A method and device for processing health data of people in a target area based on big data

Abstract

The present invention discloses a method and device for processing health data of a population in a target area based on big data, and relates to the field of health big data processing. The method comprises: obtaining candidate physical examination reports of successive batches of examinees in the target area, and extracting physical examination data; establishing a model based on quality control rules to pre-process the physical examination data, extracting reasonable physical examination data therein, analyzing and processing the reasonable physical examination data, and generating personal health reports of each examinee; processing the personal health reports, and generating personal health guidance opinions of the examinee; summarizing all personal health reports and personal health guidance opinions in the target area, and performing health analysis to generate health reports of the population in the target area. The present invention can enable residents to more intuitively grasp their own health conditions, and public health managers to more accurately grasp the health status of the population in the target area, and provide a more accurate data basis and a clearer work direction for the development of public health services.

Description

Technical Field

[0001] The present invention relates to the field of health big data processing, and in particular to a method and device for processing health data of a population in a target area based on big data. Background Art

[0002] At present, people's pursuit and demand for health are growing day by day. As an important means to protect the health of the population, health examinations are becoming increasingly important. The existing physical examination result management system generally stays at the level of individual case management of the examinee, and only supports the recording and viewing of the examinee's health data. With the development of medical technology, the means of examination are becoming more and more abundant, the abnormal content of individual health conditions is more diverse and detailed, the types of data are many and complex, and intelligent big data analysis is difficult. Health status analysis relies on manual comparison by doctors, which is inefficient and unstable in quality. It is impossible to scientifically predict the development of individual health status, and it has not realized the analysis and application of regional health data, and it is impossible to provide a data basis and theoretical basis for future public health decisions. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides a method and device for processing health data of a population in a target area based on big data, so as to solve the problem that the existing physical examination result management system generally remains at the case management level of the examinee, cannot predict the development of individual health status, cannot realize the analysis and application of regional health data, and cannot provide a data basis and theoretical basis for future public health decision-making.

[0004] According to a first aspect, an embodiment of the present invention provides a method for processing health data of a population in a target area based on big data, the method comprising:

[0005] Obtaining consecutive batches of candidate physical examination reports of physical examinees in the target area, and extracting physical examination data of the physical examinees from the candidate physical examination reports; the candidate physical examination reports are physical examination reports generated within a preset time period;

[0006] Based on the constructed quality control rules, a model is established to pre-process the physical examination data, judge the rationality of the physical examination data, extract the reasonable physical examination data, and establish a model based on the quality control rules to analyze and process the reasonable physical examination data to generate personal health reports for each examinee;

[0007] Processing the personal health report based on historical trends and the degree of correlation between diagnosis and treatment to generate personal health guidance for the examinee;

[0008] Summarize all the personal health reports and personal health guidelines in the target area, conduct health analysis from three dimensions: population groups, physical examination institutions, and historical comparisons, and generate a population health report for the target area.

[0009] In combination with the first aspect, in a first implementation of the first aspect, obtaining consecutive batches of candidate physical examination reports of physical examinees in the target area and extracting physical examination data of the physical examinees from the candidate physical examination reports specifically includes:

[0010] Obtaining physical examination reports generated by physical examinees in the target area within a preset time period;

[0011] Determine the time interval for generating chronologically adjacent physical examination reports;

[0012] Use the most recent physical examination report as the baseline physical examination report;

[0013] Divide the baseline physical examination report into a candidate group, and determine the time interval between the physical examination report before and adjacent to the baseline physical examination report and the baseline physical examination report;

[0014] If it is determined that the time interval does not exceed the preset interval, the physical examination report before and adjacent to the baseline physical examination report will be used as the baseline physical examination report;

[0015] The medical examination reports in the candidate group are used as candidate medical examination reports;

[0016] The physical examination data of each physical examination item of the examinee is obtained from the candidate physical examination report.

[0017] In combination with the first aspect, in the second implementation of the first aspect, the quality control rule establishment model is constructed by the following steps:

[0018] Collect historical physical examination reports and historical medical records of historical physical examinees in the target area, and obtain the associated regions corresponding to each historical physical examinee based on the associated information of each historical physical examinee;

[0019] Obtain historical medical examination reports and historical medical records of historical medical examinees in the associated area;

[0020] Extract reasonable historical physical examination data from historical physical examination reports, and extract reasonable historical diagnosis and treatment data from historical medical records;

[0021] According to the mapping correlation trend between the historical physical examination data and the historical diagnosis and treatment data which are mutually related in chronological order, a mapping relationship between the historical physical examination data and the historical diagnosis and treatment data is established, and a quality control rule establishment model is constructed.

[0022] In combination with the second implementation of the first aspect, in the third implementation of the first aspect, the mapping association trend between the historical physical examination data and the historical diagnosis and treatment data that are mutually related in chronological order, establishing a mapping relationship between the historical physical examination data and the historical diagnosis and treatment data, and constructing a quality control rule establishment model specifically include:

[0023] Sort and group the historical physical examination data and historical diagnosis and treatment data of the historical physical examinees in chronological order, and obtain the local physical examination data and local diagnosis and treatment data corresponding to the historical physical examinees in several time intervals;

[0024] Determine the associated diagnosis and treatment data corresponding to each type of physical examination data in the historical physical examination data; each type of physical examination data has at least one type of associated diagnosis and treatment data;

[0025] Obtaining each physical examination extreme value point of each type of physical examination data in the local physical examination data of each time interval and each diagnosis and treatment extreme value point of each type of diagnosis and treatment data in the local diagnosis and treatment data;

[0026] The time interval between the physical examination extreme value points with the same extreme value characteristics is divided into a mapping analysis interval, and the associated diagnosis and treatment data corresponding to the physical examination extreme value points in the mapping analysis interval and the diagnosis and treatment extreme value points of the associated diagnosis and treatment data are determined; the same extreme value features are the same type of maximum value points or minimum value points located in the same time interval and adjacent;

[0027] The diagnosis and treatment extreme value points exceeding the first threshold and not exceeding the second threshold within the mapping analysis interval are taken as associated data, and the data mean of all associated data is determined; the first threshold is greater than the second threshold;

[0028] Determine the mapping correlation trend of the physical examination data corresponding to the type of physical examination data at the physical examination extreme point according to the number of associated data, the number of associated diagnosis and treatment data, the data mean of the associated data, and the data value of the physical examination extreme point;

[0029] Summarize and map related trends, establish mapping relationships between interrelated historical physical examination data and historical diagnosis and treatment data, and build quality control rule establishment models.

[0030] In combination with the first aspect, in a fourth implementation of the first aspect, the processing of the personal health report based on the historical trend and the degree of association between diagnosis and treatment to generate personal health guidance opinions for the examinee specifically includes:

[0031] Obtain the historical change area of ​​each physical examination data in the personal health report, and determine whether the historical change trend is within the preset change range to obtain the first health guidance;

[0032] When it is determined that the historical change trend of the physical examination data is not within the preset change range, the degree of correlation between the single diagnosis and treatment of the physical examination data is obtained, and a second health guidance opinion is generated according to the degree of correlation between the single diagnosis and treatment; the degree of correlation between the single diagnosis and treatment includes abnormal results, diagnostic criteria for diseases, treatment recommendations and preventive measures;

[0033] The first health guidance opinion and the second health guidance opinion are summarized to generate the personal health guidance opinion of the examinee.

[0034] In combination with the first aspect, in a fifth implementation of the first aspect, the aggregation of all the personal health reports and the personal health guidance opinions in the target area, and the health analysis from three dimensions of population groups, physical examination institutions, and historical comparisons to generate a population health report for the target area specifically includes:

[0035] Summarize all the personal health reports and personal health guidance opinions in the target area;

[0036] Compare all the personal health reports and personal health guidance opinions in the target area by population to obtain a first population health report;

[0037] Tracing the source of the physical examination report, determining the physical examination institution corresponding to the physical examination report, and classifying and comparing all the personal health reports and personal health guidance opinions in the target area between different physical examination institutions to obtain a second population health report;

[0038] A historical comparison is performed between all the personal health reports in the target area and the historical physical examination data obtained in the target area to obtain a health report for a third group of people.

[0039] In combination with the third implementation of the first aspect, in a sixth implementation of the first aspect, the method further includes:

[0040] Based on the examinee's personal health report, personal health guidance, and the mapping association trend between various types of physical examination data and corresponding associated diagnosis and treatment data in historical physical examination data, the examinee's predicted physical examination items are generated.

[0041] In a second aspect, an embodiment of the present invention further provides a device for predicting a treatment plan for a patient's entire course of illness, the device comprising:

[0042] A data acquisition module, used to acquire consecutive batches of candidate physical examination reports of physical examinees in a target area, and extract physical examination data of the physical examinees from the candidate physical examination reports; the candidate physical examination reports are physical examination reports generated within a preset time period;

[0043] The data processing module is used to establish a model based on the constructed quality control rules to pre-process the physical examination data, judge the rationality of the physical examination data, extract the reasonable physical examination data, and establish a model based on the quality control rules to analyze and process the reasonable physical examination data, and generate a personal health report for each examinee;

[0044] A case analysis module, for processing the personal health report based on historical trends and the degree of correlation between diagnosis and treatment, and generating personal health guidance opinions for the examinee;

[0045] The regional summary module is used to summarize all the personal health reports and personal health guidelines in the target area, and conduct health analysis from three dimensions: population groups, physical examination institutions, and historical comparisons to generate a population health report for the target area.

[0046] In a third aspect, an embodiment of the present invention further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of processing health data of a population in a target area based on big data as described in any one of the above are implemented.

[0047] In a fourth aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of processing health data of a population in a target area based on big data as described in any of the above.

[0048] The method and device for processing health data of a population in a target area based on big data provided by the present invention establish a model based on quality control rules to generate a personal health report of each examinee, and then process the personal health report based on historical trends and the degree of association between diagnosis and treatment to generate personal health guidance opinions for the examinee, summarize all personal health reports and personal health guidance opinions in the target area, and perform health analysis from three dimensions: population group, physical examination institution, and historical comparison to generate a health report for the population in the target area, and then standardize and normalize the physical examination data of the examinee to make the health analysis based on big data more accurate, and can more effectively form health data analysis of individual cases and target areas, so that subsequent health management and measure formulation are more targeted, and can establish a health management closed loop of the entire process of physical examination-analysis-intervention-treatment-follow-up, so that residents can more intuitively grasp their own health status, public health managers can more clearly grasp the health status of the population in the target area, and public health managers can more accurately grasp the health status of the population in the target area, providing a more accurate data basis and a clearer work direction for the development of public health services, and through the follow-up management of physical examination results, potential health problems can be discovered in time and intervened in time to reduce the high cost of treatment in the later stage and save medical funds. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The features and advantages of the present invention will be more clearly understood by referring to the accompanying drawings, which are schematic and should not be construed as limiting the present invention in any way. In the accompanying drawings:

[0050] Figure 1 A schematic diagram of the process of the method for processing health data of a population in a target area based on big data provided by the present invention is shown;

[0051] Figure 2The specific flow chart of step S10 in the method for processing health data of a population in a target area based on big data provided by the present invention is shown;

[0052] Figure 3 The schematic diagram of the structure of the target area population health data processing device based on big data provided by the present invention is shown;

[0053] Figure 4 A structural schematic diagram of an electronic device provided by the present invention is shown. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0055] At present, people's pursuit and demand for health are growing day by day. As an important means to protect the health of the population, health examinations are becoming increasingly important. The existing physical examination result management system generally stays at the level of individual case management of the examinee, and only supports the recording and viewing of the examinee's health data. With the development of medical technology, the means of examination are becoming more and more abundant, the abnormal content of individual health conditions is more diverse and detailed, the types of data are many and complex, and intelligent big data analysis is difficult. Health status analysis relies on manual comparison by doctors, which is inefficient and unstable in quality. It is impossible to scientifically predict the development of individual health status, and it has not realized the analysis and application of regional health data, and it is impossible to provide a data basis and theoretical basis for future public health decisions.

[0056] The method for processing health data of the target area population based on big data provided in this specification can be applied to electronic devices with big data processing capabilities. The electronic device may include a notebook, a desktop computer, a smart phone, a smart wearable device (virtual reality glasses, smart watches, etc.), a tablet computer, etc. Of course, the method for processing health data of the target area population based on big data provided in this specification can also be applied to applications running in the above-mentioned electronic devices. For example, the message display method can be applied to a browser with big data processing capabilities, and can also be applied to immediately corresponding big data processing software.

[0057] Figure 1 is a flow chart of a method for processing health data of a population in a target area based on big data according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0058] S10: Obtain candidate physical examination reports of consecutive batches of physical examination subjects in the target area, and extract physical examination data of the physical examination subjects from the candidate physical examination reports.

[0059] The scope of the target area can be configured and determined by the user who applies the method, such as various public health institutions. For example, the scope of the target area can be the entire city or the entire rural area, which is used to manage and analyze the physical examination quality of the corresponding urban population or rural population. The scope of the target area can also be a certain administrative area or some adjacent administrative areas. The scope of the target area can also be down to the control area, community, or even the grid unit in the community. In this embodiment, there is no restriction on the specific scope of the target area.

[0060] Public health institutions in some areas, such as primary medical institutions, regularly organize free health check-up programs. For these areas, public health institutions and examinees may retain physical examination reports corresponding to the examinees. Considering that if the relevant physical examination data collection mechanism is not perfect, or the corresponding physical examination data cannot be collected, it will lead to poor data integrity, or due to multiple collections and repeated collections, resulting in high data inconsistency and redundancy, in this embodiment, continuous batches of candidate physical examination reports of the examinees are obtained, and continuous batches of candidate physical examination reports can ensure the integrity and continuity of the physical examination data corresponding to the examinees.

[0061] Among them, the candidate physical examination report is a physical examination report within a preset time period, such as calculating from the current time and moving forward for a period of time to form the above-mentioned preset time period. The length of the moving time can still be configured and determined by users who apply this method, such as various public health institutions.

[0062] To give a specific example, for the examinee A in the target area, a total of 8 physical examination reports are obtained. The examinee A undergoes a routine physical examination every year. If the preset time period is set to the past five years, then physical examination reports 1, 2, 3, 4 and 5 of the 8 physical examination reports are physical examination reports within the preset time period. Other physical examination reports are not considered because they are too old.

[0063] The physical examination report contains the required physical examination data. In this embodiment, various items of physical examination data will be extracted therefrom, including but not limited to: the name of the examinee, the examinee's place of residence, the examinee's registered residence, physical examination items, physical examination content and other multi-dimensional data. The physical examination data contains demographic information, physical sign information, health information, personal special circumstances and other information.

[0064] S20: Based on the constructed quality control rules, a model is established to pre-process the physical examination data, judge the rationality of the physical examination data, extract the reasonable physical examination data, and analyze and process the reasonable physical examination data based on the quality control rules to generate a personal health report for each examinee. This step can also further assist in judging the correctness of the physical examination report corresponding to the physical examination data.

[0065] In this embodiment, rationality refers to the ability to fully and correctly reflect the corresponding physical examination items of the examinee. If there are omissions of key items in the physical examination report, data exceeding the value range, input character length exceeding the standard, input character type not meeting the requirements, etc., the physical examination data is unreasonable. Using unreasonable physical examination data as big data for health data processing will obviously result in inaccurate results.

[0066] In this embodiment, preset standard requirements are adopted for all physical examination items, and a health examination quality control intelligent verification rule library, that is, a quality control rule establishment model, is established, including the examinee's name, number, examination date, responsible doctor, symptoms, general condition, lifestyle, organ function, physical examination information, auxiliary examinations, existing major problems, hospitalization, major medication, health evaluation, health guidance, risk factor control, etc., an intelligent verification program is set up, and rule verification and associated logic settings for integrity, effectiveness, standardization, and consistency are established.

[0067] In this way, intelligent calculations can be performed according to the preset specifications set according to the physical examination quality control specifications, aiming to ensure the rationality of the physical examination data (including accuracy and reliability). Through pre-set rules, the data in the physical examination data input process can be self-checked, such as the value range, input character length, input character type, etc. If the preset rules are violated, the quality control rule model will have an error warning prompt, which will promptly alert the relevant personnel to make modifications or provide feedback to the relevant personnel if there are problems with the physical examination report corresponding to the physical examination data, further strengthening the rigor of physical examination quality control and laying the foundation for subsequent data analysis and calculations.

[0068] By building a model based on quality control rules, it can also determine whether there are missing items in the physical examination report, thereby realizing self-inspection protection of the physical examination items. By building a model based on quality control rules, feedback is provided to public health institutions, private physical examination institutions, etc., and these institutions are assisted in guiding the optimization of physical examination items, setting mandatory items, mandatory content, scope and association relationship rules, and self-checking and troubleshooting of missing items in the physical examination report. Through this mechanism, it can ensure that key information is fully collected during the physical examination process to avoid inaccurate health assessments caused by missing or incorrect information. For example, in the smoking situation, "quit smoking" is selected, and "start smoking age" and "quit smoking age" are mandatory items, and "never smoked" cannot be selected, which can effectively reduce the occurrence of missing items, wrong items, etc.

[0069] S30. Process the personal health report based on historical trends and the degree of correlation between diagnosis and treatment, and generate personal health guidance for the examinee.

[0070] For example, by displaying and comparing the historical trends of all physical examination indicators such as "weight" and "hemoglobin", and indicating whether they are within the normal range, it can intuitively reflect the changes in the examination values ​​of the project over the years, help discover the progress of abnormal indicators of the examinee's body, and provide direction and data basis for health status prediction. Intelligent analysis of the indicator results in the physical examination report, identification of abnormal indicators and possible health problems, and intelligent interpretation of the indicators and examination items in the physical examination report, mainly for the content of the examination items, abnormal causes, definition of the disease, common clinical manifestations and other dimensions, and provide professional health interpretation and suggestions.

[0071] The degree of correlation between diagnosis and treatment is based on the various common abnormal results, diagnostic criteria, treatment recommendations and preventive measures for each disease. When the personal health report indicates that the examinee has abnormal indicators and possible health problems, the examinee can be given personalized management suggestions for improving health risk factors based on the physical examination results and personal health status, according to the degree of correlation between diagnosis and treatment. This includes health advice and guidance for the examinee's specific abnormal results, including but not limited to diet, exercise plans, living habits, etc., to help the examinee reduce health risks and improve the quality of life, so that the examinee can have a quantitative understanding of their own health risk status and obtain a set of practical health action plans. Such personal health guidance makes the interpretation of the physical examination report not limited to the simple presentation of indicator results, but can also provide in-depth health guidance and help for the examinee.

[0072] Specifically, the step includes:

[0073] Obtain the historical change areas of various physical examination data in personal health reports, and determine whether the historical change trend is within the preset change range to obtain the first health guidance;

[0074] When it is determined that the historical change trend of the physical examination data is not within the preset change range, the single diagnosis and treatment correlation degree of the physical examination data is obtained, and the second health guidance opinion is generated according to the single diagnosis and treatment correlation degree. In this embodiment, the single diagnosis and treatment correlation degree includes abnormal results, diagnostic criteria of the disease, treatment suggestions and preventive measures;

[0075] The first health guidance opinion and the second health guidance opinion are summarized to generate the personal health guidance opinion of the examinee.

[0076] S40, summarizing all the personal health reports and personal health guidance opinions in the target area, and performing health analysis from three dimensions of population groups, physical examination institutions and historical comparison to generate a population health report for the target area.

[0077] After summarizing the personal health reports and personal health guidance opinions of all physical examination participants in the target area, highly customized, fine-grained, and multi-dimensional data analysis can be performed on the target area, and abnormal results in the area can be deeply mined. A variety of screening conditions and a combination of factors can be provided, such as physical examination type, physical examination package, gender, age, street, insurance type, physical examination indicators, physical examination items, physical examination positive indicator results and other factors. Users can make highly liberal and highly customized selections of statistical conditions to generate the results they want to count, effectively and quickly analyze the results, provide data support for development decisions to promote health management and services, and help managers accurately take preventive and control measures to reduce the risk of disease.

[0078] Specifically, the step includes:

[0079] Compare all personal health reports and personal health guidance opinions in the target area by population to obtain the first population health report. For example, compare the physical examination data of the entire target area by population, and count the distribution of physical examination results of physical examination indicators among various populations to help provide direction for future health guidance. For example, by comparing the proportion of men and women in body mass index (BMI), it is found that men have a higher incidence of obesity. In this case, weight management publicity can be carried out in areas or scenes with more men to improve publicity efficiency and effectiveness.

[0080] The physical examination report is traced to determine the physical examination institution that generated the physical examination report, and all personal health reports and personal health guidance opinions in the target area are classified and compared among different physical examination institutions to obtain the second population health report. For example, the physical examination results of the entire target area are classified and compared among institutions, and the classification proportion of the physical examination results of various physical examination indicators of each physical examination institution is counted to help the physical examination institution understand whether the medical equipment used for physical examination in the institution is biased or whether the data dispersion ratio meets the calculation rules. For example, by counting the proportion and average value of the population with increased "weight" indicators in a certain institution in the statistical area, the reliability of the physical examination equipment of the physical examination institution can be understood and the quality of physical examination can be improved.

[0081] All personal health reports in the target area are compared with the historical physical examination data obtained in the target area to obtain a third-party population health report. By comparing the physical examination data with the historical data, the incidence of diseases can be accurately predicted to provide support for relevant decisions. For example, if the incidence of thyroid diseases in the physical examination results in the region shows an upward trend compared with the same period in history, it can be recommended to conduct free thyroid disease screening in the region to promote early detection and treatment of diseases and improve the health level of the population.

[0082] The method for processing health data of a population in a target area based on big data provided by the present invention establishes a model based on quality control rules to generate a personal health report of each examinee, then processes the personal health report based on historical trends and the degree of association between diagnosis and treatment, generates personal health guidance opinions for the examinee, summarizes all personal health reports and personal health guidance opinions in the target area, and performs health analysis from three dimensions: population group, physical examination institution and historical comparison, to generate a health report for the population in the target area, and then standardizes and normalizes the individual physical examination data of the examinee, so that the health analysis based on big data is more accurate, and the health data analysis of individual cases and the target area can be formed more effectively, so that the subsequent health management and measure formulation are more targeted, and a health management closed loop of the whole process of physical examination-analysis-intervention-treatment-follow-up can be established, so that residents can more intuitively grasp their own health status, public health managers can more clearly grasp the health status of the population in the target area, and public health managers can more accurately grasp the health status of the population in the target area, providing a more accurate data basis and a clearer work direction for the development of public health services, and through the follow-up management of the physical examination results, potential health problems can be discovered in time and intervened in time to reduce the high treatment costs in the later stage and save medical funds.

[0083] Combine the following Figure 2 The method for processing health data of a population in a target area based on big data of the present invention is described as follows: Figure 2 As shown, step S10 specifically includes:

[0084] S11, obtaining physical examination reports generated by examinees in the target area within a preset time period.

[0085] After the user sets the scope of the target area, it connects with the physical examination data management systems of primary medical institutions, hospitals, professional physical examination institutions, etc., connects with public health archive information or imports a list to obtain relevant data. After that, the data acquisition scope is determined to be the physical examination reports of the examinees within the preset time period.

[0086] S12, determine the time interval between the physical examination reports that are adjacent in the time sequence. For example, for the physical examination person B in the target area, there are 5 physical examination reports in the preset time period, which are physical examination reports 1, 2, 3, 4 and 5 in the time sequence of generation. The time intervals between adjacent physical examination reports (physical examination reports 1 and 2, physical examination reports 2 and 3, etc.) are obtained in sequence. In addition to the index data of various physical examination items, the physical examination report also records the physical examination date of the physical examination person. The time interval is the difference between the physical examination dates of adjacent physical examination reports.

[0087] S13. Use the most recent physical examination report as the baseline physical examination report.

[0088] S14. Classify the baseline physical examination report into a candidate group, and determine the time interval between the physical examination report before and adjacent to the baseline physical examination report and the baseline physical examination report.

[0089] S15. When it is determined that the time interval does not exceed the preset interval, the physical examination report before and adjacent to the benchmark physical examination report is used as the benchmark physical examination report, and the loop processing from step S14 to step S15 is performed until all physical examination reports of the examinee within the preset time period are traversed and processed.

[0090] S16. Use the physical examination reports in the candidate group as candidate physical examination reports.

[0091] Statistics are collected from the most recent physical examination report, and this physical examination report is used as a judgment basis to be divided into the above-mentioned candidate group. After that, it is determined whether the time interval between the physical examination report before the most recent physical examination report and adjacent to the most recent physical examination report, i.e. the second most recent physical examination report, and the most recent physical examination report exceeds the preset interval. If not, the second most recent physical examination report is also included in the subsequent selection, and the second most recent physical examination report is used as a new judgment basis to determine whether the third most recent physical examination report can be divided into the candidate group. This process is repeated in a cycle until all physical examination reports of the examinees within the preset time period are traversed and processed, and the candidate physical examination report can be determined from the candidate reports.

[0092] S17. Submit the physical examination data of each physical examination item of the examinee from the candidate physical examination report.

[0093] At present, various types of physical examination reports are presented in the form of paper physical examination books or digital physical examination information. In this embodiment, for the paper physical examination book, text recognition such as OCR recognition is used to separate the text content according to the name of the examinee, the examinee's place of residence, the examinee's registered residence, physical examination items, physical examination content, etc., and structured processing is performed to form structured physical examination data. If the physical examination report is presented in the form of digital physical examination information such as an electronic physical examination report, the above-mentioned physical examination data is extracted from the electronic physical examination report accordingly.

[0094] In this application, the quality control rule establishment model is trained in the following way:

[0095] A10. Collect historical physical examination reports and historical medical records of historical physical examinees in the target area, and obtain the associated regions corresponding to each historical physical examinee based on the associated information of each historical physical examinee.

[0096] In this embodiment, the associated information includes the examinee's name, age, gender, registered residence, permanent residence, current residence, and other information.

[0097] A20. Obtain historical physical examination reports and historical medical records data of historical physical examination subjects in the related areas.

[0098] In this embodiment, the historical medical record data includes information in multiple dimensions, such as symptom data, physical sign data, drug allergy, personal special circumstances, work and rest time, chief complaint information, medical history information, diagnosis and treatment opinions, medication information, etc. The historical medical record information can reflect the various relevant data generated by the examinee during the treatment, and can reflect the symptoms, physical signs, medication data, etc. of the examinee during the previous treatments. The historical medical record data can be obtained by connecting with the systems of various medical institutions, and no restriction is imposed on the specific method of obtaining the historical medical record data.

[0099] It should be noted that the historical physical examinees in the target area can be the current physical examinees or other physical examinees in the target area. Based on the related information, people who are similar to the historical physical examinees in terms of blood relationship, living habits, folk customs, etc. can be determined. Therefore, the historical physical examinees in the related areas are the above-mentioned people who are similar to the historical physical examinees in terms of blood relationship, living habits, folk customs, etc.

[0100] A30. Extract reasonable historical physical examination data from historical physical examination reports, and extract reasonable historical diagnosis and treatment data from historical medical records. For more information on how to extract structured historical physical examination data from historical physical examination reports and further extract reasonable historical physical examination data, see Figure 1 The step S10 is not described in detail here. Similarly, since the medical record report can be a paper medical record book or a digital medical record information, the method of extracting structured historical diagnosis and treatment data from the historical medical record report and further extracting reasonable historical diagnosis and treatment data is similar to the corresponding processing method of the historical medical record report, and is not described in detail here.

[0101] A40. According to the mapping correlation trend between the historical physical examination data and the historical diagnosis and treatment data which are mutually related in chronological order, establish the mapping relationship between the historical physical examination data and the historical diagnosis and treatment data, and construct the quality control rule establishment model.

[0102] Based on the quality control rules constructed in this way, the model generates a personal health report. During the physical examination, the doctor can view the historical examination items and results of the examinee according to the personal health report, and make corresponding modifications to the relevant content of the departmental examination. The doctor can view the physical examination data (results) displayed in the recent physical examination reports of the examinee. For example, by clicking "View historical data", the doctor can view more physical examination results in the past, which is convenient for the doctor to understand whether the examinee has abnormalities in the previous physical examinations during the examination process, and further improve the accuracy and effectiveness of the doctor's diagnosis of the results of this physical examination. For example: if the doctor finds that the examinee has a cyst on the left liver in the history, he can further check the changes in the cyst, etc., so as to check the progression of the disease in a timely and efficient manner.

[0103] During the physical examination, the model is established through quality control rules to pre-process the physical examination data of the examinee, and the physical examination progress of the examinee can be managed accordingly. Based on the quality control rules, statistical analysis can be performed on the items that have not been examined during the physical examination of the examinee, to prevent the examinee from missing or abandoning the examination but not being discovered in time, and to improve the integrity of the physical examination. For example: there are 10 items in this physical examination, and a physical examinee only checked 8 items and left. At this time, the physical examination institution will notify the examinee to continue the examination through this function phone.

[0104] More specifically, step A40 specifically includes:

[0105] A41. Sort and group the historical physical examination data and historical diagnosis and treatment data of the historical physical examinees in chronological order, and obtain the local physical examination data and local diagnosis and treatment data corresponding to the historical physical examinees in several time intervals. It can be understood that in each time interval, the historical physical examinees have corresponding local physical examination data and local diagnosis and treatment data. When the historical physical examinee does not undergo a physical examination or go to a medical institution for treatment within a certain time interval, correspondingly, there will be no local physical examination data or local diagnosis and treatment data corresponding to the historical physical examinee in this time interval.

[0106] In this embodiment, the length of each time interval is equal to facilitate data processing.

[0107] A42. Determine the associated diagnosis and treatment data corresponding to each type of physical examination data in the historical physical examination data. In this embodiment, each type of physical examination data has at least one type of associated diagnosis and treatment data. The historical diagnosis and treatment data includes several types of diagnosis and treatment data. Some of the diagnosis and treatment data may be associated diagnosis and treatment data of at least one type of physical examination data. For example, diagnosis and treatment data A may be associated diagnosis and treatment data of two types of data, physical examination data A and B. Therefore, there is overlap between the associated diagnosis and treatment data corresponding to each type of different types of physical examination data.

[0108] A43. Obtain each physical examination extreme value point of each type of physical examination data in the local physical examination data of each time interval and each diagnosis and treatment extreme value point of each type of diagnosis and treatment data in the local diagnosis and treatment data.

[0109] A44. Divide the time interval between the physical examination extreme points with the same extreme value characteristics into a mapping analysis interval, and determine the associated diagnosis and treatment data corresponding to the physical examination extreme points in the mapping analysis interval and the diagnosis and treatment extreme points of the associated diagnosis and treatment data. In this embodiment, the same extreme value characteristics are the same type of maximum points or minimum points located in the same time interval and adjacent to each other.

[0110] A45. The diagnosis and treatment extreme value points that exceed the first threshold and do not exceed the second threshold within the mapping analysis interval are taken as associated data, and the data mean of all associated data is determined. Among them, the first threshold is greater than the second threshold. It can be understood that the first threshold is the maximum value and the second threshold is the minimum value. Starting from the local, we start to judge the relationship between a certain type of physical examination data and diagnosis and treatment data, thereby improving the accuracy of data detection and data analysis after the quality control rule model is established.

[0111] At the same time, there may be a mutual influence relationship between physical examination data and diagnosis and treatment data. Therefore, it is also necessary to obtain the mapping correlation degree between any two of the above data. This can not only improve the accuracy of quality control rules when establishing models to process big data, but also better learn the influence between data and improve the representativeness of subsequent personal health reports for physical examinees.

[0112] In this embodiment, what type of associated diagnosis and treatment data each type of physical examination data corresponds to can be configured by the user using the method, and can be specifically determined in combination with expert experience, etc. when the user performs the configuration.

[0113] A46. Determine the mapping correlation trend of the type of physical examination data corresponding to the physical examination extreme point based on the number of associated data, the number of associated diagnosis and treatment data, the data mean of the associated data, and the data value of the physical examination extreme point.

[0114] Extreme points are divided into maximum points and minimum points. Therefore, when calculating the mapping association trend, first determine the ratio between the number of associated data and the number of associated medical data, and then multiply them by the data mean and the data value of a certain maximum physical examination extreme point, respectively, to obtain the first mapping association trend corresponding to each maximum physical examination extreme point. In the same way, obtain the second mapping association trend corresponding to each minimum physical examination extreme point. Collect all the first mapping association trends and second mapping association trends of the physical examination extreme points of a certain type of physical examination data, that is, the mapping association trend of the physical examination extreme points can be determined, that is, the mapping association trend between the type of physical examination data and its associated associated medical data.

[0115] A47. Summarize and map related trends, establish a mapping relationship between interrelated historical physical examination data and historical diagnosis and treatment data, and construct a quality control rule establishment model.

[0116] Currently, most of the free health check-up programs are routine check-ups. With the improvement of people's health awareness, the free health check-up programs no longer meet the requirements of self-management of the target population. The rigid conditions such as the equipment conditions of primary medical institutions in various regions, the time and location of health check-ups, etc., have also been limited, resulting in a decrease in the enthusiasm and initiative of some residents for health check-ups. The promotion and work of health check-ups cannot be carried out smoothly, and it is impossible to provide residents with comprehensive health services and improve the health quality level of residents.

[0117] While improving the conditions of medical institutions, it is urgently necessary to improve and enrich the content of health examinations, actively encourage residents in all regions to participate in health examinations, increase the health examination rate, and ultimately provide residents with continuous and comprehensive health services to meet the diversified needs of residents for health examinations.

[0118] In response to the ever-increasing demands for residents' health management, it is still necessary to further carry out refined management of residents' health records to better meet the diverse needs of the people.

[0119] In this application, after obtaining the examinee's personal health report and personal health guidance, it is also possible to generate the examinee's predicted physical examination items based on the mapping association trends between various types of physical examination data and corresponding related diagnosis and treatment data in the historical physical examination data. Different from conventional physical examination items, the predicted physical examination items include predicted personalized physical examination items for each examinee. For example, if the personal health report and personal health guidance generated based on the examinee A's most recent batch of physical examination reports indicate that there may be problems with his body mass index, then the predicted physical examination items will also include related test items that may not be included in the conventional items, thereby realizing personalized customization of the examinee's physical examination items "N+M (M≥1)" in future physical examinations.

[0120] The following describes a target area population health data processing device based on big data provided by an embodiment of the present invention. The target area population health data processing device based on big data described below and the target area population health data processing method based on big data described above can be referenced to each other.

[0121] Figure 3 is a schematic diagram of the structure of a target area population health data processing device based on big data according to an embodiment of the present invention. Figure 3 As shown, the device comprises:

[0122] S11. Obtain candidate physical examination reports of consecutive batches of physical examination subjects in the target area, and extract physical examination data of the physical examination subjects from the candidate physical examination reports.

[0123] The scope of the target area can be configured and determined by the user who applies the method, such as various public health institutions. For example, the scope of the target area can be the entire city or the entire rural area, which is used to manage and analyze the physical examination quality of the corresponding urban population or farm population. The scope of the target area can also be a certain administrative area or some adjacent administrative areas. The scope of the target area can also be down to the control area, community, or even the grid unit in the community. In this embodiment, there is no restriction on the specific scope of the target area.

[0124] Public health institutions in some areas, such as primary medical institutions, regularly organize free health check-up programs. For these areas, public health institutions and examinees may retain physical examination reports corresponding to the examinees. Considering that if the relevant physical examination data collection mechanism is not perfect, or the corresponding physical examination data cannot be collected, it will lead to poor data integrity, or due to multiple collections and repeated collections, resulting in high data inconsistency and redundancy, in this embodiment, continuous batches of candidate physical examination reports of the examinees are obtained, and continuous batches of candidate physical examination reports can ensure the integrity and continuity of the physical examination data corresponding to the examinees.

[0125] Among them, the candidate physical examination report is a physical examination report within a preset time period, such as calculating from the current time and moving forward for a period of time to form the above-mentioned preset time period. The length of the moving time can still be configured and determined by users who apply this method, such as various public health institutions.

[0126] To give a specific example, for the examinee A in the target area, a total of 8 physical examination reports are obtained. The examinee A undergoes a routine physical examination every year. If the preset time period is set to the past five years, then physical examination reports 1, 2, 3, 4 and 5 of the 8 physical examination reports are physical examination reports within the preset time period. Other physical examination reports are not considered because they are too old.

[0127] The physical examination report contains the required physical examination data. In this embodiment, various items of physical examination data will be extracted therefrom, including but not limited to: the name of the examinee, the examinee's place of residence, the examinee's registered residence, physical examination items, physical examination content and other multi-dimensional data. The physical examination data contains demographic information, physical sign information, health information, personal special circumstances and other information.

[0128] S20: Based on the constructed quality control rules, a model is established to pre-process the physical examination data, judge the rationality of the physical examination data, extract the reasonable physical examination data, and analyze and process the reasonable physical examination data based on the quality control rules to generate a personal health report for each examinee. This step can also further assist in judging the correctness of the physical examination report corresponding to the physical examination data.

[0129] In this embodiment, rationality refers to the ability to fully and correctly reflect the corresponding physical examination items of the examinee. If there are omissions of key items in the physical examination report, data exceeding the value range, input character length exceeding the standard, input character type not meeting the requirements, etc., the physical examination data is unreasonable. Using unreasonable physical examination data as big data for health data processing will obviously result in inaccurate results.

[0130] In this embodiment, preset standard requirements are adopted for all physical examination items, and a health examination quality control intelligent verification rule library, that is, a quality control rule establishment model, is established, including the examinee's name, number, examination date, responsible doctor, symptoms, general condition, lifestyle, organ function, physical examination information, auxiliary examinations, existing major problems, hospitalization, major medication, health evaluation, health guidance, risk factor control, etc., an intelligent verification program is set up, and rule verification and associated logic settings for integrity, effectiveness, standardization, and consistency are established.

[0131] In this way, intelligent calculations can be performed according to the preset specifications set according to the physical examination quality control specifications, aiming to ensure the rationality of the physical examination data (including accuracy and reliability). Through pre-set rules, the data in the physical examination data input process can be self-checked, such as the value range, input character length, input character type, etc. If the preset rules are violated, the quality control rule model will have an error warning prompt, which will promptly alert the relevant personnel to make modifications or provide feedback to the relevant personnel if there are problems with the physical examination report corresponding to the physical examination data, further strengthening the rigor of physical examination quality control and laying the foundation for subsequent data analysis and calculations.

[0132] By building a model based on quality control rules, it can also determine whether there are missing items in the physical examination report, thereby realizing self-inspection protection of the physical examination items. By building a model based on quality control rules, feedback is provided to public health institutions, private physical examination institutions, etc., and these institutions are assisted in guiding the optimization of physical examination items, setting mandatory items, mandatory content, scope and association relationship rules, and self-checking and troubleshooting of missing items in the physical examination report. Through this mechanism, it can ensure that key information is fully collected during the physical examination process to avoid inaccurate health assessments caused by missing or incorrect information. For example, in the smoking situation, "quit smoking" is selected, and "start smoking age" and "quit smoking age" are mandatory items, and "never smoked" cannot be selected, which can effectively reduce the occurrence of missing items, wrong items, etc.

[0133] S30. Process the personal health report based on historical trends and the degree of correlation between diagnosis and treatment, and generate personal health guidance for the examinee.

[0134] For example, by displaying and comparing the historical trends of all physical examination indicators such as "weight" and "hemoglobin", and indicating whether they are within the normal range, it can intuitively reflect the changes in the examination values ​​of the project over the years, help discover the progress of abnormal indicators of the examinee's body, and provide direction and data basis for health status prediction. Intelligent analysis of the indicator results in the physical examination report, identification of abnormal indicators and possible health problems, and intelligent interpretation of the indicators and examination items in the physical examination report, mainly for the content of the examination items, abnormal causes, definition of the disease, common clinical manifestations and other dimensions, and provide professional health interpretation and suggestions.

[0135] The degree of correlation between diagnosis and treatment is based on the various common abnormal results, diagnostic criteria, treatment recommendations and preventive measures for each disease. When the personal health report indicates that the examinee has abnormal indicators and possible health problems, the examinee can be given personalized management suggestions for improving health risk factors based on the physical examination results and personal health status, according to the degree of correlation between diagnosis and treatment. This includes health advice and guidance for the examinee's specific abnormal results, including but not limited to diet, exercise plans, living habits, etc., to help the examinee reduce health risks and improve the quality of life, so that the examinee can have a quantitative understanding of their own health risk status and obtain a set of practical health action plans. Such personal health guidance makes the interpretation of the physical examination report not limited to the simple presentation of indicator results, but can also provide in-depth health guidance and help for the examinee.

[0136] S40, summarizing all the personal health reports and personal health guidance opinions in the target area, and performing health analysis from three dimensions of population groups, physical examination institutions and historical comparison to generate a population health report for the target area.

[0137] After summarizing the personal health reports and personal health guidance opinions of all physical examination participants in the target area, highly customized, fine-grained, and multi-dimensional data analysis can be performed on the target area, and abnormal results in the area can be deeply mined. A variety of screening conditions and a combination of factors can be provided, such as physical examination type, physical examination package, gender, age, street, insurance type, physical examination indicators, physical examination items, physical examination positive indicator results and other factors. Doctors can make highly liberal and highly customized selections of statistical conditions to generate the desired statistical results, effectively and quickly analyze the results, provide data support for development decisions to promote health management and services, and help managers accurately take preventive and control measures to reduce the risk of disease.

[0138] The target area population health data processing device provided by the present invention based on big data establishes a model based on quality control rules to generate personal health reports of each examinee, and then processes the personal health reports based on historical trends and the degree of diagnosis and treatment correlation to generate personal health guidance opinions for the examinee, summarizes all personal health reports and personal health guidance opinions in the target area, and performs health analysis from three dimensions of population groups, physical examination institutions and historical comparisons to generate a population health report for the target area, and then standardizes and normalizes the individual physical examination data of the examinee to make the health analysis based on big data more accurate, and can more effectively form health data analysis of individual cases and target areas, so that subsequent health management and measure formulation are more targeted, and can establish a health management closed loop of the whole process of physical examination-analysis-intervention-treatment-follow-up, so that residents can more intuitively grasp their own health status, and public health managers can more clearly grasp the health status of the population in the target area, and public health managers can more accurately grasp the health status of the population in the target area, providing a more accurate data basis and a clearer work direction for the development of public health services, and through the follow-up management of physical examination results, potential health problems can be discovered in time and intervened in time to reduce the high treatment costs in the later stage and save medical funds.

[0139] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor 410 (processor), a communication interface 420 (Communications Interface), a memory 430 (memory) and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic command in the memory 430 to execute the target area population health data processing method based on big data, the method comprising:

[0140] Obtaining consecutive batches of candidate physical examination reports of physical examinees in the target area, and extracting physical examination data of the physical examinees from the candidate physical examination reports; the candidate physical examination reports are physical examination reports generated within a preset time period;

[0141] Based on the constructed quality control rules, a model is established to pre-process the physical examination data, judge the rationality of the physical examination data, extract the reasonable physical examination data, and establish a model based on the quality control rules to analyze and process the reasonable physical examination data to generate personal health reports for each examinee;

[0142] Processing the personal health report based on historical trends and the degree of correlation between diagnosis and treatment to generate personal health guidance for the examinee;

[0143] Summarize all the personal health reports and personal health guidelines in the target area, conduct health analysis from three dimensions: population groups, physical examination institutions, and historical comparisons, and generate a population health report for the target area.

[0144] In addition, the logic commands in the above-mentioned memory 430 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 medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software medium, and the computer software medium is stored in a storage medium, including several commands to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. 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.

[0145] On the other hand, the present invention further provides a computer program medium, the computer program medium includes a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer can execute the target area population health data processing method based on big data provided by the above methods, the method comprising:

[0146] Obtaining consecutive batches of candidate physical examination reports of physical examinees in the target area, and extracting physical examination data of the physical examinees from the candidate physical examination reports; the candidate physical examination reports are physical examination reports generated within a preset time period;

[0147] Based on the constructed quality control rules, a model is established to pre-process the physical examination data, judge the rationality of the physical examination data, extract the reasonable physical examination data, and establish a model based on the quality control rules to analyze and process the reasonable physical examination data to generate personal health reports for each examinee;

[0148] Processing the personal health report based on historical trends and the degree of correlation between diagnosis and treatment to generate personal health guidance for the examinee;

[0149] Summarize all the personal health reports and personal health guidelines in the target area, conduct health analysis from three dimensions: population groups, physical examination institutions, and historical comparisons, and generate a population health report for the target area.

[0150] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the target area population health data processing method based on big data provided by the above methods, the method comprising:

[0151] Obtaining consecutive batches of candidate physical examination reports of physical examinees in the target area, and extracting physical examination data of the physical examinees from the candidate physical examination reports; the candidate physical examination reports are physical examination reports generated within a preset time period;

[0152] Based on the constructed quality control rules, a model is established to pre-process the physical examination data, judge the rationality of the physical examination data, extract the reasonable physical examination data, and establish a model based on the quality control rules to analyze and process the reasonable physical examination data to generate personal health reports for each examinee;

[0153] Processing the personal health report based on historical trends and the degree of correlation between diagnosis and treatment to generate personal health guidance for the examinee;

[0154] Summarize all the personal health reports and personal health guidelines in the target area, conduct health analysis from three dimensions: population groups, physical examination institutions, and historical comparisons, and generate a population health report for the target area.

[0155] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention 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 invention.

Claims

1. A method for processing health data of people in a target area based on big data, characterized in that: The method comprises: Obtaining consecutive batches of candidate physical examination reports of physical examinees in the target area, and extracting physical examination data of the physical examinees from the candidate physical examination reports; the candidate physical examination reports are physical examination reports generated within a preset time period; Based on the constructed quality control rules, a model is established to pre-process the physical examination data, judge the rationality of the physical examination data, extract the reasonable physical examination data, and establish a model based on the quality control rules to analyze and process the reasonable physical examination data to generate personal health reports for each examinee; Processing the personal health report based on historical trends and the degree of correlation between diagnosis and treatment to generate personal health guidance for the examinee; Summarize all the personal health reports and personal health guidance opinions in the target area, and conduct health analysis from three dimensions: population group, physical examination institution and historical comparison to generate a population health report for the target area; Generate predicted physical examination items for the examinee based on the examinee's personal health report, personal health guidance, and mapping correlation trends between various types of physical examination data and corresponding associated diagnosis and treatment data in historical physical examination data; The quality control rule establishment model is constructed by the following steps: Collect historical physical examination reports and historical medical records of historical physical examinees in the target area, and obtain the associated regions corresponding to each historical physical examinee based on the associated information of each historical physical examinee; Obtain historical physical examination reports and historical diagnosis and treatment data of historical physical examinees in related areas; Extract reasonable historical physical examination data from historical physical examination reports, and extract reasonable historical diagnosis and treatment data from historical diagnosis and treatment information; According to the mapping correlation trend between the historical physical examination data and the historical diagnosis and treatment data that are mutually related in chronological order, a mapping relationship between the historical physical examination data and the historical diagnosis and treatment data is established, and a quality control rule establishment model is constructed; The mapping relationship between the historical physical examination data and the historical diagnosis and treatment data is established according to the mapping association trend between the historical physical examination data and the historical diagnosis and treatment data that are mutually related in chronological order, and the quality control rule establishment model is constructed, specifically including: Sort and group the historical physical examination data and historical diagnosis and treatment data of the historical physical examinees in chronological order, and obtain the local physical examination data and local diagnosis and treatment data corresponding to the historical physical examinees in several time intervals; Determine the associated diagnosis and treatment data corresponding to each type of physical examination data in the historical physical examination data; each type of physical examination data has at least one type of associated diagnosis and treatment data; Obtaining each physical examination extreme value point of each type of physical examination data in the local physical examination data of each time interval and each diagnosis and treatment extreme value point of each type of diagnosis and treatment data in the local diagnosis and treatment data; The time interval between the physical examination extreme value points with the same extreme value characteristics is divided into a mapping analysis interval, and the associated diagnosis and treatment data corresponding to the physical examination extreme value points in the mapping analysis interval and the diagnosis and treatment extreme value points of the associated diagnosis and treatment data are determined; the same extreme value features are the same type of maximum value points or minimum value points located in the same time interval and adjacent; The diagnosis and treatment extreme value points exceeding the first threshold and not exceeding the second threshold within the mapping analysis interval are taken as associated data, and the data mean of all associated data is determined; the first threshold is greater than the second threshold; Determine the mapping correlation trend of the physical examination data corresponding to the type of physical examination data at the physical examination extreme point according to the number of associated data, the number of associated diagnosis and treatment data, the data mean of the associated data, and the data value of the physical examination extreme point; Summarize and map related trends, establish mapping relationships between interrelated historical physical examination data and historical diagnosis and treatment data, and build quality control rule establishment models.

2. The method for processing health data of people in a target area based on big data according to claim 1 is characterized in that: The step of obtaining candidate physical examination reports of consecutive batches of physical examination subjects in the target area and extracting physical examination data of the physical examination subjects from the candidate physical examination reports specifically includes: Obtaining physical examination reports generated by physical examinees in the target area within a preset time period; Determine the time interval for generating chronologically adjacent physical examination reports; Use the most recent physical examination report as the baseline physical examination report; Divide the baseline physical examination report into a candidate group, and determine the time interval between the physical examination report before and adjacent to the baseline physical examination report and the baseline physical examination report; If it is determined that the time interval does not exceed the preset interval, the physical examination report before and adjacent to the baseline physical examination report will be used as the baseline physical examination report; The medical examination reports in the candidate group are used as candidate medical examination reports; The physical examination data of each physical examination item of the examinee is obtained from the candidate physical examination report.

3. The method for processing health data of people in a target area based on big data according to claim 1 is characterized in that: The processing of the personal health report based on the historical trend and the degree of correlation between diagnosis and treatment to generate personal health guidance opinions for the examinee specifically includes: Obtain the historical change area of ​​each physical examination data in the personal health report, and determine whether the historical change trend is within the preset change range to obtain the first health guidance opinion; When it is determined that the historical change trend of the physical examination data is not within the preset change range, the degree of correlation between the single diagnosis and treatment of the physical examination data is obtained, and a second health guidance opinion is generated according to the degree of correlation between the single diagnosis and treatment; the degree of correlation between the single diagnosis and treatment includes abnormal results, diagnostic criteria for diseases, treatment recommendations and preventive measures; The first health guidance opinion and the second health guidance opinion are summarized to generate the personal health guidance opinion of the examinee.

4. The method for processing health data of people in a target area based on big data according to claim 1 is characterized in that: The summarizing of all the personal health reports and personal health guidance opinions in the target area, and performing health analysis from three dimensions of population groups, physical examination institutions, and historical comparison, to generate a population health report for the target area specifically includes: Summarize all the personal health reports and personal health guidance opinions in the target area; Compare all the personal health reports and personal health guidance opinions in the target area by population to obtain a first population health report; Tracing the source of the physical examination report, determining the physical examination institution corresponding to the physical examination report, and classifying and comparing all the personal health reports and personal health guidance opinions in the target area between different physical examination institutions to obtain a second population health report; A historical comparison is performed between all the personal health reports in the target area and the historical physical examination data obtained in the target area to obtain a health report for a third group of people.

5. A device for processing health data of people in a target area based on big data, characterized in that: The device comprises: A data acquisition module, used to acquire consecutive batches of candidate physical examination reports of physical examinees in a target area, and extract physical examination data of the physical examinees from the candidate physical examination reports; the candidate physical examination reports are physical examination reports generated within a preset time period; The data processing module is used to establish a model based on the constructed quality control rules to pre-process the physical examination data, judge the rationality of the physical examination data, extract the reasonable physical examination data, and establish a model based on the quality control rules to analyze and process the reasonable physical examination data, and generate a personal health report for each examinee; A case analysis module, for processing the personal health report based on historical trends and the degree of correlation between diagnosis and treatment, and generating personal health guidance opinions for the examinee; A regional summary module is used to summarize all the personal health reports and personal health guidance opinions in the target area, and to perform health analysis from three dimensions: population group, physical examination institution, and historical comparison, to generate a population health report for the target area; The predictive physical examination module is used to generate the predicted physical examination items for the examinee based on the examinee's personal health report, personal health guidance, and the mapping and association trends of various types of physical examination data and corresponding associated diagnosis and treatment data in the historical physical examination data; The quality control rule establishment model is constructed by the following steps: Collect historical physical examination reports and historical medical records of historical physical examinees in the target area, and obtain the associated regions corresponding to each historical physical examinee based on the associated information of each historical physical examinee; Obtain historical physical examination reports and historical diagnosis and treatment data of historical physical examinees in related areas; Extract reasonable historical physical examination data from historical physical examination reports, and extract reasonable historical diagnosis and treatment data from historical diagnosis and treatment information; According to the mapping correlation trend between the historical physical examination data and the historical diagnosis and treatment data that are mutually related in chronological order, a mapping relationship between the historical physical examination data and the historical diagnosis and treatment data is established, and a quality control rule establishment model is constructed; The mapping relationship between the historical physical examination data and the historical diagnosis and treatment data is established according to the mapping association trend between the historical physical examination data and the historical diagnosis and treatment data that are mutually related in chronological order, and the quality control rule establishment model is constructed, specifically including: Sort and group the historical physical examination data and historical diagnosis and treatment data of the historical physical examinees in chronological order, and obtain the local physical examination data and local diagnosis and treatment data corresponding to the historical physical examinees in several time intervals; Determine the associated diagnosis and treatment data corresponding to each type of physical examination data in the historical physical examination data; each type of physical examination data has at least one type of associated diagnosis and treatment data; Obtaining each physical examination extreme value point of each type of physical examination data in the local physical examination data of each time interval and each diagnosis and treatment extreme value point of each type of diagnosis and treatment data in the local diagnosis and treatment data; The time interval between the physical examination extreme value points with the same extreme value characteristics is divided into a mapping analysis interval, and the associated diagnosis and treatment data corresponding to the physical examination extreme value points in the mapping analysis interval and the diagnosis and treatment extreme value points of the associated diagnosis and treatment data are determined; the same extreme value features are the same type of maximum value points or minimum value points located in the same time interval and adjacent; The diagnosis and treatment extreme value points exceeding the first threshold and not exceeding the second threshold within the mapping analysis interval are taken as associated data, and the data mean of all associated data is determined; the first threshold is greater than the second threshold; Determine the mapping correlation trend of the physical examination data corresponding to the type of physical examination data at the physical examination extreme point according to the number of associated data, the number of associated diagnosis and treatment data, the data mean of the associated data, and the data value of the physical examination extreme point; Summarize and map related trends, establish mapping relationships between interrelated historical physical examination data and historical diagnosis and treatment data, and build quality control rule establishment models.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of processing health data of the population in the target area based on big data as described in any one of claims 1 to 4 are implemented.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of processing health data of the target area population based on big data as described in any one of claims 1 to 4 are implemented.

Images