CN115186113A - Method, device and equipment for screening guide texts and storage medium - Google Patents
Method, device and equipment for screening guide texts and storage medium Download PDFInfo
- Publication number
- CN115186113A CN115186113A CN202211088133.XA CN202211088133A CN115186113A CN 115186113 A CN115186113 A CN 115186113A CN 202211088133 A CN202211088133 A CN 202211088133A CN 115186113 A CN115186113 A CN 115186113A
- Authority
- CN
- China
- Prior art keywords
- information
- patient
- nodes
- guide
- decision
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/383—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/316—Indexing structures
- G06F16/322—Trees
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Software Systems (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to the technical field of medical text processing, in particular to a method, a device, equipment and a storage medium for screening guide texts. The method firstly fills the existing disease data information into the internal nodes of the tree structure, and then fills the guide text made aiming at the disease data information into the leaf nodes. When the illness information of the patient is input into a system where the tree structure is located, the illness information is compared with the illness data information at each internal node on the tree structure, so that an internal target intermediate node matched with the illness information of the patient is found, then the decision data information at each leaf node of the internal target intermediate node is compared with the decision information of the patient, a leaf target node matched with the patient is found from each leaf node, and a guide text recorded by the leaf target node is a decision suggestion for patient treatment. The target tree structure constructed by the method can quickly screen out the guideline text for the patient so as to save manpower.
Description
Technical Field
The invention relates to the technical field of medical text processing, in particular to a method, a device, equipment and a storage medium for screening guide texts.
Background
Clinical guidelines, sets of guidelines for system development, help physicians and patients to address specific clinical problems appropriately. The medical clinical guideline not only covers basic clinical relevant theoretical knowledge, but also fuses a large number of scientific and rigorous clinical diagnosis and treatment suggestions, and has important significance for standardizing medical behaviors, reducing medical cost, reducing medical disputes and improving medical quality and efficiency. However, the clinical guidelines have not been used as expected in clinical practice, mainly because: the clinical guideline is based on a static text form, lacks an effective organizational structure and is time-consuming to look up; the vast amount of medical knowledge is frequently modified and supplemented, and it is very difficult to simply rely on manual memory of such knowledge and apply them to complex clinical practices. How to use the artificial intelligence technology for reference, the clinical guideline in the form of static text is structured and knowledgeable, and a clinical decision support system for assisting doctors is built based on the structured and knowledgeable clinical guideline, so that the clinical guideline exerts the maximum value, and the problem to be solved is urgent.
Currently, a representative method for structuring and knowledge of clinical guidelines includes a Guideline Elements Model (GEM), which defines more than 100 Elements in advance and then stores heterogeneous knowledge in clinical guidelines in the form of Elements by adopting a multi-level hierarchical structure. Another representative method is a knowledge network as shown in fig. 2, where the guideline text for the patient is obtained by screening the knowledge network. However, the current structured clinical guidelines are complex in structure, and it is difficult to screen out the guideline text for the patient through the existing structured clinical guidelines (the guideline text records what treatment is taken for what disease in what group of people).
In summary, it is difficult to screen out the guide text for the patient in the prior art.
Thus, there is a need for improvements and enhancements in the art.
Disclosure of Invention
In order to solve the technical problems, the invention provides a method, a device, equipment and a storage medium for screening guide texts, which solve the problem that guide texts for patients are difficult to screen in the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, the present invention provides a method for screening guide texts, wherein the method comprises:
establishing a target tree structure, wherein the target tree structure comprises internal nodes and leaf nodes corresponding to the internal nodes, the internal nodes are filled with disease data information, and the leaf nodes are filled with guide texts formulated aiming at the disease data information;
extracting decision data information in the guide texts, wherein the decision data information is used for distinguishing each guide text;
comparing the diseased information of the patient with the disease data information, and screening the internal nodes of the target tree structure to obtain internal target intermediate nodes matched with the diseased information of the patient in the internal nodes;
comparing patient decision information with the decision data information, and screening from a plurality of leaf nodes of the internal target intermediate node to obtain a leaf target node matched with the patient decision information in the leaf nodes;
and taking the guideline text covered by the leaf target node as the guideline target text for the patient.
In one implementation, the creating a target tree structure, where the target tree structure includes internal nodes and leaf nodes corresponding to the internal nodes, the internal nodes are populated with disease data information, and the leaf nodes are populated with guide texts formulated for the disease data information, and the method includes:
establishing an unfilled tree structure frame, wherein the tree structure frame comprises unfilled internal nodes and unfilled leaf nodes corresponding to the unfilled internal nodes;
filling the disease data information into unfilled internal nodes to obtain a pre-filled tree structure frame;
and filling the guide text into unfilled leaf nodes in the pre-filled tree structure frame to obtain a target tree structure.
In one implementation, the populating the disease data information to unfilled internal nodes results in a pre-populated tree structure framework, including:
according to the internal nodes, obtaining root nodes in the internal nodes and intermediate nodes between the root nodes and the leaf nodes;
according to the disease data information, obtaining first-level disease information and second-level disease information in the disease data information, wherein the second-level disease information is a fine classification of the first-level disease information;
and filling the first-level disease information into the unfilled root nodes, and filling the second-level disease information into the unfilled intermediate nodes according to the dependency relationship, so as to obtain the pre-filled tree structure framework.
In one implementation, the populating the guide text to unfilled leaf nodes in a pre-populated tree structure framework to obtain a target tree structure includes:
recognizing a set symbol of the guide text;
disassembling the guide text according to the set symbol to obtain each guide sentence;
and filling each guide sentence to each unfilled leaf node according to the dependency relationship to obtain a target tree structure.
In one implementation, the extracting decision data information in the guide texts, the decision data information being used for distinguishing each guide text, includes:
recognizing a set symbol of the guide text;
disassembling the guide text according to the set symbol to obtain each guide sentence;
identifying medical entity and/or patient basic information and/or index information covered by each of the guideline sentences, the medical entity being used for characterizing medical interventions taken against the disease, the index information being used for characterizing medical examination indices;
and constructing various decision conditions of each guide sentence in the decision data information according to the medical entity and/or the patient basic information and/or the index information.
In one implementation, the extracting decision data information in the guide text, where the decision data information is used to distinguish between the guide texts, further includes:
extracting relation words among various decision conditions;
and combining various decision conditions into decision condition combinations according to the relation words.
In one implementation, the comparing the disease information of the patient with the disease data information and screening from a plurality of leaf nodes of the internal target intermediate node to obtain the internal target intermediate node matched with the disease information of the patient in the internal node includes:
obtaining first-stage illness information and second-stage illness information in the illness information of the patient according to the illness information of the patient, wherein the second-stage illness information is a fine classification of the first-stage illness information;
comparing the first-level disease information with the first-level disease information in the disease data information, and screening root nodes in the internal nodes to obtain target root nodes in the internal target intermediate nodes;
and comparing the secondary disease information with the secondary disease information in the disease data information, and screening the intermediate nodes of the target root node to obtain the target intermediate nodes in the internal target intermediate nodes.
In one implementation, the comparing the patient decision information with the decision data information and filtering from a plurality of leaf nodes of the internal target intermediate node to obtain a leaf target node matched with the patient decision information includes:
obtaining a patient decision condition composed of patient information and/or patient indexes and/or a medical entity of the patient in the patient decision information according to the patient decision information;
obtaining a decision condition of the guideline sentence, which is composed of medical entity and/or patient basic information and/or index information of the guideline sentence, in the decision data information according to the decision data information;
and comparing the patient decision condition with the decision condition of the guide sentence, and screening from a plurality of leaf nodes of the internal target intermediate node to obtain a leaf target node matched with the patient decision condition in the leaf nodes.
In one implementation, the recognizing the set symbol of the guide text includes:
identifying a semicolon in the set symbol "; "and/or period". ".
In one implementation, the identifying of medical entity and/or patient basic information and/or index information covered by each of the guideline sentences, the medical entity being used to characterize medical interventions undertaken against diseases, the index information being used to characterize various medical examination indices, comprises:
identifying the medical entity and/or the patient basis information and/or the index information using a named entity identification algorithm.
In a second aspect, an embodiment of the present invention further provides an apparatus for screening guide texts, where the apparatus includes the following components:
the tree structure building module is used for building a target tree structure, the target tree structure comprises internal nodes and leaf nodes corresponding to the internal nodes, the internal nodes are filled with disease data information, and the leaf nodes are filled with guide texts formulated aiming at the disease data information;
the information extraction module is used for extracting decision data information in the guide texts, and the decision data information is used for distinguishing each guide text;
the information comparison module is used for comparing the illness information of the patient with the illness data information, screening the internal nodes of the target tree structure, and obtaining internal target intermediate nodes matched with the illness information of the patient in the internal nodes;
a node screening module, configured to compare patient decision information with the decision data information, and screen from a plurality of leaf nodes of the internal target intermediate node to obtain a leaf target node, which is matched with the patient decision information, in the leaf node;
and the guide text screening module is used for taking the guide text covered by the leaf target node as the guide target text for the patient.
In a third aspect, an embodiment of the present invention further provides a terminal device, where the terminal device includes a memory, a processor, and a program that is stored in the memory and is capable of running on the processor, and when the processor executes the program that filters guide texts, the steps of the method for filtering guide texts are implemented.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where a program for filtering guide texts is stored, and when the program for filtering guide texts is executed by a processor, the steps of the method for filtering guide texts described above are implemented.
Has the beneficial effects that: the method fills the existing disease data information into the internal nodes of the tree structure, and then fills the guide text formulated aiming at the disease data information into the leaf nodes, and the disease data information and the guide text also have the subordination relation because the internal nodes and the leaf nodes have the subordination relation. When the illness information of the patient is input into a system where the tree structure is located, the illness information of the patient is compared with the illness data information of each internal node on the tree structure, so that an internal target intermediate node matched with the illness information of the patient can be found step by step, after the internal target intermediate node is found, the decision data information of each leaf node of the internal target intermediate node can be compared with the decision information of the patient, so that the leaf target node matched with the patient is found from each leaf node, and a guide sentence covered by the leaf target node is a decision suggestion for patient treatment. From the analysis, the target tree structure constructed by the method can quickly screen out the guideline text for the patient so as to save labor.
Drawings
FIG. 1 is an overall flow chart of the present invention;
FIG. 2 is a prior art knowledge network;
FIG. 3 is a schematic diagram of a target tree structure according to an embodiment of the present invention;
FIG. 4 is a flow chart of a clinical decision support method based on Chinese medical clinical guidelines in an embodiment of the present invention;
fig. 5 is a schematic block diagram of an internal structure of a terminal device according to an embodiment of the present invention.
Detailed Description
The technical scheme of the invention is clearly and completely described below by combining the embodiment and the attached drawings of the specification. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Clinical guidelines, sets of guidelines for system development, help physicians and patients to address specific clinical problems appropriately. The medical clinical guidelines not only cover basic clinical relevant theoretical knowledge, but also integrate a large number of scientific and rigorous clinical diagnosis and treatment suggestions, and have important significance for standardizing medical behaviors, reducing medical cost, reducing medical disputes and improving medical quality and efficiency. However, the clinical guidelines have not been used as expected in clinical practice, mainly because: the clinical guideline is based on a static text form, lacks an effective organizational structure and is time-consuming to look up; the vast amount of medical knowledge is frequently modified and supplemented, and it is very difficult to simply rely on manual memory of such knowledge and apply them to complex clinical practices. How to use the artificial intelligence technology for reference, the clinical guideline in the form of static text is structured and knowledgeable, and a clinical decision support system for assisting doctors is built based on the structured and knowledgeable clinical guideline, so that the clinical guideline exerts the maximum value, and the problem to be solved is urgent.
A representative method for structuring and knowledge of clinical guidelines currently exists is a Guideline Elements Model (GEM), which defines more than 100 Elements in advance and then stores heterogeneous knowledge in clinical guidelines in the form of Elements by adopting a multi-level hierarchical structure. Another representative method is a knowledge network as shown in fig. 2, where the guideline text for the patient is obtained by screening the knowledge network. However, the current structured clinical guideline is complex in structure, and it is difficult to screen out the guideline text for the patient through the existing structured clinical guideline.
In order to solve the technical problems, the invention provides a method, a device, equipment and a storage medium for screening guide texts, which solve the problem that guide texts for patients are difficult to screen in the prior art. In specific implementation, a target tree structure is established, then the disease information and decision information of a patient are compared with the disease data information and decision data information on the target tree structure respectively, and a target is screened from the guide texts of the leaf target nodes, wherein the guide texts are decision suggestions for the patient (the decision suggestions are treatment suggestions provided for the patient).
For example, the target tree structure established in this embodiment is shown in fig. 3, where "primary stroke prevention guidance specification", "dyslipidemia", "hypertension", "eye disease guidance specification", "ocular tension abnormality", "lens abnormality" belong to disease data information and are located in an internal node, "blood lipid of 50-year-old male is higher than 6mmol/l, requires a certain amount of exercise of long-term drug dry pre-loading", "at least 1 fasting blood lipid is measured every 5 years for adults over 20 years old, including total cholesterol, LDC-C, high density lipoprotein cholesterol and triglyceride measurement", "for ischemic cardiovascular disease and ischemic stroke high risk group, blood lipid should be measured 1 time every 3 to 6 months", "ocular pressure of immature people under 18 years old is higher than 21mmhg, ocular tension should be measured once a day", and are located in a leaf node.
Decision data information such as 50 years old, 20 years old and 18 years old and male and female are extracted from the guide text.
When the illness information of a patient is hypertension and the decision information is 25 years old, the internal node of hypertension matched with the patient is screened out in fig. 3 according to the comparison of the illness information of the patient with the illness data information in the internal nodes in fig. 3, then the decision information of the patient of 25 years old is compared with the decision data corresponding to the internal node of hypertension in fig. 3, so that a guideline text of fasting blood lipids including total cholesterol, LDC-C, high density lipoprotein cholesterol and triglyceride determination for adults over 20 years old and covered by leaf target nodes is screened out, wherein the fasting blood lipids include total cholesterol, LDC-C, high density lipoprotein cholesterol and triglyceride determination for at least 1 measurement every 5 years, and the doctor obtains the decision suggestion of fasting blood lipids including total cholesterol, LDC-C, high density lipoprotein cholesterol and triglyceride determination for the patient according to the guideline text.
Exemplary method
The method for screening guide texts according to the embodiment can be applied to terminal equipment, and the terminal equipment can be a terminal product with a computing function, such as a mobile phone, a computer and the like. In this embodiment, as shown in fig. 1, the method for filtering guide texts specifically includes the following steps S100 to S500:
s100, establishing a target tree structure, wherein the target tree structure comprises internal nodes and leaf nodes corresponding to the internal nodes, the internal nodes are filled with disease data information, and the leaf nodes are filled with guide texts formulated aiming at the disease data information.
The embodiment fills the existing disease data information and guide texts into an empty tree structure frame, so as to realize the combing of the information and facilitate the subsequent screening of the required guide texts. Step S100 includes steps S101 to S106 as follows:
s101, establishing an unfilled tree structure frame, wherein the tree structure frame comprises unfilled root nodes and intermediate nodes (both the root nodes and the intermediate nodes belong to internal nodes) and unfilled leaf nodes corresponding to the unfilled internal nodes.
S102, obtaining first-level disease information and second-level disease information in the disease data information according to the disease data information, wherein the second-level disease information is a fine classification of the first-level disease information.
S103, filling the first-level disease information into the unfilled root nodes, and filling the second-level disease information into the unfilled intermediate nodes according to the dependency relationship, so as to obtain a pre-filled tree structure framework.
The nodes of the embodiment include three levels of nodes, namely a root node, a middle node and a leaf node, the root node is used for placing first-level disease information, the first-level disease information is roughly divided into diseases, for example, stroke is roughly divided into diseases, the middle node is used for placing second-level disease information generated by finely dividing the first-level disease information (dyslipidemia in fig. 3 is finely divided into diseases of stroke), and the leaf node is used for placing guide texts formulated according to the second-level disease information in each middle node. In the embodiment, the disease is divided through the root node and the intermediate node, and the root node, the intermediate node and the disease have a subordinate relationship, so that the corresponding guide text can be conveniently searched step by step according to the disease type.
And S104, identifying the setting symbol of the guide text.
S105, disassembling the guide text according to the set symbol to obtain each guide sentence.
In the present embodiment, a reference symbol includes a semicolon (";") and/or a period (").
In one embodiment, the set symbol is identified by:
and dividing each sentence where each symbol of the guide text is positioned, counting the character length of each sentence to obtain the sentences the character length of which is greater than the set length, and marking as the preselected sentences. Then identifying whether the preselected sentence contains; "and/or". ", if any"; "and/or". The preselected sentence is used as a guide sentence.
For example, the guideline text "an adult over 20 years of age measures fasting plasma lipids at least every 5 years, including total cholesterol, LDC-C, high density lipoprotein cholesterol and triglyceride determinations. For high risk population suffering from ischemic cardiovascular disease and ischemic stroke, the blood lipid should be measured every 3 to 6 months for 1 time. ".
The guide text is divided into the following sentences according to the symbols:
"an adult aged 20 or older measures fasting plasma lipids at least 1 time every 5 years", "an adult aged 20 or older measures fasting plasma lipids at least 1 time every 5 years, including total cholesterol," LDC-C, "high density lipoprotein cholesterol and triglyceride determinations". "," adults over 20 years old measure fasting plasma lipids at least every 5 years, including total cholesterol, LDC-C, high density lipoprotein cholesterol and triglyceride determinations. "," for high risk group of ischemic cardiovascular disease and ischemic stroke ",", should measure the blood lipid every 3 to 6 months for 1 time. "," for high risk group of ischemic cardiovascular disease and ischemic stroke, blood lipid should be measured every 3 to 6 months for 1 time. ".
Of these, only "adults over 20 years of age measure fasting plasma lipids at least 1 time every 5 years, including total cholesterol, LDC-C, high density lipoprotein cholesterol and triglyceride determinations. "," for high risk group of ischemic cardiovascular disease and ischemic stroke, blood lipid should be measured every 3 to 6 months for 1 time. "," an adult over the age of 20 measures fasting plasma lipids at least every 5 years, including total cholesterol, "the character length of these three sentences is greater than twenty, and thus these three sentences are pre-selected sentences.
Then judging whether the three preselected sentences comprise; "and/or". "finally, it was determined that" adults over 20 years of age measured fasting blood lipids, including total cholesterol, LDC-C, high density lipoprotein cholesterol and triglyceride determinations, at least every 5 years. "and" for high risk group of ischemic cardiovascular disease and ischemic stroke, blood lipid should be measured every 3 to 6 months for 1 time. "refers to the south sentence.
In this embodiment, the sentence length is determined first, and then whether the sentence with the length larger than the set character length is included is identified; "and/or". "these two set symbols are because"; "and/or". "generally used to indicate the end of a sentence, the character length is generally larger, so it is identified whether the sentence contains characters or not from the sentences with larger character length; "and/or". "the speed and efficiency of recognition can be improved.
S106, filling each guide sentence to each unfilled leaf node according to the dependency relationship to obtain a target tree structure.
The present embodiment splits the guide text into guide sentences, and one guide sentence is placed in one leaf node to which it is subordinate, i.e., one leaf node corresponds to one guide sentence. Splitting into guideline sentences enables a fine-partitioning of the guideline text such that one guideline sentence is directed to a class of patients, facilitating subsequent accurate localization to one or more guideline sentences matching the patient based on the patient's information, thereby facilitating a physician or patient's understanding of patient treatment decision suggestions from the guideline sentences.
S200, extracting decision data information in the guide texts, wherein the decision data information is used for distinguishing each guide text.
The decision data information is used to characterize what kind of patient is applicable to the guideline text in which the decision data information is located, i.e. the decision data information is the basis for screening guideline text that is applicable to the patient. And the accuracy of the screened guide text can be improved by setting decision data information. Step S200 includes steps S201, S202, S203, S204 as follows:
s201, identifying basic information and/or index information of a medical entity and/or a patient, wherein the basic information and/or the index information of the medical entity and/or the patient are/is covered by each guide sentence, the medical entity is used for representing medical intervention taken aiming at diseases, and the index information is used for representing various medical examination indexes.
In one embodiment, the medical entity includes a disease, a symptom, an operation, an observation operation, a clinical observation, a type of visit, an operation, an event, a morphology and structure of a human body, a drug. The basic information of the patient includes basic information such as age and sex. The index information includes systolic pressure, diastolic pressure, and the like. The medical entity, the patient basic information and the index information are identified by a medical NER (named entity identification) algorithm.
S202, constructing various decision conditions of each guide sentence in the decision data information according to the medical entity and/or the basic information of the patient and/or the index information.
If three of the medical entity, the basic information of the patient and the index information are included in one guide sentence, any one of the three can be used as a decision condition of the guide sentence. In another embodiment, a combination of the three or two is used as the decision condition of the guide sentence. The former can reduce the time required to subsequently identify the decision conditions in the target tree structure based on the patient's decision conditions. The latter can improve the accuracy of the decision conditions in the identified target tree structure.
S203, extracting relation words among various decision conditions.
In this embodiment, the relational terms include "and," "or," "non," "and," and the like.
S204, combining various decision conditions into decision condition combinations according to the relation words.
The decision combination is extracted according to text semantics, and the relation of a plurality of decision variables is changed into the relation of the sum or. When the decision variable value of the patient is obtained, the most relevant complete sentence in the recommended guideline text is decided according to the variable value.
For example, a guideline sentence includes "for high risk group of ischemic cardiovascular disease and ischemic stroke, blood lipid should be measured 1 time every 3 to 6 months", and the guideline sentence includes two decision conditions: ischemic cardiovascular disease (recorded as decision condition A) and ischemic cerebral apoplexy (recorded as decision condition B). Because the decision condition A and the decision condition B are connected by the relation word 'and', the decision condition A and the decision condition B form the relation of 'and'. Namely, only if the decision conditions of the follow-up patients simultaneously satisfy the decision condition A and the decision condition B, the guideline sentences in which the decision condition A and the decision condition B are located can be used as decision suggestions recommended to the patients.
S300, comparing the illness information of the patient with the illness data information, and screening from a plurality of leaf nodes of the internal target intermediate node to obtain the internal target intermediate node matched with the illness information of the patient in the internal node.
Step S300 includes the following steps:
s301, according to the disease information of the patient, primary disease information and secondary disease information of the patient are obtained, and the secondary disease information is a fine classification of the primary disease information.
S302, comparing the first-level disease information with the first-level disease information in the disease data information, and screening root nodes in the internal nodes to obtain target root nodes in the internal target intermediate nodes.
In this embodiment, the primary disease information may be the primary stroke prevention guidance specification or the eye disease guidance specification in fig. 3.
In one embodiment, the length of the English character and the length of the Chinese character contained in the first-level diseased information are counted, the English character length of the first-level diseased information is compared with the English character length of the first-level diseased information in the target tree structure, the Chinese character length of the first-level diseased information is compared with the Chinese character length of the first-level diseased information in the target tree structure, the first-level diseased information matched with the first-level diseased information is matched from each first-level diseased information, and the root node where the matched first-level diseased information is located is the target root node.
And S303, comparing the secondary disease information with the secondary disease information in the disease data information, and screening the intermediate node of the target root node to obtain a target intermediate node in the internal target intermediate node.
The second grade disease information in this embodiment may be dyslipidemia and hypertension in fig. 3, or abnormal intraocular pressure and abnormal crystalline lens.
For example, the second-level disease information is 'intraocular pressure is greater than a normal value', the 'intraocular pressure is greater than the normal value', the 'intraocular pressure abnormality' and the 'lens abnormality' are compared, the 'intraocular pressure abnormality' is matched, and the middle node where the 'intraocular pressure abnormality' is located is the target middle node of the root node 'ocular disease guide specification'.
S400, comparing the patient decision information with the decision data information, and screening from a plurality of leaf nodes of the internal target intermediate node to obtain a leaf target node matched with the patient decision information in the leaf nodes.
The step S400 includes the following steps S401, S402, S403:
s401, obtaining a patient decision condition composed of patient information and/or patient index and/or patient medical entity in the patient decision information according to the patient decision information.
The information of the patient includes age and gender, the indicator of the patient may be triglycerides in fig. 3, and the medical entity may be total cholesterol in fig. 3.
S402, obtaining the decision condition of the guide sentence, which is formed by the medical entity and/or patient basic information and/or index information of the guide sentence, in the decision data information according to the decision data information.
S403, comparing the patient decision condition with the decision condition of the guide sentence, and screening from a plurality of leaf nodes of the internal target intermediate node to obtain a leaf target node matched with the patient decision condition.
If "hypertension" corresponding to the patient is matched in the target tree structure of fig. 3 through step S300, the decision condition of the patient is compared with the two decision conditions of "20 year old adult" and "ischemic cardiovascular disease" in the guideline sentence, respectively, and a decision condition matching with the decision condition of the patient is found, and the leaf node where the matched decision condition is located is the leaf target node.
As shown in fig. 4, steps S300 and S400 are performed by inputting information of disease, symptom, age, sex, etc. of a patient through a clinical decision support system, routing the information to one or more leaf nodes from a root node of a directory tree, then screening a guideline text according to the information of the patient, decision conditions of the guideline sentences contained in the leaf nodes, and decision combinations, and finally presenting the guideline text to a doctor or a patient for assisting or suggesting information.
And S500, taking the guide sentence covered by the leaf target node as a guide target text for the patient.
A patient 25 years old diagnosed with "stroke" and having "hypertension" is screened for guideline text as the guideline target text for that patient, e.g., the guideline sentence on the leaf target node is "an adult aged 20 years old measures fasting blood lipids at least 1 time every 5 years, including total cholesterol, LDC-C, high density lipoprotein cholesterol and triglyceride determinations", which is the guideline target text, and "fasting blood lipids measured at least 1 time every 5 years, including total cholesterol, LDC-C, high density lipoprotein cholesterol and triglyceride determinations", which is the treatment decision suggestion for the patient, in the guideline target text.
In summary, the present invention fills the existing disease data information into the internal nodes of the tree structure, and then fills the guide text formulated for the disease data information into the leaf nodes, and since the internal nodes and the leaf nodes have an affiliation, the disease data information and the guide text also have a corresponding relationship. When the disease information of the patient is input into the system where the tree structure is located, the disease information of the patient is compared with the disease data information at each internal node on the tree structure, so that an internal target intermediate node matched with the disease information of the patient can be found, after the internal target intermediate node is found, the decision data information at each leaf node of the internal target intermediate node can be compared with the decision information of the patient, so that the leaf target node matched with the patient is found from each leaf node, and a guide sentence covered by the leaf target node is a decision suggestion for patient treatment. From the analysis, the target tree structure constructed by the method can quickly screen out the guide text for the patient so as to save labor.
In addition, the method can structure the medical clinical guideline text in a subordinate relationship, divide the guideline text into guideline sentences, and refine decision data information in the guideline sentences so that the guideline clauses can be automatically positioned according to the diseased information of the patient, thereby realizing the automatic clinical decision recommendation, saving the labor cost and applying the method to the structuring and the knowledge of massive clinical guidelines. The knowledge structured by the method can be directly used for building a clinical decision support system.
Exemplary devices
The embodiment also provides a device for screening guide texts, which comprises the following components:
the tree structure building module is used for building a target tree structure, the target tree structure comprises internal nodes and leaf nodes corresponding to the internal nodes, the internal nodes are filled with disease data information, and the leaf nodes are filled with guide texts formulated aiming at the disease data information;
the information extraction module is used for extracting decision data information in the guide texts, and the decision data information is used for distinguishing each guide text;
the information comparison module is used for comparing the illness information of the patient with the illness data information, screening the internal nodes of the target tree structure, and obtaining internal target intermediate nodes matched with the illness information of the patient in the internal nodes;
a node screening module, configured to compare patient decision information with the decision data information, and screen from a plurality of leaf nodes of the internal target intermediate node to obtain a leaf target node, which is matched with the patient decision information, in the leaf node;
and the guide text screening module is used for taking the guide text covered by the leaf target node as the guide target text for the patient.
Based on the above embodiments, the present invention further provides a terminal device, and a schematic block diagram thereof may be as shown in fig. 5. The terminal equipment comprises a processor, a memory, a network interface and a display screen which are connected through a system bus. Wherein the processor of the terminal device is configured to provide computing and control capabilities. The memory of the terminal equipment comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the terminal device is used for connecting and communicating with an external terminal through a network. The computer program is executed by a processor to implement a method of filtering guide text.
It will be understood by those skilled in the art that the block diagram of fig. 5 is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation to the terminal equipment to which the solution of the present invention is applied, and a specific terminal equipment may include more or less components than those shown in the figure, or may combine some components, or have different arrangements of components.
In one embodiment, a terminal device is provided, where the terminal device includes a memory, a processor, and a filtering guidance text program stored in the memory and executable on the processor, and the processor executes the filtering guidance text program to implement the following operation instructions:
establishing a target tree structure, wherein the target tree structure comprises internal nodes and leaf nodes corresponding to the internal nodes, the internal nodes are filled with disease data information, and the leaf nodes are filled with guide texts formulated aiming at the disease data information;
extracting decision data information in the guide texts, wherein the decision data information is used for distinguishing each guide text;
comparing the diseased information of the patient with the disease data information, and screening the internal nodes of the target tree structure to obtain internal target intermediate nodes matched with the diseased information of the patient in the internal nodes;
comparing patient decision information with the decision data information, and screening from a plurality of leaf nodes of the internal target intermediate node to obtain a leaf target node matched with the patient decision information in the leaf nodes;
and taking the guideline text covered by the leaf target node as the guideline target text for the patient.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, databases, or other media used in embodiments provided herein may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct Rambus Dynamic RAM (DRDRAM), and Rambus Dynamic RAM (RDRAM), among others.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (13)
1. A method of filtering guide text, comprising:
establishing a target tree structure, wherein the target tree structure comprises internal nodes and leaf nodes corresponding to the internal nodes, the internal nodes are filled with disease data information, and the leaf nodes are filled with guide texts formulated aiming at the disease data information;
extracting decision data information in the guide texts, wherein the decision data information is used for distinguishing each guide text;
comparing the diseased information of the patient with the disease data information, and screening the internal nodes of the target tree structure to obtain internal target intermediate nodes matched with the diseased information of the patient in the internal nodes;
comparing patient decision information with the decision data information, and screening from a plurality of leaf nodes of the internal target intermediate node to obtain a leaf target node matched with the patient decision information in the leaf nodes;
and taking the guideline text covered by the leaf target node as the guideline target text for the patient.
2. The method of screening guide texts as claimed in claim 1, wherein said building a target tree structure, said target tree structure comprising internal nodes and leaf nodes corresponding to the internal nodes, said internal nodes being populated with disease data information, said leaf nodes being populated with guide texts formulated for said disease data information, comprises:
establishing an unfilled tree structure frame, wherein the tree structure frame comprises unfilled internal nodes and unfilled leaf nodes corresponding to the unfilled internal nodes;
filling the disease data information into unfilled internal nodes to obtain a pre-filled tree structure frame;
and filling the guide text into unfilled leaf nodes in the pre-filled tree structure frame to obtain a target tree structure.
3. The method of screening guide text according to claim 2, wherein the populating the disease data information into unfilled internal nodes results in a pre-populated tree structure framework comprising:
according to the internal nodes, obtaining root nodes in the internal nodes and intermediate nodes between the root nodes and the leaf nodes;
according to the disease data information, obtaining first-level disease information and second-level disease information in the disease data information, wherein the second-level disease information is a fine classification of the first-level disease information;
and filling the first-level disease information into the unfilled root nodes, and filling the second-level disease information into the unfilled intermediate nodes according to the dependency relationship, so as to obtain the pre-filled tree structure framework.
4. The method of screening guide text as recited in claim 2, wherein the populating the guide text to unfilled leaf nodes in a pre-populated tree structure frame to obtain a target tree structure, comprises:
recognizing a set symbol of the guide text;
disassembling the guide text according to the set symbol to obtain each guide sentence;
and filling each guide sentence to each unfilled leaf node according to the dependency relationship to obtain a target tree structure.
5. The method of screening guide texts as claimed in claim 1, wherein said extracting decision data information in said guide texts, said decision data information being used to distinguish each of said guide texts, comprises:
recognizing a set symbol of the guide text;
disassembling the guide text according to the set symbol to obtain each guide sentence;
identifying medical entities and/or patient basic information and/or index information covered by each of the guideline sentences, the medical entities being used for characterizing medical interventions taken against the disease, the index information being used for characterizing medical examination indices;
and constructing various decision conditions of each guide sentence in the decision data information according to the medical entity and/or the patient basic information and/or the index information.
6. The method of screening guide texts as claimed in claim 5, wherein said extracting decision data information in said guide texts, said decision data information being used to distinguish between individual ones of said guide texts, further comprises:
extracting relation words among various decision conditions;
and combining various decision conditions into decision condition combinations according to the relation words.
7. The method of screening guideline text of claim 3 wherein comparing the disease information of the patient with the disease data information, screening from a plurality of leaf nodes of the internal target intermediate node to obtain an internal target intermediate node of the internal nodes that matches the disease information of the patient, comprises:
obtaining first-level diseased information and second-level diseased information in the diseased information of the patient according to the diseased information of the patient, wherein the second-level diseased information is a fine classification of the first-level diseased information;
comparing the first-level disease information with the first-level disease information in the disease data information, and screening root nodes in the internal nodes to obtain target root nodes in the internal target intermediate nodes;
and comparing the secondary disease information with the secondary disease information in the disease data information, and screening the intermediate nodes of the target root node to obtain the target intermediate nodes in the internal target intermediate nodes.
8. The method of screening guideline text of claim 7 wherein comparing patient decision information to the decision data information and screening from a plurality of leaf nodes of the internal target intermediate node to obtain a leaf target node matching the patient decision information comprises:
obtaining a patient decision condition composed of patient information and/or patient indexes and/or a medical entity of the patient in the patient decision information according to the patient decision information;
obtaining a decision condition of the guideline sentence, which is composed of medical entity and/or patient basic information and/or index information of the guideline sentence, in the decision data information according to the decision data information;
and comparing the patient decision condition with the decision condition of the guide sentence, and screening from a plurality of leaf nodes of the internal target intermediate node to obtain a leaf target node matched with the patient decision condition in the leaf nodes.
9. The method of screening guide texts as claimed in claim 5, wherein said identifying the set symbol of the guide text comprises:
a semicolon and/or period in the set symbol is identified.
10. The method of screening guideline text of claim 5 wherein said identifying medical entities and/or patient essential information and/or metric information covered by each of said guideline sentences, said medical entities being for characterizing medical interventions taken against a disease, said metric information being for characterizing medical examination metrics, comprises:
identifying the medical entity and/or the patient basis information and/or the index information using a named entity identification algorithm.
11. An apparatus for screening guide text, the apparatus comprising:
the tree structure building module is used for building a target tree structure, the target tree structure comprises internal nodes and leaf nodes corresponding to the internal nodes, the internal nodes are filled with disease data information, and the leaf nodes are filled with guide texts formulated aiming at the disease data information;
the information extraction module is used for extracting decision data information in the guide texts, and the decision data information is used for distinguishing each guide text;
the information comparison module is used for comparing the illness information of the patient with the illness data information, screening the internal nodes of the target tree structure, and obtaining internal target intermediate nodes matched with the illness information of the patient in the internal nodes;
a node screening module, configured to compare patient decision information with the decision data information, and screen from a plurality of leaf nodes of the internal target intermediate node to obtain a leaf target node, which is matched with the patient decision information, in the leaf node;
and the guide text screening module is used for taking the guide text covered by the leaf target node as the guide target text for the patient.
12. A terminal device, characterized in that the terminal device comprises a memory, a processor and a program for filtering guide texts stored in the memory and operable on the processor, and the processor implements the steps of the method for filtering guide texts according to any one of claims 1 to 10 when executing the program for filtering guide texts.
13. A computer-readable storage medium, characterized in that a program for filtering guide texts is stored on the computer-readable storage medium, and when the program for filtering guide texts is executed by a processor, the steps of the method for filtering guide texts according to any one of claims 1 to 10 are implemented.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211088133.XA CN115186113B (en) | 2022-09-07 | 2022-09-07 | Method, device and equipment for screening guide texts and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211088133.XA CN115186113B (en) | 2022-09-07 | 2022-09-07 | Method, device and equipment for screening guide texts and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115186113A true CN115186113A (en) | 2022-10-14 |
| CN115186113B CN115186113B (en) | 2023-03-31 |
Family
ID=83523494
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211088133.XA Active CN115186113B (en) | 2022-09-07 | 2022-09-07 | Method, device and equipment for screening guide texts and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115186113B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7725328B1 (en) * | 1996-10-30 | 2010-05-25 | American Board Of Family Practice, Inc. | Computer architecture and process of patient generation evolution, and simulation for computer based testing system |
| CN105335620A (en) * | 2015-11-13 | 2016-02-17 | 冯金辉 | System and method for automatically and intelligently providing personalized medical information services |
| US20160063212A1 (en) * | 2014-09-02 | 2016-03-03 | Kyron, Inc. | System for Generating and Updating Treatment Guidelines and Estimating Effect Size of Treatment Steps |
| US20160321402A1 (en) * | 2015-04-28 | 2016-11-03 | Siemens Medical Solutions Usa, Inc. | Data-Enriched Electronic Healthcare Guidelines For Analytics, Visualization Or Clinical Decision Support |
| US20180137250A1 (en) * | 2016-11-15 | 2018-05-17 | Hefei University Of Technology | Mobile health intelligent medical guide system and method thereof |
| CN110379475A (en) * | 2019-06-19 | 2019-10-25 | 平安科技（深圳）有限公司 | The method, apparatus and storage medium of clinical guidelines are improved based on electronic health record |
| CN110929752A (en) * | 2019-10-18 | 2020-03-27 | 平安科技（深圳）有限公司 | Knowledge-driven and data-driven clustering method and related equipment |
| US20200152336A1 (en) * | 2018-11-10 | 2020-05-14 | International Business Machines Corporation | Automated personalized annotation of clinical guidelines |
| CN111834005A (en) * | 2020-07-02 | 2020-10-27 | 医渡云（北京）技术有限公司 | Method, device, medium and equipment for screening medical data based on infectious diseases |
| WO2021125479A1 (en) * | 2019-12-17 | 2021-06-24 | 주식회사 엘지생활건강 | Hair loss management device and hair loss management guideline providing method therefor |
| CN114078576A (en) * | 2021-11-19 | 2022-02-22 | 中国人民解放军总医院 | Clinical assistant decision method, device, equipment and medium |
| US20220230763A1 (en) * | 2019-10-14 | 2022-07-21 | Roche Molecular Systems, Inc. | Method and system for providing interactive medical guideline |
-
2022
- 2022-09-07 CN CN202211088133.XA patent/CN115186113B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7725328B1 (en) * | 1996-10-30 | 2010-05-25 | American Board Of Family Practice, Inc. | Computer architecture and process of patient generation evolution, and simulation for computer based testing system |
| US20160063212A1 (en) * | 2014-09-02 | 2016-03-03 | Kyron, Inc. | System for Generating and Updating Treatment Guidelines and Estimating Effect Size of Treatment Steps |
| US20160321402A1 (en) * | 2015-04-28 | 2016-11-03 | Siemens Medical Solutions Usa, Inc. | Data-Enriched Electronic Healthcare Guidelines For Analytics, Visualization Or Clinical Decision Support |
| CN105335620A (en) * | 2015-11-13 | 2016-02-17 | 冯金辉 | System and method for automatically and intelligently providing personalized medical information services |
| US20180137250A1 (en) * | 2016-11-15 | 2018-05-17 | Hefei University Of Technology | Mobile health intelligent medical guide system and method thereof |
| US20200152336A1 (en) * | 2018-11-10 | 2020-05-14 | International Business Machines Corporation | Automated personalized annotation of clinical guidelines |
| CN110379475A (en) * | 2019-06-19 | 2019-10-25 | 平安科技（深圳）有限公司 | The method, apparatus and storage medium of clinical guidelines are improved based on electronic health record |
| US20220230763A1 (en) * | 2019-10-14 | 2022-07-21 | Roche Molecular Systems, Inc. | Method and system for providing interactive medical guideline |
| CN110929752A (en) * | 2019-10-18 | 2020-03-27 | 平安科技（深圳）有限公司 | Knowledge-driven and data-driven clustering method and related equipment |
| WO2021073259A1 (en) * | 2019-10-18 | 2021-04-22 | 平安科技（深圳）有限公司 | Knowledge-driven and data-driven grouping method and related device |
| WO2021125479A1 (en) * | 2019-12-17 | 2021-06-24 | 주식회사 엘지생활건강 | Hair loss management device and hair loss management guideline providing method therefor |
| CN111834005A (en) * | 2020-07-02 | 2020-10-27 | 医渡云（北京）技术有限公司 | Method, device, medium and equipment for screening medical data based on infectious diseases |
| CN114078576A (en) * | 2021-11-19 | 2022-02-22 | 中国人民解放军总医院 | Clinical assistant decision method, device, equipment and medium |
Non-Patent Citations (5)
| Title |
|---|
| LP WONG: ""Data Analysis in Qualitative Research: A Brief Guide to Using Nvivo"", 《HTTPS://WWW.NCBI.NLM.NIH.GOV/PMC/ARTICLES/PMC4267019/》 * |
| MATHIJS P. HENDRIKS 等: ""Transformation of the National Breast Cancer Guideline Into Data-Driven Clinical Decision Trees"", 《HTTPS://ASCOPUBS.ORG/DOI/FULL/10.1200/CCI.18.00150》 * |
| SHABINA SAYED 等: ""Holo entropy enabled decision tree classifier for breast cancer diagnosis using wisconsin (prognostic) data set"", 《HTTPS://IEEEXPLORE.IEEE.ORG/STAMP/STAMP.JSP?TP=&ARNUMBER=8418532》 * |
| 尹梓名 等: ""基于临床指南的知识图谱构建技术研究"", 《软件》 * |
| 赵延: ""基于本体的开放式临床指南学习工具的研究与实现"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115186113B (en) | 2023-03-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110136788B (en) | Medical record quality inspection method, device, equipment and storage medium based on automatic detection | |
| US10885150B2 (en) | System and a method for assessing patient treatment risk using open data and clinician input | |
| US10831863B2 (en) | System and a method for assessing patient risk using open data and clinician input | |
| CN111710420B (en) | Complication onset risk prediction method, system, terminal and storage medium based on electronic medical record big data | |
| CN105608091B (en) | A kind of construction method and device of dynamic medical knowledge base | |
| CN109887596A (en) | Chronic obstructive disease of lung diagnostic method, device and the computer equipment of knowledge based map | |
| Topaz et al. | Automated identification of wound information in clinical notes of patients with heart diseases: Developing and validating a natural language processing application | |
| JP6907831B2 (en) | Context-based patient similarity methods and equipment | |
| CN112133441B (en) | Method and terminal for establishing MH postoperative crack state prediction model | |
| WO2021151302A1 (en) | Drug quality-control analysis method, apparatus, device, and medium based on machine learning | |
| CN112786204A (en) | Machine learning diabetes onset risk prediction method and application | |
| CN105054897A (en) | Multi-combined-type traditional Chinese medicine electronic diagnosis and treatment method and system | |
| CN110689939A (en) | Recommendation method and device for medication sequence, readable medium and electronic equipment | |
| CN112967803A (en) | Early mortality prediction method and system for emergency patients based on integrated model | |
| CN112786203A (en) | Machine learning diabetic retinopathy morbidity risk prediction method and application | |
| CN111192691A (en) | Method and device for determining medical evaluation table, readable medium and electronic equipment | |
| Chandra et al. | Natural language Processing and Ontology based Decision Support System for Diabetic Patients | |
| CN112071431B (en) | Clinical path automatic generation method and system based on deep learning and knowledge graph | |
| CN115186113B (en) | Method, device and equipment for screening guide texts and storage medium | |
| CN112185564B (en) | Ophthalmic disease prediction method based on structured electronic medical record and storage device | |
| CN107066816B (en) | Medical treatment guidance method and device based on clinical data and server | |
| CN117152827A (en) | Training method of myopia prediction model, myopia prediction method and device | |
| CN116030932A (en) | Medicine recommendation system for hypertension | |
| CN116030934A (en) | System for fusing medical knowledge graph and clinical data aiming at hypertension | |
| CN113140315B (en) | Health self-testing system, server and health detection system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |