Elderly-friendly intelligent accompanying diagnosis method and system and electronic equipment

Abstract

The invention provides an elderly-friendly intelligent diagnosis accompanying method and system and electronic equipment, and relates to the technical field of artificial intelligence, and the method comprises the steps: carrying out the biological information recognition of a target user through activating a biological recognizer; calling a target diagnosis and treatment record based on the target identity, and judging whether the target diagnosis and treatment record conforms to a predetermined reservation constraint; if yes, a reservation list in the target diagnosis and treatment record is extracted; dynamically monitoring real-time human traffic information, and calling an expert guidance library to perform priority analysis on a plurality of items of the reservation list to obtain an optimal item list; and activating the friendly diagnosis accompanying device to carry out intelligent diagnosis accompanying on the target user according to the optimal item list. According to the method and the device, the technical problems of low accompanying diagnosis service efficiency and poor user diagnosis experience caused by lack of flexible adjustment for real-time diagnosis conditions in the prior art are solved, and the technical effects of improving the intelligent and personalized level of the accompanying diagnosis service, reducing the waiting time and enhancing the accompanying diagnosis convenience and safety of the elderly user are achieved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an elderly-friendly intelligent medical accompanying method, system, and electronic equipment. Background Art

[0002] As an emerging medical service model, intelligent medical companion services integrate big data, artificial intelligence, and other technologies to provide patients with intelligent medical guidance services, thereby improving the efficiency and quality of medical services. Current intelligent medical companion services are mainly limited to basic appointment reminders and static navigation functions. For example, they can remind users of medical appointments based on appointment times and provide navigation to the approximate location of hospital departments. However, they cannot dynamically perceive real-time changes in the hospital environment, nor can they intelligently adjust the medical companionship plan based on the patient's individual situation. This fixed service model, especially for elderly patients with slower movements and relatively weaker cognitive abilities, can easily lead to long waits or miss the best time to see a doctor due to unreasonable routes and insufficient preparation before the examination, increasing the difficulty of seeing a doctor, thereby reducing the efficiency of medical companionship and the user's medical experience. Summary of the Invention

[0003] This application provides an elderly-friendly intelligent accompanying medical treatment method, system and electronic equipment, which solves the technical problems of the existing technology due to the relatively fixed service model and the lack of flexible adjustment to real-time medical conditions, resulting in rigid accompanying medical treatment processes, long waiting times for users, and thus reduced accompanying medical treatment efficiency and user experience. It achieves the technical effect of improving the intelligence and personalization level of accompanying medical treatment services, reducing waiting time, and enhancing the convenience and safety of accompanying medical treatment for elderly users.

[0004] In view of the above problems, on the one hand, the present application provides an elderly-friendly intelligent accompanying medical method, including: activating a biometric identifier, and performing biometric information identification on a target user through the biometric identifier to obtain a target identity, wherein the biometric identifier is mounted on an intelligent accompanying medical electronic device; retrieving a target medical record based on the target identity, and judging whether the target medical record meets the predetermined appointment constraints; if so, extracting an appointment form in the target medical record, wherein the appointment form includes multiple items; dynamically monitoring to obtain real-time traffic information, and retrieving an expert guidance library to perform priority analysis on the multiple items to obtain an optimal item list; activating a friendly accompanying medical device mounted on the intelligent accompanying medical electronic device, and performing intelligent accompanying medical treatment on the target user according to the optimal item list.

[0005] On the other hand, the present application also provides an elderly-friendly intelligent accompanying medical system, including: a biometric information recognition unit, used to activate a biometric identifier, and perform biometric information recognition on a target user through the biometric identifier to obtain a target identity, wherein the biometric identifier is mounted on an intelligent accompanying medical electronic device; an appointment judgment unit, used to retrieve a target medical record based on the target identity, and determine whether the target medical record meets the predetermined appointment constraints; an appointment form extraction unit, used to extract an appointment form from the target medical record if it meets the requirements, wherein the appointment form includes multiple items; a project priority analysis unit, used to dynamically monitor and obtain real-time traffic information, and retrieve an expert guidance library to perform priority analysis on the multiple items to obtain an optimal project list; an intelligent accompanying medical activation unit, used to activate a friendly accompanying medical device mounted on the intelligent accompanying medical electronic device, and perform intelligent accompanying medical treatment on the target user according to the optimal project list.

[0006] In a third aspect, the present application also provides an electronic device including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned elderly-friendly intelligent accompanying medical method when executing the computer program.

[0007] One or more technical solutions provided in this application have at least the following beneficial effects:

[0008] Activate the biometric identifier and identify the target user's biometric information. This step uses biometric technology to quickly and accurately identify the identity of the elderly user, simplifying the traditional identity verification process. Retrieve medical records based on the target identity and determine whether they meet the appointment constraints, ensuring the orderliness of the entire accompanying process and avoiding confusion caused by appointment-related issues. Extract the appointment form and combine it with the real-time traffic information monitored dynamically and the expert guidance library to perform priority analysis on the medical treatment items, providing personalized medical treatment sequence arrangements for elderly users, reducing unnecessary waiting time and improving medical treatment efficiency. Activate the friendly accompanying device to conduct intelligent accompanying according to the optimal project list, providing convenient and accurate accompanying service.

[0009] To sum up, this application introduces technical means such as biometrics, crowd flow monitoring, expert guidance library analysis, and friendly accompanying devices, fully considering the hospital environment and individual user conditions to optimize and adjust the diagnosis and treatment process, reducing the waiting time for elderly users, improving the efficiency of accompanying treatment, and enhancing the intelligence and personalization of accompanying treatment services, thereby comprehensively improving the medical experience of elderly users.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A flowchart of an elderly-friendly intelligent medical accompanying method provided in an embodiment of the present application.

[0012] Figure 2 A schematic structural diagram of an elderly-friendly intelligent medical accompanying system provided in an embodiment of the present application.

[0013] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0014] Explanation of the accompanying symbols: biometric information recognition unit 10, appointment judgment unit 20, appointment form extraction unit 30, project priority analysis unit 40, intelligent accompanying medical consultation activation unit 50, bus 300, receiver 301, processor 302, transmitter 303, memory 304, bus interface 305. DETAILED DESCRIPTION

[0015] The embodiments of the present application provide an elderly-friendly intelligent medical accompanying method, system and electronic equipment, which solves the technical problems in the prior art due to the relatively fixed service model and the lack of flexible adjustment to real-time medical conditions, resulting in rigid accompanying medical process, long waiting time for users, and thus reduced accompanying medical efficiency and user experience. The embodiment of the present application achieves the technical effect of improving the intelligence and personalization level of accompanying medical services, reducing waiting time, and enhancing the convenience and safety of accompanying medical services for elderly users.

[0016] Example 1, as Figure 1 As shown, the embodiment of the present application provides an elderly-friendly intelligent accompanying medical treatment method, including:

[0017] Step S100: activating a biometric identifier and performing biometric information recognition on a target user through the biometric identifier to obtain a target identity, wherein the biometric identifier is mounted on an intelligent accompanying electronic device.

[0018] Specifically, a biometric identifier is a device that confirms an individual's identity by identifying their biological characteristics (such as fingerprints, faces, irises, etc.). The target user refers to a specific person who needs to receive the intelligent medical escort service, and in this embodiment of the application, it specifically refers to an elderly user. The target identity is the unique identity of the user determined by the biometric identifier after the target user's biological information is identified. For example, after facial recognition, it is determined that the elderly user is a specific individual named Zhang San, and Zhang San's identity information is the target identity.

[0019] Activate the biometric reader on the smart electronic device used for accompanying patients. This device can be a handheld terminal designed specifically for accompanying patients or a module integrated into the hospital's self-service equipment. Once activated, the biometric reader collects the target user's biometric information, such as a facial image captured by a camera or a fingerprint sensor. The biometric information is then analyzed and processed using a biometric recognition algorithm, compared with a pre-stored database of legitimate users' biometric information, and the target user's identity is determined.

[0020] Compared with traditional password or card verification methods, biometric technology is faster and more accurate. Users do not need to remember complex passwords or carry additional documents, which simplifies the medical treatment process. Biometric features are unique and difficult to forge, thereby improving the security of identity authentication.

[0021] Step S200: Retrieving target medical records based on the target identity, and determining whether the target medical records comply with predetermined appointment constraints.

[0022] Specifically, the target medical record is the medical history associated with the target identity, including past disease diagnoses, treatment plans, medication history, and more. Appointment constraints are the rules and restrictions related to appointments set by hospitals or medical service systems. For example, a user may need to schedule an appointment with a specialist 24 hours in advance, or a specific examination may only be scheduled from Monday to Wednesday.

[0023] After determining the target's identity, the intelligent accompanying electronic device interacts with the hospital's medical information management system (HIS), using the target's identity as an index to retrieve the target's medical records from the HIS. The device then analyzes and judges the retrieved medical records based on the retrieved medical records, combined with its internal rule engine, and according to predetermined appointment constraints (these constraints are stored in the system in the form of code or configuration files). For example, the rule engine checks whether the target medical records have any unfinished appointments and whether they are within the allowed appointment time.

[0024] By acquiring the target medical records, we can fully understand the user's medical needs and provide a basis for subsequent accompanying medical treatment plans. At the same time, judging whether the scheduled appointment constraints are met can avoid wasting time due to not meeting the appointment or medical conditions, ensuring that the accompanying medical treatment process can proceed smoothly according to the hospital's regulations.

[0025] Step S300: If it is consistent, extract the appointment form in the target medical record, wherein the appointment form includes multiple items.

[0026] Specifically, after determining that the target medical record meets the predetermined appointment constraints, the target medical record is parsed and the appointment order information is extracted from it. The appointment order is a part of the target medical record, which contains detailed information on various items that the target user has booked for this visit, such as the doctor's outpatient appointment, various examination items (such as X-ray examinations, blood tests, etc.), and treatment items (such as physical therapy, infusion, etc.). For example, an elderly user's appointment order may include information such as seeing an internal medicine specialist at 9 am and a routine blood test at 10:30 am. The extraction process can use data parsing algorithms and tools, such as using an XML parser (for appointment order data stored in XML format) or a JSON parser (for appointment order data stored in JSON format) to extract information on various items in the appointment order.

[0027] By extracting the appointment form, we can identify the specific items that the target user needs to perform during this visit, providing a direct basis for the subsequent accompanying medical process planning.

[0028] Step S400: Dynamically monitor and obtain real-time pedestrian flow information, and retrieve an expert guidance library to perform priority analysis on the multiple projects to obtain an optimal project list.

[0029] Specifically, real-time traffic information refers to the current flow of people in various areas of the hospital (such as department waiting areas and areas near examination rooms). For example, a hospital registration hall might be crowded with patients at 8 a.m., resulting in heavy traffic, while at 3 p.m. traffic might be relatively light. The expert guidance database is a database that stores the experience and knowledge of medical experts. This experience includes the prioritization of treatment options for different conditions, the relationships between different treatment options, and recommendations for handling special circumstances.

[0030] Interact with the hospital's crowd monitoring system to obtain real-time traffic information for each area. The hospital's crowd monitoring system collects real-time traffic data within the hospital through a sensor network (such as infrared sensors and Wi-Fi access points). For example, by analyzing changes in Wi-Fi signal strength, it can estimate the number of people in a specific area. Simultaneously, it draws on relevant empirical knowledge from the expert guidance library, combines real-time traffic information with the rules of the expert guidance library, and uses algorithms (such as weighted scoring and queuing theory) to prioritize multiple items in the appointment list, generating a prioritized list of items—the optimal list of items.

[0031] By dynamically monitoring real-time traffic information and combining it with an expert guidance database for priority analysis, we can rationally arrange the order of diagnosis and treatment projects, guide target users to avoid peak traffic areas, and enable target users to complete the medical treatment process more efficiently. This can especially reduce physical exertion and the hassle of medical treatment for elderly users.

[0032] Step S500: activating the friendly accompanying device installed in the intelligent accompanying electronic device, and performing intelligent accompanying diagnosis on the target user according to the optimal item list.

[0033] Specifically, the Friendly Patient Companion Device is a software module integrated into smart medical devices, designed to provide users with friendly and convenient medical companion services. It includes an interactive medical companion module and a friendly navigation module. The interactive medical companion module is responsible for interacting with the user and providing personalized medical companion services based on the optimal list of items. This includes reminding the user of the next item, providing wait time estimates, and guiding the user through each examination. The friendly navigation module provides real-time indoor navigation services by obtaining the user's current location and the location of the target department.

[0034] After obtaining the optimal list of procedures, the friendly navigation module in the smart medical companion electronic device is activated. During this process, the friendly navigation module uses indoor positioning technologies (such as Bluetooth and Wi-Fi) to determine the target user's precise location within the hospital. Then, based on the department location information corresponding to each item in the optimal list (this department location information can be pre-stored in the smart medical companion system's database and corresponds to the hospital's department layout), it calculates the optimal path from the target user's current location to the target department using a built-in path planning algorithm (such as a Dijkstra algorithm or a variant of the A-STAR algorithm). The smart medical companion electronic device then provides real-time image or voice navigation via the screen or voice function. Simultaneously, the interactive medical companion module uses natural language interaction to provide timely information to the target user based on the user's medical treatment progress. This includes automatically notifying the target user of precautions (such as dietary restrictions and metal dosing) based on the examination items, reminding the target user of their upcoming department, and informing them of the approximate wait time for the next medical procedure. Furthermore, the hospital can also interact with the hospital's HIS system through the interactive medical companion module to monitor the user's medical process and dynamics in real time, providing voice prompts and assistance when the user encounters difficulties. The Friendly Medical Companion Device also connects to the hospital's HIS system to update patient information in real time, guiding the user to the next procedure after the current procedure is completed. Furthermore, the Friendly Medical Companion Device integrates an emergency assistance function, allowing users to call medical staff with a single click, ensuring their safety in emergencies.

[0035] By activating the friendly accompanying device and combining it with the optimal project list, users can be provided with convenient and intelligent accompanying services, reducing delays in medical treatment due to unfamiliarity with the path or process, thereby improving the user's medical experience.

[0036] Furthermore, the biometric identifier described in the embodiment of the present application includes one or more combinations of a face recognition component, a fingerprint recognition component, an iris recognition component, an ID card reading component, a medical insurance card reading component, a QR code scanning component, a barcode scanning component and a radio frequency identification component.

[0037] Specifically, for elderly users, traditional identity authentication methods (such as passwords, verification codes, etc.) are complex and insecure. However, the present application embodiment uses a biometric identifier mounted on an intelligent electronic medical device to identify the target user's biometric information, quickly and accurately obtaining the user's identity information. This not only simplifies the identity authentication process and improves medical treatment efficiency, but also enhances the security of identity authentication, avoids security risks caused by password leakage, and provides elderly users with a more convenient and secure medical treatment experience.

[0038] Biometric identifiers can use a variety of biometric technologies for identity verification, including facial recognition, fingerprint recognition, iris recognition, ID card readers, medical insurance card readers, QR code scanners, barcode scanners, and radio frequency identification. Facial recognition uses a camera or other device to capture facial images and analyze unique biometric information such as facial features and facial contours to identify the user. Fingerprint recognition uses an optical or capacitive fingerprint sensor to scan the user's fingerprint and compare it with fingerprint templates stored in a hospital database to confirm the user's identity. Iris recognition uses an infrared camera to scan the user's iris image and perform identity matching. ID card readers use NFC (near-field communication) or optical scanning to read the ID card chip or printed information for identity verification. Medical insurance card readers read the chip or magnetic stripe information on the medical insurance card to verify the user's medical insurance status and entitlements. QR code scanners use a camera or infrared scanner to read the QR code presented by the user and match it with the hospital database. Barcode scanners read the barcode on the user's medical record to quickly retrieve relevant information. The RFID component uses RFID wireless radio frequency identification technology to automatically read the information of the RFID wristband or IC card worn, achieving contactless identity recognition. These components can be used individually or in combination to adapt to different scenarios and user needs, improving the reliability and applicability of user identity recognition. For example: Combination solution 1 is a facial recognition component combined with an ID card reading component: When the user stands in front of the hospital self-service terminal, the facial recognition camera automatically scans the face and requires the user to insert the ID card for secondary verification to ensure the accuracy of the identity. Combination solution 2 is an RFID component combined with fingerprint recognition: When the user wears an accompanying medical bracelet with an RFID chip, the identity is automatically recognized when the user approaches the accompanying medical device. Fingerprint recognition can also be used for manual verification. Combination solution 3 (quick self-service) is a QR code scanning component combined with a medical insurance card reading component: The user displays the appointment QR code on the mobile phone, and after scanning, the device automatically reads the medical insurance card information to complete the identity matching.

[0039] Furthermore, step S200 in the embodiment of the present application further includes:

[0040] Step S210: If not, activate the friendly accompanying device.

[0041] Step S220: obtaining the target user's medical companionship requirement information through the interactive medical companionship module in the friendly medical companionship device.

[0042] Step S230: activating the information processing middle platform in the smart accompanying medical electronic device, and processing the accompanying medical demand information through the information processing middle platform to obtain the target accompanying medical demand.

[0043] Step S240: Make an intelligent appointment based on the target accompanying medical treatment requirement and generate a registration form.

[0044] Step S250: Perform intelligent medical consultation according to the registration form to obtain the appointment form.

[0045] Specifically, when the target medical record does not meet the pre-set appointment constraints, for example, the appointment time has expired or is not valid; the doctor or department has been adjusted or is unavailable, the Friendly Accompanying Device is automatically launched, activating the interactive accompanying module in the Friendly Accompanying Device, notifying the user that the current appointment is invalid and guiding them to the next step.

[0046] Once the interactive accompanying module is activated, it uses voice interaction to obtain the target user's accompanying request information, that is, the user's current medical needs. For example, if the user's appointment time does not meet the hospital's regulations, the interactive accompanying module will collect the user's voice, use speech recognition technology to convert the voice into text, and determine the user's desired time range, department, and other requirements for rescheduling.

[0047] The information processing middle platform is a module in the intelligent accompanying electronic device, which is responsible for processing and analyzing the acquired user demand information and generating target accompanying demand. Activate the information processing middle platform in the intelligent accompanying electronic device, and transmit the accompanying demand information obtained from the interactive accompanying module to the information processing middle platform. The information processing middle platform uses pre-set algorithms and rules to process the accompanying demand information. For example, for the user's input of the need to see a doctor in a certain department, the information processing middle platform will standardize the department name, query the department's available reservation resources, and optimize the demand in combination with other user information (such as age, medical history, etc.), so as to obtain the target accompanying demand, that is, to clarify the next accompanying task.

[0048] Based on the target accompanying medical consultation requirements obtained by the information processing center, the intelligent accompanying electronic device connects to the hospital's appointment system and utilizes a built-in intelligent appointment algorithm to make an appointment. For example, based on the target accompanying medical consultation requirements, such as the department and time range, it searches for a suitable doctor in the hospital's appointment system and makes an appointment. Once the appointment is successful, a registration form is generated containing information such as the user's name, appointment department, doctor's name, and appointment time. All registration form information is integrated to generate an appointment form for subsequent accompanying medical consultation operations.

[0049] Through the above steps, if the appointment does not meet the requirements, the user can automatically make a new appointment and generate a registration form to ensure that the user can receive medical treatment smoothly, thereby improving the flexibility and adaptability of intelligent medical companionship.

[0050] Furthermore, step S230 includes:

[0051] Step S231: Acquire predetermined language features.

[0052] Step S232: extracting features of the medical companion requirement information based on the predetermined language features to obtain language feature parameters.

[0053] Step S233: calling a language recognition support vector machine to perform recognition analysis on the language feature parameters to obtain the target language type.

[0054] Step S234: Matching the information processing channel corresponding to the target language type in the information processing station.

[0055] Step S235: Processing the accompanying medical consultation requirement information through the information processing channel to obtain the target accompanying medical consultation requirement.

[0056] Specifically, predetermined language features are pre-set language-related characteristic patterns or standards, such as intonation, phoneme distribution, and speech rate. Language feature parameters are obtained by extracting features from the accompanying medical consultation request information based on the predetermined language features. They can reflect certain linguistic characteristics of the accompanying medical consultation request information, such as frequency, energy (volume), and vocabulary frequency.

[0057] Predetermined language features are obtained from a pre-stored language feature library. This language feature library can be constructed by linguists or developers based on the characteristics of multiple languages. The language features in the accompanying medical consultation request information are then extracted to obtain language feature parameters. For example, Mel-frequency cepstral coefficients are used to extract speech spectral features, calculate the fundamental frequency and formants of the speech, and thus distinguish the tonal characteristics of different languages.

[0058] Retrieve a trained language recognition support vector machine model. This model, trained on a large amount of labeled language data, constructs a classification hyperplane capable of classifying data across different languages. The resulting language feature parameters are fed into this support vector machine model. Based on previously learned language classification knowledge, the model analyzes these parameters to determine the most likely language for the accompanying medical request information, thereby determining the target language. The target language can be Mandarin or a local dialect.

[0059] The information processing platform stores a pre-set mapping table of information processing channels for different languages. Once the target language is determined, the corresponding information processing channel is found based on this mapping table. Each channel is equipped with a different information processing path to adapt to the characteristics of each language.

[0060] After the information processing channel is determined, the accompanying request information is sent to that channel for processing. The algorithms and programs within this channel perform various operations based on the specific content of the accompanying request information, such as semantic analysis and demand integration. For example, if the accompanying request information is in Mandarin, the semantic analysis algorithm within the channel will understand the request and transform the user's vague request into a specific accompanying request that the system can recognize. For example, "I want to see a doctor as soon as possible" can be converted into "Search for doctors with available appointments today and prioritize appointments," thereby identifying the target accompanying request.

[0061] Through the above differences, the user's language can be automatically identified and accurate accompanying services can be provided, which is especially suitable for the elderly and dialect users, greatly improving the accompanying experience and service efficiency.

[0062] Furthermore, before step S233, the following steps are also included:

[0063] Step S233-1: Obtain a dialect dataset.

[0064] Step S233 - 2 : Obtain a Mandarin Chinese dataset.

[0065] Step S233 - 3 : language features of the dialect dataset and the Mandarin dataset are collected in sequence to obtain dialect feature parameters and Mandarin feature parameters respectively.

[0066] Step S233-4: Perform machine learning on the data set formed based on the dialect feature parameters and the Mandarin feature parameters to obtain the language recognition support vector machine.

[0067] Specifically, dialect datasets contain speech data from different regional dialects, such as Cantonese, Wu, and Minnan. These datasets are used to train and optimize dialect recognition models and can be obtained from publicly available dialect speech libraries maintained by dialect research institutions. Mandarin datasets contain speech data from standard Mandarin and can be obtained from a wide range of sources, including news broadcasts, reading recordings, and Mandarin exam samples. These dialect and Mandarin datasets provide a sufficient data foundation for subsequent feature extraction and machine learning, ensuring comprehensive coverage of various linguistic phenomena in both dialects and Mandarin, thereby improving the accuracy and generalization capabilities of speech recognition support vector machines.

[0068] Use speech processing tools (such as Librosa, Praat) to extract features from the dialect dataset and the Mandarin dataset respectively, including Mel-frequency cepstral coefficients, linear prediction coefficients, pitch, etc., and then determine the characteristic parameters such as the pitch pattern, syllable distribution, and pronunciation habits of each language, obtaining the dialect characteristic parameters corresponding to various dialects and the Mandarin characteristic parameters corresponding to Mandarin. For example, Mandarin has four tones (yinping, yangping, shangsheng, qusheng); Cantonese has nine tones and includes entering tones; Minnan dialect has continuous tone sandhi, and there are changes in auxiliary words such as "a, ne" at the end of sentences.

[0069] Mix the dialect data and the Mandarin data, and label the corresponding language type tags (such as "Cantonese", "Mandarin", etc.) to form a training dataset. For example, data point 1: pitch: "four tones", pinyin structure: "standard pinyin", label: "Mandarin". Data point 2: pitch: "nine tones", pinyin structure: "non-standard pinyin", label: "Cantonese". Use the SVM algorithm to train the dataset, thereby obtaining a language recognition support vector machine. During the training process, the SVM algorithm will adjust the model parameters of the support vector machine according to the characteristic parameters in the dataset, so that it can accurately classify different language types. For example, according to the differences in pitch and pronunciation habits between the dialect characteristic parameters and the Mandarin characteristic parameters, adjust the classification boundary of the support vector machine, so that when new accompanying diagnosis demand information is input, it can accurately judge whether it is a dialect expression or a Mandarin expression, and further identify the specific language type.

[0070] The language recognition support vector machine obtained through machine learning in the above steps can accurately identify whether the accompanying diagnosis demand information belongs to a dialect or Mandarin, thereby providing a strong guarantee for accurately identifying the target language type in the subsequent process, enabling the intelligent accompanying diagnosis device to automatically adapt to different language environments, and ensuring that dialect users can smoothly obtain accompanying diagnosis services.

[0071] Furthermore, step S400 of the embodiment of the present application includes:

[0072] Step S410: Extract the first item from the multiple items. [[ID=第十四条]]

[0073] Step S420: Match the first person flow of the first consulting room corresponding to the first item in the real-time passenger flow information.

[0074] Step S430: Obtain the first predetermined consulting duration of the first item, and combine the first person flow to obtain the first predicted queuing duration.

[0075] Step S440: Ascendingly sort the multiple items based on the first predicted queuing duration to obtain the optimal item list.

[0076] Specifically, an item is selected sequentially or randomly from the multiple items in the appointment form and recorded as the first item. The specific clinic corresponding to the first item and performing the treatment for that item is the first clinic. The first clinic is determined by searching the real-time traffic flow database for the traffic flow data for the first clinic corresponding to the first item.

[0077] The first scheduled treatment time of the first project is obtained from the pre-stored project information library, that is, the pre-set length of time required to complete the first project. This project information library is established based on the hospital's historical data, medical standards, etc. Then, combined with the obtained first flow of people, the first predicted queuing time is calculated according to the queuing model (such as a simple average service time model: predicted queuing time = current number of people × average treatment time / number of people that can be served per unit time). For example, if the first flow of people is 10 people, the first scheduled treatment time is 10 minutes, and the number of people that can be served per unit time is 2, then the first predicted queuing time = (10×10) / 2 = 50 minutes.

[0078] Using the same method, calculate the multiple first predicted waiting times for each item in the reservation list. Then, sort the items in ascending order of their first predicted waiting times to create the optimal list of items. For example, if the predicted waiting time for item A is 30 minutes, the predicted waiting time for item B is 45 minutes, and the predicted waiting time for item C is 20 minutes, then the optimal list of items, in ascending order, would be item C, item A, and item B.

[0079] Through the above steps, according to the strategy of prioritizing the shortest waiting time, users are guided to complete all medical treatment items, reducing the overall waiting time and improving the user's medical experience.

[0080] Furthermore, step S440 includes:

[0081] Step S441: Determine the first precautions for the first project based on the expert guidance library.

[0082] Step S442: Mark the first precaution to the first project, and visually display the optimal project list.

[0083] Specifically, while generating the optimal list of items, the system connects to the expert guidance library, uses the first item as the query condition, and performs a search and match in the expert guidance library to determine the first precautions for the first item, including dietary requirements, taboos, etc., to help users better prepare for the diagnosis and treatment process and avoid delays or unnecessary risks due to lack of understanding of precautions. For example, if the first item is a gastroscopy, the system will search the expert guidance library for precautions regarding gastroscopy, such as how long to fast and drink before the examination, and whether certain medications need to be discontinued in advance.

[0084] The determined first precautions are added to the first item in a specific marking manner. For example, the content of the first precaution can be identified with a special icon or color on the interface displaying the first item. Then, the optimal project list is presented to the user using visual display technology. This visual display can be displayed in the form of a list on the screen of the smart accompanying medical device, with the corresponding precautions displayed next to each item. The items can also be arranged in a certain order (such as ascending order of queue time), and different project types can be distinguished by different colors. Marking precautions and visually displaying them improves the readability of information, allowing users to more intuitively understand the queue situation and precautions of each diagnosis and treatment item, thereby improving the user's medical experience and diagnosis and treatment efficiency.

[0085] Furthermore, after step S440, the following steps are further included:

[0086] Step S451: determining a plurality of matters needing attention for the plurality of items according to the expert guidance library.

[0087] Step S452: clustering the multiple items based on the multiple precautions to obtain a clustering result.

[0088] Step S453: extracting a first cluster from the clustering result, wherein the first cluster includes a plurality of cluster items.

[0089] Step S454: adjusting the overall priority of the plurality of clustered items in the optimal item list.

[0090] Specifically, for each item in the appointment form, the project name or project type is used as a keyword to search the expert guidance database one by one, extract the corresponding precautions before and after the inspection, and obtain multiple precautions.

[0091] Clustering algorithms (such as K-Means clustering or hierarchical clustering) are used to cluster multiple items based on the similarity of multiple precautions. By comparing key information in the precautions, such as whether there are the same preparation requirements, whether the same body parts are operated on, etc., items with similar precautions can be grouped together to obtain clustering results. For example, Cluster 1 (fasting requirement): blood test; Cluster 2 (drinking water required): B-ultrasound; Cluster 3 (metal ban): CT, MRI; Cluster 4 (avoid exercise): electrocardiogram. By clustering, items with similar precautions are grouped together, which facilitates the overall planning and management of diagnosis and treatment items and reduces unnecessary process adjustments for users.

[0092] From the clustering results, a cluster is selected as the first cluster, which contains multiple cluster items. This selection can be based on the size of the clusters, such as selecting the cluster with the most items first; or based on the order of importance of the items, such as selecting the cluster containing key diagnosis and treatment items first.

[0093] In the optimal item list, the multiple cluster items in the first cluster are adjusted as a whole based on their mutual relationships, their relevance to other items, the urgency of diagnosis and treatment, etc. For example, if the items in the first cluster are all urgent examination items that need to be completed as soon as possible, the order of these items in the optimal item list can be advanced as a whole to reduce waiting time and unnecessary repeated preparation, improve overall diagnosis and treatment efficiency, and optimize the user's treatment experience.

[0094] In summary, the embodiment of the present application provides an elderly-friendly intelligent accompanying diagnosis method with the following features:

[0095] Beneficial effects:

[0096] The embodiment of the present application activates the biometric identifier and utilizes multiple biometric components to accurately identify the user's identity, simplifying the verification process and improving security. Then, the user's medical records are retrieved to determine the compliance with the appointment constraints. If not, the friendly accompanying device is activated, and the user's needs are obtained through the interactive module. After processing by the information processing center, an intelligent appointment registration is made to ensure service continuity and efficiency. Subsequently, the flow of people is dynamically monitored and the project priority is analyzed in combination with the expert guidance library to generate an optimal project list to achieve resource optimization and efficiency improvement. Finally, the friendly accompanying device is used to intelligently accompany the patient according to the list, integrate the precautions of the expert guidance library and display them visually, and further optimize the order of projects through cluster analysis and priority adjustment, thereby comprehensively improving the medical experience of elderly users and making the accompanying service more intelligent, personalized and efficient.

[0097] Overall, the embodiments of the present application fully consider the hospital environment and the individual conditions of users to optimize and adjust the diagnosis and treatment process, reduce the waiting time for elderly users to see a doctor, improve the efficiency of accompanying the doctor, and enhance the intelligence and personalization level of the accompanying doctor service, thereby comprehensively improving the medical experience of elderly users.

[0098] Example 2, as Figure 2 As shown, based on the same inventive concept as the aforementioned embodiment 1, this embodiment of the present application provides an elderly-friendly intelligent accompanying medical system, comprising:

[0099] The biometric information recognition unit 10 is used to activate the biometric identifier and perform biometric information recognition on the target user through the biometric identifier to obtain the target identity, wherein the biometric identifier is mounted on the intelligent accompanying electronic device.

[0100] The appointment constraint judgment unit is used to retrieve the target diagnosis and treatment record based on the target identity and judge whether the target diagnosis and treatment record meets the predetermined appointment constraint.

[0101] The appointment form extracting unit 30 is configured to extract the appointment form in the target medical record if the condition is met, wherein the appointment form includes a plurality of items.

[0102] The project priority analysis unit 40 is used to dynamically monitor and obtain real-time pedestrian flow information, and to retrieve an expert guidance library to perform priority analysis on the multiple projects to obtain an optimal project list.

[0103] The intelligent accompanying diagnosis activation unit 50 is used to activate the friendly accompanying diagnosis device installed in the intelligent accompanying diagnosis electronic device, and perform intelligent accompanying diagnosis on the target user according to the optimal item list.

[0104] Furthermore, the biometric identifier described in the embodiment of the present application includes one or more combinations of a face recognition component, a fingerprint recognition component, an iris recognition component, an ID card reading component, a medical insurance card reading component, a QR code scanning component, a barcode scanning component and a radio frequency identification component.

[0105] Furthermore, the reservation constraint determination unit in the embodiment of the present application is further configured to perform the following steps:

[0106] If it does not meet the requirements, the friendly accompanying device is activated; the accompanying requirement information of the target user is obtained through the interactive accompanying module in the friendly accompanying device; the information processing middle platform in the intelligent accompanying electronic device is activated, and the accompanying requirement information is processed by the information processing middle platform to obtain the target accompanying requirement; an intelligent appointment is made based on the target accompanying requirement, and a registration form is generated; an intelligent accompanying is made according to the registration form to obtain the appointment form.

[0107] Furthermore, the reservation constraint determination unit in the embodiment of the present application is further configured to perform the following steps:

[0108] Acquire predetermined language features; perform feature extraction on the accompanying medical consultation requirement information based on the predetermined language features to obtain language feature parameters; call a language recognition support vector machine to perform recognition and analysis on the language feature parameters to obtain a target language type; match the information processing channel corresponding to the target language type in the information processing center; process the accompanying medical consultation requirement information through the information processing channel to obtain the target accompanying medical consultation requirement.

[0109] Furthermore, the system of the embodiment of the present application further includes a language recognition support vector machine training module, wherein the language recognition support vector machine training module is configured to perform the following steps:

[0110] Obtain a dialect data set; obtain a Mandarin data set; collect language features of the dialect data set and the Mandarin data set in turn to obtain dialect feature parameters and Mandarin feature parameters respectively; perform machine learning on the data set constructed based on the dialect feature parameters and the Mandarin feature parameters to obtain the language recognition support vector machine.

[0111] Furthermore, the project priority analysis unit 40 of the embodiment of the present application is further configured to perform the following steps:

[0112] Extract the first item from the multiple items; match the first traffic flow of the first treatment room corresponding to the first item in the real-time traffic flow information; obtain the first scheduled treatment time of the first item, and obtain the first predicted queuing time in combination with the first traffic flow; arrange the multiple items in ascending order based on the first predicted queuing time to obtain the optimal item list.

[0113] Furthermore, the project priority analysis unit 40 of the embodiment of the present application is further configured to perform the following steps:

[0114] According to the expert guidance library, a first point of attention for the first project is determined; the first point of attention is marked to the first project, and the optimal project list is visually displayed.

[0115] Furthermore, the project priority analysis unit 40 of the embodiment of the present application is further configured to perform the following steps:

[0116] Determine multiple precautions for the multiple projects based on the expert guidance library; cluster the multiple projects based on the multiple precautions to obtain clustering results; extract a first cluster cluster from the clustering results, wherein the first cluster cluster includes multiple cluster projects; and adjust the overall priority of the multiple cluster projects in the optimal project list.

[0117] Through the above detailed description of an elderly-friendly intelligent accompanying medical treatment method in this specification, those skilled in the art can clearly understand that this embodiment provides an elderly-friendly intelligent accompanying medical treatment system. For the system disclosed in Example 2, since it corresponds to the method disclosed in Example 1 and has corresponding functional modules and beneficial effects, the relevant details can be referred to the method section.

[0118] Example 3. Based on the same inventive concept of an elderly-friendly intelligent accompanying medical method in the aforementioned Example 1, the present application also provides an electronic device, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the method described in the aforementioned Example 1.

[0119] like Figure 3 As shown, the bus architecture is represented by bus 300, which can include any number of interconnected buses and bridges. Bus 300 connects various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 can also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are all well known in the art and therefore will not be described further herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 can be the same component, namely a transceiver, which provides a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 can be used to store data used by processor 302 when performing operations.

[0120] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An elderly-friendly intelligent accompanying medical method, characterized in that: include: activating a biometric identifier and performing biometric identification on a target user through the biometric identifier to obtain the target identity, wherein the biometric identifier is mounted on an intelligent accompanying electronic device; Retrieving target diagnosis and treatment records based on the target identity, and determining whether the target diagnosis and treatment records comply with predetermined appointment constraints; If it is consistent, extracting the appointment form in the target medical record, wherein the appointment form includes multiple items; Dynamic monitoring obtains real-time traffic information, and retrieves expert guidance database to conduct priority analysis on the multiple projects to obtain the optimal project list; Activate the friendly accompanying device installed in the intelligent accompanying electronic device to perform intelligent accompanying diagnosis on the target user according to the optimal item list.

2. The elderly-friendly intelligent accompanying medical treatment method according to claim 1, characterized in that: The biometric identifier includes one or more combinations of a face recognition component, a fingerprint recognition component, an iris recognition component, an ID card reading component, a medical insurance card reading component, a QR code scanning component, a barcode scanning component and a radio frequency identification component.

3. The elderly-friendly intelligent accompanying medical treatment method according to claim 1, characterized in that: Retrieving target diagnosis and treatment records based on the target identity and determining whether the target diagnosis and treatment records comply with predetermined appointment constraints further includes: If not, activating the friendly companion device; Acquiring the target user's medical companionship demand information through the interactive medical companionship module in the friendly medical companionship device; activating an information processing middle platform in the intelligent accompanying medical device, and processing the accompanying medical requirement information through the information processing middle platform to obtain a target accompanying medical requirement; Make an intelligent appointment based on the target accompanying medical needs and generate a registration form; Perform intelligent accompanying consultation according to the registration form to obtain the appointment form.

4. The elderly-friendly intelligent accompanying medical treatment method according to claim 3, characterized in that: The information processing center processes the accompanying medical consultation requirement information to obtain the target accompanying medical consultation requirement, including: Obtaining predetermined language features; Extracting features of the accompanying medical consultation requirement information based on the predetermined language features to obtain language feature parameters; Retrieving a language recognition support vector machine to perform recognition and analysis on the language feature parameters to obtain the target language type; Matching the information processing channel corresponding to the target language type in the information processing station; The accompanying medical consultation requirement information is processed through the information processing channel to obtain the target accompanying medical consultation requirement.

5. The elderly-friendly intelligent accompanying medical treatment method according to claim 4, characterized in that: Before calling the language recognition support vector machine to perform recognition and analysis on the language feature parameters to obtain the target language type, the method further includes: Get the dialect dataset; Get the Mandarin Chinese dataset; Collecting language features of the dialect dataset and the Mandarin dataset in sequence to obtain dialect feature parameters and Mandarin feature parameters respectively; Machine learning is performed on a data set formed based on the dialect feature parameters and the Mandarin feature parameters to obtain the language recognition support vector machine.

6. The elderly-friendly intelligent accompanying medical treatment method according to claim 1, characterized in that: Dynamic monitoring obtains real-time traffic information, and the expert guidance library is used to conduct priority analysis on the multiple projects to obtain the optimal project list, including: extracting a first item from the plurality of items; Matching the first flow of people in the first consulting room corresponding to the first item in the real-time flow of people information; Obtaining a first scheduled treatment duration for the first item, and combining this with the first passenger flow to obtain a first predicted waiting time; The plurality of items are arranged in ascending order based on the first predicted queuing time to obtain the optimal item list.

7. The elderly-friendly intelligent accompanying medical treatment method according to claim 6, characterized in that: Arranging the plurality of items in ascending order based on the first predicted queuing time to obtain the optimal item list includes: Determining a first consideration for the first project based on the expert guidance database; The first consideration is marked on the first project, and the optimal project list is visually displayed.

8. The elderly-friendly intelligent accompanying medical treatment method according to claim 7, characterized in that: After arranging the plurality of items in ascending order based on the first predicted queuing time to obtain the optimal item list, the method further includes: determining a plurality of considerations for the plurality of projects according to the expert guidance library; Clustering the multiple items based on the multiple precautions to obtain a clustering result; Extracting a first cluster from the clustering result, wherein the first cluster includes a plurality of cluster items; An overall priority adjustment is performed on the plurality of clustered items in the optimal item list.

9. An elderly-friendly intelligent medical companion system, characterized by: The system is used to execute the elderly-friendly intelligent accompanying medical treatment method according to any one of claims 1 to 8, comprising: A biometric information recognition unit is used to activate a biometric identifier and perform biometric information recognition on a target user through the biometric identifier to obtain the target identity, wherein the biometric identifier is mounted on an intelligent accompanying electronic device; an appointment constraint judgment unit, configured to retrieve a target diagnosis and treatment record based on the target identity and judge whether the target diagnosis and treatment record complies with a predetermined appointment constraint; An appointment form extracting unit, configured to extract the appointment form in the target medical record if the conditions are met, wherein the appointment form includes a plurality of items; A project priority analysis unit is used to dynamically monitor and obtain real-time traffic information, and to retrieve an expert guidance library to perform priority analysis on the multiple projects to obtain an optimal project list; The intelligent accompanying diagnosis activation unit is used to activate the friendly accompanying diagnosis device installed in the intelligent accompanying diagnosis electronic device, and perform intelligent accompanying diagnosis on the target user according to the optimal item list.

10. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the elderly-friendly intelligent accompanying medical treatment method described in any one of claims 1-8 are implemented.

Images