A method and system for intelligent entry of outpatient medical records

Abstract

A method and system for intelligent entry of outpatient medical records, constructing a patient information database, which includes patient medical record numbers and patient facial data; performing facial recognition on patients entering the outpatient department, matching patient facial data and patient medical record numbers through facial recognition; synchronizing outpatient, emergency, inpatient and discharge medical records from the hospital information system at a preset time, extracting patient identities and medical data and storing them in a search engine; retrieving patient identities and historical medical data in the search engine with the patient medical record number as an index, and bringing the retrieved patient identities and historical medical data into the outpatient medical record; converting the voice conversation between the doctor and the patient into a medical conversation text through voice recognition, extracting the patient's current medical information from the medical conversation text, and bringing the extracted patient's current medical information into the outpatient medical record. The present invention ensures the correctness and accuracy of medical record data; greatly optimizes the response speed of medical record entry and improves the doctor's experience.

Description

Technical Field

[0001] The present invention belongs to the field of smart medical technology, and specifically relates to a method and system for intelligently entering outpatient medical records. Background Art

[0002] Face recognition is a biometric technology that identifies a person based on his or her facial features. It uses a camera or camcorder to capture images or video streams containing faces, and automatically detects and tracks faces in the images, and then performs face recognition on the detected faces. It is also called portrait recognition or facial recognition.

[0003] Speech recognition is a field of research that uses speech to allow machines to automatically recognize and understand spoken language. Speech recognition allows machines to convert speech signals into corresponding text or commands through the process of recognition and understanding.

[0004] Relevant statistics show that using the electronic medical record information system to see patients costs doctors an average of 48 minutes more per day. For outpatient doctors, this time is far from enough. Tests show that an emergency doctor needs to click the mouse 4,000 times, spend 3 to 4 minutes on consultation, and spend 10 minutes writing electronic medical records to complete all electronic medical records during his duty. Outpatient doctors need to spend a lot of time and energy to manually enter medical record information. How to quickly and accurately complete the filling of outpatient medical records and optimize the response speed of medical record entry is a technical problem that needs to be solved urgently. Summary of the invention

[0005] To this end, the present invention provides an outpatient medical record intelligent entry method and system, which realizes the rapid, intelligent and automatic generation of outpatient medical records, and solves the problems of low efficiency and poor accuracy in filling out outpatient medical records.

[0006] In order to achieve the above object, the present invention provides the following technical solution: a method for intelligently entering outpatient medical records, comprising the following steps:

[0007] Constructing a patient information database, wherein the patient information database includes patient medical record numbers and patient facial data;

[0008] Perform facial recognition on patients entering the outpatient department, and match the patient's facial data and medical record number through facial recognition;

[0009] Synchronize outpatient, inpatient, and discharge medical records from the hospital information system at preset times, extract patient identity and medical data, and store them in the search engine;

[0010] Retrieve the patient's identity and historical medical data from the search engine using the patient's medical record number as an index, and bring the retrieved patient's identity and historical medical data into the outpatient medical record;

[0011] Through speech recognition, the voice conversation between the doctor and the patient is converted into a medical conversation text, and the patient's current medical information is extracted from the medical conversation text, and the extracted patient's current medical information is brought into the outpatient medical record.

[0012] As a preferred solution of the outpatient medical record intelligent entry method, the patient information database stores the patient facial data of patients who have visited the hospital in the past. When the patient visits the hospital again, the facial feature value is scanned, and the scanned facial feature value is matched with the patient facial data in the patient information database. If the match is successful, the patient medical record number is returned.

[0013] If the match is successful, the patient's name, age, ID number, gender and consultation time will also be returned.

[0014] As the preferred solution for the intelligent entry method of outpatient medical records, outpatient, inpatient and discharge medical records are synchronized with the hospital information system on a regular basis every day; medical records are sorted in reverse order of patient registration time, and the latest patient identity and historical medical data of each patient are extracted from the medical records; the extracted patient identity and historical medical data are stored in the elastic search search engine.

[0015] As a preferred solution for the intelligent entry method of outpatient medical records, if the information pushed by the hospital information system contains updated or new patient information, the elastic search index record is updated.

[0016] As the preferred solution for the intelligent entry method of outpatient medical records, the outpatient medical template is used to dynamically extract the patient's chief complaint information, drug allergy history information, past medical history information, family history information, diagnosis information and treatment opinions from the medical conversation text;

[0017] Medical connotations are compared through the drug allergy dictionary, medical history dictionary, family history dictionary, and drug allergy history, past medical history, and family history found in the elastic search engine library. If the drug allergy names of the drug allergy history, the names of the diseases in the medical history, and the names of the genetic diseases in the family history expressed in the two texts are the same, the drug allergy history, past medical history, and family history information of the patient that have been brought in will not be overwritten;

[0018] If the main information of drug allergy history, past medical history, and family history is inconsistent, the patient's latest result shall prevail, covering the drug allergy history, past medical history, and family history information that have been entered.

[0019] As a preferred solution of the outpatient medical record intelligent entry method, it also includes obtaining the doctor's operation voice instructions for the outpatient medical record, and modifying or confirming the outpatient medical record according to the operation voice instructions;

[0020] Synchronize the patient's final outpatient medical record to the hospital's electronic medical record system and update the patient index record of the elastic search search engine.

[0021] The present invention also provides an outpatient medical record intelligent entry system, comprising:

[0022] A patient information database construction module is used to construct a patient information database, wherein the patient information database includes patient medical record numbers and patient facial data;

[0023] The face recognition module is used to perform face recognition on patients entering the outpatient department and match the patient's face data with the patient's medical record number through face recognition;

[0024] The medical record document processing module is used to synchronize outpatient, inpatient and discharge medical records from the hospital information system according to the preset time, extract patient identity and medical data and store them in the search engine;

[0025] Patient history information retrieval module, used to retrieve patient identity and historical medical data in the search engine using the patient medical record number as an index, and bring the retrieved patient identity and historical medical data into the outpatient medical record;

[0026] The medical conversation processing module is used to convert the voice conversation between the doctor and the patient into medical conversation text through voice recognition, extract the patient's current medical information from the medical conversation text, and bring the extracted patient's current medical information into the outpatient medical record.

[0027] As a preferred solution for the outpatient medical record intelligent entry system, in the patient information database construction module, the patient information database stores the patient facial data of historically treated patients;

[0028] In the face recognition module, when the patient visits the doctor again, the face feature value is scanned, and the scanned face feature value is matched with the patient face data in the patient information database. If the match is successful, the patient's medical record number is returned;

[0029] If the match is successful, the patient's name, age, ID number, gender and consultation time will also be returned.

[0030] As a preferred solution for the outpatient medical record intelligent entry system, the medical record document processing module synchronizes outpatient, emergency, inpatient and discharge medical records from the hospital information system on a regular basis every day; sorts the medical records in reverse order of the patient's registration time, extracts the latest patient identity and historical medical data of each patient from the medical record documents; and stores the extracted patient identity and historical medical data in the elastic search search engine.

[0031] As a preferred solution for the outpatient medical record intelligent entry system, in the medical consultation processing module, the patient's chief complaint information, drug allergy history information, past medical history information, family history information, diagnosis information and treatment opinions in the medical consultation text are dynamically extracted through the outpatient medical template;

[0032] In the consultation conversation processing module, the medical connotation is compared through the drug allergy dictionary, medical history dictionary, family history dictionary, and the drug allergy history, past medical history, and family history found from the elastic search engine library. If the drug allergy name of the drug allergy history, the disease name in the medical history, and the genetic disease name in the family history expressed in the two texts are consistent, the drug allergy history, past medical history, and family history information of the patient that have been brought in will not be overwritten;

[0033] In the medical consultation processing module, if the main information of drug allergy history, past medical history, and family history is inconsistent, the patient's latest result shall prevail, covering the drug allergy history, past medical history, and family history information that have been brought in.

[0034] As a preferred solution for the outpatient medical record intelligent entry system, it also includes an operation voice processing module for obtaining the doctor's operation voice instructions for the outpatient medical record, and modifying or confirming the outpatient medical record according to the operation voice instructions.

[0035] As a preferred solution for the outpatient medical record intelligent entry system, it also includes an information update module for updating elastic search index records if there is updated or new patient information in the information pushed by the hospital information system;

[0036] The information update module is also used to synchronize the patient's final outpatient medical record to the hospital's electronic medical record system and update the patient index record of the elastic search search engine.

[0037] The present invention has the following advantages: constructing a patient information database, which includes patient medical record numbers and patient face data; performing face recognition on patients entering the outpatient department, and matching patient face data and patient medical record numbers through face recognition; synchronizing outpatient, inpatient and discharge medical records from the hospital information system at a preset time, extracting patient identity and medical data, and storing them in a search engine; retrieving patient identity and historical medical data in a search engine with the patient medical record number as an index, and bringing the retrieved patient identity and historical medical data into the outpatient medical record; converting the voice conversation between the doctor and the patient into a medical conversation text through voice recognition, extracting the patient's current medical information from the medical conversation text, and bringing the extracted patient's current medical information into the outpatient medical record. The present invention preferentially obtains patient information from the patient's previous medical records, and uses a search engine to ensure the correctness and accuracy of medical record data; greatly optimizes the response speed of medical record entry, improves the doctor's experience, can help doctors quickly and intelligently complete the filling of outpatient medical records, saves doctors' precious consultation time, improves doctors' work efficiency, and is convenient for patients and doctors. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0039] The structures, proportions, sizes, etc. illustrated in this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with the technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantial technical significance. Any structural modification, change in proportion or adjustment of size shall still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and purposes that can be achieved by the present invention.

[0040] Figure 1 A schematic diagram of a flow chart of an outpatient medical record intelligent entry method provided in Example 1 of the present invention;

[0041] Figure 2 Schematic diagram of the outpatient medical record intelligent entry system provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0042] The following is a description of the implementation of the present invention by specific embodiments. People familiar with the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] Example 1

[0044] See also Figure 1 Embodiment 1 of the present invention provides an outpatient medical record intelligent entry method, comprising the following steps:

[0045] S1. Build a patient information database, which includes patient medical record numbers and patient facial data;

[0046] S2. Perform facial recognition on patients entering the outpatient department, and match the patient's facial data and medical record number through facial recognition;

[0047] S3, synchronize outpatient, inpatient and discharge medical records from the hospital information system according to the preset time, extract patient identity and medical data and store them in the search engine;

[0048] S4, using the patient's medical record number as an index to retrieve the patient's identity and historical medical data in a search engine, and bringing the retrieved patient's identity and historical medical data into the outpatient medical record;

[0049] S5. The voice conversation between the doctor and the patient is converted into a medical conversation text through voice recognition, the patient's current medical information is extracted from the medical conversation text, and the extracted patient's current medical information is brought into the outpatient medical record.

[0050] In this embodiment, the patient information database stores the patient facial data of patients who have visited the hospital in the past. When the patient visits the hospital again, the facial feature values ​​are scanned and matched with the patient facial data in the patient information database. If the match is successful, the patient's medical record number is returned; if the match is successful, the patient's name, age, ID number, gender and visit time are also returned.

[0051] Specifically, the basis of intelligent entry of outpatient medical records is to match patient users through facial recognition. The hospital pre-builds a patient information database for patients who have visited the hospital. The patient information database stores the facial recognition feature values ​​of historical patients. When the patient visits the hospital again, the patient information database is searched for a match based on the facial feature values ​​scanned by the facial recognition machine. If a match is found, the patient's basic information is returned, such as name, age, ID number, gender, visit time, patient medical record number, etc.

[0052] In this embodiment, the outpatient, inpatient and discharge medical records are synchronized from the hospital information system on a regular basis every day; the medical records are sorted in reverse order of the patient registration time, and the latest patient identity and historical medical data of each patient are extracted from the medical records; the extracted patient identity and historical medical data are stored in the elastic search search engine. If the information pushed by the hospital information system contains updated or newly added patient information, the elastic search index record is updated.

[0053] Specifically, the elastic search search engine is a Lucene-based search server that provides a distributed multi-user full-text search engine based on a RESTful web interface. It is a popular enterprise-level search engine that can achieve real-time search, is stable, reliable, fast, and easy to install and use.

[0054] In this embodiment, the patient's medical record number is used as the elastic search index, and the name, age, native place, occupation, work unit, contact number, date of birth, history of drug allergy, past medical history, family history and registration time are used as index fields. The outpatient and emergency, inpatient and discharge medical records synchronized from the hospital information system (HIS system) are sorted in reverse order according to the patient's registration time every day, and the latest name, age, native place, occupation, work unit, contact number, date of birth, history of drug allergy, past medical history, family history and registration time information of each patient are extracted from the medical record documents, and the extracted information is stored in the elastic search search engine. If the information pushed by the hospital information system has updated and newly added patient information, the elastic search index record is updated. According to the patient's medical record number, the patient's name, age, native place, occupation, work unit, contact number, date of birth, history of drug allergy, past medical history and family history are quickly retrieved from the elastic search engine library, and automatically brought into the outpatient medical record.

[0055] In this embodiment, the outpatient medical template is used to dynamically extract the patient's chief complaint information, drug allergy history information, past medical history information, family history information, diagnosis information and treatment opinions from the medical conversation text;

[0056] Medical connotations are compared through the drug allergy dictionary, medical history dictionary, family history dictionary, and drug allergy history, past medical history, and family history found in the elastic search engine library. If the drug allergy names of the drug allergy history, the names of the diseases in the medical history, and the names of the genetic diseases in the family history expressed in the two texts are the same, the drug allergy history, past medical history, and family history information of the patient that have been brought in will not be overwritten;

[0057] If the main information of drug allergy history, past medical history, and family history is inconsistent, the patient's latest result shall prevail, covering the drug allergy history, past medical history, and family history information that have been entered.

[0058] Specifically, the elements of the outpatient medical template generally include: name, age, place of origin, occupation, work unit, contact number, date of birth, history of drug allergies, past medical history and family history. By converting the conversation between the doctor and the patient about family history into a medical conversation text, and then through semantic analysis, the doctor's questions and the patient's answers are classified according to the template elements. For example, in family history, doctors will ask patients in practice whether they have a family history of genetic diseases or the health of their family members. The patient's answer does not contain a negative answer, and there is a specific description of the disease. According to the patient's answer, whether it is the patient himself or his family, who is screened first, and then the disease name is matched to the genetic disease dictionary according to the disease description, so that the family history record can be dynamically generated.

[0059] Specifically, in the process of converting the voice conversation between the doctor and the patient into the text of the medical conversation through voice recognition, the patient and the doctor are identified according to the voiceprint. The theoretical basis of voiceprint recognition is that each voice has unique characteristics, and the voices of different people can be effectively distinguished through voice characteristics. This unique characteristic is mainly determined by two factors. The first is the size of the vocal cavity, including the throat, nasal cavity and oral cavity. The shape, size and position of these organs determine the size of the vocal cord tension and the range of sound frequency. Therefore, although different people say the same words, the frequency distribution of the sound is different, and some sound low and some sound loud. Everyone's vocal cavity is different, just like fingerprints, and everyone's voice has unique characteristics. The second factor that determines the sound characteristics is the way the vocal organs are manipulated. The vocal organs include lips, teeth, tongue, soft palate and palatal muscles, and the interaction between them will produce clear speech. The way of cooperation between them is randomly learned by people through communication with people around them. In the process of learning to speak, people will gradually form their own voiceprint characteristics by imitating the way different people around them speak. Therefore, the voice conversation between doctors and patients can be converted into the text of medical conversation through voice recognition.

[0060] In this embodiment, it also includes obtaining the doctor's voice instructions for operating the outpatient medical record, and modifying or confirming the outpatient medical record according to the voice instructions;

[0061] Synchronize the patient's final outpatient medical record to the hospital's electronic medical record system and update the patient index record of the elastic search search engine.

[0062] Specifically, during the outpatient medical record entry process, if the doctor believes that the automatically generated outpatient medical record has defects, the outpatient medical record can be modified. For example, if the patient's gender in the outpatient medical record is female, but the patient is actually male, the doctor can use voice instructions to change the gender to male, and after receiving the voice instructions, analyze it as an outpatient medical record gender modification instruction, and the modification content is to change the gender to male, and then update the gender field of the patient's outpatient record. If the doctor believes that there is no problem with the automatically generated or modified outpatient medical record, he can confirm it through voice, and the final version of the patient's outpatient medical record will be synchronized to the hospital's electronic medical record system and update the elastic search index record of the patient.

[0063] In summary, the present invention constructs a patient information database, which includes patient medical record numbers and patient facial data; performs facial recognition on patients entering the outpatient department, and matches patient facial data and patient medical record numbers through facial recognition; synchronizes outpatient, inpatient and discharge medical records from the hospital information system at a preset time, extracts patient identity and medical data, and stores them in a search engine; retrieves patient identity and historical medical data in the search engine with the patient medical record number as an index, and brings the retrieved patient identity and historical medical data into the outpatient medical record; converts the voice conversation between the doctor and the patient into a medical conversation text through voice recognition, extracts the patient's current medical information from the medical conversation text, and brings the extracted patient's current medical information into the outpatient medical record. The present invention preferentially obtains patient information from the patient's previous medical records, and uses a search engine to ensure the correctness and accuracy of medical record data; greatly optimizes the response speed of medical record entry, improves the doctor's experience, can help doctors quickly and intelligently complete the filling of outpatient medical records, saves doctors' precious consultation time, improves doctors' work efficiency, and is convenient for patients and doctors.

[0064] Example 2

[0065] See also Figure 2 Embodiment 2 of the present invention further provides an outpatient medical record intelligent entry system, comprising:

[0066] Patient information database construction module 1, used to construct a patient information database, the patient information database includes patient medical record number and patient facial data;

[0067] Face recognition module 2, used for face recognition of patients entering the outpatient department, and matching the patient's face data and the patient's medical record number through face recognition;

[0068] Medical record document processing module 3, used to synchronize outpatient, inpatient and discharge medical record documents from the hospital information system according to the preset time, extract patient identity and medical data and store them in the search engine;

[0069] Patient history information retrieval module 4, used to retrieve the patient identity and historical medical data in the search engine using the patient medical record number as an index, and bring the retrieved patient identity and historical medical data into the outpatient medical record;

[0070] The medical conversation processing module 5 is used to convert the voice conversation between the doctor and the patient into a medical conversation text through voice recognition, extract the patient's current medical information from the medical conversation text, and bring the extracted patient's current medical information into the outpatient medical record.

[0071] In this embodiment, in the patient information database construction module 1, the patient information database stores patient facial data of patients with historical medical visits;

[0072] In the face recognition module 2, when the patient visits the doctor again, the face feature value is scanned, and the scanned face feature value is matched with the patient face data in the patient information database. If the match is successful, the patient's medical record number is returned;

[0073] If the match is successful, the patient's name, age, ID number, gender and consultation time will also be returned.

[0074] The basis of intelligent entry of outpatient medical records is to match patient users through facial recognition. The hospital pre-builds a patient information database for patients who have visited the hospital. The patient information database stores the facial recognition feature values ​​of historical patients. When the patient visits the hospital again, the patient information database is searched for a match based on the facial feature values ​​scanned by the facial recognition machine. If a match is found, the patient's basic information is returned, such as name, age, ID number, gender, visit time, patient medical record number, etc.

[0075] In this embodiment, in the medical record document processing module 3, outpatient, inpatient and discharge medical record documents are synchronized with the hospital information system on a regular basis every day; the medical record documents are sorted in reverse order of the patient registration time, and the latest patient identity and historical medical data of each patient are extracted from the medical record documents; the extracted patient identity and historical medical data are stored in the elastic search search engine.

[0076] Specifically, the elastic search search engine is a Lucene-based search server that provides a distributed multi-user full-text search engine based on a RESTful web interface. It is a popular enterprise-level search engine that can achieve real-time search, is stable, reliable, fast, and easy to install and use.

[0077] In this embodiment, the patient's medical record number is used as the elastic search index, and the name, age, native place, occupation, work unit, contact number, date of birth, history of drug allergy, past medical history, family history and registration time are used as index fields. The outpatient and emergency, inpatient and discharge medical records synchronized from the hospital information system (HIS system) are sorted in reverse order according to the patient's registration time every day, and the latest name, age, native place, occupation, work unit, contact number, date of birth, history of drug allergy, past medical history, family history and registration time information of each patient are extracted from the medical record documents, and the extracted information is stored in the elastic search search engine. If the information pushed by the hospital information system has updated and newly added patient information, the elastic search index record is updated. According to the patient's medical record number, the patient's name, age, native place, occupation, work unit, contact number, date of birth, history of drug allergy, past medical history and family history are quickly retrieved from the elastic search engine library, and automatically brought into the outpatient medical record.

[0078] In this embodiment, the consultation conversation processing module 5 dynamically extracts the patient's chief complaint information, drug allergy history information, past medical history information, family history information, diagnosis information and treatment opinions from the consultation conversation text through the outpatient medical template;

[0079] In the medical consultation processing module 5, the medical connotation is compared through the drug allergy dictionary, medical history dictionary, family history dictionary, and the drug allergy history, past medical history, and family history found from the elastic search engine library. If the drug allergy names of the drug allergy history, the names of the diseases in the medical history, and the names of the genetic diseases in the family history expressed in the two texts are consistent, the drug allergy history, past medical history, and family history information of the patient that have been brought in will not be overwritten;

[0080] In the medical consultation processing module 5, if the main information of drug allergy history, past medical history, and family history is inconsistent, the patient's latest result shall prevail, covering the drug allergy history, past medical history, and family history information that have been brought in.

[0081] Specifically, the elements of the outpatient medical template generally include: name, age, place of origin, occupation, work unit, contact number, date of birth, history of drug allergies, past medical history and family history. By converting the conversation between the doctor and the patient about family history into a medical conversation text, and then through semantic analysis, the doctor's questions and the patient's answers are classified according to the template elements. For example, in family history, doctors will ask patients in practice whether they have a family history of genetic diseases or the health of their family members. The patient's answer does not contain a negative answer, and there is a specific description of the disease. According to the patient's answer, whether it is the patient himself or his family, who is screened first, and then the disease name is matched to the genetic disease dictionary according to the disease description, so that the family history record can be dynamically generated.

[0082] Specifically, in the process of converting the voice conversation between the doctor and the patient into the text of the medical conversation through voice recognition, the patient and the doctor are identified according to the voiceprint. The theoretical basis of voiceprint recognition is that each voice has unique characteristics, and the voices of different people can be effectively distinguished through voice characteristics. This unique characteristic is mainly determined by two factors. The first is the size of the vocal cavity, including the throat, nasal cavity and oral cavity. The shape, size and position of these organs determine the size of the vocal cord tension and the range of sound frequency. Therefore, although different people say the same words, the frequency distribution of the sound is different, and some sound low and some sound loud. Everyone's vocal cavity is different, just like fingerprints, and everyone's voice has unique characteristics. The second factor that determines the sound characteristics is the way the vocal organs are manipulated. The vocal organs include lips, teeth, tongue, soft palate and palatal muscles, and the interaction between them will produce clear speech. The way of cooperation between them is randomly learned by people through communication with people around them. In the process of learning to speak, people will gradually form their own voiceprint characteristics by imitating the way different people around them speak. Therefore, the voice conversation between doctors and patients can be converted into the text of medical conversation through voice recognition.

[0083] In this embodiment, an operation voice processing module 6 is also included, which is used to obtain the doctor's operation voice instructions for the outpatient medical record, and modify or confirm the outpatient medical record according to the operation voice instructions.

[0084] In this embodiment, an information updating module 7 is also included, which is used to update the elastic search index record if there is updated or newly added patient information in the information pushed by the hospital information system;

[0085] The information updating module 7 is also used to synchronize the patient's final outpatient medical record to the hospital's electronic medical record system and update the patient index record of the elastic search search engine.

[0086] Specifically, during the outpatient medical record entry process, if the doctor believes that the automatically generated outpatient medical record has defects, the outpatient medical record can be modified. For example, if the patient's gender in the outpatient medical record is female, but the patient is actually male, the doctor can use voice instructions to change the gender to male, and after receiving the voice instructions, analyze it as an outpatient medical record gender modification instruction, and the modification content is to change the gender to male, and then update the gender field of the patient's outpatient record. If the doctor believes that there is no problem with the automatically generated or modified outpatient medical record, he can confirm it through voice, and the final version of the patient's outpatient medical record will be synchronized to the hospital's electronic medical record system and update the elastic search index record of the patient.

[0087] It should be noted that the information interaction, execution process, etc. between the modules / units of the above-mentioned system are based on the same concept as the method embodiment in Example 1 of the present application, and the technical effects they bring are the same as those of the method embodiment of the present application. For specific contents, please refer to the description in the method embodiment shown in the previous part of the present application, and will not be repeated here.

[0088] Example 3

[0089] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium, in which the program code of the outpatient medical record intelligent entry method is stored, and the program code includes instructions for executing the outpatient medical record intelligent entry method of embodiment 1 or any possible implementation method thereof.

[0090] The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more available media. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0091] Example 4

[0092] Embodiment 4 of the present invention provides an electronic device, including: a memory and a processor;

[0093] The processor and the memory communicate with each other via a bus; the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the outpatient medical record intelligent entry method of embodiment 1 or any possible implementation method thereof.

[0094] Specifically, the processor can be implemented by hardware or by software. When implemented by hardware, the processor can be a logic circuit, an integrated circuit, etc.; when implemented by software, the processor can be a general-purpose processor implemented by reading software codes stored in a memory. The memory can be integrated in the processor or can be located outside the processor and exist independently.

[0095] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center.

[0096] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0097] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.

Claims

1. A method for intelligently entering outpatient medical records, characterized in that: The following steps are involved: Constructing a patient information database, wherein the patient information database includes patient medical record numbers and patient facial data; Perform facial recognition on patients entering the outpatient department, and match the patient's facial data and medical record number through facial recognition; Synchronize outpatient, inpatient, and discharge medical records from the hospital information system at preset times, extract patient identity and medical data, and store them in the search engine; Retrieve the patient's identity and historical medical data from the search engine using the patient's medical record number as an index, and bring the retrieved patient's identity and historical medical data into the outpatient medical record; The speech conversation between the doctor and the patient is converted into a medical conversation text through speech recognition, and the patient's current medical information is extracted from the medical conversation text, and the extracted patient's current medical information is brought into the outpatient medical record; The patient information database stores the patient facial data of patients who have visited the hospital in the past. When the patient visits the hospital again, the facial feature value is scanned, and the scanned facial feature value is matched with the patient facial data in the patient information database. If the match is successful, the patient's medical record number is returned. If the match is successful, the patient's name, age, ID number, gender and consultation time will also be returned; Synchronize outpatient, inpatient, and discharge medical records from the hospital information system on a regular basis every day; sort medical records in reverse order of patient registration time, extract the latest patient identity and historical medical data of each patient from the medical records; store the extracted patient identity and historical medical data in the elastic search engine; If the information pushed by the hospital information system contains updated or new patient information, update the elastic search index record; Dynamically extract information about the patient's chief complaint, drug allergy history, past medical history, family history, diagnosis and treatment opinions from the medical conversation text through the outpatient medical template; Medical connotations are compared through the drug allergy dictionary, medical history dictionary, family history dictionary, and drug allergy history, past medical history, and family history found in the elastic search engine library. If the drug allergy names of the drug allergy history, the names of the diseases in the medical history, and the names of the genetic diseases in the family history expressed in the two texts are the same, the drug allergy history, past medical history, and family history information of the patient that have been brought in will not be overwritten; If the main information of drug allergy history, past medical history, and family history is inconsistent, the patient's latest result shall prevail, covering the drug allergy history, past medical history, and family history information that have been entered.

2. According to claim 1, a method for intelligently entering outpatient medical records is characterized in that: It also includes obtaining the doctor's voice instructions for operating the outpatient medical record, and modifying or confirming the outpatient medical record according to the voice instructions; Synchronize the patient's final outpatient medical record to the hospital's electronic medical record system and update the patient index record of the elastic search search engine.

3. An intelligent outpatient medical record entry system, characterized in that: include: A patient information database construction module is used to construct a patient information database, wherein the patient information database includes patient medical record numbers and patient facial data; The face recognition module is used to perform face recognition on patients entering the outpatient department and match the patient's face data with the patient's medical record number through face recognition; The medical record document processing module is used to synchronize outpatient, inpatient and discharge medical records from the hospital information system according to the preset time, extract patient identity and medical data and store them in the search engine; Patient history information retrieval module, used to retrieve patient identity and historical medical data in the search engine using the patient medical record number as an index, and bring the retrieved patient identity and historical medical data into the outpatient medical record; The consultation conversation processing module is used to convert the voice conversation between the doctor and the patient into the consultation conversation text through voice recognition, extract the patient's current consultation information from the consultation conversation text, and bring the extracted patient's current consultation information into the outpatient medical record; In the patient information database construction module, the patient information database stores patient facial data of patients with historical medical visits; In the face recognition module, when the patient visits the doctor again, the face feature value is scanned, and the scanned face feature value is matched with the patient face data in the patient information database. If the match is successful, the patient's medical record number is returned; If the match is successful, the patient's name, age, ID number, gender and consultation time will also be returned; In the medical record document processing module, outpatient, inpatient and discharge medical record documents are synchronized from the hospital information system on a regular basis every day; medical record documents are sorted in reverse order of patient registration time, and the latest patient identity and historical medical data of each patient are extracted from the medical record documents; the extracted patient identity and historical medical data are stored in the elastic search search engine; In the medical consultation processing module, the patient's chief complaint information, drug allergy history information, past medical history information, family history information, diagnosis information and treatment opinions are dynamically extracted from the medical consultation text through the outpatient medical template; In the consultation conversation processing module, the medical connotation is compared through the drug allergy dictionary, medical history dictionary, family history dictionary, and the drug allergy history, past medical history, and family history found from the elastic search engine library. If the drug allergy name of the drug allergy history, the disease name in the medical history, and the genetic disease name in the family history expressed in the two texts are consistent, the drug allergy history, past medical history, and family history information of the patient that have been brought in will not be overwritten; In the medical consultation processing module, if the main information of drug allergy history, past medical history, and family history is inconsistent, the patient's latest result shall prevail, covering the drug allergy history, past medical history, and family history information that have been brought in.

4. The intelligent outpatient medical record entry system according to claim 3, characterized in that: It also includes an operation voice processing module for obtaining the doctor's operation voice instructions for the outpatient medical record, and modifying or confirming the outpatient medical record according to the operation voice instructions; It also includes an information update module, which is used to update the elastic search index record if there is an update or new patient information in the information pushed by the hospital information system; The information update module is also used to synchronize the patient's final outpatient medical record to the hospital's electronic medical record system and update the patient index record of the elastic search search engine.

Images