledge points in the medical record diagnosis samples; elements in the disease diagnosis and treatment model are diagnosis and treatment knowledge points of a medical record diagnosis sample; each medical record diagnosis sample comprises medical record data information of a sample user and/or information of a diagnosis and treatment method which is performed and corresponds to the medical record;
the conversion module 430 is configured to label basic diagnosis and treatment knowledge points in the disease diagnosis and treatment model, and convert the disease diagnosis and treatment model labeled with the basic diagnosis and treatment knowledge points into data in a target format, where the target format includes at least one of an image format, a matrix format, and a text format;
the diagnosis and treatment path determining module 440 is configured to input the data in the target format into a preset artificial intelligence algorithm to obtain at least one diagnosis and treatment path, and determine a target diagnosis and treatment path from the at least one diagnosis and treatment path; and the nodes of the diagnosis and treatment path represent basic diagnosis and treatment knowledge points or target diagnosis and treatment knowledge points corresponding to the information of the subsequent diagnosis and treatment method.
According to the embodiment of the application, a disease diagnosis and treatment model corresponding to a disease diagnosis sample is established, a diagnosis and treatment process full table recorded by a large number of electronic medical records reaches the diagnosis and treatment model to form chess game data, important diagnosis and treatment steps related in a diagnosis and treatment manual become chess game nodes, complex logic calculation participated by diagnosis and treatment information is simplified, a target diagnosis and treatment path is determined, and a diagnosis and treatment method corresponding to the target diagnosis and treatment path is the maximum possible diagnosis and treatment method corresponding to case data information of a target user. The complexity of electronic medical record data in the diagnosis and treatment field is simplified, a data compatible entry is provided for application of algorithms such as counterstudy and the like in the diagnosis and treatment field, changes and rules in massive medical record information are effectively processed, a diagnosis and treatment path is formed by the rules, clinical diagnosis and treatment services are provided, the trial and error process in medical diagnosis is effectively reduced, and the waste of medical resources is effectively reduced.
The embodiment of the present application provides a possible implementation manner, and the conversion module includes:
the first conversion sub-module is used for converting the disease diagnosis and treatment model marked with the basic diagnosis and treatment knowledge points into a target image if the target format is an image format; pixel points of the target image are elements of a disease diagnosis and treatment model;
the second conversion submodule is used for converting the disease diagnosis and treatment model marked with the basic diagnosis and treatment knowledge points into a target matrix if the target format is a matrix format; the elements of the target matrix are elements of a disease diagnosis and treatment model;
and the third conversion sub-module is used for converting the disease diagnosis and treatment model labeled with the basic diagnosis and treatment knowledge points into text contents if the target format is a text format, and each vocabulary in the text contents is an element of the disease diagnosis and treatment model.
The embodiment of the application provides a possible implementation mode, a transverse axis in a disease diagnosis and treatment model represents different attributes of diagnosis and treatment knowledge points, the diagnosis and treatment model comprises at least one attribute, elements in the same column belong to the same attribute, and the size of the diagnosis and treatment model is n x n; the conversion module is specifically used for determining a target attribute corresponding to the basic diagnosis and treatment knowledge point, marking elements corresponding to the target attribute in the disease diagnosis and treatment model, connecting the marked elements to form chess data in the diagnosis and treatment process, and converting the chess data into data in a target format.
The embodiment of the present application provides a possible implementation manner, and the diagnosis and treatment path determining module includes:
the prior library calling sub-module is used for calling a preset prior library and determining the node value of each node in each diagnosis and treatment path based on the preset prior library; the node value represents the influence of the diagnosis and treatment knowledge point corresponding to the node on the target disease diagnosis;
the depth value determining submodule is used for determining the depth value of each diagnosis and treatment path;
the target diagnosis and treatment path determining submodule is used for determining a target diagnosis and treatment path from at least one diagnosis and treatment path according to the node value and the depth value; the prior library is a library constructed based on a disease diagnosis and treatment manual.
The embodiment of the application provides a possible implementation manner, and the target diagnosis and treatment path determining submodule comprises:
the reference path determining unit is used for determining at least one reference path from at least one diagnosis and treatment path; the total node value corresponding to the node of the reference path meets a first preset condition;
and the target diagnosis and treatment path determining unit is used for determining the depth value of each reference path and determining the target diagnosis and treatment path from the reference paths according to the depth value.
The embodiment of the application provides a possible implementation manner, and the target diagnosis and treatment path determining unit is configured to determine a reference path with a smallest depth value as the target diagnosis and treatment path.
The apparatus in the embodiment of the present application may execute the method provided in the embodiment of the present application, and the implementation principle is similar, the actions executed by the modules in the apparatus in the embodiments of the present application correspond to the steps in the method in the embodiments of the present application, and for the detailed functional description of the modules in the apparatus, reference may be made to the description in the corresponding method shown in the foregoing, and details are not repeated here.
The embodiment of the application provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory, wherein the processor executes the computer program to realize the steps of the data processing method, and compared with the related art, the method can realize the following steps: according to the embodiment of the application, basic diagnosis and treatment knowledge points in the case data information of the target user are determined by acquiring the case data information of the target user; acquiring a pre-established disease diagnosis and treatment model; the disease diagnosis and treatment model is a go chessboard type data model which is constructed based on medical record diagnosis samples and contains all diagnosis and treatment knowledge points in the medical record diagnosis samples; elements in the disease diagnosis and treatment model are diagnosis and treatment knowledge points of a medical record diagnosis sample; each medical record diagnosis sample comprises medical record data information of a sample user and/or information of a diagnosis and treatment method which is performed and corresponds to the medical record; marking basic diagnosis and treatment knowledge points in a disease diagnosis and treatment model, and converting the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points into data in a target format, wherein the target format comprises at least one of an image format, a matrix format and a text format; inputting the data in the target format into a preset artificial intelligence algorithm to obtain at least one diagnosis and treatment path output by the artificial intelligence algorithm, and determining a target diagnosis and treatment path from the at least one diagnosis and treatment path; and the nodes of the diagnosis and treatment path represent basic diagnosis and treatment knowledge points or target diagnosis and treatment knowledge points corresponding to the subsequent diagnosis and treatment method information. According to the embodiment of the application, a disease diagnosis and treatment model corresponding to a disease diagnosis sample is established, a diagnosis and treatment process sufficient list recorded by a large number of electronic medical records reaches the diagnosis and treatment model to form chess game data, important diagnosis and treatment steps related in a diagnosis and treatment manual become chess game nodes, complex logic calculation of diagnosis and treatment information participation is simplified, a target diagnosis and treatment path is determined, and a corresponding diagnosis and treatment method in the target diagnosis and treatment path is a maximum-possibility diagnosis and treatment method corresponding to case data information of a target user. The complexity of electronic medical record data in the diagnosis and treatment field is simplified, a data compatible entry is provided for application of algorithms such as counterstudy and the like in the diagnosis and treatment field, changes and rules in massive medical record information are effectively processed, a diagnosis and treatment path is formed by the rules, clinical diagnosis and treatment services are provided, the trial and error process in medical diagnosis is effectively reduced, and the waste of medical resources is effectively reduced.
In an alternative embodiment, an electronic device is provided, as shown in fig. 5, the electronic device 5000 shown in fig. 5 includes: a processor 5001 and a memory 5003. The processor 5001 and the memory 5003 are coupled, such as via a bus 5002. Optionally, the electronic device 5000 may further include a transceiver 5004, and the transceiver 5004 may be used for data interaction between the electronic device and other electronic devices, such as transmission of data and/or reception of data. It should be noted that the transceiver 5004 is not limited to one in practical application, and the structure of the electronic device 5000 is not limited to the embodiment of the present application.
The Processor 5001 may be a CPU (Central Processing Unit), a general-purpose Processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other Programmable logic device, a transistor logic device, a hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. The processor 5001 may also be a combination of computing functions, e.g., comprising one or more microprocessors, a combination of a DSP and a microprocessor, or the like.
Bus 5002 can include a path that conveys information between the aforementioned components. The bus 5002 may be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus 5002 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 5, but this is not intended to represent only one bus or type of bus.
The Memory 5003 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical Disc storage, optical Disc storage (including Compact Disc, laser Disc, optical Disc, digital versatile Disc, blu-ray Disc, etc.), a magnetic Disc storage medium, other magnetic storage devices, or any other medium that can be used to carry or store a computer program and that can be Read by a computer, without limitation.
The memory 5003 is used for storing computer programs for executing the embodiments of the present application, and is controlled by the processor 5001 for execution. The processor 5001 is configured to execute computer programs stored in the memory 5003 to implement the steps shown in the foregoing method embodiments.
The electronic device package may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle-mounted terminal (e.g., a car navigation terminal), etc., and a stationary terminal such as a digital TV, a desktop computer, etc., among others. The electronic device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
Embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, and when being executed by a processor, the computer program may implement the steps and corresponding contents of the foregoing method embodiments. Compared with the prior art, the method can realize that: according to the embodiment of the application, basic diagnosis and treatment knowledge points in the case data information of the target user are determined by acquiring the case data information of the target user; acquiring a pre-established disease diagnosis and treatment model; the disease diagnosis and treatment model is a go chessboard type data model which is constructed based on medical record diagnosis samples and contains all diagnosis and treatment knowledge points in the medical record diagnosis samples; elements in the disease diagnosis and treatment model are diagnosis and treatment knowledge points of a medical record diagnosis sample; each medical record diagnosis sample comprises medical record data information of a sample user and/or information of a diagnosis and treatment method which is performed and corresponds to the medical record; marking basic diagnosis and treatment knowledge points in a disease diagnosis and treatment model, and converting the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points into data in a target format, wherein the target format comprises at least one of an image format, a matrix format and a text format; inputting the data in the target format into a preset artificial intelligence algorithm to obtain at least one diagnosis and treatment path output by the artificial intelligence algorithm, and determining a target diagnosis and treatment path from the at least one diagnosis and treatment path; and the nodes of the diagnosis and treatment path represent basic diagnosis and treatment knowledge points or target diagnosis and treatment knowledge points corresponding to the information of the subsequent diagnosis and treatment method. According to the embodiment of the application, a disease diagnosis and treatment model corresponding to a disease diagnosis sample is established, a diagnosis and treatment process sufficient list recorded by a large number of electronic medical records reaches the diagnosis and treatment model to form chess game data, important diagnosis and treatment steps related in a diagnosis and treatment manual become chess game nodes, complex logic calculation of diagnosis and treatment information participation is simplified, a target diagnosis and treatment path is determined, and a corresponding diagnosis and treatment method in the target diagnosis and treatment path is a maximum-possibility diagnosis and treatment method corresponding to case data information of a target user. The complexity of electronic medical record data in the diagnosis and treatment field is simplified, a data compatible entry is provided for application of algorithms such as counterstudy in the diagnosis and treatment field, changes and rules in massive medical record information are effectively processed, a diagnosis and treatment path is formed by the rules, clinical diagnosis and treatment services are provided, the trial and error process in medical diagnosis is effectively reduced, and waste of medical resources is effectively reduced.
It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
Embodiments of the present application further provide a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps and corresponding contents of the foregoing method embodiments can be implemented. Compared with the prior art, the method can realize that: according to the embodiment of the application, basic diagnosis and treatment knowledge points in the case data information of the target user are determined by acquiring the case data information of the target user; acquiring a pre-established disease diagnosis and treatment model; the disease diagnosis and treatment model is a go chessboard type data model which is constructed based on medical record diagnosis samples and contains all diagnosis and treatment knowledge points in the medical record diagnosis samples; elements in the disease diagnosis and treatment model are diagnosis and treatment knowledge points of medical record diagnosis samples; each medical record diagnosis sample comprises medical record data information of a sample user and/or information of a diagnosis and treatment method which is performed and corresponds to the medical record; marking basic diagnosis and treatment knowledge points in a disease diagnosis and treatment model, and converting the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points into data in a target format, wherein the target format comprises at least one of an image format, a matrix format and a text format; inputting the data in the target format into a preset artificial intelligence algorithm to obtain at least one diagnosis and treatment path output by the artificial intelligence algorithm, and determining a target diagnosis and treatment path from the at least one diagnosis and treatment path; and the nodes of the diagnosis and treatment path represent basic diagnosis and treatment knowledge points or target diagnosis and treatment knowledge points corresponding to the information of the subsequent diagnosis and treatment method. According to the embodiment of the application, a disease diagnosis and treatment model corresponding to a disease diagnosis sample is established, a diagnosis and treatment process sufficient list recorded by a large number of electronic medical records reaches the diagnosis and treatment model to form chess game data, important diagnosis and treatment steps related in a diagnosis and treatment manual become chess game nodes, complex logic calculation of diagnosis and treatment information participation is simplified, a target diagnosis and treatment path is determined, and a corresponding diagnosis and treatment method in the target diagnosis and treatment path is a maximum-possibility diagnosis and treatment method corresponding to case data information of a target user. The complexity of electronic medical record data in the diagnosis and treatment field is simplified, a data compatible entry is provided for application of algorithms such as counterstudy and the like in the diagnosis and treatment field, changes and rules in massive medical record information are effectively processed, a diagnosis and treatment path is formed by the rules, clinical diagnosis and treatment services are provided, the trial and error process in medical diagnosis is effectively reduced, and the waste of medical resources is effectively reduced.
The terms "first," "second," "third," "fourth," "1," "2," and the like in the description and in the claims of the present application and in the above-described drawings (if any) are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used are interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in other sequences than described or illustrated herein.
It should be understood that, although each operation step is indicated by an arrow in the flowchart of the embodiment of the present application, the implementation order of the steps is not limited to the order indicated by the arrow. In some implementation scenarios of the embodiments of the present application, the implementation steps in the flowcharts may be performed in other sequences as desired, unless explicitly stated otherwise herein. In addition, some or all of the steps in each flowchart may include multiple sub-steps or multiple stages based on an actual implementation scenario. Some or all of these sub-steps or stages may be performed at the same time, or each of these sub-steps or stages may be performed at different times. Under the scenario that the execution time is different, the execution sequence of the sub-steps or phases may be flexibly configured according to the requirement, which is not limited in the embodiment of the present application.
The above are only optional embodiments of partial implementation scenarios in the present application, and it should be noted that, for those skilled in the art, other similar implementation means based on the technical idea of the present application are also within the scope of protection of the embodiments of the present application without departing from the technical idea of the present application.

Claims (10)

1. A method of data processing, comprising:
acquiring medical record data information of a target user, and determining basic diagnosis and treatment knowledge points in the medical record data information of the target user;
acquiring a pre-established disease diagnosis and treatment model; the disease diagnosis and treatment model is a go chessboard type data model which is constructed based on medical record diagnosis samples and contains all diagnosis and treatment knowledge points in the medical record diagnosis samples; elements in the disease diagnosis and treatment model are diagnosis and treatment knowledge points of medical record diagnosis samples; each medical record diagnosis sample comprises medical record data information of a sample user and/or information of a diagnosis and treatment method which is performed and corresponds to a medical record;
marking the basic diagnosis and treatment knowledge points in the disease diagnosis and treatment model, and converting the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points into data in a target format, wherein the target format comprises at least one of an image format, a matrix format and a text format;
inputting the data in the target format into a preset artificial intelligence algorithm to obtain at least one diagnosis and treatment path output by the artificial intelligence algorithm, and determining a target diagnosis and treatment path from the at least one diagnosis and treatment path; and the nodes of the diagnosis and treatment path represent the basic diagnosis and treatment knowledge points or target diagnosis and treatment knowledge points corresponding to the subsequent diagnosis and treatment method information.
2. The method according to claim 1, wherein converting the disease diagnosis model labeled with the basic diagnosis knowledge points into data in a target format comprises:
if the target format is an image format, converting the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points into a target image; pixel points of the target image are elements of the disease diagnosis and treatment model;
if the target format is a matrix format, converting the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points into a target matrix; the elements of the target matrix are elements of the disease diagnosis and treatment model;
and if the target format is a text format, converting the disease diagnosis and treatment model marked with the basic diagnosis and treatment knowledge points into text contents, wherein each vocabulary in the text contents is an element of the disease diagnosis and treatment model.
3. The method according to claim 2, wherein the horizontal axis in the disease diagnosis and treatment model represents different attributes of diagnosis and treatment knowledge points, the disease diagnosis and treatment model comprises at least one attribute, elements in the same column belong to the same attribute, and the size of the disease diagnosis and treatment model is n x n; the method for converting the disease diagnosis and treatment model with the marked basic diagnosis and treatment knowledge points into data in a target format comprises the following steps:
determining a target attribute corresponding to the basic diagnosis and treatment knowledge point, labeling elements corresponding to the target attribute in the disease diagnosis and treatment model, connecting the labeled elements to form chess game data in the diagnosis and treatment process, and converting the chess game data into data in a target format.
4. The method of claim 1, wherein said determining a target clinical pathway from said at least one clinical pathway comprises:
calling a preset prior library, and determining the node value of each node in each diagnosis and treatment path based on the preset prior library; the node value represents the influence of the diagnosis and treatment knowledge point corresponding to the node on the target disease diagnosis;
determining the depth value of each diagnosis and treatment path;
determining a target diagnosis and treatment path from the at least one diagnosis and treatment path according to the node values and the depth values, wherein the prior library is a library constructed based on a disease diagnosis and treatment manual.
5. The method of claim 4, wherein determining a target clinical path from the at least one clinical path based on the node value and the depth value comprises:
determining at least one reference path from the at least one clinical path; the total node value corresponding to the node of the reference path meets a first preset condition;
and determining the depth value of each reference path, and determining a target diagnosis and treatment path from the reference paths according to the depth values.
6. The method according to claim 5, wherein the determining a target clinical path from the reference path according to the depth values comprises:
and determining the reference path with the minimum depth value as a target diagnosis and treatment path.
7. A data processing apparatus, comprising:
the basic diagnosis and treatment knowledge point determining module is used for acquiring case data information of a target user and determining basic diagnosis and treatment knowledge points in the case data information of the target user;
the disease diagnosis and treatment model acquisition module is used for acquiring a pre-established disease diagnosis and treatment model; the disease diagnosis and treatment model is a go chessboard type data model which is constructed based on medical record diagnosis samples and contains all diagnosis and treatment knowledge points in the medical record diagnosis samples; elements in the disease diagnosis and treatment model are diagnosis and treatment knowledge points of medical record diagnosis samples; each medical record diagnosis sample comprises medical record data information of a sample user and/or information of a diagnosis and treatment method which is performed and corresponds to a medical record;
the conversion module is used for marking the basic diagnosis and treatment knowledge points in the disease diagnosis and treatment model and converting the disease diagnosis and treatment model marked with the basic diagnosis and treatment knowledge points into data in a target format, wherein the target format comprises at least one of an image format, a matrix format and a text format;
the diagnosis and treatment path determining module is used for inputting the data in the target format into a preset artificial intelligence algorithm to obtain at least one diagnosis and treatment path output by the artificial intelligence algorithm and determining a target diagnosis and treatment path from the at least one diagnosis and treatment path; and the nodes of the diagnosis and treatment path represent the basic diagnosis and treatment knowledge points or the target diagnosis and treatment knowledge points corresponding to the subsequent diagnosis and treatment method information.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory, characterized in that the processor executes the computer program to implement the steps of the method of any of claims 1-6.
9. 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 according to any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1-6 when executed by a processor.
CN202210590350.2A 2022-05-26 2022-05-26 Data processing method and device, electronic equipment and computer readable storage medium Pending CN114999599A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210590350.2A CN114999599A (en) 2022-05-26 2022-05-26 Data processing method and device, electronic equipment and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210590350.2A CN114999599A (en) 2022-05-26 2022-05-26 Data processing method and device, electronic equipment and computer readable storage medium

Publications (1)

Publication Number Publication Date
CN114999599A true CN114999599A (en) 2022-09-02

Family

ID=83029813

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210590350.2A Pending CN114999599A (en) 2022-05-26 2022-05-26 Data processing method and device, electronic equipment and computer readable storage medium

Country Status (1)

Country Link
CN (1) CN114999599A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116013487A (en) * 2023-03-27 2023-04-25 深圳市浩然盈科通讯科技有限公司 Data adaptation method and system applied to medical system

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104200079A (en) * 2014-08-22 2014-12-10 首都医科大学附属北京佑安医院 Clinical diagnosis and treatment route generating method and system
CN107247881A (en) * 2017-06-20 2017-10-13 北京大数医达科技有限公司 A kind of multi-modal intelligent analysis method and system
CN109346169A (en) * 2018-10-17 2019-02-15 长沙瀚云信息科技有限公司 A kind of artificial intelligence assisting in diagnosis and treatment system and its construction method, equipment and storage medium
CN109754886A (en) * 2019-01-07 2019-05-14 广州达美智能科技有限公司 Therapeutic scheme intelligent generating system, method and readable storage medium storing program for executing, electronic equipment
CN109785928A (en) * 2018-12-25 2019-05-21 平安科技(深圳)有限公司 Diagnosis and treatment proposal recommending method, device and storage medium
CN110297908A (en) * 2019-07-01 2019-10-01 中国医学科学院医学信息研究所 Diagnosis and treatment program prediction method and device

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104200079A (en) * 2014-08-22 2014-12-10 首都医科大学附属北京佑安医院 Clinical diagnosis and treatment route generating method and system
CN107247881A (en) * 2017-06-20 2017-10-13 北京大数医达科技有限公司 A kind of multi-modal intelligent analysis method and system
CN109346169A (en) * 2018-10-17 2019-02-15 长沙瀚云信息科技有限公司 A kind of artificial intelligence assisting in diagnosis and treatment system and its construction method, equipment and storage medium
CN109785928A (en) * 2018-12-25 2019-05-21 平安科技(深圳)有限公司 Diagnosis and treatment proposal recommending method, device and storage medium
CN109754886A (en) * 2019-01-07 2019-05-14 广州达美智能科技有限公司 Therapeutic scheme intelligent generating system, method and readable storage medium storing program for executing, electronic equipment
CN110297908A (en) * 2019-07-01 2019-10-01 中国医学科学院医学信息研究所 Diagnosis and treatment program prediction method and device

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
商金秋;朱卫国;樊银亭;李伟亨;马翠霞;滕东兴;: "基于电子病历可视分析的临床诊断模型" *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116013487A (en) * 2023-03-27 2023-04-25 深圳市浩然盈科通讯科技有限公司 Data adaptation method and system applied to medical system

Similar Documents

Publication Publication Date Title
US10496748B2 (en) Method and apparatus for outputting information
CN111090987B (en) Method and apparatus for outputting information
CN111414393B (en) Semantic similar case retrieval method and equipment based on medical knowledge graph
CN106844368B (en) Method for man-machine conversation, neural network system and user equipment
CN108108426B (en) Understanding method and device for natural language question and electronic equipment
CN112232065B (en) Method and device for mining synonyms
WO2014126657A1 (en) Latent semantic analysis for application in a question answer system
CN110795913B (en) Text encoding method, device, storage medium and terminal
US20220222447A1 (en) Translation method and apparatus, electronic device, and computer-readable storage medium
US20210183526A1 (en) Unsupervised taxonomy extraction from medical clinical trials
CN113707307A (en) Disease analysis method and device, electronic equipment and storage medium
CN113704428A (en) Intelligent inquiry method, device, electronic equipment and storage medium
CN114330267A (en) Structural report template design method based on semantic association
CN114999599A (en) Data processing method and device, electronic equipment and computer readable storage medium
CN109284491A (en) Medicine text recognition method, sentence identification model training method
CN113590811A (en) Text abstract generation method and device, electronic equipment and storage medium
CN113571196A (en) Method and device for constructing medical training sample and method for retrieving medical text
CN110088748B (en) Question generation method and device, question inquiry system and computer readable storage medium
CN116662495A (en) Question-answering processing method, and method and device for training question-answering processing model
CN116090458A (en) Medical information extraction method, device, electronic equipment and storage medium
CN113468307B (en) Text processing method, device, electronic equipment and storage medium
CN114898895A (en) Xinjiang local adverse drug reaction identification method and related device
CN110457455B (en) Ternary logic question-answer consultation optimization method, system, medium and equipment
CN113704421A (en) Information retrieval method and device, electronic equipment and computer readable storage medium
CN116453702B (en) Data processing method, device, system and medium for autism behavior feature set

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