An intelligent management system and method for follow-up nursing information

Abstract

This application relates to the field of data compression technology, specifically to an intelligent management system and method for follow-up nursing information. The solution includes: obtaining health characteristic data of each follow-up visit of a postoperative patient; based on the positive and negative words in the health characteristic data of each follow-up visit, combined with the negative words of different health characteristic data, obtaining a fluctuation index of the health characteristic data of each follow-up visit; based on the frequency of occurrence of all negative words between different health characteristic data of each follow-up visit, combined with the fluctuation index of various health characteristic data of previous follow-ups, obtaining the change factor of various health characteristic data of each follow-up visit, compressing all types of health characteristic data of each follow-up visit, and obtaining the final follow-up data of the postoperative patient. This application aims to adaptively compress follow-up data based on the specific situation and treatment needs of the patient, ensuring the accuracy and effectiveness of the follow-up data.

Description

Technical Field

[0001] The present application relates to the technical field of data compression, and in particular to an intelligent management system and method for follow-up nursing information. Background Art

[0002] With the increasing global aging population and the continued rise in the incidence of chronic non-communicable diseases, the focus of healthcare services is gradually shifting from simple treatment to prevention, management, and rehabilitation. Postoperative follow-up care, as a key link between in-hospital treatment and out-of-hospital rehabilitation, is crucial for stabilizing patients' conditions, improving rehabilitation outcomes, preventing complications, and rationally utilizing medical resources. Regular follow-up visits allow medical staff to promptly monitor patients' recovery progress, adjust treatment plans, and provide necessary health guidance, thereby improving patients' quality of life and reducing the risk of readmission.

[0003] However, postoperative follow-up data from patients often contains a large amount of information, requiring effective data compression to reduce storage and transmission costs. To achieve optimal compression, lossy compression techniques may be required, which can compromise the detail and accuracy of the data. Existing technologies fail to select the optimal compression method based on the patient's specific condition and treatment needs, resulting in the loss of critical information in the compressed follow-up data, impacting the accuracy and effectiveness of treatment decisions. Summary of the Invention

[0004] In view of the above, it is necessary to provide an intelligent management system and method for follow-up nursing information to solve the above problems.

[0005] The first aspect of the present application provides a method for intelligent management of follow-up nursing information, the method comprising:

[0006] Obtain various health characteristic data of postoperative patients at each follow-up visit;

[0007] Obtaining positive and negative words in the various health characteristic data at each follow-up; based on the differences in the distribution of positive and negative words in the various health characteristic data at each follow-up, combined with the differences in the distribution of negative words in the different health characteristic data at each follow-up, obtaining the fluctuation index of the various health characteristic data at each follow-up;

[0008] Based on the similarity of the frequency of all negative words between different health characteristic data at each follow-up, combined with the changing trend of the fluctuation index of various health characteristic data at each follow-up and all previous follow-ups, the change factor of various health characteristic data at each follow-up was obtained;

[0009] Based on the compression level of the compression algorithm and the variation factor, all kinds of health characteristic data of each follow-up are compressed to obtain the final follow-up data of the postoperative patient.

[0010] The process of obtaining the positive and negative words in the various health characteristic data during each follow-up is as follows:

[0011] A Chinese word segmentation algorithm is used to segment various health characteristic data, and the segmentation results are matched with a positive word library and a negative word library respectively to obtain a number of positive words and a number of negative words for various health characteristic data.

[0012] The Chinese word segmentation algorithm adopts a forward maximum matching algorithm.

[0013] The fluctuation index of various health characteristic data obtained during each follow-up visit is specifically:

[0014] Compare the frequencies of positive and negative words in various health characteristic data of various patients at each follow-up visit to obtain comparative status values ​​of various health characteristic data;

[0015] Based on the difference in the frequency distribution of negative words in the various health characteristic data of each follow-up and all other health characteristic data, the negative state difference value of the various health characteristic data of each follow-up is obtained;

[0016] The comparison state value and the negative state difference value are fused to obtain the fluctuation index of various health characteristic data in each follow-up.

[0017] The comparison status values ​​of various health characteristic data are obtained, including:

[0018] Calculate the average frequency of all positive words in various health data at each follow-up to obtain the positive frequency of various health characteristic data; calculate the average frequency of all negative words in various health data at each follow-up to obtain the negative frequency of various health characteristic data;

[0019] According to the negative frequencies and positive frequencies of various health characteristic data, comparative state values ​​of various health characteristic data are obtained; wherein the comparative state values ​​are positively correlated with the negative frequencies and negatively correlated with the positive frequencies.

[0020] The negative state difference values ​​of various health characteristic data obtained during each follow-up visit include:

[0021] The difference in negative frequency between the health characteristic data of each follow-up is calculated and recorded as the characteristic difference; the average level of the characteristic difference between various health characteristic data and all other health characteristic data is calculated to obtain the negative state difference value.

[0022] The change factors of various health characteristic data obtained during each follow-up are specifically:

[0023] The occurrence frequencies of all negative words in various health characteristic data of each follow-up are combined into a feature sequence;

[0024] The fluctuation index of various health characteristic data at each follow-up and all previous follow-ups is used to form a health fluctuation sequence;

[0025] Obtaining a trend index for the various health characteristic data at each follow-up visit based on the similarity between the characteristic sequence of the various health characteristic data at each follow-up visit and all previous follow-ups, combined with the changing trend of the health fluctuation sequence;

[0026] According to the degree of dispersion of the health fluctuation sequence, the change characteristic values ​​of various health characteristic data of each follow-up are obtained;

[0027] The trend index and change characteristic value of various health characteristic data at each follow-up are integrated to obtain the change factor of various health characteristic data at each follow-up.

[0028] The trend index of various health characteristic data of each follow-up is obtained as follows: the trend index of the i-th health characteristic data of the x-th follow-up is recorded as , its formula form is: ;in, is the cosine similarity function, 、 They represent the characteristic sequences of the i-th health characteristic data at the x-th follow-up and the k-th follow-up respectively; x represents the number of follow-up visits; represents the slope of the health fluctuation series fitting line of the i-th health characteristic data at the x-th follow-up, Indicates that the adjustment parameter is preset to be greater than zero.

[0029] The final follow-up data of the postoperative patient include:

[0030] The rounded-up value of the product of the normalized value of the change factor of various health characteristic data in each follow-up and the highest level of the compression algorithm is used as the compression level of the corresponding health characteristic data;

[0031] The ZSTD compression algorithm is used to compress various health characteristic data of each follow-up at the corresponding compression level to obtain the final follow-up data of the postoperative patients.

[0032] In a second aspect, the present application also provides an intelligent management system for follow-up nursing information, including:

[0033] Health characteristic data collection module, used to obtain various health characteristic data of postoperative patients at each follow-up visit;

[0034] The health characteristic data analysis module is used to obtain positive and negative words in various health characteristic data at each follow-up; based on the differences in the distribution of positive and negative words in various health characteristic data at each follow-up, combined with the differences in the distribution of negative words in different health characteristic data at each follow-up, the fluctuation index of various health characteristic data at each follow-up is obtained; based on the similar characteristics of the occurrence frequency of all negative words between different types of health characteristic data at each follow-up, combined with the changing trends of the fluctuation index of various health characteristic data at each follow-up and all previous follow-ups, the change factor of various health characteristic data at each follow-up is obtained;

[0035] The health characteristic data processing module is used to compress all types of health characteristic data of each follow-up based on the compression level of the compression algorithm and the change factor to obtain the final follow-up data of the postoperative patient.

[0036] In the above scheme, various health characteristic data of each follow-up of the postoperative patient are obtained to provide a data basis for analyzing the patient's physical health status by recording and analyzing the follow-up data; obtaining positive and negative words in the health characteristic data is helpful to analyze the patient's recent physical condition with the help of the literal reflection of the physical health status when the patient's health characteristic data is collected; based on the distribution difference of positive and negative words in the health characteristic data, the patient's emotions towards the health status in that aspect are measured, and then based on the difference in the distribution of negative words in different health characteristic data in the same follow-up, it is judged whether the patient has obvious emotional characteristic fluctuations for only one aspect of the health status, and further obtain the fluctuation index to comprehensively reflect the patient's emotions towards one health characteristic data after surgery. According to the fluctuation trend of the health characteristic data, the possibility of the instability of the patient's health status in this aspect is measured; according to the similar characteristics of the frequency of occurrence of negative words between different types of health characteristic data, the similarities and differences between the patient's health status in one aspect and the health status in other aspects are more accurately measured; combined with the changing trend of the fluctuation index of the health characteristic data of each follow-up and all previous follow-ups, the change factor of the health characteristic data is obtained, indicating that the patient's health status in one aspect is unstable; based on the change factor, the compression algorithm dynamically adjusts the compression level, which has the beneficial effect of selecting the best compression method according to the patient's specific situation and treatment needs, and reasonably compressing the follow-up data while ensuring the integrity and accuracy of the follow-up data, thereby optimizing storage space and transmission efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A flowchart of the steps of an intelligent management method for follow-up nursing information provided in this application;

[0038] Figure 2 Schematic diagram of the process for obtaining the variation factor provided in this application;

[0039] Figure 3This is a block diagram of an intelligent management system for follow-up nursing information provided in this application. DETAILED DESCRIPTION

[0040] In the description of the embodiments of this application, words such as "exemplary," "or," and "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary," "or," and "for example" is intended to present the relevant concepts in a concrete manner.

[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the art of this application. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0042] It should also be noted that the terms "first" and "second" in this application and the accompanying drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. The methods disclosed in the embodiments of this application or the methods shown in the flowcharts include one or more steps for implementing the methods. Without departing from the scope of this application, the order of executing multiple steps can be interchanged with each other, and some steps can also be deleted.

[0043] See also Figure 1 , which shows a flowchart of a method for intelligent management of follow-up nursing information provided by one embodiment of the present application, the method comprising the following steps:

[0044] Step 1: Obtain various health characteristic data of postoperative patients at each follow-up visit.

[0045] When processing the follow-up data of postoperative patients, the accuracy and efficiency of data compression often face a dilemma that cannot be achieved at the same time. Since the specific conditions of each patient are different, such as liver function, kidney function, cardiopulmonary condition, etc., these factors may affect the choice of data compression. For example, for patients with poor physical recovery, more detailed data records are needed to accurately assess their condition and treatment effects. A high compression ratio can save storage space, but it may take longer to process the data. On the contrary, although fast compression can improve data processing efficiency, it may sacrifice some data quality. Based on this, this application analyzes the follow-up data of postoperative patients:

[0046] Patients who have undergone surgery were selected as follow-up subjects, and guidance on medication and diet was provided to the patients who had undergone surgery. The patients and their families were informed of the high-risk factors after surgery, and postoperative follow-up was conducted. The frequency of postoperative follow-up can be as follows: 7 online follow-ups, once every two weeks within the first month after discharge, once a month within the second to third months, and once every three months thereafter. The patients were also instructed to return to the hospital for reexamination at 1, 3, 6, and 12 months after discharge.

[0047] Each follow-up visit includes the patient completing an electronic physical status questionnaire, which covers medication, diet, sleep, and bowel movements, as well as electronic health characteristic data from the Chronic Disease Medication Adherence Scale, Self-Management Ability, Pittsburgh Sleep Quality, and Quality of Life Scale. It should be understood that since each form represents a specific health status, the patient's responses to each form can be considered as the patient's characteristic data in that specific health aspect, referred to as health characteristic data.

[0048] A database was established based on each form. Since the Chronic Disease Medication Compliance Scale, Self-Management Ability Scale, Pittsburgh Sleep Quality Scale, and Quality of Life Scale contained structured choice questions, corresponding fields were set for each form's choice questions to store the patient's selected answers. When the patient submitted the questionnaire, only the selected option identifier was sent. When collecting health characteristic data, only the fields corresponding to the option identifier were extracted from the database, and unselected options were ignored.

[0049] Step 2: Obtain positive and negative words in the various health characteristic data at each follow-up; based on the differences in the distribution of positive and negative words in the various health characteristic data at each follow-up, combined with the differences in the distribution of negative words in different health characteristic data at each follow-up, obtain the fluctuation index of the various health characteristic data at each follow-up.

[0050] During the analysis of various health characteristic data from each follow-up visit, negative and positive words in the patient's health characteristic data can reflect the patient's subjective feelings about their emotional and physical state. The frequent occurrence of negative words may indicate that the patient is experiencing more stress or discomfort, which may affect their health behaviors and treatment compliance. Therefore, when there are more negative words, the medical team should pay more attention to the accuracy and depth of data collection. When compressing data, they should pay attention to retaining key information and details to ensure that even when the amount of data is reduced, the patient's emotional state and health indicators can still be accurately captured and analyzed.

[0051] As an embodiment, for various health characteristic data of the same patient in each follow-up, the text data of the various health characteristic data are used as input, and word segmentation processing is performed using the forward maximum matching algorithm. The word segmentation results of the various health characteristic data are output, and the word segmentation results are matched with the positive vocabulary and the negative vocabulary respectively to obtain several positive words and several negative words for the various health characteristic data.

[0052] Among them, the positive word library and the negative word library can be obtained from open source websites; the forward maximum matching algorithm and the acquisition of the word library are well-known technologies and will not be described in detail in this application.

[0053] For various health characteristic data of each follow-up, the occurrence frequency of each positive word is counted, and the average occurrence frequency of all positive words in various health data of each follow-up is calculated to obtain the positive frequency of various health characteristic data; the occurrence frequency of each negative word is counted, and the average occurrence frequency of all negative words in various health data of each follow-up is calculated to obtain the negative frequency of various health characteristic data; based on the negative frequency and positive frequency of various health characteristic data, the comparative state value of various health characteristic data is obtained; wherein, the comparative state value is positively correlated with the negative frequency and negatively correlated with the positive frequency; the difference in negative frequency between the health characteristic data of each follow-up is calculated and recorded as the characteristic difference; the average level of the characteristic difference between various health characteristic data and all other types of health characteristic data is calculated to obtain the negative state difference value.

[0054] As an embodiment, the comparative status value of various health characteristic data refers to the ratio of the negative frequency to the positive frequency of various health characteristic data; the characteristic difference is specifically the absolute value of the difference in negative frequency between two types of health characteristic data in each follow-up; the average value of the characteristic difference between various health characteristic data and all other types of health characteristic data is calculated to obtain the negative status difference value.

[0055] It should be understood that the increase in the contrast state value reflects that the patient's negative emotions are stronger than their positive emotions in each follow-up, which is used to evaluate the patient's postoperative recovery status in a certain aspect between each follow-up and the previous follow-up; a larger contrast state value means that the patient has more negative emotional influences in postoperative recovery; the negative state difference value indicates the difference in the patient's negative emotions expressed in words in this health characteristic data relative to other health characteristic data between each follow-up and the previous follow-up.

[0056] The comparative state values ​​and negative state difference values ​​of various health characteristic data at each follow-up are fused to obtain the fluctuation index of various health characteristic data at each follow-up.

[0057] As an embodiment, the variables are fused by multiplication, that is, the fluctuation index is specifically the product of the fluctuation index and the comparison state value; in other embodiments, the product can be replaced by a sum value.

[0058] It should be understood that the larger the contrast state value, the more negative emotions are contained in the text of the patient's health characteristic data in the corresponding aspect after surgery, the worse the patient's health status in this aspect, and the greater the possibility of unstable health status, that is, the larger the fluctuation index; the larger the negative state difference value, it indicates that the patient only has obvious emotional characteristic fluctuations in this aspect of health status, and the larger the fluctuation index.

[0059] Step 3: Based on the similar characteristics of the frequency of occurrence of all negative words between different types of health characteristic data at each follow-up, combined with the changing trends of the fluctuation index of various health characteristic data at each follow-up and all previous follow-ups, the change factors of various health characteristic data at each follow-up are obtained.

[0060] Postoperative follow-up health characteristic data from patients can help healthcare professionals more comprehensively assess and understand a patient's physical recovery from surgery to follow-up. This data is crucial for evaluating the effectiveness of treatment and adjusting subsequent care plans. When performing lossy compression, a balance must be struck between compression efficiency and data integrity. Overly aggressive compression algorithms can result in the loss of certain details in the recovery indicator data, affecting the accurate assessment of the patient's recovery stability. For example, if key recovery data points are mistakenly discarded or altered during the compression process, this can lead to a misunderstanding of the patient's recovery trend. On the other hand, insufficient compression efficiency can increase data storage and transmission costs, impacting the sustainability of the follow-up system.

[0061] The frequencies of occurrence of all negative words in various health characteristic data of each follow-up are combined into a characteristic sequence; the fluctuation indexes of various health characteristic data of each follow-up and all previous follow-ups are combined into a health fluctuation sequence; based on the average level of similarity between the characteristic sequences of various health characteristic data of each follow-up and all previous follow-ups, combined with the changing trend of the health fluctuation sequence, the trend index of various health characteristic data of each follow-up is obtained; based on the degree of dispersion of the health fluctuation sequence, the changing characteristic value of various health characteristic data of each follow-up is obtained.

[0062] As an embodiment, for each follow-up of a patient, taking the xth follow-up as an example, the frequencies of occurrence of all negative words in the i-th health characteristic data of the xth follow-up are arranged in descending order to form a characteristic sequence of the i-th health characteristic data of the xth follow-up; the fluctuation index of the i-th health characteristic data of the xth follow-up and the previous x-1 follow-ups is used to form a health fluctuation sequence of the i-th health characteristic data of the xth follow-up, and a linear fitting is performed using the least squares method; the formula for the trend index of the i-th health characteristic data of the xth follow-up is: ; Among them, the trend index of the i-th health characteristic data at the x-th follow-up is recorded as , is the cosine similarity function, 、 They represent the characteristic sequences of the i-th health characteristic data at the x-th follow-up and the k-th follow-up respectively; x represents the number of follow-up visits; It represents the slope of the fitted straight line of the health fluctuation series of the i-th health characteristic data at the x-th follow-up; Indicates an adjustment parameter that is preset to be greater than zero, with a value of 0.01, which can be adjusted by the implementer.

[0063] Furthermore, the product of the standard deviation and the range value of the health fluctuation sequence of the i-th health characteristic data at the x-th follow-up is calculated to obtain the trend change index of the i-th health characteristic data at the x-th follow-up; in other embodiments, the standard deviation of the health fluctuation sequence can be used as the trend change index of the corresponding health characteristic data; in some other embodiments, the range value of the health fluctuation sequence can be used as the trend change index of the corresponding health characteristic data.

[0064] The product of the trend index of various health characteristic data at each follow-up and the change characteristic value is used as the change factor of various health characteristic data at each follow-up.

[0065] Among them, the schematic diagram of the process of obtaining the change factor is as follows: Figure 2 shown.

[0066] It should be understood that the smaller the similarity between the feature sequences and the stronger the trend of the health fluctuation sequence, the more obvious the trend of the patient's health status during the continuous follow-up after surgery, and the larger the trend index; the larger the standard deviation and range of the health fluctuation sequence, the more volatile the trend of the patient's physical health status during the continuous follow-up after surgery, the larger the trend change index, and the greater the instability of the patient's physical health status; the larger the change factor means that the patient's health recovery status in the corresponding aspect of the health feature data needs closer attention.

[0067] Step 4: Based on the compression level of the compression algorithm and the variation factor, all health characteristic data of each follow-up are compressed to obtain the final follow-up data of the postoperative patient.

[0068] For each follow-up, taking the x-th follow-up as an example, all follow-up content types in the x-th follow-up are used as input and compressed using the Zstandard (ZSTD) compression algorithm. The ZSTD compression algorithm provides multiple compression levels, among which the lowest level provides the fastest compression speed, and the highest level provides the highest compression ratio.

[0069] Based on the compression level of the compression algorithm and the change factor, the compression level of various health characteristic data in each follow-up is obtained: the upward rounded value of the product of the normalized value of the change factor of various health characteristic data in each follow-up and the highest level of the compression algorithm is used as the compression level of the corresponding health characteristic data.

[0070] As an embodiment, the compression level of the ZSTD compression algorithm is obtained according to the change factor of the i-th health characteristic data in the x-th follow-up. The specific formula is: ;in is the compression level of the i-th health characteristic data in the x-th follow-up, is the change factor of the i-th health characteristic data in the x-th follow-up, The highest compression level of the ZSTD compression algorithm. is the ceiling function.

[0071] By mapping the variation factor to When the change factor is larger, the normalized result is closer to 1, and the changes in the patient's corresponding health data are more irregular. At this time, when compressing the data, it is necessary to retain the original data as much as possible, and a smaller compression level should be used, with a faster compression rate and decompression rate; if the change factor is smaller, the normalized result is smaller, which means that the changes in the patient's corresponding health data are regular and relatively stable. At this time, the maximum compression ratio can be used to reduce its occupancy rate of storage space to ensure the accuracy of the patient's follow-up data, and vice versa.

[0072] The improved ZSTD algorithm is used to compress various health characteristic data of each follow-up. Appropriate storage media, such as SSD, hard disk or cloud storage, are selected to store the compressed patient follow-up data and back them up regularly to complete the follow-up of postoperative patients.

[0073] Based on the same inventive concept as the above method, the embodiment of the present application also provides an intelligent management system for follow-up nursing information, comprising:

[0074] Health characteristic data collection module, used to obtain various health characteristic data of postoperative patients at each follow-up visit;

[0075] The health characteristic data analysis module is used to obtain positive and negative words in various health characteristic data at each follow-up; based on the differences in the distribution of positive and negative words in various health characteristic data at each follow-up, combined with the differences in the distribution of negative words in different health characteristic data at each follow-up, the fluctuation index of various health characteristic data at each follow-up is obtained; based on the similar characteristics of the occurrence frequency of all negative words between different types of health characteristic data at each follow-up, combined with the changing trends of the fluctuation index of various health characteristic data at each follow-up and all previous follow-ups, the change factor of various health characteristic data at each follow-up is obtained;

[0076] The health characteristic data processing module is used to compress all types of health characteristic data of each follow-up based on the compression level of the compression algorithm and the change factor to obtain the final follow-up data of the postoperative patient.

[0077] Among them, a block diagram of an intelligent management system for follow-up nursing information, such as Figure 3 shown.

[0078] In summary, the embodiment of the present application obtains various health characteristic data of each follow-up of the postoperative patient, and provides a data basis for analyzing the patient's physical health status by recording and analyzing the follow-up data; obtaining positive and negative words in the health characteristic data is helpful to analyze the patient's recent physical condition with the help of the literal reflection of the physical health status when the patient's health characteristic data is collected; based on the distribution difference of positive and negative words in the health characteristic data, the patient's emotions towards this aspect of health status are measured, and then based on the difference in the distribution of negative words in different health characteristic data in the same follow-up, it is judged whether the patient has obvious emotional characteristic fluctuations for only one aspect of health status, and further obtains the fluctuation index to comprehensively reflect the patient's emotional fluctuations towards one aspect of health status after surgery. The fluctuation trend of health characteristic data can be used to measure the possibility of instability of the patient's health status in this aspect; based on the similar characteristics of the frequency of occurrence of negative words between different types of health characteristic data, the similarities and differences between the patient's health status in one aspect and the health status in other aspects can be more accurately measured; combined with the changing trend of the fluctuation index of the health characteristic data of each follow-up and all previous follow-ups, the change factor of the health characteristic data is obtained, indicating that the patient's health status in one aspect is unstable; based on the change factor, the compression algorithm dynamically adjusts the compression level, and its beneficial effect is to select the best compression method according to the patient's specific situation and treatment needs, ensure the accuracy and effectiveness of the follow-up data, reasonably compress the follow-up data, and optimize the storage space and transmission efficiency.

[0079] It should be noted that the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the systems, methods and computer program products according to the embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment or part of the code, and the module, program segment or part of the code contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, or they can sometimes be executed in the opposite order, which can depend on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in an order different from that disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, or they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified function or action, or may be implemented by a combination of dedicated hardware and computer instructions.

[0080] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for intelligent management of follow-up nursing information, characterized in that: The method comprises the following steps: Obtain various health characteristic data of postoperative patients at each follow-up visit; Obtaining positive and negative words in the various health characteristic data at each follow-up; based on the differences in the distribution of positive and negative words in the various health characteristic data at each follow-up, combined with the differences in the distribution of negative words in the different health characteristic data at each follow-up, obtaining the fluctuation index of the various health characteristic data at each follow-up; Based on the similarity of the frequency of all negative words between different health characteristic data at each follow-up, combined with the changing trend of the fluctuation index of various health characteristic data at each follow-up and all previous follow-ups, the change factor of various health characteristic data at each follow-up was obtained; Based on the compression level of the compression algorithm and the variation factor, compressing all health characteristic data of each follow-up to obtain the final follow-up data of the postoperative patient; The change factors of various health characteristic data obtained during each follow-up are specifically: The occurrence frequencies of all negative words in various health characteristic data of each follow-up are combined into a feature sequence; The fluctuation index of various health characteristic data at each follow-up and all previous follow-ups is used to form a health fluctuation sequence; Obtaining a trend index for the various health characteristic data at each follow-up visit based on the similarity between the characteristic sequence of the various health characteristic data at each follow-up visit and all previous follow-ups, combined with the changing trend of the health fluctuation sequence; According to the degree of dispersion of the health fluctuation sequence, the change characteristic values ​​of various health characteristic data of each follow-up are obtained; The trend index and change characteristic value of various health characteristic data of each follow-up are integrated to obtain the change factor of various health characteristic data of each follow-up; The trend index of various health characteristic data of each follow-up is obtained as follows: the trend index of the i-th health characteristic data of the x-th follow-up is recorded as , its formula form is: ;in, is the cosine similarity function, 、 They represent the characteristic sequences of the i-th health characteristic data at the x-th follow-up and the k-th follow-up respectively; x represents the number of follow-up visits; represents the slope of the health fluctuation series fitting line of the i-th health characteristic data at the x-th follow-up, Indicates that the adjustment parameter is preset to be greater than zero.

2. The intelligent management method for follow-up nursing information according to claim 1, characterized in that: The process of obtaining the positive and negative words in the various health characteristic data during each follow-up is as follows: A Chinese word segmentation algorithm is used to segment various health characteristic data, and the segmentation results are matched with a positive word library and a negative word library respectively to obtain a number of positive words and a number of negative words for various health characteristic data.

3. The intelligent management method for follow-up nursing information according to claim 2, characterized in that: The Chinese word segmentation algorithm adopts a forward maximum matching algorithm.

4. The intelligent management method for follow-up nursing information according to claim 1, characterized in that: The fluctuation index of various health characteristic data obtained at each follow-up is specifically: Compare the frequencies of positive and negative words in various health characteristic data of various patients at each follow-up visit to obtain comparative status values ​​of various health characteristic data; Based on the difference in the frequency distribution of negative words in the various health characteristic data of each follow-up and all other health characteristic data, the negative state difference value of the various health characteristic data of each follow-up is obtained; The comparison state value and the negative state difference value are fused to obtain the fluctuation index of various health characteristic data in each follow-up.

5. The intelligent management method for follow-up nursing information according to claim 4, characterized in that: The comparison status values ​​of various health characteristic data are obtained, including: Calculate the average frequency of all positive words in various health data at each follow-up to obtain the positive frequency of various health characteristic data; calculate the average frequency of all negative words in various health data at each follow-up to obtain the negative frequency of various health characteristic data; According to the negative frequencies and positive frequencies of various health characteristic data, comparative state values ​​of various health characteristic data are obtained; wherein the comparative state values ​​are positively correlated with the negative frequencies and negatively correlated with the positive frequencies.

6. The intelligent management method for follow-up nursing information according to claim 5, characterized in that: The negative state difference values ​​of various health characteristic data obtained at each follow-up visit include: The difference in negative frequency between the health characteristic data of each follow-up is calculated and recorded as the characteristic difference; the average level of the characteristic difference between various health characteristic data and all other health characteristic data is calculated to obtain the negative state difference value.

7. The intelligent management method for follow-up nursing information according to claim 1, characterized in that: The final follow-up data of the postoperative patients include: The rounded-up value of the product of the normalized value of the change factor of various health characteristic data in each follow-up and the highest level of the compression algorithm is used as the compression level of the corresponding health characteristic data; The ZSTD compression algorithm is used to compress various health characteristic data of each follow-up at the corresponding compression level to obtain the final follow-up data of the postoperative patients.

8. An intelligent management system for follow-up nursing information, implementing the method according to claim 1, characterized in that: include: Health characteristic data collection module, used to obtain various health characteristic data of postoperative patients at each follow-up visit; The health characteristic data analysis module is used to obtain positive and negative words in various health characteristic data at each follow-up; based on the differences in the distribution of positive and negative words in various health characteristic data at each follow-up, combined with the differences in the distribution of negative words in different health characteristic data at each follow-up, the fluctuation index of various health characteristic data at each follow-up is obtained; based on the similar characteristics of the occurrence frequency of all negative words between different types of health characteristic data at each follow-up, combined with the changing trends of the fluctuation index of various health characteristic data at each follow-up and all previous follow-ups, the change factor of various health characteristic data at each follow-up is obtained; The health characteristic data processing module is used to compress all types of health characteristic data of each follow-up based on the compression level of the compression algorithm and the change factor to obtain the final follow-up data of the postoperative patient.

Images