CN109711402A - A kind of medical document recognition methods and computer readable storage medium - Google Patents
A kind of medical document recognition methods and computer readable storage medium Download PDFInfo
- Publication number
- CN109711402A CN109711402A CN201811534174.0A CN201811534174A CN109711402A CN 109711402 A CN109711402 A CN 109711402A CN 201811534174 A CN201811534174 A CN 201811534174A CN 109711402 A CN109711402 A CN 109711402A
- Authority
- CN
- China
- Prior art keywords
- information
- reimbursement
- medical document
- medical
- insurance
- 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
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The present invention provides a kind of recognition methods of medical document, the following steps are included: according to trained in advance region recognition model and character recognition model, obtain the identification information and cost information on the medical document, it is connected to corresponding information database, and reimbursement reference information corresponding with the medical document is obtained from the information database, obtain the reimbursement information of the medical document.A kind of medical document recognition methods provided by the invention, not only available medical insurance reimbursement information and/or business insurance submit an expense account information, further, can also obtain the prompt for needing reimbursement material to be offered and submitting an expense account mode；Further, know medicine information and taking prompt, it is user-friendly.Meanwhile for submitting an expense account mechanism, automatic identification classification and the amount of money realize automatic calculating reimbursed sum and beat money automatically, saves manpower and audit cost.
Description
Technical field
The invention belongs to form recognition technical field more particularly to a kind of medical document recognition methods and computer-readable
Storage medium.
Background technique
In the prior art, the medical documents such as hospital or pharmacy output invoice or disbursement and sattlement inventory, some do not have medical insurance
Submit an expense account information；Some medical insurances reimbursement information is not intuitive specific enough, and especially cities and towns and Rural medical treatment insurance reimbursement ratio are different, outpatient service
Reimbursement is different with being hospitalized, and the medical reimbursement in strange land is also more complicated, and ordinary user faces these medical documents, is difficult to differentiate tool
The reimbursement content and reimbursement ratio of body.
Meanwhile with the raising of people's insurance awareness, people can voluntarily purchase or purchase additional business by company and protect
Danger, this kind of business insurance is many kinds of, has medical insurance, serious illness insurance, accident insurance, amount of money difference may have different limitations, there are also in
Ground insurance, Hong Kong insurance, international insurance, some users have more parts of different business insurances, which can be submitted an expense account, which can be with
Superposition all has different clauses, and reimbursement ratio and range are different, and on the medical document of the prior art, usually not
Business insurance submits an expense account information, faces medical document, and ordinary user can not differentiate business insurance and specifically submit an expense account content and reimbursement
Ratio.
Further, due to being difficult to differentiate specific insurance reimbursement information, ordinary user needs material to be offered for reimbursement
Material and/or reimbursement mode are difficult to hold, when leading to the reimbursement for being easy to omit some insurance, or even forgetting to submit and miss reimbursement
Machine influences later period reimbursement processing, brings unnecessary economic loss to user.
Summary of the invention
The present invention to solve the above problems existing in the prior art, provides a kind of medical document recognition methods.
To achieve the above object, the present invention is achieved by the following technical programs: a kind of medical document recognition methods,
The following steps are included:
S1: according to region recognition model trained in advance, the first area and the secondth area on the medical document are identified
Domain；
S2: according to character recognition model trained in advance, the corresponding first information in the first area and described the are obtained
Corresponding second information in two regions；
S3: the corresponding information database of the first information is connected according to the first information, and according to second letter
Breath obtains reference information from the information database；
S4: according to second information and the reference information, the identification information of the medical document is obtained；
Wherein, the first information includes the identification information on the medical document；
Second information includes the cost information on the medical document；
The reference information includes reimbursement reference information corresponding with the medical document；
The identification information includes the corresponding reimbursement information of the medical document.
Preferably, in step S1, the region recognition model is obtained by following process: to the first medical document image
Each of sample set medical document image sample is labeled processing, to mark out each medical document image
Each region in several regions in sample；
And using through it is described mark processing the first medical document image sample set, to first nerves network into
Row training, to obtain the region recognition model.
Preferably, in step S2, the character recognition model is obtained by following process: to the second medical document image
Each of sample set medical document image sample is labeled processing, to mark out each medical document image
The character in each region in several regions in sample；
And using through it is described mark processing the second medical document image sample set, to nervus opticus network into
Row training, to obtain the character recognition model.
Preferably, further comprising the steps of before step S1: according to classification identification model trained in advance, to identify institute
The classification for stating medical document determines corresponding region recognition model according to the classification.
Preferably, the first information includes the side's of making out an invoice title and user's name；Second information includes expense name
Title, quantity, the individual event amount of money, total amount and date.
Preferably, information database described in the step S3 at least one, the reference information includes from least one
The reimbursement ratio and/or reimbursement range obtained in a information database；
Identification information described in step S4 includes the practical reimbursement ratio of the corresponding insurance of the medical document, practical reimbursement
Classification and/or practical reimbursement information.
Preferably, information database described in step S3 includes medical insurance database, obtains and uses from the medical insurance database
Family regional information and medical insurance information, to obtain the reference information, the reference information includes from the medical insurance data
The medical insurance reimbursement ratio and/or medical insurance reimbursement range obtained in library；
Identification information described in step S4 includes the medical document corresponding practical medical insurance reimbursement ratio, practical medical insurance
Reimbursement classification and/or the practical medical insurance drug reimbursement information.
Preferably, information database described in step S3 includes business insurance database, from the business insurance database
Middle acquisition user business insurance information, to obtain the reference information, the reference information includes from the business insurance number
According to the business insurance reimbursement ratio and/or business insurance reimbursement range obtained in library；
Identification information described in step S4 includes the medical document corresponding practical commercial insurance reimbursement ratio, practical quotient
Industry insurance reimbursement classification and/or practical commercial insurance reimbursement information.
Preferably, identification information described in step S4 further includes insuring the material of remaining reimbursement amount, insurance reimbursement needs
And/or reimbursement mode.
The present invention also provides a kind of computer readable storage medium, it is stored on the computer readable storage medium
The executable instruction of computer realizes doctor as described in any one of the above embodiments when the instruction that the computer can be performed is performed
Treat form recognition method.
The beneficial effects of the present invention are: a kind of medical document recognition methods provided by the present invention can directly pass through bat
Take the photograph invoice or document, obtain medical insurance reimbursement information and/or business insurance submits an expense account information, further, obtain reimbursement material and
The prompt of reimbursement mode；Further, know medicine information and taking prompt, it is user-friendly.Meanwhile for submitting an expense account machine
For structure, automatic identification classification and the amount of money realize automatic calculating reimbursed sum and beat money automatically, saves manpower and audit cost.
Detailed description of the invention
Fig. 1 is a kind of medical document recognition methods flow chart of the embodiment of the present invention；
Fig. 2 is a kind of medical document recognition methods flow chart of the embodiment of the present invention one；
Fig. 3 is a kind of medical document recognition methods flow chart of the embodiment of the present invention two.
Specific embodiment
Core of the invention thought is to provide a kind of medical document recognition methods, obtains medical insurance reimbursement information and/or business
Insurance reimbursement information further obtains reimbursement material and submits an expense account the prompt of mode；Further, know medicine information kimonos
It is user-friendly with prompt.
To realize above-mentioned thought, the present invention provides a kind of medical document recognition methods, comprising the following steps:
S1: according to region recognition model trained in advance, the first area and the secondth area on the medical document are identified
Domain；
S2: according to character recognition model trained in advance, the corresponding first information in the first area and described the are obtained
Corresponding second information in two regions；
S3: the corresponding information database of the first information is connected according to the first information, and according to second letter
Breath obtains reference information from the information database；
S4: according to second information and the reference information, the identification information of the medical document is obtained；
Wherein, the first information includes the identification information on the medical document；
Second information includes the cost information on the medical document；
The reference information includes reimbursement reference information corresponding with the medical document；
The identification information includes the corresponding reimbursement information of the medical document.
To keep the purpose of the present invention, advantages and features clearer, below in conjunction with attached drawing 1-3 to proposed by the present invention one
Kind medical document recognition methods is described in further detail.It should be noted that attached drawing is all made of very simplified form and makes
With non-accurate ratio, only for the purpose of facilitating and clarifying the purpose of the embodiments of the invention.
Firstly, it is necessary to explanation, the so-called medical document of the present invention refers to the entity for recording information on it, this
A little information are arranged on the medical document with determining mode, and by one in middle text, outer text, number, symbol etc.
Kind or diversified forms express.Some specific examples of the medical document include the expense invoices of hospital or pharmacy, receive
According to all kinds of medical documents filled in by artificial and/or machine such as, receipt or disbursement and sattlement inventories.Those skilled in the art can be with
Understand, the so-called medical document of the present invention is not limited to these specific examples listed above, is also not necessarily limited to thereon with public affairs
The medical document of chapter can be the medical document with type fount and be also possible to the medical document with hand-written script, can be with
It is that the medical document with regulation and/or general format may not be the medical document with regulation and/or general format.
As shown in Fig. 1, it is a kind of medical document recognition methods flow chart of the embodiment of the present invention, includes the following steps:
S1: according to region recognition model trained in advance, the first area and the secondth area on the medical document are identified
Domain；
The region recognition model is obtained by following process: to each institute in the first medical document image sample set
It states medical document image sample and is labeled processing, to mark out several areas in each medical document image sample
Each region in domain；
And using through it is described mark processing the first medical document image sample set, to first nerves network into
Row training, to obtain the region recognition model.
The first medical document image sample refers to the same category of medical document presented with visual means, example
Picture, the video of such as medical document；For example the medical document is the statement of expense.
S2: according to character recognition model trained in advance, the corresponding first information in the first area and described the are obtained
Corresponding second information in two regions；Wherein, the first information includes the identification information on the medical document；Described second
Information includes the cost information on the medical document.
The first information includes the side's of making out an invoice title and user's name in embodiments of the present invention；Second letter
Breath includes expense title, quantity, the individual event amount of money, total amount and date.
The character recognition model is obtained by following process: to each institute in the second medical document image sample set
It states medical document image sample and is labeled processing, to mark out several areas in each medical document image sample
The character in each region in domain；It is right and using the second medical document image sample set through the mark processing
Nervus opticus network is trained, to obtain the character recognition model.
S3: the corresponding information database of the first information is connected according to the first information, and according to second letter
Breath obtains reference information from the information database；
The information database at least one, the reference information includes from information database described at least one
The reimbursement ratio and/or reimbursement range of acquisition；In a specific embodiment of the invention, described information storehouse includes but is not limited to
Medicare data library, business insurance database, medicine information database and/or treatment information database.
The reference information includes reimbursement reference information corresponding with the medical document.
S4: according to second information and the reference information, the identification information of the medical document is obtained；
The identification information include the practical reimbursement ratio of the medical document corresponding insurance, practical reimbursement classify and/or
Practical reimbursement information.
It is further comprising the steps of before step S1 in another embodiment of the invention: according to class trained in advance
Other identification model, identifies the classification of the medical document, determines corresponding region recognition model according to the classification.
The classification identification model is obtained by following process: to each doctor in third medical document image sample set
It treats document image sample and is labeled processing, to mark out the classification of each medical document image sample；
And using through it is described mark processing the third medical document image sample set, to third nerve network into
Row training, to obtain the classification identification model.
It is further to a kind of medical document recognition methods work proposed by the present invention below in conjunction with more specifical embodiment
It is described in detail.
<embodiment one>
A kind of recognition methods of medical document of the present embodiment is for obtaining user's actual medical insurance reimbursement information, such as
It is a kind of flow chart of medical document recognition methods of the embodiment of the present invention shown in attached drawing 2, comprising the following steps:
Step 1: identifying name identification region and expense region on the medical document
In the present embodiment, first area of the present invention includes name identification region, and the second area includes expense
Region.
Step 2: obtain the side's of making out an invoice title and user's name and expense title, quantity, the individual event amount of money, total amount and
Date.
The first information includes the side's of making out an invoice title and user's name；Second information include expense title, quantity,
The individual event amount of money, total amount and date.
Since reimbursement is related to remaining amount problem, prevent from others' expense document misrecognition to be included in reimbursement, identification is made out an invoice
Square title and user's name；
Identify the expense title, e.g. registration fee, treatment cost, survey fees, Laboratory Fee, bed takes, cost of hospitalization, shield
Reason is taken, Operation Fee, and fee of material or drug expenditure, these expenses have different titles, if submitting an expense account type if there is medical insurance
Also it is identified, such as medical insurance Class A, Class B, Class C etc., identifies quantity and Fee Amount, total amount is identified, to calculate reality
Border reimbursed sum；Identification Date is used to determine whether in allowable range.
Step 3: be connected to medical insurance database according to user information, obtained from medical insurance database user's regional information and
Medical insurance information obtains medical insurance reimbursement ratio and/or medical insurance reimbursement range
It obtains user's regional information and social security information, the medical insurance information refers to the insured type of user, mesh
The preceding insured type of medical insurance contains new rural village cooperative medical service, town dweller's medical insurance, Medical Insurance, at one's own expense etc.
Situation.Its reimbursement ratio of different insured types and range are different, the reimbursement ratio and drug reimbursement range of different regions
May be inconsistent, user can be allowed to select regional information such as province, city and region's information, while user being allowed to select cities and towns or Rural medical treatment insurance
Information, obtains specific reimbursement ratio directly from medical insurance database and range is submitted an expense account in medical insurance.
Step 4: according to expense title, quantity, the individual event amount of money, total amount and date and medical insurance reimbursement ratio and medical insurance
Range is submitted an expense account, practical medical insurance reimbursement ratio, practical medical insurance reimbursement classification and/or practical medical insurance drug reimbursement information are obtained
Ratio and/or medical insurance reimbursement range computation medical insurance reimbursement classification and the amount of money, such as individual event are submitted an expense account according to the medical insurance
Submit an expense account respectively how much, reimbursement total value is how much, calculates remaining medical insurance and submits an expense account amount.
Needing user for strange land medical insurance reimbursement, offer bill and testimonial material go the case where submitting an expense account afterwards at one's own expense, at other
Embodiment in, the identification information further include medical insurance reimbursement need material and/or reimbursement mode.Exempt from well
In addition to ordinary user may lack strange land medical insurance reimbursement material and/or submit an expense account the unclear puzzlement of mode.
<embodiment two>
A kind of recognition methods of medical document provided by the present embodiment is for obtaining user's practical commercial insurance reimbursement letter
Breath is as shown in Fig. 3 a kind of flow chart of medical document recognition methods of the embodiment of the present invention, comprising the following steps:
Step 1: identifying name identification region and expense region on the medical document
In the present embodiment, first area of the present invention includes name identification region, and the second area includes expense
Region.
Step 2: obtaining the side's of making out an invoice title and user's name；And expense title, quantity, the individual event amount of money, total amount and
Date.
According to the character recognition model, the side's of making out an invoice title is obtained from the medical document, the side of making out an invoice is entitled
The hospital or pharmacy that user goes to a doctor；
The first information includes the side's of making out an invoice title and user's name；Second information include expense title, quantity,
The individual event amount of money, total amount and date.
Since reimbursement is related to remaining amount problem, prevent from others' expense document misrecognition to be included in reimbursement, identification is made out an invoice
Square title and user's name；
Identify the expense title, e.g. registration fee, treatment cost, survey fees, Laboratory Fee, bed takes, cost of hospitalization, shield
Reason is taken, Operation Fee, and fee of material or drug expenditure, these expenses have different titles, if there is reimbursement type if also into
Row identification, identifies quantity and Fee Amount, total amount is identified, to calculate practical reimbursed sum；Identification Date, for determining
Whether in allowable range.
Step 3: being connected to business insurance database according to user information, business is obtained from business insurance database and is protected
Danger reimbursement ratio and/or business insurance submit an expense account range
The business insurance type that different users insures is different, the different kind of insurances and different insured amounts pair
The reimbursement range answered, reimbursement ratio and reimbursement amount are different, therefore, need in advance user fill in business insurance title and
Insured amount information is connected to the business insurance database that user insures according to user information, obtains user's business insurance letter
Breath, to obtain user's business insurance reimbursement ratio and drug reimbursement range information.
Step 4: according to expense title, quantity, the individual event amount of money, total amount and date and business insurance reimbursement ratio and
Business insurance submits an expense account range, obtains practical commercial insurance reimbursement ratio, practical commercial insurance reimbursement classification and/or practical commercial
Insure drug reimbursement information.
Disclosure recited above through this embodiment, business insurance reimbursement mechanism can insure information and user according to user
The title of the bills such as the medical invoice of upload, recognition time, place, hospital or pharmacy, article or service can be submitted an expense account
Part and the amount of money, according to reimbursement type (imported medicine, Domestic Drugs) and drug (the first and second the third) or service (various treatments inspections
Test and check inpatient etc.) type, and reimbursement ratio makes by oneself to obtain reimbursed sum, obtain user account and beat automatically money or
Money reimbursement is played by audit.It is the validity and consistency that bill is determined according to official seal while identification, wherein described one
Cause property includes but is not limited to consistent with the side's of making out an invoice title by identification official seal title.It is thereby achieved that automatic identification classification
And the amount of money, it is automatic to calculate reimbursed sum and beat money automatically, it saves manpower and audits cost.
Further, in other implementations, the identification information further include business insurance residue reimbursement amount,
The material and/or reimbursement mode that business insurance reimbursement needs.By shooting invoice or document, ordinary user obtains business and protects
Danger reimbursement information, obtains reimbursement material and mode prompts, know medicine information and taking prompt, user-friendly, so that general
It is very clear that general family submits an expense account to medical treatment, knows what's what.
Further, it is thus evident that in real life, the both insured medical insurance of some users or insured business are protected
Danger, therefore, in other implementations, those skilled in the art, according to above-mentioned revealed content, without
It is available while obtaining actual medical insurance and practical commercial insures the skill submitted an expense account in the case where crossing creative work
Art scheme, it is within the scope of the present invention.
<embodiment three>
In the present embodiment, the first information of the present invention is medicine information, and step S3 further includes being believed according to the drug
Breath, connects the corresponding medicine information database of the medicine information, and according to the medicine information from the medicine information data
Library obtains drug identification information.The drug identification information include the manufacturer of the drug, classification, description and/
Or taking prompt, the taking prompt include Time of Administration, dosage and dieting.
Further, in the present embodiment, the information database includes treatment information database, the reference information
It further include that the user obtained from the treatment information database treats information, the treatment information includes the property of the user
Not, age and weight personal information and previously inspection, diagnosis, treatment, medication and nursing situation history information；And combine institute
It states user and treats information and the drug identification information and provide nursing points for attention, the nursing points for attention include but unlimited
In the interval of administration time, dosage and dietary recommendation.
The present invention still further provides a kind of computer readable storage medium, on the computer readable storage medium
It is stored with the executable instruction of computer, realizes doctor as described above when the instruction that the computer can be performed is performed
The step for the treatment of form recognition method, specific step has been described in detail above, and details are not described herein again.
By the description of embodiment of above, those skilled in the art can be understood that above embodiment
It can realize by means of software and necessary general hardware platform, naturally it is also possible to by hardware realization, but many situations
Under, the former is more preferably embodiment.Based on this understanding, technical solution of the present invention contributes to the prior art
Part can be expressed in the form of software products.The computer software product is stored on computer readable storage medium, packet
It includes some instructions to use so that equipment executes method described in each embodiment of the present invention, the equipment includes but unlimited
In server, the network terminal, computer and/or mobile phone.
In addition, term " first ", " second " are used for description purposes only, it is not understood to indicate or imply relatively important
Property or implicitly indicate the quantity of indicated technical characteristic." first " is defined as a result, the feature of " second " can be expressed
Or implicitly include at least one this feature.In the description of the present invention, the meaning of " plurality " is at least two, such as two
It is a, three etc., unless otherwise specifically defined.
It should be noted that in the description of this specification, reference term " one embodiment ", " some embodiments ",
The description of " example ", " specific example " or " some examples " etc. mean specific features described in conjunction with this embodiment or example,
Structure, material or feature are included at least one embodiment or example of the invention.In the present specification, to above-mentioned art
The schematic representation of language is necessarily directed to identical embodiment or example.Moreover, the specific features of description, structure, material
Material or feature may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, not conflicting
In the case where, those skilled in the art can be by different embodiments or examples described in this specification and different implementations
Example or exemplary feature are combined.
To sum up, a kind of various configuration of medical document recognition methods is described in detail in above-described embodiment, certainly,
Foregoing description is only the description to present pre-ferred embodiments, not to any restriction of the scope of the invention, the present invention include but
It is not limited to configuration cited in above-mentioned implementation, it is anti-that those skilled in the art can lift one according to the content of above-described embodiment
Three, any change, the modification that the those of ordinary skill in field of the present invention does according to the disclosure above content belong to claim
The protection scope of book.
Claims (10)
1. a kind of medical document recognition methods, which comprises the following steps:
S1: according to region recognition model trained in advance, the first area on the medical document and second area are identified；
S2: according to character recognition model trained in advance, the corresponding first information in the first area and secondth area are obtained
Corresponding second information in domain；
S3: connecting the corresponding information database of the first information according to the first information, and according to second information from
The information database obtains reference information；
S4: according to second information and the reference information, the identification information of the medical document is obtained；
Wherein, the first information includes the identification information on the medical document；
Second information includes the cost information on the medical document；
The reference information includes reimbursement reference information corresponding with the medical document；
The identification information includes the corresponding reimbursement information of the medical document.
2. a kind of medical document recognition methods according to claim 1, which is characterized in that in step S1, the region is known
Other model is obtained by following process: to each of the first medical document image sample set medical document image sample into
Rower note processing, to mark out each region in several regions in each medical document image sample；
And using the first medical document image sample set through the mark processing, first nerves network is instructed
Practice, to obtain the region recognition model.
3. a kind of medical document recognition methods according to claim 1, which is characterized in that in step S2, the character is known
Other model is obtained by following process: to each of the second medical document image sample set medical document image sample into
Rower note processing, to mark out the word in each region in several regions in each medical document image sample
Symbol；
And using the second medical document image sample set through the mark processing, nervus opticus network is instructed
Practice, to obtain the character recognition model.
4. a kind of medical document recognition methods according to claim 1, which is characterized in that before step S1 further include with
Lower step: according to classification identification model trained in advance, identifying the classification of the medical document, is determined and is corresponded to according to the classification
Region recognition model.
5. a kind of medical document recognition methods according to claim 1, which is characterized in that the first information includes making out an invoice
Square title and user's name；Second information includes expense title, quantity, the individual event amount of money, total amount and date.
6. a kind of medical document recognition methods according to claim 5, which is characterized in that information described in the step S3
Database at least one, the reference information include the reimbursement ratio that is obtained from information database described at least one and/
Or reimbursement range；
Identification information described in step S4 includes the practical reimbursement ratio of the corresponding insurance of the medical document, practical reimbursement classification
And/or practical reimbursement information.
7. a kind of medical document recognition methods according to claim 6, which is characterized in that information data described in step S3
Library includes medical insurance database, user's regional information and medical insurance information is obtained from the medical insurance database, to obtain institute
Reference information is stated, the reference information includes the medical insurance reimbursement ratio and/or medical insurance reimbursement obtained from the medical insurance database
Range；
Identification information described in step S4 includes the corresponding practical medical insurance reimbursement ratio of the medical document, practical medical insurance reimbursement point
Class and/or the practical medical insurance drug reimbursement information.
8. a kind of medical document recognition methods according to claim 6, which is characterized in that information data described in step S3
Library includes business insurance database, and user's business insurance information is obtained from the business insurance database, to obtain described
Reference information, the reference information include the business insurance reimbursement ratio obtained from the business insurance database and/or quotient
Industry insurance reimbursement range；
Identification information described in step S4 includes the corresponding practical commercial insurance reimbursement ratio of the medical document, practical commercial insurance
Reimbursement classification and/or practical commercial insurance reimbursement information.
9. a kind of medical document recognition methods according to claim 6, which is characterized in that identification information described in step S4 is also
The material and/or reimbursement mode needed including the remaining reimbursement amount of insurance, insurance reimbursement.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Executable instruction, when the instruction that the computer can be performed is performed realization such as the described in any item doctors of claim 1-9
Treat form recognition method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811534174.0A CN109711402B (en) | 2018-12-14 | 2018-12-14 | Medical document identification method and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811534174.0A CN109711402B (en) | 2018-12-14 | 2018-12-14 | Medical document identification method and computer-readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109711402A true CN109711402A (en) | 2019-05-03 |
| CN109711402B CN109711402B (en) | 2021-06-04 |
Family
ID=66256382
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811534174.0A Active CN109711402B (en) | 2018-12-14 | 2018-12-14 | Medical document identification method and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109711402B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110675270A (en) * | 2019-09-05 | 2020-01-10 | 平安健康保险股份有限公司 | Method and device for determining medical insurance deduction amount based on invoice information |
| CN111489487A (en) * | 2019-05-09 | 2020-08-04 | 杭州睿琪软件有限公司 | Bill identification method, device, equipment and storage medium |
| CN112348017A (en) * | 2020-11-09 | 2021-02-09 | 浙江太美医疗科技股份有限公司 | Identification method and identification device for clinical test charging document |
| CN112634065A (en) * | 2020-12-21 | 2021-04-09 | 山东众阳健康科技集团有限公司 | Method and system for reimbursing remote medical care receipt |
| CN113658671A (en) * | 2021-08-19 | 2021-11-16 | 湖南和信安华区块链科技有限公司 | Medical and health mutual-aid system based on block chain |
| CN114723420A (en) * | 2022-06-07 | 2022-07-08 | 武汉金豆医疗数据科技有限公司 | Medical insurance, business and insurance integrated auditing method and device, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003186990A (en) * | 2001-12-19 | 2003-07-04 | Sanyo Electric Co Ltd | Prescription reading device |
| CN104134157A (en) * | 2014-08-08 | 2014-11-05 | 平安养老保险股份有限公司 | Suspicious behavior audit system and method in medical insurance reimbursement process |
| CN105654072A (en) * | 2016-03-24 | 2016-06-08 | 哈尔滨工业大学 | Automatic character extraction and recognition system and method for low-resolution medical bill image |
| CN106530166A (en) * | 2016-08-31 | 2017-03-22 | 中国人民解放军总医院第附属医院 | Hospital medical insurance expense nonpayment prevention auxiliary management information system and nonpayment prevention method |
| CN107292597A (en) * | 2017-05-26 | 2017-10-24 | 深圳医畅科技发展有限公司 | Medical method, mobile terminal and the storage device paid is realized based on social security card |
| CN108280389A (en) * | 2017-01-06 | 2018-07-13 | 南通艾思达智能科技有限公司 | Medical bill ICR identifying systems and its medical bank slip recognition method |
| CN108564035A (en) * | 2018-04-13 | 2018-09-21 | 杭州睿琪软件有限公司 | The method and system for the information recorded on identification document |
| CN108961077A (en) * | 2018-07-02 | 2018-12-07 | 四川长虹电器股份有限公司 | A kind of medical insurance reimbursement system and medical insurance method of charging out based on OCR |
-
2018
- 2018-12-14 CN CN201811534174.0A patent/CN109711402B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003186990A (en) * | 2001-12-19 | 2003-07-04 | Sanyo Electric Co Ltd | Prescription reading device |
| CN104134157A (en) * | 2014-08-08 | 2014-11-05 | 平安养老保险股份有限公司 | Suspicious behavior audit system and method in medical insurance reimbursement process |
| CN105654072A (en) * | 2016-03-24 | 2016-06-08 | 哈尔滨工业大学 | Automatic character extraction and recognition system and method for low-resolution medical bill image |
| CN106530166A (en) * | 2016-08-31 | 2017-03-22 | 中国人民解放军总医院第附属医院 | Hospital medical insurance expense nonpayment prevention auxiliary management information system and nonpayment prevention method |
| CN108280389A (en) * | 2017-01-06 | 2018-07-13 | 南通艾思达智能科技有限公司 | Medical bill ICR identifying systems and its medical bank slip recognition method |
| CN107292597A (en) * | 2017-05-26 | 2017-10-24 | 深圳医畅科技发展有限公司 | Medical method, mobile terminal and the storage device paid is realized based on social security card |
| CN108564035A (en) * | 2018-04-13 | 2018-09-21 | 杭州睿琪软件有限公司 | The method and system for the information recorded on identification document |
| CN108961077A (en) * | 2018-07-02 | 2018-12-07 | 四川长虹电器股份有限公司 | A kind of medical insurance reimbursement system and medical insurance method of charging out based on OCR |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111489487A (en) * | 2019-05-09 | 2020-08-04 | 杭州睿琪软件有限公司 | Bill identification method, device, equipment and storage medium |
| WO2020224131A1 (en) * | 2019-05-09 | 2020-11-12 | 杭州睿琪软件有限公司 | Receipt recognition method and apparatus, electronic device, and computer readable storage medium |
| US11361570B2 (en) | 2019-05-09 | 2022-06-14 | Hangzhou Glorify Software Limited | Receipt identification method, apparatus, device and storage medium |
| US12008828B2 (en) | 2019-05-09 | 2024-06-11 | Hangzhou Glority Software Limited | Receipt identification method, apparatus, electronic device and computer-readable storage medium |
| CN110675270A (en) * | 2019-09-05 | 2020-01-10 | 平安健康保险股份有限公司 | Method and device for determining medical insurance deduction amount based on invoice information |
| CN112348017A (en) * | 2020-11-09 | 2021-02-09 | 浙江太美医疗科技股份有限公司 | Identification method and identification device for clinical test charging document |
| CN112348017B (en) * | 2020-11-09 | 2024-01-23 | 浙江太美医疗科技股份有限公司 | Identification method and identification device for clinical test charging receipt |
| CN112634065A (en) * | 2020-12-21 | 2021-04-09 | 山东众阳健康科技集团有限公司 | Method and system for reimbursing remote medical care receipt |
| CN113658671A (en) * | 2021-08-19 | 2021-11-16 | 湖南和信安华区块链科技有限公司 | Medical and health mutual-aid system based on block chain |
| CN114723420A (en) * | 2022-06-07 | 2022-07-08 | 武汉金豆医疗数据科技有限公司 | Medical insurance, business and insurance integrated auditing method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109711402B (en) | 2021-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109711402A (en) | A kind of medical document recognition methods and computer readable storage medium | |
| Ong et al. | Pan‐Asian resuscitation outcomes study (PAROS): rationale, methodology, and implementation | |
| Huckvale et al. | Smartphone apps for calculating insulin dose: a systematic assessment | |
| Mainous et al. | Availability of antibiotics for purchase without a prescription on the internet | |
| Nguyen | The principal-agent problems in health care: evidence from prescribing patterns of private providers in Vietnam | |
| Sacarny et al. | Medicare letters to curb overprescribing of controlled substances had no detectable effect on providers | |
| Green et al. | Quality of life, depression, and healthcare resource utilization among adults with type 2 diabetes mellitus and concomitant hypertension and obesity: a prospective survey | |
| Hollingworth et al. | Measuring medicine use: Applying ATC/DDD methodology to real-world data | |
| Smith et al. | Advancing the field of pharmaceutical risk minimization through application of implementation science best practices | |
| Lubman et al. | The National Ambulance Surveillance System: A novel method for monitoring acute alcohol, illicit and pharmaceutical drug related-harms using coded Australian ambulance clinical records | |
| Britt et al. | General practice activity in Australia | |
| Kendall et al. | An agenda for UK clinical pharmacology: provision of medicines information: the example of the British National Formulary | |
| Geuijen et al. | Success rates of monitoring for healthcare professionals with a substance use disorder: a meta-analysis | |
| Skoy et al. | Patient acceptance of naloxone resulting from targeted intervention from community pharmacists to prevent opioid misuse and accidental overdose | |
| Bloom et al. | Guideline‐concordant weight‐loss programs in an urban area are uncommon and difficult to identify through the internet | |
| Engstrom et al. | Toilet paper, minced meat and diabetes medicines: Australian panic buying induced by COVID-19 | |
| Leone et al. | Pandemics and burden of stroke and epilepsy in sub-Saharan Africa: experience from a longstanding health programme | |
| Aziz et al. | Patients’ anticipation for the pharmacies of rural communities: A qualitative study from Pakistan | |
| Lee et al. | Impact of up-scheduling medicines on pharmacy personnel, using codeine as an example, with possible adaption to complementary medicines: a scoping review | |
| Sharma et al. | A review of data quality of an electronic tuberculosis surveillance system for case-based reporting in Kenya | |
| Bowcutt et al. | Implementation of an intravenous medication infusion pump system: implications for nursing | |
| Moriya et al. | The complex relationships among race/ethnicity, social determinants, and opioid utilization | |
| Cranston et al. | Models of chronic disease management in primary care for patients with mild‐to‐moderate asthma or COPD: a narrative review | |
| Murphy et al. | Using brief clinician and parent measures to track outcomes in outpatient child psychiatry: longer term follow‐up and comparative effectiveness | |
| Dahal et al. | Economic evaluation of health behavior interventions to prevent and manage type 2 diabetes mellitus in Asia: a systematic review of randomized controlled trials |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211207 Address after: 310053 room d3201, 3rd floor, building 1 (North), No. 368, Liuhe Road, Binjiang District, Hangzhou, Zhejiang Patentee after: Hangzhou Ruizhen Technology Co.,Ltd. Address before: Room B2019, 2nd floor, building 1 (North), 368 Liuhe Road, Binjiang District, Hangzhou City, Zhejiang Province, 310053 Patentee before: HANGZHOU GLORITY SOFTWARE Ltd. |