CN110019826A - Construction method, construction device, equipment and the storage medium of medical knowledge map - Google Patents
Construction method, construction device, equipment and the storage medium of medical knowledge map Download PDFInfo
- Publication number
- CN110019826A CN110019826A CN201710625156.2A CN201710625156A CN110019826A CN 110019826 A CN110019826 A CN 110019826A CN 201710625156 A CN201710625156 A CN 201710625156A CN 110019826 A CN110019826 A CN 110019826A
- Authority
- CN
- China
- Prior art keywords
- field
- knowledge map
- medical knowledge
- related coefficient
- aiming
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 41
- 230000015654 memory Effects 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 8
- 238000000034 method Methods 0.000 claims description 5
- 201000010099 disease Diseases 0.000 description 17
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 17
- 238000010586 diagram Methods 0.000 description 7
- 238000013507 mapping Methods 0.000 description 7
- 238000007418 data mining Methods 0.000 description 5
- 238000011012 sanitization Methods 0.000 description 4
- 238000001228 spectrum Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000003646 Spearman's rank correlation coefficient Methods 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention proposes construction method, construction device, equipment and the storage mediums of a kind of medical knowledge map, wherein the construction method of the medical knowledge map includes: the related coefficient in the multiple fields for calculate medical medical record between every two field；According to each field marking that the related coefficient is in the multiple field；According to the score and the related coefficient of each field, selection target field and relative field in the multiple field；Medical knowledge map is constructed according to the aiming field and relative field.According to the technical solution of the present invention, medical knowledge map can be constructed with Additional Specialty and experienced doctor, reduces the workload of doctor.
Description
Technical field
The present invention relates to knowledge mapping constructing technology fields, construction method, doctor in particular to medical knowledge map
Treat construction device, computer equipment and the computer readable storage medium of knowledge mapping.
Background technique
Data mining is the processing such as to be processed, classified, clustered to mass data, utilizes statistical analysis and logic analysis
Mode picks out useful information, including feature extraction.As digitizing technique is in the application of medical field, medical data amount is more next
It is bigger, contain many valuable information resources.Medical data mining has a wide range of applications field, comprising: curative activity
Auxiliary diagnosis, medical quality managent, medical information processing, medical research and development, biomedicine, medical image etc..
Medical data has mode polymorphism (such as several with disease), imperfection, timeliness, redundancy and privacy etc.
Feature constitutes challenge to data excacation, and unstructured data especially therein is even more to be difficult to analyze.So being directed to structure
The medical data of change does data mining, is one preferable breach of medical data mining.
Knowledge mapping includes entity (including entity attribute) and the reticular structure that relationship is constituted, in addition rule or rule.Benefit
With knowledge mapping, it may be convenient to the operation such as scan for, predict.Knowledge mapping is combined with data mining, increasingly by
The attention of people.In medical domain, doctor's manual construction medical knowledge map, still, artificial constructed knowledge mapping are relied primarily on
Workload it is very big, need to expend a large amount of human resources.
Therefore, how to reduce doctor and construct the workload of medical knowledge map as technical problem urgently to be resolved.
Summary of the invention
The present invention is based on the above problems, proposes a kind of new technical solution, it is possible to reduce doctor constructs medical treatment and knows
Know the workload of map.
In view of this, the first aspect of the present invention proposes a kind of construction method of medical knowledge map, comprising: calculate doctor
Treat the related coefficient in multiple fields of medical record between every two field；It is in the multiple field according to the related coefficient
Each field marking；According to the score and the related coefficient of each field, the selection target word in the multiple field
Section and relative field；Medical knowledge map is constructed according to the aiming field and relative field.
In the technical scheme, it by calculating the related coefficient between every two field, and gives a mark to it, more
Selection target field and its relevant field in a field construct medical knowledge figure according to aiming field and its relevant field
Spectrum, can assist doctor to construct medical knowledge map, reduce the workload of doctor, to improve building medical knowledge map
Efficiency, save human resources.In addition, since medical knowledge map is constructed according to aiming field and its relevant field
, do not reflect the relationship between all fields, so that medical knowledge map more intuitively reflects between primary fields
Relationship.
In the above-mentioned technical solutions, it is preferable that it is described according to the related coefficient be the multiple field in each word
Section marking, specifically includes: obtaining the related coefficient and its weight between each field and other fields；According to described
The related coefficient between each field and other fields is added by weight, to obtain the score of each field.
In the technical scheme, according to the weight of related coefficient, by the related coefficient between each field and other fields
It is added, so as to which the score of each field is accurately calculated, and then ensure that the accuracy of the medical knowledge map of building.
In any of the above-described technical solution, it is preferable that the medical knowledge map include: the aiming field vertex,
Line segment between the aiming field and relative field and described according to the aiming field and relative word
Section building medical knowledge map, specifically includes: according to the score of the aiming field, determining the vertex ginseng of the aiming field
Number, according to the related coefficient between the aiming field and relative field, determine the aiming field and and its
Line segment parameter between relevant field；The medical knowledge map is constructed according to the vertex parameter and the line segment parameter.
In the technical scheme, the vertex of different target field is different, and different aiming fields is associated therewith
Field between line segment be also different so that medical knowledge map is more intuitive, user when checking medical knowledge map,
It can be quick according to the line segment between the vertex of aiming field in medical knowledge map and the relative field of the aiming field
Ground gets medical information.
In any of the above-described technical solution, it is preferable that the score and the related coefficient according to each field,
Selection target field and relative field in the multiple field, specifically include: obtaining and divide in the multiple field
Number is greater than the field of the first preset threshold as the aiming field；It selects big with the related coefficient of the aiming field
In the second preset threshold field as field relevant to the aiming field.
In the technical scheme, if the score of field is less than or equal to the first preset threshold, i.e. the score of the field compares
It is small, illustrate that the field is not common, then fall the Field Sanitization, to highlight the relatively high word of score in medical knowledge map
Section.In addition, if related coefficient between certain field and aiming field is less than or equal to the second preset threshold, illustrate the field with
Correlation between aiming field is little or even uncorrelated, then does not show the relationship between the field and aiming field.Therefore, lead to
Cross above technical scheme building medical knowledge map so that medical knowledge map more intuitively reflect common field and its
Relevant field.
In any of the above-described technical solution, it is preferable that the related coefficient includes following one or a variety of combinations: inclined phase
Relationship number, multiple correlation coefficient, simple linear correlation coefficient, coefficient of rank correlation, rank correlation coefficient.
The second aspect of the present invention proposes a kind of construction device of medical knowledge map, comprising: computing unit, based on
Calculate the related coefficient in multiple fields of medical medical record between every two field；Marking unit, for according to the related coefficient
For each field marking in the multiple field；Selecting unit, for according to the score of each field to it is described related
Coefficient, selection target field and relative field in the multiple field；Construction unit, for according to the target word
Section and relative field construct medical knowledge map.
In the technical scheme, it by calculating the related coefficient between every two field, and gives a mark to it, more
Selection target field and its relevant field in a field construct medical knowledge figure according to aiming field and its relevant field
Spectrum, can assist doctor to construct medical knowledge map, reduce the workload of doctor, to improve building medical knowledge map
Efficiency, save human resources.In addition, since medical knowledge map is constructed according to aiming field and its relevant field
, do not reflect the relationship between all fields, so that medical knowledge map more intuitively reflects between primary fields
Relationship.
In the above-mentioned technical solutions, it is preferable that the marking unit is specifically used for, and obtains each field and other words
The related coefficient and its weight between section, according to the weight by the phase between each field and other fields
Relationship number is added, to obtain the score of each field.
In the technical scheme, according to the weight of related coefficient, by the related coefficient between each field and other fields
It is added, so as to which the score of each field is accurately calculated, and then ensure that the accuracy of the medical knowledge map of building.
In any of the above-described technical solution, it is preferable that the medical knowledge map include: the aiming field vertex,
Line segment and the construction unit between the aiming field and relative field are specifically used for, according to the target
The score of field determines the vertex parameter of the aiming field, according between the aiming field and relative field
The related coefficient determines the line segment parameter between the aiming field and relative field, according to the vertex parameter
The medical knowledge map is constructed with the line segment parameter.
In the technical scheme, the vertex of different target field is different, and different aiming fields is associated therewith
Field between line segment be also different so that medical knowledge map is more intuitive, user when checking medical knowledge map,
It can be quick according to the line segment between the vertex of aiming field in medical knowledge map and the relative field of the aiming field
Ground gets medical information.
In any of the above-described technical solution, it is preferable that the score and the related coefficient according to each field,
The selecting unit is specifically used for, and score is obtained in the multiple field and is greater than the field of the first preset threshold as the mesh
Marking-up section, select with the related coefficient of the aiming field be greater than the second preset threshold field as with the target
The relevant field of field.
In the technical scheme, if the score of field is less than or equal to the first preset threshold, i.e. the score of the field compares
It is small, illustrate that the field is not common, then fall the Field Sanitization, to highlight the relatively high word of score in medical knowledge map
Section.In addition, if related coefficient between certain field and aiming field is less than or equal to the second preset threshold, illustrate the field with
Correlation between aiming field is little or even uncorrelated, then does not show the relationship between the field and aiming field.Therefore, lead to
Cross above technical scheme building medical knowledge map so that medical knowledge map more intuitively reflect common field and its
Relevant field.
In any of the above-described technical solution, it is preferable that the related coefficient includes following one or a variety of combinations: inclined phase
Relationship number, multiple correlation coefficient, simple linear correlation coefficient, coefficient of rank correlation, rank correlation coefficient.
According to the third aspect of the invention we, a kind of computer equipment is proposed, computer equipment includes processor, processor
The medical treatment such as any one of the technical solution of above-mentioned first aspect is realized when for executing the computer program stored in memory
The step of construction method of knowledge mapping.
According to the fourth aspect of the invention, a kind of computer readable storage medium is proposed, computer journey is stored thereon with
Sequence realizes the medical knowledge map such as any one of the technical solution of above-mentioned first aspect when computer program is executed by processor
Construction method the step of.
According to the technical solution of the present invention, medical knowledge map can be constructed with Additional Specialty and experienced doctor, from
And reduce the workload that doctor constructs medical knowledge map.
Detailed description of the invention
Fig. 1 shows the flow diagram of the construction method of medical knowledge map according to an embodiment of the invention；
Fig. 2 shows the schematic diagrames of medical knowledge map according to an embodiment of the invention；
Fig. 3 shows the structural schematic diagram of the construction device of medical knowledge map according to an embodiment of the invention；
Fig. 4 shows the schematic block diagram of the computer equipment of the embodiment of the present invention.
Specific embodiment
It is with reference to the accompanying drawing and specific real in order to be more clearly understood that the above objects, features and advantages of the present invention
Applying mode, the present invention is further described in detail.It should be noted that in the absence of conflict, the implementation of the application
Feature in example and embodiment can be combined with each other.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention, still, the present invention may be used also
To be implemented using other than the one described here other modes, therefore, protection scope of the present invention is not by described below
Specific embodiment limitation.
Fig. 1 shows the flow diagram of the construction method of medical knowledge map according to an embodiment of the invention.
As shown in Figure 1, the construction method of medical knowledge map according to an embodiment of the invention, comprising:
Step 102, the related coefficient in multiple fields of medical medical record between every two field is calculated.
Wherein, multiple fields include but is not limited to following one or a variety of combinations: the age, disease, department, is controlled gender
Treatment expense, treatment time.
Step 104, according to each field marking that related coefficient is in multiple fields.
Step 106, according to the score and related coefficient of each field, in multiple fields selection target field and with its phase
The field of pass.
Step 108, medical knowledge map is constructed according to aiming field and relative field.
Preferably, above-mentioned medical knowledge map be relation map and be it is undirected, can to the medical knowledge map into
Row causality analysis is constructed to oriented medical knowledge map.
In the technical scheme, it by calculating the related coefficient between every two field, and gives a mark to it, more
Selection target field and its relevant field in a field construct medical knowledge figure according to aiming field and its relevant field
Spectrum, can assist doctor to construct medical knowledge map, reduce the workload of doctor, to improve building medical knowledge map
Efficiency, save human resources.In addition, since medical knowledge map is constructed according to aiming field and its relevant field
, do not reflect the relationship between all fields, so that medical knowledge map more intuitively reflects between primary fields
Relationship.And the relationship in this programme between field is that automatic processing obtains, and is not obtained by artificial treatment, with auxiliary
Help doctor's decision.
It is understood that step 104 specifically includes: obtain related coefficient between each field and other fields and its
Weight；The related coefficient between each field and other fields is added according to weight, to obtain the score of each field.
For example, field is disease, the related coefficient between disease and age is 0.8, the phase relation between disease and age
Several weights is a, and the related coefficient between disease and gender is 0.2, and the weight of the related coefficient between disease and gender is b,
Related coefficient between disease and medical expense is 0.6, and the weight of the related coefficient between disease and medical expense is c, Z=a
× 0.8+b × 0.2+c × 0.6, Z indicate score when field is disease.
According to the weight of related coefficient, the related coefficient between each field and other fields is added, so as to standard
The score of each field really is calculated, and then ensure that the accuracy of the medical knowledge map of building.
It is understood that medical knowledge map includes: vertex, aiming field and the relative field of aiming field
Between line segment and step 108 specifically include: according to the score of aiming field, determine the vertex parameter of aiming field, according to
Related coefficient between aiming field and relative field determines the line segment between aiming field and relative field
Parameter；Medical knowledge map is constructed according to vertex parameter and line segment parameter.
Wherein, vertex parameter includes but is not limited to: vertex size and/or vertex color, line segment parameter includes but is not limited to:
Line segment thickness and/or line segment color.For example, the score of aiming field is bigger, vertex is bigger or the color on its vertex just
It is deeper.Related coefficient between aiming field and relative field is bigger, between aiming field and relative field
Line segment it is thicker or line segment color is deeper.
For example, there is a field on each vertex of tetrahedron figure, often as shown in Fig. 2, medical knowledge map is tetrahedron figure
There is line segment connection between two fields.Take second place, where treatment time on the vertex where vertex maximum, medical expense where disease
Vertex of the vertex third, where season it is minimum, illustrate that disease, medical expense, treatment time and the score in season successively drop
It is low.Line segment, medical expense between disease and medical expense and the line segment between treatment time are most thick, treatment time and disease it
Between line segment take second place, between line segment, season between season and treatment time and the line segment between disease, season and medical expense
Line segment it is most thin, illustrate correlation, medical expense and the correlation maximum between treatment time between disease and medical expense,
Correlation between season and other fields (treatment time, medical expense or disease) is minimum.
The vertex of different target field is different, and the line segment between the different relative fields of aiming field
Also it is different, so that medical knowledge map is more intuitive, user, can be according to medical knowledge when checking medical knowledge map
Line segment in map between the vertex of aiming field and the relative field of the aiming field rapidly gets medical information.
It is understood that step 106 specifically includes: obtaining the word that score is greater than the first preset threshold in multiple fields
Duan Zuowei aiming field；Select with the related coefficient of aiming field be greater than the second preset threshold field as with aiming field
Relevant field.
If the score of field is less than or equal to the first preset threshold, i.e. the score of the field is smaller, illustrates the field simultaneously
It is uncommon, then the Field Sanitization is fallen, to highlight the relatively high field of score in medical knowledge map.In addition, if some
Related coefficient between field and aiming field is less than or equal to the second preset threshold, illustrates between the field and aiming field
Correlation is little or even uncorrelated, then does not show the relationship between the field and aiming field.Therefore, pass through above technical scheme
Medical knowledge map is constructed, so that medical knowledge map more intuitively reflects common field and its relevant field.
It is understood that related coefficient includes following one or a variety of combinations: partial correlation coefficient, multiple correlation coefficient,
Simple linear correlation coefficient (such as Pearson correlation coefficient), coefficient of rank correlation (such as Kendall's tua-b grade phase
Relationship number), rank correlation coefficient (such as Spearman rank correlation coefficient).
Fig. 3 shows the structural schematic diagram of the construction device of medical knowledge map according to an embodiment of the invention.
As shown in figure 3, the construction device 300 of medical knowledge map according to an embodiment of the invention, comprising: calculate
Unit 302, marking unit 304, selecting unit 306 and construction unit 308.
Computing unit 302, the related coefficient in multiple fields for calculating medical medical record between every two field；Marking
Unit 304, for being that each field in multiple fields is given a mark according to related coefficient；Selecting unit 306, for according to each word
The score and related coefficient of section, selection target field and relative field in multiple fields；Construction unit 308, is used for
Medical knowledge map is constructed according to aiming field and relative field.
In the technical scheme, it by calculating the related coefficient between every two field, and gives a mark to it, more
Selection target field and its relevant field in a field construct medical knowledge figure according to aiming field and its relevant field
Spectrum, can assist doctor to construct medical knowledge map, reduce the workload of doctor, to improve building medical knowledge map
Efficiency, save human resources.In addition, since medical knowledge map is constructed according to aiming field and its relevant field
, do not reflect the relationship between all fields, so that medical knowledge map more intuitively reflects between primary fields
Relationship.And the relationship in this programme between field is that automatic processing obtains, and is not obtained by artificial treatment, with auxiliary
Help doctor's decision.
It is understood that marking unit 304 is specifically used for, the related coefficient between each field and other fields is obtained
And its weight, the related coefficient between each field and other fields is added according to weight, to obtain the score of each field.
According to the weight of related coefficient, the related coefficient between each field and other fields is added, so as to standard
The score of each field really is calculated, and then ensure that the accuracy of the medical knowledge map of building.
It is understood that medical knowledge map includes: vertex, aiming field and the relative field of aiming field
Between line segment and construction unit 308 be specifically used for, according to the score of aiming field, determine the vertex parameter of aiming field,
According to the related coefficient between aiming field and relative field, determine between aiming field and relative field
Line segment parameter constructs medical knowledge map according to vertex parameter and line segment parameter.
The vertex of different target field is different, and the line segment between the different relative fields of aiming field
Also it is different, so that medical knowledge map is more intuitive, user, can be according to medical knowledge when checking medical knowledge map
Line segment in map between the vertex of aiming field and the relative field of the aiming field rapidly gets medical information.
It is understood that selecting unit 306 is specifically used for, multiple according to the score and related coefficient of each field
Field of the score greater than the first preset threshold is obtained in field as aiming field, is selected big with the related coefficient of aiming field
In the second preset threshold field as field relevant to aiming field.
If the score of field is less than or equal to the first preset threshold, i.e. the score of the field is smaller, illustrates the field simultaneously
It is uncommon, then the Field Sanitization is fallen, to highlight the relatively high field of score in medical knowledge map.In addition, if some
Related coefficient between field and aiming field is less than or equal to the second preset threshold, illustrates between the field and aiming field
Correlation is little or even uncorrelated, then does not show the relationship between the field and aiming field.Therefore, pass through above technical scheme
Medical knowledge map is constructed, so that medical knowledge map more intuitively reflects common field and its relevant field.
It is understood that related coefficient includes following one or a variety of combinations: partial correlation coefficient, multiple correlation coefficient,
Simple linear correlation coefficient, coefficient of rank correlation, rank correlation coefficient.
Fig. 4 shows the schematic block diagram of the computer equipment of the embodiment of the embodiment of the present disclosure.
As shown in figure 4, according to the computer equipment 40 of the embodiment of the embodiment of the present disclosure, including memory 402, processor
404 and it is stored in the computer program that can be run on the memory 402 and on the processor 404, wherein memory 402
It can be connected by bus between processor 404, the processor 404 is for executing the computer stored in memory 402
The step of as above construction method of medical knowledge map as described in the examples is realized when program.
Step in the method for the embodiment of the present disclosure can be sequentially adjusted, merged and deleted according to actual needs.
Unit in the construction device and computer equipment of the medical knowledge map of the embodiment of the present disclosure can be according to reality
It needs to be combined, divided and deleted.
According to the embodiment of the present disclosure, a kind of computer readable storage medium is proposed, is stored thereon with computer program, institute
The step of stating the construction method that the medical knowledge map as described in above-described embodiment is realized when computer program is executed by processor.
Further, one of ordinary skill in the art will appreciate that whole in the various methods of above-described embodiment
Or part steps are relevant hardware can be instructed to complete by program, which can store computer-readable deposits in one
In storage media, storage medium includes read-only memory (Read-Only Memory, ROM), random access memory (Random
Access Memory, RAM), it is programmable read only memory (Programmable Read-only Memory, PROM), erasable
Only except programmable read only memory (Erasable Programmable Read Only Memory, EPROM), disposable programmable
Reading memory (One-time Programmable Read-Only Memory, OTPROM), the electronics formula of erasing can make carbon copies read-only
Memory (Electrically-Erasable Programmable Read-Only Memory, EEPROM), CD-ROM
(Compact Disc Read-Only Memory, CD-ROM) or other disc memories, magnetic disk storage, magnetic tape storage,
Or it can be used in any other computer-readable medium of carrying or storing data.
Further, above-mentioned computer equipment can hold for PC (Personal Computer, PC).
The technical scheme of the present invention has been explained in detail above with reference to the attached drawings, according to the technical solution of the present invention, can assist
Professional and experienced doctor constructs medical knowledge map, to reduce the workload that doctor constructs medical knowledge map
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (12)
1. a kind of construction method of medical knowledge map characterized by comprising
Calculate the related coefficient in multiple fields of medical medical record between every two field；
According to each field marking that the related coefficient is in the multiple field；
According to the score and the related coefficient of each field, in the multiple field selection target field and with its phase
The field of pass；
Medical knowledge map is constructed according to the aiming field and relative field.
2. the construction method of medical knowledge map according to claim 1, which is characterized in that described according to the phase relation
Number is each field marking in the multiple field, is specifically included:
Obtain the related coefficient and its weight between each field and other fields；
The related coefficient between each field and other fields is added according to the weight, it is described each to obtain
The score of field.
3. the construction method of medical knowledge map according to claim 1, which is characterized in that the medical knowledge map packet
It includes: line segment between the vertex of the aiming field, the aiming field and relative field and described according to
Aiming field and relative field construct medical knowledge map, specifically include:
According to the score of the aiming field, determine the vertex parameter of the aiming field, according to the aiming field and and its
The related coefficient between relevant field determines the line segment parameter between the aiming field and relative field；
The medical knowledge map is constructed according to the vertex parameter and the line segment parameter.
4. the construction method of medical knowledge map according to claim 1, which is characterized in that described according to each word
The score and the related coefficient of section, selection target field and relative field in the multiple field specifically include:
Score is obtained in the multiple field is greater than the field of the first preset threshold as the aiming field；
Select with the related coefficient of the aiming field be greater than the second preset threshold field as with the target word
The relevant field of section.
5. the construction method of medical knowledge map according to any one of claim 1 to 4, which is characterized in that
The related coefficient includes following one or a variety of combinations: partial correlation coefficient, multiple correlation coefficient, simple linear correlation system
Number, coefficient of rank correlation, rank correlation coefficient.
6. a kind of construction device of medical knowledge map characterized by comprising
Computing unit, the related coefficient in multiple fields for calculating medical medical record between every two field；
Marking unit, for being that each field in the multiple field is given a mark according to the related coefficient；
Selecting unit selects mesh in the multiple field for the score and the related coefficient according to each field
Marking-up section and relative field；
Construction unit, for constructing medical knowledge map according to the aiming field and relative field.
7. the construction device of medical knowledge map according to claim 6, which is characterized in that the marking unit is specifically used
In,
The related coefficient and its weight between each field and other fields are obtained,
The related coefficient between each field and other fields is added according to the weight, it is described each to obtain
The score of field.
8. the construction device of medical knowledge map according to claim 6, which is characterized in that the medical knowledge map packet
It includes: line segment and the construction unit between the vertex of the aiming field, the aiming field and relative field
It is specifically used for,
According to the score of the aiming field, determine the vertex parameter of the aiming field, according to the aiming field and and its
The related coefficient between relevant field determines the line segment parameter between the aiming field and relative field,
The medical knowledge map is constructed according to the vertex parameter and the line segment parameter.
9. the construction device of medical knowledge map according to claim 6, which is characterized in that the selecting unit is specifically used
In,
Score is obtained in the multiple field is greater than the field of the first preset threshold as the aiming field,
Select with the related coefficient of the aiming field be greater than the second preset threshold field as with the target word
The relevant field of section.
10. the construction device of medical knowledge map according to any one of claims 6 to 9, which is characterized in that
The related coefficient includes following one or a variety of combinations: partial correlation coefficient, multiple correlation coefficient, simple linear correlation system
Number, coefficient of rank correlation, rank correlation coefficient.
11. a kind of computer equipment, which is characterized in that the computer equipment includes processor, and the processor is for executing
The building of the medical knowledge map as described in any one of claims 1 to 5 is realized when the computer program stored in memory
The step of method.
12. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of construction method of the medical knowledge map as described in any one of claims 1 to 5 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710625156.2A CN110019826B (en) | 2017-07-27 | 2017-07-27 | Construction method, construction device, equipment and storage medium of medical knowledge map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710625156.2A CN110019826B (en) | 2017-07-27 | 2017-07-27 | Construction method, construction device, equipment and storage medium of medical knowledge map |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110019826A true CN110019826A (en) | 2019-07-16 |
| CN110019826B CN110019826B (en) | 2023-02-28 |
Family
ID=67185990
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710625156.2A Active CN110019826B (en) | 2017-07-27 | 2017-07-27 | Construction method, construction device, equipment and storage medium of medical knowledge map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110019826B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114998816A (en) * | 2022-08-08 | 2022-09-02 | 深圳市指南针医疗科技有限公司 | Skeleton AI video-based case improvement method, device and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1701343A (en) * | 2002-09-20 | 2005-11-23 | 德克萨斯大学董事会 | Computer program products, systems and methods for information discovery and relational analyses |
| KR20060090539A (en) * | 2005-02-07 | 2006-08-11 | 오성환 | Integrated knowledge building system of university libraries |
| EP2015249A2 (en) * | 2007-06-07 | 2009-01-14 | Kabushiki Kaisha Toshiba | Data processing apparatus, medical diagnostic apparatus, data processing method and medical diagnostic method |
| CN106326211A (en) * | 2016-08-17 | 2017-01-11 | 海信集团有限公司 | Determination method and device for distance between keywords in interactive statement |
| CN106447419A (en) * | 2015-08-11 | 2017-02-22 | 奥多比公司 | Visitor identification based on feature selection |
| CN106844325A (en) * | 2015-12-04 | 2017-06-13 | 北大医疗信息技术有限公司 | Medical information processing method and medical information processing unit |
| CN106874643A (en) * | 2016-12-27 | 2017-06-20 | 中国科学院自动化研究所 | Build the method and system that knowledge base realizes assisting in diagnosis and treatment automatically based on term vector |
| CN106874695A (en) * | 2017-03-22 | 2017-06-20 | 北京大数医达科技有限公司 | The construction method and device of medical knowledge collection of illustrative plates |
| CN106951526A (en) * | 2017-03-21 | 2017-07-14 | 北京邮电大学 | A kind of entity set extended method and device |
-
2017
- 2017-07-27 CN CN201710625156.2A patent/CN110019826B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1701343A (en) * | 2002-09-20 | 2005-11-23 | 德克萨斯大学董事会 | Computer program products, systems and methods for information discovery and relational analyses |
| KR20060090539A (en) * | 2005-02-07 | 2006-08-11 | 오성환 | Integrated knowledge building system of university libraries |
| EP2015249A2 (en) * | 2007-06-07 | 2009-01-14 | Kabushiki Kaisha Toshiba | Data processing apparatus, medical diagnostic apparatus, data processing method and medical diagnostic method |
| CN106447419A (en) * | 2015-08-11 | 2017-02-22 | 奥多比公司 | Visitor identification based on feature selection |
| CN106844325A (en) * | 2015-12-04 | 2017-06-13 | 北大医疗信息技术有限公司 | Medical information processing method and medical information processing unit |
| CN106326211A (en) * | 2016-08-17 | 2017-01-11 | 海信集团有限公司 | Determination method and device for distance between keywords in interactive statement |
| CN106874643A (en) * | 2016-12-27 | 2017-06-20 | 中国科学院自动化研究所 | Build the method and system that knowledge base realizes assisting in diagnosis and treatment automatically based on term vector |
| CN106951526A (en) * | 2017-03-21 | 2017-07-14 | 北京邮电大学 | A kind of entity set extended method and device |
| CN106874695A (en) * | 2017-03-22 | 2017-06-20 | 北京大数医达科技有限公司 | The construction method and device of medical knowledge collection of illustrative plates |
Non-Patent Citations (2)
| Title |
|---|
| SEN WANG; XIAOJUN CHANG; XUE LI; GUODONG LONG; LINA YAO; QUAN Z. SHENG: "Diagnosis Code Assignment Using Sparsity-Based Disease Correlation Embedding" * |
| 漆桂林;高桓;吴天星;: "知识图谱研究进展" * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114998816A (en) * | 2022-08-08 | 2022-09-02 | 深圳市指南针医疗科技有限公司 | Skeleton AI video-based case improvement method, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110019826B (en) | 2023-02-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kukkala et al. | Core concepts of spatial prioritisation in systematic conservation planning | |
| Hunt et al. | A general procedure for constructing mortality models | |
| Braithwaite | Glacier mass balance: the first 50 years of international monitoring | |
| Collen et al. | The tropical biodiversity data gap: addressing disparity in global monitoring | |
| Miller | Virtual species distribution models: using simulated data to evaluate aspects of model performance | |
| Umlauf et al. | A primer on Bayesian distributional regression | |
| Golicher et al. | Pseudo-absences, pseudo-models and pseudo-niches: pitfalls of model selection based on the area under the curve | |
| Matthews et al. | Multimodal species abundance distributions: a deconstruction approach reveals the processes behind the pattern | |
| Zhu et al. | Schistosoma japonicum transmission risk maps at present and under climate change in mainland China | |
| Hefley et al. | Statistical indicators and state–space population models predict extinction in a population of bobwhite quail | |
| KR102075743B1 (en) | Apparatus and method for body growth prediction modeling | |
| CN107784046B (en) | POI information processing method and device | |
| Robinson-García et al. | An insight into the importance of national university rankings in an international context: the case of the I-UGR rankings of Spanish universities | |
| Yin et al. | Confidence intervals for differences between volumes under receiver operating characteristic surfaces (VUS) and generalized Youden indices (GYIs) | |
| Houlden et al. | Does nature make us happier? A spatial error model of greenspace types and mental wellbeing | |
| Grassetti et al. | An extended regularized adjusted plus-minus analysis for lineup management in basketball using play-by-play data | |
| Willis et al. | Uncertainty in phylogenetic tree estimates | |
| Wang et al. | Predicting fatality rates due to earthquakes accounting for community vulnerability | |
| Fang et al. | Novel methods of estimating relative pollen productivity: A key parameter for reconstruction of past land cover from pollen records | |
| CN110019826A (en) | Construction method, construction device, equipment and the storage medium of medical knowledge map | |
| Sporer et al. | Meta-analysis | |
| Verburg et al. | Individual and clustered rankability of ICUs according to case-mix–adjusted mortality | |
| Asar et al. | Dynamic predictions of kidney graft survival in the presence of longitudinal outliers | |
| Sheanshang et al. | Outlier accommodation with semiparametric density processes: A study of Antarctic snow density modelling | |
| Bradley et al. | Heavy-tailed distributions for building stock data |
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 | ||
| PP01 | Preservation of patent right |
Effective date of registration: 20240202 Granted publication date: 20230228 |
|
| PP01 | Preservation of patent right |