CN109935287A - A kind of similarity analysis method, device and equipment of medical record information - Google Patents
A kind of similarity analysis method, device and equipment of medical record information Download PDFInfo
- Publication number
- CN109935287A CN109935287A CN201910151693.7A CN201910151693A CN109935287A CN 109935287 A CN109935287 A CN 109935287A CN 201910151693 A CN201910151693 A CN 201910151693A CN 109935287 A CN109935287 A CN 109935287A
- Authority
- CN
- China
- Prior art keywords
- medical record
- record information
- information
- similarity
- feature vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application discloses a kind of similarity analysis method, device and equipment of medical record information, which comprises is based on business diagnosis demand, obtains the medical record information for meeting the patient of the business diagnosis demand, the medical record information includes several attribute informations;Using variance analysis algorithm, the attribute information that dispersion in each medical record information is greater than preset first threshold value is rejected;Extract the corresponding feature vector of each medical record information;And calculate the similarity between the corresponding feature vector of each medical record information;The corresponding medical record information of feature vector that similarity is greater than default second threshold is determined as similar medical record information.The application can carry out similarity analysis to medical record information, find and handle to forge the illegal activities that medical record information extracts medical insurance fund using medical record templates in time, reduce the loss of medical insurance fund.
Description
Technical field
This application involves data processing fields, and in particular to a kind of similarity analysis method, apparatus of medical record information and sets
It is standby.
Background technique
Medical record information includes the letter in the entire medical procedure such as whole medications, the physician practice of patient during medical treatment
Breath extracts the illegal row of medical insurance fund currently, there are doctors, and medical record templates to be utilized to forge medical record information for the discovery of medical supervision department
To cause the heavy losses of medical insurance fund.
For this purpose, need at present one kind can find in time and handle it is above-mentioned using medical record templates forge medical record information extract doctor
The effective ways for protecting the illegal activities of fund, reduce the loss of medical insurance fund.
Summary of the invention
For this purpose, can believe case history this application provides a kind of similarity analysis method, device and equipment of medical record information
Breath carries out similarity analysis, finds and handle to forge the illegal row that medical record information extracts medical insurance fund using medical record templates in time
To reduce the loss of medical insurance fund.
In a first aspect, this application provides a kind of similarity analysis methods of medical record information, which comprises
Based on business diagnosis demand, the medical record information for meeting the patient of the business diagnosis demand, the case history letter are obtained
Breath includes several attribute informations;
Using variance analysis algorithm, the attribute information that dispersion in each medical record information is greater than preset first threshold value is rejected;
Extract the corresponding feature vector of each medical record information;And it calculates between the corresponding feature vector of each medical record information
Similarity;
The corresponding medical record information of feature vector that similarity is greater than default second threshold is determined as similar medical record information.
In a kind of optional embodiment, it is described extract the corresponding feature vector of each medical record information before, further includes:
According to the conversion table pre-established, the attribute information of the text formatting in the medical record information is converted into numerical value lattice
Formula;Wherein, the text formatting of the attribute information and the corresponding relationship of numeric format are stored in the conversion table.
In a kind of optional embodiment, the similarity calculated between the corresponding feature vector of each medical record information,
Include:
Using COS distance algorithm, the similarity between the corresponding feature vector of each medical record information is calculated.
In a kind of optional embodiment, the method also includes:
Based on the similar medical record information, determines and occur to forge the object that case history extracts medical insurance fund behavior;The object
Including hospital or doctor.
In a kind of optional embodiment, the method also includes:
It is for statistical analysis to the similar medical record information, determine the base therapy information of any disease, it is described to control substantially
Information is treated to be used to provide reference for the patient of the disease.
Second aspect, present invention also provides a kind of similarity analysis device of medical record information, described device includes:
Module is obtained, for being based on business diagnosis demand, obtains the case history letter for meeting the patient of the business diagnosis demand
Breath, the medical record information includes several attribute informations;
Module is rejected, for utilizing variance analysis algorithm, dispersion in each medical record information is rejected and is greater than default first threshold
The attribute information of value;
Extraction module, for extracting the corresponding feature vector of each medical record information;
Computing module, for calculating the similarity between the corresponding feature vector of each medical record information;
Determining module, the corresponding medical record information of feature vector for similarity to be greater than default second threshold are determined as phase
Like medical record information.
In a kind of optional embodiment, described device further include:
Conversion module, for according to the conversion table pre-established, the attribute of the text formatting in the medical record information to be believed
Breath is converted into numeric format;Wherein, the text formatting of the attribute information and pair of numeric format are stored in the conversion table
It should be related to.
In a kind of optional embodiment, the computing module is specifically used for:
Using COS distance algorithm, the similarity between the corresponding feature vector of each medical record information is calculated.
The third aspect, present invention also provides a kind of computer readable storage medium, the computer readable storage medium
In be stored with instruction, when described instruction is run on the terminal device so that the terminal device execute any of the above-described described in
Medical record information similarity analysis method.
Fourth aspect, present invention also provides a kind of medical insurance frauds to identify equipment characterized by comprising storage
Device, processor, and it is stored in the computer program that can be run on the memory and on the processor, the processor is held
When the row computer program, the similarity analysis method of medical record information described in any of the above embodiments is realized.
In the similarity analysis method of medical record information provided by the present application, firstly, being based on business diagnosis demand, obtains and meet
The medical record information of the patient of the business diagnosis demand, the medical record information include several attribute informations;Secondly, utilizing variance point
Algorithm is analysed, the attribute information that dispersion in each medical record information is greater than preset first threshold value is rejected;Then, each case history letter is extracted
Cease corresponding feature vector;And calculate the similarity between the corresponding feature vector of each medical record information;Finally, similarity is big
It is determined as similar medical record information in the corresponding medical record information of feature vector of default second threshold.The application can be to medical record information
Similarity analysis is carried out, finds and handle to forge the illegal activities that medical record information extracts medical insurance fund using medical record templates in time,
Reduce the loss of medical insurance fund.
Detailed description of the invention
In order to more clearly explain the technical solutions in the embodiments of the present application, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the drawings in the following description are only some examples of the present application, for
For those of ordinary skill in the art, without any creative labor, it can also be obtained according to these attached drawings
His attached drawing.
Fig. 1 is a kind of flow chart of the similarity analysis method of medical record information provided by the embodiments of the present application;
Fig. 2 is a kind of structural schematic diagram of the similarity analysis device of medical record information provided by the embodiments of the present application;
Fig. 3 is a kind of structural schematic diagram of the similarity analysis equipment of medical record information provided by the embodiments of the present application.
Specific embodiment
Medical record information is forged using medical record templates for doctor, extracts the illegal activities of medical insurance fund, this application provides
A kind of similarity analysis method of medical record information, is primarily based on business diagnosis demand, and acquisition meets the business diagnosis demand
The medical record information of patient, the medical record information include several attribute informations;Secondly, rejecting each disease using variance analysis algorithm
Go through the attribute information that dispersion in information is greater than preset first threshold value;Again, the corresponding feature vector of each medical record information is extracted;
And calculate the similarity between the corresponding feature vector of each medical record information;Finally, similarity is greater than default second threshold
The corresponding medical record information of feature vector is determined as similar medical record information.Since the quantity of similar medical record information is larger and it is same to be all from
One doctor or when hospital, same institute, it may be said that the bright doctor or the hospital, which exist, forges case history using medical record templates and believe
Breath, extracts the illegal activities of medical insurance fund, is based on this, and medical supervision department can carry out the doctor or the hospital further
Investigation, determines whether that there are above-mentioned illegal activities.As it can be seen that the similarity analysis method energy of medical record information provided by the present application
It is enough that above-mentioned illegal activities are identified in time, to be effectively treated to it, to avoid the loss of medical insurance fund.
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall in the protection scope of this application.
Embodiment of the method
It is a kind of flow chart of the similarity analysis method of medical record information provided by the embodiments of the present application, the party referring to Fig. 1
Method includes:
S101: being based on business diagnosis demand, obtains the medical record information for meeting the patient of the business diagnosis demand, the disease
Going through information includes several attribute informations.
The similarity analysis object of the embodiment of the present application is medical record information, so, the embodiment of the present application obtains patient first
Medical record information.Specifically, the medical record information of patient can be obtained by medical insurance interface.Business diagnosis demand may indicate that acquisition
Patient medical record information range, for example, business diagnosis demand is to carry out similarity analysis to the medical record information of a certain hospital,
The then medical record information of the patient of the available hospital.Medical record information includes several attribute informations, wherein attribute information one
As include patient age, unit joining insurance, hospital grade, Gender, Main Diagnosis, prescription number, expenses for medicine, plan as a whole reimbursement ratio,
Prescription number, drug expenditure, diagnosis and treatment item expense, service facility expense plan as a whole the amount of money, total cost etc..
S102: utilizing variance analysis algorithm, rejects the attribute that dispersion in each medical record information is greater than preset first threshold value
Information.
It in practical application, is analyzed from regulation of longitudinal angle, if any one of medical record information attribute information is believed with other case histories
The attribute information in breath is too high compared to dispersion, and the attribute information is not rejected, then it is opposite to will lead to this attribute information
It is little in influence of other attribute informations to feature vector, for this purpose, the embodiment of the present application need by each medical record information from
The attribute information that divergence is greater than preset first threshold value is rejected, and reduces shadow of this attribute information in feature vector to avoid it
It rings.
For example, being rejected in this medical record information if one dispersion of surgery cost in a medical record information is higher
Surgery cost;If dispersion of document number in a medical record information is higher, the list in this medical record information is rejected
According to number.
The embodiment of the present application utilizes variance analysis algorithm, rejects dispersion in each medical record information and is greater than preset first threshold value
Attribute information, and utilize other attribute informations remaining in each medical record information carry out medical record information similarity analysis.It is logical
Often, the attribute information of rejecting is generally surgery cost, mega project inspection fee, prescription ID, document number, serial number etc. of going to a doctor.
Specifically, existing variance analysis algorithm can be applied to the similarity analysis of medical record information provided by the present application
In method, specific implementation process of variance analysis algorithm is not repeated them here at this.
In addition, in order to improve the similarity calculation efficiency two-by-two of subsequent characteristics vector, the embodiment of the present application can be by case history
The attribute information of text formatting in information is converted to numeric format, specifically, can be stored with by what inquiry pre-established
The conversion table of the corresponding relationship of the text formatting and numeric format of attribute information, determines the attribute of the text formatting in medical record information
The corresponding numeric format of information.For example, disease type includes that Cervical Disk Herniation, diabetes and hypertension can respectively correspond
01,02 and 03, by the way that Cervical Disk Herniation, diabetes and hypertension are respectively converted into 01,02 and 03 in advance, improve subsequent spy
Levy the similarity calculation efficiency two-by-two of vector.
S103: the corresponding feature vector of each medical record information is extracted;And calculate the corresponding feature vector of each medical record information
Between similarity.
In the embodiment of the present application, since the data volume of the attribute information of text formatting in medical record information is usually larger, such as
Prescription in medical record information, the prescription in the medical record information of a patient generally include up to a hundred even thousands of prescriptions, and every
Bar prescription generally includes five or six texts, so the character quantity that the prescription information of a case history is related to can be close to up to ten thousand, such as
Whole prescription titles directly as a description dimension of the corresponding feature vector of medical record information, then may cause subsequent phase by fruit
Calculation amount like degree analysis is too big.For this purpose, the embodiment of the present application can be by prescription number, drug expenditure, diagnosis and treatment item expense, clothes
Business facility expense plans as a whole the amount of money, and the data volumes such as total cost are smaller and can characterize the attribute information of the certain feature of medical record information work
For the basis for extracting medical record information.
Specifically, above-mentioned attribute information can be carried out characterization by the embodiment of the present application, each medical record information is extracted
Corresponding feature vector.
In practical application, after extracting the corresponding feature vector of each medical record information, each medical record information pair is calculated
Similarity two-by-two between the feature vector answered.In order to improve the accuracy of similarity calculation, the embodiment of the present application utilizes cosine
Distance algorithm calculates the similarity between the corresponding feature vector of each medical record information.In general, if between two feature vectors
Angle it is essentially identical, it may be considered that the similarity between the two feature vectors is larger.Certainly, the embodiment of the present application may be used also
To utilize other similarity algorithms, such as sinusoidal distance algorithm, it is not limited here.
S104: the corresponding medical record information of feature vector that similarity is greater than default second threshold is determined as similar case history and is believed
Breath.
In the embodiment of the present application, second threshold is preset, wherein second threshold is used to control the mark of similar medical record information
It is quasi-.Second threshold is arranged bigger, it is determined that the similar medical record information gone out is more similar, based on the similar medical record information determined
Subsequent applications result is more accurate.
In a kind of application scenarios, it can use the similar medical record information that the embodiment of the present application is determined, carry out forgery case history
Extract the determination of the object of medical insurance fund behavior.Specifically, the business diagnosis demand in the embodiment of the present application can be for certain family
The similarity analysis demand of the medical record information of hospital, second threshold for example can be set to 100%, then are based on above-mentioned medical record information
The similar medical record information determined of similarity analysis method, can determine that the hospital occurs to forge case history and extract medical insurance fund row
For.For example, the quantity of similar medical record information reaches threshold value, it is determined that the hospital occurs forgery case history and extracts medical insurance fund behavior.
Based on this, medical supervision department can be effectively treated it, to avoid the further loss of medical insurance fund.
In another application scenarios, it can use the similar medical record information that the embodiment of the present application is determined, determine any disease
The base therapy information of disease, to provide reference for the patient of the disease.Specifically, since hospital grade is higher, for patient
For reference value it is bigger, so, business diagnosis demand in the embodiment of the present application can be the case information to Grade A hospital
Similarity analysis demand, then can be using the similar medical record information that the similarity analysis method of above-mentioned medical record information is determined
The case information of any disease can determine the disease by for statistical analysis to the corresponding similar medical record information of the disease
The base therapy information of disease.For example, expenditure pattern of the patient of the disease in future therapeutic lysis can be supplied to, locate
Square detail oneself reasonably plans, prevent excessive diagnosis and treatment, unreasonable charge shows so that treatment cycle of the patient to oneself has
As making the therapeutic process transparence of medical institutions.
In addition, for statistical analysis to the similar medical record information of a certain disease in above-mentioned application scenarios, additionally it is possible to count
Single diseases plan as a whole payment amount, and whether the distribution of the amount of money of most of case information needs medical insurance department to carry out political affairs
The adjustment of plan class properly increases Single diseases limit and then reduces the disease treatment difficulty of patient, or suitably reduces certain single diseases
Kind limit provides data support to reduce medical insurance fund loss etc..
In addition, for statistical analysis to the similar medical record information of a certain disease in above-mentioned application scenarios, additionally it is possible to build
The clinical path of day-mark standard provides support, helps the disease treatment plan for establishing standardization, standardization and sequencing, reduces patient
Because of the contradiction that medical staff's therapeutic process and method generate during in hospital, patient satisfaction is improved.
To sum up, in the similarity analysis method of medical record information provided by the embodiments of the present application, firstly, being needed based on business diagnosis
It asks, obtains the medical record information for meeting the patient of the business diagnosis demand, the medical record information includes several attribute informations;Its
It is secondary, using variance analysis algorithm, reject the attribute information that dispersion in each medical record information is greater than preset first threshold value;Then,
Extract the corresponding feature vector of each medical record information;And calculate the similarity between the corresponding feature vector of each medical record information;
Finally, the corresponding medical record information of feature vector that similarity is greater than default second threshold is determined as similar medical record information.This Shen
Please embodiment can to medical record information carry out similarity analysis, find in time and handle utilize medical record templates forge medical record information set
The illegal activities for taking medical insurance fund reduce the loss of medical insurance fund.
Installation practice
It referring to fig. 2, is a kind of structural schematic diagram of the similarity analysis device of medical record information provided in this embodiment, the dress
It sets and includes:
Module 201 is obtained, for being based on business diagnosis demand, obtains the case history for meeting the patient of the business diagnosis demand
Information, the medical record information include several attribute informations;
Module 202 is rejected, for utilizing variance analysis algorithm, dispersion in each medical record information is rejected and is greater than default first
The attribute information of threshold value;
Extraction module 203, for extracting the corresponding feature vector of each medical record information;
Computing module 204, for calculating the similarity between the corresponding feature vector of each medical record information;
Determining module 205, the corresponding medical record information of feature vector for similarity to be greater than to default second threshold determine
For similar medical record information.
In a kind of optional embodiment, described device further include:
Conversion module, for according to the conversion table pre-established, the attribute of the text formatting in the medical record information to be believed
Breath is converted into numeric format;Wherein, the text formatting of the attribute information and pair of numeric format are stored in the conversion table
It should be related to.
Specifically, the computing module, is specifically used for:
Using COS distance algorithm, the similarity between the corresponding feature vector of each medical record information is calculated.
In addition, described device can be also used for determining that occurring to forge case history extracts medical insurance based on the similar medical record information
The object of fund behavior;The object includes hospital or doctor.
In another application scenarios, described device can be also used for it is for statistical analysis to the similar medical record information, really
The base therapy information of fixed any disease, the base therapy information are used to provide reference for the patient of the disease.
In the similarity analysis device of medical record information provided by the embodiments of the present application, firstly, being based on business diagnosis demand, obtain
The medical record information for meeting the patient of the business diagnosis demand is taken, the medical record information includes several attribute informations;Secondly, utilizing
Variance analysis algorithm rejects the attribute information that dispersion in each medical record information is greater than preset first threshold value;Then, it extracts each
The corresponding feature vector of medical record information;And calculate the similarity between the corresponding feature vector of each medical record information;Finally, by phase
It is determined as similar medical record information like the corresponding medical record information of feature vector that degree is greater than default second threshold.The embodiment of the present application energy
It is enough that similarity analysis is carried out to medical record information, it finds and handles to extract medical insurance fund using medical record templates forgery medical record information in time
Illegal activities, reduce the loss of medical insurance fund.
Correspondingly, the embodiment of the present invention also provides a kind of similarity analysis equipment of medical record information, and it is shown in Figure 3, it can
To include:
Processor 301, memory 302, input unit 303 and output device 304.The similarity analysis equipment of medical record information
In the quantity of processor 301 can be one or more, taken a processor as an example in Fig. 3.In some embodiments of the present invention
In, processor 301, memory 302, input unit 303 and output device 304 can be connected by bus or other means, wherein
In Fig. 3 for being connected by bus.
Memory 302 can be used for storing software program and module, and processor 301 is stored in memory 302 by operation
Software program and module, at the various function application and data thereby executing the similarity analysis equipment of medical record information
Reason.Memory 302 can mainly include storing program area and storage data area, wherein storing program area can storage program area, extremely
Application program needed for a few function etc..In addition, memory 302 may include high-speed random access memory, can also wrap
Include nonvolatile memory, a for example, at least disk memory, flush memory device or other volatile solid-state parts.
Input unit 303 can be used for receiving the number or character information of input, and generate the similarity analysis equipment with medical record information
User setting and function control related signal input.
Specifically in the present embodiment, processor 301 can be according to following instruction, by one or more application program
The corresponding executable file of process be loaded into memory 302, and run by processor 301 storage in the memory 302
Application program, to realize the various functions in the similarity analysis method of above-mentioned medical record information.
In addition, the embodiment of the present application also provides a kind of computer readable storage medium, the computer-readable storage medium
Instruction is stored in matter, when described instruction is run on the terminal device, so that the terminal device executes any of the above-described institute
The similarity analysis method for the medical record information stated.
For device embodiment, since it corresponds essentially to embodiment of the method, so related place is referring to method reality
Apply the part explanation of example.The apparatus embodiments described above are merely exemplary, wherein described be used as separation unit
The unit of explanation may or may not be physically separated, and component shown as a unit can be or can also be with
It is not physical unit, it can it is in one place, or may be distributed over multiple network units.It can be according to actual
It needs that some or all of the modules therein is selected to achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not
In the case where making the creative labor, it can understand and implement.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
A kind of similarity analysis method, device and equipment of medical record information provided by the embodiment of the present application is carried out above
It is discussed in detail, specific examples are used herein to illustrate the principle and implementation manner of the present application, above embodiments
Explanation be merely used to help understand the present processes and its core concept;At the same time, for those skilled in the art,
According to the thought of the application, there will be changes in the specific implementation manner and application range, in conclusion in this specification
Hold the limitation that should not be construed as to the application.
Claims (10)
1. a kind of similarity analysis method of medical record information, which is characterized in that the described method includes:
Based on business diagnosis demand, the medical record information for meeting the patient of the business diagnosis demand, the medical record information packet are obtained
Include several attribute informations;
Using variance analysis algorithm, the attribute information that dispersion in each medical record information is greater than preset first threshold value is rejected;
Extract the corresponding feature vector of each medical record information;And it calculates similar between the corresponding feature vector of each medical record information
Degree;
The corresponding medical record information of feature vector that similarity is greater than default second threshold is determined as similar medical record information.
2. the method according to claim 1, wherein it is described extract the corresponding feature vector of each medical record information it
Before, further includes:
According to the conversion table pre-established, the attribute information of the text formatting in the medical record information is converted into numeric format;
Wherein, the text formatting of the attribute information and the corresponding relationship of numeric format are stored in the conversion table.
3. the method according to claim 1, wherein it is described calculate the corresponding feature vector of each medical record information it
Between similarity, comprising:
Using COS distance algorithm, the similarity between the corresponding feature vector of each medical record information is calculated.
4. method according to claim 1-3, which is characterized in that the method also includes:
Based on the similar medical record information, determines and occur to forge the object that case history extracts medical insurance fund behavior;The object includes
Hospital or doctor.
5. method according to claim 1-3, which is characterized in that the method also includes:
It is for statistical analysis to the similar medical record information, determine the base therapy information of any disease, the base therapy letter
Breath is for providing reference for the patient of the disease.
6. a kind of similarity analysis device of medical record information, which is characterized in that described device includes:
Module is obtained, for being based on business diagnosis demand, obtains the medical record information for meeting the patient of the business diagnosis demand, institute
Stating medical record information includes several attribute informations;
Module is rejected, for utilizing variance analysis algorithm, dispersion in each medical record information is rejected and is greater than preset first threshold value
Attribute information;
Extraction module, for extracting the corresponding feature vector of each medical record information;
Computing module, for calculating the similarity between the corresponding feature vector of each medical record information;
Determining module, the corresponding medical record information of feature vector for similarity to be greater than default second threshold are determined as similar disease
Go through information.
7. device according to claim 6, which is characterized in that described device further include:
Conversion module, for according to the conversion table pre-established, the attribute information of the text formatting in the medical record information to be turned
Change numeric format into;Wherein, the text formatting pass corresponding with numeric format of the attribute information is stored in the conversion table
System.
8. device according to claim 6, which is characterized in that the computing module is specifically used for:
Using COS distance algorithm, the similarity between the corresponding feature vector of each medical record information is calculated.
9. a kind of computer readable storage medium, which is characterized in that instruction is stored in the computer readable storage medium, when
When described instruction is run on the terminal device, so that the terminal device executes case history as described in any one in claim 1-5
The similarity analysis method of information.
10. a kind of medical insurance fraud identifies equipment characterized by comprising memory, processor, and it is stored in described deposit
On reservoir and the computer program that can run on the processor, when the processor executes the computer program, realize
The similarity analysis method of medical record information as described in any one in claim 1-5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910151693.7A CN109935287A (en) | 2019-02-28 | 2019-02-28 | A kind of similarity analysis method, device and equipment of medical record information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910151693.7A CN109935287A (en) | 2019-02-28 | 2019-02-28 | A kind of similarity analysis method, device and equipment of medical record information |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109935287A true CN109935287A (en) | 2019-06-25 |
Family
ID=66986193
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910151693.7A Pending CN109935287A (en) | 2019-02-28 | 2019-02-28 | A kind of similarity analysis method, device and equipment of medical record information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109935287A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110517785A (en) * | 2019-08-28 | 2019-11-29 | 北京百度网讯科技有限公司 | Lookup method, device and the equipment of similar case |
CN112016302A (en) * | 2020-08-03 | 2020-12-01 | 青岛国新健康产业科技有限公司 | Recognition method and device for decomposing hospitalization behaviors, electronic equipment and storage medium |
CN117542535A (en) * | 2024-01-10 | 2024-02-09 | 电子科技大学 | Clinical path correction method and device |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102255922A (en) * | 2011-08-24 | 2011-11-23 | 山东师范大学 | Intelligent multilevel junk email filtering method |
-
2019
- 2019-02-28 CN CN201910151693.7A patent/CN109935287A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102255922A (en) * | 2011-08-24 | 2011-11-23 | 山东师范大学 | Intelligent multilevel junk email filtering method |
Non-Patent Citations (2)
Title |
---|
卞德忠: ""基于关键字自动提取的口述病历识别***设计与实现"", 《万方》 * |
杨凯艳: ""基于改进的TFIDF关键词自动提取算法研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110517785A (en) * | 2019-08-28 | 2019-11-29 | 北京百度网讯科技有限公司 | Lookup method, device and the equipment of similar case |
CN112016302A (en) * | 2020-08-03 | 2020-12-01 | 青岛国新健康产业科技有限公司 | Recognition method and device for decomposing hospitalization behaviors, electronic equipment and storage medium |
CN112016302B (en) * | 2020-08-03 | 2024-04-30 | 青岛国新健康产业科技有限公司 | Identification method and device for decomposing hospitalization behaviors, electronic equipment and storage medium |
CN117542535A (en) * | 2024-01-10 | 2024-02-09 | 电子科技大学 | Clinical path correction method and device |
CN117542535B (en) * | 2024-01-10 | 2024-03-22 | 电子科技大学 | Clinical path correction method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110880361B (en) | Personalized accurate medication recommendation method and device | |
CN109543863A (en) | A kind of medical treatment task management method, server and storage medium | |
WO2020082793A1 (en) | Drug transaction processing method, server and storage medium | |
CN112700838A (en) | Big data-based medication scheme recommendation method and device and related equipment | |
CN109935287A (en) | A kind of similarity analysis method, device and equipment of medical record information | |
CN109524083A (en) | Based on the rational method of medical big data monitoring adjuvant drug and Related product | |
CN111180024A (en) | Data processing method and device based on word frequency and inverse document frequency and computer equipment | |
CN109785919B (en) | Noun matching method, noun matching device, noun matching equipment and computer readable storage medium | |
CN112216361A (en) | Follow-up plan list generation method, device, terminal and medium based on artificial intelligence | |
CN111582699A (en) | Medical resource scheduling platform | |
CN109671476A (en) | Recognition methods, device, terminal and the computer readable storage medium of unrelated medication | |
CN112365941A (en) | Method and system for recruitment of subjects | |
CN110570916A (en) | diagnosis assistance method, system, device and storage medium | |
CN107463773A (en) | Method of getting it filled, system and the storage medium of identity-based identification | |
CN110752027B (en) | Electronic medical record data pushing method, device, computer equipment and storage medium | |
CA3088562A1 (en) | Restricted-access and/or data chip device for healthcare | |
Chen et al. | An approach for transgender population information extraction and summarization from clinical trial text | |
WO2020082804A1 (en) | Medical data classified storage method and apparatus | |
WO2020087971A1 (en) | Prediction model-based hospitalization rationality prediction method and related products | |
CN109522331B (en) | Individual-centered regionalized multi-dimensional health data processing method and medium | |
CN104699968A (en) | Intelligent medical guide system and method | |
CN110675270A (en) | Method and device for determining medical insurance deduction amount based on invoice information | |
CN115831298A (en) | Clinical trial patient recruitment method and device based on hospital management information system | |
CN112116976A (en) | Method and device for processing medicine information and computer readable storage medium | |
CN109830273A (en) | Electronic prescription generation method, device, computer equipment and readable storage medium storing program for executing |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190625 |
|
RJ01 | Rejection of invention patent application after publication |