CN110570916A - diagnosis assistance method, system, device and storage medium - Google Patents
diagnosis assistance method, system, device and storage medium Download PDFInfo
- Publication number
- CN110570916A CN110570916A CN201910749007.6A CN201910749007A CN110570916A CN 110570916 A CN110570916 A CN 110570916A CN 201910749007 A CN201910749007 A CN 201910749007A CN 110570916 A CN110570916 A CN 110570916A
- Authority
- CN
- China
- Prior art keywords
- information
- patient
- service window
- face information
- comparing
- 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
Classifications
-
- 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
-
- 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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- 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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
-
- 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Abstract
The invention relates to the technical field of artificial intelligence, and provides a diagnosis assisting method, a system, a device and a storage medium. The method comprises the following steps: registering and collecting the identity and face information of a patient, and pushing the collected information to a clinic; acquiring face information of the office of the doctor again, comparing the face information with the pushed information, and inquiring if the face information is consistent with the pushed information; if not, confirming offline; during inquiry, voice recording is carried out on the communication process between a doctor and a patient, keywords recorded by the voice are extracted and compared with a pre-established disease database, and then a disease report and a medication scheme are output; pushing all information to a service window needing to be continued; and acquiring and comparing the face information of the service window, if the face information of the service window is consistent, performing a service window program, and if the face information of the service window is inconsistent, performing offline confirmation. By using the invention, the efficiency of seeing a doctor can be improved, the accuracy of medication can be improved, and disputes between doctors and patients can be reduced.
Description
Technical Field
the invention relates to the technical field of artificial intelligence, in particular to a diagnosis assisting method, a diagnosis assisting system, a diagnosis assisting device and a storage medium.
Background
In the process of acquiring patient information by outpatient doctor sitting diagnosis, the condition of a patient needs to be recorded by handwriting while communicating with the patient, then the cause of disease is deduced according to the recorded condition of the patient, and then the cause of disease is recorded by handwriting, so that the process takes a long time for the doctor and has low working efficiency; moreover, depending on the patient's condition, the physician may need to spend a certain amount of time analyzing the condition and not be able to give a proper medication plan if they encounter difficult and complicated conditions. In addition, in the communication process between the doctor and the patient, the doctor only carries out the patient condition record by handwriting, no conversation record is formed, and if a medical accident occurs, a conversation evidence is difficult to find, so that doctor-patient disputes occur.
disclosure of Invention
the invention aims to provide a diagnosis assisting method, a diagnosis assisting system, a diagnosis assisting device and a storage medium, so that the diagnosis efficiency and the medication accuracy are improved, and doctor-patient disputes are reduced.
the above purpose is realized by the following technical scheme:
According to one aspect of the present invention, the present invention provides a method for assisting medical treatment, applied to an electronic device, including:
Acquiring identity information and face information of a patient, completing registration, pushing the acquired information to a clinic and automatically queuing;
based on the face recognition technology, acquiring face information of the patient in the clinic again, comparing the face information with the information acquired during registration, and if the face information is inconsistent with the information acquired during registration, performing offline confirmation; if the communication is consistent, performing inquiry, and performing voice recording on the communication process of the doctor and the patient;
Extracting keywords recorded by voice, comparing the keywords with a pre-established disease database, and outputting a disease report and a medication scheme;
pushing the medication scheme and the acquired information to a next service window to be performed; acquiring the face information of the service window and comparing the face information with the information pushed by the clinic; and if the two are consistent, performing the service window program, and if the two are not consistent, performing offline confirmation.
Preferably, the steps of extracting keywords recorded by voice, comparing the keywords with a pre-established disease condition library, and outputting a disease condition report and a medication scheme comprise: performing word segmentation processing on the dialogue content recorded by the voice by using a word segmentation technology to obtain a plurality of words; calculating the TF-IDF value of each word through a TF-IDF algorithm, and sequencing all the words according to the sequence of the TF-IDF values from large to small; taking a plurality of preset words with the TF-IDF value ranked at the top as keywords of the belonged disease condition content, and extracting; and comparing the extracted keywords with the keywords of each disease condition of the clinic in the disease condition library by using an NLP (non line segment) word vector technology, calculating the similarity, outputting three disease condition reports with the highest similarity to assist a doctor to determine the final disease condition, and outputting a medicine taking scheme corresponding to the final disease condition. More preferably, the preset number is 2-10, namely 2-10 words with the TF-IDF value ranked at the top are taken as keywords of the disease condition content and extracted.
Preferably, the service window is one or more of a payment window, a medicine taking chamber and an instrument detection chamber.
Preferably, after the service window program is executed, the method further includes: and pushing the information collected by the service window and the generated information back to the clinic for continuous treatment.
Preferably, the step of performing offline confirmation includes: verifying identity information of the queuing personnel at the service window; and acquiring identity information and face information of queuing personnel at the service window.
preferably, the method further comprises: continuing to push the information generated by the service window and the acquired information to the next service window after the service window program is finished; and acquiring the face information of the next service window and comparing the face information with the pushed information.
Preferably, the method further comprises: and after the respective procedures of the department of medical treatment or the service window are finished, transferring the generated information and the acquired information to a history library for storage.
According to another aspect of the present invention, there is provided a visit support system, the system comprising: the information acquisition unit is used for acquiring patient identity information and face information during registration, treatment, instrument detection, payment, medicine taking and medicine taking, and/or identity information and face information of a payer and a medicine taking person; the pushing unit is used for pushing the information collected by the previous service window/clinic to the next service window/clinic; the information comparison unit is used for comparing the collected information with the pushed information; the diagnosis and inquiry unit is used for recording the communication process between the doctor and the patient by voice, extracting keywords through NLP, comparing the keywords with a pre-established disease database and outputting a disease report and a medication scheme; and the history storage unit is used for storing all the information generated and collected by the clinic or the service window.
According to still another aspect of the present invention, there is provided an electronic apparatus, including: a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program performs the steps of the method for assisting a medical visit as described above.
According to yet another aspect of the present invention, there is also provided a computer-readable storage medium, including a computer program, which, when executed by a processor, implements the steps of the diagnosis assistance method as described above.
Has the advantages that: according to the auxiliary method, the system, the device and the storage medium for seeing a doctor, face recognition is adopted to conduct face acquisition in the whole seeing a doctor process (such as registration, seeing a doctor and asking a doctor, instrument detection, payment, medicine taking and the like), and the face acquisition is compared with information acquired in the last service window, so that the patient in the whole seeing a doctor process is guaranteed to be the same person, the patient and the state of an illness are unified, and the problems that a medical insurance card is falsely used by a person and the like are avoided. And moreover, the face recognition technology is adopted, so that paper bills do not need to be printed in the treatment process, and if the sales are required to be reimbursed, the printing can be completed through face recognition at a counter/self-service machine after the treatment is finished, so that the treatment time is saved, and the treatment efficiency is improved.
The invention combines face recognition and audio recording when in treatment and inquiry, extracts keywords recorded by voice through NLP, compares the keywords with a pre-established disease database, and automatically outputs a disease report and a medication scheme, thereby assisting a doctor to make a judgment, saving the inquiry time of the doctor, improving the inquiry efficiency and improving the medication accuracy. Moreover, mutual repudiation can be avoided by combining face recognition and audio recording, and misdiagnosis and doctor-patient disputes are reduced to a certain extent.
Drawings
other objects and results of the present invention will become more apparent and more readily appreciated as the same becomes better understood by reference to the following description taken in conjunction with the accompanying drawings. In the drawings:
FIG. 1 is a schematic flow chart of a method of assisting medical treatment according to an embodiment of the present invention;
Fig. 2 is a schematic structural diagram of a diagnosis support system according to an embodiment of the present invention.
Detailed Description
The embodiments of the present invention will be described below with reference to the accompanying drawings. Those of ordinary skill in the art will recognize that the described embodiments can be modified in various different ways, or combinations thereof, without departing from the spirit and scope of the present invention. Accordingly, the drawings and description are illustrative in nature and are only intended to illustrate the invention and not to limit the scope of the claims. Furthermore, in the present description, the drawings are not to scale and like reference numerals refer to like parts.
fig. 1 schematically shows a flow chart of a diagnosis assistance method, and as shown in fig. 1, the diagnosis assistance method provided by the present invention includes:
And step S1, acquiring the identity information and the face information of the patient, completing registration, pushing the acquired information to a clinic and automatically queuing. Wherein the office of visiting a doctor is the office hung during registration.
Step S2, acquiring the face information of the patient in the clinic again based on the face recognition technology (at the time of clinic visit), comparing the face information with the information acquired at the time of registration, and if the face information is consistent with the information acquired at the time of registration, inquiring and recording the voice of the communication process between the doctor and the patient; if not, an offline confirmation is performed. E.g., off-line with a nurse on the office to verify identity, etc.
And step S3, extracting keywords of the voice record, comparing the keywords with a pre-established disease database, and outputting a disease report and a medication scheme. Meanwhile, the final disease condition and the corresponding medication scheme are recorded in a patient database, and the patient database can be established for each patient during inquiry; when recording the voice, converting the voice into text information in real time, encrypting and storing the text information into a patient database; after comparison, several disease reports, for example 3-5, are output to assist the doctor in determining the final disease, and the output medication scheme corresponds to the final disease.
And step S4, pushing the medication scheme and the collected information to a service window needing to be carried out next, collecting the face information of the service window, comparing the face information with the information pushed by the office of treatment, carrying out the service window program if the face information is consistent with the information, and carrying out offline confirmation if the face information is inconsistent with the information.
According to the auxiliary method for seeing a doctor, the face information of the relevant person is collected at each service window and is compared with the information pushed by the last service window, and the procedure of the service window can be carried out only after the comparison is passed, so that the patient is ensured to be the same person in the whole seeing a doctor process, the patient and the state of an illness are unified, the problems that a medical insurance card is falsely used by a person and the like are avoided, various documents are prevented from being printed, and the time is saved; and face recognition and audio recording are combined in the inquiry process, so that the consistency of voice recording in the inquiry process of the patient and the doctor is ensured, mutual repudiation can be avoided, and misdiagnosis and doctor-patient disputes can be reduced to a certain extent.
in step S1, the identity information collected during registration includes the name, identification number, etc. of the patient, and then the patient is subjected to face collection, and the patient face picture information is bound with the medical insurance card/hospital visit card, so that registration is completed, and the patient can check the health of the medical insurance card, and the medical insurance card is prevented from being falsely used by the patient. The patient registers with the social security card for the first time in a hospital, needs to check the body by a testimony, and registers with the face recognition after the body passes through the testimony. And then, the acquired information is pushed to the corresponding clinic and automatically queued, so that the follow-up procedures of inquiry, medicine taking and the like are facilitated, and the unification of the patient and the state of an illness is ensured. For example, in the inquiry of step S2, the face recognition is performed again on the patient in the office of the doctor, and it is checked whether the information is consistent with the information of the patient collected during registration, and whether the information is the same person, so as to avoid the problem that the medical insurance card is falsely used by the person. And if the medicine is taken, the patient and/or the person taking the medicine finishes taking the medicine by comparing the face through the medical insurance card/the treatment card and the face identification. Thus, the face recognition verification in the whole process of treatment (including registration, inquiry, medicine taking and the like) is realized, and the patients and the state of illness are unified.
In step S2, during the inquiry, voice recording is required for the communication process between the doctor and the patient. The voice recording mode may be a separate recording mode, such as a microphone for each of the doctor and the patient, but is not limited thereto, and may also be a combination of recording and video. The recorded conversation content can be converted into related text information in real time for archiving, an audio file of voice recording is generated in the whole treatment process of a patient and is stored in a database of the patient, and the audio file storage format is pcm. During the communication process between the doctor and the patient, the words are converted into words after the answering is finished each time until the inquiry is finished, and the words and the audio files are subjected to Hash signatures and aes encryption storage.
preferably, before the voice recording, the method further comprises: and (3) performing language identification on doctors and/or patients, and then matching corresponding languages to improve the accuracy of voice recording. For example, the languages may include Chinese, English, etc.; preferably, a plurality of dialects, especially dialects which are greatly different from the characteristics of the Mandarin language, can be configured, so that the accuracy of voice recording is further improved.
Preferably, template inquiry is adopted in the communication process between the doctor and the patient, so that the follow-up comparison with keywords in a pre-established disease database is facilitated, and the accuracy of keyword extraction is improved. For example: 1. where it is uncomfortable; 2 or more times; 3. there is no other place to be uncomfortable; 4. a similar situation has been previously experienced, etc. Preferably, a template corresponding to the inquiry is adopted in the disease database to record each disease condition, so that comparison is convenient and comparison accuracy is improved.
Preferably, in the step of extracting the keywords of the voice record in step S3, comparing the keywords with a pre-established disease condition library, and outputting a disease condition report and a medication scheme, the extracting the keywords of the voice record by NLP includes: firstly, performing word segmentation processing on the dialogue content recorded by the voice by using a word segmentation technology to obtain a plurality of words, calculating a TF-IDF value of each word by using a TF-IDF algorithm, and sequencing all the words according to the sequence of the TF-IDF values from large to small; among them, TF-IDF (Term Frequency-Inverse Document Frequency) is a common weighting technique used for information retrieval and data mining, TF is Term Frequency (Term Frequency), IDF is Inverse Document Frequency (Inverse Document Frequency); then, 2-10 words with the TF-IDF value ranked at the top are determined as keywords of the disease condition content, and extraction is carried out; then, the word segmentation result (extracted keywords/words) is compared with the keywords of the illness state of the department in the illness state library for inquiry, each illness state is established for comparison with the department by utilizing an NLP word vector technology, similarity calculation is carried out, and the top3 with the highest similarity is found and recommended to a doctor; finally, the doctor decides the final disease condition with the maximum possibility, and automatically outputs a medication scheme corresponding to the final disease condition after the doctor confirms the final disease condition; step S4 is then performed. In the above process, the final disease condition and the corresponding medication scheme are recorded in the patient database, and after the inquiry is finished, the patient database (including the identity information, the voice record, the final disease condition, the medication scheme and the like of the patient) is transferred to the history library for storage. The medication scheme comprises the types of medicines, cautions, medication rules, medication cycles and the like. Calculating the similarity by adopting cosine similarity, wherein the cosine similarity is the measurement for measuring the difference between two individuals by using the cosine value of the included angle between two vectors in a vector space; when the cosine of the vector included angle of the two individuals is equal to 1, the two individuals are completely the same; when the cosine value of the included angle is close to 1, the two individuals are similar; the smaller the cosine of the angle, the less correlated the two individuals are.
Preferably, pre-establishing a library of conditions comprises: establishing disease types of each department; establishing keywords associated with various disease types; establishing a medication scheme corresponding to the disease condition type. Wherein the keywords associated with each disease category include: the cause (etiology), symptoms (clinical manifestations), and severity of the disease condition. Some keywords in the gastrointestinal family are for example: the key words such as uncomfortable stomach, stomachache and belly pulling are adopted. Preferably, the medication plan is set in association with the disease condition type, so that a doctor does not need to inquire one more time, and after the final disease condition and the severity are confirmed, the system directly outputs a corresponding medication scheme, thereby saving thinking time of the doctor and improving diagnosis efficiency and medication accuracy. Wherein, doctors can also simply adjust according to the medication scheme and the specific situation of patients so as to improve the medication accuracy.
In an optional embodiment, after the performing the service window procedure, the method further includes: and pushing the information collected and generated by the service window back to the clinic for continuous treatment. For example, the patient information collected by the department of treatment is pushed to the instrument detection room, the face information of the patient in the instrument detection room is collected, and the face information is compared with the information pushed by the department of treatment. If the medical conditions are consistent with the medical conditions, performing instrument detection, and pushing the detection result of the instrument back to the clinic room for further verification of the disease condition report and the medication scheme; if not, an offline confirmation is performed. Specifically, when the patient needs to be further judged by an instrument in an inquiry process, relevant data (faces, names, certificate numbers and the like) of the patient can be pushed to a corresponding instrument detection room, such as a B-ultrasonic room, an x-ray examination room and the like, the face information of the patient is collected before the examination and compared with the faces of the patients pushed by a clinic, the data such as the names of the patients are displayed when the comparison is consistent, when the comparison is not passed, a worker needs to check the identity information of the patient offline, after the comparison is passed, the picture of the patient is collected, after the examination is completed, a corresponding diagnosis analysis conclusion is pushed to a doctor mainly treating the patient, and the face information of the current patient is removed from a face library of the instrument detection room to a history library for storage. The doctor can be assisted to make a final scheme through the steps, and the diagnosis accuracy rate is indirectly improved. During instrument detection, face recognition is adopted for checking, and the condition that partial patients without diseases require the patients to check so as to obtain improper benefit such as collection and social security reimbursement is avoided.
The service window in step S4 may be one or more of a payment window, a medicine taking window, a medicine administration room, an instrument detection room, and the like. For example, the medication scheme and the acquired information are simultaneously pushed to a payment window, a medication taking window, a medication room and the like, and the accuracy of the whole treatment process is further improved by acquiring the faces at each service window and comparing the faces with the previous service window/treatment department.
In an optional embodiment, the method further comprises: the payment window receives the medication scheme pushed by the doctor department and the acquired information; automatically acquiring the face information of a person who queues in a payment window, comparing the face information with the face information pushed by a clinic, and when the comparison is passed, paying the fee by the patient according to the name information of the patient displayed on the display screen and the payment amount; and if the identity of the payer is inconsistent, verifying the identity of the payer, acquiring the identity information and the face information of the payer, and paying the fee by the payer according to the name of the patient and the payment amount displayed by the display screen. After the payment is successful, the information of the patient, the payer, the medication scheme and the like is pushed to a next service window, such as a medicine taking window. And then transferring the payment list and the collected related face information to a history library for storage.
In an optional embodiment, the method further comprises: the medicine taking window receives all face information pushed by the payment window; collecting face information of a person who gets the medicine at the medicine taking window, comparing the face information with all face information pushed by the payment window, and displaying information such as names on a display screen when the comparison is passed; when the comparison fails, verifying the identity of the person who gets the medicine, acquiring the identity information and the face information of the person who gets the medicine after the verification passes, and then sending the medicine; and push the medication plan and patient information to the next service window, such as a medication room, wherein the medication plan includes: the dosage and period of administration of the medicine, etc. And after pushing, transferring the medication plan generated by the patient and the acquired information to a history library for storage.
In an optional embodiment, the method further comprises: receiving face information of a patient pushed by a medicine taking window by a medicine room; collecting face information of a patient in a pharmacy, comparing the face information with all information pushed by a medicine taking window (mainly comparing the face information of the patient), and displaying information such as names on a display screen when the face information passes the comparison; when the comparison fails, the identity card information needs to be provided, and the medication service can be provided for the patient only after the manual check passes, so that the occurrence of medical accidents is reduced.
In the whole treatment process, the comparison results are consistent, which generally means that the information of the patients is consistent, namely the patients in the treatment process are the same person; in special cases, for example, when taking medicine, the consistency of the comparison result can also refer to the consistency of the person who takes medicine and the payer, so that the repeated verification of the identity of the person is avoided, and the time for seeing a doctor is saved.
Fig. 2 schematically shows the structure of the visit assisting system of the embodiment of the present invention. As shown in fig. 2, the visit support system includes: the system comprises an information acquisition unit 10, a pushing unit 20, an information comparison unit 30, a visit inquiry unit 40 and a history storage unit 50.
The information acquisition unit 10 is used for acquiring patient identity information and face information during registration, treatment, instrument detection, payment, medicine taking and medicine taking, and/or identity information and face information of a payer and a medicine taking person. When the non-patient pays and takes the medicine, the identities of the payer and the medicine taker need to be verified for verification, and after the verification is passed, identity information and face information are collected so as to facilitate follow-up inquiry.
And the pushing unit 20 is configured to push the information collected in the previous service window/clinic to the next service window/clinic. In the system, the information acquired by the information acquisition unit 10 at each time needs to be pushed to the next service window, so that the next service window can be compared conveniently, and the unification of the patient and the state of illness is ensured. The content pushed by the pushing unit 20 includes identity information and face information of related persons, and also includes information generated after each service window program is finished, for example, information such as medication schemes, payment documents, medication plans, medication effects, and the like.
And the information comparison unit 30 is used for comparing the information collected by the consulting department or the service window with the pushed information. Including comparing patient information, payer information, or drug taker information, etc. If the comparison result is consistent, the program of the service window can be executed; otherwise, offline confirmation is required, for example, the payment window is not the patient himself, the attendant nurse is required to verify the identity of the payment person, and if the verification is passed, the identity of the payment person and the face information are required to be acquired through the information acquisition unit 10.
the visit inquiry unit 40 is used for recording the communication process between the doctor and the patient by adopting voice or voice and video, extracting keywords through NLP, comparing the keywords with a pre-established disease database, and outputting a disease report and a medication scheme. In order to assist the doctor in determining the final disease condition, the visit inquiry unit 40 further includes: the instrument detection unit acquires the face information, compares the face information with the information pushed by the department in clinic, detects the instrument after the face information is consistent with the information pushed by the department in clinic, and pushes the detection result of the instrument back to the department in clinic so as to assist a doctor in determining the final state of an illness. Preferably, the following steps are performed in the visit interrogation unit 40: recording the communication process between the doctor and the patient by voice; segmenting the dialogue content recorded by the voice by utilizing a segmentation technology; calculating the TF-IDF value of each word through a TF-IDF algorithm, and sequencing from big to small; taking 2-10 words with the TF-IDF value ranked at the top as keywords of the disease condition content, for example, 5 words, and extracting the words; and comparing the extracted keywords with the keywords of each disease condition of the department in the disease condition library by using an NLP (non line segment) word vector technology, calculating the similarity, outputting three disease condition reports with the highest similarity to assist a doctor to determine the final disease condition, and outputting a medicine taking scheme corresponding to the final disease condition. Preferably, the recording is performed using a voice system, and the recording process includes: the system comprises voice receiving, voice recognition, voice recording, character conversion and the like, wherein the language of a patient and/or a doctor needs to be recognized in the voice recognition, a plurality of languages such as Chinese, English and the like are matched in a voice system, and the corresponding languages are automatically matched according to the language characteristics of the patient and/or the doctor so as to be recorded accurately. Preferably, a plurality of dialects, especially dialects with a great difference from the mandarin language feature, can be arranged in the voice system, so that the accuracy of voice recording is further improved.
A history saving unit 50 for saving all information generated and collected by the office or service window. The patient database can be established by the consulting department before the inquiry, the voice is converted into characters and stored in the patient database in the inquiry process, the determined final illness state and the medication scheme are also stored in the patient database, and the patient database is moved to the history database for storage after the inquiry is finished. After the programs of the window or department are executed by other service windows or departments, all the information generated and collected by the windows or departments is transferred to the historical library for subsequent inquiry, thereby reducing doctor-patient disputes to a certain extent.
the electronic device provided by the invention can be a television, a smart phone, a tablet computer, a computer and other terminal equipment. The electronic device includes: a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the present invention, when executing the computer program.
Illustratively, a computer program may be partitioned into one or more modules/units, which are stored in a memory and executed by a processor to implement the present invention. One or more modules/units may be a series of computer program instruction segments capable of performing certain functions, which are used to describe the execution of a computer program in an electronic device. For example, the consultation assistance program may be divided into the information acquisition unit 10, the push unit 20, the information comparison unit 30, the consultation inquiry unit 40, and the history storage unit 50 in the consultation assistance system. The functional role of which is described in detail above, is not repeated herein.
the steps of the method for assisting medical treatment according to the present invention when executed by a processor are similar to the above, and are not described in detail herein, for example, the following steps are performed:
Acquiring identity information and face information of a patient to complete registration; and pushing the acquired information to the corresponding office and automatically queuing.
based on the face recognition technology, acquiring face information of the patient in the clinic again, comparing the face information with the information acquired during registration, and performing inquiry if the face information is consistent with the information acquired during registration, wherein during inquiry, voice recording (or voice and video) is performed on the communication process between the doctor and the patient; if not, an offline confirmation is performed.
Extracting keywords of the voice record by adopting NLP, comparing the keywords with a pre-established disease database, and outputting three disease reports with highest similarity and a final disease medication scheme through similarity calculation; and pushing the medication scheme and the collected information to a payment window after the inquiry is finished.
Automatically acquiring face information of queuing people at a payment window according to the queuing sequence, and comparing the face information with information pushed by a doctor; if the patient name and the payment amount are consistent, the payment is carried out according to the patient name and the payment amount displayed on the display screen; if the identity of the payer is inconsistent, verifying the identity of the payer, collecting the identity information and the face information of the payer, and paying according to the name and the payment amount of the patient and/or the payer displayed on the display screen; and after the payment is successful, pushing information of the patient, the payer and the like to the medicine taking window.
collecting face information of a medicine taker at a medicine taking window, and comparing the face information with all face information pushed by a payment window and a clinic for treatment; if the comparison is passed, sending the medicine; if the comparison fails, verifying the identity of the person who gets the medicine, acquiring the identity information and the face information of the person who gets the medicine after the verification passes, and then sending the medicine; after the medicine is sent, the medication plan and all the collected information are pushed to the medication room.
Acquiring the face information of a patient in a medicine taking room, and comparing the face information with the face information of the patient pushed by a medicine taking window and a clinic; if the two are consistent, the medication service is carried out; if not, an offline confirmation is performed.
wherein, when the inquiry, when the doctor needs the supplementary judgement of instrument, still include: pushing the relevant data of the patient to a corresponding instrument detection room, such as a B-ultrasonic room, an X-ray examination and the like, acquiring the face information of the patient before the examination, comparing the face information with the face of the patient pushed by a doctor room, displaying the data of the name and the like of the patient when the face information is consistent with the face information, and carrying out instrument detection; when the checking fails, the staff is required to check the identity information of the patient offline, and after the checking passes, the picture of the patient is collected for instrument detection; and after the examination is finished, pushing the obtained diagnosis and analysis conclusion to the main doctor of the patient to assist the main doctor to further judge the disease condition, and removing the face information of the current patient from the face library of the instrument detection room to the historical library.
The Processor may be a Central Processing Unit (CPU), or may be other general-purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, a discrete hardware component, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may be an internal storage unit of the electronic device, such as a hard disk or a memory of the electronic device. The memory may be an external storage device of the electronic apparatus, such as a plug-in hard disk provided on the electronic apparatus, a Smart Memory Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like. Further, the memory may also include both an internal storage unit and an external storage device of the electronic apparatus. The memory is used for storing computer programs and other programs and data required by the electronic device. The memory may also be used to temporarily store data that has been output or is to be output.
In the computer-readable storage medium provided by the present invention, the computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, the steps of the diagnosis assisting method and the functions of the diagnosis assisting reminding units of the present invention are implemented, and are not described herein again in order to avoid repetition.
In an alternative embodiment, a computer readable storage medium may be any tangible medium that can contain, or store a program or instructions, where the program can be executed to implement corresponding functions via hardware in association with stored program instructions. For example, the computer readable storage medium may be a computer diskette, hard disk, random access memory, read only memory, or the like. The invention is not so limited and can be any means that stores the instructions or software and any associated data files or data structures in a non-transitory manner and that can be provided to a processor to cause the processor to execute the programs or instructions therein. The computer-readable storage medium includes a diagnosis and treatment plan recommendation program, and when the diagnosis and treatment plan recommendation program is executed by the processor, the diagnosis and treatment plan recommendation method is implemented, and is not described herein again to avoid repetition.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments. Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A diagnosis assisting method is applied to an electronic device and is characterized by comprising the following steps:
Acquiring identity information and face information of a patient, completing registration, pushing the acquired information to a clinic and automatically queuing;
Based on the face recognition technology, acquiring face information of the patient in the clinic again, comparing the face information with the information acquired during registration, and if the face information is inconsistent with the information acquired during registration, performing offline confirmation; if the communication is consistent, performing inquiry, and performing voice recording on the communication process of the doctor and the patient;
Extracting keywords recorded by voice, comparing the keywords with a pre-established disease database, and outputting a disease report and a medication scheme;
Pushing the medication scheme and the acquired information to a service window which needs to be carried out next, acquiring the face information of the service window and comparing the face information with the information pushed by the clinic; and if the two are consistent, performing the service window program, and if the two are not consistent, performing offline confirmation.
2. The medical assistance method as claimed in claim 1, wherein the step of extracting the keywords recorded in the voice and comparing the keywords with a pre-established patient database to output a patient report and a medication scheme comprises:
performing word segmentation processing on the dialogue content recorded by the voice by using a word segmentation technology to obtain a plurality of words;
Calculating the TF-IDF value of each word through a TF-IDF algorithm, and sequencing all the words according to the sequence of the TF-IDF values from large to small;
Taking a plurality of preset words with the TF-IDF value ranked at the top as keywords of the belonged disease condition content, and extracting;
and comparing the extracted keywords with the keywords of each disease condition of the clinic in the disease condition library by using an NLP (non line segment) word vector technology, calculating the similarity, outputting three disease condition reports with the highest similarity to assist a doctor to determine the final disease condition, and outputting a medicine taking scheme corresponding to the final disease condition.
3. The visit support method of claim 1 wherein the service window is one or more of a payment window, a medication room, and an instrument detection room.
4. The visit assistance method of claim 1, further comprising, after performing the service window procedure: and pushing the information collected and generated by the service window back to a clinic for continuous treatment.
5. The visit support method of claim 1, wherein the step of performing an offline confirmation comprises: verifying identity information of the queuing personnel at the service window; and acquiring identity information and face information of queuing personnel at the service window.
6. The visit support method of claim 1, wherein the method further comprises:
After the service window program is finished, continuously pushing the information generated by the service window and the collected information to the next service window; and
And acquiring the face information of the next service window and comparing the face information with the pushed information.
7. the visit support method of claim 1, further comprising:
And after the respective procedures of the department of medical treatment or the service window are finished, transferring the generated information and the acquired information to a history library for storage.
8. A visit support system, the system comprising:
The information acquisition unit is used for acquiring patient identity information and face information during registration, treatment, instrument detection, payment, medicine taking and medicine taking, and/or identity information and face information of a payer and a medicine taking person;
The pushing unit is used for pushing the information collected by the previous service window/clinic to the next service window/clinic;
The information comparison unit is used for comparing the collected information with the pushed information;
the diagnosis and inquiry unit is used for recording the communication process between the doctor and the patient by voice, extracting keywords through NLP, comparing the keywords with a pre-established disease database and outputting a disease report and a medication scheme;
and the history storage unit is used for storing all information generated and collected by the clinic and each service window.
9. An electronic device, the electronic device comprising: memory, processor and computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the visit support method according to any of the claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, comprising a computer program which, when executed by a processor, carries out the steps of the visit support method as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910749007.6A CN110570916A (en) | 2019-08-14 | 2019-08-14 | diagnosis assistance method, system, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910749007.6A CN110570916A (en) | 2019-08-14 | 2019-08-14 | diagnosis assistance method, system, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110570916A true CN110570916A (en) | 2019-12-13 |
Family
ID=68775457
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910749007.6A Pending CN110570916A (en) | 2019-08-14 | 2019-08-14 | diagnosis assistance method, system, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110570916A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111402985A (en) * | 2020-02-28 | 2020-07-10 | 华中科技大学同济医学院附属协和医院 | Hospitalization report writing system and use method thereof |
| CN111508580A (en) * | 2020-03-31 | 2020-08-07 | 创业慧康科技股份有限公司 | Nuclear medicine patient reception method, system and device based on face recognition |
| CN113113094A (en) * | 2021-03-15 | 2021-07-13 | 广州零端科技有限公司 | Medical information processing method, system, device and medium based on face recognition |
| CN113536110A (en) * | 2021-06-09 | 2021-10-22 | 四川数字链享科技有限公司 | Medical information pushing system based on big data |
| CN115497615A (en) * | 2022-10-24 | 2022-12-20 | 王征 | Remote medical treatment method and system |
| CN116344009A (en) * | 2023-05-22 | 2023-06-27 | 武汉盛博汇信息技术有限公司 | Online diagnosis notification method and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106650261A (en) * | 2016-12-22 | 2017-05-10 | 上海智臻智能网络科技股份有限公司 | Intelligent inquiry method, device and system |
| CN107247868A (en) * | 2017-05-18 | 2017-10-13 | 深思考人工智能机器人科技（北京）有限公司 | A kind of artificial intelligence aids in interrogation system |
| CN107818823A (en) * | 2017-12-05 | 2018-03-20 | 成都法线网络科技有限公司 | A kind of artificial intelligence way of inquisition |
| CN108986908A (en) * | 2018-05-31 | 2018-12-11 | 平安医疗科技有限公司 | Interrogation data processing method, device, computer equipment and storage medium |
| CN109003648A (en) * | 2018-06-29 | 2018-12-14 | 北京大学口腔医学院 | Outpatient Service Stomatology speech electronic case history generation method and computer readable storage medium |
| CN109036544A (en) * | 2018-05-31 | 2018-12-18 | 平安医疗科技有限公司 | Medical information method for pushing, device, computer equipment and storage medium |
| CN109887557A (en) * | 2018-12-29 | 2019-06-14 | 北京天鹏恒宇科技发展有限公司 | A kind of pre- interrogation system of intelligent sound |
| CN208985713U (en) * | 2017-11-27 | 2019-06-14 | 重庆市中迪医疗信息科技股份有限公司 | Medical information system based on recognition of face |
-
2019
- 2019-08-14 CN CN201910749007.6A patent/CN110570916A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106650261A (en) * | 2016-12-22 | 2017-05-10 | 上海智臻智能网络科技股份有限公司 | Intelligent inquiry method, device and system |
| CN107247868A (en) * | 2017-05-18 | 2017-10-13 | 深思考人工智能机器人科技（北京）有限公司 | A kind of artificial intelligence aids in interrogation system |
| CN208985713U (en) * | 2017-11-27 | 2019-06-14 | 重庆市中迪医疗信息科技股份有限公司 | Medical information system based on recognition of face |
| CN107818823A (en) * | 2017-12-05 | 2018-03-20 | 成都法线网络科技有限公司 | A kind of artificial intelligence way of inquisition |
| CN108986908A (en) * | 2018-05-31 | 2018-12-11 | 平安医疗科技有限公司 | Interrogation data processing method, device, computer equipment and storage medium |
| CN109036544A (en) * | 2018-05-31 | 2018-12-18 | 平安医疗科技有限公司 | Medical information method for pushing, device, computer equipment and storage medium |
| CN109003648A (en) * | 2018-06-29 | 2018-12-14 | 北京大学口腔医学院 | Outpatient Service Stomatology speech electronic case history generation method and computer readable storage medium |
| CN109887557A (en) * | 2018-12-29 | 2019-06-14 | 北京天鹏恒宇科技发展有限公司 | A kind of pre- interrogation system of intelligent sound |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111402985A (en) * | 2020-02-28 | 2020-07-10 | 华中科技大学同济医学院附属协和医院 | Hospitalization report writing system and use method thereof |
| CN111508580A (en) * | 2020-03-31 | 2020-08-07 | 创业慧康科技股份有限公司 | Nuclear medicine patient reception method, system and device based on face recognition |
| CN113113094A (en) * | 2021-03-15 | 2021-07-13 | 广州零端科技有限公司 | Medical information processing method, system, device and medium based on face recognition |
| CN113536110A (en) * | 2021-06-09 | 2021-10-22 | 四川数字链享科技有限公司 | Medical information pushing system based on big data |
| CN115497615A (en) * | 2022-10-24 | 2022-12-20 | 王征 | Remote medical treatment method and system |
| CN115497615B (en) * | 2022-10-24 | 2023-09-01 | 北京亿家老小科技有限公司 | Remote medical method and system |
| CN116344009A (en) * | 2023-05-22 | 2023-06-27 | 武汉盛博汇信息技术有限公司 | Online diagnosis notification method and device |
| CN116344009B (en) * | 2023-05-22 | 2023-08-15 | 武汉盛博汇信息技术有限公司 | Online diagnosis notification method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110570916A (en) | diagnosis assistance method, system, device and storage medium | |
| US20210005297A1 (en) | Method and system for generating a medical report and computer program product therefor | |
| CN106529177B (en) | A kind of patient's portrait method and device based on medical big data | |
| CN104487972B (en) | A kind of various dimensions medication information processing method, system and equipment | |
| JP5952835B2 (en) | Imaging protocol updates and / or recommenders | |
| US20160103963A1 (en) | Method and system for smart healthcare management | |
| US20060178913A1 (en) | Medical and other consent information management system | |
| US20070027710A1 (en) | Method and system for automatically processing and evaluating medical data | |
| US7505867B2 (en) | System and method for predicting medical condition | |
| CN112331298A (en) | Method and device for issuing prescription, electronic equipment and storage medium | |
| KR20210015767A (en) | Subject candidate extraction method and subject candidate extraction system | |
| WO2021151302A1 (en) | Drug quality-control analysis method, apparatus, device, and medium based on machine learning | |
| CN112951414A (en) | Primary medical clinical assistant decision-making system | |
| CN113724830B (en) | Medication risk detection method based on artificial intelligence and related equipment | |
| US20160378922A1 (en) | Methods and apparatuses for electronically documenting a visit of a patient | |
| US20230028948A1 (en) | Generation of patient-specific content | |
| JP7388450B2 (en) | Conversation support device, conversation support system, conversation support method, and recording medium | |
| Whipple et al. | Piloting electronic case reporting for improved surveillance of sexually transmitted diseases in Utah | |
| Jayathissa et al. | Development of Minimum Clinical Data Set for Master Patient index for Sri Lankan Context | |
| CN111477322A (en) | Medical inquiry system | |
| CN112116976A (en) | Method and device for processing medicine information and computer readable storage medium | |
| KR102371738B1 (en) | Apparatus and method for producing drug code | |
| JP2019040624A (en) | Research information management system | |
| RU2701702C2 (en) | System and method for uniform comparison of unstructured recorded features with associated therapeutic features | |
| US20160162650A1 (en) | Method for automating medical billing |
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 |