Data processing method of trauma auditing system platform

Abstract

The invention discloses a data processing method of a trauma auditing system platform, and relates to the technical field of electric data processing. The method comprises the following steps: comparing a patient basic data structure difference evaluation coefficient with a patient basic data structure difference evaluation threshold value, and according to a patient basic data structure difference correction coefficient and a threshold value comparison result of the patient basic data structure difference evaluation coefficient and the patient basic data structure difference evaluation threshold value, obtaining a patient basic data structure difference correction coefficient; obtaining a patient basic data structure difference correction result evaluation coefficient, and optimizing different data structures according to the patient basic data structure difference correction result evaluation coefficient. By analyzing the patient basic data structure difference correction coefficient and the threshold comparison result, the evaluation coefficient of the patient basic data structure difference correction result is obtained, the effect of reducing errors of cross-system data transmission is achieved, and the problem that data are inconsistent in different systems in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical data processing, and in particular to a data processing method for a trauma audit system platform. Background Art

[0002] With the continuous development of Internet technology, in order to ensure the safe use of medical insurance funds, it is necessary to conduct behavioral investigations and audits on trauma behaviors in designated medical institutions, realize the supervision and use of medical insurance funds, and also establish a series of auditing methods to ensure the smooth implementation of auditing work, and use relevant data platforms to conduct comprehensive statistics and analysis of trauma medical insurance work. Optimize and standardize the working mode of trauma auditing, facilitate the connection of auditing data between medical insurance centers and individuals, know the progress of case handling in real time, effectively reduce time costs, and reduce burdens.

[0003] For example, the invention patent with publication number: CN113987021A discloses a platform audit data processing system and method, which include: an acquisition module, used to obtain instructions for users to add or upload files, and identify whether the files added or uploaded by users are authorized; to query the status of files added or uploaded by users through query rules preset by the platform; an information extraction module, used to perform rule authorization on files added or uploaded by users through authorization rules preset by the platform, and to extract information from files added or uploaded by users using the authorization rules; to display source files and all target files related to files added or uploaded by users according to matching rules preset by the platform; and to initiate audit tasks for files added or uploaded by users according to the audit list preset by the platform.

[0004] For example, the data processing method and system for synchronization auditing announced by the invention patent with announcement number: CN117992441 B include: in the process of data synchronization from the data source address to the data target address, obtaining part of the sent data sent by the data source address and part of the received data received by the data target address according to a preset ratio; matching part of the sent data and part of the received data according to the data volume matching rule to obtain a matching result; sampling auditing part of the sent data and part of the received data according to the data sampling auditing algorithm to obtain an auditing result; determining the synchronization success result corresponding to the part of the sent data and the part of the received data according to the matching result and the auditing result.

[0005] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0006] In the prior art, the data processing of the trauma audit system platform needs to ensure the integration of the trauma audit system platform with other systems, but the structures of the same data in different systems are different, and there is a problem of inconsistent data in different systems. Summary of the invention

[0007] The embodiment of the present application solves the problem of data inconsistency in different systems in the prior art by providing a data processing method for a trauma audit system platform, thereby reducing errors in cross-system data transmission.

[0008] The embodiment of the present application provides a data processing method for a trauma audit system platform, comprising the following steps: collecting facial image data and basic patient data through sensors, and obtaining basic patient data structure difference data and basic patient data structure difference correction data through a database; comparing the collected facial image data with the facial image data stored in the audit system, regulating the audit system according to the comparison result, analyzing the basic patient data structure difference data to obtain a basic patient data structure difference evaluation coefficient, obtaining a basic patient data structure difference evaluation threshold from a database, comparing the basic patient data structure difference evaluation coefficient with the basic patient data structure difference evaluation threshold, and obtaining a threshold comparison result of the basic patient data structure difference evaluation coefficient and the basic patient data structure difference evaluation threshold; analyzing the basic patient data structure difference correction data to obtain a basic patient data structure difference correction coefficient, and obtaining a basic patient data structure difference correction result evaluation coefficient according to a threshold comparison result of the basic patient data structure difference correction coefficient and the basic patient data structure difference evaluation coefficient and the basic patient data structure difference evaluation threshold; optimizing different data structures according to the basic patient data structure difference correction result evaluation coefficient.

[0009] Furthermore, facial image data, patient basic data structure difference data and patient basic data structure difference correction data include: facial image data includes: facial feature point coordinates, facial feature vectors and facial image acquisition timestamp; patient basic data structure difference data includes: field matching rate, data conversion error rate, number of data mapping rules, average data conversion time and data conversion rate; patient basic data structure difference correction data includes: difference recognition rate, number of affected business processes and data structure consistency index.

[0010] Furthermore, the specific comparison process of comparing the collected facial image data with the facial image data stored in the audit system is: aligning the facial image using the facial feature point coordinates, performing feature extraction on the collected facial image data based on the facial feature point coordinates to obtain a feature vector of the facial image data, comparing the feature vector of the facial image data with the feature vector of the facial image data stored in the audit system to obtain a feature vector matching degree, and obtaining a feature vector matching result based on the feature vector matching degree.

[0011] Furthermore, the specific analysis process of analyzing the patient basic data structure difference data is as follows: analyze the field matching rate, data conversion error rate, number of data mapping rules, average data conversion time and data conversion rate to obtain the patient basic data structure difference evaluation coefficient, obtain the patient basic data structure difference evaluation standard value from the database, perform difference processing on the patient basic data structure difference evaluation coefficient and the patient basic data structure difference evaluation standard value, and optimize different data structures according to the size of the difference.

[0012] Furthermore, the specific comparison process of comparing the patient basic data structure difference evaluation coefficient with the patient basic data structure difference evaluation threshold is as follows: if the patient basic data structure difference evaluation coefficient is greater than or equal to the patient basic data structure difference evaluation threshold, the patient basic data structure difference correction coefficient is used to correct the patient basic data structure difference evaluation coefficient downward to obtain the patient basic data structure difference correction result evaluation coefficient; if the patient basic data structure difference evaluation coefficient is less than the patient basic data structure difference evaluation threshold, the patient basic data structure difference correction coefficient is used to correct the patient basic data structure difference evaluation coefficient upward to obtain the patient basic data structure difference correction result evaluation coefficient.

[0013] Furthermore, the specific analysis process of analyzing the patient basic data structure difference correction data is: analyzing the difference recognition rate, the number of affected business processes and the data structure consistency index to obtain the patient basic data structure difference correction coefficient.

[0014] Furthermore, the specific correction process of using the patient basic data structure difference correction coefficient to downwardly correct the patient basic data structure difference evaluation coefficient is as follows: if the patient basic data structure difference evaluation coefficient is greater than or equal to the patient basic data structure difference evaluation threshold, the patient basic data structure difference evaluation coefficient is the value of the exponent of e minus the patient basic data structure difference correction coefficient as the value of the exponent of e to obtain the patient basic data structure difference correction result evaluation coefficient.

[0015] Furthermore, the specific correction process of using the patient basic data structure difference correction coefficient to upwardly correct the patient basic data structure difference evaluation coefficient is as follows: if the patient basic data structure difference evaluation coefficient is less than the patient basic data structure difference evaluation threshold, the patient basic data structure difference evaluation coefficient is added as the value of the exponent of e plus the patient basic data structure difference correction coefficient as the value of the exponent of e to obtain the patient basic data structure difference correction result evaluation coefficient.

[0016] Furthermore, the specific optimization process for optimizing different data structures according to the evaluation coefficient of the difference correction result of the patient's basic data structure is as follows: obtaining the evaluation threshold of the difference correction result of the patient's basic data structure from the database; if the evaluation coefficient of the difference correction result of the patient's basic data structure is less than or equal to the evaluation threshold of the difference correction result of the patient's basic data structure, optimizing the different data structures; if the evaluation coefficient of the difference correction result of the patient's basic data structure is greater than the evaluation threshold of the difference correction result of the patient's basic data structure, there is no need to optimize the different data structures.

[0017] Furthermore, the specific method for obtaining the evaluation coefficient of the correction result of the patient's basic data structure difference is as follows:

[0018]

[0019] In the formula, QA is represented by the evaluation coefficient of the correction result of the patient's basic data structure difference, which is used to evaluate the result after the patient's basic data structure difference correction coefficient corrects the patient's basic data structure difference evaluation coefficient, DS is represented by the patient's basic data structure difference evaluation coefficient, α is represented by the weight factor of the patient's basic data structure difference evaluation coefficient, DST is represented by the patient's basic data structure difference evaluation threshold, DR is represented by the patient's basic data structure difference correction coefficient, β is represented by the weight factor of the patient's basic data structure difference correction coefficient, and e is represented by a natural constant.

[0020] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0021] 1. By analyzing the threshold comparison results of the patient basic data structure difference correction coefficient and the patient basic data structure difference evaluation coefficient and the patient basic data structure difference evaluation threshold, the patient basic data structure difference correction result evaluation coefficient is obtained, thereby achieving the effect of reducing the error of cross-system data transmission, and effectively solving the problem of inconsistent data in different systems in the prior art.

[0022] 2. By obtaining the evaluation coefficient of the correction result of the patient's basic data structure difference, different data structures are optimized, thereby achieving the effect of improving the accuracy of cross-system data transmission.

[0023] 3. Align the facial image by using the coordinates of facial feature points, perform feature extraction on the collected facial image data based on the coordinates of the facial feature points, and obtain the feature vector of the facial image data. Then, compare the feature vector of the facial image data with the feature vector of the facial image data saved in the audit system to obtain the feature vector matching degree. Based on the feature vector matching degree, obtain the feature vector matching result, thereby achieving the effect of improving the accuracy of information auditing in the audit system. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A flow chart of a data processing method for a trauma audit system platform provided in an embodiment of the present application;

[0025] Figure 2 An image of a patient's basic data structure difference correction coefficient in a data processing method for a trauma audit system platform provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] The embodiment of the present application solves the problem of data inconsistency in different systems in the prior art by providing a data processing method for a trauma audit system platform, and obtains the patient's basic data structure difference correction result evaluation coefficient by analyzing the threshold comparison results of the patient's basic data structure difference correction coefficient and the patient's basic data structure difference evaluation coefficient with the patient's basic data structure difference evaluation threshold, thereby reducing the error of cross-system data transmission.

[0027] The technical solution in the embodiment of the present application is to solve the above-mentioned problem of inconsistent data in different systems. The overall idea is as follows:

[0028] By analyzing the threshold comparison results of the patient basic data structure difference correction coefficient and the patient basic data structure difference evaluation coefficient and the patient basic data structure difference evaluation threshold, the patient basic data structure difference correction result evaluation coefficient is obtained, thereby reducing the error of cross-system data transmission.

[0029] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0030] like Figure 1As shown, it is a flow chart of a data processing method of a trauma audit system platform provided by an embodiment of the present application, and the method includes the following steps: collecting facial image data and patient basic data through sensors, and obtaining patient basic data structure difference data and patient basic data structure difference correction data through a database; comparing the collected facial image data with the facial image data stored inside the audit system, regulating the audit system according to the comparison result, analyzing the patient basic data structure difference data to obtain the patient basic data structure difference evaluation coefficient, obtaining the patient basic data structure difference evaluation threshold from the database, comparing the patient basic data structure difference evaluation coefficient with the patient basic data structure difference evaluation threshold, and obtaining a threshold comparison result of the patient basic data structure difference evaluation coefficient and the patient basic data structure difference evaluation threshold; analyzing the patient basic data structure difference correction data to obtain the patient basic data structure difference correction coefficient, and obtaining the patient basic data structure difference correction result evaluation coefficient according to the threshold comparison result of the patient basic data structure difference correction coefficient and the patient basic data structure difference evaluation coefficient and the patient basic data structure difference evaluation threshold; optimizing different data structures according to the patient basic data structure difference correction result evaluation coefficient.

[0031] In this embodiment, a high-resolution camera is used to collect facial images of the injured person in a medical institution, and the collected facial image data is stored in the database of the audit system. At the same time, the previously stored facial image data is extracted from the database for comparison, and the collected facial images are standardized to ensure that the image format, resolution, etc. are consistent with the images stored in the database. By evaluating and correcting the differences in the basic data structure of the patient, recognition errors caused by inconsistent image quality or format can be reduced, thereby improving the accuracy of facial recognition.

[0032] When the hospital system and the audit system are connected for the first time, a temporary script will be used to temporarily solve the problem of data structure differences. When either the hospital or the audit system is updated, the temporary script will become ineffective and the problem cannot be solved once and for all.

[0033] Furthermore, facial image data, patient basic data structure difference data and patient basic data structure difference correction data include: facial image data includes: facial feature point coordinates, facial feature vectors and facial image acquisition timestamp; patient basic data structure difference data includes: field matching rate, data conversion error rate, number of data mapping rules, average data conversion time and data conversion rate; patient basic data structure difference correction data includes: difference recognition rate, number of affected business processes and data structure consistency index.

[0034] In this embodiment, the system collects facial image data through a high-resolution camera while the patient is receiving treatment, including facial feature point coordinates, facial feature vectors and facial image collection timestamps. The system compares the newly collected facial image data with the data structure in the existing database, evaluates the field matching rate and data conversion error rate, lists the number of data mapping rules and the average data conversion time. The system monitors the performance of the corrected data in the business process, records the rework rate and the number of affected business processes, and ensures that the patient information is accurate through precise facial feature data and timestamps. The automated patient basic data structure difference assessment and correction process greatly improves data processing efficiency.

[0035] Furthermore, the specific comparison process of comparing the collected facial image data with the facial image data stored in the audit system is: aligning the facial image using the facial feature point coordinates, performing feature extraction on the collected facial image data based on the facial feature point coordinates to obtain a feature vector of the facial image data, comparing the feature vector of the facial image data with the feature vector of the facial image data stored in the audit system to obtain a feature vector matching degree, and obtaining a feature vector matching result based on the feature vector matching degree.

[0036] In this embodiment, the system captures the facial image of the injured patient through a camera, records the facial image acquisition timestamp, and marks the coordinates of key feature points in the facial image, such as the positions of the eyes, nose, mouth, etc. According to the extracted facial feature point coordinates, the system performs a geometric transformation on the collected facial image to align it with the standard facial model. The system extracts the facial feature vector based on the aligned facial image, compares the feature vector of the facial image data with the feature vector of the facial image data stored in the audit system, and obtains the feature vector matching degree. If the feature vector matching degree exceeds the preset threshold, the patient's identity authentication is successful, and data transmission between the hospital system and the audit system is performed; if the feature vector matching degree is lower than the preset threshold, if the matching degree is not enough due to the patient's facial injury, the match is unsuccessful. If the matching degree of other feature vectors is lower than the preset threshold, the system issues an alarm to notify the relevant auditors. The feature vector matching degree refers to the similarity between two feature vectors, which can be expressed here as the distance between the coordinates of two key feature points.

[0037] Furthermore, the specific analysis process of analyzing the patient basic data structure difference data is as follows: analyze the field matching rate, data conversion error rate, number of data mapping rules, average data conversion time and data conversion rate to obtain the patient basic data structure difference evaluation coefficient, obtain the patient basic data structure difference evaluation standard value from the database, perform difference processing on the patient basic data structure difference evaluation coefficient and the patient basic data structure difference evaluation standard value, and optimize different data structures according to the size of the difference.

[0038] In this embodiment, the specific method for obtaining the patient basic data structure difference evaluation coefficient is:

[0039]

[0040] Where DS represents the patient basic data structure difference evaluation coefficient, which is used to evaluate the impact of the field matching rate, data conversion error rate, number of data mapping rules, average data conversion time and data conversion rate of the patient basic data structure difference data on the patient basic data structure difference. Several patient basic data structure difference time monitoring points are set, Z = 1, 2, 3, ..., a, a represents the total number of patient basic data structure difference time monitoring points, FMR Z It is expressed as the field matching rate of the Zth patient’s basic data structure difference time monitoring point, DCER Z It is expressed as the data conversion error rate of the Zth patient's basic data structure difference time monitoring point, NODMR Z It is represented by the number of data mapping rules for the Zth patient’s basic data structure difference time monitoring point, NODMR0 is represented by the standard value of the number of data mapping rules, ACTOD Z It is expressed as the average data conversion time of the Zth patient's basic data structure difference time monitoring point, Expressed as the weight factor of the average data conversion time, DCR Z It is expressed as the data conversion rate of the difference time monitoring point of the basic data structure of the Zth patient, and e is expressed as a natural constant.

[0041] If the number of data mapping rules is closer to the standard value, the field matching rate will be greater, and the patient's basic data structure difference evaluation coefficient will be smaller. The standard value of the number of data mapping rules can be directly obtained through the database, the average data conversion time will be shorter, and the data conversion rate will be higher. The system can process data quickly and efficiently, and the higher the data conversion rate, the lower the data conversion error rate.

[0042] The field matching rate refers to the ratio of source data fields to target data fields that are successfully matched during data processing. The rules for matching source data fields to target data fields are defined as matching by field name, data type, data length, and data format. It can be obtained by comparing the number of source data fields and target data fields and calculating the ratio of the number of successfully matched fields to the total number of fields. The value range is 0%-60%.

[0043] The data conversion error rate refers to the proportion of records that have errors during the data conversion process. It can be obtained by comparing the number of records that have errors during the statistical data conversion process with the total number of records. The records that have errors during the statistical data conversion process refer to records with data type mismatch, data values ​​outside the expected range, and data conversion failures. The value range is 0%-60%.

[0044] The number of data mapping rules refers to the total number of mapping rules defined in the data processing process, which can be obtained by counting the number of mapping rules. In this embodiment, the value range is 3-7.

[0045] The average data conversion time refers to the average time required to complete the conversion of a record from the source data format to the target data format. It can be obtained by recording the conversion time of each record and calculating the average conversion time of all records. The value range is 20-100ms.

[0046] The data conversion rate refers to the ratio of the number of successfully converted data records to the total number of records. It can be obtained by counting the number of successfully converted records and comparing it with the total number of records. The value range is 0%-60%.

[0047] The weight factor of the average data conversion time can be obtained through the dynamic information database, which represents the proportion of the average data conversion time in the correction coefficient of the difference in the basic data structure of the patient. The weight factor of the average data conversion time can also be obtained through a mapping relationship. For example, a mapping set of the average data conversion time and its corresponding weight is established through the relationship between the average data conversion time in the historical data and the dynamic information. The weight factor of the corresponding average data conversion time in the mapping set is obtained by inputting the real-time average data conversion time.

[0048] In this embodiment, the specific process of performing difference processing on the patient basic data structure difference evaluation coefficient and the patient basic data structure difference evaluation standard value is: subtract the patient basic data structure difference evaluation coefficient from the patient basic data structure difference evaluation standard value and take the absolute value. The larger the absolute value, the greater the difference. When the difference is greater than or equal to 1, the methods of adjusting data mapping rules, optimizing data query and enhancing data monitoring are adopted to optimize different data structures. When the difference is less than 1, there is no need to optimize different data structures.

[0049] Adjust data mapping rules: Modify data mapping and transformation rules and update mapping configurations during data integration and synchronization.

[0050] Optimize data query: Optimize database query, improve query efficiency and performance, and modify or create new indexes to speed up data retrieval.

[0051] Enhanced data monitoring: Add monitoring indicators to more accurately assess data quality, monitor data changes in real time, and identify and resolve problems in a timely manner.

[0052] Furthermore, the specific comparison process of comparing the patient basic data structure difference evaluation coefficient with the patient basic data structure difference evaluation threshold is as follows: if the patient basic data structure difference evaluation coefficient is greater than or equal to the patient basic data structure difference evaluation threshold, the patient basic data structure difference correction coefficient is used to correct the patient basic data structure difference evaluation coefficient downward to obtain the patient basic data structure difference correction result evaluation coefficient; if the patient basic data structure difference evaluation coefficient is less than the patient basic data structure difference evaluation threshold, the patient basic data structure difference correction coefficient is used to correct the patient basic data structure difference evaluation coefficient upward to obtain the patient basic data structure difference correction result evaluation coefficient.

[0053] In this embodiment, the calculated patient basic data structure difference evaluation coefficient is compared with the patient basic data structure difference evaluation threshold. If the patient basic data structure difference evaluation coefficient is greater than or equal to the patient basic data structure difference evaluation threshold, the patient basic data structure difference correction coefficient is used to correct the patient basic data structure difference evaluation coefficient downward to reduce the patient basic data structure difference evaluation coefficient. A penalty is imposed on the result that the difference between the patient basic data structure difference evaluation coefficient and the patient basic data structure difference evaluation threshold is greater than 0.5, for example, the patient basic data structure difference evaluation coefficient is added with 0.1, so as to urge the data provider to improve the patient basic data structure difference correction result. If the patient basic data structure difference evaluation coefficient is less than the patient basic data structure difference evaluation threshold, the patient basic data structure difference correction coefficient is used to correct the patient basic data structure difference evaluation coefficient downward to reduce the patient basic data structure difference evaluation coefficient. The data structure difference correction coefficient revises the patient's basic data structure difference assessment coefficient upward to improve the patient's basic data structure difference assessment coefficient, and gives incentives to data structures whose difference between the patient's basic data structure difference assessment coefficient and the patient's basic data structure difference assessment threshold is close to 0. For example, the patient's basic data structure difference assessment coefficient is processed according to the patient's basic data structure difference assessment threshold to make the patient's basic data structure difference assessment coefficient closer to the patient's basic data structure difference assessment threshold, and encourages maintaining or improving the patient's basic data structure difference correction results. Through the above correction process, the final patient's basic data structure difference correction result assessment coefficient is obtained, which reflects the overall quality of the data. Through the correction process, the accuracy and consistency of the data are improved, providing a high-quality data foundation for subsequent processing.

[0054] Furthermore, the specific analysis process of analyzing the patient basic data structure difference correction data is: analyzing the difference recognition rate, the number of affected business processes and the data structure consistency index to obtain the patient basic data structure difference correction coefficient.

[0055] In this embodiment, the specific method for obtaining the patient basic data structure difference correction coefficient is:

[0056]

[0057] Where DR is the correction coefficient of the difference in the patient's basic data structure, which is used to evaluate the difference recognition rate of the correction data of the patient's basic data structure difference, the number of affected business processes and the influence of the data structure consistency index on the correction of the patient's basic data structure difference. A number of patient basic data structure difference correction time monitoring points are set, X = 1, 2, 3, ..., b, b represents the total number of patient basic data structure difference correction time monitoring points, ND X It is represented as the difference recognition rate of the Xth patient’s basic data structure difference correction time monitoring point, μ is represented as the weight factor of the difference recognition rate, DB X It is represented by the number of affected business processes at the Xth patient basic data structure difference correction time monitoring point, ρ is represented by the weight factor of the number of affected business processes, DCF X It is represented as the data structure consistency index of the Xth patient's basic data structure difference correction time monitoring point, τ is represented as the weight factor of the data structure consistency index, and e is represented as a natural constant.

[0058] The difference recognition rate refers to the proportion of data differences that the system can correctly identify, which can be obtained through the calculation formula of the difference recognition rate: Difference recognition rate = (amount of correctly identified difference data / total amount of difference data) × 100%. The amount of correctly identified difference data and the total amount of difference data can be directly obtained through the log.

[0059] The number of affected business processes refers to the number of business processes that are affected or interrupted due to data problems during the data processing process. It can be obtained by monitoring the operation of business processes and recording interruptions or abnormal situations caused by data problems.

[0060] The data structure consistency index refers to the degree of standardization and uniformity of the data in structure, which can be obtained through the formula: data structure consistency index = (amount of data that complies with the standards / total amount of data) × 100%. The amount of data that complies with the standards and the total amount of data can be obtained through logs.

[0061] When the data structure consistency index is 1, it is judged that the format structures of the same data in different systems are exactly the same. The more it deviates from 1, the more different the format structures of the same data in different systems are.

[0062] The weight factor of the difference recognition rate, the weight factor of the number of affected business processes and the weight factor of the data structure consistency index can be obtained through the dynamic information database, which represents the proportion of the difference recognition rate, the number of affected business processes and the data structure consistency index in the patient's basic data structure difference correction coefficient. The weight factor of the difference recognition rate, the weight factor of the number of affected business processes and the weight factor of the data structure consistency index can be obtained through a mapping relationship. For example, a mapping set of the difference recognition rate, the number of affected business processes and the data structure consistency index and their corresponding weights is established through the relationship between the difference recognition rate, the number of affected business processes and the data structure consistency index in the historical data and the dynamic information. The weight factor of the difference recognition rate, the weight factor of the number of affected business processes and the data structure consistency index corresponding to the mapping set is obtained by inputting the real-time difference recognition rate, the number of affected business processes and the data structure consistency index.

[0063] A high difference recognition rate helps to improve the data structure consistency index and reduce the number of affected business processes. A low difference recognition rate leads to data structure problems not being discovered in a timely manner, and the problems spread to more business processes, increasing the number of affected business processes. A high data structure consistency index can make difference recognition easier and reduce the number of affected business processes. The number of affected business processes is inversely proportional to the difference recognition rate and the data structure consistency index, that is, when the difference recognition rate and the data structure consistency index are high, the number of affected business processes is small.

[0064] In a specific embodiment, examples of patient basic data structure difference correction coefficient data are shown in the following table.

[0065] Table 1 Patient basic data structure difference correction coefficient data example table

[0066]

[0067]

[0068] When the weight factors of the difference recognition rate, the number of affected business processes, and the data structure consistency index are 0.8, 0.1, and 0.1 respectively, Figure 2 From the data in Table 1, it can be seen that when the average value of the number of affected business processes at b patient basic data structure difference correction time monitoring points and the average value of the data structure consistency index at b patient basic data structure difference correction time monitoring points are fixed, the greater the average value of the difference recognition rate at b patient basic data structure difference correction time monitoring points, the greater the patient basic data structure difference correction coefficient.

[0069] Furthermore, the specific correction process of using the patient basic data structure difference correction coefficient to downwardly correct the patient basic data structure difference evaluation coefficient is as follows: if the patient basic data structure difference evaluation coefficient is greater than or equal to the patient basic data structure difference evaluation threshold, the patient basic data structure difference evaluation coefficient is the value of the exponent of e minus the patient basic data structure difference correction coefficient as the value of the exponent of e to obtain the patient basic data structure difference correction result evaluation coefficient.

[0070] In this embodiment, for example, the patient basic data structure difference evaluation coefficient is 0.85, the preset patient basic data structure difference evaluation threshold is 0.7, and the patient basic data structure difference correction coefficient is 0.2. At this time, the patient basic data structure difference evaluation coefficient is greater than the patient basic data structure difference evaluation threshold, and the patient basic data structure difference correction result evaluation coefficient is e 0.85 -e 0.2 =1.1182.

[0071] Furthermore, the specific correction process of using the patient basic data structure difference correction coefficient to upwardly correct the patient basic data structure difference evaluation coefficient is as follows: if the patient basic data structure difference evaluation coefficient is less than the patient basic data structure difference evaluation threshold, the patient basic data structure difference evaluation coefficient is added as the value of the exponent of e plus the patient basic data structure difference correction coefficient as the value of the exponent of e to obtain the patient basic data structure difference correction result evaluation coefficient.

[0072] In this embodiment, for example, the patient basic data structure difference evaluation coefficient is 0.6, the preset patient basic data structure difference evaluation threshold is 0.7, and the patient basic data structure difference correction coefficient is 0.25. At this time, the patient basic data structure difference evaluation coefficient is less than the patient basic data structure difference evaluation threshold, and the patient basic data structure difference correction result evaluation coefficient is e 0.6 -e 0.25 =0.5381.

[0073] Furthermore, the specific optimization process for optimizing different data structures according to the evaluation coefficient of the difference correction result of the patient's basic data structure is as follows: obtaining the evaluation threshold of the difference correction result of the patient's basic data structure from the database; if the evaluation coefficient of the difference correction result of the patient's basic data structure is less than or equal to the evaluation threshold of the difference correction result of the patient's basic data structure, optimizing the different data structures; if the evaluation coefficient of the difference correction result of the patient's basic data structure is greater than the evaluation threshold of the difference correction result of the patient's basic data structure, there is no need to optimize the different data structures.

[0074] In this embodiment, the system obtains the threshold value of the correction result of the patient's basic data structure difference from the database. If the evaluation coefficient of the correction result of the patient's basic data structure difference is less than or equal to the evaluation threshold value of the correction result of the patient's basic data structure difference, the system executes a deep optimization process, including building a data conversion layer, data verification and process reconstruction. If the evaluation coefficient of the correction result of the patient's basic data structure difference is greater than the evaluation threshold value of the correction result of the patient's basic data structure difference, the system considers that the data structure does not need to be optimized and continuously monitors, updates and maintains the data structure at regular intervals, and continues to operate normally. By setting the evaluation threshold, the system can flexibly take appropriate optimization measures according to the situation of the correction results of the patient's basic data structure difference to improve processing efficiency.

[0075] Build a data conversion layer: Develop a middleware or service layer that is responsible for converting data from different systems into the standard format required by the audit system.

[0076] Data verification: Verify the cleaned and converted data to ensure that it complies with the new data standards, implement data quality audits to monitor the effectiveness of data quality improvements, and implement data quality audits in the following ways: define data quality dimensions such as accuracy, completeness, consistency, timeliness, reliability, and comprehensibility, set audit goals, for example, improve data accuracy to more than 99%, develop audit standards based on data quality dimensions, determine the data sample for the audit, calculate data quality indicators (DQIs), such as error rate, missing rate, and outlier ratio, and summarize the audit results, including a detailed description of the data quality issues, cause analysis, and improvement suggestions.

[0077] Process reconstruction: Redesign the processes of data collection, processing and storage, add data quality control nodes, and ensure that data maintains high quality throughout its life cycle.

[0078] Furthermore, the specific method for obtaining the evaluation coefficient of the correction result of the patient's basic data structure difference is as follows:

[0079]

[0080] In the formula, QA is represented by the evaluation coefficient of the correction result of the patient's basic data structure difference, which is used to evaluate the result after the patient's basic data structure difference correction coefficient corrects the patient's basic data structure difference evaluation coefficient, DS is represented by the patient's basic data structure difference evaluation coefficient, α is represented by the weight factor of the patient's basic data structure difference evaluation coefficient, DST is represented by the patient's basic data structure difference evaluation threshold, DR is represented by the patient's basic data structure difference correction coefficient, β is represented by the weight factor of the patient's basic data structure difference correction coefficient, and e is represented by a natural constant.

[0081] In this embodiment, when the patient basic data structure difference evaluation coefficient is greater than or equal to the patient basic data structure difference evaluation threshold, the patient basic data structure difference evaluation coefficient is taken as the value of the exponent of e minus the patient basic data structure difference correction coefficient as the value of the exponent of e to obtain the patient basic data structure difference correction result evaluation coefficient; when the patient basic data structure difference evaluation coefficient is less than the patient basic data structure difference evaluation threshold, the patient basic data structure difference evaluation coefficient is taken as the value of the exponent of e plus the patient basic data structure difference correction coefficient as the value of the exponent of e to obtain the patient basic data structure difference correction result evaluation coefficient.

[0082] The weight factor of the patient's basic data structure difference assessment coefficient and the weight factor of the patient's basic data structure difference correction coefficient can be obtained through the dynamic information database, which represents the proportion of the patient's basic data structure difference assessment coefficient and the patient's basic data structure difference correction coefficient in the patient's basic data structure difference correction result assessment coefficient. The weight factor of the patient's basic data structure difference assessment coefficient and the weight factor of the patient's basic data structure difference correction coefficient can also be obtained through a mapping relationship. For example, a mapping set of the patient's basic data structure difference assessment coefficient and the patient's basic data structure difference correction coefficient and their corresponding weights is established respectively through the relationship between the patient's basic data structure difference assessment coefficient and the patient's basic data structure difference correction coefficient in the historical data and the dynamic information. The weight factor of the patient's basic data structure difference assessment coefficient and the weight factor of the patient's basic data structure difference correction coefficient corresponding to the mapping set are obtained by inputting the real-time patient's basic data structure difference assessment coefficient and the patient's basic data structure difference correction coefficient.

[0083] In this embodiment, different data structures are first optimized according to the difference between the patient basic data structure difference evaluation coefficient and the patient basic data structure difference evaluation standard value, and then different data structures are optimized according to the patient basic data structure difference correction result evaluation coefficient. These two optimization measures cannot be performed at the same time, because if they are performed at the same time, the difficulty and cost of maintenance and management will increase, and the root cause cannot be traced when a problem occurs.

[0084] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0085] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0086] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0087] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0088] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0089] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A data processing method for a trauma audit system platform, characterized in that: The following steps are involved: Collect facial image data and basic patient data through sensors, and obtain basic patient data structure difference data and basic patient data structure difference correction data through a database; Compare the collected facial image data with the facial image data stored in the audit system, regulate the audit system according to the comparison result, analyze the patient basic data structure difference data to obtain the patient basic data structure difference evaluation coefficient, obtain the patient basic data structure difference evaluation threshold from the database, compare the patient basic data structure difference evaluation coefficient with the patient basic data structure difference evaluation threshold, and obtain the threshold comparison result of the patient basic data structure difference evaluation coefficient and the patient basic data structure difference evaluation threshold; Analyze the patient basic data structure difference correction data to obtain the patient basic data structure difference correction coefficient, and obtain the patient basic data structure difference correction result evaluation coefficient according to the threshold comparison result of the patient basic data structure difference correction coefficient and the patient basic data structure difference evaluation coefficient and the patient basic data structure difference evaluation threshold; The result evaluation coefficients were corrected according to the differences in the basic data structures of the patients to optimize different data structures.

2. A data processing method for a trauma audit system platform as claimed in claim 1, characterized in that: The face image data, patient basic data structure difference data and patient basic data structure difference correction data include: The face image data includes: facial feature point coordinates, facial feature vectors and facial image acquisition timestamp; The data on differences in the basic patient data structure include: field matching rate, data conversion error rate, number of data mapping rules, average data conversion time, and data conversion rate; The patient basic data structure difference correction data include: difference recognition rate, number of affected business processes and data structure consistency index.

3. The data processing method of the trauma audit system platform as claimed in claim 1, characterized in that: The specific comparison process of comparing the collected facial image data with the facial image data stored in the audit system is as follows: The facial image is aligned using the coordinates of the facial feature points, and the features of the collected facial image data are extracted based on the coordinates of the facial feature points to obtain the feature vector of the facial image data. The feature vector of the facial image data is compared with the feature vector of the facial image data saved in the audit system to obtain the feature vector matching degree, and the feature vector matching result is obtained based on the feature vector matching degree.

4. The data processing method of the trauma audit system platform as claimed in claim 1, characterized in that: The specific analysis process of analyzing the patient basic data structure difference data is as follows: The field matching rate, data conversion error rate, number of data mapping rules, average data conversion time and data conversion rate were analyzed to obtain the patient basic data structure difference evaluation coefficient, obtain the patient basic data structure difference evaluation standard value from the database, perform difference processing on the patient basic data structure difference evaluation coefficient and the patient basic data structure difference evaluation standard value, and optimize different data structures according to the size of the difference.

5. The data processing method of the trauma audit system platform as claimed in claim 1, characterized in that: The specific comparison process of comparing the patient basic data structure difference evaluation coefficient with the patient basic data structure difference evaluation threshold is as follows: If the patient's basic data structure difference assessment coefficient is greater than or equal to the patient's basic data structure difference assessment threshold, the patient's basic data structure difference correction coefficient is used to correct the patient's basic data structure difference assessment coefficient downward to obtain the patient's basic data structure difference correction result assessment coefficient; if the patient's basic data structure difference assessment coefficient is less than the patient's basic data structure difference assessment threshold, the patient's basic data structure difference correction coefficient is used to correct the patient's basic data structure difference assessment coefficient upward to obtain the patient's basic data structure difference correction result assessment coefficient.

6. The data processing method of the trauma audit system platform as claimed in claim 1, characterized in that: The specific analysis process of analyzing the patient's basic data structure difference correction data is as follows: The difference recognition rate, number of affected business processes and data structure consistency index were analyzed to obtain the difference correction coefficient of the patient's basic data structure.

7. A data processing method for a trauma audit system platform as claimed in claim 5, characterized in that: The specific correction process of using the patient basic data structure difference correction coefficient to downwardly correct the patient basic data structure difference assessment coefficient is as follows: If the patient basic data structure difference evaluation coefficient is greater than or equal to the patient basic data structure difference evaluation threshold, the patient basic data structure difference evaluation coefficient is the value of the exponent of e minus the patient basic data structure difference correction coefficient as the exponent of e to obtain the patient basic data structure difference correction result evaluation coefficient.

8. The data processing method of the trauma audit system platform as claimed in claim 5, characterized in that: The specific correction process of using the patient basic data structure difference correction coefficient to upwardly correct the patient basic data structure difference assessment coefficient is as follows: If the patient basic data structure difference evaluation coefficient is less than the patient basic data structure difference evaluation threshold, the patient basic data structure difference evaluation coefficient is added to the patient basic data structure difference correction coefficient as the exponent value of e to obtain the patient basic data structure difference correction result evaluation coefficient.

9. The data processing method of the trauma audit system platform as claimed in claim 1, characterized in that: The specific optimization process of optimizing different data structures by correcting the result evaluation coefficient according to the difference in the basic data structure of the patient is as follows: Obtain the patient's basic data structure difference correction result evaluation threshold from the database; if the patient's basic data structure difference correction result evaluation coefficient is less than or equal to the patient's basic data structure difference correction result evaluation threshold, optimize different data structures; if the patient's basic data structure difference correction result evaluation coefficient is greater than the patient's basic data structure difference correction result evaluation threshold, there is no need to optimize different data structures.

10. The data processing method of the trauma audit system platform as claimed in claim 1, characterized in that: The specific method for obtaining the patient basic data structure difference correction result evaluation coefficient is: In the formula, QA is represented by the evaluation coefficient of the correction result of the patient's basic data structure difference, which is used to evaluate the result after the patient's basic data structure difference correction coefficient corrects the patient's basic data structure difference evaluation coefficient, DS is represented by the patient's basic data structure difference evaluation coefficient, α is represented by the weight factor of the patient's basic data structure difference evaluation coefficient, DST is represented by the patient's basic data structure difference evaluation threshold, DR is represented by the patient's basic data structure difference correction coefficient, β is represented by the weight factor of the patient's basic data structure difference correction coefficient, and e is represented by a natural constant.

Images