Voice registration method and system based on target detection and electronic equipment

Abstract

The invention provides a voice registration method and system based on target detection and electronic equipment, and the method comprises the steps: judging whether a patient exists in a registration region of a self-service registration machine or not based on a human body infrared sensor, and obtaining a starting instruction through a camera when the patient exists, and obtaining the video information of the patient in the registration region; the video information of the patients in the registration area is analyzed and judged, and registration IDs are generated for the patients difficult to register; based on the registration ID of the difficult-to-register patient, starting a voice registration module, acquiring and analyzing voice information of the difficult-to-register patient, and generating registration information for the difficult-to-register patient; after the patient finishes registration, generating a doctor-seeing route map for the patient based on the registration information of the patient; and after the patient sees a doctor, based on the identity information of the patient, obtaining a query medical examination result, thereby improving the registration and doctor-seeing experience of the patient with difficulty in registration, and effectively supporting hospital management and resource allocation.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent registration, and specifically to a method, system and electronic equipment for voice registration based on target detection. Background Art

[0002] The self-service registration machine is a self-service device used in hospitals. It is mainly designed to address the current situation of long registration queues and long waiting times in large hospitals in my country, which causes congestion and blockage in hospitals. By combining hardware technologies such as touch screens and connecting with the hospital's existing information system (HIS), it can meet patients' needs for self-service registration, self-service appointments, self-service recharges, and information inquiries on charging items in hospitals. It can also help hospitals optimize business processes, improve daily operating efficiency and service quality, effectively alleviate queuing problems, and improve patient experience.

[0003] Although the current registration machines are highly intelligent, they are still inconvenient for some patients who have difficulty registering. For these patients, they have two main options: one is to queue up at the manual window for registration, but in this process, the staff may make inaccurate recommendations when recommending outpatient clinics based on the patient's description; the other is to seek assistance from the nurses at the self-service registration machine. However, when there are many people registering, the nurses may not be able to provide registration services to every patient who needs help in time, resulting in reduced registration efficiency.

[0004] Although Chinese patent CN105913847b discloses a method, device and system for implementing voice registration, the patent obtains the voice registration information input by the user; converts the voice registration information into text registration information; matches the corresponding registration department according to the medical-related keywords included in the text registration information; if the registration department can be matched, prompt the user to perform the registration operation; if not, prompt the user to re-enter the voice registration information. However, the patent does not provide a corresponding solution for how to identify and judge patients with difficulty in registration, so that in the process of voice registration, it is impossible to use the voice registration function for patients with difficulty in registration in a targeted manner. Therefore, how to overcome the above-mentioned technical problems and defects has become a key issue that needs to be solved. Summary of the invention

[0005] In order to overcome the above problems existing in the prior art, the present application provides a method and system for voice registration based on target detection, which adopts the following technical solutions:

[0006] In a first aspect, the present application provides a method for voice registration based on target detection, comprising:

[0007] Based on the human infrared sensor, it is judged whether there is a patient in the registration area of ​​the self-service registration machine. When there is a patient, the camera obtains the opening instruction to obtain the video information of the patient in the registration area;

[0008] Analyze and judge the video information of the patients in the registration area, and when there are patients with difficulty in registration in the registration area, generate a registration ID for the patients with difficulty in registration;

[0009] Based on the registration ID of patients with difficulty in registration, the voice registration module is enabled to obtain and analyze the voice information of patients with difficulty in registration, and generate registration information for patients with difficulty in registration;

[0010] After the patient completes the registration, a medical route map is generated for the patient based on the patient's registration information;

[0011] After the patient's consultation is completed, the patient's identity information is obtained, and the patient's query medical examination results are obtained based on the preset real-time medical examination service smart platform and the patient's identity information.

[0012] Furthermore, judging whether there is a patient in the registration area of ​​the self-service registration machine based on the human infrared sensor includes:

[0013] When a patient enters the registration area of ​​the self-service registration machine, based on the difference between the patient's body temperature and the background environment, the human infrared sensor detects the signal of the infrared beam emitted being reflected by the human body;

[0014] After the human infrared sensor detects the signal, it converts the signal into an electrical signal and sends it to the control unit;

[0015] The control unit analyzes the electrical signal to determine whether there is a patient in the registration area of ​​the self-service registration machine;

[0016] When the control unit confirms that there is a patient in the registration area of ​​the self-service registration machine, the control unit generates instruction information that the patient exists.

[0017] Furthermore, when there is a patient, the camera obtains an opening instruction to obtain video information of the patient in the registration area, including:

[0018] Based on the control unit generating instruction information indicating the presence of a patient, the camera obtains the instruction information, and the camera is turned on to obtain video information of the patient in the registration area.

[0019] Furthermore, the video information of the patients in the registration area is analyzed and judged, specifically as follows:

[0020] Performing target detection on the video information of the patients in the registration area based on the YOLO algorithm to obtain the patients in the video information;

[0021] Perform human posture estimation and behavior recognition on the acquired patients; identify the patient's posture and movement based on the preset human posture estimation algorithm, obtain human posture estimation, and perform behavior recognition on the patient based on the time series data of human posture estimation; human posture estimation includes whether the patient is standing, sitting, walking or using assistive devices, etc., and behavior recognition includes whether the patient is wandering, hesitating, frequently checking the surroundings, etc. in the registration area, and whether the patient is using assistive devices, such as crutches, wheelchairs, stretchers, etc.;

[0022] The results of target detection, human posture estimation, and behavior recognition are integrated, and the integrated results are classified based on the support vector machine to determine whether the patient is difficult to register.

[0023] Furthermore, when there are patients with difficulty in registering in the registration area, a registration ID is generated for the patients with difficulty in registering, which is specifically manifested as follows:

[0024] When there is a patient with difficulty in registration in the registration area, the face recognition unit is turned on to obtain the identity information of the patient with difficulty in registration, and a registration ID is generated based on the identity information of the patient with difficulty in registration;

[0025] When the identity information of the patient with difficulty in registering cannot be obtained through the face recognition unit, the identity information of the patient with difficulty in registering is obtained based on the preset other identity information obtaining unit;

[0026] When a patient with difficulty in registration is unable to provide identity information, the patient will be marked, images of the patient will be collected, and a temporary registration ID will be generated for the patient.

[0027] Furthermore, the analysis and judgment of patients who have difficulty registering in the registration area also includes:

[0028] When the result of analyzing the video information of the patient in the registration area is that the patient is not a patient with difficulty in registration, a time series analysis is performed on the patient's operating behavior at the self-service registration machine based on the interaction information between the patient and the self-service registration machine. When the patient fails to complete the registration operation within the preset time, the patient is determined to be a patient with difficulty in registration. If a registration ID already exists, no registration ID is generated. If not, a registration ID is generated for the patient with difficulty in registration.

[0029] Furthermore, based on the registration ID of the patient with difficulty in registration, the voice registration module is turned on to obtain and analyze the voice information of the patient with difficulty in registration, and to generate registration information for the patient with difficulty in registration, which is specifically manifested as follows:

[0030] Convert captured voice information into text information based on ASR technology;

[0031] Use natural language processing to extract features from text information and obtain symptom characteristics and disease characteristics of patients with difficulty registering;

[0032] Generate a medical knowledge graph based on the medical knowledge base and historical medical data, where the knowledge graph represents entities in the medical field, including diseases, symptoms, departments, doctors, and the relationships between diseases, symptoms, departments, and doctors;

[0033] Use historical medical data to train machine learning models to identify matching relationships between diseases, symptoms, departments, and doctors;

[0034] The symptom characteristics and disease characteristics are used as inputs of a machine learning model to obtain departments and doctors that match the symptom characteristics and disease characteristics.

[0035] In the second aspect, the present application also provides a voice registration system based on target detection, including:

[0036] The patient judgment module is used to judge whether there is a patient in the registration area of ​​the self-service registration machine based on the human infrared sensor. When there is a patient, the camera obtains a start instruction to obtain video information of the patient in the registration area;

[0037] A registration ID generation module is used to analyze and judge the video information of the patients in the registration area, and when there are patients with registration difficulties in the registration area, generate a registration ID for the patients with registration difficulties;

[0038] A registration information generation module is used to start the voice registration module based on the registration ID of the patient with difficulty in registration, obtain and analyze the voice information of the patient with difficulty in registration, and generate registration information for the patient with difficulty in registration;

[0039] A medical consultation route map generation module is used to generate a medical consultation route map for the patient based on the patient's registration information after the patient completes the registration;

[0040] The medical examination result query module is used to obtain the patient's identity information after the patient completes the medical treatment, and obtain the patient's query medical examination results based on the preset real-time medical examination service intelligent platform and the patient's identity information.

[0041] In a third aspect, the present application provides an electronic device, including:

[0042] One or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the device, cause the device to perform the method as described in the first aspect.

[0043] In a fourth aspect, the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer executes the method described in the first aspect.

[0044] In a fifth aspect, the present application provides a computer program, which, when executed by a computer, is used to execute the method described in the first aspect.

[0045] In one possible design, the program in the fifth aspect may be stored in whole or in part on a storage medium packaged together with the processor, or may be stored in whole or in part on a memory not packaged together with the processor.

[0046] This application has the following beneficial effects:

[0047] 1. This application uses human infrared sensors to determine whether there are patients in the registration area of ​​the self-service registration machine. When there are patients, the camera receives a start instruction to obtain video information of the patient. The infrared sensing technology can automatically detect whether the patient has entered the registration area without manual monitoring. The camera is only activated when a patient is detected in the registration area, which helps to reduce power consumption, extend the service life of the equipment, and reduce unnecessary maintenance costs. Compared with a continuously running camera system, the method of selectively triggering the operation is more economical and environmentally friendly. The infrared sensing can be used to activate the camera only when a patient is detected in the registration area to reduce privacy concerns caused by constant video surveillance. There are fewer limitations when using image capture devices, and patients may feel less violated.

[0048] 2. Different patients may come from different places and have different accents. This application uses ASR technology to convert the captured voice information into text information, which can accurately convert voice information with different accents into text information. ASR technology supports multiple languages, providing strong technical support for patients who have difficulty in registration and improving registration efficiency.

[0049] 3. This application re-determines whether a patient is difficult to register based on the patient's behavior and the environmental context information of the patient in the registration area during the registration process, so as to make up for the misjudgment caused by the initial judgment.

[0050] 4. Through automated identification and assistance, this application eliminates the need for patients who have difficulty registering to queue up at a manual window or seek assistance from nurses at self-service registration machines. Patients who have difficulty registering can complete the registration process, thus improving the overall medical experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is an exemplary system architecture diagram to which the embodiments of the present application can be applied;

[0052] Figure 2 This is a flow chart of a method for voice registration based on target detection according to an embodiment of the present application;

[0053] Figure 3 This is a flowchart of determining whether there is a patient in the registration area in step S1 of the embodiment of the present application;

[0054] Figure 4 This is a flowchart of step S2 of the embodiment of the present application for determining whether the patient is a difficult-to-register patient;

[0055] Figure 5 Step S3 of the embodiment of the present application generates a flow chart of registration information for patients with difficulty in registration;

[0056] Figure 6 This is a system flow chart of an embodiment of the present application;

[0057] Figure 7 It is a schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0058] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0059] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0060] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0061] like Figure 1As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0062] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0063] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, Moving Picture Experts Group Audio Layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Group Audio Layer 4) players, laptop computers and desktop computers, etc.

[0064] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0065] It should be noted that the target detection-based voice registration method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the target detection-based voice registration system is generally set in the server / terminal device.

[0066] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0067] Explanation: ASR technology is automatic speech recognition technology.

[0068] Continue to refer Figure 2 , the figure shows a flow chart of a method for voice registration based on target detection of the present application, the method comprising the following steps:

[0069] Step S1, based on the human infrared sensor, it is judged whether there is a patient in the registration area of ​​the self-service registration machine. When there is a patient, the camera obtains a start instruction to obtain video information of the patient in the registration area;

[0070] In a possible implementation, when there is no patient in the registration area of ​​the self-service registration machine, the camera does not receive a start instruction and is in a dormant state.

[0071] In a possible implementation, a human infrared sensor is provided on the self-service registration machine. The embodiment of the present application provides a human infrared sensor for detecting whether there is a patient in the registration area of ​​the self-service registration machine. When the presence of a patient is detected, the camera is awakened to obtain the patient's video information to determine whether the patient is a person who has difficulty in registration.

[0072] In a possible implementation, the human infrared sensor is used to determine whether there is a patient in the registration area of ​​the self-service registration machine. Figure 3 , the specific steps include:

[0073] Step S101, when a patient enters the registration area of ​​the self-service registration machine, based on the difference between the patient's body temperature and the background environment, the human infrared sensor detects the signal of the infrared beam emitted being reflected by the human body;

[0074] Step S102, after the human infrared sensor detects the signal, the signal is converted into an electrical signal and sent to the control unit;

[0075] Step S103, the control unit analyzes the electrical signal to determine whether there is a patient in the registration area of ​​the self-service registration machine;

[0076] Step S104, when the control unit confirms that there is a patient in the registration area of ​​the self-service registration machine, the control unit generates instruction information indicating the presence of the patient.

[0077] In a possible implementation, when there is a patient, the camera obtains a start instruction to obtain video information of the patient in the registration area, including:

[0078] Based on the control unit generating instruction information indicating the presence of a patient, the camera obtains the instruction information, and the camera is turned on to obtain video information of the patient in the registration area.

[0079] In a possible real-time method, after the video information of the patient in the registration area is collected, the camera obtains a sleep instruction and enters a sleep state.

[0080] Step S2, analyzing and judging the video information of the patients in the registration area, and generating a registration ID for the patients who are difficult to register when there are patients in the registration area;

[0081] In a possible implementation, the video information of the patient in the registration area is analyzed and judged, please refer to Figure 4 , specifically:

[0082] Step S201, performing target detection on the video information of the patients in the registration area based on the YOLO algorithm to obtain the patients in the video information;

[0083] Step S202, performing human posture estimation and behavior recognition on the acquired patient; identifying the patient's posture and movement based on a preset human posture estimation algorithm, obtaining human posture estimation, and performing behavior recognition on the patient based on the time series data of the human posture estimation; wherein human posture estimation includes the patient standing, sitting, walking or using auxiliary equipment, etc., and behavior recognition includes the patient wandering, hesitating, frequently checking the surroundings, etc. in the registration area, and whether the patient uses auxiliary equipment, such as crutches, wheelchairs, stretchers, etc.; wherein the preset human posture estimation algorithm can use OpenPose or PoseNet algorithm.

[0084] Step S203, the target detection, human posture estimation, and behavior recognition results are integrated, and the integrated results are classified based on a support vector machine to determine whether the patient is a patient with difficulty in registering.

[0085] In a possible implementation, when there are patients with difficulty in registration in the registration area, a registration ID is generated for the patients with difficulty in registration, which is specifically manifested as follows:

[0086] When there is a patient with difficulty in registration in the registration area, the face recognition unit is turned on to obtain the identity information of the patient with difficulty in registration, and a registration ID is generated based on the identity information of the patient with difficulty in registration;

[0087] When the identity information of the patient with difficulty in registration cannot be obtained through the face recognition unit, the identity information of the patient with difficulty in registration is obtained based on the preset other identity information acquisition units; for example, the identity information can be obtained through identity cards, social security cards, etc.

[0088] When a patient with difficulty in registration is unable to provide identity information, the patient will be marked, images of the patient will be collected, and a temporary registration ID will be generated for the patient.

[0089] In a possible implementation, the analysis and judgment of the presence of patients who have difficulty registering in the registration area also includes: when the result of analyzing and judging the patient based on the video information of the patient in the registration area is that the patient is not a patient with difficulty registering, based on the interaction information between the patient and the self-service registration machine, a time series analysis is performed on the patient's operating behavior at the self-service registration machine; when the patient fails to complete the registration operation within a preset time, the patient is determined to be a patient with difficulty registering; if a registration ID already exists, the registration ID is not generated; if it does not exist, a registration ID is generated for the patient with difficulty registering.

[0090] This application re-determines whether a patient is difficult to register based on the patient's behavior and the environmental context information of the patient in the registration area during the registration process, so as to make up for the misjudgment caused by the initial judgment.

[0091] Step S3, based on the registration ID of the patient with difficulty in registration, start the voice registration module, obtain and analyze the voice information of the patient with difficulty in registration, and generate registration information for the patient with difficulty in registration;

[0092] In a possible implementation, based on the registration ID of the patient with difficulty in registration, the voice registration module is turned on to obtain and analyze the voice information of the patient with difficulty in registration, and to generate registration information for the patient with difficulty in registration. Please refer to Figure 5 , specifically:

[0093] Step S301, converting the captured voice information into text information based on ASR technology;

[0094] Step S302, using natural language processing to extract features from text information, and obtaining symptom features and disease features of patients who have difficulty registering;

[0095] Step S303, generating a medical knowledge graph based on the medical knowledge base and historical medical data, wherein the knowledge graph represents entities in the medical field, and the entities in the medical field include diseases, symptoms, departments, doctors, and the relationships between diseases, symptoms, departments, and doctors;

[0096] Step S304, using historical medical data to train the machine learning model to identify matching relationships between diseases, symptoms, departments, and doctors;

[0097] Step S305, using the symptom characteristics and disease characteristics as input to the machine learning model to obtain departments and doctors that match the symptom characteristics and disease characteristics.

[0098] In one possible implementation, when the voice registration module is turned on, the self-service registration machine screen displays different options for patients who have difficulty registering to choose from. Patients who have difficulty registering can click on the screen or respond by voice to register, thereby generating registration information for patients who have difficulty registering.

[0099] In a possible implementation, when the voice information of the patient who has difficulty registering contains specific registration content, it is confirmed whether to directly generate the registration information. After obtaining the confirmation information of the patient who has difficulty registering, the registration information is directly generated.

[0100] For example, when the patient orally says "Anorectal Department, Doctor Liu xx", the voice registration module obtains the patient's voice information and generates registration information for the patient to see "Anorectal Department, Doctor Liu xx" based on the patient's confirmation information.

[0101] In a possible implementation, when the voice information obtained from patients who have difficulty registering is oral symptom information, departments and doctors are recommended to patients who have difficulty registering based on the symptom information and a preset intelligent recommendation algorithm, and the patient is asked to confirm whether to choose the doctor for registration.

[0102] When the patient does not choose to register with the recommended doctor, the patient is asked for information on his needs in selecting a doctor to register with, and a doctor is recommended to the patient based on the patient's need information.

[0103] For example, the patient's oral statement is "I have been feeling unwell recently, and it has been gradually getting worse; I started with persistent headaches, ranging from mild tingling to violent throbbing, and frequent insomnia. I often have difficulty falling asleep at night or having difficulty falling asleep again after waking up. In addition, I feel tired and weak, even after resting." Based on the patient's oral statement, the patient's symptoms fall within the diagnosis and treatment scope of neurology. A list of doctors in neurology that match the patient's oral condition is obtained, and the list is sorted from high to low according to the degree of match, and the doctor with the highest degree of match is recommended to the patient first.

[0104] In one possible implementation, the patient's registration information is transmitted to the live medical examination service smart platform;

[0105] Step S4: after the patient completes the registration, a medical consultation route map is generated for the patient based on the patient's registration information;

[0106] Step S5, after the patient's consultation is completed, the patient's identity information is obtained, and based on the preset real-time medical examination service smart platform and the patient's identity information, the patient's query medical examination results are obtained.

[0107] In a possible implementation, during the course of the patient's medical consultation, the patient's medical consultation information is transmitted to the live medical examination service intelligent platform in real time.

[0108] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0109] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0110] Continue to refer Figure 6 The target detection-based voice registration system described in this embodiment includes:

[0111] The patient judgment module 601 is used to judge whether there is a patient in the registration area of ​​the self-service registration machine based on the human infrared sensor. When there is a patient, the camera obtains a start instruction to obtain video information of the patient in the registration area;

[0112] A registration ID generating module 602 is used to analyze and judge the video information of the patients in the registration area, and when there are patients with registration difficulties in the registration area, generate a registration ID for the patients with registration difficulties;

[0113] The registration information generating module 603 is used to start the voice registration module based on the registration ID of the patient with difficulty in registration, obtain the voice information of the patient with difficulty in registration and analyze it, and generate registration information for the patient with difficulty in registration;

[0114] A medical consultation route map generating module 604 is used to generate a medical consultation route map for the patient based on the patient's registration information after the patient completes the registration;

[0115] The medical examination result query module 605 is used to obtain the patient's identity information after the patient completes the medical consultation, and obtain the patient's query medical examination results based on the preset real-time medical examination service intelligent platform and the patient's identity information.

[0116] To solve the above technical problems, the present application also provides a computer device. Figure 7 , Figure 7 This is a basic structural block diagram of the computer device in this embodiment.

[0117] The computer device 7 includes a memory 7a, a processor 7b, and a network interface 7c that are interconnected through a system bus. It should be noted that the figure only shows a computer device 7 with components 7a-7c, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0118] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0119] The memory 7a includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 7a can be an internal storage unit of the computer device 7, such as a hard disk or memory of the computer device 7. In other embodiments, the memory 7a can also be an external storage device of the computer device 7, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 7. Of course, the memory 7a can also include both the internal storage unit of the computer device 7 and its external storage device. In this embodiment, the memory 7a is generally used to store the operating system and various application software installed on the computer device 7, such as the program code of the voice registration method based on target detection, etc. In addition, the memory 7a can also be used to temporarily store various types of data that have been output or are to be output.

[0120] The processor 7b may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 7b is generally used to control the overall operation of the computer device 7. In this embodiment, the processor 7b is used to run the program code stored in the memory 7a or process data, such as running the program code of the voice registration method based on target detection.

[0121] The network interface 7c may include a wireless network interface or a wired network interface. The network interface 7c is generally used to establish a communication connection between the computer device 7 and other electronic devices.

[0122] The present application also provides another embodiment, namely, providing a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a program of a voice registration method based on target detection, and the voice registration method based on target detection can be executed by at least one processor so that the at least one processor performs the steps of the voice registration method based on target detection as described above.

[0123] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0124] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A voice registration method based on target detection, characterized in that: include: Based on the human infrared sensor, it is judged whether there is a patient in the registration area of ​​the self-service registration machine. When there is a patient, the camera obtains the opening instruction to obtain the video information of the patient in the registration area; Analyze and judge the video information of the patients in the registration area, and when there are patients with difficulty in registration in the registration area, generate a registration ID for the patients with difficulty in registration; Based on the registration ID of patients with difficulty in registration, the voice registration module is enabled to obtain and analyze the voice information of patients with difficulty in registration, and generate registration information for patients with difficulty in registration; After the patient completes the registration, a medical route map is generated for the patient based on the patient's registration information; After the patient's consultation is completed, the patient's identity information is obtained, and the patient's query medical examination results are obtained based on the preset real-time medical examination service smart platform and the patient's identity information.

2. The method for voice registration based on target detection according to claim 1, characterized in that: The method of judging whether there is a patient in the registration area of ​​the self-service registration machine based on the human infrared sensor includes: When a patient enters the registration area of ​​the self-service registration machine, based on the difference between the patient's body temperature and the background environment, the human infrared sensor detects the signal of the infrared beam emitted being reflected by the human body; After the human infrared sensor detects the signal, it converts the signal into an electrical signal and sends it to the control unit; The control unit analyzes the electrical signal to determine whether there is a patient in the registration area of ​​the self-service registration machine; When the control unit confirms that there is a patient in the registration area of ​​the self-service registration machine, the control unit generates instruction information that the patient exists.

3. The method for voice registration based on target detection according to claim 2, characterized in that: When there is a patient, the camera obtains an opening instruction to obtain video information of the patient in the registration area, including: Based on the control unit generating instruction information indicating the presence of a patient, the camera obtains the instruction information, and the camera is turned on to obtain video information of the patient in the registration area.

4. The method for voice registration based on target detection according to claim 1, characterized in that: The analysis and judgment of the video information of the patients in the registration area is specifically performed as follows: Performing target detection on the video information of the patients in the registration area based on the YOLO algorithm to obtain the patients in the video information; Perform human posture estimation and behavior recognition on the acquired patients; identify the patient's posture and movement based on a preset human posture estimation algorithm, obtain human posture estimation, and perform behavior recognition on the patient based on the time series data of human posture estimation; The results of target detection, human posture estimation, and behavior recognition are integrated, and the integrated results are classified based on the support vector machine to determine whether the patient is difficult to register.

5. The method for voice registration based on target detection according to claim 1, characterized in that: When there are patients with difficulty in registration in the registration area, a registration ID is generated for the patients with difficulty in registration, which is specifically manifested as follows: When there is a patient with difficulty in registration in the registration area, the face recognition unit is turned on to obtain the identity information of the patient with difficulty in registration, and a registration ID is generated based on the identity information of the patient with difficulty in registration; When the identity information of the patient with difficulty in registering cannot be obtained through the face recognition unit, the identity information of the patient with difficulty in registering is obtained based on the preset other identity information obtaining unit; When a patient with difficulty in registration is unable to provide identity information, the patient will be marked, images of the patient will be collected, and a temporary registration ID will be generated for the patient.

6. The method for voice registration based on target detection according to claim 1, characterized in that: The analysis and judgment of patients who have difficulty registering in the registration area also includes: When the result of analyzing the video information of the patient in the registration area is that the patient is not a patient with difficulty in registration, a time series analysis is performed on the patient's operating behavior at the self-service registration machine based on the interaction information between the patient and the self-service registration machine. When the patient fails to complete the registration operation within the preset time, the patient is determined to be a patient with difficulty in registration. If a registration ID already exists, no registration ID is generated. If not, a registration ID is generated for the patient with difficulty in registration.

7. The method for voice registration based on target detection according to claim 1, characterized in that: Based on the registration ID of the patient with difficulty in registration, the voice registration module is turned on to obtain and analyze the voice information of the patient with difficulty in registration, and to generate registration information for the patient with difficulty in registration, which is specifically manifested as follows: Convert captured voice information into text information based on ASR technology; Use natural language processing to extract features from text information and obtain symptom characteristics and disease characteristics of patients with difficulty registering; Generate a medical knowledge graph based on the medical knowledge base and historical medical data, where the knowledge graph represents entities in the medical field, including diseases, symptoms, departments, doctors, and the relationships between diseases, symptoms, departments, and doctors; Use historical medical data to train machine learning models to identify matching relationships between diseases, symptoms, departments, and doctors; The symptom characteristics and disease characteristics are used as inputs of a machine learning model to obtain departments and doctors that match the symptom characteristics and disease characteristics.

8. A voice registration system based on target detection, used to implement the voice registration method based on target detection of claims 1-7, characterized in that: include: The patient judgment module is used to judge whether there is a patient in the registration area of ​​the self-service registration machine based on the human infrared sensor. When there is a patient, the camera obtains a start instruction to obtain video information of the patient in the registration area; A registration ID generation module is used to analyze and judge the video information of the patients in the registration area, and when there are patients with registration difficulties in the registration area, generate a registration ID for the patients with registration difficulties; A registration information generation module is used to start the voice registration module based on the registration ID of the patient with difficulty in registration, obtain and analyze the voice information of the patient with difficulty in registration, and generate registration information for the patient with difficulty in registration; A medical consultation route map generation module is used to generate a medical consultation route map for the patient based on the patient's registration information after the patient completes the registration; The medical examination result query module is used to obtain the patient's identity information after the patient completes the medical treatment, and obtain the patient's query medical examination results based on the preset real-time medical examination service intelligent platform and the patient's identity information.

9. An electronic device, characterized in that: include: one or more processors; Memory; And one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the device, enable the device to perform the steps of the target detection-based voice registration method as described in any one of claims 1 to 7.

Images