Equipment-assisted optimization system and method for anesthesia surgery

Abstract

The present invention discloses an equipment-assisted optimization system and method for anesthesia surgery, belonging to the technical field of anesthesia surgery equipment. The system includes: data collection in the early stage, which is performed in a clustering manner, allocating data storage space in a data storage device, the data storage device is arranged in an anesthesia machine, the anesthesia machine is used to gasify anesthetics and inject them into the patient's body, and the data storage space records data sample clusters; feature analysis in the mid-term of data, which is used to calibrate the error weight of sample features in response to the completion of the collection in the early stage of data; carrier recording in the late stage of data, which is used to construct a two-dimensional coordinate system as a carrier in response to the completion of the feature analysis in the mid-term of data, and the carrier carries the gasification time of anesthetics and the duration of anesthetic drug effect, which is used to attach point attribute values ​​to coordinate points in the two-dimensional coordinate system; equipment-assisted optimization decision, which is used to realize the display of auxiliary recommendation results of anesthetic drugs in the interface of the anesthesia machine in response to the completion of the carrier recording in the late stage of data.

Description

Technical Field

[0001] The present invention relates to the technical field of anesthesia surgery equipment, and in particular to an equipment auxiliary optimization system and method for anesthesia surgery. Background Art

[0002] In the field of medical equipment, the process of intelligence is profoundly changing the model and quality of medical services, bringing unprecedented convenience and efficiency to patients and medical staff, including but not limited to improving diagnostic accuracy and efficiency, promoting personalized medicine and reducing the burden on medical staff.

[0003] In gasification anesthesia equipment, the intelligent process can improve the accuracy and safety of anesthesia management, promote the overall efficiency of medical services and optimize patient experience, and assist medical staff in evaluating anesthesia parameters before surgery; however, due to different physical conditions of patients, the gasification time and efficacy control time of anesthetics vary from person to person, making the vision of the intelligent process difficult to achieve. Summary of the invention

[0004] The object of the present invention is to provide a device-assisted optimization system and method for anesthesia surgery to solve the problems raised in the above-mentioned background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] A device-assisted optimization system for anesthesia surgery, the system comprising: a memory, a processor, and a server program stored in the memory and executable on the processor, wherein the server executes instructions so that when the processor executes the server program, an device-assisted optimization method for anesthesia surgery of the present invention is implemented; the memory, the processor, and the server are all integrated in an anesthesia machine, and the anesthesia machine is used to gasify anesthetics and inject them into a patient's body;

[0007] The memory also includes a data source module, the data source module is used to realize the early stage of data collection, and present the collection results in the form of data sample clusters, and the data sample clusters record sample features; the data source module is used to record the error weights generated by the feature analysis of the mid-term of data; the data source module is also used to realize the carrier recording of the late stage of data, and construct a two-dimensional coordinate system as the carrier, the horizontal coordinate value of the two-dimensional coordinate system is the gasification time of the anesthetic drug, the vertical coordinate value of the two-dimensional coordinate system is the effect time of the anesthetic drug, and based on the error weight, the coordinate points in the two-dimensional coordinate system are added with point attribute values;

[0008] The processor also includes an algorithm module, which is used to calculate the sample cluster average, the global average, the error weight of the sample feature, and the correlation value between the point attribute values; the algorithm module is also used to evaluate whether the narcotic drug is displayed on a visual interface;

[0009] The server is used to implement the code programming of the algorithm module to form the server program.

[0010] Furthermore, the anesthesia machine is also integrated with a display interface, and the display interface is used to display the results of the evaluation.

[0011] A device-assisted optimization method for anesthesia surgery, the method comprising the following steps:

[0012] Step S1, data is stored in the early stage, the storage method is clustering, and further, data storage space is allocated in a data storage device, the data storage device is set in an anesthesia machine, the anesthesia machine is used to gasify anesthetics and inject them into the patient's body, and the data storage space records data sample clusters, including:

[0013] Step S11: compile an anesthesia surgery case log library to record the anesthetic drugs used in each anesthesia surgery, the anesthetic gasification time and the anesthetic drug effect time to form a log tag;

[0014] Step S12: a data storage space is allocated to a corresponding anesthetic drug, and a data sample cluster is generated based on the log tag, and the data sample cluster is recorded in the data storage space, wherein the data sample cluster records sample features.

[0015] Step S2: feature analysis of the data in the mid-term, in response to the completion of the collection of the data in the early stage, further, based on the data sample cluster, calibrate the error weight of the sample feature, including:

[0016] Step S21: Calculate the sample cluster average based on the data sample cluster;

[0017] Step S22: based on the data sample cluster, locking the sample domain, and calculating the whole domain average value based on the sample domain;

[0018] Step S23: Calculate the error weight of the sample feature based on the sample cluster average and the global average.

[0019] Step S3: After the feature analysis of the mid-term data is completed, a two-dimensional coordinate system is further constructed as the carrier, and the carrier carries the anesthetic gasification time and the anesthetic drug effect time, including:

[0020] Step S31: the horizontal coordinate value of the two-dimensional coordinate system is the gasification time of the anesthetic, and the vertical coordinate value of the two-dimensional coordinate system is the effect time of the anesthetic;

[0021] Step S32: adding point attribute values ​​to the coordinate points in the two-dimensional coordinate system based on the error weights.

[0022] Step S4: equipment-assisted optimization decision, which is used to realize the display of auxiliary recommendation results of anesthetic drugs in the interface of the anesthesia machine. Further, the staff inputs a parameter range in the anesthesia machine, and a rectangular outline is formed in the two-dimensional coordinate system through the parameter range, and auxiliary recommendation analysis of anesthetic drugs is performed based on the rectangular outline, including:

[0023] Step S41: the parameter range includes the value range of the anesthetic gasification time and the value range of the anesthetic effect time, and in the two-dimensional coordinate system, the point attribute values ​​of all coordinate points contained in the rectangular outline are used to generate a sample set to be optimized;

[0024] Step S42: Calculate the correlation value between two point attribute values ​​based on the sample set to be optimized;

[0025] Step S43: Based on the relevant values, evaluate whether the narcotic drugs are displayed on a visual interface.

[0026] Further, the data sample cluster is generated, and the specific process includes:

[0027] The anesthesia surgery cases are uniformly numbered, and the i-th anesthesia surgery case is recorded as SC i , and based on the anesthetic drugs, anesthetic gasification time and anesthetic effect duration, log tags are added to the anesthesia surgery cases, recorded as SC i :[SF a , t(SF a ), T(SF a )], where SF a represents the ath anesthetic drug, t(SF a ) indicates the use of narcotic drugs SF a The duration of anesthetic gasification during anesthesia surgery, T(SF a ) indicates the use of narcotic drugs SF a The duration of anesthetic effect during anesthesia surgery;

[0028] Based on the number of anesthetic drugs, data storage space is allocated, and one anesthetic drug is allocated one data storage space; based on the log label, a data sample cluster is generated, denoted as C(SF a )={SC i [t(SF a ), T(SF a)]|i∈[1,I]}, where C(SF a ) indicates narcotic SF a Corresponding to the generated data sample cluster, SC i [t(SF a ), T(SF a )] represents the sample characteristics, and SC i [t(SF a ), T(SF a )]=T(SF a ), I represents the total number of anesthesia surgery cases.

[0029] Further, based on the data sample cluster, the error weight of the sample feature is calibrated, and the specific process includes:

[0030] Based on the data sample cluster, calculate the sample cluster average

[0031] Based on data sample clusters, lock the sample domain Where A represents the total number of narcotic drugs, and the average value of the entire domain is calculated based on the sample domain D.

[0032] Calculate the sample feature SC based on the sample cluster average and the global average i [t(SF a )]

[0033] In the formula, NUM[C(SF a )] represents the data sample cluster C(SF a ), NUM(D) represents the total number of sample features contained in the sample domain D.

[0034] Further, the error weight is subjected to carrier characterization, and the specific process includes:

[0035] Constructing a two-dimensional coordinate system, wherein the horizontal axis value of the two-dimensional coordinate system is the duration of anesthetic drug gasification, and the vertical axis value of the two-dimensional coordinate system is the duration of anesthetic drug effect;

[0036] Based on the error weight, the coordinate point [t(SF a ), T(SF a )] additional point attribute value, denoted as F[t(SF a ), T(SF a )]=EW{SC i [t(SF a ), T(SF a )]}.

[0037] Further, auxiliary recommendation analysis of narcotic drugs is implemented based on the point attribute value, and the specific process includes:

[0038] The staff inputs the value range of the anesthetic gasification time and the value range of the anesthetic effect time in the anesthesia machine respectively, forms a rectangular outline L in the two-dimensional coordinate system through the value range, obtains the point attribute values ​​of all coordinate points in the rectangular outline L, and generates a sample set to be optimized, which is recorded as OS(L)={F[t(SF a ), T(SF a )]|a∈[1,A]};

[0039] In the sample set OS(L) to be optimized, any two point attribute values ​​are obtained, which are respectively recorded as point attribute value F1 and point attribute value F2, and the correlation value between the two point attribute values ​​is calculated.

[0040] If the correlation value RV is greater than or equal to the correlation threshold, the anesthetic drug SF corresponding to the two point attribute values ​​is displayed in the anesthesia machine interface a Otherwise, the anesthetic drugs SF corresponding to the two coordinate points will not be displayed in the anesthesia machine interface. a .

[0041] According to the above method, a medical record records a type of anesthetic drug, a type of gasification time and a type of anesthetic drug effect time of the anesthetic drug, and the gasification time and the anesthetic drug effect time are different due to the patient's physical condition, making the data characteristics very complex;

[0042] In the present invention, the early data collection and clustering is realized based on anesthetic drugs, anesthetic gasification time and anesthetic drug effect time. The amount of medical record data is huge, and it is necessary to regularly comb the properties of anesthetic drugs to form data sample clusters. The representation of sample features is simplified by log tags to reduce data storage space and size.

[0043] During the feature analysis of the data in the middle stage, the sample characteristics can reflect the specific medical records and the parameter characteristics of the anesthetic drugs used by the patient under the specific medical records, including the gasification time and anesthetic effect time of the anesthetic drug used during the patient's surgery. The anesthetic gasification time can affect the concentration of the anesthetic drug, and the concentration of the anesthetic drug reflects the anesthetic effect time characteristics in the patient's body. The sample characteristics are characterized by the anesthetic effect time characteristics, and then the medical record information, anesthetic drug information and anesthetic effect time information are sorted out; through big data, the average effect time of a certain anesthetic drug in different medical records can be quantified. The sample domain is formed by removing the duplication of the drug effect duration, and the average drug effect duration of a certain anesthetic drug for different patients is quantified through the sample domain. The former is an observation value based on the medical record quantity, and the latter is a universal value for reference based on the type of anesthetic drugs. The sample characteristics reflect that there is an observation error between the observation value and the universal value. The difference in the weight attribute of this error reflects the correlation characteristics between different anesthetic drugs, which is a manifestation of the idea of ​​clustering data analysis. The larger the error weight, the greater the impact on the correlation characteristics between different anesthetic drugs, and the worse the effect of data clustering.

[0044] When the carrier records the data later, the carrier records of the two-dimensional coordinate system are the concrete embodiment of the relationship between the data points during clustering;

[0045] When the equipment assists in optimizing decisions, if the point attribute values ​​corresponding to two data points are closer, it means that the clustering effect of the data points is better, and the different anesthetic drugs reflected by the data points are more correlated. The staff only needs to quickly screen out different anesthetic drugs according to the range of anesthetic gasification time and anesthetic effect time required by different patients, which improves the diagnostic efficiency and quality of the staff and meets the personalized needs of patients.

[0046] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: in an equipment-assisted optimization system and method for anesthesia surgery provided by the present invention, the data is collected in the early stage by clustering, data storage space is allocated in a data storage device, the data storage device is arranged in an anesthesia machine, the anesthesia machine is used to gasify anesthetics and inject them into the patient's body, and data sample clusters are recorded in the data storage space; the feature analysis of the mid-term data is used to calibrate the error weight of the sample feature in response to the completion of the collection of the early stage of the data; the carrier recording of the late stage of the data is constructed in response to the completion of the feature analysis of the mid-term data as a carrier, the carrier carries the gasification time of the anesthetic and the duration of the anesthetic effect, and is used to attach point attribute values ​​to the coordinate points in the two-dimensional coordinate system; the equipment-assisted optimization decision is used to realize the display of the auxiliary recommendation results of anesthetic drugs in the interface of the anesthesia machine in response to the completion of the carrier recording of the late stage of the data; the present invention can combine medical record big data, through intelligent data analysis and processing, to assist medical staff in pre-operative anesthesia parameter evaluation, and help medical staff to quickly locate the optimal anesthetic drugs for different patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0048] Figure 1 It is a schematic diagram of the steps of a device-assisted optimization method for anesthesia surgery according to the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0050] In the first embodiment, a device-assisted optimization system for anesthesia surgery is provided, the system comprising: a memory, a processor, and a server program stored in the memory and executable on the processor, wherein the server executes instructions so that when the processor executes the server program, a device-assisted optimization method for anesthesia surgery in the second embodiment is implemented; the memory, the processor, and the server are all integrated in an anesthesia machine, and the anesthesia machine is used to gasify anesthetics and inject them into a patient's body,

[0051] The memory also includes a data source module, the data source module is used to realize the early stage of data collection, and present the collection results in the form of data sample clusters, and the data sample clusters record sample features; the data source module is used to record the error weights generated by the feature analysis of the mid-term of data; the data source module is also used to realize the carrier recording of the late stage of data, and construct a two-dimensional coordinate system as the carrier, the horizontal coordinate value of the two-dimensional coordinate system is the gasification time of the anesthetic drug, the vertical coordinate value of the two-dimensional coordinate system is the effect time of the anesthetic drug, and based on the error weight, the coordinate points in the two-dimensional coordinate system are added with point attribute values;

[0052] The processor also includes an algorithm module, which is used to calculate the sample cluster average, the global average, the error weight of the sample feature, and the correlation value between the point attribute values; the algorithm module is also used to evaluate whether the narcotic drug is displayed on a visual interface;

[0053] The server is used to implement the code programming of the algorithm module to form the server program.

[0054] Preferably, the anesthesia machine is also integrated with a display interface, and the display interface is used to display the results of the evaluation.

[0055] See also Figure 1 In the second embodiment, a device-assisted optimization method for anesthesia surgery is provided, the method comprising the following steps:

[0056] Step S1, data is stored in the early stage, and the storage method is clustering. Exemplarily, data storage space is allocated in a data storage device, and the data storage device is set in an anesthesia machine, and the anesthesia machine is used to gasify anesthetics and inject them into the patient's body. The data storage space records data sample clusters, including:

[0057] Step S11: compile an anesthesia surgery case log library to record the anesthetic drugs used in each anesthesia surgery, the anesthetic gasification time and the anesthetic drug effect time to form a log tag;

[0058] Step S12: a data storage space is allocated to each anesthetic drug, and a data sample cluster is generated based on the log tag, and the data sample cluster is recorded in the data storage space, wherein the data sample cluster has sample features recorded therein;

[0059] Specifically, the anesthesia surgery cases are uniformly numbered, and the i-th anesthesia surgery case is recorded as SC i , and based on the anesthetic drugs, anesthetic gasification time and anesthetic effect duration, log tags are added to the anesthesia surgery cases, recorded as SC i :[SF a , t(SFa ), T(SF a )], where SF a represents the ath anesthetic drug, t(SF a ) indicates the use of narcotic drugs SF a The duration of anesthetic gasification during anesthesia surgery, T(SF a ) indicates the use of narcotic drugs SF a The duration of anesthetic effect during anesthesia surgery;

[0060] Based on the number of anesthetic drugs, data storage space is allocated, and one anesthetic drug is allocated one data storage space; based on the log label, a data sample cluster is generated, denoted as C(SF a )={SC i [t(SF a ), T(SF a )]|i∈[1,I]}, where C(SF a ) indicates narcotic SF a Corresponding to the generated data sample cluster, SC i [t(SF a ), T(SF a )] represents the sample characteristics, and SC i [t(SF a ), T(SF a )]=T(SF a ), I represents the total number of anesthesia surgery cases.

[0061] Step S2: mid-term feature analysis of data, in response to the completion of the early stage collection of data, exemplary, based on the data sample cluster, calibrating the error weight of the sample feature, including:

[0062] Step S21: Calculate the sample cluster average based on the data sample cluster;

[0063] Step S22: based on the data sample cluster, locking the sample domain, and calculating the whole domain average value based on the sample domain;

[0064] Step S23: Calculate the error weight of the sample feature based on the sample cluster average and the global average;

[0065] Specifically, based on the data sample cluster, calculate the sample cluster average

[0066] Based on data sample clusters, lock the sample domain Where A represents the total number of narcotic drugs, and the average value of the entire domain is calculated based on the sample domain D.

[0067] Calculate the sample feature SC based on the sample cluster average and the global average i [t(SF a )]

[0068] In the formula, NUM[C(SF a )] represents the data sample cluster C(SF a ), NUM(D) represents the total number of sample features contained in the sample domain D.

[0069] Step S3: After the feature analysis of the mid-term data is completed, a two-dimensional coordinate system is constructed as the carrier, and the carrier carries the anesthetic gasification time and the anesthetic drug effect time, including:

[0070] Step S31: the horizontal coordinate value of the two-dimensional coordinate system is the gasification time of the anesthetic, and the vertical coordinate value of the two-dimensional coordinate system is the effect time of the anesthetic;

[0071] Step S32: adding point attribute values ​​to the coordinate points in the two-dimensional coordinate system based on the error weights;

[0072] Specifically, a two-dimensional coordinate system is constructed, wherein the horizontal axis value of the two-dimensional coordinate system is the duration of anesthetic drug gasification, and the vertical axis value of the two-dimensional coordinate system is the duration of anesthetic drug effect;

[0073] Based on the error weight, the coordinate point [t(SF a ), T(SF a )] additional point attribute value, denoted as F[t(SF a ), T(SF a )]=EW{SC i [t(SF a ), T(SF a )]}.

[0074] Step S4: equipment-assisted optimization decision, in response to the completion of the data later carrier recording, is used to realize the display of auxiliary recommendation results of anesthetic drugs in the interface of the anesthesia machine. For example, the staff inputs a parameter range in the anesthesia machine, and a rectangular outline is formed in the two-dimensional coordinate system through the parameter range, and auxiliary recommendation analysis of anesthetic drugs is performed based on the rectangular outline, including:

[0075] Step S41: the parameter range includes the value range of the anesthetic gasification time and the value range of the anesthetic effect time, and in the two-dimensional coordinate system, the point attribute values ​​of all coordinate points contained in the rectangular outline are used to generate a sample set to be optimized;

[0076] Step S42: Calculate the correlation value between two point attribute values ​​based on the sample set to be optimized;

[0077] Step S43: Based on the relevant value, evaluating whether the anesthetic drug is displayed on a visual interface;

[0078] Specifically, the staff inputs the value range of the anesthetic gasification time and the value range of the anesthetic effect time in the anesthesia machine, respectively, forms a rectangular outline L in the two-dimensional coordinate system through the value range, obtains the point attribute values ​​of all coordinate points in the rectangular outline L, and generates a sample set to be optimized, which is recorded as OS(L)={F[t(SF a ), T(SF a )]|a∈[1,A]};

[0079] In the sample set OS(L) to be optimized, any two point attribute values ​​are obtained, which are respectively recorded as point attribute value F1 and point attribute value F2, and the correlation value between the two point attribute values ​​is calculated.

[0080] If the correlation value RV is greater than or equal to the correlation threshold, the anesthetic drug SF corresponding to the two point attribute values ​​is displayed in the anesthesia machine interface a Otherwise, the anesthetic drugs SF corresponding to the two coordinate points will not be displayed in the anesthesia machine interface. a .

[0081] In the third embodiment: a device-assisted optimization system for anesthesia surgery may be an electronic device;

[0082] The electronic device has a built-in computer storage medium, which may adopt any combination of one or more computer-readable media, and the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium;

[0083] Computer-readable storage media may be, for example, but not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses or devices, or any combination thereof; more specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof; in this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device;

[0084] A computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code; such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing; a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device;

[0085] The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire, optical cable, etc., or any suitable combination of the foregoing; the computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or a combination thereof, and the programming language includes an object-oriented programming language - such as Java, Smalltalk, C++, and also includes a conventional procedural programming language - such as "C" language or a similar programming language; the program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server; in the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0086] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0087] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A device-assisted optimization method for anesthesia surgery, the method comprising: Step S1, the data is stored in the early stage, and the storage method is clustering, which is characterized in that: data storage space is allocated in a data storage device, and the data storage device is set in an anesthesia machine, and the anesthesia machine is used to gasify anesthetics and inject them into the patient's body. The data storage space records data sample clusters, including: Step S11: compile an anesthesia surgery case log library to record the anesthetic drugs used in each anesthesia surgery, the anesthetic gasification time and the anesthetic drug effect time to form a log tag; Step S12: a data storage space is allocated to each anesthetic drug, and a data sample cluster is generated based on the log tag, and the data sample cluster is recorded in the data storage space, wherein the data sample cluster has sample features recorded therein; Step S2: mid-term feature analysis of data, in response to the completion of the early stage collection of data, is characterized by: based on the data sample cluster, calibrating the error weight of the sample feature, including: Step S21: Calculate the sample cluster average based on the data sample cluster; Step S22: based on the data sample cluster, locking the sample domain, and calculating the whole domain average value based on the sample domain; Step S23: Calculate the error weight of the sample feature based on the sample cluster average and the global average; Step S3: recording of the carrier of the late data, in response to the completion of the feature analysis of the mid-term data, is characterized by: constructing a two-dimensional coordinate system as the carrier, the carrier carrying the gasification time of the anesthetic and the duration of the anesthetic effect, including: Step S31: the horizontal coordinate value of the two-dimensional coordinate system is the gasification time of the anesthetic, and the vertical coordinate value of the two-dimensional coordinate system is the effect time of the anesthetic; Step S32: adding point attribute values ​​to the coordinate points in the two-dimensional coordinate system based on the error weights; Step S4: Equipment-assisted optimization decision, in response to the completion of the data later carrier recording, is used to realize the display of auxiliary recommendation results of anesthetic drugs in the interface of the anesthesia machine, characterized in that: the staff inputs a parameter range in the anesthesia machine, and a rectangular outline is formed in the two-dimensional coordinate system through the parameter range, and auxiliary recommendation analysis of anesthetic drugs is performed based on the rectangular outline, including: Step S41: the parameter range includes the value range of the anesthetic gasification time and the value range of the anesthetic effect time, and in the two-dimensional coordinate system, the point attribute values ​​of all coordinate points contained in the rectangular outline are used to generate a sample set to be optimized; Step S42: Calculate the correlation value between two point attribute values ​​based on the sample set to be optimized; Step S43: Based on the relevant values, evaluate whether the narcotic drugs are displayed on a visual interface.

2. The device-assisted optimization method for anesthesia surgery according to claim 1, characterized in that: The data sample cluster is generated, and the specific process includes: The anesthesia surgery cases are uniformly numbered, and the i-th anesthesia surgery case is recorded as SC i , and based on the anesthetic drugs, anesthetic gasification time and anesthetic effect duration, log tags are added to the anesthesia surgery cases, recorded as SC i :[SF a , t(SF a ), T(SF a )], where SF a represents the ath anesthetic drug, t(SF a ) indicates the use of narcotic drugs SF a The duration of anesthetic gasification during anesthesia surgery, T(SF a ) indicates the use of narcotic drugs SF a The duration of anesthetic effect during anesthesia surgery; Based on the number of anesthetic drugs, data storage space is allocated, and one anesthetic drug is allocated one data storage space; based on the log label, a data sample cluster is generated, denoted as C(SF a )={SC i [t(SF a ), T(SF a )]|i∈[1,I]}, where C(SF a ) indicates narcotic SF a Corresponding to the generated data sample cluster, SC i [t(SF a ), T(SF a )] represents the sample characteristics, and SC i [t(SF a ), T(SF a )]=T(SF a ), I represents the total number of anesthesia surgery cases.

3. The device-assisted optimization method for anesthesia surgery according to claim 2, characterized in that: Based on the data sample cluster, the error weight of the sample feature is calibrated, and the specific process includes: Based on the data sample cluster, calculate the sample cluster average Based on data sample clusters, lock the sample domain Where A represents the total number of narcotic drugs, and the average value of the entire domain is calculated based on the sample domain D. Calculate the sample feature SC based on the sample cluster average and the global average i [t(SF a )] In the formula, NUM[C(SF a )] represents the data sample cluster C(SF a ), NUM(D) represents the total number of sample features contained in the sample domain D.

4. The device-assisted optimization method for anesthesia surgery according to claim 3, characterized in that: The error weight is subjected to carrier characterization, and the specific process includes: Constructing a two-dimensional coordinate system, wherein the horizontal axis value of the two-dimensional coordinate system is the duration of anesthetic drug gasification, and the vertical axis value of the two-dimensional coordinate system is the duration of anesthetic drug effect; Based on the error weight, the coordinate point [t(SF a ), T(SF a )] additional point attribute value, denoted as F[t(SF a ), T(SF a )]=EW{SC i [t(SF a ), T(SF a )]}.

5. The device-assisted optimization method for anesthesia surgery according to claim 4, characterized in that: Based on the point attribute value, auxiliary recommendation analysis of narcotic drugs is realized, and the specific process includes: The staff inputs the value range of the anesthetic gasification time and the value range of the anesthetic effect time in the anesthesia machine respectively, forms a rectangular outline L in the two-dimensional coordinate system through the value range, obtains the point attribute values ​​of all coordinate points in the rectangular outline L, and generates a sample set to be optimized, which is recorded as OS(L)={F[t(SF a ), T(SF a )]|a∈[1,A]}; In the sample set OS(L) to be optimized, any two point attribute values ​​are obtained, which are respectively recorded as point attribute value F1 and point attribute value F2, and the correlation value between the two point attribute values ​​is calculated. If the correlation value RV is greater than or equal to the correlation threshold, the anesthetic drug SF corresponding to the two point attribute values ​​is displayed in the anesthesia machine interface a Otherwise, the anesthetic drugs SF corresponding to the two coordinate points will not be displayed in the anesthesia machine interface. a .

6. A device-assisted optimization system for anesthesia surgery, comprising a memory, a processor, and a server program stored in the memory and executable on the processor, wherein the processor executes the server program by executing instructions on the server to implement the device-assisted optimization method for anesthesia surgery according to claim 1, characterized in that: The memory, the processor and the server are all integrated in an anesthesia machine, and the anesthesia machine is used to gasify anesthetics and inject them into a patient's body. The memory also includes a data source module, which is used to realize the early stage of data collection and present the collection results in the form of data sample clusters, wherein the data sample clusters record sample features; the data source module is used to record the error weights generated by the feature analysis of the mid-term data; The data source module is also used to realize the carrier recording of the data later, and construct a two-dimensional coordinate system as the carrier, the horizontal coordinate value of the two-dimensional coordinate system is the gasification time of the anesthetic, the vertical coordinate value of the two-dimensional coordinate system is the effect time of the anesthetic, and based on the error weight, the point attribute value is added to the coordinate point in the two-dimensional coordinate system; The processor also includes an algorithm module, which is used to calculate the sample cluster average, the global average, the error weight of the sample feature, and the correlation value between the point attribute values; the algorithm module is also used to evaluate whether the narcotic drug is displayed on a visual interface; The server is used to implement the code programming of the algorithm module to form the server program.

7. The device-assisted optimization system for anesthesia surgery according to claim 6, characterized in that: The anesthesia machine is also integrated with a display interface, and the display interface is used to display the results of the evaluation.

Images