Real-time anesthesia parameter adjustment and medical analysis method and system

Abstract

The invention discloses a real-time anesthesia parameter adjustment and medical analysis method and system, and relates to the technical field of medical treatment, and the method comprises the steps: regularly obtaining the configuration information of a multi-source sensor interface on anesthesia monitoring equipment, and transmitting a currently supported data collection instruction to the multi-source sensor interface based on the configuration information, obtaining a sensor connected with anesthesia monitoring equipment; the sensor comprises an existing sensor and a newly accessed sensor. By introducing a multi-source data time scale unified positioning mechanism, a unified time reference frame is established for the physiological parameters under the action of different anesthetics, and the problem that the comprehensive analysis accuracy is limited due to lack of a unified time scale in the prior art is solved.

Description

Technical Field

[0001] This invention relates to the field of medical technology, specifically to a method and system for real-time anesthesia parameter adjustment and medical analysis. Background Technology

[0002] Anesthesia is crucial in surgery and treatment, requiring the maintenance of stable vital signs and reduction of pain and level of consciousness. Traditional anesthesia relies heavily on physician experience and a limited number of physiological parameters, leaving room for improvement in accuracy and reliability. With advancements in biosensing and machine learning technologies, multi-parameter anesthesia monitoring systems are gradually being implemented, but certain challenges remain.

[0003] Most current anesthesia parameter regulation and analysis systems have limitations in data fusion when processing multi-source data generated by different anesthetic drugs acting on the human body. Different drugs have different onset times and durations of action, and the patterns of change in associated physiological parameters also differ. For example, inhaled anesthetics affect EEG signals relatively rapidly, while intravenous anesthetics have a relatively delayed effect on circulatory system parameters. Existing systems lack a unified time-scale method for fusing multi-source data under different drug effects, which limits the accuracy of comprehensive analysis of anesthetic states. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method and system for real-time anesthesia parameter adjustment and medical analysis. It solves the problem of the lack of a unified time scale method when processing multi-source data fusion under different anesthetic drugs in existing technologies, thereby improving the accuracy of comprehensive analysis of anesthesia status and realizing precise real-time adjustment of anesthesia parameters.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a method for real-time anesthesia parameter adjustment and medical analysis, comprising:

[0006] The system periodically acquires the configuration information of the multi-source sensor interface on the anesthesia monitoring device, and sends the currently supported data acquisition command to the multi-source sensor interface based on the configuration information to obtain the sensors connected to the anesthesia monitoring device; the sensors include existing sensors and newly connected sensors.

[0007] Based on the signal characteristics of the newly accessed sensors, and according to the signal types supported by the multi-source sensor interface, the corresponding signal parsing rules are searched from the local signal parsing library to distinguish the types of the newly accessed sensors. Then, a signal recognition command is constructed by combining the signal parsing rules and the sensor type, and a query operation is performed to obtain the response signal returned by the newly accessed sensors.

[0008] The response signals returned by the newly connected sensors are analyzed, matched and identified with signal templates in the local signal analysis library, and all monitoring channels of the newly connected sensors are located to obtain the data types and access permissions of the monitoring channels.

[0009] Based on the data types and access permissions of the monitoring channels, the sets of input channels and output channels are obtained respectively, and the monitoring channel data set is constructed.

[0010] Using the monitoring channel data set and the access interface information of newly connected sensors as input parameters, the anesthesia monitoring equipment configuration program is invoked to automatically apply signal analysis rules, obtain the final signal analysis information and sensor information, and generate a configuration file.

[0011] Optionally, before acquiring the configuration information of the multi-source sensor interface on the anesthesia monitoring device, the method further includes:

[0012] The signal types used by different sensors are obtained, a local signal parsing library is established, and the configuration information of the read and write parameters of each sensor under different signal types is recorded. The read and write parameters of the sensors include the frequency range of the electroencephalogram (EEG) signal, the fluctuation range of the heart rate, the baseline value of blood pressure, the threshold range of blood oxygen saturation, and the change curve of end-tidal carbon dioxide concentration.

[0013] The automatic configuration program runs on the anesthesia monitoring device and periodically retrieves the latest signal analysis rules from the cloud to update the local signal analysis library.

[0014] Optionally, the step of periodically acquiring configuration information of the multi-source sensor interface on the anesthesia monitoring device, and sending currently supported data acquisition commands to the multi-source sensor interface based on the configuration information, to obtain the sensors connected to the anesthesia monitoring device, includes:

[0015] When the multi-source sensor interface has been configured with signal parsing rules and can obtain sensor information according to the signal parsing rules, it is determined that a sensor is normally connected to the current multi-source sensor interface.

[0016] When the multi-source sensor interface has been configured with signal parsing rules but cannot obtain sensor information according to the signal parsing rules, a signal parsing rule traversal test is performed to detect the sensor response.

[0017] When the multi-source sensor interface is not configured with signal parsing rules, a signal parsing rule traversal test is triggered to detect the sensor response.

[0018] Optionally, the step of performing signal analysis rule traversal testing to detect sensor response includes:

[0019] Based on the signal types supported by the current multi-source sensor interface, various signal analysis parameter information is combined to obtain different combinations of signal analysis rules; the signal analysis parameter information includes sampling frequency, resolution, filtering method, and gain setting.

[0020] Based on the signal parsing rules for each combination, broadcast data or specific instructions are sent respectively, and the sensor response is monitored; the specific instructions are standardized query instructions for sensor types, including sensor ID request fields, signal format negotiation parameters and basic configuration query information, which are used to trigger the sensor to return core data such as its own device identifier, signal output accuracy and supported monitoring parameter types;

[0021] When a sensor responds during the signal parsing rule traversal test, it is considered that a new sensor has been connected, and the current signal parsing rule information is saved.

[0022] If no sensor responds during the signal parsing rule traversal test, it is assumed that no new sensor has been connected, and the original signal parsing rules of the multi-source sensor interface are restored.

[0023] Optionally, based on the signal characteristics of the newly accessed sensor and according to the signal types supported by the multi-source sensor interface, the corresponding signal parsing rules are searched from the local signal parsing library to distinguish the type of the newly accessed sensor. A signal recognition command is then constructed by combining the signal parsing rules and the sensor type, and a query operation is performed to obtain the response signal returned by the newly accessed sensor, including:

[0024] Acquire the signal characteristics of the newly connected sensor;

[0025] Based on the signal characteristics of the newly acquired sensors, and according to the signal types supported by the multi-source sensor interfaces on the anesthesia monitoring equipment, the corresponding signal parsing rules are searched from the local signal parsing library.

[0026] Retrieve the list of sensor types supported by the found signal parsing rules from the local signal parsing library, parse the data packets sent by the newly connected sensor, and distinguish and determine the sensor type of the newly connected sensor;

[0027] Based on the established signal analysis rules and sensor types, construct signal recognition instructions;

[0028] It iterates through the constructed signal identification commands, performs query operations, and receives response signals returned by newly accessed sensors.

[0029] Optionally, the process of parsing the response signal returned by the newly accessed sensor, matching and identifying it with signal templates in the local signal parsing library, and searching all monitoring channels of the newly accessed sensor to obtain the data type and access permissions of the monitoring channels includes:

[0030] The response signal returned by the newly accessed sensor based on the normal response format is parsed according to the response frame format corresponding to the signal recognition command to obtain the parsed response signal returned by the newly accessed sensor.

[0031] Based on the response signal returned by the newly accessed sensor after parsing, it is matched and identified with the signal template corresponding to the current signal identification command in the local signal parsing library to obtain the matching and identification result;

[0032] When the response signal returned by the newly accessed sensor after parsing matches the signal template bound to the current signal recognition instruction in the local signal parsing library, the newly accessed sensor is considered to have been correctly identified. Based on the search of all monitoring channels of the newly accessed sensor in the local signal parsing library, the data type and access permissions of the monitoring channel data are obtained.

[0033] If the response signal returned by the newly accessed sensor after parsing does not match the signal template bound to the current signal recognition command in the local signal parsing library, the newly accessed sensor is considered to have been incorrectly identified. The system will then perform sequential matching and identification based on other signal recognition commands in the local signal parsing library. If the response signal returned by the newly accessed sensor after parsing does not match the signal template bound to any of the other signal recognition commands in the local signal parsing library, the automatic configuration process is considered to have failed. The matching and identification results will be recorded, and a manual processing prompt will be sent to the administrator simultaneously.

[0034] Optionally, the step of obtaining the input channel set and the output channel set based on the monitoring channel data type and monitoring channel data access permissions, and constructing the monitoring channel data set, includes:

[0035] If the current monitoring channel data type is continuous and the monitoring channel data access permission is read-only or read-write, then obtain the monitoring channel name, read function code, register address, monitoring channel value type, conversion factor information, and generate a unique tag name containing the monitoring channel data type information, and save it to obtain the continuous input channel set;

[0036] If the current monitoring channel data type is continuous and the monitoring channel data access permission is write-only or read-write, then obtain the monitoring channel name, write function code, register address, monitoring channel value type, conversion factor information, and generate a unique tag name containing the monitoring channel data type information, and save it to obtain the continuous output channel set;

[0037] If the current monitoring channel data type is discrete and the monitoring channel data access permission is read-only or read-write, then obtain the monitoring channel name, read function code, register address, bit information, and generate a unique tag name containing the monitoring channel data type information, and save it to obtain the discrete input channel set;

[0038] If the current monitoring channel data type is discrete and the monitoring channel data access permission is write-only or read-write, then obtain the monitoring channel name, write function code, register address, bit information, and generate a unique tag name containing the monitoring channel data type information, and save it to obtain the discrete output channel set;

[0039] By combining the sets of continuous input channels, continuous output channels, discrete input channels, and discrete output channels, a monitoring channel data set is constructed, and the monitoring channel data within it is exported and logged.

[0040] Optionally, the monitoring channel data set and the access interface information of newly connected sensors are used as input parameters to call the anesthesia monitoring equipment configuration program to automatically apply signal analysis rules, obtain the final signal analysis information and sensor information, and generate a configuration file, including:

[0041] Using the monitoring channel data set and the access interface information of the newly connected sensor as input parameters, the anesthesia monitoring equipment configuration program is invoked to automatically read the monitoring channel data set information and apply it to the specified access interface to perform automatic signal parsing rule configuration and obtain the automatic signal parsing rule configuration result.

[0042] Based on the successfully configured signal parsing rules, a specific test instruction is sent to the newly connected sensor to verify and identify the data received by the anesthesia monitoring device against the expected data, thereby obtaining the data verification and identification result. The specific test instruction includes standard test data simulating physiological signals, which is used to verify the sensor data acquisition accuracy, transmission stability, and parsing logic correctness.

[0043] Based on the signal parsing rules that have been successfully verified by data, the final signal parsing information and sensor information are used to generate a configuration file, which is then saved to the local signal parsing library.

[0044] Optionally, if the automatic signal parsing rule configuration result or data verification result fails, the reason for the failure will be recorded in the log, and a manual processing prompt will be sent to the administrator simultaneously.

[0045] This invention also proposes a real-time anesthesia parameter adjustment and medical analysis system, comprising:

[0046] The sensor information acquisition module is used to periodically acquire the configuration information of the multi-source sensor interface on the anesthesia monitoring device, and send the currently supported data acquisition command to the multi-source sensor interface based on the configuration information to obtain the sensors connected to the anesthesia monitoring device; the sensors include existing sensors and newly connected sensors; and based on the signal characteristics of the newly connected sensors, according to the signal types supported by the multi-source sensor interface, the module searches for the corresponding signal parsing rules in the local signal parsing library to distinguish the types of newly connected sensors, and constructs a signal recognition command by combining the signal parsing rules and sensor types, executes the query operation, and obtains the response signal returned by the newly connected sensor;

[0047] The monitoring channel data acquisition module is used to parse the response signals returned by newly connected sensors, match and identify them with signal templates in the local signal parsing library, and find all monitoring channels of the newly connected sensors to obtain the monitoring channel data type and monitoring channel data access permissions; and based on the monitoring channel data type and monitoring channel data access permissions, obtain the input channel set and the output channel set respectively, and construct the monitoring channel data set.

[0048] The configuration file generation module takes the monitoring channel data set and the access interface information of newly connected sensors as input parameters, calls the anesthesia monitoring equipment configuration program to automatically apply signal analysis rules, obtains the final signal analysis information and sensor information, and generates a configuration file.

[0049] Beneficial effects: This invention acquires the configuration information of multi-source sensor interfaces of anesthesia monitoring equipment at regular intervals, identifies existing and newly connected sensors, analyzes response signals and constructs a monitoring channel data set, generates a configuration file, and introduces a unified positioning mechanism for multi-source data time scale and a dynamic weight allocation algorithm. This solves the problem of analysis accuracy caused by the lack of a unified time scale in existing technologies, improves the accuracy of multi-source data fusion, reduces the complexity and error of manual operation, optimizes the real-time monitoring and adjustment process, and automatically updates the local signal analysis library. It has strong compatibility and reliability, and high practicality and promotion value. Attached Figure Description

[0050] Figure 1 The diagram below shows a structural block diagram of a real-time anesthesia parameter adjustment and medical analysis method and system provided in this embodiment of the invention. Detailed Implementation

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0052] This invention provides a method and system for real-time anesthesia parameter adjustment and medical analysis. Its core lies in generating precise anesthesia parameter adjustment schemes through a unified time-scale positioning mechanism for multi-source data and a dynamic weight allocation algorithm based on drug action characteristics, combined with a multimodal data analysis module. The following is in conjunction with the appendix... Figure 1 The specific embodiments of the present invention will be described in detail below.

[0053] In practical applications, the entire system consists of multiple modules working collaboratively to complete anesthesia parameter adjustment and medical analysis tasks. It begins with the sensor information acquisition module, which periodically acquires the configuration information of the multi-source sensor interfaces on the anesthesia monitoring equipment. Based on this configuration information, it sends currently supported data acquisition commands to the multi-source sensor interfaces, thereby identifying and connecting existing and newly connected sensors. During this process, the sensor information acquisition module determines the sensor status based on whether the multi-source sensor interface has configured signal parsing rules. If the multi-source sensor interface has configured signal parsing rules and sensor information can be acquired according to the rules, the sensor is considered to be connected normally. If sensor information cannot be acquired according to the rules or the interface does not have configured signal parsing rules, a signal parsing rule traversal test is triggered to check the sensor response. The signal parsing rule traversal test combines various signal parsing parameter information to obtain different combinations of signal parsing rules, including parameters such as sampling frequency, resolution, filtering method, and gain settings. Based on each combination of signal parsing rules, broadcast data or specific commands are sent, and the sensor response is monitored. The specific command is a standardized query command for each sensor type, containing a sensor ID request field, signal format negotiation parameters, and basic configuration query information. It is used to trigger the sensor to return core data such as its own device identifier, signal output accuracy, and supported monitoring parameter types. If a sensor responds, the current signal parsing rule information is saved; otherwise, the original signal parsing rules are restored.

[0054] When a new sensor is connected, the sensor information acquisition module, based on the signal characteristics of the new sensor and the signal types supported by the multi-source sensor interface, searches the local signal parsing library for corresponding signal parsing rules to distinguish the new sensor type. This process first acquires the signal characteristics of the new sensor, then searches the local signal parsing library for corresponding signal parsing rules based on the signal types supported by the multi-source sensor interface on the anesthesia monitoring device. Next, it retrieves a list of sensor types supported by the found signal parsing rules from the local signal parsing library, parses the data packets sent by the new sensor to distinguish and determine its sensor type. After determining the signal parsing rules and sensor type, it constructs signal recognition commands and sends them iteratively, executing a query operation to receive the response signal returned by the new sensor.

[0055] The system then enters the monitoring channel data acquisition module's working phase. This module parses the response signals returned by newly accessed sensors, matches them against signal templates in the local signal parsing library, and searches for all monitoring channels of the newly accessed sensor to obtain the monitoring channel data type and access permissions. Specifically, based on the normal response format of the newly accessed sensor's response signal, it is parsed according to the response frame format corresponding to the signal recognition command to obtain the parsed response signal. The parsed response signal is then matched against the signal template corresponding to the current signal recognition command in the local signal parsing library to obtain the matching result. If the parsed response signal matches the signal template bound to the current signal recognition command, the newly accessed sensor is considered correctly identified, and all monitoring channels of the newly accessed sensor are searched based on the local signal parsing library to obtain the monitoring channel data type and access permissions. If the parsed response signal does not match the signal template bound to the current signal recognition command, other signal recognition commands are tried sequentially for matching. If all signal recognition commands fail to match, the matching result is recorded, and a manual processing prompt is sent to the administrator.

[0056] After obtaining the data type and access permissions of the monitoring channels, the monitoring channel data acquisition module further obtains the input channel set and output channel set based on this information, and constructs the monitoring channel data set. For continuous quantity monitoring channels, if their data access permissions are read-only or read-write, the module obtains the monitoring channel name, read function code, register address, monitoring channel value type, and conversion factor information, and generates a unique label name containing the monitoring channel data type information, saving it to obtain the continuous quantity input channel set; if their data access permissions are write-only or read-write, the module obtains the monitoring channel name, write function code, register address, monitoring channel value type, and conversion factor information, and generates a unique label name containing the monitoring channel data type information, saving it to obtain the continuous quantity output channel set. For discrete quantity monitoring channels, if their data access permissions are read-only or read-write, the monitoring channel name, read function code, register address, and bit information are obtained, and a unique tag name containing the monitoring channel data type information is generated and saved to obtain the discrete quantity input channel set. If their data access permissions are write-only or read-write, the monitoring channel name, write function code, register address, and bit information are obtained, and a unique tag name containing the monitoring channel data type information is generated and saved to obtain the discrete quantity output channel set. Finally, the continuous quantity input channel set, continuous quantity output channel set, discrete quantity input channel set, and discrete quantity output channel set are combined to construct the monitoring channel dataset, and the monitoring channel data within it is exported and logged.

[0057] Finally, the module enters its configuration file generation phase. This module takes the monitoring channel data set and the access interface information of the newly connected sensors as input parameters, calls the anesthesia monitoring equipment configuration program to automatically apply signal analysis rules, obtains the final signal analysis information and sensor information, and generates a configuration file. Specifically, it calls the anesthesia monitoring equipment configuration program with the monitoring channel data set and the access interface information of the newly connected sensors as input parameters. The program automatically reads the monitoring channel data set information and applies it to the specified access interface, performs automatic signal analysis rule configuration, and obtains the automatic signal analysis rule configuration result. Based on the successfully configured signal analysis rules, it sends specific test commands to the newly connected sensors, compares the data received by the anesthesia monitoring equipment with the expected data, and obtains the data verification and identification result. The specific test commands include standard test data simulating physiological signals, such as preset EEG signal alpha wave frequency range of 4-8Hz, heart rate baseline of 60-100 beats / minute, blood pressure baseline reference value of 120 / 80 mmHg, blood oxygen saturation threshold of 95%, and end-tidal carbon dioxide concentration baseline value of 35-45 mmHg, used to verify the sensor data acquisition accuracy, transmission stability, and the correctness of the analysis logic. If data verification is successful, the final signal analysis information and sensor information will be generated into a configuration file and saved to the local signal analysis library. If the automatic signal analysis rule configuration result or data verification result fails, the reason for the failure will be logged and a manual handling prompt will be sent to the administrator.

[0058] In practical applications, the collaborative work of the aforementioned modules ensures that the anesthesia monitoring device can quickly and accurately identify newly connected sensors and generate precise adjustment parameters suitable for different anesthetic drugs. For example, during surgery, anesthesiologists need to monitor changes in physiological parameters such as the patient's electroencephalogram (EEG), heart rate, blood pressure, blood oxygen saturation, and end-tidal carbon dioxide concentration in real time. Through the method and system provided by this invention, the anesthesia monitoring device can automatically identify newly connected sensors and generate corresponding configuration files based on their monitoring channel data type and access permissions, thereby achieving real-time monitoring and precise adjustment of the patient's physiological parameters. Furthermore, the local signal analysis library automatically retrieves the latest signal analysis rules from the cloud and updates them to ensure system compatibility and reliability. This design not only reduces the complexity and errors caused by numerous repetitive operations during manual adjustments but also significantly improves the accuracy of multi-source data fusion, optimizing the real-time monitoring and parameter adjustment process of the anesthesia state, demonstrating high practicality and promotional value.

[0059] To enable those skilled in the art to fully understand and implement this invention, the specific implementation principles of this invention are further supplemented below with a specific application scenario.

[0060] During surgery, anesthesiologists need to monitor changes in the patient's physiological parameters in real time, including electroencephalogram (EEG) signals, heart rate, blood pressure, blood oxygen saturation, and end-tidal carbon dioxide concentration. Using the method and system provided by this invention, anesthesia monitoring equipment can automatically identify newly connected sensors and generate precise adjustment parameters suitable for different anesthetic drugs. The following is in conjunction with the appendix... Figure 1 The structural block diagram in the document details the system's operation steps and its technical implementation principles.

[0061] First, the sensor information acquisition module starts working before the surgery begins, periodically acquiring the configuration information of the multi-source sensor interfaces on the anesthesia monitoring device. Taking an EEG sensor as an example, when a new sensor is inserted into the anesthesia monitoring device, the sensor information acquisition module detects that the interface is not configured with signal parsing rules, thus triggering a signal parsing rule traversal test. During this process, module 1 combines parameters such as sampling frequency, resolution, filtering method, and gain settings based on the signal types supported by the interface to generate various signal parsing rules. For example, for EEG signals, module 1 may try a combination of a 500Hz sampling frequency, 16-bit resolution, and a bandpass filter. By sending broadcast data or specific commands to the newly connected sensor, module 1 monitors its response. If the sensor responds, the current signal parsing rule information is saved; if there is no response, the original signal parsing rule is restored. This process ensures rapid identification and adaptation of newly connected sensors.

[0062] Subsequently, the monitoring channel data acquisition module intervenes. Taking a newly connected EEG sensor as an example, module 2 analyzes its returned response signal and matches it with signal templates in the local signal analysis library. For example, module 2 compares the analyzed response signal with the EEG sensor's preset signal template. If the match is successful, the sensor is considered correctly identified, and all its monitoring channels are searched based on the local signal analysis library. Assuming the sensor supports continuous EEG signal monitoring, module 2 further acquires its monitoring channel name, read function code, register address, value type, and conversion factor information, and generates a unique tag name, saving it to the continuous input channel set. For discrete monitoring channels (such as alarm status), module 2 also acquires its bit information and generates a unique tag name, saving it to the discrete input channel set. Finally, module 2 integrates all monitoring channel data into a monitoring channel data set and exports log records for subsequent analysis.

[0063] Finally, the configuration file generation module takes the monitoring channel data set and the access interface information of the newly connected sensor as input parameters, and calls the anesthesia monitoring device configuration program to automatically apply the signal analysis rules. For example, in the scenario of an EEG sensor, module 3 will apply the information in the monitoring channel data set to the specified interface and configure the signal analysis rules for a 500Hz sampling frequency, 16-bit resolution, and bandpass filter. Subsequently, module 3 sends a specific test command to the newly connected sensor to verify the received data against the expected data. If the verification is successful, the final signal analysis information and sensor information are generated and saved to the local signal analysis library. If the verification fails, the reason for the failure is recorded and a manual processing prompt is sent to the administrator.

[0064] Through the above steps, the anesthesia monitoring equipment can quickly and accurately identify newly connected EEG sensors and generate precise adjustment parameters applicable to different anesthetic drugs. For example, during surgery, inhaled anesthetics have a rapid effect on EEG signals, while intravenous anesthetics have a relatively delayed effect on circulatory system parameters. This system introduces a unified time-scale positioning mechanism for multi-source data to establish a unified time reference framework for physiological parameters such as EEG signals, heart rate, and blood pressure. Combined with a dynamic weight allocation algorithm based on drug action characteristics, the system can dynamically adjust the weights of each physiological parameter according to the characteristics of different anesthetic drugs. For example, for inhaled anesthetics, the system assigns higher weight to EEG signals, while for intravenous anesthetics, it focuses more on changes in heart rate and blood pressure. This design significantly improves the accuracy of multi-source data fusion and optimizes the real-time monitoring and parameter adjustment process of the anesthesia state.

[0065] Furthermore, the local signal analysis library automatically retrieves and updates the latest signal analysis rules from the cloud to ensure system compatibility and reliability. For example, when a new EEG sensor becomes available, the cloud pushes its corresponding signal analysis rules to the local signal analysis library, allowing the system to automatically adapt to the new sensor without manual intervention. This design not only reduces the complexity and errors caused by numerous repetitive operations during manual adjustments but also significantly enhances the system's practicality and promotional value.

[0066] In summary, this invention, through modular design and automated processes, enables anesthesia monitoring equipment to quickly identify and accurately adapt to newly connected sensors, while optimizing the accuracy of multi-source data fusion, providing reliable technical support for real-time monitoring and parameter adjustment of anesthesia status.

[0067] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, 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 process, method, article, or apparatus.

[0068] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for real-time anesthesia parameter adjustment and medical analysis, characterized in that, include: The system periodically acquires the configuration information of the multi-source sensor interface on the anesthesia monitoring device, and sends the currently supported data acquisition command to the multi-source sensor interface based on the configuration information to obtain the sensors connected to the anesthesia monitoring device; the sensors include existing sensors and newly connected sensors. Based on the signal characteristics of the newly accessed sensors, and according to the signal types supported by the multi-source sensor interface, the corresponding signal parsing rules are searched from the local signal parsing library to distinguish the types of the newly accessed sensors. Then, a signal recognition command is constructed by combining the signal parsing rules and the sensor type, and a query operation is performed to obtain the response signal returned by the newly accessed sensors. The response signals returned by the newly connected sensors are analyzed, matched and identified with signal templates in the local signal analysis library, and all monitoring channels of the newly connected sensors are located to obtain the data types and access permissions of the monitoring channels. Based on the data types and access permissions of the monitoring channels, the sets of input channels and output channels are obtained respectively, and the monitoring channel data set is constructed. Using the monitoring channel data set and the access interface information of newly connected sensors as input parameters, the anesthesia monitoring equipment configuration program is invoked to automatically apply signal analysis rules, obtain the final signal analysis information and sensor information, and generate a configuration file.

2. The method for real-time anesthesia parameter adjustment and medical analysis according to claim 1, characterized in that, Before acquiring the configuration information of the multi-source sensor interface on the anesthesia monitoring device, the process also includes: The signal types used by different sensors are obtained, a local signal parsing library is established, and the configuration information of the read and write parameters of each sensor under different signal types is recorded. The read and write parameters of the sensors include the frequency range of the electroencephalogram (EEG) signal, the fluctuation range of the heart rate, the baseline value of blood pressure, the threshold range of blood oxygen saturation, and the change curve of end-tidal carbon dioxide concentration. The automatic configuration program runs on the anesthesia monitoring device and periodically retrieves the latest signal analysis rules from the cloud to update the local signal analysis library.

3. The method for real-time anesthesia parameter adjustment and medical analysis according to claim 1, characterized in that, The process involves periodically acquiring configuration information of the multi-source sensor interface on the anesthesia monitoring device, and sending currently supported data acquisition commands to the multi-source sensor interface based on the configuration information to obtain the sensors connected to the anesthesia monitoring device, including: When the multi-source sensor interface has been configured with signal parsing rules and can obtain sensor information according to the signal parsing rules, it is determined that a sensor is normally connected to the current multi-source sensor interface. When the multi-source sensor interface has been configured with signal parsing rules but cannot obtain sensor information according to the signal parsing rules, a signal parsing rule traversal test is performed to detect the sensor response. When the multi-source sensor interface is not configured with signal parsing rules, a signal parsing rule traversal test is triggered to detect the sensor response.

4. The method for real-time anesthesia parameter adjustment and medical analysis according to claim 3, characterized in that, The process of performing signal analysis rule traversal testing and detecting sensor response includes: Based on the signal types supported by the current multi-source sensor interface, various signal analysis parameter information is combined to obtain different combinations of signal analysis rules; the signal analysis parameter information includes sampling frequency, resolution, filtering method, and gain setting. Based on the signal parsing rules for each combination, broadcast data or specific instructions are sent respectively, and the sensor response is monitored; the specific instructions are standardized query instructions for sensor types, including sensor ID request fields, signal format negotiation parameters and basic configuration query information, which are used to trigger the sensor to return core data such as its own device identifier, signal output accuracy and supported monitoring parameter types; When a sensor responds during the signal parsing rule traversal test, it is considered that a new sensor has been connected, and the current signal parsing rule information is saved. If no sensor responds during the signal parsing rule traversal test, it is assumed that no new sensor has been connected, and the original signal parsing rules of the multi-source sensor interface are restored.

5. The method for real-time anesthesia parameter adjustment and medical analysis according to claim 1, characterized in that, Based on the signal characteristics of the newly accessed sensors and the signal types supported by the multi-source sensor interface, the corresponding signal parsing rules are searched from the local signal parsing library to distinguish the types of the newly accessed sensors. A signal recognition command is then constructed by combining the signal parsing rules and the sensor type, and a query operation is executed to obtain the response signals returned by the newly accessed sensors, including: Acquire the signal characteristics of the newly connected sensor; Based on the signal characteristics of the newly acquired sensors, and according to the signal types supported by the multi-source sensor interfaces on the anesthesia monitoring equipment, the corresponding signal parsing rules are searched from the local signal parsing library. Retrieve the list of sensor types supported by the found signal parsing rules from the local signal parsing library, parse the data packets sent by the newly connected sensor, and distinguish and determine the sensor type of the newly connected sensor; Based on the established signal analysis rules and sensor types, construct signal recognition instructions; It iterates through the constructed signal identification commands, performs query operations, and receives response signals returned by newly accessed sensors.

6. The method for real-time anesthesia parameter adjustment and medical analysis according to claim 1, characterized in that, The process involves analyzing the response signals returned by the newly connected sensor, matching them with signal templates in the local signal analysis library, and searching for all monitoring channels of the newly connected sensor to obtain the data type and access permissions of the monitoring channels, including: The response signal returned by the newly accessed sensor based on the normal response format is parsed according to the response frame format corresponding to the signal recognition command to obtain the parsed response signal returned by the newly accessed sensor. Based on the response signal returned by the newly accessed sensor after parsing, it is matched and identified with the signal template corresponding to the current signal identification command in the local signal parsing library to obtain the matching and identification result; When the response signal returned by the newly accessed sensor after parsing matches the signal template bound to the current signal recognition instruction in the local signal parsing library, the newly accessed sensor is considered to have been correctly identified. Based on the search of all monitoring channels of the newly accessed sensor in the local signal parsing library, the data type and access permissions of the monitoring channel are obtained. If the response signal returned by the newly accessed sensor after parsing does not match the signal template bound to the current signal recognition command in the local signal parsing library, the newly accessed sensor is considered to have been incorrectly identified. The system will then perform sequential matching and identification based on other signal recognition commands in the local signal parsing library. If the response signal returned by the newly accessed sensor after parsing does not match the signal template bound to any of the other signal recognition commands in the local signal parsing library, the automatic configuration process is considered to have failed. The matching and identification results will be recorded, and a manual processing prompt will be sent to the administrator simultaneously.

7. The method for real-time anesthesia parameter adjustment and medical analysis according to claim 1, characterized in that, Based on the data type and access permissions of the monitoring channels, the input channel set and output channel set are obtained respectively, and a monitoring channel data set is constructed, including: If the current monitoring channel data type is continuous and the monitoring channel data access permission is read-only or read-write, then obtain the monitoring channel name, read function code, register address, monitoring channel value type, conversion factor information, and generate a unique tag name containing the monitoring channel data type information, and save it to obtain the continuous input channel set; If the current monitoring channel data type is continuous and the monitoring channel data access permission is write-only or read-write, then obtain the monitoring channel name, write function code, register address, monitoring channel value type, conversion factor information, and generate a unique tag name containing the monitoring channel data type information, and save it to obtain the continuous output channel set; If the current monitoring channel data type is discrete and the monitoring channel data access permission is read-only or read-write, then obtain the monitoring channel name, read function code, register address, bit information, and generate a unique tag name containing the monitoring channel data type information, and save it to obtain the discrete input channel set; If the current monitoring channel data type is discrete and the monitoring channel data access permission is write-only or read-write, then obtain the monitoring channel name, write function code, register address, bit information, and generate a unique tag name containing the monitoring channel data type information, and save it to obtain the discrete output channel set; By combining the sets of continuous input channels, continuous output channels, discrete input channels, and discrete output channels, a monitoring channel data set is constructed, and the monitoring channel data within it is exported and logged.

8. The method for real-time anesthesia parameter adjustment and medical analysis according to claim 1, characterized in that, Using the monitoring channel data set and the access interface information of newly connected sensors as input parameters, the anesthesia monitoring equipment configuration program is invoked to automatically apply signal analysis rules, obtaining the final signal analysis information and sensor information, and generating a configuration file, including: Using the monitoring channel data set and the access interface information of the newly connected sensor as input parameters, the anesthesia monitoring equipment configuration program is invoked to automatically read the monitoring channel data set information and apply it to the specified access interface to perform automatic signal parsing rule configuration and obtain the automatic signal parsing rule configuration result. Based on the successfully configured signal parsing rules, a specific test instruction is sent to the newly connected sensor to verify and identify the data received by the anesthesia monitoring device against the expected data, thereby obtaining the data verification and identification result. The specific test instruction includes standard test data simulating physiological signals, which is used to verify the sensor data acquisition accuracy, transmission stability, and parsing logic correctness. Based on the signal parsing rules that have been successfully verified by data, the final signal parsing information and sensor information are used to generate a configuration file, which is then saved to the local signal parsing library.

9. The method for real-time anesthesia parameter adjustment and medical analysis according to claim 8, characterized in that, If the automatic signal parsing rule configuration result or data verification result fails, the reason for the failure will be recorded in the log, and a manual processing prompt will be sent to the administrator simultaneously.

10. A system for the real-time anesthesia parameter adjustment and medical analysis method according to claim 1, characterized in that, include: The sensor information acquisition module is used to periodically acquire the configuration information of the multi-source sensor interface on the anesthesia monitoring device, and send the currently supported data acquisition command to the multi-source sensor interface based on the configuration information to obtain the sensors connected to the anesthesia monitoring device; the sensors include existing sensors and newly connected sensors; Based on the signal characteristics of the newly accessed sensors and according to the signal types supported by the multi-source sensor interface, the corresponding signal parsing rules are searched from the local signal parsing library to distinguish the types of the newly accessed sensors. The signal recognition instructions are constructed by combining the signal parsing rules and the sensor types, and the query operation is executed to obtain the response signals returned by the newly accessed sensors. The monitoring channel data acquisition module is used to parse the response signals returned by newly connected sensors, match and identify them with signal templates in the local signal parsing library, and find all monitoring channels of the newly connected sensors to obtain the monitoring channel data type and monitoring channel data access permissions; and based on the monitoring channel data type and monitoring channel data access permissions, obtain the input channel set and the output channel set respectively, and construct the monitoring channel data set. The configuration file generation module takes the monitoring channel data set and the access interface information of newly connected sensors as input parameters, calls the anesthesia monitoring equipment configuration program to automatically apply signal analysis rules, obtains the final signal analysis information and sensor information, and generates a configuration file.

Images