Electronic medical record intelligent input method and system

Abstract

The invention discloses an electronic medical record intelligent entry method and system, and relates to the technical field of data processing, and the method comprises the steps: building an electronic medical record library in advance according to the reservation record of a patient, and setting a patient doctor-seeing intelligent entry mechanism through the electronic medical record library; a comparison database is established through texts, videos and voices of historical medical records to achieve keyword triggering, key information is extracted to serve as comparison detection indexes, preliminary treatment data of a patient is analyzed, a comprehensive analysis input value is obtained by combining the voices and physiological data, autonomous input types are divided, and dynamic evaluation switching is conducted. The input mode can be adjusted according to the autonomous ability of a patient, key symptom associated features of the patient are compared with a doctor-seeing standardized knowledge base, a diagnosis standard with a high matching degree is screened out, symptom types and risk estimation values are obtained by integrating multiple analysis lists, grades are divided according to the different symptom types, permission encryption is performed, and the permission encryption efficiency is improved. Triggering mechanisms are set for different risk levels, and patients with different risks are effectively managed.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and system for intelligently entering electronic medical records. Background Art

[0002] With the rapid development of information technology, electronic medical record systems have been widely used in the medical industry, greatly improving the efficiency of recording, storage and retrieval of medical information. Electronic medical records, also known as computerized medical record systems, are digital medical records that are stored, managed, transmitted and reproduced by electronic devices (computers, health cards), replacing traditional paper medical records. Intelligent electronic medical record entry aims to use various advanced technologies to record patient medical information into the electronic medical record system more efficiently and accurately. As the core product of medical informatization, electronic medical records are used in various departments within the hospital.

[0003] In the existing technology, the entry of psychiatric electronic medical records mainly relies on patient self-reports and doctor notes in the traditional electronic medical record entry process. In the existing entry information, patients may not be able to clearly and completely describe their psychological state and symptoms due to their expression ability and emotional state. It is also impossible to accurately capture key details such as patients' emotional fluctuations and the specific time points of emotional fluctuations. When entering medical records, doctors rely more on personal memory and experience to make diagnostic judgments. There is a lack of systematic standardized diagnostic prompts, which is prone to inconsistent or inaccurate diagnoses. This is not conducive to improving the quality of psychiatric medical care and standardized data management, and makes medical records unable to fully reflect the dynamic changes of patients' conditions.

[0004] In view of the above technical defects, a solution is now proposed. Summary of the Invention

[0005] The purpose of the present invention is to establish an electronic medical record library and set up an intelligent entry mechanism to conduct multi-dimensional analysis of the patient's medical data at different stages, generate multiple analysis sheets, and then conduct factor risk assessment analysis to obtain symptom type and risk estimation value analysis sheets, and take different measures according to the risk level.

[0006] In order to achieve the above-mentioned object, the present invention adopts the following technical solution: a method for intelligently entering electronic medical records, comprising the following steps:

[0007] Step 1: Pre-establish an electronic medical record database based on the patient's appointment records. Set up an intelligent patient entry mechanism through the electronic medical record database. Enter the patient's real-time data according to the intelligent entry mechanism. Divide the patient's visit data into preliminary visit data, communication visit data, and later visit data according to the patient's visit process.

[0008] Step 2: Obtain the patient's initial visit data at the beginning of the visit in real time, analyze the key data features based on voice and physiological data, analyze and evaluate the patient's autonomy index, and obtain the patient's autonomous input type analysis sheet. The autonomous input type is divided into autonomous, coaching, and passive types;

[0009] Step 3: During the data entry process, obtain the patient's real-time communication and medical treatment data. Based on the patient's language data and behavioral data, standard time interval breakpoints and emotional differences, perform key feature extraction, evaluation and analysis of the language data. Dynamic risk behavior analysis is performed based on the behavioral data. Combined with the dynamic risk behavior, emotional fluctuation analysis is performed to generate a comprehensive emotional capture analysis sheet.

[0010] Step 4: Obtain real-time patient follow-up visit data and patient language data, establish a standardized visit knowledge base based on historical electronic medical records, obtain key symptom correlation features, and perform intelligent matching and comparison to generate a diagnostic standard analysis sheet based on the matching degree;

[0011] Step 5: Based on the self-entered type analysis sheet, emotional comprehensive capture analysis sheet, and diagnostic standard analysis sheet as influencing factor constraints, perform factor risk assessment analysis to obtain the patient symptom type and risk estimate analysis sheet.

[0012] It also includes a dynamic risk classification encryption strategy, which classifies different levels according to the symptom type, and the levels are divided into common type, risk type, and threat type. It encrypts the level authority according to different levels, obtains the symptom type and risk estimate analysis sheet, triggers the risk dynamic threshold according to the symptom type and risk estimate, and sets the risk estimate standard threshold R.

[0013] When the level is threatening and the risk estimate is ≥ the standard threshold, temporary access rights are automatically granted to the hospital security director and the local police;

[0014] When the level is risky and the risk estimate is ≥ the standard threshold, the patient will be automatically marked as an intelligent warning patient and the time interval constraint conditions for the medical reminder will be set.

[0015] The setting of the patient consultation intelligent entry mechanism through the electronic medical record library specifically includes the following:

[0016] S100, extract keywords based on the text, video, and voice content of historical electronic medical records, establish a comparison database, automatically identify keywords based on the comparison database for collaborative entry, and use keyword triggering as an auxiliary mode;

[0017] S101, speech recognition input step: During the diagnosis process, the medical staff and the patient's conversation is converted into text information in real time using speech recognition technology. Key information is extracted from the converted text information, including negative word library, sensitive word library and the patient's acoustic intonation fundamental frequency, which serves as comparative detection indicators in the recognition process;

[0018] S102. When performing video recognition, facial monitoring indicators and limb movement indicators are established based on the patient's behavior and facial features as comparative detection indicators during intelligent entry.

[0019] Conduct autonomous input of decision-making and judgment, and analyze and evaluate the patient's autonomy index, including the following:

[0020] S200, obtaining the patient's initial medical data in real time, and analyzing the patient's key symptom descriptions, medical history records, and various indicators of the current physical condition;

[0021] S201. Perform semantic analysis and behavioral response analysis based on speech and physiological data, including autonomous willingness Y, enthusiasm for answering questions J, and frequency of external assistance C, to obtain a comprehensive analysis input value A, where A = 0.2*Y + J*0.3 + C*0.3 + 0.1, where J ≤ 10 and C ≤ 10.

[0022] S202. Based on the comprehensive analysis of the input values, the input types are divided into three levels: autonomous, coached, and passive. Autonomous type ≥1.5, 1.5>coached type ≥1, and passive type ≤1. An analysis sheet of the patient's autonomous input type is automatically generated, and re-evaluation is performed every 2 minutes to achieve dynamic mode switching, and encrypted early warning reminder information is generated simultaneously.

[0023] Generate a comprehensive emotion capture analysis sheet, including the following:

[0024] S300, obtain language data, set standard comparison time interval breakpoints, and perform comparison to extract language silence time points as the emotion fluctuation time point set E1={T E 1. T E 2,…,T E N}, extract the time point feature vector when the fundamental frequency of the speech suddenly changes, as the emotional difference point set E2 = {V E 1, V E 2,…,V E N};

[0025] S301, obtain behavior mutation points through motion sensing sensors and behavior data, record the time points when the patient produces behavior, and generate a set of action behavior fluctuation points D = {D E 1, D E 2,…,D E N};

[0026] S302 , construct a three-dimensional emotional state dynamic analysis set based on the emotional fluctuation time point set, the emotional difference point set, and the behavioral fluctuation point set, and obtain a comprehensive emotional analysis frequency P, where P=E1+E2+D.

[0027] Furthermore, we obtained the patient's symptom type and risk estimation analysis sheet,

[0028] S400: Acquire patient language data, obtain key symptom-related features, compare them with feature data in a standardized medical consultation knowledge base, and screen out diagnostic criteria with a high degree of match with the patient's key symptom-related features based on predefined matching rules and similarity thresholds to obtain symptom types;

[0029] S401. Set the risk dynamic adjustment coefficients w1, w2, and w3 based on the self-entered type analysis sheet L, emotion comprehensive capture analysis sheet Q, and diagnostic standard analysis sheet Z;

[0030] S402, calculate the risk estimate F,

[0031]

[0032] Where N is the number of data points in each set, T E is the data point in the Eth emotional fluctuation time point set, V E is the data point in the Eth emotional difference point set, D E is the data point in the E-th action behavior fluctuation point set.

[0033] An electronic medical record intelligent entry system includes a medical record creation module, a medical record classification module, a medical record analysis module, a medical record diagnosis module, and a medical record evaluation module.

[0034] The medical record establishment module pre-establishes an electronic medical record database based on the patient's appointment records, sets up an intelligent patient entry mechanism through the electronic medical record database, enters the patient's real-time data according to the intelligent entry mechanism, and divides the patient's medical data into preliminary medical data, communication medical data, and later medical data according to the patient's medical process;

[0035] The medical record classification module obtains the patient's initial medical data at the beginning of the visit in real time, analyzes and evaluates the patient's autonomy index based on voice and physiological data, and obtains the patient's autonomous input type analysis sheet. The autonomous input type is divided into autonomous, coaching, and passive types;

[0036] The medical record analysis module obtains real-time patient communication and consultation data during the data entry process. Based on the patient's language and behavioral data, standard time interval breakpoints and emotional differences, it extracts, evaluates and analyzes key features of the language data. It also conducts dynamic risk behavior analysis based on behavioral data, and analyzes emotional fluctuations based on dynamic risk behavior to generate a comprehensive emotional capture analysis sheet.

[0037] The medical record diagnosis module obtains real-time patient follow-up data and patient language data, establishes a standardized medical knowledge base based on historical electronic medical records, obtains key symptom correlation features, and performs intelligent matching and comparison to generate a diagnostic standard analysis sheet based on the matching degree;

[0038] The medical record assessment module conducts factor risk assessment analysis based on the self-entered type analysis sheet, emotional comprehensive capture analysis sheet, and diagnostic standard analysis sheet as influencing factor constraints, and obtains the patient symptom type and risk estimate analysis sheet.

[0039] Furthermore, it includes a preventive security module, which is used to obtain the patient's symptom type and risk estimation analysis sheet, establish a data sharing mechanism based on medical institutions, community grids and police platforms, and perform geographic location association.

[0040] Build dynamic risk monitoring indicators, including regular follow-up of stable symptoms, trigger community attention, initiate psychological intervention, and automatically push them to the local alarm command center to link with the police response plan;

[0041] Get the symptom type and risk estimate analysis sheet,

[0042] When the level is threatening and the risk estimate is ≥ the standard threshold, temporary access rights will be automatically granted to the hospital security director and the local police, and the information will be automatically pushed to the 110 command center to link the police response plan;

[0043] When the level is risky and the risk estimate is ≥ the standard threshold, the patient will be automatically marked as an intelligent warning patient, and the time interval constraint for the medical reminder will be set, and the indicator is to trigger community attention.

[0044] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0045] This electronic medical record intelligent entry method and system establishes a comparative database through the text, video and voice of historical medical records to achieve keyword triggering, extracts key information as comparative detection indicators, analyzes the patient's initial medical data, combines voice and physiological data to derive comprehensive analysis entry values, divides autonomous entry types and dynamically evaluates and switches, can adjust the entry method according to the patient's autonomous ability, compares the patient's key symptom-related characteristics with the standardized medical knowledge base, screens out diagnostic standards with a high degree of match, and integrates multiple analysis sheets to derive symptom types and risk estimates. It also encrypts permissions based on the levels of different symptom types, sets trigger mechanisms for different risk levels, and effectively manages patients with different risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 Shows a schematic diagram of the method flow structure of the present invention;

[0047] Figure 2 The figure shows the overall structure diagram of the system of the present invention. DETAILED DESCRIPTION

[0048] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0049] Example 1:

[0050] like Figure 1 As shown, a method for intelligently entering electronic medical records includes the following steps:

[0051] Step 1: Pre-establish an electronic medical record database based on the patient's appointment records. Set up an intelligent patient entry mechanism through the electronic medical record database. Enter the patient's real-time data according to the intelligent entry mechanism. Divide the patient's visit data into preliminary visit data, communication visit data, and later visit data according to the patient's visit process.

[0052] Step 2: Obtain the patient's initial visit data at the beginning of the visit in real time, analyze the key data features based on voice and physiological data, analyze and evaluate the patient's autonomy index, and obtain the patient's autonomous input type analysis sheet. The autonomous input type is divided into autonomous, coaching, and passive types;

[0053] Step 3: During the data entry process, obtain the patient's real-time communication and medical treatment data. Based on the patient's language data and behavioral data, standard time interval breakpoints and emotional differences, perform key feature extraction, evaluation and analysis of the language data. Dynamic risk behavior analysis is performed based on the behavioral data. Combined with the dynamic risk behavior, emotional fluctuation analysis is performed to generate a comprehensive emotional capture analysis sheet.

[0054] Step 4: Obtain real-time patient follow-up visit data and patient language data, establish a standardized visit knowledge base based on historical electronic medical records, obtain key symptom correlation features, and perform intelligent matching and comparison to generate a diagnostic standard analysis sheet based on the matching degree;

[0055] Step 5: Based on the self-entered type analysis sheet, emotional comprehensive capture analysis sheet, and diagnostic standard analysis sheet as influencing factor constraints, perform factor risk assessment analysis to obtain the patient symptom type and risk estimate analysis sheet.

[0056] It also includes a dynamic risk classification encryption strategy, which classifies different levels according to the symptom type, and the levels are divided into common type, risk type, and threat type. It encrypts the level authority according to different levels, obtains the symptom type and risk estimate analysis sheet, triggers the risk dynamic threshold according to the symptom type and risk estimate, and sets the risk estimate standard threshold R.

[0057] When the level is threatening and the risk estimate is ≥ the standard threshold, temporary access rights are automatically granted to the hospital security director and the local police;

[0058] When the level is risky and the risk estimate is ≥ the standard threshold, the patient will be automatically marked as an intelligent warning patient and the time interval constraint conditions for the medical reminder will be set.

[0059] The setting of the patient consultation intelligent entry mechanism through the electronic medical record library specifically includes the following:

[0060] S100, extract keywords based on the text, video, and voice content of historical electronic medical records, establish a comparison database, automatically identify keywords based on the comparison database for collaborative entry, and use keyword triggering as an auxiliary mode;

[0061] S101, speech recognition input step: During the diagnosis process, the medical staff and the patient's conversation is converted into text information in real time using speech recognition technology. Key information is extracted from the converted text information, including negative word library, sensitive word library and the patient's acoustic intonation fundamental frequency, which serves as comparative detection indicators in the recognition process;

[0062] S102. When performing video recognition, facial monitoring indicators and limb movement indicators are established based on the patient's behavior and facial features as comparative detection indicators during intelligent entry.

[0063] Conduct autonomous input of decision-making and judgment, and analyze and evaluate the patient's autonomy index, including the following:

[0064] S200, obtaining the patient's initial medical data in real time, and analyzing the patient's key symptom descriptions, medical history records, and various indicators of the current physical condition;

[0065] S201. Perform semantic analysis and behavioral response analysis based on speech and physiological data, including autonomous willingness Y, enthusiasm for answering questions J, and frequency of external assistance C, to obtain a comprehensive analysis input value A, where A = 0.2*Y + J*0.3 + C*0.3 + 0.1, where J ≤ 10 and C ≤ 10.

[0066] S202. Based on the comprehensive analysis of the input values, the input types are divided into three levels: autonomous, coached, and passive. Autonomous type ≥1.5, 1.5>coached type ≥1, and passive type ≤1. An analysis sheet of the patient's autonomous input type is automatically generated, and re-evaluation is performed every 2 minutes to achieve dynamic mode switching, and encrypted early warning reminder information is generated simultaneously.

[0067] Generate a comprehensive emotion capture analysis sheet, including the following:

[0068] S300, obtain language data, set standard comparison time interval breakpoints, and perform comparison to extract language silence time points as the emotion fluctuation time point set E1={T E 1. T E 2,…,T E N}, extract the time point feature vector when the fundamental frequency of the speech suddenly changes, as the emotional difference point set E2 = {V E 1, V E 2,…,V E N};

[0069] S301, obtain behavior mutation points through motion sensing sensors and behavior data, record the time points when the patient produces behavior, and generate a set of action behavior fluctuation points D = {D E 1, D E 2,…,D E N};

[0070] S302 , construct a three-dimensional emotional state dynamic analysis set based on the emotional fluctuation time point set, the emotional difference point set, and the behavioral fluctuation point set, and obtain a comprehensive emotional analysis frequency P, where P=E1+E2+D.

[0071] Get the patient's symptom type and risk estimation analysis sheet,

[0072] S400: Acquire patient language data, obtain key symptom-related features, compare them with feature data in a standardized medical consultation knowledge base, and screen out diagnostic criteria with a high degree of match with the patient's key symptom-related features based on predefined matching rules and similarity thresholds to obtain symptom types;

[0073] S401. Set the risk dynamic adjustment coefficients w1, w2, and w3 based on the self-entered type analysis sheet L, emotion comprehensive capture analysis sheet Q, and diagnostic standard analysis sheet Z;

[0074] S402, calculate the risk estimate F,

[0075]

[0076] Where N is the number of data points in each set, T E is the data point in the Eth emotional fluctuation time point set, V E is the data point in the Eth emotional difference point set, D E is the data point in the E-th action behavior fluctuation point set.

[0077] like Figure 2 As shown, an electronic medical record intelligent entry system includes a medical record establishment module, a medical record classification module, a medical record analysis module, a medical record diagnosis module, and a medical record evaluation module.

[0078] The medical record establishment module pre-establishes an electronic medical record database based on the patient's appointment records, sets up an intelligent patient entry mechanism through the electronic medical record database, enters the patient's real-time data according to the intelligent entry mechanism, and divides the patient's medical data into preliminary medical data, communication medical data, and later medical data according to the patient's medical process;

[0079] The medical record classification module obtains the patient's initial medical data at the beginning of the visit in real time, analyzes and evaluates the patient's autonomy index based on voice and physiological data, and obtains the patient's autonomous input type analysis sheet. The autonomous input type is divided into autonomous, coaching, and passive types;

[0080] The medical record analysis module obtains real-time patient communication and consultation data during the data entry process. Based on the patient's language and behavioral data, standard time interval breakpoints and emotional differences, it extracts, evaluates and analyzes key features of the language data. It also conducts dynamic risk behavior analysis based on behavioral data, and analyzes emotional fluctuations based on dynamic risk behavior to generate a comprehensive emotional capture analysis sheet.

[0081] The medical record diagnosis module obtains real-time patient follow-up data and patient language data, establishes a standardized medical knowledge base based on historical electronic medical records, obtains key symptom correlation features, and performs intelligent matching and comparison to generate a diagnostic standard analysis sheet based on the matching degree;

[0082] The medical record assessment module conducts factor risk assessment analysis based on the self-entered type analysis sheet, emotional comprehensive capture analysis sheet, and diagnostic standard analysis sheet as influencing factor constraints, and obtains the patient symptom type and risk estimate analysis sheet.

[0083] 8. An electronic medical record intelligent entry system, characterized by including a preventive security module, which is used to obtain a patient's symptom type and risk estimation analysis sheet, establish a data sharing mechanism based on medical institutions, community grids, and police platforms, and perform geographic location association.

[0084] Build dynamic risk monitoring indicators, including regular follow-up of stable symptoms, trigger community attention, initiate psychological intervention, and automatically push them to the local alarm command center to link with the police response plan;

[0085] Get the symptom type and risk estimate analysis sheet,

[0086] When the level is threatening and the risk estimate is ≥ the standard threshold, temporary access rights will be automatically granted to the hospital security director and the local police, and the information will be automatically pushed to the 110 command center to link the police response plan;

[0087] When the level is risky and the risk estimate is ≥ the standard threshold, the patient will be automatically marked as an intelligent warning patient, and the time interval constraint for the medical reminder will be set, and the indicator is to trigger community attention.

[0088] The size of the interval and threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technical personnel in this field for each set of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0089] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by those skilled in the art according to actual conditions.

[0090] In the two embodiments provided in this application, it should be understood that the disclosed devices and systems can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the module division is merely a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not implemented. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interface, and the indirect coupling or communication connection of devices or modules may be electrical, mechanical or other forms.

[0091] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A method for intelligent entry of electronic medical records, characterized in that: The following steps are involved: Step 1: Pre-establish an electronic medical record database based on the patient's appointment records. Set up an intelligent patient entry mechanism through the electronic medical record database. Enter the patient's real-time data according to the intelligent entry mechanism. Divide the patient's visit data into preliminary visit data, communication visit data, and later visit data according to the patient's visit process. Step 2: Obtain the patient's initial visit data at the beginning of the visit in real time, analyze the key data features based on voice and physiological data, analyze and evaluate the patient's autonomy index, and obtain the patient's autonomous input type analysis sheet. The autonomous input type is divided into autonomous, coaching, and passive types; Step 3: During the data entry process, obtain the patient's real-time communication and medical treatment data. Based on the patient's language data and behavioral data, standard time interval breakpoints and emotional differences, perform key feature extraction, evaluation and analysis of the language data. Dynamic risk behavior analysis is performed based on the behavioral data. Combined with the dynamic risk behavior, emotional fluctuation analysis is performed to generate a comprehensive emotional capture analysis sheet. Step 4: Obtain real-time patient follow-up visit data and patient language data, establish a standardized visit knowledge base based on historical electronic medical records, obtain key symptom correlation features, and perform intelligent matching and comparison to generate a diagnostic standard analysis sheet based on the matching degree; Step 5: Based on the self-entered type analysis sheet, emotional comprehensive capture analysis sheet, and diagnostic standard analysis sheet as influencing factor constraints, perform factor risk assessment analysis to obtain the patient symptom type and risk estimate analysis sheet.

2. The electronic medical record intelligent entry method according to claim 1, characterized in that: It also includes a dynamic risk classification encryption strategy, which classifies different levels according to the symptom type, and the levels are divided into common type, risk type, and threat type. It encrypts the level authority according to different levels, obtains the symptom type and risk estimate analysis sheet, triggers the risk dynamic threshold according to the symptom type and risk estimate, and sets the risk estimate standard threshold R. When the level is threatening and the risk estimate is ≥ the standard threshold, temporary access rights are automatically granted to the hospital security director and the local police; When the level is risky and the risk estimate is ≥ the standard threshold, the patient will be automatically marked as an intelligent warning patient and the time interval constraint conditions for the medical reminder will be set.

3. The electronic medical record intelligent entry method according to claim 1, characterized in that: The setting of the patient consultation intelligent entry mechanism through the electronic medical record library specifically includes the following: S100, extract keywords based on the text, video, and voice content of historical electronic medical records, establish a comparison database, automatically identify keywords based on the comparison database for collaborative entry, and use keyword triggering as an auxiliary mode; S101, speech recognition input step: During the diagnosis process, the medical staff and the patient's conversation is converted into text information in real time using speech recognition technology. Key information is extracted from the converted text information, including negative word library, sensitive word library and the patient's acoustic intonation fundamental frequency, which serves as comparative detection indicators in the recognition process; S102. When performing video recognition, facial monitoring indicators and limb movement indicators are established based on the patient's behavior and facial features as comparative detection indicators during intelligent entry.

4. The electronic medical record intelligent entry method according to claim 1, characterized in that: Conduct autonomous input of decision-making and judgment, and analyze and evaluate the patient's autonomy index, including the following: S200, obtaining the patient's initial medical data in real time, and analyzing the patient's key symptom descriptions, medical history records, and various indicators of the current physical condition; S201. Perform semantic analysis and behavioral response analysis based on speech and physiological data, including autonomous willingness Y, enthusiasm for answering questions J, and frequency of external assistance C, to obtain a comprehensive analysis input value A, where A = 0.2*Y + J*0.3 + C*0.3 + 0.1, where J ≤ 10 and C ≤ 10. S202. Based on the comprehensive analysis of the input values, the input types are divided into three levels: autonomous, coached, and passive. Autonomous type ≥1.5, 1.5>coached type ≥1, and passive type ≤1. An analysis sheet of the patient's autonomous input type is automatically generated, and re-evaluation is performed every 2 minutes to achieve dynamic mode switching, and encrypted early warning reminder information is generated simultaneously.

5. The electronic medical record intelligent entry method according to claim 1, characterized in that: Generate a comprehensive emotion capture analysis sheet, including the following: S300, obtain language data, set standard comparison time interval breakpoints, and perform comparison to extract language silence time points as the emotion fluctuation time point set E1={T E 1. T E 2,…,T E N}, extract the time point feature vector when the fundamental frequency of the speech suddenly changes, as the emotional difference point set E2 = {V E 1, V E 2,…,V E N}; S301, obtain behavior mutation points through motion sensing sensors and behavior data, record the time points when the patient produces behavior, and generate a set of action behavior fluctuation points D = {D E 1, D E 2,…,D E N}; S302 , construct a three-dimensional emotional state dynamic analysis set based on the emotional fluctuation time point set, the emotional difference point set, and the behavioral fluctuation point set, and obtain a comprehensive emotional analysis frequency P, where P=E1+E2+D.

6. The electronic medical record intelligent entry method according to claim 1, characterized in that: Get the patient's symptom type and risk estimation analysis sheet, S400: Acquire patient language data, obtain key symptom-related features, compare them with feature data in a standardized medical consultation knowledge base, and screen out diagnostic criteria with a high degree of match with the patient's key symptom-related features based on predefined matching rules and similarity thresholds to obtain symptom types; S401. Set the risk dynamic adjustment coefficients w1, w2, and w3 based on the self-entered type analysis sheet L, emotion comprehensive capture analysis sheet Q, and diagnostic standard analysis sheet Z; S402, calculate the risk estimate F, Where N is the number of data points in each set, T E is the data point in the Eth emotional fluctuation time point set, V E is the data point in the Eth emotional difference point set, D E is the data point in the E-th action behavior fluctuation point set.

7. An electronic medical record intelligent entry system, characterized in that: Including medical record establishment module, medical record classification module, medical record analysis module, medical record diagnosis module, and medical record evaluation module. The medical record establishment module pre-establishes an electronic medical record database based on the patient's appointment records, sets up an intelligent patient entry mechanism through the electronic medical record database, enters the patient's real-time data according to the intelligent entry mechanism, and divides the patient's medical data into preliminary medical data, communication medical data, and later medical data according to the patient's medical process; The medical record classification module obtains the patient's initial medical data at the beginning of the visit in real time, analyzes and evaluates the patient's autonomy index based on voice and physiological data, and obtains the patient's autonomous input type analysis sheet. The autonomous input type is divided into autonomous, coaching, and passive types; The medical record analysis module obtains real-time patient communication and consultation data during the data entry process. Based on the patient's language and behavioral data, standard time interval breakpoints and emotional differences, it extracts, evaluates and analyzes key features of the language data. It also conducts dynamic risk behavior analysis based on behavioral data, and analyzes emotional fluctuations based on dynamic risk behavior to generate a comprehensive emotional capture analysis sheet. The medical record diagnosis module obtains real-time patient follow-up data and patient language data, establishes a standardized medical knowledge base based on historical electronic medical records, obtains key symptom correlation features, and performs intelligent matching and comparison to generate a diagnostic standard analysis sheet based on the matching degree; The medical record assessment module conducts factor risk assessment analysis based on the self-entered type analysis sheet, emotional comprehensive capture analysis sheet, and diagnostic standard analysis sheet as influencing factor constraints, and obtains the patient symptom type and risk estimate analysis sheet.

8. An electronic medical record intelligent entry system, characterized in that: It includes a preventive security module, which is used to obtain the patient's symptom type and risk estimation analysis sheet, establish a data sharing mechanism based on medical institutions, community grids and police platforms, and associate geographic locations. Build dynamic risk monitoring indicators, including regular follow-up of stable symptoms, trigger community attention, initiate psychological intervention, and automatically push them to the local alarm command center to link with the police response plan; Get the symptom type and risk estimate analysis sheet, When the level is threatening and the risk estimate is ≥ the standard threshold, temporary access rights will be automatically granted to the hospital security director and the local police, and the information will be automatically pushed to the 110 command center to link the police response plan; When the level is risky and the risk estimate is ≥ the standard threshold, the patient will be automatically marked as an intelligent warning patient, and the time interval constraint for the medical reminder will be set, and the indicator is to trigger community attention.

Images