Medical information processing method and device, storage medium and computer equipment

Abstract

The invention discloses a medical information processing method and device, a storage medium and computer equipment, relates to the technical field of medical information processing, and mainly aims to improve the processing efficiency and processing accuracy of medical information. Comprising the steps of determining data source information and timestamp information of to-be-processed medical information in response to a medical information processing signal; based on the data source information and the timestamp information, acquiring to-be-processed medical information, and acquiring medical information verification data corresponding to the to-be-processed medical information; determining channel information of the medical information verification data, and determining an information processing mode suitable for the to-be-processed medical information based on the channel information; and utilizing the information processing mode and the medical information verification data to check and process the to-be-processed medical information to obtain a medical information processing result. The method and the device are suitable for application scenarios for performing accuracy checking processing on the medical information.

Description

Technical Field

[0001] The present invention relates to the technical field of medical information processing, and in particular, to a method, device, storage medium, and computer device for processing medical information. Background Art

[0002] In view of the complex subdivision in the payment field and the sharp increase in the number of online business orders in the current medical scenario, a solution for effectively verifying the accuracy of medical information, such as medical payment information, needs to be proposed.

[0003] Currently, medical information is usually processed through a unified manual verification method. However, this manual processing method is greatly affected by subjective factors of people, which may lead to information processing errors. Moreover, the unified method may not be applicable to medical information, further resulting in a low accuracy of medical information processing. At the same time, the efficiency of the manual processing method is also low. Summary of the Invention

[0004] The present invention provides a method, device, storage medium, and computer device for processing medical information, mainly aiming to improve the processing efficiency and accuracy of medical information.

[0005] According to a first aspect of the present invention, a method for processing medical information is provided, including:

[0006] Responding to a medical information processing signal, determining data source information and timestamp information of the medical information to be processed;

[0007] Based on the data source information and the timestamp information, obtaining the medical information to be processed, and obtaining medical information verification data corresponding to the medical information to be processed;

[0008] Determining channel information of the medical information verification data, and based on the channel information, determining an information processing method applicable to the medical information to be processed;

[0009] Using the information processing method and the medical information verification data to perform a verification process on the medical information to be processed, and obtaining a medical information processing result.

[0010] Optionally, the channel information includes a self-developed channel and a third-party channel of the hospital to which the medical information to be processed belongs; the information processing methods include a round-robin matching processing method corresponding to the self-developed channel and a preset information processing model processing method corresponding to the third-party channel;

[0011] The step of using the information processing method and the medical information verification data to perform a verification process on the medical information to be processed, and obtaining a medical information processing result includes:

[0012] Using the above-mentioned polling matching processing method, match the medical information verification data with the medical information to be processed, and based on the matching result, determine the medical information processing result;

[0013] Input the medical information verification data and the medical information to be processed into the preset information processing model to obtain the medical information processing result.

[0014] Optionally, the step of using the above-mentioned polling matching processing method to match the medical information verification data with the medical information to be processed includes:

[0015] Classify each piece of medical information to be processed to obtain medical information under different classification categories, where the different classification categories include: marked information category with a preset identification mark, other information category, unilateral data missing information category, error handling information category, and reversal information category;

[0016] Determine the matching rounds of polling matching for the medical information under different classification categories, and based on the matching rounds, set a timing task to perform polling matching on the medical information under different classification categories.

[0017] Optionally, the marked information category corresponds to the first round of matching, the other information category corresponds to the second round of matching, the unilateral data missing information category corresponds to the third round of matching, the error handling information category corresponds to the fourth round of matching, and the reversal information category corresponds to the fifth round of matching;

[0018] The step of setting a timing task to perform polling matching on the medical information under different classification categories based on the matching rounds includes:

[0019] When the matching task time of the first round of matching arrives, determine the first medical field in the medical information under the marked information category, and determine the first verification field that matches the first medical field in the medical information verification data;

[0020] Determine the first medical information verification data corresponding to the first verification field in the medical information verification data, and determine the first medical information corresponding to the first medical field in the medical information under the marked information category, match the first medical information verification data with the first medical information, and based on the matching result, determine the accuracy of the first medical information;

[0021] Store the medical information under the other information category and the medical information verification data in the cache. When the matching task time of the second round of matching arrives, determine the second medical field in the medical information under the other information category in the cache, and determine the second verification field that matches the second medical field in the medical information verification data;

[0022] Determine the second medical information verification data corresponding to the second verification field in the medical information verification data, and determine the second medical information corresponding to the second medical field in the medical information under the remaining information categories, match the second medical information verification data with the second medical information, and determine the accuracy of the second medical information based on the matching result;

[0023] When the matching task time of the third-round matching arrives, determine the backward medical information verification data at a preset time after the medical information verification data, determine the third medical field in the medical information under the unilateral data missing information category, and determine the third verification field matching the third medical field in the backward medical information verification data;

[0024] Determine the third medical information verification data corresponding to the third verification field in the backward medical information verification data, and determine the third medical information corresponding to the third medical field in the medical information under the unilateral data missing information category, match the third medical information verification data with the third medical information, and determine the accuracy of the third medical information based on the matching result;

[0025] When the matching task time of the fourth-round matching arrives, determine the fourth medical field in the medical information under the error handling information category, and determine the fourth verification field matching the fourth medical field in the medical information verification data;

[0026] Determine the fourth medical information verification data corresponding to the fourth verification field in the medical information verification data, and determine the fourth medical information corresponding to the fourth medical field in the medical information under the single error handling information category, match the fourth medical information verification data with the fourth medical information, and determine the accuracy of the fourth medical information based on the matching result;

[0027] Based on the medical information verification data, conduct an information missing check on the medical information to be processed. Based on the check result, determine the category of the missing medical information as the reversal information category. When the matching task time of the fifth-round matching arrives, determine the verification data category matching the reversal information category in the medical information verification data, and determine the incoming account information and outgoing account information under the verification data category;

[0028] Determine the compliance of the information missing under the reversal information category based on the difference between the incoming account information and the outgoing account information.

[0029] Optionally, after verifying the to-be-processed medical information by using the information processing method and the medical information verification data to obtain a medical information processing result, the method further includes:

[0030] If there is abnormal information in the to-be-processed medical information, automatically correct the abnormal information based on the medical information verification data;

[0031] Classify the corrected medical information according to the information processing period, information processing cycle, and information type dimension to obtain corrected medical information under different categories;

[0032] In response to a user's medical information query request, based on the query requirements carried in the query request, determine the corrected medical information under the required category that the user needs among the corrected medical information under different categories, and display the corrected medical information under the required category on the user's display terminal.

[0033] Optionally, the step of inputting the medical information verification data and the to-be-processed medical information into the preset information processing model to obtain the medical information processing result includes:

[0034] Obtain the forward medical information verification data of a preset time before the medical information verification data, and the backward medical information verification data of a preset time after the medical information verification data;

[0035] Determine the verification feature vector corresponding to the medical information verification data, the forward verification feature vector corresponding to the forward medical information verification data, the backward verification feature vector corresponding to the backward medical information verification data, and the medical feature vector corresponding to the to-be-processed medical information;

[0036] Perform cross-processing on the verification feature vector, the forward verification feature vector, the backward verification feature vector, and the medical feature vector to obtain a medical cross vector;

[0037] Input the medical cross vector into the preset information processing model for verification processing to obtain the accuracy verification processing result of the medical information.

[0038] Optionally, before obtaining the to-be-processed medical information based on the data source information and the timestamp information, the method includes:

[0039] Obtain all historical medical information and its corresponding historical data source information before receiving the medical information processing signal, and determine the data source feature vector corresponding to each historical data source information;

[0040] Initialize the initial centroids of different clusters, and determine the centroid vectors corresponding to the initial centroids;

[0041] Calculate the distances between the data source feature vectors and the centroid vectors corresponding to each of the clusters, and based on the distances, partition each of the historical medical information into each of the clusters;

[0042] Based on the data source feature vectors corresponding to the historical medical information in each of the clusters, determine the updated centroid vectors corresponding to each of the clusters;

[0043] Based on the updated centroid vectors, re-partition each of the historical medical information into each of the clusters until the updated centroid vectors do not change, and determine the historical medical information finally partitioned into each of the clusters as the historical medical information under different data source categories;

[0044] Determine the historical timestamp information corresponding to the historical medical information under each of the data source categories, and based on the historical timestamp information, perform clustering processing on the historical medical information under each of the data source categories to obtain the historical medical information under different time categories for each of the data source categories.

[0045] According to the second aspect of the present invention, there is provided a processing device for medical information, including:

[0046] A first determination unit, configured to determine the data source information and timestamp information of the medical information to be processed in response to a medical information processing signal;

[0047] An acquisition unit, configured to acquire the medical information to be processed based on the data source information and the timestamp information, and acquire medical information verification data corresponding to the medical information to be processed;

[0048] A second determination unit, configured to determine the channel information of the medical information verification data, and based on the channel information, determine the information processing method applicable to the medical information to be processed;

[0049] An information processing unit, configured to perform verification processing on the medical information to be processed by using the information processing method and the medical information verification data to obtain a medical information processing result.

[0050] According to the third aspect of the present invention, there is provided a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned processing method for medical information is implemented.

[0051] According to the fourth aspect of the present invention, there is provided a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the above-mentioned processing method for medical information is implemented.

[0052] A method, apparatus, storage medium, and computer device for processing medical information according to the present invention, compared with the current method of manually processing medical information in a unified manner, the present invention determines the data source information and timestamp information of the medical information to be processed in response to a medical information processing signal; and based on the data source information and the timestamp information, obtains the medical information to be processed, and obtains medical information verification data corresponding to the medical information to be processed; then determines the channel information of the medical information verification data, and based on the channel information, determines the information processing method applicable to the medical information to be processed; finally, uses the information processing method and the medical information verification data to perform a verification process on the medical information to be processed to obtain a medical information processing result. Thus, by determining the information processing method applicable to the medical information to be processed through the channel information of the medical information verification data, and using the applicable information processing method to perform a verification process on the medical information to be processed, it is possible to select the applicable information processing method for different medical information to be processed, thereby improving the accuracy of medical information processing. At the same time, the present invention can automatically respond to information processing signals and automatically complete processes such as obtaining and verifying medical information, reducing the risk of manual intervention and errors, and thus improving the processing efficiency and accuracy of medical information. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The illustrative embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0054] Figure 1 A flowchart of a method for processing medical information according to an embodiment of the present invention is shown;

[0055] Figure 2 A functional architecture diagram of an information processing system according to an embodiment of the present invention is shown;

[0056] Figure 3 A functional architecture diagram of a reconciliation system according to an embodiment of the present invention is shown;

[0057] Figure 4 A flowchart of a processing process of a log management module according to an embodiment of the present invention is shown;

[0058] Figure 5 A flowchart of another method for processing medical information according to an embodiment of the present invention is shown;

[0059] Figure 6 A structural schematic diagram of a device for processing medical information according to an embodiment of the present invention is shown;

[0060] Figure 7The figure shows a schematic structural diagram of another medical information processing device provided by an embodiment of the present invention;

[0061] Figure 8 The figure shows a schematic physical structure diagram of a computer device provided by an embodiment of the present invention. Detailed implementation manners

[0062] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments. It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments may be combined with each other.

[0063] Currently, the method of processing medical information through a unified manual verification method will lead to the problem of low information processing efficiency, and the unified method may not be applicable to medical information, resulting in low processing accuracy of medical information.

[0064] To solve the above problems, an embodiment of the present invention provides a method for processing medical information, as Figure 1 shown, the method includes:

[0065] 101. In response to a medical information processing signal, determine the data source information and timestamp information of the medical information to be processed.

[0066] Among them, the medical information may be payment transaction information between a hospital and a patient, medical device procurement transaction information, or a patient's diagnosis information. When the medical information is payment transaction information, the medical information verification data is the bank statement information corresponding to the payment transaction information; when the medical information is medical device procurement transaction information, the medical information verification data is the bank statement information corresponding to the procurement transaction information; when the medical information to be processed is diagnosis information, the medical information verification data may be historical diagnosis results and experimental value inspection results, etc. The data source information refers to the source of the medical information to be processed, including outpatient clinics, inpatient departments, departments, pharmacies, etc.; the timestamp information refers to the generation time of the medical information to be processed.

[0067] For the embodiment of the present invention, it is applied to an information processing system, and the information processing system includes an access layer, an application layer, a domain layer, and an infrastructure layer. As Figure 2As shown, the functional module content of each layer is presented. The access layer is the front end of the system, responsible for interacting with users or other systems, providing user interfaces and API interfaces. The front-end H5 application is reverse-proxied through NGINX (engine x, a high-performance reverse proxy server), passing through the gateway and the permission system, enabling users to access the reconciliation middle platform through the H5 page. The application layer is responsible for coordinating the interaction between the user interface and the domain layer, providing the integration of multiple basic operations, and offering corresponding services to the business layer. It provides the orchestration of business processes and the combination of business logics. The domain layer is the core of the information processing system, responsible for implementing specific information processing business logics and rules. The infrastructure layer provides the technical infrastructure and general services for the reconciliation platform, including data storage technologies, middleware services, network services, monitoring, and logging. Through the information processing system, the present invention automatically processes medical information, avoiding manual participation, thereby improving the processing efficiency and accuracy of medical information. Further, if the information processing system of the embodiment of the present invention processes hospital transaction information (reconciliation processing of transaction information), the information processing system can be deployed in a unified reconciliation platform, such as Figure 3 shows the functional modules of the unified reconciliation platform.

[0068] Specifically, when a medical information processing signal is received, the data source information and timestamp information of the medical information to be processed are determined, and based on the data source information and timestamp information, the medical information to be processed is specifically obtained and specifically processed. By clarifying the data source and timestamp, the medical information that needs to be processed can be accurately located, avoiding the processing of a large amount of irrelevant or redundant information, thereby improving the accuracy of information processing. Specifically obtaining and processing information means that unnecessary steps can be skipped and key information can be directly processed, thus significantly reducing the time required for information processing.

[0069] 102. Based on the data source information and timestamp information, obtain the medical information to be processed and obtain the medical information verification data corresponding to the medical information to be processed.

[0070] Among them, the medical information verification data refers to the data for verifying the accuracy of the medical information to be processed. The medical information verification data is accurate and standard data.

[0071] For the embodiments of the present invention, in order to quickly and accurately obtain the medical information to be processed based on the data source information and the timestamp information, it is first necessary to perform clustering processing on all the medical information stored in the hospital system. Based on this, the method includes: obtaining all the historical medical information and its corresponding historical data source information before receiving the medical information processing signal, and determining the data source feature vectors corresponding to each of the historical data source information; initializing the initial centroids of different clusters, and determining the centroid vectors corresponding to the initial centroids; calculating the distances between the data source feature vectors and the centroid vectors corresponding to each of the clusters, and based on the distances, dividing each of the historical medical information into each of the clusters; determining the updated centroid vectors corresponding to each of the clusters based on the data source feature vectors corresponding to the historical medical information in each of the clusters; based on the updated centroid vectors, re-dividing each of the historical medical information into each of the clusters until the updated centroid vectors do not change, and determining the historical medical information finally divided into each of the clusters as the historical medical information under different data source categories; determining the historical timestamp information corresponding to the historical medical information under each of the data source categories, and based on the historical timestamp information, performing clustering processing on the historical medical information under each of the data source categories to obtain the historical medical information under different time categories under each of the data source categories.

[0072] Specifically, if it is necessary to process medical transaction information, the historical medical information is all the historical medical transaction information. Specifically, select the centroid vectors corresponding to the initial centroids respectively corresponding to K clusters, where the K clusters are the clusters corresponding to different data sources, calculate the distances from each data source feature vector to the K centroid vectors, and allocate the historical medical information corresponding to each data source feature vector to the cluster corresponding to the centroid vector with the closest distance. Then, for each cluster, recalculate the centroid and its corresponding centroid vector of each cluster, and re-divide the historical medical information into different clusters, and continuously divide the historical medical information in this way until the position of the centroid does not change, that is, the centroid vector does not change. Finally, determine the historical medical information divided into different clusters as the historical medical information under different data source categories. Further, cluster the historical medical information under each data source category according to the timestamp information. For example, cluster according to the date, and cluster the historical medical information within the same date into one category.

[0073] Further, after clustering historical medical information according to data sources and time, based on the data source information and timestamp information of the medical information to be processed, obtain the historical medical information (medical information to be processed) corresponding to the data source information and timestamp information from the historical medical information under different data source categories and different time categories. For example, if reconciliation processing is to be performed on payment transaction information generated by the inpatient department on December 24, 2024, the required medical information to be processed needs to be obtained from the historical medical information under different data source categories and different time categories based on the two keywords, namely the inpatient department and December 24, 2024. By clustering historical medical information according to data sources and time in the embodiments of the present invention, it is convenient to quickly and accurately obtain the subsequent medical information to be processed. Further, after obtaining the medical information to be processed, in order to perform accuracy verification processing on the medical information to be processed, it is also necessary to obtain medical information verification data, which can be obtained from the hospital's own system or from a third-party platform.

[0074] 103. Determine the channel information of the medical information verification data, and based on the channel information, determine the information processing method applicable to the medical information to be processed.

[0075] Among them, the channel information refers to the generation channels of the medical information verification data, including the hospital's own channels and third-party channels. If the medical information to be processed is payment transaction information, the hospital's own channel is the hospital's own payment channel, and the third-party channel is other payment channels, such as payment channels like Alipay and WeChat. Different channel information corresponds to different information processing methods. For example, if the format and specification of the medical information verification data in the hospital's own channel are the same as those of the medical information to be processed, a relatively simple information processing method can be used to process the medical information to be processed at this time. However, the format and specification of the medical information verification data corresponding to the third-party channel are different from those of the medical information to be processed, and the processing is more complex. Therefore, a higher-precision information processing method is required to process the medical information to be processed. By processing the medical information to be processed through the information processing method applicable to it in the embodiments of the present invention, waste of processing resources can be avoided, and the accuracy of information processing can be improved.

[0076] 104. Use the information processing method and the medical information verification data to perform reconciliation processing on the medical information to be processed, and obtain the medical information processing result.

[0077] For the embodiments of the present invention, medical information verification data is mainly used to check the accuracy of the medical information to be processed. For example, if the medical information to be processed is payment information, the payment amount is matched with the corresponding amount in the medical information verification data. If the match is successful, it is determined that the medical information to be processed is accurate. If the match is unsuccessful, the medical information to be processed needs to be corrected for anomalies based on the medical information verification data. The embodiments of the present invention determine the applicable information processing method for the medical information to be processed through the channel information of the medical information verification data, and use the applicable information processing method to check the medical information to be processed, which can select the applicable information processing method for different medical information to be processed, thereby improving the processing accuracy of medical information. At the same time, the present invention can automatically respond to information processing signals and automatically complete processing processes such as obtaining and checking medical information, reducing manual intervention and the risk of errors, and thus improving the processing efficiency and accuracy of medical information.

[0078] Further, after checking the accuracy of the medical information to be processed, anomalies in the information also need to be corrected and made convenient for users to view. Based on this, the method includes: if there are anomalies in the medical information to be processed, automatically correct the anomalies based on the medical information verification data; classify the corrected medical information according to the information processing time period, information processing cycle, and information type dimension to obtain corrected medical information under different categories; in response to a user's medical information query request, based on the query requirements carried in the query request, determine the corrected medical information under the required category that the user needs among the corrected medical information under different categories, and display the corrected medical information under the required category on the user's display terminal.

[0079] Among them, anomalies include inconsistencies between the information in the medical information to be processed and the corresponding information in the medical information verification data, or missing information, etc. Specifically, the anomalies are corrected according to the information in the medical information verification data. For example, relevant error handling is performed on abnormal data of unilateral accounts. For standard long-term data (where an actual deduction transaction occurs on the bank side, but there is no such record on the medical institution side), the user can refund this transaction through error handling; for other non-standard long-term data, the user can reconcile this transaction according to the actual situation. To ensure the security of hospital transactions, a certain permission design is made in combination with the user permission system here. All users can apply for processing of abnormal bills, but only hospital administrator accounts with a higher permission level can perform actual review and refund operations.

[0080] Furthermore, the corrected medical information is classified according to the information processing time, information processing cycle, and information type. When the user needs to query the medical information of a certain processing cycle, the corresponding medical information can be quickly found according to the information processing cycle category and displayed to the user's terminal. For example, the information processing system also includes two parts: home page data analysis and business data statistics. The information processing system processes, analyzes, calculates and stores the relevant data on the memory according to the corresponding data processing method. The user can intuitively see the amount and corresponding number of long and short payments, even payments, receivable amounts, actual amounts received, and account amounts. At the same time, the user can also see and download single-dimensional and multi-dimensional statistical reports of the overall income of the hospital, as well as other information, through the visualization page. At the same time, the information processing system also includes a log management module, such as Figure 4 The processing flow of the log management module is shown. The log management module is mainly divided into two parts: user log and background log. The user log records the relevant operation track information of the logged-in user; the background log is used to monitor and record the execution of the hospital's daily information processing, and the failure reasons are recorded in detail for the failed processing tasks. When the original data is wrong and needs to be replaced, a window is left for the business personnel at the same time, and the supplementary collection of missing and erroneous data and the reprocessing of information operations can be completed directly on the visualization page. The information processing system also includes a user module to set user permissions. The user module mainly includes hospital management, merchant management, user management, role management, user log and background log. Using preset data permission strategies to pave the way for the data security needs of medical institutions, refined management and data security management can be achieved. The designed separate user level management can personalize the data that users can see and the page permissions that they can operate according to the user role type.

[0081] A method for processing medical information provided by the present invention, compared with the current method of checking and processing medical information through a unified manual processing method, the present invention determines the data source information and timestamp information of the medical information to be processed in response to a medical information processing signal; and based on the data source information and the timestamp information, obtains the medical information to be processed, and obtains medical information verification data corresponding to the medical information to be processed; then determines the channel information of the medical information verification data, and based on the channel information, determines the information processing method applicable to the medical information to be processed; finally, uses the information processing method and the medical information verification data to check and process the medical information to be processed, and obtains a medical information processing result. Thus, by determining the information processing method applicable to the medical information to be processed through the channel information of the medical information verification data, and using the applicable information processing method to check and process the medical information to be processed, it is possible to select the applicable information processing method for different medical information to be processed, thereby improving the processing accuracy of medical information. At the same time, the present invention can automatically respond to the information processing signal and automatically complete the processing processes such as obtaining and checking medical information, reducing the risk of manual intervention and errors, thereby improving the processing efficiency and processing accuracy of medical information.

[0082] Further, in order to better illustrate the above process of processing medical information, as a refinement and extension of the above embodiment, the embodiment of the present invention provides another method for processing medical information, as Figure 5 shown, the method includes:

[0083] 201. In response to a medical information processing signal, determine the data source information and timestamp information of the medical information to be processed.

[0084] Specifically, when medical information needs to be processed, the user can fill in or select the data source information and timestamp information in the medical information processing system, and the medical information processing system will retrieve the medical information to be processed that meets the user's needs in the database based on the data source information and timestamp information.

[0085] 202. Based on the data source information and timestamp information, obtain the medical information to be processed, and obtain medical information verification data corresponding to the medical information to be processed.

[0086] Specifically, for the acquisition of medical information to be processed, for example, the following three methods (but not limited to any one of them) are used to capture the original data: 1. Data file ftp transfer mode: The data is transmitted in the form of files with fixed rules by medical institutions to the ftp (File Transfer Protocol Server, a computer providing file storage and access services on the Internet) server through the ftp protocol (File Transfer Protocol) or the sftp protocol (Secure File Transfer Protocol). The system captures relevant medical information and medical information verification data corresponding to the medical information based on the data source information and timestamp information at a fixed time every day through a scheduled task; 2. Interface docking mode: The data is transmitted in the form of interfaces. The system calls relevant interfaces at a fixed time every day through a scheduled task to obtain medical information data of relevant data sources and timestamps, as well as medical information verification data corresponding to the medical information; 3. RPA (Robotic Process Automation, a software program) robot automatic capture mode: For some bank data that is inconvenient to obtain, the RPA robot automatically completes relevant online banking logins, bill searches, file downloads, decompressions, and uploads them to the ftp server. The reconciliation system captures the medical information to be processed of relevant data sources and timestamps and the medical information verification data corresponding to the medical information at a fixed time through a scheduled task, and parses and processes the relevant medical information.

[0087] Furthermore, in order to improve data quality, after acquiring the medical information to be processed and the medical information verification data, it is necessary to preprocess the above data. For example. Merge data from different data sources into a consistent data store to support analysis. Use database join operations to merge multiple data tables into one. Perform formatting, normalization, and standardization processing on the data, and convert the data into a format suitable for analysis, etc. Then, according to the preprocessed medical information verification data, perform an accuracy check on the preprocessed medical information to be processed, so as to improve the processing efficiency and accuracy of the information.

[0088] 203. Determine the channel information of the medical information verification data.

[0089] 204. If the channel information is the self-developed channel of the hospital to which the medical information to be processed belongs, determine the round-robin matching processing method applicable to the medical information to be processed.

[0090] 205. Use the round-robin matching processing method to match the medical information verification data and the medical information to be processed, and determine the medical information processing result based on the matching result.

[0091] For the embodiments of the present invention, if the acquisition channel of the medical information verification data is the self-developed channel of the hospital, it indicates that the format and specifications of the medical information verification data are the same as those of the medical information to be processed. At this time, the processing method used for the medical information to be processed is the round-robin matching processing method. Then, the medical information to be processed is processed using the round-robin matching processing method. Based on this, step 205 specifically includes: classifying each piece of the medical information to be processed to obtain medical information under different classification categories, where the different classification categories include: a marked information category with a preset identification mark, the remaining information category, a unilateral data missing information category, an error handling information category, and a reversal information category; determining the matching rounds of round-robin matching corresponding to the medical information under different classification categories, and based on the matching rounds, setting a timing task to perform round-robin matching on the medical information under different classification categories. Among them, the marked information category corresponds to the first round of matching, the remaining information category corresponds to the second round of matching, the unilateral data missing information category corresponds to the third round of matching, the error handling information category corresponds to the fourth round of matching, and the reversal information category corresponds to the fifth round of matching; based on this, the method for setting a timing task to perform round-robin matching on the medical information under different classification categories includes: when the matching task time of the first round of matching arrives, determining a first medical field in the medical information under the marked information category, and determining a first verification field in the medical information verification data that matches the first medical field; determining the first medical information verification data corresponding to the first verification field in the medical information verification data, and determining the first medical information corresponding to the first medical field in the medical information under the marked information category, and matching the first medical information verification data and the first medical information, and based on the matching result, determining the accuracy of the first medical information; storing the medical information under the remaining information category and the medical information verification data in a cache. When the matching task time of the second round of matching arrives, determining a second medical field in the medical information under the remaining information category in the cache, and determining a second verification field in the medical information verification data that matches the second medical field; determining the second medical information verification data corresponding to the second verification field in the medical information verification data, and determining the second medical information corresponding to the second medical field in the medical information under the remaining information category, and matching the second medical information verification data and the second medical information, and based on the matching result, determining the accuracy of the second medical information; when the matching task time of the third round of matching arrives, determining the backward medical information verification data at a preset time after the medical information verification data, and determining a third medical field in the medical information under the unilateral data missing information category, and determining a third verification field in the backward medical information verification data that matches the third medical field;Determine the third medical information verification data corresponding to the third verification field in the backward medical information verification data, and determine the third medical information corresponding to the third medical field in the medical information under the unilateral data missing information category, match the third medical information verification data with the third medical information, and determine the accuracy of the third medical information based on the matching result; when the matching task time of the fourth round of matching arrives, determine the fourth medical field in the medical information under the error handling information category, and determine the fourth verification field matching the fourth medical field in the medical information verification data; determine the fourth medical information verification data corresponding to the fourth verification field in the medical information verification data, and in the single error handling Determine the fourth medical information corresponding to the fourth medical field in the medical information under the information category category, match the fourth medical information verification data with the fourth medical information, and determine the accuracy of the fourth medical information based on the matching result; based on the medical information verification data, perform information missing check on the medical information to be processed, and based on the check result, determine the category of the missing medical information as the reversal information category; when the matching task time of the fifth round of matching arrives, determine the verification data category that matches the reversal information category in the medical information verification data, and determine the account entry information and account exit information under the verification data category; based on the difference between the account entry information and the account exit information, determine the compliance of the information missing under the reversal information category. ;

[0092] Among them, the preset identification mark is set according to actual needs. For example, if the abnormality of the information is known when it is generated, it will be marked. Information that needs to be checked in detail needs to be marked; medical fields and verification fields are matching fields, such as order ID, information generation date, information type code, etc. Specifically, the medical information to be processed contains information of various situations. In order to personalize the information in each situation, it is necessary to classify the medical information to be processed first. If the medical information to be processed contains information with a preset identification mark, the information with the preset identification mark is classified into the marking information category; the information that exists in the medical information to be processed but does not exist in the medical information verification data is classified into the unilateral data missing information category, the information that has been error processed is classified into the error processing information category, and the information that does not exist in the medical information to be processed but exists in the medical information verification data is determined as the correction information category; the information in the medical information other than the marking information category, the unilateral data missing information category, the error processing information category, and the correction information category is determined as the medical information under the remaining information category.

[0093] Specifically, data matching is performed multiple times using a polling method based on preset keyword fields. The processing of the information to be processed for each hospital is regarded as a processing item. The system adopts a polling traversal mode to count all processing items and sequentially execute the relevant logic of data matching. Each round of polling task is preset with a polling time. When the corresponding polling time arrives, the polling task of the corresponding round is started to perform polling matching on the medical information to be processed. First, the medical information to be processed and the medical information verification data that need to be processed under the belonging timestamp and data source category are stored in a computer-readable storage medium; according to the preset relevant conditions and rules, such as according to the information category, the relevant data (medical information under the marked information category) and medical information verification data that need to be preprocessed in the storage medium are found, and they are processed separately and subjected to a round of matching, and the processing results are updated and recorded in the storage medium. The matching rules for this round mainly target the data under the marked information category in the hospital data, and can be customized according to the hospital's needs. For example, the matching fields (such as order number and order type) in the medical information to be processed are determined, and the verification data under the corresponding matching fields in the medical information verification data is determined through the matching fields, and the verification data is used to perform accuracy verification on the medical information to be processed. That is, if a certain medical information in the medical information to be processed is inconsistent with the corresponding information in the medical information verification data, it is determined that the medical information is incorrect, and in this case, the corresponding information in the medical information verification data needs to be used to correct it.

[0094] Furthermore, when the second-round matching time arrives, the medical information under the remaining information categories in the storage medium is subjected to second-round matching, and the processing results are updated and recorded in the storage medium. In this round of rules, the medical information to be processed and the medical information verification data under the remaining information categories are both placed in the cache queue. The medical information to be processed in the hospital is traversed, and it is matched with the medical information verification data in the cache queue through the matching fields (such as order keyword fields: order number, order type, etc.). After successful matching, information such as the transaction amount is further compared. If the transaction amounts are the same, it is determined that the medical information to be processed is correct; otherwise, the medical information to be processed is corrected.

[0095] Furthermore, when the third-round matching time arrives, if the information to be processed is processed by day, the medical information verification data for the day after the date of the medical information verification data is queried. The medical information to be processed under the category of unilateral data missing information in the hospital is traversed, and it is matched with the medical information verification data for the day after through the matching fields (such as order keyword fields: order number, order type, etc.). After successful matching, information such as the transaction amount is further compared. If the transaction amounts are the same, it is determined that the medical information to be processed is correct; otherwise, the medical information to be processed is corrected. The processing results are updated and recorded in the storage medium. The matching rules for this round mainly target the abnormal matching problems caused by the cut-off point of the bank bill date.

[0096] Further, when the four-round matching time arrives, if there is medical information with successful error handling on the current date, find the corresponding medical information in the storage medium according to the flag of the medical information with successful error handling in the memory, and perform four-round matching on the medical information with successful error handling and the medical information verification data, and update and record the processing result in the storage medium. For example, this round of matching rules mainly applies to information that has undergone error transactions on the platform, generated return transactions and is marked as shortfall anomaly. Such information is only recorded on the hospital side and the medical information verification data side. The matching method is to match through the matching fields in the medical information to be processed (such as order key fields: order number, order type, etc.) with the medical information verification data. After successful matching, further compare information such as the transaction amount. If the transaction amounts are the same, it is determined that the medical information to be processed is correct.

[0097] Further, when the five-round matching time arrives, perform five-round matching on the medical information to be processed that remains unmatched and needs to be reversed in the memory medium according to the keyword, and update and record the reconciliation result in the storage medium. This round of matching mainly applies to the medical information to be processed without a hospital, but there are data in the medical information verification data that can be exactly matched with one positive and one negative or one positive and multiple negatives. This round of matching mainly processes the cases that fail to match successfully after the first four rounds of matching, and the exception flag indicates that no matching medical information to be processed can be found. For example, first classify such information according to the transaction type into consumption and return, and then match the key reconciliation fields of the consumption type with the keyword fields of the return type. After successful matching, judge whether the consumption amount is consistent with the total amount of all successfully matched return amounts. If they are consistent, it is considered that the several transactions are successfully reversed. Thus, the five-round matching is completed, the final result in the storage medium is retained, and the relevant data is processed and stored in the relevant memory of the system. In the embodiments of the present invention, different processing rounds are set for different categories of medical information to be processed, because different categories of medical information have different characteristics and importance. By setting different processing rounds for them, it can be ensured that each category of information receives appropriate attention and processing. This targeted processing method helps to avoid blindness and randomness in information processing, thereby improving the efficiency of information processing.

[0098] 206. If the channel information is a third-party channel of the hospital to which the medical information to be processed belongs, determine the preset information processing model applicable to the medical information to be processed.

[0099] 207. Input the medical information verification data and the medical information to be processed into the preset information processing model to obtain the medical information processing result.

[0100] For the embodiments of the present invention, if the channel information is a third-party channel of the hospital to which the medical information to be processed belongs, the format, specification, and other forms of the medical information verification data at this time are different from the medical information to be processed. Therefore, it is necessary to select a preset information processing model with a higher processing accuracy to check and process the medical information to be processed. In order to further improve the processing accuracy of the preset information processing model, it is first necessary to construct the preset information processing model. Based on this, the method includes: constructing an initial model and obtaining a sample data set, where the sample data set includes sample medical information with label information and sample medical information verification data, and the label information is the accuracy of the sample medical information; dividing the sample data set into training data and test data, training the initial model with the training data, and testing the trained initial model with the test data, and finally determining the initial model that meets the test conditions as the preset information processing model. Among them, the sample medical information may include: sample medical payment information, sample medical diagnosis information, sample medical procurement transaction information, etc. The sample medical information verification data is standard medical data of the same category as the sample medical information.

[0101] Further, after constructing the preset information processing model, it is necessary to use the preset information processing model and the medical information verification data to perform an accuracy check and processing on the medical information to be processed. Based on this, step 207 specifically includes: obtaining the forward medical information verification data of the preset time before the medical information verification data, and the backward medical information verification data of the preset time after the medical information verification data; determining the verification feature vector corresponding to the medical information verification data, the forward verification feature vector corresponding to the forward medical information verification data, the backward verification feature vector corresponding to the backward medical information verification data, and the medical feature vector corresponding to the medical information to be processed; performing cross-processing on the verification feature vector, the forward verification feature vector, the backward verification feature vector, and the medical feature vector to obtain a medical cross vector; inputting the medical cross vector into the preset information processing model for check and processing to obtain the accuracy check and processing result of the medical information. Among them, the method of performing cross-processing on the verification feature vector, the forward verification feature vector, the backward verification feature vector, and the medical feature vector includes: performing feature-level cross-processing on the verification feature vector, the forward verification feature vector, the backward verification feature vector, and the medical feature vector to obtain a feature cross vector; performing element-level cross-processing on the verification feature vector, the forward verification feature vector, the backward verification feature vector, and the medical feature vector to obtain an element cross vector; performing low-order cross-processing on the verification feature vector, the forward verification feature vector, the backward verification feature vector, and the medical feature vector to obtain a low-order cross vector; using a preset transformation function to perform combination processing on the feature cross vector, the element cross vector, and the low-order cross vector to obtain the medical cross vector.

[0102] Specifically, the verification feature vector corresponding to the medical information verification data, the forward verification feature vector corresponding to the forward medical information verification data, the backward verification feature vector corresponding to the backward medical information verification data, and the medical feature vector corresponding to the medical information to be processed are respectively determined by means of word embedding, etc. Then, in order to make full use of the relationships between the data, extract more implicit features, take into account both high-order and low-order processing, make the data utilization more sufficient, and make the subsequent prediction results more accurate to meet the requirements of the actual application scenario, it is necessary to perform cross-processing on the verification feature vector, the forward verification feature vector, the backward verification feature vector, and the medical feature vector. The specific cross-processing method is as follows: If the verification feature vector is (a1, a2), the forward verification feature vector is (b1, b2), the backward verification feature vector is (c1, c2), and the medical feature vector is (d1, d2), the specific cross-processing methods include: performing feature-level cross on different feature vectors, that is, after performing the Hadamard product on all elements between the vectors, performing a convolution transformation under a certain weight to obtain a feature cross vector of f(w*(a1*b1*c1*d1, a2*b2*c2*d2, a3*b3*c3*d3)); at the same time, performing element-level cross on all feature vector data, that is, performing the Hadamard product on each element between the vectors, assigning different weight values to each product result, and then performing a linear transformation to obtain an element cross vector of f(w1*a1*b1*c1*d1, w2*a2*b2*d2*c2, w3*a3*b3*c3*d3); in addition, performing low-order cross-processing on all feature vectors, then assigning a weight coefficient to the result of the cross-processing, and then performing a linear transformation to obtain a low-order cross vector of f(w2(a1, a2, b1, b2, c1, c2, d1d2)); finally, using a preset transformation function to perform transformation processing on the above feature cross vector, element cross vector, and low-order cross vector, such as horizontal splicing, to obtain a medical cross vector. It should be noted that the preset transformation function can be set according to the actual situation, and this embodiment does not limit it. And the above examples are only illustrative and do not limit the embodiments of the present application. Thus, by performing cross-processing on the verification feature vector, the forward verification feature vector, the backward verification feature vector, and the medical feature vector, different features can be automatically or explicitly combined to generate new feature combinations. These combined features may contain complex non-linear relationships between the original features, enabling the model to capture more refined and rich information in the data, that is, being able to make full use of the relationships between various data, extract more implicit features, take into account both high-order and low-order processing, make the data utilization more sufficient, and make the subsequent information verification results more accurate to meet the requirements of the actual application scenario. Further, the medical cross vector is input into a preset information processing model for verification processing to obtain the accuracy verification processing result of the medical information. Then, according to the accuracy verification result, the medical information to be processed is corrected.

[0103] According to another method for processing medical information provided by the present invention, compared with the current method of manually checking and processing medical information in a unified manner, the present invention determines the data source information and timestamp information of the medical information to be processed in response to a medical information processing signal; and based on the data source information and the timestamp information, obtains the medical information to be processed, and obtains medical information verification data corresponding to the medical information to be processed; then determines the channel information of the medical information verification data, and based on the channel information, determines the information processing method applicable to the medical information to be processed; finally, uses the information processing method and the medical information verification data to perform a checking process on the medical information to be processed to obtain a medical information processing result. Thus, by determining the information processing method applicable to the medical information to be processed through the channel information of the medical information verification data, and using the applicable information processing method to perform a checking process on the medical information to be processed, it is possible to select an appropriate information processing method for different medical information to be processed, thereby improving the processing accuracy of medical information. At the same time, the present invention can automatically respond to the information processing signal and automatically complete the processes of obtaining and checking medical information, reducing the risk of manual intervention and errors, and thus improving the processing efficiency and processing accuracy of medical information. Further, in order to improve the information processing accuracy, a review process can also be performed on the processed and corrected medical information.

[0104] Further, as Figure 1 a specific implementation, an embodiment of the present invention provides a device for processing medical information, as Figure 6 shown, the device includes: a first determination unit 31, an acquisition unit 32, a second determination unit 33, and an information processing unit 34.

[0105] The first determination unit 31 can be used to determine the data source information and timestamp information of the medical information to be processed in response to a medical information processing signal.

[0106] The acquisition unit 32 can be used to obtain the medical information to be processed based on the data source information and the timestamp information, and obtain medical information verification data corresponding to the medical information to be processed.

[0107] The second determination unit 33 can be used to determine the channel information of the medical information verification data, and based on the channel information, determine the information processing method applicable to the medical information to be processed.

[0108] The information processing unit 34 can be used to perform a checking process on the medical information to be processed using the information processing method and the medical information verification data to obtain a medical information processing result.

[0109] In a specific application scenario, the channel information includes the self-developed channels and third-party channels of the hospital to which the medical information to be processed belongs; the information processing methods include the round-robin matching processing method corresponding to the self-developed channels and the preset information processing model processing method corresponding to the third-party channels; in order to process the medical information to be processed, such as Figure 7 As shown, the information processing unit 34 includes a matching module 341 and a processing module 342.

[0110] The matching module 341 can be used to match the medical information verification data and the medical information to be processed by using the round-robin matching processing method, and determine the medical information processing result based on the matching result.

[0111] The processing module 342 can be used to input the medical information verification data and the medical information to be processed into the preset information processing model to obtain the medical information processing result.

[0112] In a specific application scenario, in order to match the medical information verification data and the medical information to be processed, the matching module 341 can specifically be used to classify each piece of medical information to be processed to obtain medical information under different classification categories, where the different classification categories include: a marked information category with a preset identification mark, other information categories, a unilateral data missing information category, an error handling information category, and a reversal information category; determine the matching rounds of round-robin matching corresponding to the medical information under different classification categories, and set a timing task to perform round-robin matching on the medical information under different classification categories based on the matching rounds.

[0113] In a specific application scenario, the marker information category corresponds to the first-round matching, the remaining information category corresponds to the second-round matching, the unilateral data missing information category corresponds to the third-round matching, the error handling information category corresponds to the fourth-round matching, and the reversal information category corresponds to the fifth-round matching; To perform information matching, the matching module 341 can specifically be used to, when the matching task time of the first-round matching arrives, determine the first medical field in the medical information under the marker information category, and determine the first verification field that matches the first medical field in the medical information verification data; Determine the first medical information verification data corresponding to the first verification field in the medical information verification data, and determine the first medical information corresponding to the first medical field in the medical information under the marker information category, and match the first medical information verification data and the first medical information, and based on the matching result, determine the accuracy of the first medical information; Store the medical information under the remaining information category and the medical information verification data in the cache. When the matching task time of the second-round matching arrives, determine the second medical field in the medical information under the remaining information category in the cache, and determine the second verification field that matches the second medical field in the medical information verification data; Determine the second medical information verification data corresponding to the second verification field in the medical information verification data, and determine the second medical information corresponding to the second medical field in the medical information under the remaining information category, and match the second medical information verification data and the second medical information, and based on the matching result, determine the accuracy of the second medical information; When the matching task time of the third-round matching arrives, determine the backward medical information verification data at a preset time after the medical information verification data, and determine the third medical field in the medical information under the unilateral data missing information category, and determine the third verification field that matches the third medical field in the backward medical information verification data; Determine the third medical information verification data corresponding to the third verification field in the backward medical information verification data, and determine the third medical information corresponding to the third medical field in the medical information under the unilateral data missing information category, and match the third medical information verification data and the third medical information, and based on the matching result, determine the accuracy of the third medical information; When the matching task time of the fourth-round matching arrives, determine the fourth medical field in the medical information under the error handling information category, and determine the fourth verification field that matches the fourth medical field in the medical information verification data;Determine the fourth medical information verification data corresponding to the fourth verification field in the medical information verification data, and determine the fourth medical information corresponding to the fourth medical field in the medical information under the single error handling information category. Then, match the fourth medical information verification data with the fourth medical information, and based on the matching result, determine the accuracy of the fourth medical information. Based on the medical information verification data, conduct a check on the missing information of the medical information to be processed. Based on the check result, determine the category of the missing medical information as the reversal information category. When the matching task time of the fifth round arrives, determine the verification data category that matches the reversal information category in the medical information verification data, and determine the incoming information and outgoing information under the verification data category. Based on the difference between the incoming information and the outgoing information, determine the compliance of the missing information under the reversal information category.

[0114] In a specific application scenario, in order to correct and display the processed medical information, the device further includes: a display unit 35.

[0115] The display unit 35 can be used to automatically correct the abnormal information based on the medical information verification data if there is abnormal information in the medical information to be processed; classify the corrected medical information according to the information processing period, information processing cycle, and information type dimension to obtain the corrected medical information under different categories; in response to the user's medical information query request, based on the query requirements carried in the query request, determine the corrected medical information under the required category that the user needs among the corrected medical information under different categories, and display the corrected medical information under the required category on the user's display terminal.

[0116] In a specific application scenario, in order to process medical information, the processing module 342 can specifically be used to obtain the forward medical information verification data before a preset time of the medical information verification data, and the backward medical information verification data after the preset time of the medical information verification data; determine the verification feature vector corresponding to the medical information verification data, the forward verification feature vector corresponding to the forward medical information verification data, the backward verification feature vector corresponding to the backward medical information verification data, and the medical feature vector corresponding to the medical information to be processed; perform cross-processing on the verification feature vector, the forward verification feature vector, the backward verification feature vector, and the medical feature vector to obtain a medical cross vector; input the medical cross vector into the preset information processing model for verification processing to obtain the accuracy verification processing result of the medical information.

[0117] In a specific application scenario, in order to cluster all medical information in a hospital, the device further includes a clustering unit 36.

[0118] The clustering unit 36 can be used to obtain all historical medical information and its corresponding historical data source information before receiving the medical information processing signal, and determine the data source feature vectors corresponding to the respective historical data source information; initialize the initial centroids of different clusters, and determine the centroid vectors corresponding to the initial centroids; calculate the distances between the data source feature vectors and the centroid vectors corresponding to each of the clusters, and based on the distances, divide the respective historical medical information into each of the clusters; determine the updated centroid vectors corresponding to each of the clusters based on the data source feature vectors corresponding to the historical medical information in each of the clusters; based on the updated centroid vectors, re-divide the respective historical medical information into each of the clusters until the updated centroid vectors do not change, and determine the historical medical information finally divided into each of the clusters as the historical medical information under different data source categories; determine the historical timestamp information corresponding to the historical medical information under each of the data source categories, and based on the historical timestamp information, perform clustering processing on the historical medical information under each of the data source categories to obtain the historical medical information under different time categories under each of the data source categories.

[0119] It should be noted that for other corresponding descriptions of each functional module involved in the medical information processing device provided in the embodiments of the present invention, reference can be made to Figure 1 the corresponding description of the method shown, which will not be elaborated here.

[0120] Based on the above as Figure 1 shown in the method, correspondingly, the embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the following steps are implemented: in response to a medical information processing signal, determine the data source information and timestamp information of the medical information to be processed; based on the data source information and the timestamp information, obtain the medical information to be processed, and obtain the medical information verification data corresponding to the medical information to be processed; determine the channel information of the medical information verification data, and based on the channel information, determine the information processing method applicable to the medical information to be processed; use the information processing method and the medical information verification data to perform a verification process on the medical information to be processed to obtain a medical information processing result.

[0121] Based on the above as Figure 1 shown in the method and as Figure 6 shown in the embodiment of the device, the embodiments of the present invention further provide an entity structure diagram of a computer device, as Figure 8As shown in the figure, the computer device includes: a processor 41, a memory 42, and a computer program stored on the memory 42 and executable on the processor. Both the memory 42 and the processor 41 are provided on a bus 43. When the processor 41 executes the program, the following steps are implemented: in response to a medical information processing signal, determine the data source information and timestamp information of the medical information to be processed; based on the data source information and the timestamp information, obtain the medical information to be processed, and obtain medical information verification data corresponding to the medical information to be processed; determine the channel information of the medical information verification data, and based on the channel information, determine the information processing method applicable to the medical information to be processed; use the information processing method and the medical information verification data to perform a verification process on the medical information to be processed to obtain a medical information processing result.

[0122] Through the technical solution of the present invention, the present invention determines the data source information and timestamp information of the medical information to be processed in response to a medical information processing signal; and based on the data source information and the timestamp information, obtains the medical information to be processed, and obtains medical information verification data corresponding to the medical information to be processed; then determines the channel information of the medical information verification data, and based on the channel information, determines the information processing method applicable to the medical information to be processed; finally, uses the information processing method and the medical information verification data to perform a verification process on the medical information to be processed to obtain a medical information processing result. Thus, by determining the information processing method applicable to the medical information to be processed through the channel information of the medical information verification data, and using the applicable information processing method to perform a verification process on the medical information to be processed, it is possible to select the applicable information processing method for different medical information to be processed, thereby improving the processing accuracy of medical information. At the same time, the present invention can automatically respond to the information processing signal and automatically complete the processing processes such as obtaining and verifying medical information, reducing the risk of manual intervention and errors, and thus improving the processing efficiency and processing accuracy of medical information.

[0123] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present invention can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Optionally, they can be implemented by program codes executable by the computing device, so that they can be stored in a storage device and executed by the computing device. And in some cases, the steps shown or described can be executed in a different order than here, or they can be separately made into individual integrated circuit modules, or multiple modules or steps among them can be made into a single integrated circuit module to implement. In this way, the present invention is not limited to any specific combination of hardware and software.

[0124] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for processing medical information, characterized in that: include: In response to the medical information processing signal, determining data source information and timestamp information of the medical information to be processed; Based on the data source information and the timestamp information, obtaining the medical information to be processed, and obtaining the medical information verification data corresponding to the medical information to be processed; Determine the channel information of the medical information verification data, and based on the channel information, determine the information processing method applicable to the medical information to be processed; The medical information to be processed is checked and processed using the information processing method and the medical information verification data to obtain a medical information processing result.

2. The method according to claim 1, characterized in that The channel information includes the self-developed channel and the third-party channel of the hospital to which the medical information to be processed belongs; the information processing method includes the round-robin matching processing method corresponding to the self-developed channel and the preset information processing model processing method corresponding to the third-party channel; The method of using the information processing method and the medical information verification data to check and process the medical information to be processed to obtain a medical information processing result includes: Using the round-robin matching processing method, the medical information verification data is matched with the medical information to be processed, and based on the matching result, the medical information processing result is determined; The medical information verification data and the medical information to be processed are input into the preset information processing model to obtain the medical information processing result.

3. The method according to claim 2, characterized in that The method of matching the medical information verification data with the medical information to be processed by using the round-robin matching processing method includes: Classifying each of the medical information to be processed to obtain medical information under different classification categories, wherein the different classification categories include: a marked information category with a preset identification mark, a remaining information category, a unilateral data missing information category, an error handling information category, and a reversal information category; The matching rounds of patrol matching corresponding to the medical information under different classification categories are determined, and based on the matching rounds, a scheduled task is set to perform patrol matching on the medical information under different classification categories.

4. The method according to claim 3, characterized in that The marking information category corresponds to the first round of matching, the remaining information category corresponds to the second round of matching, the unilateral data missing information category corresponds to the third round of matching, the error handling information category corresponds to the fourth round of matching, and the reversal information category corresponds to the fifth round of matching; The method of setting a scheduled task to perform round-trip matching on medical information under different classification categories based on the matching rounds includes: When the matching task time of the first round of matching arrives, determining a first medical field in the medical information under the tag information category, and determining a first verification field matching the first medical field in the medical information verification data; Determining the first medical information verification data corresponding to the first verification field in the medical information verification data, and determining the first medical information corresponding to the first medical field in the medical information under the tag information category, matching the first medical information verification data with the first medical information, and determining the accuracy of the first medical information based on the matching result; storing the medical information under the remaining information categories and the medical information verification data in a cache, and when the matching task time of the second round of matching arrives, determining a second medical field in the medical information under the remaining information categories in the cache, and determining a second verification field matching the second medical field in the medical information verification data; Determining the second medical information verification data corresponding to the second verification field in the medical information verification data, and determining the second medical information corresponding to the second medical field in the medical information under the remaining information categories, matching the second medical information verification data with the second medical information, and determining the accuracy of the second medical information based on the matching result; When the matching task time of the third round of matching arrives, determine the backward medical information verification data of the preset time after the medical information verification data, determine the third medical field in the medical information under the unilateral data missing information category, and determine the third verification field matching the third medical field in the backward medical information verification data; Determine the third medical information verification data corresponding to the third verification field in the backward medical information verification data, and determine the third medical information corresponding to the third medical field in the medical information under the unilateral data missing information category, match the third medical information verification data with the third medical information, and determine the accuracy of the third medical information based on the matching result; When the matching task time of the fourth round of matching arrives, determining a fourth medical field in the medical information under the error handling information category, and determining a fourth verification field matching the fourth medical field in the medical information verification data; Determining fourth medical information verification data corresponding to the fourth verification field in the medical information verification data, and determining fourth medical information corresponding to the fourth medical field in the medical information under the single error handling information category, and matching the fourth medical information verification data with the fourth medical information, and determining the accuracy of the fourth medical information based on the matching result; Based on the medical information verification data, the to-be-processed medical information is checked for missing information, and based on the check result, the category of the missing medical information is determined as the category of the reversal information, and when the matching task time of the fifth round of matching arrives, the category of the verification data that matches the category of the reversal information is determined in the medical information verification data, and the account entry information and account exit information under the verification data category are determined; Based on the difference between the deposit information and the withdrawal information, the compliance of the missing information under the reversal information category is determined.

5. The method according to claim 1, characterized in that After the medical information to be processed is checked and processed by using the information processing method and the medical information verification data to obtain a medical information processing result, the method further includes: If there is abnormal information in the medical information to be processed, the abnormal information is automatically corrected based on the medical information verification data; Classify the corrected medical information according to the information processing period, information processing cycle, and information type dimensions to obtain corrected medical information under different categories; In response to a user's medical information query request, based on the query requirements carried in the query request, the corrected medical information under the requirement category required by the user is determined from the corrected medical information under different categories, and the corrected medical information under the requirement category is displayed on the user's display terminal.

6. The method according to claim 2, characterized in that The step of inputting the medical information verification data and the to-be-processed medical information into the preset information processing model to obtain the medical information processing result includes: Acquire forward medical information verification data of a preset time before the medical information verification data, and backward medical information verification data of a preset time after the medical information verification data; Determine a verification feature vector corresponding to the medical information verification data, a forward verification feature vector corresponding to the forward medical information verification data, a backward verification feature vector corresponding to the backward medical information verification data, and a medical feature vector corresponding to the medical information to be processed; Cross-processing the verification feature vector, the forward verification feature vector, the backward verification feature vector, and the medical feature vector to obtain a medical cross-vector; The medical cross vector is input into the preset information processing model for verification processing to obtain the accuracy verification processing result of the medical information.

7. The method according to claim 1, characterized in that Before acquiring the medical information to be processed based on the data source information and the timestamp information, the method includes: Acquire all historical medical information and its corresponding historical data source information before receiving the medical information processing signal, and determine the data source feature vector corresponding to each of the historical data source information; Initializing the initial centroids of different clusters, and determining the centroid vectors corresponding to the initial centroids; Calculating the distance between the data source feature vector and the centroid vector corresponding to each cluster, and dividing each historical medical information into each cluster based on the distance; Determine an updated centroid vector corresponding to each cluster based on a data source feature vector corresponding to the historical medical information in each cluster; Based on the updated centroid vector, each of the historical medical information is re-divided into each of the clusters until the updated centroid vector does not change, and the historical medical information finally divided into each of the clusters is determined as historical medical information under different data source categories; Determine the historical timestamp information corresponding to the historical medical information under each of the data source categories, and based on the historical timestamp information, cluster the historical medical information under each of the data source categories to obtain the historical medical information under different time categories under each of the data source categories.

8. A medical information processing device, characterized in that: include: A first determining unit, configured to determine data source information and timestamp information of the medical information to be processed in response to the medical information processing signal; an acquisition unit, configured to acquire the medical information to be processed based on the data source information and the timestamp information, and acquire medical information verification data corresponding to the medical information to be processed; A second determining unit, configured to determine the channel information of the medical information verification data, and based on the channel information, determine an information processing method applicable to the medical information to be processed; The information processing unit is used to use the information processing method and the medical information verification data to verify the medical information to be processed and obtain a medical information processing result.

9. A 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 the method according to any one of claims 1 to 7 are implemented.

10. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images