Information processing method and system, electronic equipment and storage medium

Abstract

The invention discloses an information processing method and system, electronic equipment and a storage medium, and belongs to the technical field of medical information processing. The method comprises the steps of obtaining health state data of a user based on a user interface; classifying the health state data according to a preset medical rule, and determining category information corresponding to the health state data, the category information representing the processing priority and complexity of the health state data; determining medical resource information corresponding to the category information from a preset medical resource library; and according to the category information and the medical resource information, generating planning information corresponding to processing the health state data. According to the method, the user health state data is intelligently classified, and the plan is generated in combination with the medical resource information, so that the medical resources can be reasonably allocated according to the emergency degree and complexity of the health state, the utilization efficiency of the medical resources is improved, and more accurate medical service guidance is provided for the user.

Description

Technical Field

[0001] This invention relates to the field of information processing, and more specifically to an information processing method, system, electronic device, and storage medium. Background Technology

[0002] With the rapid development of information technology, information processing methods in the healthcare field are constantly being innovated and improved. Currently, healthcare information processing mainly involves the acquisition and classification of user health status data, matching of medical resources, and treatment planning. These technological advancements have greatly improved the efficiency of medical resource utilization and enhanced patients' healthcare experience.

[0003] However, existing technologies still have the following problems: First, medical triage technologies based on large-scale models cannot effectively guide users to fully describe their own conditions during processing, resulting in generation stability issues and difficulty in ensuring the consistency of consultation quality. Second, while decision tree-based medical triage technologies have a clear structure, they suffer from cumbersome steps and rigid question content, failing to flexibly adjust the inquiry path based on the user's actual response. Third, existing technologies are usually limited to the resources of a single medical institution; users can only inquire on the triage system of one institution, unable to understand the situation of the entire medical resource system, which may lead to not obtaining the most suitable registration and consultation suggestions, uneven distribution of medical resources, and a poor user experience. Furthermore, existing technologies still have significant room for improvement in the accuracy of health data classification, the determination of processing priorities, and the dynamic matching of medical resources. Summary of the Invention

[0004] To address the technical challenges of large-scale medical triage technologies failing to guide users to fully describe their condition, decision tree-based medical triage technologies being cumbersome and rigid in their questioning, and users being unable to understand the overall medical resource system, this paper proposes an information processing method that can achieve dynamic balancing of medical resources and improve user experience.

[0005] The technical solution adopted by this invention to solve its technical problem is as follows: An information processing method is provided, the method comprising: acquiring a user's health status data based on a user interface; classifying the health status data according to preset medical rules to determine category information corresponding to the health status data; the category information being used to characterize the processing priority and complexity of the health status data; determining medical resource information corresponding to the category information from a preset medical resource database; and generating planning information corresponding to processing the health status data based on the category information and the medical resource information.

[0006] In one embodiment, acquiring user health status data based on the user interface includes: classifying user responses according to intent, and adjusting the inquiry path according to the intent classification; the inquiry path includes: if the user response is reasonable, proceeding to the next inquiry node; if the user response is unreasonable, reconstructing the inquiry content and asking the question again.

[0007] Furthermore, if the user response is unreasonable, the inquiry content is reconstructed and the question is asked again, including: generating guiding symptom descriptions based on a clinical knowledge base; performing correlation analysis on the user response; reconstructing the inquiry content based on the guiding symptom descriptions and correlation analysis; and determining the user's health status data based on the inquiry content.

[0008] In one embodiment, determining the medical resource information corresponding to the category information from a preset medical resource database includes: determining the disease type based on the health status data; filtering the preset medical resource database based on the disease type to obtain an initial resource database; filtering the initial resource database based on the health status data to obtain a target resource database; and obtaining the medical resource information based on the target resource database.

[0009] Furthermore, the process of constructing the preset resource library includes: constructing a standard medical resource classification template; and obtaining the preset medical resource library based on the mapping relationship between the departments of each medical institution and the standard medical resource classification template.

[0010] Preferably, obtaining the medical resource information based on the target resource database includes: acquiring department information from the target resource database, the department information including: scope of treatment, equipment configuration, and expert qualifications; determining the target department based on the matching degree between the disease type and the scope of treatment of the department information; and obtaining the medical resource information from the target resource database based on the target department. Further, the processing priority corresponding to the health data includes at least three levels, including: the first level of processing priority is greater than the second level, the second level is less than the first level but greater than the third level.

[0011] Preferably, the preset medical resource database includes at least one of the following dynamic parameters: the saturation of medical departments, the dynamic scheduling of specialist physicians, the availability of medical equipment, and historical medical quality evaluation data.

[0012] Furthermore, based on the category information and the medical resource information, planning information corresponding to the processing of the health status data is generated, including: generating planning information including a recommended geographical location and an execution time window based on the health status data; wherein, the recommended geographical location is determined based on the institution location in the medical resource information, and the execution time window is determined based on the at least one dynamic parameter in the medical resource information.

[0013] The present invention also provides an information processing system, characterized in that it includes:

[0014] The data acquisition module is used to acquire users' health status data based on the user interface.

[0015] The data classification module is used to classify the health status data according to preset medical rules and determine the category information corresponding to the health status data; the category information is used to characterize the processing priority and complexity of the health status data.

[0016] The information determination module is used to determine the medical resource information corresponding to the category information from a preset medical resource database;

[0017] The information generation module is used to generate planning information corresponding to the processing of the health status data based on the category information and the medical resource information.

[0018] The present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the information processing method as described above.

[0019] The present invention also provides a computer storage medium storing a computer program, which, when executed by a processor, implements the information processing method as described above.

[0020] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the information processing method as described above.

[0021] The beneficial effects of this invention are as follows: By combining decision trees and large models to construct an intelligent assisted guidance inquiry module, it intelligently guides users to answer symptom descriptions in a conversational manner, improving user experience and trust, while also obtaining a more comprehensive understanding of the user's basic condition; by using department mapping, it solves the problem of inconsistent department names among multiple hospitals, allowing the system to add new hospital department mapping files when expanding to more hospitals without requiring new code adaptation; if a higher-performance model is available, iterative upgrades can be performed at a low cost; by comprehensively utilizing decision tree technology, large model technology, structured knowledge base, and resource scheduling algorithms, it achieves dynamic balance of medical resources, solving the problems existing in current medical triage systems. Attached Figure Description

[0022] Figure 1 This is a flowchart illustrating an information processing method in one embodiment;

[0023] Figure 2This is an interactive schematic diagram of an information processing method in one embodiment;

[0024] Figure 3 This is a schematic diagram of an information processing system provided in this specification;

[0025] Figure 4 The corresponding information provided in this specification Figure 1 A schematic diagram of an electronic device. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0027] In one embodiment, an information processing method is provided that can provide appropriate medical resource planning information based on a user's health status data.

[0028] The information processing method includes the following steps:

[0029] S100 acquires user health status data based on the user interface;

[0030] User health status data may include, but is not limited to: the user's subjective description, physiological parameters, medical history, and behavior and environment. Specifically, subjective symptom descriptions include: abnormal physical sensations actively stated by the user or reported through system guidance, including but not limited to: chief complaints, objective physiological parameters, medical history background information, and environmental behaviors. Chief complaints include, but are not limited to: cough, headache, duration, or accompanying fever. Objective physiological parameters mainly consist of quantifiable vital signs, including but not limited to: body temperature, blood pressure, or characteristic parameters such as body surface condition. Medical history background information includes, but is not limited to: past medical history, surgical history, drug allergy history, or family history of genetic diseases. Environmental behaviors include, but are not limited to: exposure events, lifestyle habits, or traumatic events.

[0031] In one embodiment, the system collects user health status data through multi-turn dialogue interactions. This step includes classifying user intent based on their responses and adjusting the inquiry path accordingly. Specifically, the inquiry path involves proceeding to the next inquiry node when the user's response is reasonable, and reconstructing the inquiry and asking the question again when the response is unreasonable, ultimately obtaining the user's health status data.

[0032] In one embodiment, the system parses the user-input text or voice data in real time, obtains an intent classification model using a natural language understanding model, such as the Qwen model fine-tuned from a medical corpus, classifies the intent based on the intent classification model, identifies key symptom entities in the user's description, and outputs the classification result—labeling the response content as either "reasonable" or "unreasonable." A "reasonable" response must simultaneously meet two technical conditions: 1) It contains at least one key symptom entity that can be mapped to a medical ontology, for example, "throbbing headache" maps to the migraine symptom set; 2) The semantic integrity score is higher than a threshold θ, which in one embodiment is 0.7. The threshold can be set according to actual conditions.

[0033] In one embodiment, when a user describes a "headache": if the response is reasonable, such as adding "lasting for 3 days, accompanied by vomiting", the system proceeds to the next node according to the decision tree logic, such as asking "is the pain throbbing?". During the jump, logic conflict detection is performed. If the user has already actively described the content of the subsequent node, such as stating in advance "throbbing pain lasting for 2 hours", the corresponding node is automatically skipped and the feature value is recorded. If the response is unreasonable, such as only answering "uncomfortable", the system activates the query reconstruction mechanism.

[0034] When a user's response is unreasonable, the process of reconstructing the query and re-asking the question includes: generating guiding symptom descriptions based on a clinical knowledge base; performing correlation analysis on the user's response; reconstructing the query content based on the guiding symptom descriptions and correlation analysis; and determining the user's health status data based on the query content.

[0035] In one embodiment, when a user response is deemed unreasonable, such as a vague expression like "feeling unwell" or irrelevant content like "the weather is bad today," the system initiates a three-level reconstruction mechanism. First, it performs correlation analysis, extracting keywords from the response, such as "feeling unwell," and expanding the associated symptom set using a medical knowledge graph, expanding "feeling unwell" to include "dizziness," "fatigue," or "palpitations," etc. Second, it guides template generation, constructing a structured follow-up question template based on the symptom set, for example: "Please select the description that best matches your condition: ① Headache ② Chest tightness and shortness of breath ③ Joint pain." Third, it resets the query, resetting the current node's interaction counter to initiate a new round of queries with reconstructed content. If three consecutive responses are invalid, the system automatically skips that node and generates an exception log, while simultaneously activating manual intervention, pushing a user session snapshot and a key feature missing alert to the backend agent.

[0036] In one embodiment, the original question is "Please describe the details of your abdominal pain". After three-level reconstruction, the reconstructed question is: "Is your abdominal pain located in the lower right abdomen? Does the pain worsen when you press on it? If you are unsure, please describe the area where the pain is most pronounced".

[0037] In one embodiment, when a user's description of pain symptoms is vague, the system may generate a guiding description such as "Do you feel chest pain like a heavy object is pressing on it?" to help the user express their symptoms more accurately.

[0038] Based on the user interface and the classification results of the user's response content, the query path is adjusted. The system infers the user's possible condition based on the current description and guides the user more accurately to other possible symptoms. Through question rephrasing and conversational questioning, users can clearly understand the problem description and provide reasonable answers. Finally, the model and professional clinical medical knowledge provide the precise disease type. S102 classifies health status data according to preset medical rules, determining the corresponding category information. This category information characterizes the processing priority and complexity of the health status data. The processing priority for health data includes at least three levels, where the first level is greater than the second, and the second level is less than the first but greater than the third.

[0039] This step involves multi-dimensional assessment using health status data to generate quantifiable medical guidance indicators. The system inputs the user-provided symptom descriptions, medical history information, and vital sign data into a large language model (such as Qwen-32B) fine-tuned with professional medical knowledge, resulting in a medical big model. The system then outputs key medical guidance indicators through the following process: The medical big model, combined with a pre-built clinical decision rule base, categorizes the urgency of the condition into a three-level dynamic classification system. Level 1 represents critical illnesses requiring urgent intervention, applicable to potentially life-threatening acute conditions such as acute myocardial infarction and stroke. The priority for Level 1 treatment is based on simultaneously meeting key symptom combinations, such as chest pain radiating to the left arm and abnormal vital sign thresholds, or oxygen saturation <90% and high-risk medical history, or a history of coronary heart disease with persistent chest pain >20 minutes. These critical illnesses require emergency intervention within the critical hour.

[0040] Level 2 priority refers to progressive conditions that require treatment within a preset timeframe. This applies to diseases that may deteriorate rapidly, such as acute appendicitis. The criteria for determination include progressive worsening of symptoms, such as abdominal pain migrating to the right lower quadrant or moderate physiological abnormalities, and body temperature >39°C for 6 hours. These progressive conditions must be treated within 24 hours.

[0041] The treatment priority level three, which is a stable condition that can be treated electively, is for chronic disease management or mild symptoms, such as hypertension follow-up visits. The criteria for judgment are stable symptoms without a worsening trend and no signs of high-risk complications. The above stable conditions are allowed to be treated electively within 72 hours.

[0042] In one embodiment, the urgency of priority level 1 is greater than that of priority level 2, and the urgency of priority level 2 is greater than that of priority level 3.

[0043] In one embodiment, while determining the processing priority, the system outputs a treatment complexity score, ranging from 1 to 10. Specifically, the system calculates the complexity score based on a multi-dimensional calculation model, considering resource requirements, professional competence, and treatment difficulty. Resource requirements could be high-complexity examinations like MRI, professional competence could be cardiac surgery > general practice, and treatment difficulty could be a wound infection risk greater than 30% for diabetic patients. For example, a suspected brain tumor patient requiring neurosurgical consultation, MRI imaging, and pathological examination might receive a complexity score of 9.2. Based on these indicators, the system performs dynamic screening of medical resources: first, it initially screens the resource pool based on treatment complexity; then, it maps the screening results to a standard classification table, and finally obtains the final screening results based on the standard classification table. In one embodiment, for scenarios requiring the association of multiple departments, the system simultaneously activates a collaborative recommendation mechanism, ultimately generating structured medical resource information. For example, only tertiary hospitals with a complexity score greater than 8 are retained, excluding community hospitals and other institutions without a target department; for abdominal pain with jaundice, multiple departments need to be associated. In one embodiment, the final generated medical information resource is: Chief Physician of Cardiology Department of xx Hospital.

[0044] In one embodiment, the assessment of treatment complexity is achieved through a quantitative model: Treatment Complexity Score = Resource Requirement Coefficient × 0.5 + Professional Competency Coefficient × 0.3 + Treatment Risk Coefficient × 0.2. Where:

[0045] Resource demand coefficient (1-10 points): Basic consultation = 1 point to ECMO support = 10 points;

[0046] Professional competence coefficient (1-10 points): General practitioner = 3 points to national-level academic leader = 10 points;

[0047] Risk factor for treatment (1-10 points): Oral medication = 2 points to heart transplantation = 10 points.

[0048] In one embodiment, the score for a patient with acute necrotizing pancreatitis is calculated as (7.0 × 0.5) + (8.5 × 0.3) + (6.5 × 0.2) = 7.25 points. The scores for resource demand, professional competence, and treatment risk are as follows: enhanced CT + ICU monitoring average score 7.0, gastroenterology chief physician + critical care team average score 8.5, and organ failure risk 38% score 7 points + septic shock risk 25% score 6 points. In this embodiment, the final resource demand coefficient is 7 points, the professional competence coefficient is 8.5 points, and the treatment risk coefficient is 6.5, taking into account the risks of organ failure and septic shock.

[0049] By combining user health status and professional clinical medical information, it determines the complexity and priority of the user's current health condition, and can filter hospitals with potential risks or insufficient resources based on the complexity of the user's illness. This provides users with more accurate medical resources, ensuring the safety and effectiveness of their medical treatment. S104 determines the medical resource information corresponding to the category information from the preset medical resource database;

[0050] This step specifically includes: determining the disease type based on the health status data; filtering the preset medical resource database based on the disease type to obtain an initial resource database; filtering the initial resource database based on the health status data to obtain a target resource database; and obtaining the medical resource information based on the target resource database.

[0051] The process of building the preset resource library includes: building a standard medical resource classification template; and obtaining the preset medical resource library based on the mapping relationship between the departments of each medical institution and the standard medical resource classification template.

[0052] Obtaining the medical resource information based on the target resource database includes: acquiring department information from the target resource database, the department information including: scope of treatment, equipment configuration, and expert qualifications; determining the target department based on the matching degree between the disease type and the scope of treatment of the department information; and obtaining the medical resource information from the target resource database based on the target department. The preset medical resource database includes at least one of the following dynamic parameters: departmental patient saturation, specialist physician scheduling dynamics, medical equipment availability, and historical treatment quality evaluation data.

[0053] This system constructs a cross-institutional medical resource database through a standardized mapping framework. First, based on the National Health Commission's "Directory of Medical Institutions' Diagnosis and Treatment Subjects" and the ICD-11 disease classification system, a tree-like hierarchical standard classification template is created. This template contains a three-level structure: first-level departments, such as internal medicine and surgery; second-level specialties, such as cardiology; and third-level disease groups. Each node clearly defines the standard scope of diagnosis and treatment, equipment baseline configuration, and expert qualification requirements. For example, the coronary heart disease group includes eight types of surgeries such as "coronary stent implantation," and mandates at least two chief physicians for DSA equipment. The system uses an intelligent standardization engine for department names, employing an embedded model to calculate the similarity of the scope of diagnosis and treatment to address the actual naming differences of departments across medical institutions. For departments with different names such as "Cardiology Department I" and "Cardiac Intervention Center," keyword matching and scope of diagnosis and treatment similarity calculation are used to map them to standard template nodes. For example, a keyword similarity threshold ≥ 0.85 and a scope of diagnosis and treatment coverage ≥ 90% are required. For institutions such as community hospitals that lack corresponding departments, the system executes a vacancy marker, such as "Interventional Treatment Capability: External Collaboration"; for new departments in tertiary hospitals, it triggers a dynamic expansion process of the classification template, such as expanding the new department "Robotic Surgery Center"; when adding a new cooperating hospital, it is only necessary to add an entry to the mapping table, such as "C Hospital Heart Center → Cardiovascular Specialty", without modifying the core system code.

[0054] The final medical resource database is maintained through a daily incremental update mechanism, synchronizing basic data from the hospital's HIS system in real time to ensure that when a hospital's catheterization lab adds an IVUS device, the resource database can be updated within 24 hours.

[0055] The system receives health status data (including symptom descriptions, vital signs, and medical history) and complexity parameters from category information as input. It then performs dynamic filtering of the medical resource database according to preset resource selection rules.

[0056] In one implementation, when the complexity parameter is greater than or equal to the threshold T1 (which can be 0.8), tertiary medical institutions with multidisciplinary consultation capabilities are selected. When the treatment priority is first-level (e.g., acute chest pain, stroke, etc.), hospitals with emergency green channels are forcibly associated. Availability is verified by combining real-time dynamic parameters (e.g., department saturation < 80%, target equipment availability = normal). Based on the above, a preliminary set of qualified medical institutions is generated, forming the initial resource pool. For example, for patients with coronary heart disease (treatment complexity = 0.92), the system only retains hospital resources with cardiac intervention centers and catheterization lab saturation < 75%.

[0057] In one embodiment, the process of generating a target medical resource library based on an initial resource library includes three stages. First, the core information of the department is extracted: three-dimensional structured data is obtained from the initial resource library, including (1) treatment scope data: such as the list of 12 surgical procedures such as "interventional treatment for acute myocardial infarction" in the Department of Cardiology; (2) equipment configuration list: accurate to the model and quantity of equipment, such as "2 digital subtraction angiography machines (Artis Q type)"; (3) expert qualification files: including physician title, practice certificate number and field of expertise, such as "Li XX: Chief Physician (certificate number CN123), specializing in the treatment of complex coronary artery lesions". Second, disease type adaptation is performed: the system analyzes the key features in the health status data, identifies the disease type through a pre-trained disease classification model, and determines the target department according to the disease-department mapping rule, such as "chest pain lasting >30 min with ST segment elevation", which determines the disease type as acute myocardial infarction, and then determines the target department as the Department of Cardiology / Coronary Heart Disease Group for acute myocardial infarction. In one embodiment, for complex cases, multi-departmental collaboration is automatically triggered. For example, if the treatment complexity is >0.85, a diabetic foot patient is associated with both endocrinology and vascular surgery. Finally, medical resource information is generated: the final output is a complete set of medical resource information including the scope of treatment, equipment configuration, expert qualifications, and dynamic parameters. For example, for the aforementioned coronary artery disease patient, the output information includes: "Scope of Treatment: Coronary stent implantation," "Equipment Configuration: DSA machine (available)," "Expert Qualification: Chief Physician Li XX (on duty today)," and "Patient saturation: 68%."

[0058] In one embodiment, the dynamic parameter system integrated into the medical resource database drives resource matching decisions through multi-source real-time data (first filtering information in the medical hospital database using thresholds, then obtaining the final result through a weighted decision algorithm). The saturation parameter for medical departments is derived from the hospital's HIS system registration queue monitoring, updated every 5 minutes. When a hospital's catheterization lab saturation is detected to be >85%, that option is automatically excluded. Specialist physician scheduling dynamically integrates scheduling system data with facial recognition attendance, tracking physicians' actual on-duty status in real time to generate time windows accurate to 15 minutes, such as "Dr. Zhang is actually on duty today: 08:15-16:30". The availability status of medical equipment is obtained through device IoT sensors, uploading operational status every 15 seconds to ensure that appointments are only opened when the catheterization lab displays a "ready" status. Historical treatment quality evaluation data comes from the DRG evaluation system and patient follow-up database, updated daily at midnight. When performing resource matching, departments with a PCI surgery success rate >95% are prioritized, and institutions with a post-operative infection rate >3% are automatically avoided.

[0059] In one embodiment, dynamic parameters are collected through a four-dimensional real-time monitoring system: The saturation of medical departments is calculated every minute from the hospital's HIS system as the ratio of registrations to beds, for example, current number of patients ÷ maximum capacity × 100%; specialist physician scheduling is dynamically synchronized in real time with schedule changes, for example, updates are made immediately when a chief physician is unavailable; the availability status of medical equipment is obtained through IoT sensors, for example, the "idle / occupied" status of MRI equipment is transmitted every second; historical treatment quality is integrated daily with patient evaluation data, for example, a satisfaction rating ≥ 4.5 stars in the past 30 days is marked as a high-quality resource. Resource status assessment uses a weighted algorithm: Resource availability score = (1 - saturation) × 0.6 + Physician qualification coefficient × 0.3 + Equipment availability rate × 0.1. Taking the neurology department of a tertiary hospital as an example: saturation 92% (deduction coefficient 0.08), 1 chief physician on duty (qualification coefficient 1.0), MRI availability rate 66.7% (2 / 3 MRI machines idle), the calculated score is 0.3927 (below the threshold of 0.5), and the system automatically excludes this resource. In one embodiment, the resource availability score threshold can be set to 0.5, depending on the specific circumstances.

[0060] By identifying the user's disease type, it's possible to effectively filter out unqualified hospitals, preventing excessive and ineffective initial treatments that could lead to missed opportunities for optimal care. Furthermore, prioritizing treatment based on the condition allows users to know the best time for intervention, thus selecting the most suitable medical resources. S106 generates planning information corresponding to the health status data based on category and medical resource information. This step specifically includes: generating planning information including a recommended geographical location and an execution time window based on the health status data; wherein, the recommended geographical location is determined based on the institution's location in the medical resource information, and the execution time window is determined based on at least one dynamic parameter in the medical resource information.

[0061] For example, for patients with a treatment priority of Level 1, the system may recommend the nearest hospital with emergency capabilities; for patients with a treatment priority of Level 2, the system may recommend hospitals with strong specialty capabilities and currently low patient load; and for patients with a treatment priority of Level 3, the system may recommend medical institutions with high medical quality ratings and a large number of available appointment slots.

[0062] This step utilizes a resource scheduling engine (enhanced by linear discriminant analysis to improve decision-making algorithms) to integrate patient priority with real-time medical resource status, generating an executable treatment configuration plan. For Level 1 critical illnesses requiring intervention within the critical hour, the system activates an emergency priority channel: dynamically calculating qualified medical institutions within a 5km radius based on the patient's geographic coordinates, filtering institutions with a patient saturation rate <90% and equipped with relevant specialist physicians in real time, and outputting navigation routes and estimated arrival times for the three nearest qualified hospitals, while simultaneously pushing emergency physician qualification information. For example, a patient with acute chest pain receives the following plan: {Institution: Chest Pain Center, XX Hospital, Distance: 3.2km, Arrival Time: 8 minutes, Physician: Wang XX (Director of Cardiovascular Intervention), Time Period: Immediate Treatment}.

[0063] For grade II progressive diseases, treatment must be completed within 24 hours. The system employs a balanced execution strategy: Institutions with a strength index > 85 and a saturation level < 70% are selected using the department's comprehensive strength index calculation formula: 0.6 × historical cure rate + 0.4 × equipment advancement. This is combined with dynamic physician scheduling to recommend the optimal consultation window within the next 6-24 hours. For example, the case plan for a suspected appendicitis patient is: {Institution: General Surgery Department, XX Hospital; Strength Index: 92; Saturation Level: 45%; Physician: Li XX (Associate Chief Physician); Time: 10:00-11:00 the next day}.

[0064] For level 3 stable conditions requiring treatment within 72 hours, the system activates a resource utilization optimization model: prioritizing departments with a satisfaction rating ≥ 4.8 stars (out of 5) and > 40% idle time within the next 48-72 hours, providing a three-tiered flexible configuration including "preferred recommendation / second-best alternative / economical option". For example, a suggested plan for a hypertension follow-up patient would be: First choice: {Community Medical Center, Satisfaction: 4.9, Time: Day 3, 14:30} Alternative: {City Hospital Chronic Disease Department, Satisfaction: 4.7, Time: Day 3, 10:00}.

[0065] Based on the user's health status data and the geographical location and medical resources of various hospitals, the system can recommend the most suitable hospital, its corresponding doctor, and the doctor's consultation time. This solves the problem of low medical efficiency caused by information asymmetry among users regarding different hospitals.

[0066] A dynamic inquiry mechanism based on the user interface intelligently adjusts the inquiry path by analyzing the classification results of user responses in real time. It combines clinical medical knowledge to predict potential user symptoms and uses conversational restatement technology to guide users to clearly describe their condition, significantly improving the completeness of symptom collection and the accuracy of disease identification. By quantitatively assessing the complexity and processing priority of user health status, a dynamic medical resource filtering mechanism is constructed: on the one hand, it proactively blocks medical institutions with insufficient qualifications or resources based on the complexity of diagnosis and treatment, avoiding the risk of delays in optimal treatment time due to ineffective initial diagnoses; on the other hand, it clarifies the optimal consultation time window based on processing priority, forming a closed loop of medical safety protection. Finally, based on a multi-dimensional resource scheduling algorithm, a three-dimensional treatment plan is generated, including recommended hospitals, precise departments, matched doctors, and optimal time windows, completely eliminating the problem of low consultation efficiency caused by medical information asymmetry and improving the efficiency from symptom identification to resource matching. Through the above methods, reasonable medical planning can be provided to users based on their health status data and the actual situation of medical resources, improving the utilization efficiency of medical resources and providing users with more convenient medical services.

[0067] In one embodiment, the aforementioned models are all trained or fine-tuned using corresponding training samples to obtain the corresponding trained models, and the training or fine-tuning methods are any of the prior art.

[0068] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0069] Based on the same inventive concept, this application also provides an information processing system for implementing the information processing method described above. The solution provided by this system is similar to the solution described in the above method; therefore, the specific limitations in one or more information processing system embodiments provided below can be found in the limitations of the pre-diagnosis method described above, and will not be repeated here.

[0070] One embodiment provides an information processing system for processing users' health status data and providing corresponding medical resource planning.

[0071] The information processing system includes a data acquisition module 300, a data classification module 302, an information determination module 304, and an information generation module 306. These modules work collaboratively to process health status data and generate medical resource plans.

[0072] Data acquisition module 300 is used to acquire user health status data based on the user interface;

[0073] The data classification module 302 is used to classify the health status data according to preset medical rules and determine the category information corresponding to the health status data; the category information is used to characterize the processing priority and complexity of the health status data.

[0074] The information determination module 304 is used to determine the medical resource information corresponding to the category information from a preset medical resource database;

[0075] The information generation module 306 is used to generate planning information corresponding to the processing of the health status data based on the category information and the medical resource information.

[0076] The data acquisition module 300 acquires the user's health status data through a user interface. The user interface employs a graphical interactive design, including a health data input area, a historical data query area, and a results display area. Users can manually input various health indicators, such as blood pressure, blood sugar, body temperature, and heart rate, and can also describe their symptoms and discomfort. Furthermore, this module supports data synchronization with wearable devices, automatically collecting real-time health data such as electrocardiograms, blood oxygen saturation, and sleep quality. The data acquisition module uses encrypted transmission technology to ensure the security and privacy protection of the user's health data.

[0077] The data classification module 302 classifies the acquired health status data according to preset medical rules, determining the corresponding category information. This module incorporates a multi-layered classification algorithm. First, it performs preliminary screening to determine the completeness and validity of the data. Then, it compares and analyzes the data against standards in the medical rule base, categorizing the health status data into four main categories: acute and critical illnesses, chronic diseases, sub-health, and healthy states. The category information not only includes the classification of the health status but also represents the processing priority and complexity of the health status data. For example, the acute and critical illness category has the highest processing priority and the highest complexity, requiring immediate intervention; while the healthy state category has a lower processing priority and relatively simpler complexity. The data classification module employs machine learning technology, continuously optimizing the classification rules based on historical data to improve classification accuracy.

[0078] In a preferred embodiment, the data classification module further includes a data verification unit 3021, used to verify the validity of the acquired health status data, remove outliers or obviously erroneous data, and ensure the accuracy of subsequent analysis. The data verification unit sets reasonable ranges for various health indicators, marks data that exceeds the range, and prompts the user to re-enter or confirm.

[0079] In another preferred embodiment, the data classification module further includes a risk assessment unit 3022, which calculates the user's health risk index based on health status data and uses the risk index as an important component of the category information. The risk assessment adopts a comprehensive scoring mechanism, considering factors such as the user's age, gender, and past medical history, combined with current health status data, to generate a risk score of 0-100. The higher the score, the greater the risk and the higher the processing priority.

[0080] The information determination module 304 identifies the medical resource information corresponding to the category information from a preset medical resource database. This module maintains a comprehensive medical resource database, including information on hospitals, specialist clinics, doctors, medicines, and medical equipment. Based on the category information determined by the data classification module, the information determination module matches the most suitable combination of medical resources. For example, for acute and critical illnesses, the system will prioritize recommending the nearest emergency hospital and relevant specialist doctors; for chronic diseases, the system will recommend specialist doctors and long-term medication plans; for sub-health conditions, the system will recommend health consultations and lifestyle adjustment suggestions. Medical resource information includes detailed information such as resource name, geographical location, specialty, available time slots, and appointment methods.

[0081] In a preferred embodiment, the information determination module further includes a resource filtering unit 3041. This unit further filters medical resources based on the user's geographical location, medical insurance type, medical preferences, and other personal information, providing more personalized medical resource recommendations. The resource filtering unit employs a multi-factor weighted algorithm, comprehensively considering factors such as distance, cost, professional level, and user reviews to provide users with the optimal selection of medical resources.

[0082] In another preferred embodiment, the information determination module further includes a resource evaluation unit 3042, which evaluates and updates the resources in the medical resource database in real time to ensure the accuracy and timeliness of the recommended medical resource information. The resource evaluation unit obtains the resource availability status in real time through a data interface with medical institutions and continuously adjusts the resource evaluation based on user feedback.

[0083] The information generation module 306 generates planning information corresponding to the processed health status data based on category information and medical resource information. The planning information is a complete health management plan, including medical advice, medication guidance, lifestyle adjustments, and follow-up plans. The content and format of the planning information differ for different categories of health status. For example, for acute and critical illnesses, the planning information includes clear medical routes and emergency measures; for chronic diseases, it includes long-term management plans and regular check-up arrangements; and for sub-health states, it focuses on preventative measures and health promotion recommendations. The planning information is presented in a visually appealing format for easy user understanding and implementation.

[0084] In a preferred embodiment, the information generation module further includes a personalization unit 3061, which personalizes the planning information based on the user's individual characteristics and preferences. The personalization unit considers factors such as the user's age, occupation, and lifestyle habits, adjusting the level of detail and execution difficulty of the planning information to ensure that the planning information is feasible and easily accepted by the user.

[0085] In another preferred embodiment, the information generation module further includes a tracking and feedback unit 3062, which is responsible for tracking the execution of the planning information, collecting user feedback, and adjusting the planning content based on the feedback. The tracking and feedback unit understands the user's execution status through regular reminders and questionnaires, and dynamically adjusts the planning content according to changes in the user's actual health status, forming a closed-loop management system.

[0086] Through the collaborative work of the aforementioned modules, this information processing system can effectively process users' health status data, provide targeted medical resource planning, help users better manage their health status, and obtain appropriate medical services in a timely manner. The system's intelligent classification and personalized recommendation functions greatly improve the efficiency of medical resource utilization and the level of users' health management.

[0087] Each module in the aforementioned information processing system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0088] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the content of any embodiment of the information processing method described above.

[0089] In one embodiment, a computer-readable storage medium is provided that stores a computer program thereon, which, when executed by a processor, implements the content of any embodiment of the information processing method described above.

[0090] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the content of any embodiment of the information processing method described above.

[0091] This instruction manual also provides Figure 4 The diagram shows a schematic structural representation of the electronic device. Figure 4 At the hardware level, the electronic device includes a processor, internal bus, network interface, memory, and non-volatile memory, and may also include other hardware required for the business operations. The processor reads the corresponding computer program from the non-volatile memory into memory and then runs it to achieve the above-mentioned functions. Figure 1 The above describes an information processing method. Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution subject of the following processing flow is not limited to individual logic units, but can also be hardware or logic devices.

[0092] Improvements in a technology can be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many improvements to the methodology can now be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that an improvement in methodology cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must also be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0093] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0094] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0095] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0096] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0097] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0098] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0099] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0100] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0101] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0102] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0103] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0104] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0105] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0106] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0107] The above description is merely an embodiment of this specification and is not intended to limit this specification. Various modifications and variations can be made to this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of the claims of this application.

Claims

1. An information processing method, characterized in that... ,include: Based on the user interface, obtain the user's health status data; The health status data is classified according to preset medical rules to determine the category information corresponding to the health status data; the category information is used to characterize the processing priority and complexity of the health status data. The medical resource information corresponding to the category information is determined from the preset medical resource database; Based on the category information and the medical resource information, planning information corresponding to the processing of the health status data is generated.

2. The method according to claim 1, characterized in that, The method of acquiring user health status data based on the user interface includes: The user's response content is categorized into intents, and the query path is adjusted accordingly. The inquiry path includes: If the user's response is reasonable, proceed to the next query node; If the user's response is unreasonable, the query content will be reconstructed and the question will be asked again.

3. The method according to claim 2, characterized in that, If the user's response is unreasonable, the query content will be reconstructed and the question will be asked again, including: Guided symptom descriptions are generated based on a clinical knowledge base; Perform correlation analysis on user responses; Reconstruct the inquiry content based on the guiding symptom description and correlation analysis; The health status data is determined based on the query content.

4. The method according to claim 1, characterized in that... The step of determining the type from the preset medical resource database The medical resource information corresponding to the information includes: The disease type is determined based on the health status data; The preset medical resource database is filtered according to the disease type to obtain an initial resource database; The initial resource library is filtered based on the health status data to obtain the target resource library. The medical resource information is obtained based on the target resource database.

5. The method according to claim 4, characterized in that... Based on the target resource database, the medical resource information is obtained. Information, including: Obtain department information from the target resource database, including: scope of diagnosis and treatment, equipment configuration, and expert qualifications; The target department is determined based on the degree of matching between the disease type and the scope of treatment information of the department. Based on the target department, the medical resource information is obtained from the target resource database.

6. The method according to claim 1, characterized in that, The preset medical resource database includes at least one of the following dynamic parameters: Data on the saturation of medical departments, the dynamic scheduling of specialist physicians, the availability of medical equipment, and historical evaluation data on the quality of medical care.

7. The method according to claim 1, characterized in that, Based on the category information and the medical resource information, generate planning information corresponding to the processing of the health status data, including: Based on the health status data, planning information including recommended geographical locations and execution time windows is generated; The recommended geographical location is determined based on the location of the institution in the medical resource information. The execution time window is determined based on at least one dynamic parameter in the medical resource information.

8. An information processing system, characterized in that... ,include: The data acquisition module is used to acquire users' health status data based on the user interface. The data classification module is used to classify the health status data according to preset medical rules and determine the category information corresponding to the health status data; the category information is used to characterize the processing priority and complexity of the health status data. The information determination module is used to determine the medical resource information corresponding to the category information from a preset medical resource database; The information generation module is used to generate planning information corresponding to the processing of the health status data based on the category information and the medical resource information.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images