CN115457586A - Case information extraction method, device, equipment and storage medium - Google Patents
Case information extraction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115457586A CN115457586A CN202211085763.1A CN202211085763A CN115457586A CN 115457586 A CN115457586 A CN 115457586A CN 202211085763 A CN202211085763 A CN 202211085763A CN 115457586 A CN115457586 A CN 115457586A
- Authority
- CN
- China
- Prior art keywords
- text information
- case
- case image
- standard
- category
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/418—Document matching, e.g. of document images
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/416—Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
Abstract
The invention discloses a case information extraction method, a case information extraction device, case information extraction equipment and a storage medium. The method comprises the following steps: receiving a case image from a target subject; performing text recognition processing on the case image to obtain the overall text information of the case image; extracting category text information from the overall text information of the case image; and performing text correction on the category text information by using a preset knowledge graph module to obtain standard text information corresponding to the case image. The invention establishes a medical record document information accurate identification and extraction mode based on text identification and knowledge map correction, and the mode can quickly and accurately extract image texts in different display formats of different hospitals, thereby improving the accuracy of identification and extraction of the medical record document and being beneficial to subsequent data processing of image medical records.
Description
Technical Field
The present invention relates to the field of information extraction technologies, and in particular, to a method, an apparatus, a device, and a storage medium for extracting case information.
Background
Today, with the rapid development of electronization, a great deal of text information exists in images, but the text in the images is too scattered to be conveniently viewed in the subsequent process. For example: the case image from the hospital or the case image uploaded by the user contains the detailed diagnosis information of the user, the diagnosis efficiency is low inevitably if the diagnosis condition of the user is determined by inquiring the case image of the user, and the inquiry efficiency of the diagnosis condition of the user is greatly improved if the texts in the case image are extracted and are subjected to normalized filing.
Currently, OCR (optical character recognition) technology can be used to recognize text in an image, but OCR technology is mostly used for a general image with less text content, and recognition accuracy is low for case images containing a large amount of professional vocabularies.
Disclosure of Invention
The invention mainly aims to provide a case information extraction method, a case information extraction device, case information extraction equipment and a storage medium, and aims to solve the problem that the recognition accuracy rate of the existing OCR technology is low for case images containing a large number of professional vocabularies.
In order to realize the technical problem, the invention is realized by the following technical scheme:
the embodiment of the invention provides a case information extraction method, which comprises the following steps: receiving a case image from a target subject; executing text recognition processing on the case image to obtain the whole text information of the case image; extracting category text information from the overall text information of the case image; and performing text correction on the category text information by using a preset knowledge graph module to obtain standard text information corresponding to the case image.
Wherein, extracting category text information from the overall text information of the case image comprises: matching the designated characteristic value in each standard document sample with the whole text information in a plurality of standard document samples configured for the target subject in advance; acquiring a standard document sample with a designated characteristic value matched with the integral text information; and extracting category text information from the whole text information by using the acquired standard characteristic value in the standard document sample.
Wherein the specified characteristic value in the standard document sample comprises a document type.
Wherein, extracting category text information from the overall text information of the case image comprises: and under the condition that a standard document sample with a specified characteristic value matched with the overall text information is not obtained, extracting category text information from the overall text information of the case image by using a preset non-standard characteristic value.
The method for correcting the category text information by using a preset knowledge graph module to obtain the standard text information corresponding to the case image comprises the following steps: performing text correction on category text information corresponding to part of the standard characteristic values by using a preset knowledge graph module; and obtaining the standard text information corresponding to the case image according to the corrected category text information and the category text information except the corrected category text information.
After obtaining the normative text information corresponding to the case image, the method further comprises the following steps: and outputting the standard text information corresponding to the case image to a preset information induction module.
The knowledge graph module is used for identifying non-standard words in the category text information and correcting the non-standard words in the category text information into standard words to obtain the standard text information corresponding to the case image.
An embodiment of the present invention further provides a case information extraction apparatus, including: a receiving module for receiving a case image from a target subject; the identification module is used for executing text identification processing on the case image to obtain the whole text information of the case image; the extraction module is used for extracting category text information from the overall text information of the case image; and the correction module is used for performing text correction on the category text information by using a preset knowledge graph module to obtain the standard text information corresponding to the case image.
The embodiment of the invention also provides a case information extraction device, which comprises a processor and a memory; the processor is configured to execute a case information extraction program stored in the memory to implement any one of the case information extraction methods described above.
An embodiment of the present invention also provides a computer-readable storage medium, which stores one or more programs that can be executed by one or more processors to implement any one of the case information extraction methods described above.
The embodiment of the invention has the following beneficial effects:
after receiving a case image from a target main body, executing text recognition processing on the case image to obtain overall text information of the case image; extracting category text information from the overall text information of the case image; and performing text correction on the category text information by using a preset knowledge graph module to obtain standard text information corresponding to the case image. The embodiment of the invention establishes a medical record document information accurate identification and extraction mode based on text identification and knowledge map correction, and the mode can quickly and accurately extract image texts with different display formats in different hospitals, thereby improving the accuracy of identification and extraction of the medical record document and being beneficial to subsequent data processing of image medical records.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a flowchart of a case information extraction method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating the steps of extracting category text information according to an embodiment of the present invention;
fig. 3 is a structural diagram of a case information extraction apparatus according to an embodiment of the present invention;
fig. 4 is a structural diagram of a case information extraction apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings and specific embodiments.
According to an embodiment of the present invention, there is provided a case information extraction method. Fig. 1 is a flowchart illustrating a case information extraction method according to an embodiment of the present invention.
In step S110, a case image from a target subject is received.
The categories of target subjects include: hospitals, users, etc. The number of target bodies is plural.
The case image refers to an electronic picture of a case document. For example: the case image is a scanned piece of the case document, and the picture of the case document is shot through the camera.
Step S120, performing text recognition processing on the case image to obtain the entire text information of the case image.
The whole text information is all the text information extracted from the case image.
The OCR technology may be utilized to perform text recognition processing on the case image, resulting in overall text information of the case image.
And step S130, extracting category text information from the overall text information of the case image.
The category text information refers to text items extracted from case images.
Categories of category text information include, but are not limited to: patient serial number, patient name, document type, disease name, disease code, clinical symptom, medication name, patient medication code, etc.
The extraction of the category text information will be described in detail later, and therefore, the detailed description thereof is omitted here.
And step S140, performing text correction on the category text information by using a preset knowledge graph module to obtain standard text information corresponding to the case image.
And presetting a knowledge graph module. The knowledge graph module is used for identifying the non-standard words in the category text information and correcting the non-standard words in the category text information into standard words to obtain the standard text information corresponding to the case image.
Specifically, OCR image recognition alone is not sufficient because there are a large number of synonyms or hypernyms for medical terms. Further, the same symptom has a wide variety of textual expressions, such as: "extra-systole", "premature beat" and "premature beat" are synonymous. The same symptom is often modified by different words to express slightly different semantic meanings, such as: "acute back pain" and "chronic back pain" can be the lower words of "back pain". Currently, ICD (International classification of diseases) codes are largely adopted in medical diagnosis, but the ICD coding structure does not contain complete upper and lower relations. Taking the example of the Chinese ICD code [1] which refers to acute rheumatic heart disease in particular, the superior words of the Chinese ICD code are rheumatic heart disease and acute rheumatic heart disease, the two diseases have the common superior word of rheumatic heart disease, and the rheumatic heart disease also has the superior word of heart disease. How to deal with the problems needs to unify the synonyms, the upper and lower terms through a knowledge graph module.
The categories of knowledge-graph modules include, but are not limited to: chinese electronic medical record knowledge map, disease knowledge map, clinical symptom knowledge map. By using the knowledge maps, the related clinical symptoms, disease names and codes and medicine names and codes in the category text information can be extracted and checked more quickly and accurately.
The knowledge-graph module may be obtained by pre-training. Further, the knowledge-graph module can be obtained by combining hospital data and Pubmed database training.
Furthermore, by using a preset knowledge graph module, text correction can be performed on category text information corresponding to part of the standard characteristic values; and obtaining the standard text information corresponding to the case image according to the corrected category text information and the category text information except the corrected category text information. That is, the corrected category text information and the other category text information other than the corrected category text information are taken as the specification text information. Further, the category text information corresponding to the part of standard feature values can be set according to requirements. For example: the category text information corresponding to the part of standard feature values may be clinical symptoms.
After the standard text information corresponding to the case image is obtained, the standard text information corresponding to the case image can be output to a preset information summarizing module. The information induction module is used for filing and storing the standard text information corresponding to the case image.
After receiving a case image from a target subject, the embodiment performs text recognition processing on the case image to obtain overall text information of the case image; extracting category text information from the overall text information of the case image; and performing text correction on the category text information by using a preset knowledge graph module to obtain standard text information corresponding to the case image. According to the embodiment, a medical record document information accurate identification and extraction mode based on text identification and knowledge graph correction is established, the mode can be used for quickly and accurately extracting image texts in different display formats of different hospitals, the accuracy rate of identification and extraction of the medical record document is improved, and the subsequent data processing of the image medical record is facilitated.
The following is specifically described with respect to the above step S130. Fig. 2 is a flowchart illustrating a procedure of extracting category text information according to an embodiment of the present invention.
Step S210, in a plurality of standard document samples configured for the target subject in advance, matching the entire text information with the specified feature value in each standard document sample.
The standard document sample is layout information of the case document.
Examples of standard documents include: a plurality of standard feature values. Each standard feature value corresponds to a category text message. Each standard feature value is used to indicate the location of the corresponding category text information in the case document.
The number of target bodies is plural. And correspondingly setting a plurality of standard document examples for each target main body.
Specifically, information of each target subject is stored in advance. The information of the target subject may be a network address of the target subject. When a case image is received, a target subject from which the case image is derived can be determined among a plurality of target subjects according to a network address from which the case image is transmitted, and a plurality of standard document samples corresponding to the target subject from which the case image is derived can be determined.
In order to be able to specify a standard document case corresponding to a case image among a plurality of standard document cases of a target subject, a specified feature value may be set in advance in each standard document case corresponding to the target subject. And after the overall text information is extracted from the case image, respectively matching the overall text information with the specified characteristic value of each standard document sample of the target subject, and determining the standard document sample of which the specified characteristic value is matched with the overall text information.
In the present embodiment, the specified feature value in the standard document sample includes a document type.
Step S220, acquiring a standard document sample with the designated characteristic value matched with the integral text information.
Step S230, extracting category text information from the whole text information by using the obtained standard feature value in the standard document sample.
And extracting category text information corresponding to each standard characteristic value according to the position indicated by each standard characteristic value in the standard document sample.
Categories of category text information include, but are not limited to: patient serial number, patient name, document type, disease name, disease code, clinical symptom, medication name, patient medication code, etc.
Further, there are cases where the case documents do not adopt a standard format, and therefore, when the standard document samples are matched, the case documents cannot be matched. For this case, it is possible to search and analyze the historical case documents, find case documents that do not adopt the standard format, and set the non-standard feature values according to the case documents that do not adopt the standard format. The non-standard feature value is used to indicate the location of category text information in the case document that is not in a standard format. In this embodiment, under the condition that a standard document sample with a specified feature value matching the whole text information is not acquired, category text information is extracted from the whole text information of the case image by using a preset non-standard feature value.
The embodiment of the invention also provides a case information extraction device. Fig. 3 is a block diagram of a case information extraction apparatus according to an embodiment of the present invention.
The case information extraction device includes:
a receiving module 310, configured to receive a case image from a target subject.
The recognition module 320 is configured to perform text recognition processing on the case image to obtain overall text information of the case image.
An extracting module 330, configured to extract category text information from the overall text information of the case image.
And the correcting module 340 is configured to perform text correction on the category text information by using a preset knowledge graph module to obtain standard text information corresponding to the case image.
Wherein, the extracting module 330 is configured to: matching the designated characteristic value in each standard document sample with the whole text information in a plurality of standard document samples configured for the target subject in advance; acquiring a standard document sample with a specified characteristic value matched with the integral text information; and extracting category text information from the whole text information by using the acquired standard characteristic value in the standard document sample.
Wherein the specified characteristic value in the standard document sample comprises a document type.
Wherein, the extracting module 330 is configured to: and under the condition that a standard document sample with a specified characteristic value matched with the overall text information is not obtained, extracting category text information from the overall text information of the case image by using a preset non-standard characteristic value.
Wherein, the correcting module 340 is configured to: performing text correction on category text information corresponding to part of the standard characteristic values by using a preset knowledge graph module; and obtaining the standard text information corresponding to the case image according to the corrected category text information and the category text information except the corrected category text information.
Wherein the apparatus further comprises: an output module (not shown). The output module is used for outputting the standard text information corresponding to the case image to a preset information summarizing module after the standard text information corresponding to the case image is obtained.
The knowledge graph module is used for identifying non-standard words in the category text information and correcting the non-standard words in the category text information into standard words to obtain the standard text information corresponding to the case image.
The functions of the apparatus according to the embodiment of the present invention have been described in the method embodiments, so that reference may be made to the relevant description in the foregoing embodiments for parts that are not described in detail in the description of the present embodiment, which are not described herein again.
The present embodiment provides a case information extraction apparatus. Fig. 4 is a block diagram of a case information extraction apparatus according to an embodiment of the present invention.
In the present embodiment, the case information extraction apparatus includes, but is not limited to: a processor 410, a memory 420.
The processor 410 is configured to execute a case information extraction program stored in the memory 420 to implement the case information extraction method described above.
Specifically, the processor 410 is configured to execute the case information extraction program stored in the memory 420 to implement the following steps: receiving a case image from a target subject; performing text recognition processing on the case image to obtain the overall text information of the case image; extracting category text information from the overall text information of the case image; and performing text correction on the category text information by using a preset knowledge graph module to obtain standard text information corresponding to the case image.
Wherein, extracting category text information from the overall text information of the case image comprises: matching the designated characteristic value in each standard document sample with the whole text information in a plurality of standard document samples configured for the target subject in advance; acquiring a standard document sample with a designated characteristic value matched with the integral text information; and extracting category text information from the whole text information by using the acquired standard characteristic value in the standard document sample.
Wherein the specified characteristic value in the standard document sample comprises a document type.
Wherein, extracting category text information from the overall text information of the case image comprises: and under the condition that a standard document sample with a specified characteristic value matched with the overall text information is not obtained, extracting category text information from the overall text information of the case image by using a preset non-standard characteristic value.
The method for performing text correction on the category text information by using a preset knowledge graph module to obtain the standard text information corresponding to the case image comprises the following steps: performing text correction on category text information corresponding to part of the standard characteristic values by using a preset knowledge graph module; and obtaining the standard text information corresponding to the case image according to the corrected category text information and the category text information except the corrected category text information.
After obtaining the normative text information corresponding to the case image, the method further comprises the following steps: and outputting the standard text information corresponding to the case image to a preset information summarizing module.
The knowledge graph module is used for identifying non-standard words in the category text information and correcting the non-standard words in the category text information into standard words to obtain the standard text information corresponding to the case image.
The embodiment of the invention also provides a computer readable storage medium. The computer-readable storage medium herein stores one or more programs. Among others, the storage medium may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, a hard disk, or a solid state disk; the memory may also comprise a combination of the above kinds of memories.
When one or more programs in the storage medium are executed by one or more processors, the case information extraction method described above is implemented.
Specifically, the processor is configured to execute a case information extraction program stored in the memory to implement the steps of: receiving a case image from a target subject; executing text recognition processing on the case image to obtain the whole text information of the case image; extracting category text information from the overall text information of the case image; and performing text correction on the category text information by using a preset knowledge graph module to obtain standard text information corresponding to the case image.
Wherein, extracting category text information from the overall text information of the case image comprises: matching the designated characteristic value in each standard document sample with the whole text information in a plurality of standard document samples configured for the target subject in advance; acquiring a standard document sample with a designated characteristic value matched with the integral text information; and extracting category text information from the whole text information by using the acquired standard characteristic value in the standard document sample.
Wherein the specified characteristic value in the standard document sample comprises a document type.
Wherein, extracting category text information from the overall text information of the case image comprises: and under the condition that a standard document sample with a specified characteristic value matched with the overall text information is not obtained, extracting category text information from the overall text information of the case image by using a preset non-standard characteristic value.
The method for correcting the category text information by using a preset knowledge graph module to obtain the standard text information corresponding to the case image comprises the following steps: performing text correction on category text information corresponding to part of the standard characteristic values by using a preset knowledge graph module; and obtaining the standard text information corresponding to the case image according to the corrected category text information and the category text information except the corrected category text information.
After obtaining the normative text information corresponding to the case image, the method further comprises the following steps: and outputting the standard text information corresponding to the case image to a preset information induction module.
The knowledge graph module is used for identifying non-standard words in the category text information and correcting the non-standard words in the category text information into standard words to obtain the standard text information corresponding to the case image.
The above description is only an example of the present invention, and is not intended to limit the present invention, and it is obvious to those skilled in the art that various modifications and variations can be made in the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (10)
1. A case information extraction method, characterized by comprising:
receiving a case image from a target subject;
performing text recognition processing on the case image to obtain the overall text information of the case image;
extracting category text information from the overall text information of the case image;
and performing text correction on the category text information by using a preset knowledge graph module to obtain standard text information corresponding to the case image.
2. The method of claim 1, wherein extracting category text information from the overall text information of the case image comprises:
matching the designated characteristic value in each standard document sample with the whole text information in a plurality of standard document samples configured for the target subject in advance;
acquiring a standard document sample with a designated characteristic value matched with the integral text information;
and extracting category text information from the whole text information by using the acquired standard characteristic value in the standard document sample.
3. The method of claim 2, wherein the specified characteristic value in the standard document sample comprises a document type.
4. The method of claim 2, wherein extracting category text information from the overall text information of the case image comprises:
and under the condition that a standard document sample with a specified characteristic value matched with the overall text information is not obtained, extracting category text information from the overall text information of the case image by using a preset non-standard characteristic value.
5. The method according to claim 2, wherein performing text correction on the category text information by using a preset knowledge graph module to obtain the normative text information corresponding to the case image comprises:
performing text correction on category text information corresponding to part of the standard characteristic values by using a preset knowledge graph module;
and obtaining the standard text information corresponding to the case image according to the corrected category text information and the category text information except the corrected category text information.
6. The method according to claim 5, further comprising, after obtaining the normative text information corresponding to the case image:
and outputting the standard text information corresponding to the case image to a preset information summarizing module.
7. The method according to any one of claims 1-6, wherein the knowledge graph module is configured to identify non-canonical words in the category text information and correct the non-canonical words in the category text information into canonical words, resulting in canonical text information corresponding to the case image.
8. A case information extraction device characterized by comprising:
a receiving module for receiving a case image from a target subject;
the identification module is used for executing text identification processing on the case image to obtain the whole text information of the case image;
the extraction module is used for extracting category text information from the overall text information of the case image;
and the correction module is used for performing text correction on the category text information by using a preset knowledge graph module to obtain the standard text information corresponding to the case image.
9. A case information extraction apparatus characterized by comprising a processor, a memory; the processor is configured to execute a case information extraction program stored in the memory to implement the case information extraction method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores one or more programs, which are executable by one or more processors, to implement the case information extraction method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211085763.1A CN115457586A (en) | 2022-09-06 | 2022-09-06 | Case information extraction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211085763.1A CN115457586A (en) | 2022-09-06 | 2022-09-06 | Case information extraction method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115457586A true CN115457586A (en) | 2022-12-09 |
Family
ID=84302039
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211085763.1A Pending CN115457586A (en) | 2022-09-06 | 2022-09-06 | Case information extraction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115457586A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116933757A (en) * | 2023-09-15 | 2023-10-24 | 京华信息科技股份有限公司 | Document generation method and system applying language artificial intelligence |
-
2022
- 2022-09-06 CN CN202211085763.1A patent/CN115457586A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116933757A (en) * | 2023-09-15 | 2023-10-24 | 京华信息科技股份有限公司 | Document generation method and system applying language artificial intelligence |
| CN116933757B (en) * | 2023-09-15 | 2023-12-29 | 京华信息科技股份有限公司 | Document generation method and system applying language artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10599709B2 (en) | Object recognition device, object recognition method, and program for recognizing an object in an image based on tag information | |
| US8064703B2 (en) | Property record document data validation systems and methods | |
| US20070217692A1 (en) | Property record document data verification systems and methods | |
| CN110796180B (en) | Model training system and method based on artificial intelligence | |
| CN114358001A (en) | Method for standardizing diagnosis result, and related device, equipment and storage medium thereof | |
| CN111462865A (en) | Medical image recognition model generation method and device, computer equipment and medium | |
| CN114912887B (en) | Clinical data input method and device based on electronic medical record | |
| CN115457586A (en) | Case information extraction method, device, equipment and storage medium | |
| CN112560400A (en) | Medical data processing method and device and storage medium | |
| CN114913942A (en) | Intelligent matching method and device for patient recruitment projects | |
| CN113762100B (en) | Method, device, computing equipment and storage medium for extracting and standardizing names in medical notes | |
| CN112116968A (en) | Medical examination report recognition method, device, equipment and storage medium | |
| CN110491519A (en) | A kind of method of inspection of medical data | |
| CN113642562A (en) | Data interpretation method, device and equipment based on image recognition and storage medium | |
| CN111104481B (en) | Method, device and equipment for identifying matching field | |
| CN116469505A (en) | Data processing method, device, computer equipment and readable storage medium | |
| CN109960707B (en) | College recruitment data acquisition method and system based on artificial intelligence | |
| US20220415456A1 (en) | Character acquisition, page processing and knowledge graph construction method and device, medium | |
| CN114400062B (en) | Interpretation method and device of inspection report, computer equipment and storage medium | |
| CN115455153A (en) | Document mapping determination method and device | |
| CN113010685B (en) | Medical term standardization method, electronic device, and storage medium | |
| CN114743209A (en) | Prescription identification and verification method, system, electronic equipment and storage medium | |
| CN113111660A (en) | Data processing method, device, equipment and storage medium | |
| CN111143374A (en) | Data auxiliary identification method, system, computing equipment and storage medium | |
| CN112348472B (en) | Method, device and computer readable medium for inputting laboratory checklist |
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 |