Intelligent waiting area propaganda and education method and system based on AI

Abstract

The invention discloses an AI-based intelligent waiting area propaganda and education method and system, and belongs to the technical field of medical informatization. Through a modularized system design and an AI-based intelligent analysis technology, precise, personalized and dynamic management of the propaganda and education content of the waiting area is realized. All the modules cooperate with one another, and a set of efficient waiting area propaganda and education system is constructed from multi-dimensional tagging labeling of propaganda and education data to comprehensive collection and analysis of real-time states of waiting areas and then content matching and dynamic playing based on an intelligent algorithm. Compared with a traditional propaganda and education mode, the method has the advantages that the integrating degree of propaganda and education content and patient requirements is remarkably improved, dependence of manual intervention is reduced, and the automation level of the system and the health education acceptance rate of patients are improved. Meanwhile, the system can flexibly adjust a content pushing and playing plan according to the real-time state of the waiting area, the waiting anxiety of the patient is effectively relieved, and the hospital service efficiency and the doctor-patient relationship are optimized.

Description

Technical Field

[0001] The present application relates to the field of medical information technology, and in particular to an AI-based intelligent waiting area education method and system. Background Art

[0002] In modern hospitals, outpatient clinics are the starting point for patients to see a doctor and are also one of the windows for the hospital's service quality. As an important part of the outpatient clinic, the waiting area undertakes the functions of patient reception, triage, nursing guidance and health education. Its service efficiency and quality directly affect the patient's medical experience and the harmony of the doctor-patient relationship. In order to make use of the idle time of patients in the waiting process, many hospitals have installed display screens in the waiting area to play health education videos.

[0003] However, the current mainstream waiting area education management system has the following technical deficiencies and limitations. Lack of flexibility in playback content: Traditional systems usually use preset playback content and sequence, and can only achieve loop playback of fixed content. It is impossible to flexibly adjust the playback content according to the real-time status of the waiting area (such as whether there are patients waiting, the number and category of waiting patients, etc.), resulting in poor applicability and pertinence of the content. Insufficient personalized education capabilities: The current education system lacks intelligent analysis capabilities and cannot make personalized content recommendations based on the actual situation of waiting patients (such as age, gender, treatment department and specific diseases). There is a large deviation between the playback content and patient needs, making it difficult to achieve accurate health education. High content repetitiveness: The health education content played in the waiting area is mostly pre-uploaded materials. Long-term loop playback of the same content can easily cause patients to be distracted or aesthetically fatigued, making it difficult to achieve the purpose of health education. High dependence on manual intervention: Traditional systems require medical staff or administrators to manually upload education content, arrange playback sequence and adjust playback plans, which increases the management burden of medical institutions and also limits the flexibility and real-time performance of system operation.

[0004] With the rapid development of artificial intelligence (AI) technology, it has been gradually applied to multiple links in the medical field, such as image analysis, auxiliary diagnosis and patient management. Combining AI technology to build an intelligent waiting area education system can effectively solve the technical limitations of traditional systems. By collecting waiting area status information and patient information in real time, intelligently matching and pushing personalized education content, it can improve the pertinence, automation and patient satisfaction of health education. Therefore, the development of an AI-based intelligent waiting area education system is of great significance to optimizing waiting management and improving the quality of medical services. Summary of the invention

[0005] The embodiment of the present application provides an AI-based intelligent waiting area education method and system. The technical solution is as follows:

[0006] According to one aspect of the present application, an AI-based intelligent waiting area education system is provided, the system comprising:

[0007] The education material management module is used to receive and store the education material, label the education material in multiple dimensions, and generate labels related to the video type, suitable population, department, disease, and playback time;

[0008] The waiting area status collection module is used to obtain the waiting area status information from the external queuing system and the waiting area monitoring equipment, including the patient's age, treatment department, waiting queue status, number of patients waiting and expected waiting time;

[0009] A waiting area status analysis module, used to analyze the waiting area status information acquired by the waiting area status acquisition module, and generate patient labels, waiting area status labels and waiting priority information;

[0010] The education content matching module is used to match the patient label and the waiting area status label generated by the waiting area status analysis module with the label of the education material stored in the education material management module, and dynamically generate an education content playback queue;

[0011] The education playback module is used to play the matching education content in sequence on the display screen in the waiting area according to the education content playback queue, and provide real-time feedback on the playback status.

[0012] Optionally, the educational material management module analyzes the text description content of the educational material through natural language processing (NLP) technology, and labels and classifies the video content in combination with video frame recognition technology.

[0013] Optionally, the waiting area status acquisition module synchronizes patient information in the queuing system in real time, and obtains the number of patients in the waiting area and the dynamic status of the area through the waiting area monitoring equipment.

[0014] Optionally, the waiting area status analysis module predicts the waiting time of waiting patients through a machine learning model, and generates patient labels based on patient information, including population labels, disease labels and waiting priority labels.

[0015] Optionally, the education content matching module adopts a multi-dimensional weighted algorithm to calculate the content priority according to the similarity between the patient tag and the education material tag, and generates a playback queue.

[0016] Optionally, the education and playback module supports a multi-screen playback mode and is used to dynamically adjust playback content based on playback status feedback.

[0017] On the other hand, an AI-based intelligent waiting area education method is provided, the method is used in the above-mentioned AI-based intelligent waiting area education system, and the method comprises:

[0018] The education material management module receives and stores the education material, and labels the education material in multiple dimensions;

[0019] The waiting area status acquisition module acquires the waiting area status information in real time, including patient information, the number of patients in the waiting area, and the waiting queue status;

[0020] Analyze the waiting area status information through the waiting area status analysis module to generate patient labels, waiting area status labels and waiting priorities;

[0021] Through the education content matching module, the most suitable education content is matched according to the patient tag and the waiting area status tag under the matching algorithm, and a play queue is generated;

[0022] The content is played in sequence according to the play queue through the propaganda and education play module, and the play plan is dynamically adjusted according to the play feedback.

[0023] Optionally, the multi-dimensional labeling of the missionary materials includes:

[0024] NLP technology is used to extract semantic information from text descriptions of educational materials, and video frame recognition technology is used to classify and annotate video content.

[0025] Optionally, the matching algorithm includes:

[0026] The content relevance score is calculated based on the similarity between the patient label and the educational material label;

[0027] The duration score is calculated based on the matching degree between the expected waiting time of patients and the duration of the educational content playback;

[0028] The content relevance score and duration score are combined to generate a play queue and determine the play priority.

[0029] On the other hand, a computer-readable storage medium is provided, wherein the storage medium stores at least one instruction, and the at least one instruction is used to be executed by a processor to implement the AI-based intelligent waiting area education method as described in the above aspects.

[0030] In the embodiment of the present application, an AI-based intelligent waiting area education system is provided, which is particularly suitable for the field of medical information technology. Through modular system design and AI-based intelligent analysis technology, accurate, personalized and dynamic management of the waiting area education content is achieved. The modules work together to build an efficient waiting area education system from multi-dimensional labeling of education materials to comprehensive collection and analysis of the real-time status of the waiting area, and then to content matching and dynamic playback based on intelligent algorithms. Compared with the traditional education model, it significantly improves the fit between the education content and patient needs, reduces the reliance on manual intervention, and improves the automation level of the system and the patient's acceptance rate of health education. At the same time, the system can also flexibly adjust the content push and playback plan according to the real-time status of the waiting area, effectively alleviating the patient's waiting anxiety and optimizing the hospital service efficiency and doctor-patient relationship. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a structural diagram of an AI-based intelligent waiting area education system provided by an exemplary embodiment of the present application;

[0032] Figure 2 A flow chart of an AI-based intelligent waiting area education method provided by an exemplary embodiment of the present application is shown. DETAILED DESCRIPTION

[0033] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0034] The term "multiple" as used herein refers to two or more than two. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the related objects are in an "or" relationship.

[0035] Example 1

[0036] like Figure 1 As shown, a structural diagram of an AI-based intelligent waiting area education system is shown, which includes an education material management module, a waiting area status collection module, a waiting area status analysis module, an education content matching module and an education playback module.

[0037] The education material management module is used to receive and store the education material, label the education material in multiple dimensions, and generate labels related to the video type, suitable population, department, disease and playback time.

[0038] Optionally, the educational material management module analyzes the text description content of the educational material through natural language processing (NLP) technology, and labels and classifies the video content in combination with video frame recognition technology.

[0039] Furthermore, the education material management module not only supports multi-dimensional labeling based on NLP technology and video frame recognition technology, but also uses deep learning models to analyze historical playback data and dynamically optimize the label system. For example, the weight of the label can be adjusted by learning patient feedback (such as viewing completion and health survey results after playback) to improve the accuracy of the label. At the same time, knowledge graph technology can be introduced to associate video labels with relevant disease science content and the latest medical research progress to build an education content knowledge base with dynamic update capabilities. It improves the accuracy and dynamic update capabilities of education materials, optimizes the system's adaptive matching efficiency, and further enhances the effect of education.

[0040] The waiting area status collection module is used to obtain the waiting area status information from the external queuing system and the waiting area monitoring equipment, including the patient's age, treatment department, waiting queue status, number of people waiting and expected waiting time.

[0041] Optionally, the waiting area status acquisition module synchronizes patient information in the queuing system in real time, and obtains the number of patients in the waiting area and the dynamic status of the area through the waiting area monitoring equipment.

[0042] Furthermore, the waiting area status acquisition module can integrate multi-sensor data, including queuing system, smart camera and RFID equipment, not only to obtain waiting patient information in real time, but also to automatically identify the patient's identity through face recognition technology, and analyze the patient's tension and emotional state in combination with emotion recognition. In addition, by integrating infrared sensors to detect the crowd density and temperature and humidity information in the waiting area, data support is provided for the dynamic adjustment of the waiting environment. The multi-dimensional acquisition of the waiting area status is realized, which can fully capture the patient's dynamics and waiting environment information, and provide richer support for the accurate matching of education content.

[0043] The waiting area status analysis module is used to analyze the waiting area status information obtained by the waiting area status acquisition module to generate patient labels, waiting area status labels and waiting priority information.

[0044] Optionally, the waiting area status analysis module predicts the waiting time of waiting patients through a machine learning model, and generates patient labels based on patient information, including population labels, disease labels and waiting priority labels.

[0045] Furthermore, the waiting area status analysis module combines time series prediction models (such as LSTM) to predict the future trends of the waiting area status, such as the dynamic changes in waiting time, the changing trend of the number of people in line, etc. At the same time, the module introduces individual portrait technology, combines the patient's previous medical records and personal health records, and generates a comprehensive health portrait of the patient, providing a more accurate basis for subsequent matching. Through the fusion of prediction models and individual health portraits, possible abnormal waiting conditions (such as long waiting times) can be identified in advance and the patient experience can be optimized, while greatly improving the matching accuracy of educational content.

[0046] The education content matching module is used to match the patient label and waiting area status label generated by the waiting area status analysis module with the label of the education material stored in the education material management module, and dynamically generate an education content playback queue.

[0047] Optionally, the education content matching module adopts a multi-dimensional weighted algorithm to calculate the content priority according to the similarity between the patient tag and the education material tag, and generates a playback queue.

[0048] Furthermore, the education content matching module introduces a deep recommendation algorithm (such as a Transformer-based recommendation model) into the matching algorithm, combines the patient's health profile, the waiting area status label and the education content label, and dynamically adjusts the matching weight. In addition, the module can balance the diversity and personalized needs of the education content through a multi-objective optimization algorithm, avoiding repeated playback of content while achieving accurate matching. The intelligence level of the matching algorithm is improved, making the recommendation results more in line with patient needs, while also improving the coverage and diversity of the education content in the waiting area.

[0049] The education playback module is used to play the matching education content in sequence on the display screen in the waiting area according to the education content playback queue, and provide real-time feedback on the playback status.

[0050] Optionally, the education and playback module supports a multi-screen playback mode and is used to dynamically adjust playback content based on playback status feedback.

[0051] Furthermore, the education and playback module can dynamically adjust the playback content and screen display mode based on real-time feedback from users' viewing behavior (such as viewing time, interactive behavior) and external environmental information (such as noise level, lighting conditions). In addition, the module supports multi-terminal collaborative playback and can simultaneously push the education content to the patient's mobile device so that the patient can continue to watch the unfinished content after the waiting period. This enhances the flexibility and continuity of the playback of education content, while improving patients' attention and acceptance of the content.

[0052] like Figure 1As shown in the figure, a modular structure of an AI-based intelligent waiting area education system is demonstrated. The system forms a complete waiting area education closed loop through external data input, core module processing, information matching and playback output. The figure includes the external system interface, five core modules (education data management module, waiting area status acquisition module, waiting area status analysis module, education content matching module, education playback module) and the output end (waiting area display screen and patient mobile device). The modules are interconnected through information flow to collaboratively realize the precise, personalized and dynamic management of the waiting area education content.

[0053] The queuing system interface obtains basic patient information from the external hospital queuing system in real time, including the patient's age, department, queue number, and expected waiting time. These data are passed as input to the waiting area status acquisition module.

[0054] In one example, the monitoring device interface collects real-time dynamic information in the waiting area through monitoring devices such as smart cameras in the waiting area, such as the number of patients in the waiting area, emotional state, regional activities, etc. The collected data is also transmitted to the waiting area status acquisition module for analyzing the waiting status. The education material management module is used to receive and store the education materials uploaded by the hospital (such as health education videos and their text descriptions). The text description is semantically extracted through natural language processing (NLP) technology, and the video content is labeled and annotated in combination with video frame recognition technology. The generated tags include video type (such as preventive health care knowledge, disease knowledge, etc.), suitable population (such as children, the elderly), relevant departments (such as endocrinology, cardiovascular medicine) and playback time, etc. The waiting area status acquisition module obtains the dynamic status information of the waiting area in real time, including patient information (such as age, treatment department, queuing status, etc.), real-time number of people in the waiting area and dynamic activities. Through data interaction with the external system interface, the module can continuously update the real-time status of the waiting area. The waiting area status analysis module analyzes and processes the data obtained by the waiting area status collection module, and generates patient tags (such as age group, gender, disease type, and appropriate content category) and waiting area status tags (such as waiting time, patient crowding, and current area dynamic status) based on AI technology. The education content matching module calculates the content priority through a multi-dimensional weighted matching algorithm based on patient tags, waiting area status tags, and content tags stored in the education material management module. The education playback module plays the content in sequence on the waiting area display screen or the patient's mobile device according to the playback queue generated by the education content matching module. At the same time, this module supports multi-screen playback mode and real-time feedback mechanism. Feedback information on the playback status (such as patient viewing completion rate and playback effect) will be transmitted back to the education content matching module for further optimization of the playback plan.

[0055] Finally, at the output end, the display screen in the waiting area plays educational content to provide health education information to waiting patients; the patient's mobile device simultaneously pushes educational content so that the patient can continue to watch the unfinished video after leaving the waiting area, thereby improving the coverage of health education.

[0056] It can be seen that through Figure 1 The structured representation can clearly understand how the system realizes the labeling of educational materials, the collection and analysis of waiting area information, the intelligent matching of content, and dynamic playback and feedback through modular design, ultimately forming a complete closed loop of the intelligent waiting area education system.

[0057] In summary, in the embodiment of the present application, through the modular system structure design, each module has clear functions and cooperates with each other, which significantly improves the overall intelligence level of the waiting area education system. The use of AI technology fully realizes the personalization, precision and automatic playback of education content, and optimizes the hospital resource allocation and patient experience.

[0058] Example 2

[0059] On the other hand, Figure 2 As shown, an AI-based intelligent waiting area education method is provided, and the method is used in the above-mentioned AI-based intelligent waiting area education system, and the method includes:

[0060] Step 201: Receive and store the education materials through the education materials management module, and label the education materials in multiple dimensions.

[0061] In a possible implementation, the propaganda materials are labeled in a multi-dimensional manner, including the following: semantic extraction of text descriptions of the propaganda materials is performed using NLP technology, and the video content is classified and labeled in combination with video frame recognition technology.

[0062] In the embodiments of the present application, the multi-dimensional labeling is further refined, and the emotional tendencies in the text (such as "prevention", "warning", "comfort", etc.) are extracted through semantic analysis technology, and emotional labels are generated. At the same time, combined with the dynamic scene recognition of the video content (such as slow motion explanation, key markup, etc.), video interactive labels are generated. The label system is more comprehensive and can accurately push content according to different patient needs (such as educational guidance or emotional comfort).

[0063] Step 202: The waiting area status information is obtained in real time through the waiting area status collection module, including patient information, the number of patients in the waiting area, and the waiting queue status.

[0064] In the embodiment of the present application, the waiting area status acquisition module integrates the environmental parameters of the waiting area (such as air quality, temperature and humidity, and light intensity), and uses emotion recognition technology to identify the patient's facial expressions and behavioral characteristics (such as anxiety, boredom, fatigue, etc.), providing more dimensional input for subsequent status analysis and content matching. This improves the comprehensiveness of the waiting area status information and provides a more accurate decision-making basis for subsequent analysis.

[0065] Step 203: Analyze the waiting area status information through the waiting area status analysis module to generate patient labels, waiting area status labels and waiting priorities.

[0066] In an embodiment of the present application, the waiting area state analysis module combines emotion recognition and time series prediction models (such as RNN) to analyze the patient's emotional state, waiting time trend, and dynamic changes in the number of waiting people. At the same time, the patient's health records and historical waiting records are introduced to dynamically adjust the weight of the patient's label. For example, short videos are recommended to patients who have not completed the educational content viewing for many times. The depth of state analysis is enhanced, and it can dynamically adapt to the patient's psychological and physiological state, further improving the accuracy of content matching.

[0067] Step 204: The education content matching module matches the most appropriate education content according to the patient tag and the waiting area status tag under the matching algorithm, and generates a play queue.

[0068] In one possible implementation, the matching algorithm includes calculating a content relevance score based on the similarity between a patient tag and an educational material tag; calculating a duration score based on the match between an estimated waiting time of a waiting patient and the duration of the educational content; and generating a playback queue and determining a playback priority based on the content relevance score and duration score.

[0069] In the embodiment of the present application, the matching algorithm adds a dynamic weight adjustment strategy based on reinforcement learning, and dynamically optimizes the recommendation model according to the real-time playback effect in the waiting area and the patient's immediate feedback (such as playback completion rate and interaction data). In addition, a scenario-based matching dimension is added, for example, when there are a large number of waiting patients, shorter and more widely applicable videos are played first. This significantly improves the adaptive ability and multi-scenario adaptability of the matching algorithm and optimizes the acceptance effect of the playback content.

[0070] Step 205: Play the content in sequence according to the play queue through the propaganda and play module, and dynamically adjust the play plan according to the play feedback.

[0071] In the embodiment of the present application, the education and playback module supports the patient's real-time feedback function, such as providing content evaluation and suggestions through voice or touch screen, and the system can optimize the subsequent playback content based on these data. In addition, the playback content is pushed synchronously through the mobile device, and the video resolution and loading speed are automatically adjusted according to the network status of the patient's device. The interactivity and continuity of the playback process are improved, and the real-time nature of content push and viewing experience are optimized.

[0072] The following example illustrates this.

[0073] In one example, the education material management module receives a health education video with the video description "Dietary considerations for patients with hypertension". By analyzing the text description with NLP technology, the system generates video tags [hypertension] [diet] [health] [prevention], and combines AI video recognition technology to generate department tags [cardiovascular medicine] and suitable population tags [adults, elderly]. After the tagging is completed, the video is stored in the education material library.

[0074] In another example, the waiting area status acquisition module obtains the waiting area status information from the external queuing system: Patient A, age 65, is in the cardiovascular department, the current waiting status is in normal queue, and the estimated waiting time is 15 minutes. The waiting area status analysis module analyzes the status of patient A and generates patient tags [Elderly] [Cardiovascular Department] [Waiting Status: In Queue] [Estimated Waiting Time: 10-20 Minutes].

[0075] In another example, the education content matching module selects education content from the education database based on the label and waiting area status of patient A. Through the weighted matching algorithm, the education materials with content labels of [hypertension] [diet] [elderly] are preferentially selected and pushed to the education playback module, and a playback queue with a playback priority of "high" is generated.

[0076] In summary, in the embodiment of the present application, through the step-by-step operation method, the system can dynamically adapt to the real-time status of the waiting area and the needs of patients. Multi-dimensional labeling, precise matching algorithm and dynamic playback plan optimization enable patients to efficiently receive educational content closely related to their health needs during the waiting period, greatly improving the effect of health education and patient satisfaction.

[0077] An embodiment of the present application also provides a computer-readable medium storing at least one instruction, wherein the at least one instruction is loaded and executed by the processor to implement the AI-based intelligent waiting area education method as described in the above embodiments.

[0078] The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. An AI-based intelligent waiting area education system, characterized in that: The system comprises: The education material management module is used to receive and store the education material, label the education material in multiple dimensions, and generate labels related to the video type, suitable population, department, disease, and playback time; The waiting area status collection module is used to obtain the waiting area status information from the external queuing system and the waiting area monitoring equipment, including the patient's age, treatment department, waiting queue status, number of patients waiting and expected waiting time; A waiting area status analysis module, used to analyze the waiting area status information acquired by the waiting area status acquisition module, and generate patient labels, waiting area status labels and waiting priority information; The education content matching module is used to match the patient label and the waiting area status label generated by the waiting area status analysis module with the label of the education material stored in the education material management module, and dynamically generate an education content playback queue; The education playback module is used to play the matching education content in sequence on the display screen in the waiting area according to the education content playback queue, and provide real-time feedback on the playback status.

2. The system according to claim 1, characterized in that The educational material management module analyzes the text description content of the educational material through natural language processing (NLP) technology, and labels and classifies the video content in combination with video frame recognition technology.

3. The system according to claim 1, characterized in that The waiting area status acquisition module synchronizes the patient information in the queuing system in real time, and obtains the number of patients and the dynamic status of the area in the waiting area through the waiting area monitoring equipment.

4. The system according to claim 1, characterized in that The waiting area status analysis module predicts the waiting time of waiting patients through a machine learning model, and generates patient labels based on patient information, including population labels, disease labels, and waiting priority labels.

5. The system according to claim 1, characterized in that The education content matching module adopts a multi-dimensional weighted algorithm to calculate the content priority according to the similarity between the patient label and the education material label, and generates a play queue.

6. The system according to claim 1, characterized in that The education and playback module supports a multi-screen playback mode and is used to dynamically adjust playback content based on playback status feedback.

7. An AI-based intelligent waiting area education method, characterized in that: The method is used in the AI-based intelligent waiting area education system according to any one of claims 1 to 6, and the method comprises: The education material management module receives and stores the education material, and labels the education material in multiple dimensions; The waiting area status acquisition module acquires the waiting area status information in real time, including patient information, the number of patients in the waiting area, and the waiting queue status; Analyze the waiting area status information through the waiting area status analysis module to generate patient labels, waiting area status labels and waiting priorities; Through the education content matching module, the most suitable education content is matched according to the patient tag and the waiting area status tag under the matching algorithm, and a play queue is generated; The content is played in sequence according to the play queue through the propaganda and education play module, and the play plan is dynamically adjusted according to the play feedback.

8. The method according to claim 7, characterized in that The multi-dimensional labeling of the missionary materials includes: NLP technology is used to extract semantic information from text descriptions of educational materials, and video frame recognition technology is used to classify and annotate video content.

9. The method according to claim 7, characterized in that: The matching algorithm comprises: The content relevance score is calculated based on the similarity between the patient label and the educational material label; The duration score is calculated based on the matching degree between the expected waiting time of patients and the duration of the educational content playback; The content relevance score and duration score are combined to generate a play queue and determine the play priority.

Images