Big data-based postoperative care data analysis method and system for obstetrics and gynecology department

Through the big data analysis system, the postoperative nursing data of obstetrics and gynecology departments is collected, preprocessed and semantic encoding, and the patient's full-time domain physiological status representation vector is generated, which solves the problems of traditional nursing data silos and unstable quality, and realizes personalization Nursing protocols and postoperative recovery assessments improve nursing efficiency and patient satisfaction.

CN118969173APending Publication Date: 2024-11-15Puyang Maternal and Child Health Hospital (Puyang Obstetrics and Gynecology Hospital, Puyang Children's Hospital)
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411011532.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-26
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

Traditional obstetrics and gynecology postoperative nursing data lacks integration and unified platform, resulting in information silos, unstable nursing quality, and traditional data analysis systems cannot provide personalized analysis and nursing solutions, which cannot meet the special needs of different patients.

Method used

Using a big data-based obstetrics and gynecology postoperative nursing data analysis system, the patient's full-time domain physiological state time domain aggregation representation vector is generated by the patient's full-time domain physiological state for use in Postoperative recovery assessment and nursing program adjustment.

Benefits of technology

It has achieved personalized assessment and grade judgment of patients' postoperative recovery, helping medical staff to formulate scientific and reasonable nursing strategies, and improve nursing efficiency and patient satisfaction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118969173A_ABST
    Figure CN118969173A_ABST
Patent Text Reader

Abstract

The invention discloses a big data-based postoperative care data analysis method and system for the obstetrics and gynecology department. The method comprises the following steps: firstly, acquiring big data related to gynecological postoperative care of a patient object, then preprocessing the big data related to gynecological postoperative care, and then acquiring the big data related to gynecological postoperative care; the pre-processed health inquiry data, the pre-processed clinical detection data and the pre-processed acute physiological chronic health score data are acquired; performing global data context correlation analysis based on embedded coding and context coding on the preprocessed operation data and the preprocessed postoperative care responsibility data, and inputting the data into an information transfer aggregation analysis network to obtain a full-time-domain physiological state time-domain aggregation representation vector of the patient object; and based on the full-time-domain physiological state time domain aggregation representation vector of the patient object, determining a postoperative recovery level label.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of postoperative care, and in particular to a big data-based obstetrics and gynecology postoperative care data analysis method and system. Background Art

[0002] Gynecological surgery is a surgical treatment for women's reproductive system diseases or pregnancy complications. Postoperative care refers to the comprehensive care for patients after surgery, which aims to promote the patient's recovery, relieve pain, prevent complications, and improve the patient's quality of life. Gynecological and obstetric postoperative care involves postoperative pain management, infection prevention, emotional support, nutritional guidance and other aspects. Through scientific and reasonable postoperative care, patients' pain can be relieved, recovery can be promoted, the risk of complications can be reduced, and the quality of life can be improved.

[0003] However, traditional obstetrics and gynecology postoperative care data are usually scattered across various departments and systems, lacking an integrated and unified data platform, leading to information islands and making it difficult to fully understand the patient's physiological status. In addition, traditional obstetrics and gynecology postoperative care mainly relies on the experience and subjective judgment of nurses, which is highly subjective and has a low degree of standardization, which can easily lead to instability in care quality. In addition, traditional obstetrics and gynecology postoperative care data analysis systems can often only provide general statistical information, lack personalized analysis of individual patients and support for the formulation of care plans, and cannot meet the special needs of different patients.

[0004] Therefore, an optimized obstetrics and gynecology postoperative care data analysis system is desired. Summary of the invention

[0005] The present disclosure is made in consideration of the above problems. One object of the present disclosure is to provide a method and system for analyzing gynecological and obstetric postoperative nursing data based on big data.

[0006] The embodiment of the present disclosure provides a big data-based obstetrics and gynecology postoperative care data analysis system, which includes:

[0007] A postoperative care-related big data collection module is used to obtain big data related to obstetrics and gynecology postoperative care of the patient subject, wherein the big data related to obstetrics and gynecology postoperative care includes health consultation data, clinical test data, acute physiological and chronic health score data, operation data and postoperative care responsibility data;

[0008] A data preprocessing module, used to preprocess the big data related to the obstetrics and gynecology postoperative care to obtain preprocessed health consultation data, preprocessed clinical test data, preprocessed acute physiological and chronic health score data, preprocessed surgery data and preprocessed postoperative care responsibility data;

[0009] A nursing big data semantic coding module is used to perform global data context association analysis based on embedded coding and context coding on the pre-processed health consultation data, the pre-processed clinical test data, the pre-processed acute physiological and chronic health score data, the pre-processed surgery data and the pre-processed post-operative nursing responsibility data to obtain a contextual health consultation data semantic coding vector, a contextual clinical test data semantic coding vector, a contextual acute physiological and chronic health score data semantic coding vector, a contextual surgery data semantic coding vector and a contextual post-operative nursing responsibility data semantic coding vector;

[0010] A nursing big data semantic information transmission aggregation module is used to input the context health consultation data semantic coding vector, the context clinical test data semantic coding vector, the context acute physiological chronic health score data semantic coding vector, the context surgery data semantic coding vector and the context postoperative nursing responsibility data semantic coding vector into an information transmission aggregation analysis network to obtain a time-domain aggregation representation vector of the patient object's full-time-domain physiological state;

[0011] The postoperative recovery assessment module is used to determine a postoperative recovery grade label based on the time-domain aggregated representation vector of the full-time-domain physiological state of the patient object.

[0012] For example, according to the big data-based obstetrics and gynecology postoperative nursing data analysis system of an embodiment of the present disclosure, the nursing big data semantic coding module includes:

[0013] A nursing big data embedding semantic analysis unit is used to respectively perform vector embedding coding on the pre-processed health consultation data, the pre-processed clinical test data, the pre-processed acute physiological and chronic health score data, the pre-processed surgery data and the pre-processed post-operative nursing responsibility data to obtain a health consultation data embedding coding vector, a clinical test data embedding coding vector, an acute physiological and chronic health score data embedding coding vector, a surgery data embedding coding vector and a post-operative nursing responsibility data embedding coding vector;

[0014] The nursing big data global context encoding unit is used to arrange the health consultation data embedded coding vector, the clinical test data embedded coding vector, the acute physiological chronic health score data embedded coding vector, the surgery data embedded coding vector and the postoperative nursing responsibility data embedded coding vector into a sequence of coding vectors and input them into a global data context encoder based on a Transformer structure to obtain the context health consultation data semantic coding vector, the context clinical test data semantic coding vector, the context acute physiological chronic health score data semantic coding vector, the context surgery data semantic coding vector and the context postoperative nursing responsibility data semantic coding vector.

[0015] For example, according to the big data-based obstetrics and gynecology postoperative nursing data analysis system of an embodiment of the present disclosure, the nursing big data semantic information transmission aggregation module includes:

[0016] a neighborhood-aware optimization unit, configured to perform neighborhood-aware optimization on the sth semantic coding vector among the contextual health consultation data semantic coding vector, the contextual clinical test data semantic coding vector, the contextual acute physiology and chronic health score data semantic coding vector, the contextual surgery data semantic coding vector, and the contextual postoperative care responsibility data semantic coding vector to obtain an sth weighted optimized semantic coding vector;

[0017] A position-based summing unit is used to calculate the position-based sum of the semantic coding vectors of the contextual health consultation data, the contextual clinical test data, the contextual acute physiological chronic health score data, the contextual surgery data, and the contextual postoperative care responsibility data except the sth semantic coding vector to obtain other semantic fusion representation vectors;

[0018] A summing perception unit, used for summing the other semantic fusion representation vectors and the s-th weighted optimized semantic coding vector by position and then processing the sum by a multi-layer perceptron to obtain a reinforced semantic coding vector corresponding to the s-th semantic coding vector;

[0019] The aggregation analysis unit is used to perform a time-domain aggregation analysis of the patient object's full-time physiological state on the enhanced semantic coding vectors corresponding to each of the semantic coding vectors in the context health consultation data semantic coding vector, the context clinical test data semantic coding vector, the context acute physiological chronic health score data semantic coding vector, the context surgery data semantic coding vector, and the context postoperative care responsibility data semantic coding vector to obtain a time-domain aggregation representation vector of the patient object's full-time physiological state.

[0020] For example, according to the big data-based obstetrics and gynecology postoperative care data analysis system of an embodiment of the present disclosure, the neighborhood-aware optimization unit is used to:

[0021] The sum of the trainable preset hyperparameter and one is used as the weighting coefficient to weight the positional feature values ​​of the sth semantic coding vector among the contextual health consultation data semantic coding vector, the contextual clinical examination data semantic coding vector, the contextual acute physiology and chronic health score data semantic coding vector, the contextual surgery data semantic coding vector and the contextual postoperative care responsibility data semantic coding vector to obtain the sth weighted optimized semantic coding vector.

[0022] For example, according to the big data-based obstetrics and gynecology postoperative care data analysis system of an embodiment of the present disclosure, the aggregation analysis unit is used to:

[0023] The enhanced semantic coding vectors corresponding to each semantic coding vector in the context health consultation data semantic coding vector, the context clinical examination data semantic coding vector, the context acute physiological chronic health score data semantic coding vector, the context surgery data semantic coding vector and the context postoperative care responsibility data semantic coding vector are cascaded to obtain the time-domain aggregated representation vector of the patient object's full-time-domain physiological state.

[0024] For example, according to the big data-based obstetrics and gynecology postoperative care data analysis system of an embodiment of the present disclosure, the postoperative recovery assessment module is used to:

[0025] The time-domain aggregated representation vector of the full-time-domain physiological state of the patient object is passed through a postoperative recovery evaluator based on a classifier to obtain an evaluation result, and the evaluation result is used to represent a postoperative recovery grade label.

[0026] For example, according to the big data-based gynecological and obstetric postoperative care data analysis system of an embodiment of the present disclosure, it also includes a training module for training the Transformer-based global data context encoder, the information transfer aggregation analysis network and the classifier-based postoperative recovery evaluator.

[0027] For example, according to the big data-based obstetrics and gynecology postoperative care data analysis system of an embodiment of the present disclosure, the training module includes:

[0028] A training data acquisition unit, used to obtain training data, wherein the training data includes training big data related to obstetrics and gynecology postoperative care of training patient subjects and real evaluation results, wherein the training big data related to obstetrics and gynecology postoperative care includes training health consultation data, training clinical test data, training acute physiological chronic health score data, training surgery data and postoperative care responsibility data;

[0029] A training data preprocessing unit, used for preprocessing the training big data related to the obstetrics and gynecology postoperative care to obtain preprocessed training health consultation data, preprocessed training clinical test data, preprocessed training acute physiological chronic health score data, preprocessed training surgery data and preprocessed training postoperative care responsibility data;

[0030] A training nursing big data embedding semantic analysis unit is used to respectively perform vector embedding coding on the pre-processed training health consultation data, the pre-processed training clinical detection data, the pre-processed training acute physiological chronic health scoring data, the pre-processed training surgery data and the pre-processed training post-operative nursing responsibility data to obtain a training health consultation data embedding coding vector, a training clinical detection data embedding coding vector, a training acute physiological chronic health scoring data embedding coding vector, a training surgery data embedding coding vector and a training post-operative nursing responsibility data embedding coding vector;

[0031] A training nursing big data global context encoding unit is used to arrange the training health consultation data embedding encoding vector, the training clinical test data embedding encoding vector, the training acute physiological chronic health score data embedding encoding vector, the training surgery data embedding encoding vector and the training postoperative nursing responsibility data embedding encoding vector into a sequence of encoding vectors and input them into the Transformer-structured global data context encoder to obtain a training context health consultation data semantic encoding vector, a training context clinical test data semantic encoding vector, a training context acute physiological chronic health score data semantic encoding vector, a training context surgery data semantic encoding vector and a training context postoperative nursing responsibility data semantic encoding vector;

[0032] A training nursing big data semantic information transmission aggregation unit is used to input the training context health consultation data semantic coding vector, the training context clinical test data semantic coding vector, the training context acute physiological chronic health score data semantic coding vector, the training context surgery data semantic coding vector and the training context postoperative nursing responsibility data semantic coding vector into the information transmission aggregation analysis network to obtain a time-domain aggregation representation vector of the full-time-domain physiological state of the training patient object;

[0033] A training postoperative recovery assessment unit, used for passing the time-domain aggregated representation vector of the full-time-domain physiological state of the training patient object through the classifier-based postoperative recovery assessor to obtain a training assessment result;

[0034] A training classification loss function value calculation unit, used to calculate the cross entropy loss function value between the training evaluation result and the true evaluation result to obtain a classification loss function value;

[0035] A loss training unit is used to train the Transformer-based global data context encoder, the information transfer aggregation analysis network and the classifier-based postoperative recovery evaluator based on the classification loss function value.

[0036] The embodiment of the present disclosure also provides a method for analyzing postoperative nursing data of obstetrics and gynecology based on big data, which comprises:

[0037] Obtaining big data related to postoperative care of patients in obstetrics and gynecology, wherein the big data related to postoperative care of patients in obstetrics and gynecology includes health consultation data, clinical test data, acute physiological and chronic health score data, operation data and postoperative care responsibility data;

[0038] Preprocessing the big data related to postoperative care in obstetrics and gynecology to obtain post-processing health consultation data, post-processing clinical test data, post-processing acute physiological and chronic health score data, post-processing surgery data, and post-processing postoperative care responsibility data;

[0039] Performing global data context association analysis based on embedded coding and context coding on the pre-processed health consultation data, the pre-processed clinical test data, the pre-processed acute physiological and chronic health score data, the pre-processed surgery data, and the pre-processed post-operative nursing responsibility data to obtain a contextual health consultation data semantic coding vector, a contextual clinical test data semantic coding vector, a contextual acute physiological and chronic health score data semantic coding vector, a contextual surgery data semantic coding vector, and a contextual post-operative nursing responsibility data semantic coding vector;

[0040] Inputting the contextual health consultation data semantic encoding vector, the contextual clinical test data semantic encoding vector, the contextual acute physiological chronic health score data semantic encoding vector, the contextual surgery data semantic encoding vector and the contextual postoperative care responsibility data semantic encoding vector into an information transfer aggregation analysis network to obtain a time-domain aggregation representation vector of the patient object's full-time-domain physiological state;

[0041] Based on the time-domain aggregated representation vector of the full-time-domain physiological state of the patient object, a postoperative recovery level label is determined.

[0042] For example, according to the big data-based obstetrics and gynecology postoperative care data analysis method of an embodiment of the present disclosure, the pre-processed health consultation data, the pre-processed clinical test data, the pre-processed acute physiological and chronic health score data, the pre-processed surgery data and the pre-processed post-operative care responsibility data are subjected to global data context association analysis based on embedded coding and context coding to obtain context health consultation data semantic coding vectors, context clinical test data semantic coding vectors, context acute physiological and chronic health score data semantic coding vectors, context surgery data semantic coding vectors and context post-operative care responsibility data semantic coding vectors, including:

[0043] Performing vector embedding coding on the pre-processed health consultation data, the pre-processed clinical test data, the pre-processed acute physiological and chronic health score data, the pre-processed surgical data, and the pre-processed post-operative nursing responsibility data respectively to obtain a health consultation data embedding coding vector, a clinical test data embedding coding vector, an acute physiological and chronic health score data embedding coding vector, a surgical data embedding coding vector, and a post-operative nursing responsibility data embedding coding vector;

[0044] The health consultation data embedding coding vector, the clinical test data embedding coding vector, the acute physiological chronic health score data embedding coding vector, the surgical data embedding coding vector and the postoperative care responsibility data embedding coding vector are arranged as a sequence of coding vectors and input into a global data context encoder based on a Transformer structure to obtain the context health consultation data semantic coding vector, the context clinical test data semantic coding vector, the context acute physiological chronic health score data semantic coding vector, the context surgical data semantic coding vector and the context postoperative care responsibility data semantic coding vector.

[0045] According to the big data-based obstetrics and gynecology postoperative care data analysis method and system of the embodiments of the present disclosure, it collects big data related to obstetrics and gynecology postoperative care of patients, including health consultation data, clinical test data, acute physiological and chronic health score data, surgical data and postoperative care responsibility data, and introduces data processing and analysis algorithms based on big data and artificial intelligence technology at the back end to analyze these big data related to obstetrics and gynecology postoperative care and aggregate information transmission, so as to capture the characteristic representation of the patient's obstetrics and gynecology postoperative physiological state, so as to evaluate and grade the patient's postoperative recovery, thereby helping medical staff to adjust the care plan in time, to formulate a more scientific and reasonable postoperative care strategy, and to improve care efficiency and patient satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings of the embodiments of the present disclosure. Obviously, the drawings described below only relate to some embodiments of the present disclosure, and are not intended to limit the present disclosure.

[0047] Figure 1 A schematic diagram of the application architecture of a gynecology and obstetrics postoperative care data analysis system based on big data in an embodiment of the present disclosure is shown;

[0048] Figure 2 A schematic diagram of the structure of a gynecology and obstetrics postoperative nursing data analysis system based on big data in an embodiment of the present disclosure is shown;

[0049] Figure 3A structural schematic diagram of a nursing big data semantic coding module of a gynecology and obstetrics postoperative nursing data analysis system based on big data in an embodiment of the present disclosure is shown;

[0050] Figure 4 A structural schematic diagram of a nursing big data semantic information transmission aggregation module of a big data-based obstetrics and gynecology postoperative nursing data analysis system in an embodiment of the present disclosure is shown;

[0051] Figure 5 A flowchart of a method for analyzing postoperative nursing data of obstetrics and gynecology based on big data in an embodiment of the present disclosure is shown;

[0052] Figure 6 An application scenario diagram of a gynecology and obstetrics postoperative care data analysis system based on big data in an embodiment of the present disclosure is shown; and

[0053] Figure 7 A schematic diagram of a storage medium according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0054] The technical solutions in the embodiments of the present disclosure will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present disclosure, rather than all embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present disclosure.

[0055] The terms used in this specification are those general terms currently widely used in the art in consideration of the functions of the present disclosure, but these terms may vary according to the intention of a person of ordinary skill in the art, precedents, or new technologies in the art. In addition, specific terms may be selected by the applicant, and in this case, their detailed meanings will be described in the detailed description of the present disclosure. Therefore, the terms used in the specification should not be understood as simple names, but rather as an overall description based on the meaning of the terms and the present disclosure.

[0056] Although the present disclosure makes various references to certain modules in the system according to embodiments of the present disclosure, any number of different modules can be used and run on a user terminal and / or server. The modules are illustrative only, and different aspects of the systems and methods can use different modules.

[0057] Flowcharts are used in this disclosure to illustrate the operations performed by the system according to the embodiments of the present disclosure. It should be understood that the preceding or following operations are not necessarily performed precisely in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0058] Figure 1 A schematic diagram of the application architecture of a gynecological and obstetric postoperative care data analysis system based on big data in an embodiment of the present disclosure is shown, including a server 100 and a terminal device 200.

[0059] The terminal device 200 and the server 100 can be connected via the Internet to achieve mutual communication. Optionally, the above-mentioned Internet uses standard communication technology and / or protocol. The Internet is usually the Internet, but it can also be any network, including but not limited to any combination of a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a dedicated network or a virtual private network. In some embodiments, the data exchanged through the network is represented by technologies and / or formats including Hyper Text Markup Language (HTML), Extensible Markup Language (XML), etc. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPsec) can also be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above-mentioned data communication technologies.

[0060] The server 100 can provide various network services for the terminal device 200, wherein the server 100 can be a single server, a server cluster consisting of several servers, or a cloud computing center. Specifically, the server 100 may include a processor 110 (Center Processing Unit, CPU), a memory 120, an input device 130, and an output device 140, etc. The input device 130 may include a keyboard, a mouse, a touch screen, etc., and the output device 140 may include a display device, such as a liquid crystal display (Liquid Crystal Display, LCD), a cathode ray tube (Cathode Ray Tube, CRT), etc.

[0061] The memory 120 may include a read-only memory (ROM) and a random access memory (RAM), and provides the processor 110 with program instructions and data stored in the memory 120. In the embodiment of the present disclosure, the memory 120 may be used to store the corresponding method of the obstetrics and gynecology postoperative care data analysis system based on big data in the embodiment of the present disclosure.

[0062] The processor 110 calls the program instructions stored in the memory 120, and the processor 110 is used to execute the steps of any one of the big data-based obstetrics and gynecology postoperative care data analysis methods in the embodiments of the present disclosure according to the obtained program instructions.

[0063] In addition, the application architecture diagram in the embodiment of the present disclosure is intended to more clearly illustrate the technical solution in the embodiment of the present disclosure, and does not constitute a limitation on the technical solution provided in the embodiment of the present disclosure. Of course, for other application architectures and business applications, the technical solution provided in the embodiment of the present disclosure is also applicable to similar problems.

[0064] The following is a non-restrictive description of the big data-based gynecological and obstetric postoperative care data analysis system provided according to at least one embodiment of the present disclosure through several examples or embodiments. As described below, different features in these specific examples or embodiments can be combined with each other without conflicting with each other to obtain new examples or embodiments, and these new examples or embodiments also fall within the scope of protection of the present disclosure.

[0065] In today's medical field, with the rapid development of big data and artificial intelligence technology, it has become a trend to use big data analysis to improve the quality of medical care. Especially in the field of obstetrics and gynecology, postoperative care is crucial to the recovery and health of patients. Through in-depth analysis of postoperative care-related data of a large number of patients, it can help nursing staff better understand the patient's condition, develop personalized care plans, and improve care efficiency and quality.

[0066] Based on this, in the technical solution of the present invention, a big data-based obstetrics and gynecology postoperative care data analysis system is proposed, which can collect big data related to obstetrics and gynecology postoperative care of patients, including health consultation data, clinical test data, acute physiological and chronic health score data, surgical data and postoperative care responsibility data, and introduce data processing and analysis algorithms based on big data and artificial intelligence technology at the back end to analyze and aggregate information transmission of these big data related to obstetrics and gynecology postoperative care, so as to capture the characteristic representation of the patient's obstetrics and gynecology postoperative physiological state, so as to evaluate and grade the patient's postoperative recovery, thereby helping medical staff to adjust the care plan in time, to formulate more scientific and reasonable postoperative care strategies, and to improve care efficiency and patient satisfaction.

[0067] Figure 2The structural schematic diagram of the obstetrics and gynecology postoperative care data analysis system 800 based on big data in the embodiment of the present disclosure is shown. The obstetrics and gynecology postoperative care data analysis system 800 based on big data includes: a postoperative care related big data acquisition module 810, which is used to obtain big data related to obstetrics and gynecology postoperative care of the patient object, wherein the big data related to obstetrics and gynecology postoperative care includes health consultation data, clinical test data, acute physiological and chronic health score data, surgery data and postoperative care responsibility data; a data preprocessing module 820, which is used to preprocess the big data related to obstetrics and gynecology postoperative care to obtain preprocessed health consultation data, preprocessed clinical test data, preprocessed acute physiological and chronic health score data, preprocessed surgery data and preprocessed postoperative care responsibility data; a nursing big data semantic encoding module 830, which is used to encode the preprocessed health consultation data, the preprocessed clinical test data, the preprocessed acute physiological and chronic health score data, the preprocessed surgery data and the preprocessed postoperative care responsibility data A global data context association analysis based on embedded coding and context coding is performed to obtain a context health consultation data semantic coding vector, a context clinical test data semantic coding vector, a context acute physiological and chronic health scoring data semantic coding vector, a context surgery data semantic coding vector, and a context postoperative nursing responsibility data semantic coding vector; a nursing big data semantic information transmission aggregation module 840 is used to input the context health consultation data semantic coding vector, the context clinical test data semantic coding vector, the context acute physiological and chronic health scoring data semantic coding vector, the context surgery data semantic coding vector, and the context postoperative nursing responsibility data semantic coding vector into an information transmission aggregation analysis network to obtain a patient object full-time domain physiological state time-domain aggregation representation vector; a postoperative recovery assessment module 850 is used to determine a postoperative recovery grade label based on the patient object full-time domain physiological state time-domain aggregation representation vector.

[0068] Specifically, in the technical solution of the present disclosure, first, the big data related to the postoperative care of obstetrics and gynecology of the patient object is obtained, wherein the big data related to the postoperative care of obstetrics and gynecology includes health consultation data, clinical test data, acute physiological and chronic health score data, operation data and postoperative care responsibility data. It should be understood that since the big data related to the postoperative care of obstetrics and gynecology of the patient object is usually scattered in various departments and systems, these data sources from different data sources may have formatting differences, etc., making it difficult to perform subsequent correlation analysis and semantic understanding. Based on this, in the technical solution of the present disclosure, it is necessary to pre-process the big data related to the postoperative care of obstetrics and gynecology to obtain the pre-processed health consultation data, pre-processed clinical test data, pre-processed acute physiological and chronic health score data, pre-processed operation data and pre-processed postoperative care responsibility data. By pre-processing the big data related to the postoperative care of obstetrics and gynecology of the patient object, the nursing-related big data information of different data sources can be converted into the same format, and the invalid data, abnormal values ​​or missing values ​​therein can be screened and removed to ensure the quality and consistency of the data, so as to more comprehensively understand the physiological state of the patient.

[0069] Then, considering that the health consultation data contains information such as the patient's symptom description and medical records, the clinical test data contains various clinical test indicators of the patient, the acute physiological and chronic health score data contains information such as the patient's physiological indicators and disease scores, the surgical data contains information such as the type of surgery, the time of surgery, and the surgical site, and the postoperative care responsibility data contains information such as postoperative care measures and responsibility allocation, these information contain relevant semantics about the patient's surgery and postoperative period, which can be used to judge the postoperative physiological state of the patient. Therefore, in order to better utilize these data semantics and correlation relationships to make judgments on postoperative recovery in obstetrics and gynecology, in the technical solution disclosed in the present invention, it is necessary to respectively perform vector embedding coding on the pre-processed health consultation data, the pre-processed clinical test data, the pre-processed acute physiological and chronic health score data, the pre-processed surgical data, and the pre-processed postoperative care responsibility data to obtain the health consultation data embedding coding vector, the clinical test data embedding coding vector, the acute physiological and chronic health score data embedding coding vector, the surgical data embedding coding vector, and the postoperative care responsibility data embedding coding vector. Through embedded coding processing, the embedded semantic features of each data item in the big data related to obstetrics and gynecology postoperative care can be captured, so as to more accurately understand and analyze the patient's surgical process, physiological state and postoperative recovery. For example, the patient's condition, health status, the impact of surgery on the patient, and the impact of nursing on the patient's recovery, etc., will help to subsequently transmit and integrate information on these data to improve the accuracy of the assessment of the postoperative recovery level.

[0070] Further, considering that the big data related to postoperative care in obstetrics and gynecology, such as health consultation data, clinical test data, acute physiological chronic health score data, surgical data and postoperative care responsibility data, have semantic associations and contextual features. That is to say, these big data items related to postoperative care in obstetrics and gynecology will influence and work together, thereby affecting the postoperative recovery of the patient. Based on this, in order to be able to semantically integrate and correlate these big data items related to postoperative care in obstetrics and gynecology, so as to help the model better understand the correlation between various data, so as to more accurately analyze and judge the postoperative recovery of the patient, in the technical solution disclosed in the present invention, firstly, the health consultation data embedding coding vector, the clinical test data embedding coding vector, the acute physiological chronic health score data embedding coding vector, the surgical data embedding coding vector and the postoperative care responsibility data embedding coding vector are arranged as a sequence of coding vectors and input into the global data context encoder based on the Transformer structure to obtain the context health consultation data semantic coding vector, the context clinical test data semantic coding vector, the context acute physiological chronic health score data semantic coding vector, the context surgical data semantic coding vector and the context postoperative care responsibility data semantic coding vector. Through the processing of the global data context encoder based on the Transformer structure, the embedded semantic features between health consultation data, clinical test data, acute physiological chronic health score data, surgical data and postoperative nursing responsibility data can be contextually encoded, thereby capturing the contextual semantics and association features based on global data between various nursing-related big data items, improving the semantic representation ability of nursing-related big data of patient objects, and providing more comprehensive and accurate support for the analysis of obstetrics and gynecology postoperative nursing data and postoperative recovery evaluation.

[0071] Accordingly, if Figure 3As shown, the nursing big data semantic encoding module 830 includes: a nursing big data embedded semantic analysis unit 831, which is used to perform vector embedding encoding on the pre-processed health consultation data, the pre-processed clinical test data, the pre-processed acute physiological and chronic health scoring data, the pre-processed surgery data and the pre-processed post-operative nursing responsibility data to obtain a health consultation data embedded coding vector, a clinical test data embedded coding vector, an acute physiological and chronic health scoring data embedded coding vector, a surgery data embedded coding vector and a post-operative nursing responsibility data embedded coding vector; a nursing big data global context encoding unit 832, which is used to arrange the health consultation data embedded coding vector, the clinical test data embedded coding vector, the acute physiological and chronic health scoring data embedded coding vector, the surgery data embedded coding vector and the post-operative nursing responsibility data embedded coding vector into a sequence of coding vectors and input them into a global data context encoder based on a Transformer structure to obtain the context health consultation data semantic coding vector, the context clinical test data semantic coding vector, the context acute physiological and chronic health scoring data semantic coding vector, the context surgery data semantic coding vector and the context post-operative nursing responsibility data semantic coding vector.

[0072] It should be understood that since the contextual health consultation data semantic coding vector, the contextual clinical test data semantic coding vector, the contextual acute physiological chronic health scoring data semantic coding vector, the contextual surgery data semantic coding vector and the contextual postoperative care responsibility data semantic coding vector respectively represent the global contextual semantic association features between the health consultation data embedded semantic features, the clinical test data embedded semantic features, the acute physiological chronic health scoring data embedded semantic features, the surgery data embedded semantic features and the postoperative care responsibility data embedded semantic features, this semantic feature can only reflect the constrained semantic expression of each postoperative care-related big data item in the global semantics of the postoperative care-related big data. Therefore, in order to be able to integrate and transfer information about these different contextual semantic features of big data items about postoperative care, so as to more comprehensively reflect the patient's overall physiological state, thereby facilitating the subsequent determination of the patient's postoperative recovery level, in the technical solution disclosed in the present invention, the contextual health consultation data semantic coding vector, the contextual clinical test data semantic coding vector, the contextual acute physiological chronic health score data semantic coding vector, the contextual surgery data semantic coding vector and the contextual postoperative care responsibility data semantic coding vector are further input into the information transfer aggregation analysis network to obtain the patient object's full-time domain physiological state time-domain aggregation representation vector. Through the processing of the information transfer aggregation analysis network, the contextual semantic features of the big data items related to obstetrics and gynecology postoperative care, such as health consultation data, clinical test data, acute physiological chronic health score data, surgery data and postoperative care responsibility data, can be information transferred and interacted, so as to capture the global information in the big data related to obstetrics and gynecology postoperative care and the complex semantic relationship between each data item, and help the model better understand the patient's overall postoperative physiological state, so as to make subsequent determinations of the postoperative recovery level.

[0073] Accordingly, if Figure 4As shown, the nursing big data semantic information transmission aggregation module 840 includes: a neighborhood-aware optimization unit 841, which is used to perform neighborhood-aware optimization on the sth semantic coding vector of the context health consultation data semantic coding vector, the context clinical test data semantic coding vector, the context acute physiological chronic health scoring data semantic coding vector, the context surgery data semantic coding vector and the context postoperative nursing responsibility data semantic coding vector to obtain the sth weighted optimized semantic coding vector; a position-based summation unit 842, which is used to calculate the sth semantic coding vector of the context health consultation data semantic coding vector, the context clinical test data semantic coding vector, the context acute physiological chronic health scoring data semantic coding vector, the context surgery data semantic coding vector and the context postoperative nursing responsibility data semantic coding vector except the sth semantic coding vector. The other semantic coding vectors other than the coding vector are summed up by position to obtain other semantic fusion representation vectors; the sum perception unit 843 is used to sum the other semantic fusion representation vectors and the s-th weighted optimized semantic coding vector by position and then process them through a multi-layer perceptron to obtain the enhanced semantic coding vector corresponding to the s-th semantic coding vector; the aggregation analysis unit 844 is used to perform time-domain aggregation analysis of the patient object's full-time-domain physiological state on the enhanced semantic coding vectors corresponding to each of the semantic coding vectors in the context health consultation data semantic coding vector, the context clinical test data semantic coding vector, the context acute physiological and chronic health scoring data semantic coding vector, the context surgery data semantic coding vector and the context postoperative care responsibility data semantic coding vector to obtain the patient object's full-time-domain physiological state time-domain aggregation representation vector.

[0074] Among them, the neighborhood-aware optimization unit 841 is used to: use the sum of the trainable preset hyperparameter and one as the weighting coefficient to weight the positional feature values ​​of the sth semantic coding vector in the context health consultation data semantic coding vector, the context clinical examination data semantic coding vector, the context acute physiological chronic health score data semantic coding vector, the context surgery data semantic coding vector and the context postoperative care responsibility data semantic coding vector to obtain the sth weighted optimized semantic coding vector.

[0075] Among them, the aggregation analysis unit 844 is used to: cascade the enhanced semantic coding vectors corresponding to each semantic coding vector in the context health consultation data semantic coding vector, the context clinical test data semantic coding vector, the context acute physiological chronic health score data semantic coding vector, the context surgery data semantic coding vector and the context postoperative care responsibility data semantic coding vector to obtain the time domain aggregation representation vector of the patient object's full time domain physiological state.

[0076] The nursing big data semantic information transmission aggregation module 840 is used to: input the context health consultation data semantic coding vector, the context clinical test data semantic coding vector, the context acute physiological chronic health score data semantic coding vector, the context surgery data semantic coding vector and the context postoperative nursing responsibility data semantic coding vector into the information transmission aggregation analysis network for processing with the following information transmission aggregation formula to obtain enhanced context health consultation data semantic coding vector, enhanced context clinical test data semantic coding vector, enhanced context acute physiological chronic health score data semantic coding vector, enhanced context surgery data semantic coding vector and enhanced context postoperative nursing responsibility data semantic coding vector; wherein, the information transmission aggregation formula is:

[0077]

[0078] Among them, V s is one of the semantic encoding vectors of the contextual health consultation data, the contextual clinical test data, the contextual acute physiology and chronic health score data, the contextual surgery data, and the contextual postoperative care responsibility data, V k is the context health consultation data semantic encoding vector, the context clinical test data semantic encoding vector, the context acute physiology chronic health score data semantic encoding vector, the context surgery data semantic encoding vector and the context postoperative care responsibility data semantic encoding vector except V s ∈ is a trainable preset hyperparameter, MLP(·) represents a multi-layer perceptron, n is the number of semantic encoding vectors in the contextual health consultation data semantic encoding vector, the contextual clinical test data semantic encoding vector, the contextual acute physiology and chronic health score data semantic encoding vector, the contextual surgery data semantic encoding vector, and the contextual postoperative care responsibility data semantic encoding vector minus one, V s′ is a corresponding semantic coding vector among the enhanced context health consultation data semantic coding vector, the enhanced context clinical examination data semantic coding vector, the enhanced context acute physiological chronic health scoring data semantic coding vector, the enhanced context surgery data semantic coding vector and the enhanced context postoperative care responsibility data semantic coding vector; the enhanced context health consultation data semantic coding vector, the enhanced context clinical examination data semantic coding vector, the enhanced context acute physiological chronic health scoring data semantic coding vector, the enhanced context surgery data semantic coding vector and the enhanced context postoperative care responsibility data semantic coding vector are cascaded to obtain the time-domain aggregated representation vector of the patient object's full-time-domain physiological state.

[0079] Then, the time-domain aggregated representation vector of the patient's full-time physiological state is passed through a postoperative recovery evaluator based on a classifier to obtain an evaluation result, which is used to represent the postoperative recovery grade label. In other words, the time-domain aggregated representation information of the patient's overall physiological state is used for classification processing, so that the patient's postoperative physiological state feature representation of the obstetrics and gynecology postoperative condition is used to evaluate and grade the patient's postoperative recovery, thereby helping medical staff to adjust the nursing plan in a timely manner, to formulate a more scientific and reasonable postoperative nursing strategy, and to improve nursing efficiency and patient satisfaction.

[0080] Accordingly, the postoperative recovery assessment module 850 is used to: pass the time-domain aggregated representation vector of the full-time physiological state of the patient subject through a classifier-based postoperative recovery assessor to obtain an assessment result, and the assessment result is used to represent a postoperative recovery grade label.

[0081] In the technical solution of the present application, considering that the health consultation data, the clinical test data, the acute physiological and chronic health scoring data, the surgical data and the postoperative care responsibility data have data modality differences and content differences in the data source domain, the context health consultation data semantic coding vector, the context clinical test data semantic coding vector, the context acute physiological and chronic health scoring data semantic coding vector, the context surgical data semantic coding vector and the context postoperative care responsibility data semantic coding vector obtained by embedded coding and context association coding have relatively significant feature distribution inconsistency, which will result in that when the context health consultation data semantic coding vector, the context clinical test data semantic coding vector, the context acute physiological and chronic health scoring data semantic coding vector, the context surgical data semantic coding vector and the context postoperative care responsibility data semantic coding vector are input into the information transfer aggregation analysis network, the obtained multimodal feature distribution aggregation feature manifold of the time-domain aggregated representation vector of the patient object's full-time-domain physiological state has poor monotonicity, thereby affecting the overall distribution regression constraint of the time-domain aggregated representation vector of the patient object's full-time-domain physiological state for the classifier-based postoperative recovery evaluator. Therefore, it is expected that in the information transfer aggregation analysis, the extreme category deviation caused by the imbalance of the correspondence ratio under the fine-grained distribution of time series can be further compensated to improve the accuracy of the classification results.

[0082] Preferably, the time-domain aggregated representation vector of the full-time-domain physiological state of the patient object is passed through a postoperative recovery evaluator based on a classifier to obtain an evaluation result, including:

[0083] Calculate the first norm and second norm of the mean vector of the contextual health consultation data semantic encoding vector, the contextual clinical test data semantic encoding vector, the contextual acute physiology chronic health score data semantic encoding vector, the contextual surgery data semantic encoding vector, and the contextual postoperative care responsibility data semantic encoding vector;

[0084] Calculate the weighted sum of the inverse of the square root of the two norms and the one norm, and perform point multiplication with the point-added sum vector of the contextual health consultation data semantic encoding vector, the contextual clinical test data semantic encoding vector, the contextual acute physiology and chronic health score data semantic encoding vector, the contextual surgery data semantic encoding vector, and the contextual postoperative care responsibility data semantic encoding vector to obtain a time-domain aggregated correction subvector of the full time-domain physiological state of the first patient object;

[0085] The dot product vector of the contextual health consultation data semantic coding vector, the contextual clinical test data semantic coding vector, the contextual acute physiological chronic health score data semantic coding vector, the contextual surgery data semantic coding vector and the contextual postoperative care responsibility data semantic coding vector is dotted with the square root of the length of the patient object full time domain physiological state time domain aggregation representation vector to obtain a second patient object full time domain physiological state time domain aggregation correction subvector;

[0086] Calculating a weighted sum of the time-domain aggregated correction subvector of the first patient object's full-time-domain physiological state and the time-domain aggregated correction subvector of the second patient object's full-time-domain physiological state to obtain a time-domain aggregated correction vector of the patient object's full-time-domain physiological state;

[0087] Performing a dot multiplication of the time-domain aggregation correction vector of the full-time-domain physiological state of the patient object and the time-domain aggregation representation vector of the full-time-domain physiological state of the patient object to obtain a corrected time-domain aggregation representation vector of the full-time-domain physiological state of the patient object;

[0088] The corrected patient object's full-time-domain physiological state time-domain aggregated representation vector is passed through a postoperative recovery evaluator based on a classifier to obtain an evaluation result.

[0089] The time-domain aggregated correction vector of the full-time-domain physiological state of the patient object is expressed as:

[0090]

[0091] Among them, V i (i=1-5) are respectively the semantic encoding vector of the contextual health consultation data, the semantic encoding vector of the contextual clinical test data, the semantic encoding vector of the contextual acute physiological and chronic health score data, the semantic encoding vector of the contextual surgery data and the semantic encoding vector of the contextual postoperative care responsibility data, V μ is its mean vector, ‖V μ ‖1 and ‖V μ ‖2 represents the first norm and second norm of the mean vector of the contextual health consultation data semantic encoding vector, the contextual clinical test data semantic encoding vector, the contextual acute physiological chronic health score data semantic encoding vector, the contextual surgery data semantic encoding vector and the contextual postoperative care responsibility data semantic encoding vector, respectively, L is the length of the time-domain aggregate representation vector of the full-time domain physiological state of the patient object, and α and β are weighted sums of weights as hyperparameters, represents addition by position, ⊙ represents point product, and V' represents the time-domain aggregated correction vector of the full-time-domain physiological state of the patient object.

[0092] Therefore, based on the constrained representation of the structured foreground and background distinction of the supermanifold of the mean vector norm between the context health consultation data semantic encoding vector, the context clinical examination data semantic encoding vector, the context acute physiological chronic health scoring data semantic encoding vector, the context surgery data semantic encoding vector and the context postoperative care responsibility data semantic encoding vector, the feature-level key correspondence between the feature vectors of the context health consultation data semantic encoding vector, the context clinical examination data semantic encoding vector, the context acute physiological chronic health scoring data semantic encoding vector, the context surgery data semantic encoding vector and the context postoperative care responsibility data semantic encoding vector is modeled, and the global correlation relationship between the corresponding features is adjusted, so as to make positive fine-grained corresponding suggestions by controlling the imbalance ratio between the corresponding feature values ​​of the context health consultation data semantic encoding vector, the context clinical examination data semantic encoding vector, the context acute physiological chronic health scoring data semantic encoding vector, the context surgery data semantic encoding vector and the context postoperative care responsibility data semantic encoding vector, so as to avoid extreme imbalance of categories between their feature vectors by focusing on the focus.

[0093] In this way, by correcting the time-domain aggregation representation vector of the patient's full-time physiological state through the time-domain aggregation correction vector of the patient's full-time physiological state, the accuracy of the evaluation result obtained by inputting the time-domain aggregation representation vector of the patient's full-time physiological state into the postoperative recovery evaluator based on the classifier can be improved.

[0094] Furthermore, in the technical solution of the present invention, the big data-based obstetrics and gynecology postoperative care data analysis system also includes a training module for training the Transformer-based global data context encoder, the information transfer aggregation analysis network and the classifier-based postoperative recovery evaluator.

[0095] The training module includes: a training data acquisition unit for acquiring training data, wherein the training data includes training big data related to obstetrics and gynecology postoperative care of training patients and real evaluation results, wherein the training big data related to obstetrics and gynecology postoperative care includes training health consultation data, training clinical detection data, training acute physiological and chronic health scoring data, training surgery data and postoperative care responsibility data; a training data preprocessing unit for preprocessing the training big data related to obstetrics and gynecology postoperative care to obtain preprocessed training health consultation data, preprocessed training clinical detection data, preprocessed training acute physiological and chronic health scoring data, preprocessed training surgery data and preprocessed training postoperative care responsibility data. The preprocessed training health consultation data, the preprocessed training clinical test data, the preprocessed training acute physiological chronic health score data, the preprocessed training surgery data and the preprocessed training postoperative nursing responsibility data are respectively vector embedded and coded to obtain the training health consultation data embedding coding vector, the training clinical test data embedding coding vector, the training acute physiological chronic health score data embedding coding vector, the training surgery data embedding coding vector and the training postoperative nursing responsibility data embedding coding vector; the training nursing big data global context coding unit is used to embed the training health consultation data embedding coding vector, the training clinical test data embedding coding vector, the training acute physiological chronic health score data embedding coding vector, the training surgery data embedding coding vector and the training postoperative nursing responsibility data embedding coding vector. The embedded coding vector, the embedded coding vector of the training acute physiological and chronic health score data, the embedded coding vector of the training surgery data and the embedded coding vector of the training postoperative nursing responsibility data are arranged as a sequence of coding vectors and input into the global data context encoder based on the Transformer structure to obtain the semantic coding vector of the training context health consultation data, the semantic coding vector of the training context clinical detection data, the semantic coding vector of the training context acute physiological and chronic health score data, the semantic coding vector of the training context surgery data and the semantic coding vector of the training context postoperative nursing responsibility data; the training nursing big data semantic information transmission aggregation unit is used to transmit the semantic coding vector of the training context health consultation data, The training context clinical test data semantic encoding vector, the training context acute physiological chronic health score data semantic encoding vector, the training context surgical data semantic encoding vector and the training context postoperative nursing responsibility data semantic encoding vector are input into the information transfer aggregation analysis network to obtain the time-domain aggregation representation vector of the full-time-domain physiological state of the training patient object; a training postoperative recovery evaluation unit is used to pass the time-domain aggregation representation vector of the full-time-domain physiological state of the training patient object through the classifier-based postoperative recovery evaluator to obtain a training evaluation result; a training classification loss function value calculation unit is used to calculate the cross entropy loss function value between the training evaluation result and the true evaluation result to obtain a classification loss function value;A loss training unit, used to train the Transformer-based global data context encoder, the information transfer aggregation analysis network, and the classifier-based postoperative recovery evaluator based on the classification loss function value. ;

[0096] In a preferred example, the training postoperative recovery assessment unit is specifically used to: obtain the training patient object's full time domain physiological state time domain aggregation representation vector by summing the square root of the length of the training patient object's full time domain physiological state time domain aggregation representation vector and the inverse of the square root of the second norm of the training patient object's full time domain physiological state time domain aggregation representation vector to obtain the training patient object's full time domain physiological state time domain aggregation rotation offset feature vector; calculate the exponential function of the training patient object's full time domain physiological state time domain aggregation rotation offset feature vector with a natural constant as the base to obtain the training patient object's full time domain physiological state time domain aggregation class offset prediction feature vector; The full-time physiological state time-domain aggregation representation vector is dot-multiplied with a norm and a weight hyperparameter of the full-time physiological state time-domain aggregation representation vector of the training patient object to obtain the full-time physiological state time-domain aggregation boundary constraint feature vector of the training patient object; the full-time physiological state time-domain aggregation class offset prediction feature vector of the training patient object is dot-multiplied with the full-time physiological state time-domain aggregation boundary constraint feature vector of the training patient object to obtain an optimized full-time physiological state time-domain aggregation representation vector of the training patient object; and the optimized full-time physiological state time-domain aggregation representation vector of the training patient object is passed through the classifier-based postoperative recovery evaluator to obtain the training evaluation result.

[0097] In the above preferred example, the structured norm representation of the time-domain aggregated representation vector of the full-time-domain physiological state of the training patient object is used as the local canonical coordinates for each eigenvalue of the time-domain aggregated representation vector of the full-time-domain physiological state of the training patient object to determine the class rotation offset of the vector overall distribution of the full-time-domain physiological state of the training patient object relative to the eigenvalue for the class offset prediction direction of each eigenvalue of the time-domain aggregated representation vector of the full-time-domain physiological state of the training patient object as the center, and the bounding box of the vector eigenvalue distribution of the full-time-domain physiological state of the training patient object is used for eigenvalue constraint to improve the constraint of the full-time-domain physiological state of the training patient object under the overall regression distribution, thereby improving the training speed of the model and the accuracy of the evaluation result of the full-time-domain physiological state of the training patient object obtained by the postoperative recovery evaluator based on the classifier. In this way, the postoperative recovery of the patient object can be evaluated and graded more accurately, thereby helping medical staff to adjust the nursing plan in time to formulate a more scientific and reasonable postoperative nursing strategy.

[0098] Based on the above embodiments, see Figure 5 FIG. 1 is a flowchart of a method for analyzing postoperative nursing data of obstetrics and gynecology based on big data in an embodiment of the present disclosure. For example, the method for analyzing postoperative nursing data of obstetrics and gynecology based on big data can be executed by a server, which can be Figure 1 The server 100 shown in FIG. Figure 5 As shown, according to the big data-based obstetrics and gynecology postoperative care data analysis method of the embodiment of the present disclosure, the steps include: S510, obtaining big data related to obstetrics and gynecology postoperative care of the patient subject, wherein the big data related to obstetrics and gynecology postoperative care includes health consultation data, clinical test data, acute physiological and chronic health score data, surgery data and postoperative care responsibility data; S520, preprocessing the big data related to obstetrics and gynecology postoperative care to obtain preprocessed health consultation data, preprocessed clinical test data, preprocessed acute physiological and chronic health score data, preprocessed surgery data and preprocessed postoperative care responsibility data; S530, combining the preprocessed health consultation data, the preprocessed clinical test data, the preprocessed acute physiological and chronic health score data, the preprocessed surgery data and the preprocessed postoperative care responsibility data Perform context association analysis of global data based on embedded coding and context coding to obtain context health consultation data semantic coding vector, context clinical examination data semantic coding vector, context acute physiological chronic health scoring data semantic coding vector, context surgery data semantic coding vector and context postoperative nursing responsibility data semantic coding vector; S540, input the context health consultation data semantic coding vector, the context clinical examination data semantic coding vector, the context acute physiological chronic health scoring data semantic coding vector, the context surgery data semantic coding vector and the context postoperative nursing responsibility data semantic coding vector into an information transfer aggregation analysis network to obtain a time-domain aggregation representation vector of the patient object's full-time physiological state; S550, determine a postoperative recovery level label based on the time-domain aggregation representation vector of the patient object's full-time physiological state.

[0099] Accordingly, in a possible implementation, the pre-processed health consultation data, the pre-processed clinical test data, the pre-processed acute physiological and chronic health scoring data, the pre-processed surgical data and the pre-processed post-operative nursing responsibility data are subjected to global data context association analysis based on embedded coding and context coding to obtain context health consultation data semantic coding vectors, context clinical test data semantic coding vectors, context acute physiological and chronic health scoring data semantic coding vectors, context surgical data semantic coding vectors and context post-operative nursing responsibility data semantic coding vectors, including: respectively performing vector embedding coding on the pre-processed health consultation data, the pre-processed clinical test data, the pre-processed acute physiological and chronic health scoring data, the pre-processed surgical data and the pre-processed post-operative nursing responsibility data to obtain Health consultation data embedding coding vectors, clinical test data embedding coding vectors, acute physiological chronic health score data embedding coding vectors, surgery data embedding coding vectors and postoperative care responsibility data embedding coding vectors; the health consultation data embedding coding vectors, clinical test data embedding coding vectors, acute physiological chronic health score data embedding coding vectors, surgery data embedding coding vectors and postoperative care responsibility data embedding coding vectors are arranged as a sequence of coding vectors and input into a global data context encoder based on a Transformer structure to obtain the context health consultation data semantic coding vectors, the context clinical test data semantic coding vectors, the context acute physiological chronic health score data semantic coding vectors, the context surgery data semantic coding vectors and the context postoperative care responsibility data semantic coding vectors.

[0100] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned big data-based obstetrics and gynecology postoperative nursing data analysis method have been referred to above. Figures 2 to 4 The big data-based obstetrics and gynecology postoperative care data analysis system 800 has been introduced in detail, and therefore, its repeated description will be omitted.

[0101] Figure 6 FIG. 1 is an application scenario diagram of a gynecology and obstetrics postoperative care data analysis system based on big data according to an embodiment of the present disclosure. Figure 6 As shown, in this application scenario, first, big data related to obstetrics and gynecology postoperative care of the patient object is obtained (for example, Figure 6 D), then, the big data related to obstetrics and gynecology postoperative care is input into a server (for example, Figure 6In S) shown in , the server is able to use the big data-based obstetrics and gynecology postoperative care data analysis algorithm to process the big data related to obstetrics and gynecology postoperative care to obtain an evaluation result for representing a postoperative recovery level label.

[0102] Based on the above embodiment, another exemplary embodiment of an electronic device is also provided in the embodiments of the present disclosure. In some possible implementations, the electronic device in the embodiments of the present disclosure may include a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor can implement the steps of the obstetrics and gynecology postoperative care data analysis method based on big data in the above embodiment when executing the program.

[0103] For example, the electronic device is disclosed in the present invention Figure 1 Taking the server 100 in the example as an example, the processor in the electronic device is the processor 110 in the server 100, and the memory in the electronic device is the memory 120 in the server 100.

[0104] An embodiment of the present disclosure also provides a computer-readable storage medium. Figure 7 FIG. 1 is a schematic diagram of a computer-readable storage medium 1000 according to an embodiment of the present disclosure. Figure 7 As shown, the computer-readable storage medium 1000 stores computer-executable instructions 1001. When the computer-executable instructions 1001 are executed by the processor, the obstetrics and gynecology postoperative care data analysis method based on big data according to the embodiment of the present disclosure described with reference to the above figures can be executed. The computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc.

[0105] The embodiment of the present disclosure also provides a computer program product or computer program, which includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the obstetrics and gynecology postoperative care data analysis method based on big data according to the embodiment of the present disclosure.

[0106] Those skilled in the art will appreciate that the contents disclosed in this disclosure may be subject to various modifications and improvements. For example, the various devices or components described above may be implemented by hardware, or by software, firmware, or a combination of some or all of the three.

[0107] In addition, although the present disclosure makes various references to certain units in the system according to embodiments of the present disclosure, any number of different units may be used and run on the client and / or server. The units are illustrative only, and different aspects of the systems and methods may use different units.

[0108] Those skilled in the art will appreciate that all or part of the steps in the above method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk. Optionally, all or part of the steps in the above embodiment can also be implemented using one or more integrated circuits. Accordingly, each module / unit in the above embodiment can be implemented in the form of hardware or in the form of a software functional module. The present disclosure is not limited to any particular form of combination of hardware and software.

[0109] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present disclosure belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology and should not be interpreted in an idealized or highly formal sense, unless explicitly defined as such herein.

[0110] The above is an explanation of the present disclosure and should not be considered as a limitation thereof. Although several exemplary embodiments of the present disclosure have been described, it will be readily understood by those skilled in the art that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present disclosure. Therefore, all such modifications are intended to be included within the scope of the present disclosure as defined in the claims. It should be understood that the above is an explanation of the present disclosure and should not be considered as being limited to the specific embodiments disclosed, and modifications to the disclosed embodiments and other embodiments are intended to be included within the scope of the appended claims. The present disclosure is defined by the claims and their equivalents.

Claims

1. A big data-based obstetrics and gynecology postoperative care data analysis system. It is characterized in that include: A postoperative care-related big data collection module is used to obtain big data related to obstetrics and gynecology postoperative care of the patient subject, wherein the big data related to obstetrics and gynecology postoperative care includes health consultation data, clinical test data, acute physiological and chronic health score data, operation data and postoperative care responsibility data; A data preprocessing module, used to preprocess the big data related to the obstetrics and gynecology postoperative care to obtain preprocessed health consultation data, preprocessed clinical test data, preprocessed acute physiological and chronic health score data, preprocessed surgery data and preprocessed postoperative care responsibility data; A nursing big data semantic coding module is used to perform global data context association analysis based on embedded coding and context coding on the pre-processed health consultation data, the pre-processed clinical test data, the pre-processed acute physiological and chronic health score data, the pre-processed surgery data and the pre-processed post-operative nursing responsibility data to obtain a contextual health consultation data semantic coding vector, a contextual clinical test data semantic coding vector, a contextual acute physiological and chronic health score data semantic coding vector, a contextual surgery data semantic coding vector and a contextual post-operative nursing responsibility data semantic coding vector; A nursing big data semantic information transmission aggregation module is used to input the context health consultation data semantic coding vector, the context clinical test data semantic coding vector, the context acute physiological chronic health score data semantic coding vector, the context surgery data semantic coding vector and the context postoperative nursing responsibility data semantic coding vector into an information transmission aggregation analysis network to obtain a time-domain aggregation representation vector of the patient object's full-time-domain physiological state; The postoperative recovery assessment module is used to determine a postoperative recovery grade label based on the time-domain aggregated representation vector of the full-time-domain physiological state of the patient object.

2. According to the big data-based obstetrics and gynecology postoperative care data analysis system of claim 1, It is characterized in that The nursing big data semantic coding module includes: A nursing big data embedding semantic analysis unit is used to respectively perform vector embedding coding on the pre-processed health consultation data, the pre-processed clinical test data, the pre-processed acute physiological and chronic health score data, the pre-processed surgery data and the pre-processed post-operative nursing responsibility data to obtain a health consultation data embedding coding vector, a clinical test data embedding coding vector, an acute physiological and chronic health score data embedding coding vector, a surgery data embedding coding vector and a post-operative nursing responsibility data embedding coding vector; The nursing big data global context encoding unit is used to arrange the health consultation data embedded coding vector, the clinical test data embedded coding vector, the acute physiological chronic health score data embedded coding vector, the surgery data embedded coding vector and the postoperative nursing responsibility data embedded coding vector into a sequence of coding vectors and input them into a global data context encoder based on a Transformer structure to obtain the context health consultation data semantic coding vector, the context clinical test data semantic coding vector, the context acute physiological chronic health score data semantic coding vector, the context surgery data semantic coding vector and the context postoperative nursing responsibility data semantic coding vector.

3. The obstetrics and gynecology postoperative care data analysis system based on big data according to claim 2, It is characterized in that The nursing big data semantic information transmission and aggregation module includes: a neighborhood-aware optimization unit, configured to perform neighborhood-aware optimization on the sth semantic coding vector among the contextual health consultation data semantic coding vector, the contextual clinical test data semantic coding vector, the contextual acute physiology and chronic health score data semantic coding vector, the contextual surgery data semantic coding vector, and the contextual postoperative care responsibility data semantic coding vector to obtain an sth weighted optimized semantic coding vector; A position-based summing unit is used to calculate the position-based sum of the semantic coding vectors of the contextual health consultation data, the contextual clinical test data, the contextual acute physiological chronic health score data, the contextual surgery data, and the contextual postoperative care responsibility data except the sth semantic coding vector to obtain other semantic fusion representation vectors; A summing perception unit, used for summing the other semantic fusion representation vectors and the s-th weighted optimized semantic coding vector by position and then processing the sum by a multi-layer perceptron to obtain a reinforced semantic coding vector corresponding to the s-th semantic coding vector; The aggregation analysis unit is used to perform a time-domain aggregation analysis of the patient object's full-time physiological state on the enhanced semantic coding vectors corresponding to each of the semantic coding vectors in the context health consultation data semantic coding vector, the context clinical test data semantic coding vector, the context acute physiological chronic health score data semantic coding vector, the context surgery data semantic coding vector, and the context postoperative care responsibility data semantic coding vector to obtain a time-domain aggregation representation vector of the patient object's full-time physiological state.

4. The obstetrics and gynecology postoperative care data analysis system based on big data according to claim 3, It is characterized in that The neighborhood awareness optimization unit is used to: The sum of the trainable preset hyperparameter and one is used as the weighting coefficient to weight the positional feature values ​​of the sth semantic coding vector among the contextual health consultation data semantic coding vector, the contextual clinical examination data semantic coding vector, the contextual acute physiology and chronic health score data semantic coding vector, the contextual surgery data semantic coding vector and the contextual postoperative care responsibility data semantic coding vector to obtain the sth weighted optimized semantic coding vector.

5. According to the big data-based obstetrics and gynecology postoperative care data analysis system of claim 4, It is characterized in that The aggregation analysis unit is used for: The enhanced semantic coding vectors corresponding to each semantic coding vector in the context health consultation data semantic coding vector, the context clinical examination data semantic coding vector, the context acute physiological chronic health score data semantic coding vector, the context surgery data semantic coding vector and the context postoperative care responsibility data semantic coding vector are cascaded to obtain the time-domain aggregated representation vector of the patient object's full-time-domain physiological state.

6. The obstetrics and gynecology postoperative care data analysis system based on big data according to claim 5, It is characterized in that The postoperative recovery assessment module is used to: The time-domain aggregated representation vector of the full-time-domain physiological state of the patient object is passed through a postoperative recovery evaluator based on a classifier to obtain an evaluation result, and the evaluation result is used to represent a postoperative recovery grade label.

7. The big data-based obstetrics and gynecology postoperative care data analysis system according to claim 6, It is characterized in that It also includes a training module for training the Transformer-based global data context encoder, the information transfer aggregation analysis network, and the classifier-based postoperative recovery evaluator.

8. The big data-based obstetrics and gynecology postoperative care data analysis system according to claim 7, It is characterized in that The training module comprises: A training data acquisition unit, used to obtain training data, wherein the training data includes training big data related to obstetrics and gynecology postoperative care of training patient subjects and real evaluation results, wherein the training big data related to obstetrics and gynecology postoperative care includes training health consultation data, training clinical test data, training acute physiological chronic health score data, training surgery data and postoperative care responsibility data; A training data preprocessing unit, used for preprocessing the training big data related to the obstetrics and gynecology postoperative care to obtain preprocessed training health consultation data, preprocessed training clinical test data, preprocessed training acute physiological chronic health score data, preprocessed training surgery data and preprocessed training postoperative care responsibility data; A training nursing big data embedding semantic analysis unit is used to respectively perform vector embedding coding on the pre-processed training health consultation data, the pre-processed training clinical detection data, the pre-processed training acute physiological chronic health scoring data, the pre-processed training surgery data and the pre-processed training post-operative nursing responsibility data to obtain a training health consultation data embedding coding vector, a training clinical detection data embedding coding vector, a training acute physiological chronic health scoring data embedding coding vector, a training surgery data embedding coding vector and a training post-operative nursing responsibility data embedding coding vector; A training nursing big data global context encoding unit is used to arrange the training health consultation data embedding encoding vector, the training clinical test data embedding encoding vector, the training acute physiological chronic health score data embedding encoding vector, the training surgery data embedding encoding vector and the training postoperative nursing responsibility data embedding encoding vector into a sequence of encoding vectors and input them into the Transformer-structured global data context encoder to obtain a training context health consultation data semantic encoding vector, a training context clinical test data semantic encoding vector, a training context acute physiological chronic health score data semantic encoding vector, a training context surgery data semantic encoding vector and a training context postoperative nursing responsibility data semantic encoding vector; A training nursing big data semantic information transmission aggregation unit is used to input the training context health consultation data semantic coding vector, the training context clinical test data semantic coding vector, the training context acute physiological chronic health score data semantic coding vector, the training context surgery data semantic coding vector and the training context postoperative nursing responsibility data semantic coding vector into the information transmission aggregation analysis network to obtain a time-domain aggregation representation vector of the full-time-domain physiological state of the training patient object; A training postoperative recovery assessment unit, used for passing the time-domain aggregated representation vector of the full-time-domain physiological state of the training patient object through the classifier-based postoperative recovery assessor to obtain a training assessment result; A training classification loss function value calculation unit, used to calculate the cross entropy loss function value between the training evaluation result and the true evaluation result to obtain a classification loss function value; A loss training unit is used to train the Transformer-based global data context encoder, the information transfer aggregation analysis network and the classifier-based postoperative recovery evaluator based on the classification loss function value.

9. A data analysis method for postoperative nursing care in obstetrics and gynecology based on big data. It is characterized in that include: Obtaining big data related to postoperative care of patients in obstetrics and gynecology, wherein the big data related to postoperative care of patients in obstetrics and gynecology includes health consultation data, clinical test data, acute physiological and chronic health score data, operation data and postoperative care responsibility data; Preprocessing the big data related to postoperative care in obstetrics and gynecology to obtain post-processing health consultation data, post-processing clinical test data, post-processing acute physiological and chronic health score data, post-processing surgery data, and post-processing postoperative care responsibility data; Performing global data context association analysis based on embedded coding and context coding on the pre-processed health consultation data, the pre-processed clinical test data, the pre-processed acute physiological and chronic health score data, the pre-processed surgery data, and the pre-processed post-operative nursing responsibility data to obtain a contextual health consultation data semantic coding vector, a contextual clinical test data semantic coding vector, a contextual acute physiological and chronic health score data semantic coding vector, a contextual surgery data semantic coding vector, and a contextual post-operative nursing responsibility data semantic coding vector; Inputting the contextual health consultation data semantic encoding vector, the contextual clinical test data semantic encoding vector, the contextual acute physiological chronic health score data semantic encoding vector, the contextual surgery data semantic encoding vector and the contextual postoperative care responsibility data semantic encoding vector into an information transfer aggregation analysis network to obtain a time-domain aggregation representation vector of the patient object's full-time-domain physiological state; Based on the time-domain aggregated representation vector of the full-time-domain physiological state of the patient object, a postoperative recovery level label is determined.

10. The method for analyzing obstetrics and gynecology postoperative nursing data based on big data according to claim 9, It is characterized in that The pre-processed health consultation data, the pre-processed clinical test data, the pre-processed acute physiological and chronic health score data, the pre-processed surgery data and the pre-processed post-operative nursing responsibility data are subjected to global data context association analysis based on embedded coding and context coding to obtain a context health consultation data semantic coding vector, a context clinical test data semantic coding vector, a context acute physiological and chronic health score data semantic coding vector, a context surgery data semantic coding vector and a context post-operative nursing responsibility data semantic coding vector, including: Performing vector embedding coding on the pre-processed health consultation data, the pre-processed clinical test data, the pre-processed acute physiological and chronic health score data, the pre-processed surgical data, and the pre-processed post-operative nursing responsibility data respectively to obtain a health consultation data embedding coding vector, a clinical test data embedding coding vector, an acute physiological and chronic health score data embedding coding vector, a surgical data embedding coding vector, and a post-operative nursing responsibility data embedding coding vector; The health consultation data embedding coding vector, the clinical test data embedding coding vector, the acute physiological chronic health score data embedding coding vector, the surgical data embedding coding vector and the postoperative care responsibility data embedding coding vector are arranged as a sequence of coding vectors and input into a global data context encoder based on a Transformer structure to obtain the context health consultation data semantic coding vector, the context clinical test data semantic coding vector, the context acute physiological chronic health score data semantic coding vector, the context surgical data semantic coding vector and the context postoperative care responsibility data semantic coding vector.

Citation Information

Patent Citations

  • Continuous dynamic network representation learning method based on time sequence diagram Transform

    CN114118375A

  • Intelligent auxiliary system and method for rehabilitation nursing

    CN117556220A

  • Informatization management system and method for patient safety nursing

    CN117637153A

  • Intelligent mental health evaluation system and method based on text sentiment analysis

    CN117789971A

  • Systems and methods to predict and manage post-surgical recovery

    US20230181121A1