Automatic discharge monitoring system based on data processing

Abstract

The present invention relates to the field of medical data processing technology, and in particular to an automatic discharge monitoring system based on data processing. The system includes a remote monitoring module, a medical health database, a data processing module, a data analysis module, and an early warning module. The present invention analyzes and processes the monitored self-reported data to efficiently identify repeated content appearing in text data, that is, by performing extended scanning and detection on keywords, it avoids repeated matching of repeated real-time keywords in the database, that is, avoids repeated detection of matches, improves data processing efficiency, deletes repeated content, processes data in a timely and effective manner, reduces repeated and redundant information in medical health data, improves data quality and availability, determines different risk levels based on the degree of correlation between the self-reported content and the condition, and the monitoring results of physical health parameters, analyzes discharge monitoring data in more detail, and improves system management efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and in particular to an automatic discharge monitoring system based on data processing. Background Art

[0002] Since there is a clinical need to monitor the health status of patients after discharge, how to combine medical health data, sensor technology, remote monitoring and other technologies to provide more comprehensive and timely monitoring and intervention to ensure that patients can receive effective care and management after discharge is becoming an increasingly hot topic for technical personnel in related fields.

[0003] Chinese patent publication number: CN111429986A, discloses a system and method for comprehensive feedback query of patient cases after discharge based on big data, the system includes an identity authentication login module, a patient medical data query module, a patient health status return visit module, a patient data information database and an emergency condition feedback module, the identity authentication login module is used to verify the identity of the doctor and the patient, the patient medical data query module is used to upload the patient's condition in real time, the patient health status return visit module is used to monitor the patient's physical condition in real time after the patient is discharged, the patient data information database is used to store statistics on the patient's hospitalization and discharge, and the emergency condition feedback module is used to enable the patient to seek help from the doctor in time in an emergency after discharge; it can be seen that

[0004] The existing discharge monitoring system lacks analysis and processing of the self-reported data, cannot efficiently identify repeated content in text data, and cannot analyze the discharge monitoring data based on the relevance of the self-reported content and the condition, resulting in low management efficiency of the system. Summary of the invention

[0005] To this end, the present invention provides an automatic discharge monitoring system based on data processing to overcome the problem in the prior art that the data quality is difficult to ensure due to the lack of processing of monitored patient input data and analysis of associated health test data, thereby leading to low system management efficiency.

[0006] To achieve the above object, the present invention provides an automatic discharge monitoring system based on data processing, comprising:

[0007] A remote monitoring module, used to collect medical and health data from the user, the medical and health data including physical health parameters and self-reported data;

[0008] Medical health database, used to store a number of medical keyword data packets;

[0009] A data processing module, which is connected to the remote monitoring module and the medical health database respectively, and is used to pre-process the self-reported data to obtain data to be scanned, scan and delete the data to be scanned, obtain discharge pathology data, and input it into the medical health database for storage;

[0010] Wherein, the data processing module includes:

[0011] A scanning matching unit, scanning the data to be scanned with a preset scanning length to obtain a current detection data segment, extracting real-time keywords in the current detection data segment for matching in the medical health database, and determining the keywords to be detected according to the matching results;

[0012] Wherein, when the scanning matching unit determines that the number of the extracted real-time keywords is greater than or equal to one and there is a match with the medical keyword, the real-time keyword is marked as a keyword to be detected;

[0013] An extended matching unit, configured to continuously extend and scan the keywords to be detected to obtain extended character segments, perform matching detection on the extended character segments according to the keywords to be detected, and determine whether to delete the extended character segments according to the matching detection results to obtain the discharge pathology data;

[0014] A data analysis module, which is connected to the remote monitoring module and the data processing module respectively, and is used to perform correlation analysis on the discharge pathology data and the physical health parameters to output a corresponding identification risk level;

[0015] An early warning module is connected to the data analysis module and is used to determine whether to issue an early warning prompt based on the analysis results of the data analysis module.

[0016] Furthermore, a preset scan length is set in the scan matching unit. For any data to be scanned, the scan matching unit scans the text data with the preset scan length to obtain a current detection data segment, extracts medical-related keywords in the current detection data segment as real-time keywords, and determines the number of the extracted real-time keywords.

[0017] If the number of the extracted real-time keywords is greater than or equal to one, matching the real-time keywords with the medical keywords in the medical health database to determine whether to mark the real-time keywords;

[0018] If the number of the extracted real-time keywords is less than one, a matching determination is performed on the next detection data segment.

[0019] Further, when the number of the extracted real-time keywords is determined to be greater than or equal to one, the scanning matching unit selects a real-time keyword in chronological order, and performs matching determination between the real-time keyword and the medical keyword in the medical health database.

[0020] If there is a match with the medical keyword, the keyword to be detected is obtained;

[0021] If there is no match with the medical keyword, continue to match the next real-time keyword.

[0022] Until the matching judgment of each real-time keyword in the current detection data segment is completed, if it is determined that there is no match with the medical keyword, the current detection data segment is marked as an unassociated data segment. After it is determined that there is no match with the medical keyword and the scanning and processing of the text data is completed, the data analysis module obtains the percentage of the number of unassociated data segments to the total number of detection data segments to obtain the real-time difference ratio.

[0023] Furthermore, the continuous extended scanning includes taking the character length of the keyword to be detected as the detection character length, taking the next adjacent character of the keyword to be detected as the starting node, and performing continuous extended scanning on the text data with the detection character length to obtain an extended character segment.

[0024] Further, any medical keyword data packet includes a disease keyword and an associated keyword corresponding to the disease keyword;

[0025] The result of the matching detection includes obtaining the disease keyword and the associated keyword corresponding to the keyword to be detected in the medical health database as a plurality of keywords to be matched, and performing matching detection on the extended character segment according to each of the keywords to be matched,

[0026] If the keyword to be matched matches the extended character segment, it is determined that duplicate data exists, the extended character segment is deleted, and the keyword to be detected is continuously extended and scanned to obtain the extended character segment, so as to perform matching detection on the extended character segment;

[0027] If the keyword to be matched does not match the extended character segment, it is determined that no duplicate data occurs, and a continuous extended scan of the keyword to be detected is completed. A continuous extended scan is performed on the next keyword to be detected to obtain the corresponding extended character segment to determine whether to delete the extended character segment.

[0028] Furthermore, the data analysis module obtains the monitoring result of the early warning module on the health parameter, and makes a determination based on the monitoring result.

[0029] If a warning prompt is displayed for the physical health parameter, the real-time difference ratio will be judged according to the first standard difference ratio to determine whether to display a first-level warning prompt;

[0030] If no warning prompt is displayed for the physical health parameter, no warning prompt is displayed.

[0031] Furthermore, when the data analysis module displays an early warning prompt for the physical health parameter, it obtains the real-time difference proportion and determines the real-time difference proportion according to the first standard difference proportion.

[0032] If the real-time difference ratio is less than the first standard difference ratio, the processed text data is used as the discharge pathology data, and a first-level warning prompt is displayed;

[0033] If the real-time difference ratio is greater than the first standard difference ratio, the real-time difference ratio will be judged based on the second standard difference ratio and the monitoring results to determine the warning risk level and whether to delete the self-reported data.

[0034] Furthermore, when the data analysis module determines that the real-time difference ratio is greater than the first standard difference ratio, the real-time difference ratio is determined according to the second standard difference ratio.

[0035] If the real-time difference ratio is less than the second standard difference ratio, the real-time difference ratio is judged according to the monitoring results to determine the risk level;

[0036] If the real-time difference ratio is greater than or equal to the second standard difference ratio, the percentage of the cumulative character length of each real-time keyword in the text data is obtained to obtain the real-time completeness, and the real-time difference ratio is judged according to the monitoring results to determine whether to display a third-level warning prompt.

[0037] Furthermore, when the data analysis module determines that the real-time difference ratio is greater than or equal to the second standard difference ratio, the real-time completeness is determined according to the standard completeness.

[0038] If the real-time completeness is less than the standard completeness, the self-reported data is deleted and a three-level warning prompt is displayed;

[0039] If the real-time completeness is greater than or equal to the standard completeness, a level 4 warning prompt will be displayed.

[0040] Further, the data analysis module determines the real-time difference proportion according to the monitoring result when determining that the real-time difference proportion is less than the second standard difference proportion.

[0041] If a warning prompt is displayed for the physical health parameter, a second-level warning prompt is displayed;

[0042] If no warning prompt is displayed for the physical health parameter, no warning prompt is displayed.

[0043] Compared with the prior art, the beneficial effect of the present invention lies in that, by analyzing and processing the monitored self-reported data, repeated content appearing in the text data can be efficiently identified, that is, by performing extended scanning detection on the keyword, and by continuously obtaining extended character segments adjacent to the keyword and with the same character length, until it is determined that the extended character segment does not match the keyword, the extended scanning detection of the current keyword is stopped, thereby avoiding repeated matching of repeated real-time keywords in the database, that is, avoiding repeated detection of matches, improving data processing efficiency, deleting repeated content, processing data in a timely and effective manner, reducing repeated and redundant information in medical and health data, improving data quality and availability, and determining different risk levels based on the degree of relevance of the self-reported content and the condition, as well as the monitoring results of physical health parameters, analyzing discharge monitoring data in more detail, and improving system management efficiency.

[0044] Furthermore, by obtaining the current detection data segment, real-time keywords in the current detection data segment are extracted to process or analyze the text data in the window at each window position. By adopting a fast scanning method, the input self-description content is analyzed and processed. The method is simple and effective.

[0045] In particular, when it is determined that the number of the extracted real-time keywords is greater than or equal to one, the extracted keywords are matched in chronological order to ensure the orderliness of data processing. Since the self-report data input by the patient may be incomplete or irrelevant to the condition, the self-report data needs to be analyzed in detail to ensure the accuracy of the data in a timely manner. At the same time, after completing the scanning and analysis of the text data, if it is still determined that there is no match with the medical keyword, it means that the self-report content is irrelevant to the condition, then the analysis is performed by associating the physical health parameters to determine whether the abnormal self-report content can also be accurately analyzed, that is, by associating the collected physical health parameter data of the patient, timely warning and intervention can be achieved, so as to timely discover the patient's abnormal condition and improve the patient's monitoring and management effects.

[0046] Furthermore, since consecutive words may appear repeatedly, after matching a keyword, an extended scan detection is performed on the keyword by continuously obtaining extended character segments adjacent to the keyword and with the same character length until it is determined that the extended character segments do not match the keyword. The extended scan detection of the current keyword is stopped, thereby avoiding repeated matching of repeated real-time keywords in the database, that is, avoiding repeated detection of matches, and improving data processing efficiency.

[0047] In particular, since the various expressions of disease symptoms also lead to duplication and redundancy in medical and health data, storing multiple expressions of the same disease symptoms in the medical and health database facilitates timely and effective data processing during keyword matching analysis, reduces duplication and redundant information in medical and health data, and improves data quality and availability.

[0048] Furthermore, when it is determined that the real-time difference ratio is greater than or equal to the second standard difference ratio, it indicates that the self-reported data has a low correlation with the medical history. By analyzing the data volume of medical keywords in the self-reported data, it is determined whether there are a large number of new conditions. If so, an early warning is issued for such situations. If not, it indicates that there is a lot of irrelevant information in the self-reported data. The self-reported data is deleted, redundant data is deleted, and the effectiveness of the stored data is improved.

[0049] Furthermore, when the self-reported content is not related to the condition, the risk level can be increased by correlating it with physical health parameters for analysis, thereby improving the management efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a connection diagram of an automatic discharge monitoring system based on data processing according to an embodiment of the present invention;

[0051] Figure 2 is a schematic diagram of a data processing module according to an embodiment of the present invention;

[0052] Figure 3 A logical decision diagram for determining keywords to be detected for an embodiment of the present invention;

[0053] Figure 4 This is a logical decision diagram for deleting an extended character segment according to an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0055] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0056] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0057] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0058] See also Figure 1 and Figure 2 As shown, Figure 1 This is a connection diagram of an automatic discharge monitoring system based on data processing according to an embodiment of the present invention. Figure 2 Schematic diagram of a data processing module of an embodiment of the present invention. The present invention provides an automatic discharge monitoring system based on data processing, including:

[0059] A remote monitoring module is used to collect medical and health data from the user, including historical diagnosis and treatment data, physical health parameters and self-reported data;

[0060] Medical health database, used to store a number of medical keyword data packets;

[0061] A data processing module, which is connected to the remote monitoring module and the medical health database respectively, and is used to pre-process the self-reported data to obtain data to be scanned, scan and delete the data to be scanned, obtain discharge pathology data, and input it into the medical health database for storage;

[0062] Wherein, the data processing module includes:

[0063] A scanning matching unit, scanning the data to be scanned with a preset scanning length to obtain a current detection data segment, extracting real-time keywords in the current detection data segment for matching in the medical health database, and determining the keywords to be detected according to the matching results;

[0064] Wherein, when the scanning matching unit determines that the number of the extracted real-time keywords is greater than or equal to one and there is a match with the medical keyword, the real-time keyword is marked as a keyword to be detected;

[0065] An extended matching unit, configured to continuously extend and scan the keywords to be detected to obtain extended character segments, perform matching detection on the extended character segments according to the keywords to be detected, and determine whether to delete the extended character segments according to the matching detection results to obtain the discharge pathology data;

[0066] A data analysis module, which is connected to the remote monitoring module and the data processing module respectively, and is used to perform correlation analysis on the discharge pathology data and the physical health parameters to output a corresponding identification risk level, wherein the identification risk level includes a first-level warning prompt, a second-level warning prompt, a third-level warning prompt, and a fourth-level warning prompt;

[0067] An early warning module is connected to the data analysis module and is used to determine whether to issue an early warning prompt based on the analysis results of the data analysis module.

[0068] In this embodiment, the physical health parameters include personal health characteristic data generated by various mobile health devices, such as heart rate, blood sugar, blood pressure, sleep, etc.; historical diagnosis and treatment data include electronic medical record data, imaging data, gene data, electrocardiogram, etc.; medical keyword data packets are keywords corresponding to the disease type related to the user terminal, including disease name, symptoms and other data. For example, a medical keyword data packet includes the disease name of indigestion, symptoms of stomach discomfort, loss of appetite, causes of indigestion, indigestion food, and indigestion treatment; associated keywords are words that express the same as the disease keyword. For example, if the disease keyword is "stomach discomfort", the associated keywords are "indigestion" and "indigestion food". Keywords include "stomachache", "stomachache" and other words with the same semantics; self-reported data refers to the symptoms, medical history or treatment process described by the patient after discharge, which can be image data, text data or audio data; pre-processing of self-reported data includes converting the image data in the self-reported data into text data, converting the audio data into text data, and then merging them with the original text data to obtain the data to be scanned; discharge pathology data refers to the processed discharge monitoring data, which records medical data related to the health status and treatment effect of the user, including vital signs such as body temperature, pulse, respiration, medication information such as drug name and dosage, or rehabilitation information.

[0069] In this embodiment, optical character recognition (OCR) technology is used to convert image data in medical health data. By selecting a suitable OCR tool or software, such as Tesseract, ABBYY FineReader, etc., and running the OCR tool to recognize the text in the image data, the text in the image is converted into text data.

[0070] By analyzing and processing the monitored self-reported data, repeated content in text data can be efficiently identified, that is, by performing extended scanning and detection on keywords, and continuously obtaining extended character segments that are adjacent to the keyword and have the same character length, until it is determined that the extended character segment does not match the keyword, the extended scanning and detection of the current keyword is stopped, thereby avoiding repeated matching of repeated real-time keywords in the database, that is, avoiding repeated detection of matches, improving data processing efficiency, deleting repeated content, processing data in a timely and effective manner, reducing repeated and redundant information in medical and health data, and improving data quality and availability. By determining different risk levels based on the relevance of the self-reported content to the condition and the monitoring results of physical health parameters, the discharge monitoring data can be analyzed in more detail to improve the management efficiency of the system.

[0071] See also Figure 3 As shown, it is a logical decision diagram for determining keywords to be detected according to an embodiment of the present invention;

[0072] Specifically, a preset scan length is set in the scan matching unit. For any data to be scanned, the scan matching unit scans the text data with the preset scan length to obtain a current detection data segment, extracts real-time keywords in the current detection data segment, and determines the number of the extracted real-time keywords.

[0073] If the number of the extracted real-time keywords is greater than or equal to one, matching the real-time keywords with the medical keywords in the medical health database to determine whether to mark the real-time keywords;

[0074] If the number of the extracted real-time keywords is less than one, a matching determination is performed on the next detection data segment.

[0075] The preset scan length in this embodiment is the size of the scan window, which is set by the user according to needs and can be a fixed length of characters or words. The sliding window starts from the starting position of the text data and slides on the text data with a set length, each time sliding a fixed step length. The set preset scan length is adjustable to flexibly scan and process the text data to adapt to different text processing needs; the real-time keywords are medical-related keywords, and the real-time keywords are extracted from the medical vocabulary by matching the words in the text data with the medical-related words in the vocabulary to extract the keywords.

[0076] By obtaining the current detection data segment, the real-time keywords in the current detection data segment are extracted to process or analyze the text data in the sliding window at each sliding window position. By adopting a fast scanning method, the input self-description content is analyzed and processed. The method is simple and effective.

[0077] Specifically, when the number of the extracted real-time keywords is determined to be greater than or equal to one, the scanning matching unit selects a real-time keyword in chronological order, and matches the real-time keyword with the medical keyword in the medical health database.

[0078] If there is a match with the medical keyword, the keyword to be detected is obtained;

[0079] If there is no match with the medical keyword, continue to match the next real-time keyword.

[0080] Until the matching judgment of each real-time keyword in the current detection data segment is completed, if it is determined that there is no matching item with the medical keyword, the current detection data segment is marked as an unassociated data segment.

[0081] By matching the extracted keywords in chronological order when it is determined that the number of the extracted real-time keywords is greater than or equal to one, the orderliness of data processing is ensured. Since the self-report data input by the patient may be incomplete or irrelevant to the condition, the self-report data needs to be analyzed in detail to ensure the accuracy of the data in a timely manner. At the same time, after completing the scanning and analysis of the text data, if it is still determined that there is no match with the medical keyword, it means that the self-report content is irrelevant to the condition, then the analysis is performed by associating the physical health parameters to determine whether the abnormal self-report content can also be accurately analyzed, that is, by associating the collected physical health parameter data of the patient, timely warning and intervention can be achieved, so as to timely discover the abnormal condition of the patient and improve the monitoring and management effect of the patient.

[0082] See also Figure 4 As shown, it is a logical decision diagram for deleting the extended character segment according to an embodiment of the present invention;

[0083] Specifically, the continuous extended scanning includes taking the character length of the keyword to be detected as the detection character length, taking the next adjacent character of the keyword to be detected as the starting node, and performing continuous extended scanning on the text data with the detection character length to obtain an extended character segment.

[0084] In this embodiment, since consecutive words may appear repeatedly, after matching a keyword, an extended scan detection is performed on the keyword by continuously obtaining extended character segments adjacent to the keyword and having the same character length until it is determined that the extended character segment does not match the keyword. The extended scan detection of the current keyword is stopped, thereby avoiding repeated matching of repeated real-time keywords in the database, that is, avoiding repeated detection of matches, and improving data processing efficiency.

[0085] Specifically, any medical keyword data packet includes a disease keyword and an associated keyword corresponding to the disease keyword;

[0086] The result of the matching detection includes obtaining the disease keyword and the associated keyword corresponding to the keyword to be detected in the medical health database as a plurality of keywords to be matched, and performing matching detection on the extended character segment according to each of the keywords to be matched,

[0087] If the keyword to be matched matches the extended character segment, it is determined that duplicate data exists, the extended character segment is deleted, and the keyword to be detected is continuously extended and scanned to obtain the extended character segment, so as to perform matching detection on the extended character segment;

[0088] If the keyword to be matched does not match the extended character segment, it is determined that no duplicate data occurs, and a continuous extended scan of the keyword to be detected is completed. A continuous extended scan is performed on the next keyword to be detected to obtain the corresponding extended character segment to determine whether to delete the extended character segment.

[0089] In this embodiment, since the various expressions of disease symptoms also cause duplication and redundancy in medical health data, multiple expressions of the same disease symptoms are stored in the medical health database to facilitate timely and effective data processing during keyword matching analysis, reduce duplication and redundant information in medical health data, and improve data quality and availability.

[0090] Specifically, when it is determined that there is no match with the medical keyword and the scanning process of the text data is completed, the percentage of the number of unassociated data segments to the total number of detected data segments is obtained to obtain a real-time difference ratio.

[0091] Specifically, the monitoring result of the early warning module on the health parameter is obtained, and a determination is made according to the monitoring result.

[0092] If a warning prompt is displayed for the physical health parameter, the real-time difference ratio will be judged according to the first standard difference ratio to determine whether to display a first-level warning prompt;

[0093] If no warning prompt is displayed for the physical health parameter, no warning prompt is displayed.

[0094] The physical health parameter monitoring result in this embodiment is the analysis result of the data generated by various mobile health devices. When the data is abnormal, an early warning prompt is displayed for the corresponding physical health parameter.

[0095] Specifically, when the health parameter is displayed as an early warning, the real-time difference ratio is obtained, and the real-time difference ratio is determined according to the first standard difference ratio.

[0096] If the real-time difference ratio is less than the first standard difference ratio, the processed text data is used as the discharge pathology data, and a first-level warning prompt is displayed;

[0097] If the real-time difference ratio is greater than the first standard difference ratio, the real-time difference ratio will be judged based on the second standard difference ratio and the monitoring results to determine the warning risk level and whether to delete the self-reported data.

[0098] The standard difference ratio set in this embodiment indicates the degree of correlation between the extracted medical keywords and the medical history of the user. The first standard difference ratio is set between 3% and 10%. If the real-time difference ratio is less than the first standard difference ratio, it means that the content recorded in the input self-description is highly relevant to the condition. The second standard difference ratio is set to more than 70%, which means that the content recorded in the input self-description is very different from the condition, that is, it is irrelevant to the medical history. The set standard difference ratio is selected and adjusted according to the total number of detected data segments. The larger the total number, the larger the setting value of the first standard difference ratio and the smaller the second standard difference ratio.

[0099] Specifically, when it is determined that the real-time difference ratio is greater than the first standard difference ratio, the real-time difference ratio is determined according to the second standard difference ratio.

[0100] If the real-time difference ratio is less than the second standard difference ratio, the real-time difference ratio is judged according to the monitoring results to determine the risk level;

[0101] If the real-time difference ratio is greater than or equal to the second standard difference ratio, the percentage of the cumulative character length of each real-time keyword in the text data is obtained to obtain the real-time completeness, and the real-time completeness is determined according to the standard completeness.

[0102] If the real-time completeness is less than the standard completeness, the self-reported data is deleted and a three-level warning prompt is displayed;

[0103] If the real-time completeness is greater than or equal to the standard completeness, a level 4 warning prompt will be displayed.

[0104] The standard completeness set in this embodiment represents the ratio of the extracted real-time keywords to the text data. The standard completeness is set between 60% and 80%. If the real-time completeness is greater than or equal to the standard completeness, it indicates that new medical conditions have appeared. If a large number of new medical conditions appear, a fourth-level warning prompt will be displayed.

[0105] By determining that the real-time difference ratio is greater than or equal to the second standard difference ratio, it indicates that the self-reported data has a low correlation with the medical history. By analyzing the data volume of medical keywords in the self-reported data, it is determined whether there are a large number of new conditions. If so, an early warning is issued for such situations. If not, it indicates that there is a lot of irrelevant information in the self-reported data. The self-reported data is deleted, and redundant data is deleted to improve the effectiveness of stored data.

[0106] Specifically, when it is determined that the real-time difference ratio is less than the second standard difference ratio, the real-time difference ratio is determined according to the monitoring results.

[0107] If a warning prompt is displayed for the physical health parameter, a second-level warning prompt is displayed;

[0108] If no warning prompt is displayed for the physical health parameter, no warning prompt is displayed.

[0109] In this embodiment, the early warning prompt indicates the difficulty of identifying the patient's health status and risks. The higher the level of the early warning prompt display, the more difficult it is to identify the health status based on the existing data, that is, it is relatively difficult to conduct remote consultation based on the monitoring data. Among them, the first-level early warning prompt display indicates that the patient's physical health parameters are abnormal, and the discharge pathology data can be associated for analysis. The second-level early warning prompt display indicates that the patient's physical health parameters are abnormal, and the physical health parameters and the input self-description content are relatively relevant. The third-level early warning prompt display indicates that the patient's physical health parameters are abnormal, the physical health parameters are irrelevant to the input self-description content, and there are no large number of new conditions. The fourth-level early warning prompt display indicates that a large number of new conditions are in the input self-description content. In this case, it indicates that the monitored medical data is incomplete.

[0110] In this embodiment, since the diagnosis and treatment of certain diseases may be very complicated and require the integration of multiple information, if the self-reported data is incomplete or incomplete, it may lead to inaccurate data analysis results and failure to provide timely warnings. Therefore, different risk levels are determined based on the degree of relevance between the self-reported content and the condition, as well as the monitoring results of physical health parameters, and the discharge monitoring data is analyzed in more detail to improve the management efficiency of the system.

[0111] By analyzing the self-reported content by associating it with physical health parameters when it is not related to the condition, the risk level can be increased to improve the management efficiency of the system.

[0112] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0113] The above description is only a preferred embodiment of the present invention and is 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 in the protection scope of the present invention.

Claims

1. The automatic discharge monitoring system based on data processing is characterized by: include, A remote monitoring module for collecting medical and health data from the user, the medical and health data including physical health parameters and self-reported data; Medical health database, used to store a number of medical keyword data packets; A data processing module, which is connected to the remote monitoring module and the medical health database respectively, and is used to pre-process the self-reported data to obtain data to be scanned, scan and delete the data to be scanned, obtain discharge pathology data, and input it into the medical health database for storage; Wherein, the data processing module includes: A scanning matching unit, scanning the data to be scanned with a preset scanning length to obtain a current detection data segment, extracting real-time keywords in the current detection data segment for matching in the medical health database, and determining the keywords to be detected according to the matching results; Wherein, when the scanning matching unit determines that the number of the extracted real-time keywords is greater than or equal to one and there is a match with the medical keyword, the real-time keyword is marked as a keyword to be detected; An extended matching unit, configured to continuously extend and scan the keywords to be detected to obtain extended character segments, perform matching detection on the extended character segments according to the keywords to be detected, and determine whether to delete the extended character segments according to the matching detection results to obtain the discharge pathology data; A data analysis module, which is connected to the remote monitoring module and the data processing module respectively, and is used to perform correlation analysis on the discharge pathology data and the physical health parameters to output a corresponding identification risk level; An early warning module, which is connected to the data analysis module and is used to determine whether to issue an early warning prompt according to the analysis result of the data analysis module; The scan matching unit is set with a preset scan length. For any data to be scanned, the scan matching unit scans the text data with the preset scan length to obtain a current detection data segment, extracts medical-related keywords from the current detection data segment as real-time keywords, and determines the number of the extracted real-time keywords. If the number of the extracted real-time keywords is greater than or equal to one, matching the real-time keywords with the medical keywords in the medical health database to determine whether to mark the real-time keywords; If the number of the extracted real-time keywords is less than one, performing a matching determination on the next detection data segment; When the scanning and matching unit determines that the number of the extracted real-time keywords is greater than or equal to one, the scanning and matching unit selects a real-time keyword in chronological order, and performs matching determination between the real-time keyword and the medical keyword in the medical health database. If there is a match with the medical keyword, the keyword to be detected is obtained; If there is no match with the medical keyword, continue to match the next real-time keyword. Until the matching judgment of each real-time keyword in the current detection data segment is completed, if it is determined that there is no matching item with the medical keyword, the current detection data segment is marked as an unassociated data segment. After it is determined that there is no matching item with the medical keyword and the scanning process of the text data is completed, the data analysis module obtains the percentage of the number of unassociated data segments to the total number of detection data segments, and obtains the real-time difference ratio; The continuous extended scanning includes taking the character length of the keyword to be detected as the detection character length, taking the next adjacent character of the keyword to be detected as the starting node, and performing continuous extended scanning on the text data with the detection character length to obtain an extended character segment; Any medical keyword data packet includes a disease keyword and an associated keyword corresponding to the disease keyword; The result of the matching detection includes obtaining the disease keyword and the associated keyword corresponding to the keyword to be detected in the medical health database as a plurality of keywords to be matched, and performing matching detection on the extended character segment according to each of the keywords to be matched, If the keyword to be matched matches the extended character segment, it is determined that duplicate data exists, the extended character segment is deleted, and the keyword to be detected is continuously extended and scanned to obtain the extended character segment, so as to perform matching detection on the extended character segment; If the keyword to be matched does not match the extended character segment, it is determined that no duplicate data occurs, a continuous extended scan of the keyword to be detected is completed, a continuous extended scan of the next keyword to be detected is performed, and a corresponding extended character segment is obtained to determine whether to delete the extended character segment; The data analysis module obtains the monitoring result of the early warning module on the health parameter, and makes a judgment based on the monitoring result. If a warning prompt is displayed for the physical health parameter, the real-time difference ratio will be judged according to the first standard difference ratio to determine whether to display a first-level warning prompt; If no warning prompt is displayed for the physical health parameter, no warning prompt is displayed; When the data analysis module displays an early warning prompt for the health parameter, the data analysis module obtains the real-time difference ratio and determines the real-time difference ratio according to the first standard difference ratio. If the real-time difference ratio is less than the first standard difference ratio, the processed text data is used as the discharge pathology data, and a first-level warning prompt is displayed; If the real-time difference ratio is greater than the first standard difference ratio, the real-time difference ratio will be judged according to the second standard difference ratio and the monitoring results to determine the warning risk level and whether to delete the self-reported data; When the data analysis module determines that the real-time difference ratio is greater than the first standard difference ratio, the real-time difference ratio is determined according to the second standard difference ratio. If the real-time difference ratio is less than the second standard difference ratio, the real-time difference ratio is judged according to the monitoring results to determine the risk level; If the real-time difference ratio is greater than or equal to the second standard difference ratio, the percentage of the cumulative character length of each real-time keyword in the text data is obtained to obtain the real-time completeness, and the real-time difference ratio is judged according to the monitoring results to determine whether to display a third-level warning prompt.

2. The automatic discharge monitoring system based on data processing according to claim 1 is characterized in that: When the data analysis module determines that the real-time difference ratio is greater than or equal to the second standard difference ratio, the real-time completeness is determined according to the standard completeness. If the real-time completeness is less than the standard completeness, the self-reported data is deleted and a three-level warning prompt is displayed; If the real-time completeness is greater than or equal to the standard completeness, a level 4 warning prompt will be displayed.

3. The automatic discharge monitoring system based on data processing according to claim 2 is characterized in that: The data analysis module determines the real-time difference ratio according to the monitoring result when determining that the real-time difference ratio is less than the second standard difference ratio. If a warning prompt is displayed for the physical health parameter, a second-level warning prompt is displayed; If no warning prompt is displayed for the physical health parameter, no warning prompt is displayed.

Images