A big data management method and system based on Internet of Things

Abstract

The present invention discloses a big data management method and system based on the Internet of Things, and relates to the technical field of data management, including: preliminary screening of big data, dividing the big data into evidence-based data and undocumented data; screening the undocumented data using a health certification method, and recording the screened undocumented data as evidence-based data; obtaining the health applicable scope of the evidence-based data; the present invention is used to solve the problem that the existing big data management can only manage the security and risk of the data, and when the content of the data is false and unreasonable, the content of the data cannot be securely audited, so that the data content will mislead the user or the data content is irrelevant to the user's needs.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to a big data management method and system based on the Internet of Things. Background Art

[0002] ‌‌Big ​​data management refers to ensuring the accuracy, integrity, reliability and security of data through planning, organizing, controlling and supervising the entire life cycle of data assets; this includes aspects such as data collection, storage, processing, analysis and sharing, aiming to maximize the value of data and support business decisions and operational activities; the core of big data management is to transform data into useful information to improve data quality and efficiency, reduce data redundancy and duplication, reduce management costs, and enhance the value and competitiveness of data.

[0003] Existing methods for big data management usually verify the data source and conduct a comprehensive analysis of the credibility of the data and the frequency of data updates to provide security for data management and subsequent data use, thereby reducing the security risks of data in data management. This improved method can only review the security and authenticity of the data source, but when the content of the data is false and unreasonable, it is impossible to conduct a security review of the data content, resulting in the data content misleading the user or the data content being irrelevant to the user's needs, which in turn causes the user to make decisions that affect the user's health due to the data content. For example, in the publication number CN118070 The patent application of 341A discloses a big data management method and a big data management system. This solution provides multi-dimensional and comprehensive protection for data security through data acquisition, storage and management, reduces the data security risk of the big data management system, and protects the privacy and confidentiality of user data. Other methods for big data management usually manage data in many aspects such as collection, classification, processing, early warning and visualization. This method is still a management of data security and data risks. When the content of the data is false and unreasonable, there will still be problems that the data content will mislead the user or the data content is irrelevant to user needs. Summary of the invention

[0004] The present invention aims to solve one of the technical problems in the prior art to at least a certain extent, by proposing a big data management method and system based on the Internet of Things, so as to solve the problem that the existing big data management can only manage the security and risk of the data, and when the content of the data is false and unreasonable, the content of the data cannot be security audited, resulting in the problem that the data content will mislead the user or the data content is irrelevant to the user's needs.

[0005] To achieve the above objectives, in a first aspect, the present application provides a big data management method based on the Internet of Things, comprising the following steps:

[0006] Conduct a preliminary screening of big data based on medical data, and divide the big data into evidence-based data and non-evidence-based data based on the screening results;

[0007] The unsupported data are processed using the health certificate method, and the reliability of the unsupported data is screened based on the processing results, and the unsupported data obtained by the screening is recorded as the supported data; the health certificate method includes: for any unsupported data, all related diagnostic sentences corresponding to the health symptoms of the unsupported data are obtained and recorded as unsupported diagnostic sentences; for any text segment WZD in the health text data of the unsupported data, when there is a sentence containing an unsupported diagnostic sentence in the text segment WZD, the unsupported data is recorded as reliable data; when all text segments WZD in the health text data of the unsupported data do not contain sentences containing unsupported diagnostic sentences, the unsupported data is recorded as unreliable data; the unsupported data recorded as reliable data is recorded as supported data;

[0008] Process the evidence-based data and obtain the health applicability scope of the evidence-based data based on the processing results.

[0009] Furthermore, the big data is initially screened based on medical data, and the big data is divided into evidence-based data and non-evidence-based data based on the screening results, including:

[0010] Use disease extraction method to process big data and obtain health symptoms in big data;

[0011] Analyze health conditions based on medical data, and obtain key diagnostic statements and additional diagnostic statements for each health condition based on the analysis results;

[0012] Based on the key diagnostic statements and additional diagnostic statements of health diseases, the big data of health diseases are preliminarily screened, and based on the screening results, the big data are divided into evidence-based data and unsupported data.

[0013] Furthermore, the disease item extraction method includes:

[0014] A disease database is obtained based on big data, wherein the disease database is used to store the names of various existing diseases; when the big data contains labels, the names of all the labels of the big data are compared with all the names in the disease database in turn, and when the name of any label of the big data is the same as any name in the disease database, the label is recorded as a disease label; when there is a disease label in the label of the big data, the text data of the big data is extracted and recorded as health text data; the health text data is segmented, and the Chinese words obtained by the segmentation are recorded as health Chinese words, the health Chinese words are screened based on the noun database, and the nouns in the health Chinese words are recorded as health nouns; the disease labels are compared with the health nouns respectively, and when there are disease labels in the health nouns, the big data is recorded as relatable data; when there are no disease labels in the health nouns, the big data is recorded as non-relatable data; when there are no disease labels in the labels of the big data, the big data is recorded as removable data.

[0015] Furthermore, the disease item extraction method also includes:

[0016] When the big data does not contain labels, obtain the health text data in the big data, and perform word segmentation on the health text data, and compare the obtained Chinese words with the disease names in the disease database. When there are Chinese words in the health text data that are equal to any disease name in the disease database, the big data is recorded as non-related data; when there are no Chinese words in the health text data that are equal to any disease name in the disease database, the big data is recorded as removable data;

[0017] When big data is recorded as relatable data, the disease labels in the health terms in the relatable data are recorded as health symptoms of the big data; when big data is recorded as unrelated data and there are pictures or videos in the big data, AI is used to perform text recognition on the pictures and videos in the big data, and the recognized Chinese words are recorded as multimedia words. When any multimedia word is equal to any disease name in the disease database, the multimedia word is recorded as the health symptom of the big data; when all multimedia words are not equal to any disease name in the disease database, the big data is recorded as removable data; when big data is recorded as unrelated data and there are no pictures or videos in the big data, the big data is recorded as removable data; the big data recorded as removable data is removed from the database.

[0018] Furthermore, health conditions are analyzed based on the medical data, and key diagnostic statements and additional diagnostic statements for each health condition are obtained based on the analysis results, including:

[0019] Obtain all health symptoms corresponding to the big data, and record all health symptoms as the symptoms to be analyzed BD 1 Diseases to be analyzed BD k;

[0020] For the disease to be analyzed BD 1 Diseases to be analyzed BD k Any of the symptoms to be analyzed in BD k1 , based on big data, obtain the disease in the medical data as the disease to be analyzed BD k1 Medical data of the company, and recorded as analyzed medical data FY k1 ; Will analyze medical data FY k1 The sentences in the patient rehabilitation data are recorded as medical rehabilitation sentences, and all analyzed medical data FY k1 The medical rehabilitation sentences that appear in the test are recorded as key diagnosis sentences, and the medical rehabilitation sentences other than the key diagnosis sentences are recorded as additional diagnosis sentences, where k1 is a positive integer less than or equal to k and greater than or equal to 1.

[0021] Furthermore, based on the key diagnostic statements and additional diagnostic statements of health symptoms, the big data of health symptoms are preliminarily screened, and based on the screening results, the big data is divided into evidence-based data and non-evidence-based data, including:

[0022] For any big data, obtain all key diagnostic statements and additional diagnostic statements corresponding to the health symptoms of the big data; record the paragraph of the text in the health text data as t, and record all the paragraphs as text segments WZD in sequence 1 To text segment WZD t ; Establish a plane rectangular coordinate system, recorded as the health analysis coordinate system, where the coordinate points to the right of the coordinate origin of the X-axis of the health analysis coordinate system are the text segments WZD 1 To text segment WZD t , the unit of the Y-axis is percentage.

[0023] Furthermore, based on the key diagnostic statements and additional diagnostic statements of health symptoms, the big data of health symptoms are preliminarily screened, and based on the screening results, the big data is divided into evidence-based data and non-evidence-based data, which also includes:

[0024] For any text segment WZD t1 , change the text segment WZD t1 The number of sentences in the text segment WZD is recorded as c. t1 The number of sentences containing key diagnostic statements is recorded as c1, and the text segment WZD t1 The number of sentences with additional diagnostic statements but no key diagnostic statements is recorded as c2, and the association ratio algorithm is used to obtain the text segment WZD t1 The correlation percentage, the correlation ratio algorithm is: , where F is the correlation percentage, based on the text segment WZD t1 And the text segment WZDt1 The association percentage is marked in the health analysis coordinate system and the mark is recorded as the health association point JG t1 ; Get all the health association points JG corresponding to the text segment WZD; It is recorded as the association judgment standard. When the ordinate of the health-related point JG is greater than or equal to the association judgment standard, the big data is recorded as evidence-based data; when the ordinates of all health-related points JG are less than the association judgment standard, the big data is recorded as unsupported data.

[0025] Furthermore, the evidence-based data is processed, and the health application scope of the evidence-based data is obtained based on the processing results, including:

[0026] When the evidence-based data contains labels, the fields corresponding to the labels of the evidence-based data are recorded as the health application scope of the evidence-based data;

[0027] When the evidence-based data does not contain labels, the labels corresponding to all health symptoms in the evidence-based data are recorded as temporary labels of the evidence-based data, and the fields corresponding to the temporary labels of the evidence-based data are recorded as the health applicability scope of the evidence-based data; when the evidence-based data is managed, the management scope of the evidence-based data is limited to the health applicability scope of the evidence-based data.

[0028] In a second aspect, the present application also provides a big data management system based on the Internet of Things, including a big data screening module, a secondary judgment module, and an application scope determination module;

[0029] The big data screening module is used to preliminarily screen the big data based on medical data, and divide the big data into evidence-based data and non-evidence-based data based on the screening results;

[0030] The secondary judgment module is used to process the unsupported data using the health certificate method, and to screen the reliability of the unsupported data based on the processing results, and record the screened unsupported data as the supported data;

[0031] The scope of application determination module is used to process the evidence-based data and obtain the healthy scope of application of the evidence-based data based on the processing results.

[0032] Beneficial effects of the present invention: The present invention first performs a preliminary screening of big data based on medical data, and divides the big data into evidence-based data and unsupported data based on the screening results. The advantage of this is that by dividing the big data into evidence-based data and unsupported data, the big data can be divided based on the authenticity of the content of the big data. The data content in the evidence-based data is data whose authenticity can be proved by existing data, and the data content in the unsupported data is data whose authenticity cannot be proved by existing data. Through this division method, in the subsequent data management process, big data with real content and real data with false content can be distinguished and managed to prevent the problem that the data content will mislead users;

[0033] The present invention also uses a health certification method to process unsupported data, and performs reliability screening on the unsupported data based on the processing results, and records the screened unsupported data as certificate-based data; finally, the certificate-based data is processed, and the health applicable scope of the certificate-based data is obtained based on the processing results. The advantage of this is that, by performing reliability screening on the unsupported data, it is possible to extract statements in the unsupported data that can prove the authenticity of the data content, thereby adjusting the misjudged unsupported data to certificate-based data. By obtaining the health applicable scope of the certificate-based data, it is possible to effectively prevent the problem that when users search for big data, the data content found is irrelevant to the user's needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a functional block diagram of the system of the present invention.

[0035] Figure 2 The figure is a flow chart of the steps of the method of the present invention.

[0036] Figure 3 It is a schematic diagram of the health analysis coordinate system of the present invention.

[0037] Figure 4 It is a schematic structural diagram of the electronic device of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] Example 1, first aspect, please refer to Figure 1As shown, the present application provides a big data management system based on the Internet of Things, including a big data screening module, a secondary judgment module and an application scope determination module;

[0040] The big data screening module is used to perform preliminary screening on the big data based on the medical data, and divide the big data into evidence-based data and non-evidence-based data based on the screening results; the big data screening module includes a data screening unit, the data screening unit is configured with a data screening strategy, the data screening strategy includes: using the disease item extraction method to process the big data, and obtaining health symptoms in the big data; the disease item extraction method includes: using the disease item extraction method to process the big data, and obtaining health symptoms in the big data;

[0041] The disease item extraction method includes: obtaining a disease database based on big data, wherein the disease database is used to store the names of multiple existing diseases; when the big data contains labels, the names of all the labels of the big data are compared with all the names in the disease database in turn, and when the name of any label of the big data is the same as any name in the disease database, the label is recorded as a disease label; when there is a disease label in the label of the big data, the text data of the big data is extracted and recorded as health text data; the health text data is segmented, and the Chinese words obtained by the segmentation are recorded as health Chinese words, the health Chinese words are screened based on the noun database, and the nouns in the health Chinese words are recorded as health nouns; the disease labels are compared with the health nouns respectively, and when the disease labels exist in the health nouns, the big data is recorded as relatable data; when there is no disease label in the health nouns, the big data is recorded as non-relatable data; when there is no disease label in the label of the big data, the big data is recorded as removable data;

[0042] In the specific implementation process, for example, the disease names stored in the disease database include "gout", and there is a label named "gout" in the label of the big data during analysis, then "gout" can be recorded as the disease label. In addition, there is a health term "gout" in the health text data of the big data, then the big data can be recorded as relatable data; when the content of the big data and the label of the big data have the same disease name, it can be said that the content of the big data is related to the disease; and when there is a disease label in the label of the big data, but the disease label does not appear in the health term, it means that the content of the big data may be related to the disease, but it may not be explained in the health text data due to reasons such as expression, so the big data can be recorded as non-related data and subsequent analysis; and when there is no disease label in the label of the big data, it means that the labels set by the big data are all labels unrelated to the disease, so it is impossible to accurately judge the validity of the content of the big data and the fields involved, and the big data can be eliminated;

[0043] When the big data does not contain labels, obtain the health text data in the big data, and perform word segmentation on the health text data, and compare the obtained Chinese words with the disease names in the disease database. When there are Chinese words in the health text data that are equal to any disease name in the disease database, the big data is recorded as non-related data; when there are no Chinese words in the health text data that are equal to any disease name in the disease database, the big data is recorded as removable data;

[0044] When big data is recorded as relatable data, the disease labels in the health terms in the relatable data are recorded as health symptoms of the big data; when big data is recorded as unrelated data and there are pictures or videos in the big data, AI is used to perform text recognition on the pictures and videos in the big data, and the recognized Chinese words are recorded as multimedia words. When any multimedia word is equal to any disease name in the disease database, the multimedia word is recorded as the health symptom of the big data; when all multimedia words are not equal to any disease name in the disease database, the big data is recorded as removable data; when big data is recorded as unrelated data and there is no disease name in the big data, the big data is recorded as removable data. When there are pictures or videos in the big data, the big data will be recorded as removable data; the big data recorded as removable data will be removed from the database; in the specific implementation process, for example, during an analysis, when AI is used to perform text recognition on pictures in the big data, the recognized Chinese word is "gout", and "gout" is the name of the disease, then "gout" can be recorded as a health symptom in the big data; when all multimedia words are not equal to any disease name in the disease database, it means that the pictures and videos in the big data are all unrelated to the disease, and at the same time, no disease labels appear in the health terms in the big data, so the big data can be removed as data unrelated to health.

[0045] The data screening strategy also includes: obtaining all health symptoms corresponding to the big data, and recording all health symptoms as the symptoms to be analyzed BD 1 Diseases to be analyzed BD k ;

[0046] For the disease to be analyzed BD 1 Diseases to be analyzed BD k Any of the symptoms to be analyzed in BD k1 , based on big data, obtain the disease in the medical data as the disease to be analyzed BD k1 Medical data of the company, and recorded as analyzed medical data FY k1 ; Will analyze medical data FY k1 The sentences in the patient rehabilitation data are recorded as medical rehabilitation sentences, and all analyzed medical data FY k1The medical rehabilitation sentences that appear in the data are recorded as key diagnosis sentences, and the medical rehabilitation sentences other than the key diagnosis sentences are recorded as additional diagnosis sentences, where k1 is a positive integer less than or equal to k and greater than or equal to 1; in the specific implementation process, for example, in a data analysis, the BD of the disease to be analyzed is obtained k1 is "gout", and all the analyzed medical data corresponding to "gout" FY k1 If the medical rehabilitation sentence that appears in the data is "drinking more water can prevent gout", then "drinking more water can prevent gout" can be used as the key diagnostic sentence; by obtaining the key diagnostic sentence and the additional diagnostic sentence, the authenticity of the content of the big data can be verified. When the content of the big data contains medical rehabilitation sentences and additional diagnostic sentences, it means that the content of the big data is relatively authentic and reliable, and can be used for reference by users. When the content of the big data does not contain medical rehabilitation sentences or additional diagnostic sentences, it means that the authenticity of the content of the big data cannot be verified.

[0047] The data screening strategy also includes: preliminarily screening the big data of health symptoms based on the key diagnostic statements and additional diagnostic statements of health symptoms, and dividing the big data into evidence-based data and unsupported data based on the screening results; for any big data, obtaining all the key diagnostic statements and additional diagnostic statements corresponding to the health symptoms of the big data; recording the paragraph of the text in the health text data as t, and recording all the paragraphs in turn as text segments WZD 1 To text segment WZD t ; Establish a plane rectangular coordinate system, recorded as the health analysis coordinate system, where the coordinate points to the right of the coordinate origin of the X-axis of the health analysis coordinate system are the text segments WZD 1 To text segment WZD t , the unit of Y axis is percentage;

[0048] For any text segment WZD t1 , change the text segment WZD t1 The number of sentences in the text segment WZD is recorded as c. t1 The number of sentences containing key diagnostic statements is recorded as c1, and the text segment WZD t1 The number of sentences with additional diagnostic statements but no key diagnostic statements is recorded as c2, and the association ratio algorithm is used to obtain the text segment WZD t1 The correlation percentage, the correlation ratio algorithm is: , where F is the correlation percentage, based on the text segment WZD t1 And the text segment WZD t1 The association percentage is marked in the health analysis coordinate system and the mark is recorded as the health association point JG t1 ; Get all the health association points JG corresponding to the text segment WZD; Recorded as the association judgment standard, when the vertical coordinate of the health association point JG is greater than or equal to the association judgment standard, the big data is recorded as evidence-based data; when the vertical coordinates of all health association points JG are less than the association judgment standard, the big data is recorded as unsupported data; in the specific implementation process, for example, in an analysis, the text segment WZD t1 The number of sentences is 10, and the text segment is WZD t1 The number of sentences containing key diagnostic statements is recorded as 1, and the text segment WZD t1 The number of sentences with additional diagnostic statements but no key diagnostic statements is recorded as 2, and the text segment WZD can be obtained by calculation t1 The correlation percentage is about 23.3%; after calculating the correlation percentage of all text segments WZD of a text big data, the obtained health analysis coordinate system can be found in Figure 3 As shown, the value of t is 4, and WZD1 to WZD4 are text segments WZD 1 To text segment WZD 4 , then the association judgment standard obtained by calculation is 25%, and the health association points JG obtained by calculating the association percentage of each text segment WZD are JG1 to JG4. Through analysis, it can be obtained that big data can be recorded as evidence-based data.

[0049] The secondary judgment module is used to process the undependent data using the health certification method, and to screen the reliability of the undependent data based on the processing results, and record the screened undependent data as certificate-based data; the health certification method includes: for any undependent data, all related diagnostic sentences corresponding to the health symptoms of the undependent data are obtained and recorded as undependent diagnostic sentences; for any text segment WZD in the health text data of the undependent data, when there is a sentence containing an undependent diagnostic sentence in the text segment WZD, the undependent data is recorded as reliable data; when all text segments WZD in the health text data of the undependent data do not contain sentences containing undependent diagnostic sentences, the undependent data is recorded as unreliable data; in the specific implementation process, when there are related diagnostic sentences in the health text data of the undependent data, it means that the undependent data still has a part that can verify the authenticity and validity of the undependent data, so the undependent data containing the related diagnostic sentences can be recorded as reliable data and the reliable data can be recorded as certificate-based data in subsequent analysis for subsequent management; the undependent data recorded as reliable data is recorded as certificate-based data.

[0050] The application scope determination module is used to process the evidence-based data and obtain the healthy application scope of the evidence-based data based on the processing results; the application scope determination module includes a scope determination unit, and the scope determination unit is configured with a scope determination strategy, and the scope determination strategy includes: when the evidence-based data contains a label, the field corresponding to the label of the evidence-based data is recorded as the healthy application scope of the evidence-based data;

[0051] When the evidence-based data does not contain labels, the labels corresponding to all health symptoms in the evidence-based data are recorded as temporary labels of the evidence-based data, and the fields corresponding to the temporary labels of the evidence-based data are recorded as the health applicability scope of the evidence-based data; when the evidence-based data is managed, the management scope of the evidence-based data is limited to the health applicability scope of the evidence-based data; in the specific implementation process, by setting the health applicability scope of the evidence-based data based on the labels of the evidence-based data or the temporary labels of the evidence-based data, it can effectively prevent users from finding data content that is irrelevant to their needs when searching for big data, causing users to make decisions that affect their health due to the data content.

[0052] Example 2, second aspect, please refer to Figure 2 As shown, the present application also provides a big data management method based on the Internet of Things, comprising the following steps:

[0053] Step S1, preliminarily screening the big data based on medical data, and dividing the big data into evidence-based data and unsupported data based on the screening results; Step S1 includes the following sub-steps:

[0054] Step S101, using the disease extraction method to process the big data and obtain health symptoms in the big data; the disease extraction method includes: step S1011, obtaining a disease database based on the big data, wherein the disease database is used to store the existing names of multiple diseases; when the big data contains labels, the names of all the labels of the big data are compared with all the names in the disease database in turn, and when the name of any label of the big data is the same as any name in the disease database, the label is recorded as a disease label; when there is a disease label in the label of the big data, the text data of the big data is extracted and recorded as health text data; the health text data is segmented, and the Chinese words obtained by the segmentation are recorded as health Chinese words, the health Chinese words are screened based on the noun database, and the nouns in the health Chinese words are recorded as health nouns; the disease labels are compared with the health nouns respectively, and when the disease labels exist in the health nouns, the big data is recorded as relatable data; when there is no disease label in the health nouns, the big data is recorded as non-relatable data; when there is no disease label in the label of the big data, the big data is recorded as removable data;

[0055] Step S1012, when the big data does not contain a label, obtain the health text data in the big data, perform word segmentation on the health text data, and compare the obtained Chinese words with the disease names in the disease database. When there is a Chinese word in the health text data that is equal to any disease name in the disease database, the big data is recorded as non-related data; when there is no Chinese word in the health text data that is equal to any disease name in the disease database, the big data is recorded as removable data;

[0056] Step S1013, when the big data is recorded as relatable data, the disease labels in the health terms of the relatable data are recorded as the health symptoms of the big data; when the big data is recorded as non-relatable data and there are pictures or videos in the big data, AI is used to perform text recognition on the pictures and videos in the big data, and the recognized Chinese words are recorded as multimedia words. When any multimedia word is equal to any disease name in the disease database, the multimedia word is recorded as the health symptom of the big data; when all multimedia words are not equal to any disease name in the disease database, the big data is recorded as removable data; when the big data is recorded as non-relatable data and there are no pictures or videos in the big data, the big data is recorded as removable data; the big data recorded as removable data is removed from the database.

[0057] Step S102, analyzing health symptoms based on medical data, and obtaining key diagnostic statements and additional diagnostic statements for each health symptom based on the analysis results; Step S102 includes the following sub-steps: Step S1021, obtaining health symptoms corresponding to all big data, and recording all health symptoms as symptoms to be analyzed BD 1 Diseases to be analyzed BD k ;

[0058] Step S1022, for the disease to be analyzed BD 1 Diseases to be analyzed BD k Any of the symptoms to be analyzed in BD k1 , based on big data, obtain the disease in the medical data as the disease to be analyzed BD k1 Medical data of the company, and recorded as analyzed medical data FY k1 ; Will analyze medical data FY k1 The sentences in the patient rehabilitation data are recorded as medical rehabilitation sentences, and all analyzed medical data FY k1 The medical rehabilitation sentences that appear in the test are recorded as key diagnosis sentences, and the medical rehabilitation sentences other than the key diagnosis sentences are recorded as additional diagnosis sentences, where k1 is a positive integer less than or equal to k and greater than or equal to 1.

[0059] Step S103, based on the key diagnostic statements and additional diagnostic statements of health symptoms, the big data of health symptoms are preliminarily screened, and the big data is divided into evidence-based data and non-evidence-based data based on the screening results; Step S103 includes the following sub-steps: Step S1031, for any big data, all key diagnostic statements and additional diagnostic statements corresponding to the health symptoms of the big data are obtained; the paragraph of the text in the health text data is recorded as t, and all paragraphs are recorded as text segments WZD in sequence 1 To text segment WZD t; Establish a plane rectangular coordinate system, recorded as the health analysis coordinate system, where the coordinate points to the right of the coordinate origin of the X-axis of the health analysis coordinate system are the text segments WZD 1 To text segment WZD t , the unit of Y axis is percentage;

[0060] Step S1032: for any text segment WZD t1 , change the text segment WZD t1 The number of sentences in the text segment WZD is recorded as c. t1 The number of sentences containing key diagnostic statements is recorded as c1, and the text segment WZD t1 The number of sentences with additional diagnostic statements but no key diagnostic statements is recorded as c2, and the association ratio algorithm is used to obtain the text segment WZD t1 The correlation percentage, the correlation ratio algorithm is: , where F is the correlation percentage, based on the text segment WZD t1 And the text segment WZD t1 The association percentage is marked in the health analysis coordinate system and the mark is recorded as the health association point JG t1 ; Get all the health association points JG corresponding to the text segment WZD; It is recorded as the association judgment standard. When the ordinate of the health-related point JG is greater than or equal to the association judgment standard, the big data is recorded as evidence-based data; when the ordinates of all health-related points JG are less than the association judgment standard, the big data is recorded as unsupported data.

[0061] Step S2, using the health certification method to process the undependent data, and based on the processing results, screening the reliability of the undependent data, and recording the screened undependent data as the certificate data; the health certification method includes: step S201, for any undependent data, obtaining all the associated diagnosis sentences corresponding to the health symptoms of the undependent data, and recording them as undependent diagnosis sentences; for any text segment WZD in the health text data of the undependent data, when there is a sentence containing the undependent diagnosis sentence in the text segment WZD, the undependent data is recorded as reliable data; when all the text segments WZD in the health text data of the undependent data do not contain a sentence containing the undependent diagnosis sentence, the undependent data is recorded as unreliable data;

[0062] Step S202, record the unsupported data that is recorded as reliable data as supported data.

[0063] Step S3, processing the evidence-based data, and obtaining the health application scope of the evidence-based data based on the processing result; Step S3 includes the following sub-steps: Step S301, when the evidence-based data contains a label, recording the field corresponding to the label of the evidence-based data as the health application scope of the evidence-based data;

[0064] Step S302, when the evidence-based data does not contain a label, the labels corresponding to all health symptoms in the evidence-based data are recorded as temporary labels of the evidence-based data, and the fields corresponding to the temporary labels of the evidence-based data are recorded as the health applicability scope of the evidence-based data; when the evidence-based data is managed, the management scope of the evidence-based data is limited to the health applicability scope of the evidence-based data.

[0065] Example 3, please refer to Figure 4 As shown, Figure 4 The structural diagram of an electronic device is illustrated, and the electronic device may include: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus. The memory stores computer-readable instructions, and the processor can call the instructions in the memory. When the computer-readable instructions are executed by the processor, the steps in a big data management method based on the Internet of Things are executed to achieve the following functions: firstly, the big data is preliminarily screened based on medical data, and the big data is divided into certificate-based data and non-certificate data based on the screening results, and the non-certificate data is processed using the health certification method, and the reliability of the non-certificate data is screened based on the processing results, and the non-certificate data obtained by the screening is recorded as certificate-based data; finally, the certificate-based data is processed, and the health application scope of the certificate-based data is obtained based on the processing results.

[0066] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0067] Embodiment 4. The present application also provides a computer-readable storage medium. The present application provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above big data management method based on the Internet of Things are executed to achieve the following functions: first, the big data is preliminarily screened based on medical data, and the big data is divided into certificate-based data and unsupported data based on the screening results. The unsupported data is processed using the health certificate method, and the reliability of the unsupported data is screened based on the processing results, and the unsupported data obtained by the screening is recorded as certificate-based data; finally, the certificate-based data is processed, and the health applicability scope of the certificate-based data is obtained based on the processing results.

[0068] Through the description of the above implementation methods, the embodiments of the present invention can be provided as methods, systems or computer program products. Based on such an understanding, the above technical solutions can be essentially or partly contributed to the prior art in the form of software products, which can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and include several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0069] In the embodiments provided in the present application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of systems, modules and units can be electrical, mechanical or other forms.

[0070] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. 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. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A big data management method based on the Internet of Things, characterized in that: The steps include: Conduct a preliminary screening of big data based on medical data, and divide the big data into evidence-based data and non-evidence-based data based on the screening results; The unsupported data are processed using the health certificate method, and the reliability of the unsupported data is screened based on the processing results, and the unsupported data obtained by the screening is recorded as the supported data; the health certificate method includes: for any unsupported data, all related diagnostic sentences corresponding to the health symptoms of the unsupported data are obtained and recorded as unsupported diagnostic sentences; for any text segment WZD in the health text data of the unsupported data, when there is a sentence containing an unsupported diagnostic sentence in the text segment WZD, the unsupported data is recorded as reliable data; when all text segments WZD in the health text data of the unsupported data do not contain sentences containing unsupported diagnostic sentences, the unsupported data is recorded as unreliable data; the unsupported data recorded as reliable data is recorded as supported data; Process the evidence-based data and obtain the health application scope of the evidence-based data based on the processing results; Based on medical data, the big data is initially screened and divided into evidence-based data and non-evidence-based data based on the screening results, including: Use disease extraction methods to process big data and obtain health symptoms in big data; Analyze health conditions based on medical data, and obtain key diagnostic statements and additional diagnostic statements for each health condition based on the analysis results; Preliminary screening of the big data of health symptoms based on key diagnostic statements and additional diagnostic statements of health symptoms, and classification of the big data into evidence-based data and non-evidence-based data based on the screening results; Disease item extraction methods include: A disease database is obtained based on big data, wherein the disease database is used to store the names of various existing diseases; when the big data contains labels, the names of all the labels of the big data are compared with all the names in the disease database in turn, and when the name of any label of the big data is the same as any name in the disease database, the label is recorded as a disease label; when there is a disease label in the label of the big data, the text data of the big data is extracted and recorded as health text data; the health text data is segmented, and the Chinese words obtained by the segmentation are recorded as health Chinese words, the health Chinese words are screened based on the noun database, and the nouns in the health Chinese words are recorded as health nouns; the disease labels are compared with the health nouns respectively, and when there are disease labels in the health nouns, the big data is recorded as relatable data; when there are no disease labels in the health nouns, the big data is recorded as non-relatable data; when there are no disease labels in the labels of the big data, the big data is recorded as removable data; The disease extraction method also includes: When the big data does not contain labels, obtain the health text data in the big data, and perform word segmentation on the health text data, and compare the obtained Chinese words with the disease names in the disease database. When there are Chinese words in the health text data that are equal to any disease name in the disease database, the big data is recorded as non-related data; when there are no Chinese words in the health text data that are equal to any disease name in the disease database, the big data is recorded as removable data; When big data is recorded as relatable data, the disease labels in the health terms in the relatable data are recorded as the health symptoms of the big data; when big data is recorded as non-relatable data and there are pictures or videos in the big data, AI is used to perform text recognition on the pictures and videos in the big data, and the recognized Chinese words are recorded as multimedia words. When any multimedia word is equal to any disease name in the disease database, the multimedia word is recorded as the health symptom of the big data; when all multimedia words are not equal to any disease name in the disease database, the big data is recorded as removable data; when big data is recorded as non-relatable data and there are no pictures or videos in the big data, the big data is recorded as removable data; the big data recorded as removable data is removed from the database; Analyze health conditions based on medical data, and obtain key diagnostic statements and additional diagnostic statements for each health condition based on the analysis results, including: Obtain all health symptoms corresponding to the big data, and record all health symptoms as symptoms to be analyzed BD1 to symptoms to be analyzed BD k ; For the condition to be analyzed BD1 to the condition to be analyzed BD k Any of the symptoms to be analyzed in BD k1 , based on big data, obtain the disease in the medical data as the disease to be analyzed BD k1 Medical data of the company, and recorded as analyzed medical data FY k1 ; Will analyze medical data FY k1 The sentences in the patient rehabilitation data are recorded as medical rehabilitation sentences, and all analyzed medical data FY k1 The medical rehabilitation sentences that appear in the data are recorded as key diagnosis sentences, and the medical rehabilitation sentences other than the key diagnosis sentences are recorded as additional diagnosis sentences, where k1 is a positive integer less than or equal to k and greater than or equal to 1; Based on the key diagnostic statements and additional diagnostic statements of health diseases, the big data of health diseases is preliminarily screened, and based on the screening results, the big data is divided into evidence-based data and non-evidence-based data, including: For any big data, all key diagnostic statements and additional diagnostic statements corresponding to the health symptoms of the big data are obtained; the paragraph of the text in the health text data is recorded as t, and all paragraphs are recorded as text segments WZD1 to WZD t ; Establish a plane rectangular coordinate system, recorded as the health analysis coordinate system, where the coordinate points to the right of the coordinate origin of the X-axis of the health analysis coordinate system are text segments WZD1 to WZD t , the unit of Y axis is percentage; Based on the key diagnostic statements and additional diagnostic statements of health diseases, the big data of health diseases is initially screened, and based on the screening results, the big data is divided into evidence-based data and non-evidence-based data, including: For any text segment WZD t1 , change the text segment WZD t1 The number of sentences in the text segment WZD is recorded as c. t1 The number of sentences containing key diagnostic statements is recorded as c1, and the text segment WZD t1 The number of sentences with additional diagnostic statements but no key diagnostic statements is recorded as c2. The relevance ratio algorithm is used to obtain the relevance percentage of the text segment WZDt1. The relevance ratio algorithm is: , where F is the correlation percentage, based on the text segment WZD t1 And the text segment WZD t1 The association percentage is marked in the health analysis coordinate system and the mark is recorded as the health association point JG t1 ; Get all the health association points JG corresponding to the text segment WZD; It is recorded as the association judgment standard. When the ordinate of the health-related point JG is greater than or equal to the association judgment standard, the big data is recorded as evidence-based data; when the ordinates of all health-related points JG are less than the association judgment standard, the big data is recorded as unsupported data.

2. The big data management method based on the Internet of Things according to claim 1, characterized in that: The scope of health application of processing evidence-based data and obtaining evidence-based data based on the processing results includes: When the evidence-based data contains labels, the fields corresponding to the labels of the evidence-based data are recorded as the health application scope of the evidence-based data; When the evidence-based data does not contain labels, the labels corresponding to all health symptoms in the evidence-based data are recorded as temporary labels of the evidence-based data, and the fields corresponding to the temporary labels of the evidence-based data are recorded as the health applicability scope of the evidence-based data; when the evidence-based data is managed, the management scope of the evidence-based data is limited to the health applicability scope of the evidence-based data.

3. A big data management system based on the Internet of Things, used to implement the big data management method based on the Internet of Things according to claim 1 or 2, characterized in that: It includes a big data screening module, a secondary judgment module and an application scope determination module; The big data screening module is used to preliminarily screen the big data based on medical data, and divide the big data into evidence-based data and non-evidence-based data based on the screening results; The secondary judgment module is used to process the unsupported data using the health certificate method, and to screen the reliability of the unsupported data based on the processing results, and record the screened unsupported data as the supported data; The scope of application determination module is used to process the evidence-based data and obtain the healthy scope of application of the evidence-based data based on the processing results.

Images