CN117176894A - Medical care intercom system based on artificial intelligence - Google Patents
Medical care intercom system based on artificial intelligence Download PDFInfo
- Publication number
- CN117176894A CN117176894A CN202311257697.6A CN202311257697A CN117176894A CN 117176894 A CN117176894 A CN 117176894A CN 202311257697 A CN202311257697 A CN 202311257697A CN 117176894 A CN117176894 A CN 117176894A
- Authority
- CN
- China
- Prior art keywords
- audio
- engine
- call
- information
- account
- 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
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 45
- 230000003993 interaction Effects 0.000 claims abstract description 39
- 238000004891 communication Methods 0.000 claims abstract description 28
- 238000005516 engineering process Methods 0.000 claims abstract description 13
- 238000000034 method Methods 0.000 claims description 43
- 238000012545 processing Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 8
- 238000012546 transfer Methods 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 5
- 238000007689 inspection Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 201000010099 disease Diseases 0.000 abstract description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 3
- 238000001802 infusion Methods 0.000 description 5
- 239000003999 initiator Substances 0.000 description 5
- 230000000474 nursing effect Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000003252 repetitive effect Effects 0.000 description 2
- 208000019901 Anxiety disease Diseases 0.000 description 1
- 241001672694 Citrus reticulata Species 0.000 description 1
- 206010013954 Dysphoria Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000036506 anxiety Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Accommodation For Nursing Or Treatment Tables (AREA)
Abstract
The application discloses a medical intercom system based on artificial intelligence, which relates to the technical field of medical intercom systems and comprises the following steps: the server side pre-configures an AI virtual nurse, wherein the AI virtual nurse comprises: the system comprises an artificial intelligent dialogue engine, a voice interaction engine and a knowledge base, wherein a server side is in communication connection with a call terminal through an audio-video call engine, the audio-video call engine creates a special AI virtual nurse account and a corresponding one-key direct call account according to different departments, and the call terminal initiates a call request and selectively calls the AI virtual nurse account or the one-key direct call account. The application combines the audio and video communication technology and the digital personal technology, namely, an AI nurse is added to the disease area, the AI nurse is preferentially accessed when the patient calls, the AI nurse classifies the demands of the patient, the untreated event identification and the task issuing, the waiting time of the two parties is reduced, the AI nurse carries out dialogue when the patient calls, and different contents are recovered according to different demands of the patient.
Description
Technical Field
The application relates to the technical field of medical intercom systems, in particular to a medical intercom system based on artificial intelligence.
Background
The medical intercom system is one of hospital ward standard distribution systems, mainly solves the communication problem between inpatients and nursing and doctor, and the patient can pass through voice or video with nursing staff at a nurse station or doctor at a doctor office only by equipment installed at the head of a bed. The communication cost between the patient and the medical staff is very high before the medical intercom system is assembled, the illness state of the patient can be influenced, the life and the health of the patient can be seriously endangered, the development of the medical intercom system is subjected to a plurality of stages of calling bell, audio intercom and multimedia intercom, and each stage represents different technical paths.
Currently, the main stream is a multimedia intercom system, and the system integrates the functions of audio intercom, video intercom, electronic bedside card, expense inquiry list and the like. The user experience is better improved than that of the prior two-generation products, but the core problem in communication is not solved, and the problems of the working efficiency of medical staff calling the core function point and the feeling of the patient are solved. The specific problem points are as follows:
1. both parties are waiting during the call, the calling party (patient) is waiting for the called party to answer (nurse), and the called party (nurse) is busy waiting for answering.
2. Medical intercom is the most applied time period in the day in the morning in the peak period of infusion, wherein about 85% of calls inform infusion and change medicine, 5% of infusion abnormality needs nurse treatment, 9% is other item treatment or consultation, and 1% is the situation that emergency needs treatment, and life is influenced. Because infusion and dressing change occupy other 15% of important or urgent matters, if the efficiency of nursing staff is affected by call answering, bad attitude influence can be left for patients, and mental anxiety is not caused for patients, and serious medical disputes can be caused.
3. The event tasks are not automatically archived, so that forgetting or missing treatment is easy to cause serious medical adverse events or disputes, and even medical accidents can occur.
4. Tasks are difficult to correspond to a person. There is a call event total station tasked, but the total station is not managed by a dedicated person and thus is prone to cause missing of events or distortion of the transfer of content.
5. Most of the patient queries are repetitive and have standard answer questions, and at this time, the repetitive questions can cause the patient to feel dysphoria, and the final presentation to the patient is poor in attitude, so that disputes can be seriously caused.
For the problems in the related art, no effective solution has been proposed at present.
Disclosure of Invention
Aiming at the problems in the related art, the application provides an artificial intelligence-based medical intercom system to overcome the technical problems in the prior related art.
The technical scheme of the application is realized as follows:
an artificial intelligence based medical intercom system comprising the following steps:
the server side pre-configures an AI virtual nurse, wherein the AI virtual nurse comprises: the server establishes communication connection with the call terminal through the audio-video call engine, wherein the audio-video call engine creates a special AI virtual nurse account and a corresponding one-key direct call account according to different departments,
the calling terminal initiates a calling request and selectively calls an AI virtual nurse account or a one-key direct call account, wherein the method comprises the following steps:
if the current calling terminal initiates a call request to the AI virtual nurse account, the audio/video call engine establishes a call and accesses the AI virtual nurse instance to start business processing, wherein the method comprises the following steps:
when the calling terminal initiates a call, the information of a caller is sent to the audio-video communication engine, and after receiving the call information, the audio-video communication engine invokes an AI virtual nurse instance and synchronizes the caller information to the artificial intelligence dialogue engine;
the artificial intelligent conversation engine receives caller information, outputs welcome guide text content for calling in combination with preset content, sends the text content to the voice interaction engine, converts the text into audio information, and returns the audio information to the audio-video conversation engine;
the audio-video call engine sends the received audio information to the calling terminal for playing;
the calling terminal inputs statement audio to the AI virtual nurse according to the current guiding audio and sends the statement audio to the audio-video call engine;
the audio-video call engine receives the audio and forwards the audio to the voice interaction engine;
the voice interaction engine receives the audio frequency and then carries out voice recognition, converts the reply content of the caller into text information and sends the text information to the artificial intelligent dialogue engine;
after receiving the text information, the artificial intelligence dialogue engine carries out semantic understanding and intention analysis of calling people and carries out feedback reply or business processing on analysis intention according to preset rules, and the method comprises the following steps:
if the intention is the data in the artificial intelligent dialogue engine, the output result is sent to the voice interaction engine;
after receiving the text, the voice interaction engine converts the text into audio information and returns the information to the audio-video call engine;
the audio-video call engine receives the audio information and sends the audio information to the call terminal for playing;
if the intention is that the third party service system is required to inquire, calling a third party service system interface to process, and returning a processing result to the voice interaction engine;
the voice receives the inquiry result, converts the text into audio information, and returns the information to the audio-video call engine;
the audio-video call engine receives the audio information and sends the audio information to the call terminal for playing.
Further, the caller information includes: name, gender, bed number, and hospitalization number.
Further, the artificial intelligence dialog engine performs intent analysis, including the following steps:
when the calibration intention analysis result is that the transfusion is finished, the method comprises the following steps:
the method comprises the steps of sending reply content preset by an artificial intelligent dialogue engine to a voice interaction engine, converting text content into audio information, sending the audio information to an audio-video call engine, and sending the audio information to a calling terminal through the audio-video call engine;
the artificial intelligent dialogue engine calls a business service task creation interface to create a transfusion completion task containing a bed number, and informs a nurse interfacing the bed number through a business module.
Further, the artificial intelligence dialog engine performs intent analysis, including the following steps:
when the calibration intention analysis result is business consultation, the method comprises the following steps:
calling a local knowledge base and sending text contents to a voice interaction engine;
the text content is converted into audio information and sent to an audio-video call engine, and the audio-video call engine is used for sending the audio-video call engine to the calling terminal.
Further, the artificial intelligence dialog engine performs intent analysis, including the following steps:
when the calibration intention analysis result is the service inquiry, the method comprises the following steps:
the reply content preset by the artificial intelligence dialogue engine is sent to the voice interaction engine;
converting the text content into audio information, sending the audio information to an audio-video call engine, and sending the audio information to a call terminal through the audio-video call engine;
meanwhile, the artificial intelligent dialogue engine calls interfaces such as query cost query, inspection report and the like of the business service, inputs information query of a patient, sends a query result text to the voice interaction engine, converts text content into audio information, sends the audio information to the audio-video communication engine, and sends the audio-video information to the calling terminal through the audio-video communication engine.
Further, the artificial intelligence dialog engine performs intent analysis, including the following steps:
the calibration intention analysis result is that medical staff is searched, and the method comprises the following steps:
the method comprises the steps of sending reply content preset by an artificial intelligent dialogue engine to a voice interaction engine, converting text content into audio information, sending the audio information to an audio-video call engine, and sending the audio information to a calling terminal through the audio-video call engine;
meanwhile, the artificial intelligent dialogue engine calls an account query interface of a service staff;
when the business service returns to the account, calling a call transfer interface of the audio-video call engine, and inputting the returned account to call.
Further, the method also comprises the following steps:
and the calling terminal configures a current AI virtual nurse account and a corresponding one-key direct call account according to the audio and video call engine.
Further, the calling terminal calls further comprises the following steps:
the account called by the calling terminal is a one-key direct call account, and comprises the following steps:
the calling terminal sends an account number to be called to the audio-video call engine;
and the audio and video call engine receives the account number, then performs account number call, and performs audio and video call with the account number.
Further, the step of the call terminal selecting an AI virtual nurse account or a one-touch call account to make a call includes the following steps:
the server detects the connection state of the call terminal, wherein the method comprises the following steps:
when the connection with the service fails, the point-to-multipoint instruction transmission is realized through the network multicast technology, and the local machine transmits a broadcast packet with a set port number, a called account or group call account, and the instruction types are calling, local IP address information and calling information;
other devices in the local area network open the data monitoring of the set port;
the data packet contains the own equipment account number or group call account number, records the ID information of the opposite party, starts ringing and pops up the answering interface.
The application has the beneficial effects that:
according to the medical intercom system based on artificial intelligence, through creating a special AI virtual nurse account and a corresponding one-key direct call account in advance through an audio-video conversation engine according to a department, a call terminal selects the AI virtual nurse account or the one-key direct call account to call, if the account called by the call terminal is the AI virtual nurse, the conversation is accepted and answered by the AI virtual nurse, and the AI virtual nurse sends caller information to the artificial intelligence conversation engine; the artificial intelligent dialogue engine outputs preset information according to caller information; the artificial intelligent dialogue engine acquires the audio information output by the patient or the family, sends the audio information to the voice interaction engine, carries out voice recognition on the audio information of the patient or the family, and converts the audio information into text characters; the voice interaction engine does not receive the audio information of the calling terminal and exceeds the preset time, sends the identified text characters to the artificial intelligence dialogue engine for intention analysis and matching and replying, so that the medical care intercom system based on artificial intelligence is realized, the audio and video communication technology and the digital human technology are fused, that is, an AI nurse is added to a disease area, the AI nurse is preferentially accessed when a patient calls, the AI nurse classifies the demands of the patient, the untreated event identification and the task issuing, meanwhile, the waiting time of the two parties is shortened, the AI nurse carries out dialogue when the patient calls, and different contents are replied according to different demands of the patient.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of an artificial intelligence-based medical intercom system according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which are derived by a person skilled in the art based on the embodiments of the application, fall within the scope of protection of the application.
According to an embodiment of the application, an artificial intelligence-based medical intercom system is provided.
As shown in fig. 1, the medical intercom system based on artificial intelligence according to the embodiment of the application comprises the following steps:
the server side pre-configures an AI virtual nurse, wherein the AI virtual nurse comprises: the server establishes communication connection with the call terminal through the audio-video call engine, wherein the audio-video call engine creates a special AI virtual nurse account and a corresponding one-key direct call account according to different departments,
the calling terminal initiates a calling request and selectively calls an AI virtual nurse account or a one-key direct call account, wherein the method comprises the following steps:
if the current calling terminal initiates a call request to the AI virtual nurse account, the audio/video call engine establishes a call and accesses the AI virtual nurse instance to start business processing, wherein the method comprises the following steps:
when the calling terminal initiates a call, the information of a caller is sent to the audio-video communication engine, and after receiving the call information, the audio-video communication engine invokes an AI virtual nurse instance and synchronizes the caller information to the artificial intelligence dialogue engine;
the artificial intelligent conversation engine receives caller information, outputs welcome guide text content for calling in combination with preset content, sends the text content to the voice interaction engine, converts the text into audio information, and returns the audio information to the audio-video conversation engine;
the audio-video call engine sends the received audio information to the calling terminal for playing;
the calling terminal inputs statement audio to the AI virtual nurse according to the current guiding audio and sends the statement audio to the audio-video call engine;
the audio-video call engine receives the audio and forwards the audio to the voice interaction engine;
the voice interaction engine receives the audio frequency and then carries out voice recognition, converts the reply content of the caller into text information and sends the text information to the artificial intelligent dialogue engine;
after receiving the text information, the artificial intelligence dialogue engine carries out semantic understanding and intention analysis of calling people and carries out feedback reply or business processing on analysis intention according to preset rules, and the method comprises the following steps:
if the intention is the data in the artificial intelligent dialogue engine, the output result is sent to the voice interaction engine;
after receiving the text, the voice interaction engine converts the text into audio information and returns the information to the audio-video call engine;
the audio-video call engine receives the audio information and sends the audio information to the call terminal for playing;
if the intention is that the third party service system is required to inquire, calling a third party service system interface to process, and returning a processing result to the voice interaction engine;
the voice receives the inquiry result, converts the text into audio information, and returns the information to the audio-video call engine;
the audio-video call engine receives the audio information and sends the audio information to the call terminal for playing.
According to the technical scheme, different special AI virtual nurse accounts and one-key direct call accounts are created by the audio and video call engine according to different departments, for example: a device account number and a group call account number;
the call terminal configures a current department account according to the audio and video call engine, configures a device account and a group call account, and realizes an AI virtual nurse or emergency call function by calling different department accounts;
specifically, the calling terminal may call different department accounts through different entity keys or software keys, for example: the A key is set to a special AI virtual nurse account, when the A key triggers a call, the AI virtual nurse is called, the B key is set to an emergency call account, and when the B key triggers, the call is called to a nurse station host;
when the account number of the call is an AI virtual nurse, the communication is accepted and received by the AI virtual nurse;
after answering, the AI virtual nurse sends caller information to the artificial intelligence dialog engine
The technical scheme includes that caller information comprises: name, gender, bed number, and hospitalization number;
in addition, when the voice interaction engine does not receive the audio information of the calling terminal for more than 3 seconds, the recognized text characters are sent to the artificial intelligent dialogue engine for intention analysis and matching reply, wherein the method comprises the following steps:
when the intended analysis result is that the infusion is finished, the method concretely comprises the following steps:
the method comprises the steps that reply content preset by an artificial intelligence dialogue engine (for example, I inform nurses in the current transfusion peak period, if your transfusion reaches the bottom, please close a flow control valve on a transfusion tube and wait for processing of a Miss nurse process;
meanwhile, the artificial intelligence dialogue engine calls a business service task creation interface to create a transfusion finishing task of the XX bed and informs a responsible nurse of the docking bed through a business module;
when the backlog exceeds the designated time, the system reminds the responsible nurse again and synchronously pushes the task to the nurse;
marking the to-be-done end on the business system after the nurse processes the to-be-done end;
and inquiring whether the content to be consulted exists, ending the hang-up and turn-on dialogue when the audio is not received for more than 30 seconds, and carrying out a new business dialogue according to the content of the patient.
When the intended analysis result is a business consultation, such as the consultation business that can not be eaten, what needs to be noted after operation, and the like, the method is specifically as follows:
calling a local knowledge base, sending the text content to a voice interaction engine, converting the text content into audio information, sending the audio information to an audio-video call engine, and sending the audio-video call engine to a calling terminal;
and inquiring whether the content to be consulted exists, ending the hang-up and turn-on dialogue when the audio is not received for more than 30 seconds, and carrying out a new business dialogue according to the content of the patient.
When the intention analysis result is a business query, such as a fee query, an inspection report query and the like, the method is related to the patient and comprises the following specific steps:
the method comprises the steps of sending reply content preset by an artificial intelligent dialogue engine (inquiring cost/checking report for you) to a voice interaction engine, converting text content into audio information, sending the audio information to an audio-video call engine, and sending the audio-video call engine to a calling terminal;
meanwhile, the artificial intelligence dialogue engine calls interfaces such as inquiring cost inquiry, checking report and the like of the business service, inputs information (bed number, hospitalization number, medical record number and the like) of a patient for inquiring, and transmits an inquiring result text;
the query result is sent to a voice interaction engine, text content is converted into audio information and sent to an audio-video call engine, and the audio-video call engine is used for sending the audio-video call information to a call terminal;
and inquiring whether the content to be consulted exists, ending the hang-up and turn-on dialogue when the audio is not received for more than 30 seconds, and carrying out a new business dialogue according to the content of the patient.
When the intention analysis result is to find a nurse, a doctor or continue to be served by an AI virtual nurse, the method specifically comprises the following steps:
the method comprises the steps of sending reply content preset by an artificial intelligent dialogue engine (a user calls XX nurses/doctors on the side of the user, if the user wants to make me serve the user, the user can speak love and love, and the user continues to serve the user) to a voice interaction engine, converting text content into audio information, sending the audio information to an audio-video call engine, and sending the audio information to a calling terminal through the audio-video call engine;
meanwhile, the artificial intelligent dialogue engine calls an account query interface of a service staff;
when the business service returns to the account, calling a call transfer interface of the audio-video call engine, and inputting the returned account to call;
if the patient or family members speak the AI virtual nurse awakening word in the call waiting process, at the moment, the reply content preset by the artificial intelligent dialogue engine (which is used for cancelling the call and is continued to serve for the user) is sent to the voice interaction engine, the text content is converted into audio information and sent to the audio-video call engine, and the audio-video call engine is used for sending the audio-video call engine to the call terminal;
meanwhile, the artificial intelligence dialogue engine calls an interface of the audio-video dialogue engine for canceling XX call;
when the patient or family members speak the AI virtual nurse awakening word in the call waiting process, waiting for the call response of the called nurse/doctor;
if the instruction is a receiving instruction, the audio and video call engine establishes audio and video call between a patient or family calling terminal and a portable terminal of a receiving nurse or doctor, and both parties can communicate;
if the call is overtime or refused, the audio and video call engine can carry out a second round of call, the second round of call is a nurse station host, and the nurse station host serves;
simultaneously sending a message to an artificial intelligent dialogue engine, sending a voice interaction engine by a nurse without answering a preset reply message (a Miss nurse is busy at present and is helping you to call a nurse station, and the nurse station serves you), converting text content into audio information, sending the audio information to an audio-video call engine, and sending the audio information to a calling terminal through the audio-video call engine;
if the nurse station total station answers the instruction, the audio and video call engine establishes audio and video call between the patient or family calling terminal and the portable terminal of the answering nurse or doctor, and the two parties can communicate;
if the nurse station is not answered, a message is sent to the artificial intelligent dialogue engine, the nurse station is not answering the preset reply message (the current nurses are all busy, I can inform them that you are looking for nurses, if you are urgent, you can go to the nurse station or doctor's office directly, if you are not urgent, you can be calm in the hospital, etc., the nurses can find you at the first time when they are busy, I can inquire about fees, check reports, etc. for you can tell me questions directly), the text content is converted into audio information, and the audio information is sent to the audio-video dialogue engine, and the audio-video dialogue engine is sent to the calling terminal;
and inquiring whether the content to be consulted exists, ending the hang-up and turn-on dialogue when the audio is not received for more than 30 seconds, and carrying out a new business dialogue according to the content of the patient.
The intention analysis result is when the recognition is impossible or when the intention analysis result is empty, specifically as follows:
the method comprises the steps of sending reply content preset by an artificial intelligence dialogue engine (randomly playing that I does not hear what you talk, how can you talk with Mandarin again;
if the content of the second round of patient talk is still not able to identify intent:
reply content preset by an artificial intelligent dialogue engine (i can not understand what you say, i are doing effort to learn, i transfer the call to a Miss nurse, and they call you, transfer the call, please make a little, etc.) is sent to a voice interaction engine, text content is converted into audio information, and the audio information is sent to an audio-video call engine, and then sent to a calling terminal through the audio-video call engine;
meanwhile, the artificial intelligent dialogue engine calls an account query interface of a service staff;
when the business service returns to the account, calling a call transfer interface of the audio-video call engine, and inputting the returned account to call;
if the nurse station total station answers the instruction, the audio and video call engine establishes audio and video call between the patient or family calling terminal and the portable terminal of the answering nurse or doctor, and the two parties can communicate;
if the nurse station is not answered, a message is sent to the artificial intelligent dialogue engine, the nurse station is not answering the preset reply message (the current nurses are all busy, I can inform them that you are looking for nurses, if you are urgent, you can go to the nurse station or doctor's office directly, if you are not urgent, you can be calm in the hospital, etc., the nurses can find you at the first time when they are busy, I can inquire about fees, check reports, etc. for you can tell me questions directly), the text content is converted into audio information, and the audio information is sent to the audio-video dialogue engine, and the audio-video dialogue engine is sent to the calling terminal;
and inquiring whether the content to be consulted exists, ending the hang-up and turn-on dialogue when the audio is not received for more than 30 seconds, and carrying out a new business dialogue according to the content of the patient.
In addition, when the special crowd cannot accept or use the AI function, the system can be used for presetting a one-key direct account number, the account number is directly connected with a nurse station, and the nurse station can realize two-way intercom after being connected; the method comprises the following specific steps:
when the key of the calling terminal B is pressed, an account number needing to be called is sent to an audio-video call engine;
the audio and video call engine receives the accounts and then calls the accounts, and if the accounts are group accounts, each account is sequentially called;
all devices normally connected with the audio/video call engine receive incoming call information after calling;
when any one of all the ringing devices answers; at this time, an answer instruction is sent to the audio-video call engine, and after the communication service receives the answer instruction, the call of the accounts in the group is sequentially canceled (except the answer account); simultaneously, an audio video stream channel is established, and both parties can carry out audio and video communication in some time;
when any one of all the ringing devices is refused; at this time, the refusing instruction is sent to the CS communication service, and after the communication service receives the refusing instruction, the communication service sequentially cancels the calls of the accounts in the group including the device for sending the refusing instruction.
In addition, medical care intercom is used as one of the most frequent systems in a ward, the illness state of a hospital patient can be changed at any time, the changed call is very important, if the condition of the call is unavailable, the life of the patient can be possibly dangerous when the condition is serious, so the system keeps local area network off-line emergency call, and normal call conversation can be carried out even if communication with service fails, and the method comprises the following specific implementation steps:
when any call key of the call terminal is pressed, the AI virtual nurse is included, and when the account is directly called by one key, the connection state of the server is detected;
when the connection with the service fails, the point-to-multipoint instruction transmission is realized through the network broadcasting/multicasting technology, and the local machine transmits a broadcasting packet with a set port number and a called account or group calling account, wherein the instruction type is calling, local IP address information and calling information;
other devices in the local area network open a set port (a port designated by a transmitting end) for data monitoring;
the data packet contains own equipment account number or group call account number, records ID information of the opposite party, starts ringing and pops up a receiving interface;
when the answer or refusal key is clicked, the information such as event type, IP address and the like is returned to the call initiator through the network unicast technology;
when the call initiator receives the reply event type as answering, audio and video streams are sent to the IP of the called party and the designated port through the TCP/UDP technology;
when the called party receives the audio and video streams, the called party plays the audio and video streams and simultaneously sends the audio and video streams to the initiator through the designated port, so that the audio and video call of the two parties is realized;
when the reply event type received by the call initiator is refusal, the point-to-multipoint instruction transmission is realized through the network multicast technology, the local machine transmits a broadcast packet with a set port number and a called account number or group call account number, the instruction type is a cancellation call, local IP address information and call information, and meanwhile, an answering interface is closed and ringing is stopped;
when the called party receives the instruction to cancel the call, closing the answering interface and stopping ringing;
when the call initiator does not receive the reply instruction of the called party beyond the appointed time, the point-to-multipoint instruction transmission is realized through the network multicast technology, and the local machine transmits a broadcast packet with a set port number and with a called account or group call account, wherein the instruction type is cancel call, local IP address information and call information
When the called party receives the instruction to cancel the call, the answering interface is closed and the ringing is stopped.
In summary, by means of the above technical solution of the present application, the following effects are achieved:
1. the application combines the audio and video communication technology with the digital personal technology, namely an AI nurse is added to the disease area, the AI nurse is preferentially accessed when the patient calls, and the AI nurse classifies the demands of the patient, and the AI nurse does not process event identification and task issuing.
2. The application reduces the waiting time of both parties, and when the patient calls, the AI nurse carries out a dialogue, and replies different contents according to different requirements of the patient.
3. The application can not occupy the line of the treatment problem, the AI nurse can always respond in the first time, can not be emotionally, and can always show the best side to the patient. The communication and service of the true nurses are reserved for the most needed people, the conversation processing time of the nurses is reduced by 85%, the efficiency is higher, a lot of disputes are larger than that of the two parties at present, the nurses are busy in work, the nurses can be unavoidably emotionally at times, and disputes are easy to generate when the nurses carry the nurses. While AI nurses are different and consistent.
3. After the patient call is put through, the AI nurse carries out the classification of the patient call request, the classified tasks are automatically filed and the corresponding responsible doctors or the corresponding protected places are notified, and the transfer is carried out by the nurse at present.
4. The AI nurse can automatically generate backlog matters of the accepted matters, and provide a double invisible hand for clinical nurses to better serve patients.
5. The application supports one-key direct call (emergency call), when some emergency situations occur to patients, the call can be directly sent to nurses through the preset one-key direct call, and the problem of uneven resource allocation can be better solved.
6. The AI nurse of the application can solve the problems of negative emotion caused by the repeatability of the nurse answer, whether the patient has a question to answer or not, poor answer attitude and the like by accessing the standard knowledge base.
The foregoing is merely a preferred embodiment of the present application and is not intended to limit the present application, and other embodiments of the present disclosure will be readily apparent to those skilled in the art after considering the disclosure herein in the specification and examples. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (9)
1. An artificial intelligence-based medical intercom system is characterized by comprising the following steps:
the server side pre-configures an AI virtual nurse, wherein the AI virtual nurse comprises: the server establishes communication connection with the call terminal through the audio-video call engine, wherein the audio-video call engine creates a special AI virtual nurse account and a corresponding one-key direct call account according to different departments,
the calling terminal initiates a calling request and selectively calls an AI virtual nurse account or a one-key direct call account, wherein the method comprises the following steps:
if the current calling terminal initiates a call request to the AI virtual nurse account, the audio/video call engine establishes a call and accesses the AI virtual nurse instance to start business processing, wherein the method comprises the following steps:
when the calling terminal initiates a call, the information of a caller is sent to the audio-video communication engine, and after receiving the call information, the audio-video communication engine invokes an AI virtual nurse instance and synchronizes the caller information to the artificial intelligence dialogue engine;
the artificial intelligent conversation engine receives caller information, outputs welcome guide text content for calling in combination with preset content, sends the text content to the voice interaction engine, converts the text into audio information, and returns the audio information to the audio-video conversation engine;
the audio-video call engine sends the received audio information to the calling terminal for playing;
the calling terminal inputs statement audio to the AI virtual nurse according to the current guiding audio and sends the statement audio to the audio-video call engine;
the audio-video call engine receives the audio and forwards the audio to the voice interaction engine;
the voice interaction engine receives the audio frequency and then carries out voice recognition, converts the reply content of the caller into text information and sends the text information to the artificial intelligent dialogue engine;
after receiving the text information, the artificial intelligence dialogue engine carries out semantic understanding and intention analysis of calling people and carries out feedback reply or business processing on analysis intention according to preset rules, and the method comprises the following steps:
if the intention is the data in the artificial intelligent dialogue engine, the output result is sent to the voice interaction engine;
after receiving the text, the voice interaction engine converts the text into audio information and returns the information to the audio-video call engine;
the audio-video call engine receives the audio information and sends the audio information to the call terminal for playing;
if the intention is that the third party service system is required to inquire, calling a third party service system interface to process, and returning a processing result to the voice interaction engine;
the voice receives the inquiry result, converts the text into audio information, and returns the information to the audio-video call engine;
the audio-video call engine receives the audio information and sends the audio information to the call terminal for playing.
2. The artificial intelligence based medical intercom system of claim 1, wherein the caller information comprises: name, gender, bed number, and hospitalization number.
3. The artificial intelligence based medical intercom system of claim 1, wherein the artificial intelligence dialog engine performs intent analysis comprising the steps of:
when the calibration intention analysis result is that the transfusion is finished, the method comprises the following steps:
the method comprises the steps of sending reply content preset by an artificial intelligence dialogue engine to a voice interaction engine, converting text content into audio information, sending the audio information to an audio-video dialogue engine and sending the audio-video dialogue engine to a calling terminal for playing;
the artificial intelligent dialogue engine calls a business service task creation interface to create a transfusion completion task containing a bed number, and informs a nurse interfacing the bed number through a business module.
4. The artificial intelligence based medical intercom system of claim 1, wherein the artificial intelligence dialog engine performs intent analysis comprising the steps of:
when the calibration intention analysis result is business consultation, the method comprises the following steps:
calling a local knowledge base and sending text contents to a voice interaction engine;
the text content is converted into audio information and sent to an audio-video call engine, and the audio-video call engine is used for sending the audio-video call engine to the calling terminal.
5. The artificial intelligence based medical intercom system of claim 1, wherein the artificial intelligence dialog engine performs intent analysis comprising the steps of:
when the calibration intention analysis result is the service inquiry, the method comprises the following steps:
the reply content preset by the artificial intelligence dialogue engine is sent to the voice interaction engine;
converting the text content into audio information, sending the audio information to an audio-video call engine, and sending the audio information to a call terminal through the audio-video call engine;
meanwhile, the artificial intelligent dialogue engine calls interfaces such as query cost query, inspection report and the like of the business service, inputs information query of a patient, sends a query result text to the voice interaction engine, converts text content into audio information, sends the audio information to the audio-video communication engine, and sends the audio-video information to the calling terminal through the audio-video communication engine.
6. The artificial intelligence based medical intercom system of claim 1, wherein the artificial intelligence dialog engine performs intent analysis comprising the steps of:
the calibration intention analysis result is that medical staff is searched, and the method comprises the following steps:
the method comprises the steps of sending reply content preset by an artificial intelligent dialogue engine to a voice interaction engine, converting text content into audio information, sending the audio information to an audio-video call engine, and sending the audio information to a calling terminal through the audio-video call engine;
meanwhile, the artificial intelligent dialogue engine calls an account query interface of a service staff;
when the business service returns to the account, calling a call transfer interface of the audio-video call engine, and inputting the returned account to call.
7. The artificial intelligence based medical intercom system of claim 1, further comprising the steps of:
and the calling terminal configures a current AI virtual nurse account and a corresponding one-key direct call account according to the audio and video call engine.
8. The artificial intelligence based medical intercom system of claim 7, wherein the call terminal call further comprises the steps of:
the account called by the calling terminal is a one-key direct call account, and comprises the following steps:
the calling terminal sends an account number to be called to the audio-video call engine;
and the audio and video call engine receives the account number, then performs account number call, and performs audio and video call with the account number.
9. The medical intercom system based on artificial intelligence as in claim 1 wherein said calling terminal performs a selection of AI virtual nurse account number or one-touch direct call account number for making a call comprising the steps of:
the server detects the connection state of the call terminal, wherein the method comprises the following steps:
when the connection with the service fails, the point-to-multipoint instruction transmission is realized through the network broadcasting/multicasting technology, and the local machine transmits a broadcasting packet with a set port number and a called account or group calling account, wherein the instruction type is calling, local IP address information and calling information;
other devices in the local area network open the data monitoring of the set port;
the data packet contains the own equipment account number or group call account number, records the ID information of the opposite party, starts ringing and pops up the answering interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311257697.6A CN117176894A (en) | 2023-09-27 | 2023-09-27 | Medical care intercom system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311257697.6A CN117176894A (en) | 2023-09-27 | 2023-09-27 | Medical care intercom system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117176894A true CN117176894A (en) | 2023-12-05 |
Family
ID=88939378
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311257697.6A Pending CN117176894A (en) | 2023-09-27 | 2023-09-27 | Medical care intercom system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117176894A (en) |
-
2023
- 2023-09-27 CN CN202311257697.6A patent/CN117176894A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110891124B (en) | System for artificial intelligence pick-up call | |
| CN104732468B (en) | A kind of Telemedicine System based on mobile interchange | |
| DE69834097T2 (en) | Method and apparatus for managing incoming communication events via options on multiple media | |
| US20140334615A1 (en) | System, Method and Computer Program Product for Conveying Presence Information Via Voice Mail | |
| CN101262527B (en) | Providing telephony services using intelligent end points | |
| CN208656933U (en) | A kind of hospital's visual-speaking system | |
| JPH03501559A (en) | Telephone answering service with integrated voice and text message storage | |
| US20060165225A1 (en) | Telephone interpretation system | |
| US9524717B2 (en) | System, method, and computer program for integrating voice-to-text capability into call systems | |
| CN1608369B (en) | Priority indication for voice over internet protocol calls | |
| CN108416721A (en) | A kind of emergency management system | |
| US7489698B2 (en) | Mediator based architecture for first responder interoperability systems (FRIS) | |
| CN110798579A (en) | Emergency rescue network integration system and communication method for special service number and SOS preset number | |
| US20080170672A1 (en) | Enhanced telecommunications greeting system | |
| US20040198354A1 (en) | Communication address re-direction system for a mobile communication device | |
| KR20030001053A (en) | Apparatus and method for providing telecommunication service using character identifiers | |
| CN113282732A (en) | Intelligent voice interaction comprehensive management platform and method | |
| CN117176894A (en) | Medical care intercom system based on artificial intelligence | |
| CN100539622C (en) | Voice browser with integrated TCAP and ISUP interface | |
| CN203181054U (en) | Intelligent medical calling system | |
| CN113301514B (en) | Emergency treatment method and system based on 5G message | |
| KR100965090B1 (en) | System and method for the call agent connection service using video information menu based on VRS | |
| CN111435981B (en) | Call processing method and device | |
| CN112911194A (en) | Three-way call rescue control method, system, medium, equipment and terminal | |
| KR100304124B1 (en) | Method for processing malicoius call |
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 |