A nursing data management optimization system for tumor patients

Abstract

A nursing data management optimization system for tumor patients relates to the technical field of data management, and comprises a main control center, wherein the main control center is communicatively connected with a data acquisition module, a data upload module, a damage assessment module, and a flow optimization module; the uploaded data of the tumor patient is obtained, an upload cycle and an upload channel are set, the uploaded data is uploaded and the upload coefficient is recorded, a verification key for the uploaded data is obtained, after the upload is completed, whether there is damaged data is determined according to the verification key, the damaged coefficient of the damaged data is obtained, a damage prediction model is constructed according to the upload coefficient and the damaged coefficient, and the damaged coefficient of subsequent uploaded data is predicted using the damaged prediction model; the flow optimization module is used to obtain the upload channel level of the upload channel, and to optimize the flow of upload channels of different levels; it can effectively predict whether the uploaded data is damaged, and optimize the flow of each upload channel according to the prediction result.

Description

Technical Field

[0001] The invention relates to the technical field of data management, and in particular to a nursing data management optimization system for tumor patients. Background Art

[0002] Nursing data management optimization systems designed for cancer patients usually include the following core functions and features: recording the patient's treatment plan, progress at each stage, drug use and side effects, helping medical staff to understand the patient's treatment status in real time, using data analysis technology to analyze the patient's medical record data, providing a reference for medical decision-making, recording key data and observations during the nursing process, and providing an effective communication and exchange platform between medical staff and patients' families;

[0003] In the prior art, nursing data is usually stored in the cloud. In the process of uploading nursing data to the cloud, the fluctuation of network traffic is likely to cause the nursing data to be damaged. In the prior art, there is a lack of effective means to predict and adjust the damage of the uploaded nursing data according to the fluctuation of network traffic. In view of the shortcomings of the prior art, the present invention provides a nursing data management optimization system for cancer patients. Summary of the invention

[0004] The purpose of the present invention is to provide a nursing data management optimization system for tumor patients.

[0005] The object of the present invention can be achieved by the following technical solutions: A nursing data management optimization system for tumor patients, comprising a main control center, wherein the main control center is communicatively connected with a data acquisition module, a data upload module, a damage assessment module, and a flow optimization module;

[0006] The data acquisition module is used to collect nursing data of tumor patients, divide the collected nursing data and convert it into binary form to obtain corresponding upload data;

[0007] The data upload module is used to set an upload cycle and an upload channel, upload the obtained upload data and record its corresponding upload coefficient, classify the uploaded data according to the obtained upload coefficient, obtain the verification node of the uploaded data, connect the obtained verification node to obtain the corresponding verification key, and after the upload is completed, verify the integrity of the uploaded data according to the obtained verification key to determine whether there is damaged data;

[0008] The damage assessment module is used to obtain the damaged node of the damaged data, obtain the damaged coefficient of the damaged data according to the obtained damaged node, build a corresponding damage prediction model according to the upload coefficient and the damaged coefficient, and use the damage prediction model to predict the damage coefficient of the subsequent uploaded data;

[0009] The traffic optimization module is used to evaluate each upload channel according to the predicted damage coefficient to divide it into different upload channel levels, and perform traffic optimization on upload channels of different levels respectively.

[0010] Furthermore, the process of the data collection module collecting nursing data of tumor patients includes:

[0011] A collection unit is provided to collect nursing data of cancer patients through the collection unit. The nursing data refers to the medical records, treatment plans, drug management, test results, imaging examinations, symptom monitoring, quality of life assessment, and nutritional status of cancer patients.

[0012] Furthermore, the process of the data collection module dividing the collected nursing data and converting it into binary form to obtain corresponding uploaded data includes:

[0013] A processing unit is set up, and the nursing data of a single tumor patient is divided by the processing unit to obtain its corresponding nursing sub-data. The processing unit converts the obtained nursing sub-data from original form to binary form, and marks the binary nursing sub-data as upload data.

[0014] Furthermore, the data uploading module sets an upload cycle and an upload channel, uploads the obtained upload data and records its corresponding upload coefficient, and the process of classifying the uploaded data according to the obtained upload coefficient includes:

[0015] An upload cycle is set, and an upload data packet is obtained when an upload cycle is reached. Several upload channels are set, and the obtained upload data packet is divided into several upload sub-data packets, and the upload sub-data packets are uploaded to the cloud for storage through the constructed upload channels;

[0016] Monitor the delay rate of each upload channel in the data upload process in real time, obtain the data packet size of the upload sub-data packet transmitted by each upload channel, and obtain the upload coefficient of each upload sub-data packet in its upload channel;

[0017] An upload coefficient range is set, the obtained upload coefficients are compared with the upload coefficient range respectively, and the uploaded sub-data packets are divided into a low upload state, a high upload state, and a medium upload state according to the comparison result.

[0018] Furthermore, the data uploading module obtains a verification node of the uploaded data, connects to the obtained verification node to obtain a corresponding verification key, and after the upload is completed, verifies the integrity of the uploaded data according to the obtained verification key to determine whether there is damaged data. The process includes:

[0019] Before uploading data, obtain the verification node of each uploaded sub-data packet in the same upload cycle, wherein the verification node refers to the characters at different fixed digits in each uploaded sub-data packet, and obtain the verification key of each uploaded sub-data packet according to the verification node of the same uploaded sub-data packet;

[0020] After the upload is completed, the verification key of each uploaded sub-data package is obtained after the upload is completed, and it is compared with the verification key before the data is uploaded. According to the comparison result, the uploaded sub-data package is divided into complete data and damaged data.

[0021] Furthermore, the damage assessment module obtains the damaged node of the damaged data, and the process of obtaining the damage coefficient of the damaged data according to the obtained damaged node includes:

[0022] When an uploaded sub-data packet is marked as damaged data, the verification nodes of the damaged data are compared one by one, and the verification nodes with different characters in their verification keys are marked as damaged nodes. The ratio of the total number of damaged nodes to the total number of verification nodes in the uploaded sub-data packet is used as the damage coefficient of the damaged data.

[0023] Furthermore, the damage assessment module constructs a corresponding damage prediction model according to the upload coefficient and the damage coefficient, and the process of using the damage prediction model to predict the damage coefficient of subsequent uploaded data includes:

[0024] Obtain the upload coefficient of damaged data, incorporate the upload coefficient and damage coefficient of each damaged data in different upload cycles into the same damage prediction set, select the deep learning model as the initial damage prediction model, use the obtained damage prediction set to continuously train and evaluate the initial damage prediction model, and obtain the latest damage prediction model;

[0025] The upload coefficients of the subsequent uploaded sub-data packets are obtained and input into the constructed damage prediction model, the corresponding damage coefficients are predicted using the damage prediction model, and the corresponding damage coefficients are output.

[0026] Furthermore, the traffic optimization module evaluates each upload channel according to the predicted impairment coefficient to classify it into different upload channel levels. The process of performing traffic optimization on upload channels of different levels includes:

[0027] Set a damage coefficient range, compare the damage coefficient with the damage coefficient range, and divide the upload channels into low damage level, high damage level, and medium damage level according to the comparison results. Based on the previous upload cycle, optimize the traffic of each upload channel in the current upload cycle, keep the traffic resources of the upload channel with medium damage level unchanged, increase the traffic resources of the upload channel with high damage level, and reduce the traffic resources of the upload channel with low damage level.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] The present invention divides the nursing data of tumor patients and converts it into binary form to obtain corresponding uploaded data, obtains fixed-digit verification nodes in the uploaded data, and obtains corresponding verification keys, and compares the verification keys before and after data uploading. On the one hand, it can determine whether the uploaded data is damaged, and on the other hand, it can obtain the total number of damaged nodes in the damaged data, and then obtain the damage coefficient of each damaged data, and link it with the upload coefficient to construct a damage prediction model. It can output its corresponding damage coefficient according to the upload coefficient of subsequent uploaded data, that is, it can effectively predict whether the subsequent uploaded data is damaged, and then optimize the traffic of each upload channel according to the prediction result, which is conducive to forming a targeted traffic targeting strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0031] like Figure 1 As shown, a nursing data management optimization system for tumor patients includes a main control center, and the main control center is communicatively connected to a data acquisition module, a data upload module, a damage assessment module, and a traffic optimization module;

[0032] The data acquisition module is used to collect nursing data of tumor patients, divide the collected nursing data and convert it into binary form to obtain corresponding upload data;

[0033] The data upload module is used to set an upload cycle and an upload channel, upload the obtained upload data and record its corresponding upload coefficient, classify the uploaded data according to the obtained upload coefficient, obtain the verification node of the uploaded data, connect the obtained verification node to obtain the corresponding verification key, and after the upload is completed, verify the integrity of the uploaded data according to the obtained verification key to determine whether there is damaged data;

[0034] The damage assessment module is used to obtain the damaged node of the damaged data, obtain the damaged coefficient of the damaged data according to the obtained damaged node, build a corresponding damage prediction model according to the upload coefficient and the damaged coefficient, and use the damage prediction model to predict the damage coefficient of the subsequent uploaded data;

[0035] The traffic optimization module is used to evaluate each upload channel according to the predicted damage coefficient to divide it into different upload channel levels, and perform traffic optimization on upload channels of different levels respectively.

[0036] It should be further explained that, in the specific implementation process, the process of the data acquisition module collecting the nursing data of the tumor patient includes:

[0037] Setting a collection unit to collect nursing data of cancer patients through the collection unit, wherein the nursing data refers to the medical records, treatment plans, drug management, test results, imaging examinations, symptom monitoring, quality of life assessment, and nutritional status of cancer patients;

[0038] The medical records include the name, age, gender, weight, height, medical history, etc. of the cancer patient; the treatment plan includes tumor type, chemotherapy regimen, radiotherapy regimen, surgery, etc.; the drug management includes drug name, route and frequency of administration, dosage, etc.; the test results include blood tests, urine tests, etc.; the imaging tests include CT scans, X-rays, ultrasound examinations, etc.; the symptom monitoring includes pain, nausea, vomiting, changes in appetite, changes in weight, etc.; the quality of life assessment includes activity ability, psychological state, social support, etc.; the nutritional status includes weight monitoring, diet records, nutritional assessment, etc.

[0039] It should be further explained that, in the specific implementation process, the process in which the data acquisition module divides the collected nursing data and converts it into binary form to obtain the corresponding upload data includes:

[0040] A processing unit is provided, and the nursing data of a single tumor patient is divided by the processing unit. The division standard is based on the different types of nursing data when collected. The nursing data of the same type collected at different times are divided into the same nursing sub-data. The nursing data of different tumor patients are divided in the same way, and their corresponding nursing sub-data are obtained respectively.

[0041] The nursing data and its nursing sub-data obtained at this time are in their original state, and the original state refers to the different forms of the nursing data when it is collected, including text form, image form, digital form, etc. The processing unit converts the obtained nursing sub-data from the original form into binary form, and marks the binary form of the nursing sub-data as uploaded data.

[0042] It should be further explained that, in the specific implementation process, the data upload module sets an upload cycle and an upload channel, uploads the obtained upload data and records its corresponding upload coefficient, and the process of classifying the uploaded data according to the obtained upload coefficient includes:

[0043] An upload cycle is set. When an upload cycle is reached, the upload data in the upload cycle is included in the same upload data packet. Several upload channels are set. Different upload channels are independent of each other. The obtained upload data packet is divided to obtain several upload sub-data packets. The number of the upload sub-data packets is the same as the number of upload channels. The obtained upload sub-data packets are matched with the upload channels in sequence. The corresponding upload sub-data packets are uploaded to the cloud for storage through the constructed upload channels.

[0044] The delay rate of each upload channel during data upload is monitored in real time, and the obtained delay rate is marked as D t , where t represents the specific time corresponding to the delay rate, the data packet size of the upload sub-data packet transmitted by each upload channel is obtained, and the obtained data packet size is marked as G i Based on this, the upload coefficient of the uploaded sub-data packet in the upload channel is obtained, which is recorded as R i , where i=1, 2, 3, ..., n, n represents the number of upload channels;

[0045] R i = ∫ 0 t ln [ ∑ (n+∂) G i *μ * D t ] ；

[0046] in, is a constant greater than zero, The weight coefficient preset for the upload channel is used to obtain the upload coefficient of each upload sub-data packet in its upload channel in the same upload cycle, and the upload coefficient range [R min , R max ], compare the obtained upload coefficient with the upload coefficient range respectively. If R i <R min , then the corresponding upload sub-packet is marked as low upload state, R i >R max , then the corresponding upload sub-packet is marked as high upload state. If R min ≤R i ≤R max , then the corresponding upload sub-data packet is marked as medium upload state.

[0047] It should be further explained that, in a specific implementation process, the data uploading module obtains a verification node of the uploaded data, connects to the obtained verification node to obtain a corresponding verification key, and after the upload is completed, verifies the integrity of the uploaded data according to the obtained verification key to determine whether there is damaged data. The process includes:

[0048] Before uploading data, obtain the verification node of each uploaded sub-data packet in the same upload cycle. The verification node refers to the characters at different fixed digits in each uploaded sub-data packet. Since the uploaded sub-data packet is a binary string, it is possible to determine whether the uploaded sub-data packet has changed by determining whether the characters at the fixed digits have changed.

[0049] The fixed digit is set by the relevant personnel before data is uploaded. The fixed digit and the number of fixed digits of different uploaded sub-data packets are different. The fixed digit of the same uploaded sub-data packet remains unchanged before and after uploading. The verification nodes of the same uploaded sub-data packet are arranged in sequence to obtain the verification key of the uploaded sub-data packet. The same method is adopted to obtain the verification key of each uploaded sub-data packet in the upload cycle, and the verification key is fed back to the relevant personnel.

[0050] After the upload is completed, the verification key of each uploaded sub-data packet after the upload is completed is obtained, and it is compared with the verification key before the data is uploaded. If the two are the same, the uploaded sub-data packet is judged to be complete and marked as complete data. If the two are different, the uploaded sub-data packet is judged to be damaged and marked as damaged data.

[0051] It should be further explained that, in a specific implementation process, the damage assessment module obtains the damaged node of the damaged data, and the process of obtaining the damage coefficient of the damaged data according to the obtained damaged node includes:

[0052] When an uploaded sub-data packet is marked as damaged data, the verification nodes of the damaged data are compared in turn, and the verification nodes with different characters in their verification keys are marked as damaged nodes. The total number of damaged nodes in the uploaded sub-data packet is obtained, and the ratio of the total number of damaged nodes to the total number of verification nodes in the uploaded sub-data packet is used as the damage coefficient of the damaged data. The same method is used to obtain the damage coefficient of each damaged data in the same upload cycle.

[0053] It should be further explained that, in the specific implementation process, the damage assessment module constructs a corresponding damage prediction model according to the upload coefficient and the damage coefficient, and the process of using the damage prediction model to predict the damage coefficient of subsequent uploaded data includes:

[0054] Obtain the upload coefficient of damaged data, add the upload coefficient and damage coefficient of each damaged data in different upload cycles into the same damage prediction set, divide the obtained damage prediction set into a training set and a test set, select a deep learning model as the initial damage prediction model, use the obtained training set and test set to continuously train and evaluate the initial damage prediction model, and obtain the latest damage prediction model;

[0055] The damage prediction model is used to predict and output the corresponding damage coefficient according to the input upload coefficient, obtain the upload coefficient of the subsequent uploaded sub-data packet, and input it into the constructed damage prediction model, use the damage prediction model to predict the corresponding damage coefficient, and output the corresponding damage coefficient.

[0056] It should be further explained that, in a specific implementation process, the traffic optimization module evaluates each upload channel according to the predicted damage coefficient to divide it into different upload channel levels, and the process of performing traffic optimization on upload channels of different levels includes:

[0057] Taking any upload cycle as an example, the predicted damage coefficient is marked as S i , set the damage coefficient range [S min , S max ], compare the obtained damage coefficient with the damage coefficient range respectively. If S i <S min , then the corresponding upload channel is marked as low damage level, S i >S max , then the corresponding upload channel is marked as high damage level. If S min ≤S i ≤S max , then the corresponding upload channel is marked as medium damage level;

[0058] Based on the previous upload cycle, the traffic of each upload channel in the current upload cycle is optimized respectively, the traffic resources of the upload channel with medium damage level are kept unchanged, the traffic resources of the upload channel with high damage level are increased, and the traffic resources of the upload channel with low damage level are reduced.

[0059] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A nursing data management optimization system for cancer patients, characterized in that: It includes a main control center, which is communicatively connected to a data acquisition module, a data upload module, a damage assessment module, and a traffic optimization module; The data acquisition module is used to collect nursing data of tumor patients, divide the collected nursing data and convert it into binary form to obtain corresponding upload data; The data upload module is used to set an upload cycle and an upload channel, upload the obtained upload data and record its corresponding upload coefficient, classify the uploaded data according to the obtained upload coefficient, obtain the verification node of the uploaded data, connect the obtained verification node to obtain the corresponding verification key, and after the upload is completed, verify the integrity of the uploaded data according to the obtained verification key to determine whether there is damaged data; The damage assessment module is used to obtain the damaged node of the damaged data, obtain the damaged coefficient of the damaged data according to the obtained damaged node, build a corresponding damage prediction model according to the upload coefficient and the damaged coefficient, and use the damage prediction model to predict the damage coefficient of the subsequent uploaded data; The traffic optimization module is used to evaluate each upload channel according to the predicted damage coefficient to divide it into different upload channel levels, and perform traffic optimization on upload channels of different levels respectively; The process of the data acquisition module collecting nursing data of tumor patients includes: Setting a collection unit to collect nursing data of cancer patients through the collection unit, wherein the nursing data refers to the medical records, treatment plans, drug management, test results, imaging examinations, symptom monitoring, quality of life assessment, and nutritional status of cancer patients; The process of the data acquisition module dividing the collected nursing data and converting it into binary form to obtain corresponding uploaded data includes: A processing unit is provided, wherein the nursing data of a single tumor patient is divided to obtain corresponding nursing sub-data, and each obtained nursing sub-data is converted from an original form to a binary form by the processing unit, and the nursing sub-data in the binary form is marked as upload data; The data uploading module sets an uploading cycle and an uploading channel, uploads the obtained uploading data and records its corresponding uploading coefficient, and the process of classifying the uploading data according to the obtained uploading coefficient includes: An upload cycle is set, and an upload data packet is obtained when an upload cycle is reached. Several upload channels are set, and the obtained upload data packet is divided into several upload sub-data packets, and the upload sub-data packets are uploaded to the cloud for storage through the constructed upload channels; Monitor the delay rate of each upload channel in the data upload process in real time, obtain the data packet size of the upload sub-data packet transmitted by each upload channel, and obtain the upload coefficient of each upload sub-data packet in its upload channel; Setting an upload coefficient range, comparing the obtained upload coefficients with the upload coefficient range respectively, and classifying the uploaded sub-data packets into a low upload state, a high upload state, and a medium upload state according to the comparison result; The data uploading module obtains the verification node of the uploaded data, connects the obtained verification node to obtain the corresponding verification key, and verifies the integrity of the uploaded data according to the obtained verification key after the upload is completed to determine whether there is damaged data. The process includes: Before uploading data, obtain the verification node of each uploaded sub-data packet in the same upload cycle, wherein the verification node refers to the characters at different fixed digits in each uploaded sub-data packet, and obtain the verification key of each uploaded sub-data packet according to the verification node of the same uploaded sub-data packet; After the upload is completed, the verification key of each uploaded sub-data package after the upload is completed is obtained, and it is compared with the verification key before the data is uploaded. According to the comparison result, the uploaded sub-data package is divided into complete data and damaged data; The process in which the damage assessment module obtains the damaged node of the damaged data and obtains the damage coefficient of the damaged data according to the obtained damaged node includes: When an uploaded sub-data packet is marked as damaged data, the verification nodes of the damaged data are compared in sequence, and the verification nodes with different characters in their verification keys are marked as damaged nodes, and the ratio of the total number of damaged nodes to the total number of verification nodes in the uploaded sub-data packet is used as the damage coefficient of the damaged data; The damage assessment module constructs a corresponding damage prediction model according to the upload coefficient and the damage coefficient, and the process of using the damage prediction model to predict the damage coefficient of subsequent uploaded data includes: Obtain the upload coefficient of damaged data, incorporate the upload coefficient and damage coefficient of each damaged data in different upload cycles into the same damage prediction set, select the deep learning model as the initial damage prediction model, use the obtained damage prediction set to continuously train and evaluate the initial damage prediction model, and obtain the latest damage prediction model; The upload coefficients of the subsequent uploaded sub-data packets are obtained and input into the constructed damage prediction model, the corresponding damage coefficients are predicted using the damage prediction model, and the corresponding damage coefficients are output.

2. A nursing data management optimization system for cancer patients according to claim 1, characterized in that: The traffic optimization module evaluates each upload channel according to the predicted damage coefficient to classify it into different upload channel levels. The process of performing traffic optimization on upload channels of different levels includes: Set a damage coefficient range, compare the damage coefficient with the damage coefficient range, and divide the upload channels into low damage level, high damage level, and medium damage level according to the comparison results. Based on the previous upload cycle, optimize the traffic of each upload channel in the current upload cycle, keep the traffic resources of the upload channel with medium damage level unchanged, increase the traffic resources of the upload channel with high damage level, and reduce the traffic resources of the upload channel with low damage level.

Images