Hospital information data security management method and system

Abstract

The invention relates to the technical field of medical information processing, and particularly discloses a hospital information data safety management method and system, and the method comprises the steps: carrying out the statistics of medical information, judging the similarity of to-be-stored medical information, and storing the medical information, and carrying out the analysis of the historical access information of each piece of existing medical information, existing medical information which is accessed frequently can be known in time, it is ensured that the existing medical information which is accessed at high frequency is stored more efficiently, the utilization efficiency of the overall medical information is improved, similarity judgment is carried out on the basic characteristic parameters of the to-be-stored medical information and the basic characteristic parameters of all the existing medical information, and the accuracy of the medical information is improved. Through storage management of each piece of existing medical information and the to-be-stored medical information, maximum utilization of storage resources is realized, the storage cost is reduced, the problems of unreasonable utilization of medical information storage resources and poor flexibility of a storage strategy are solved, and then the safety of hospital information data is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of medical information processing, and in particular to a hospital information data security management method and system. Background Art

[0002] At present, with the rapid development of big data technology, the scale of hospital information data is growing explosively. How to efficiently and securely manage these hospital information data has become an urgent problem to be solved. Traditional hospital information data management methods often have problems such as unreasonable utilization of data storage resources and poor flexibility in adjusting storage strategies. These problems further lead to multiple dilemmas in the security management of hospital information data.

[0003] For example, the invention patent with announcement number CN109558461B announces a medical data classification storage method and device, wherein the medical data classification storage method includes: receiving a storage request for target medical data, the storage request is used to request the storage of the target medical data; reviewing the target medical data and determining that the target medical data is qualified medical data; classifying the qualified medical data according to the data classification model to obtain a standardized classification result; scoring the qualified medical data according to the standardized classification result to obtain a scoring result of the qualified medical data; and classifying and storing the qualified medical data according to the scoring result, wherein the classified storage includes online storage, near-line storage, and archived storage. By reviewing, classifying, and scoring the medical data, and then classifying and storing the medical data according to the scoring results, the accuracy of the classified storage of the medical data is improved, the consumption of the data running space is reduced, and the efficiency of data reuse is improved.

[0004] For example, the invention patent with announcement number CN106844325B announces a medical information processing method and a medical information processing device, wherein the medical information processing method includes: segmenting multiple medical texts, and clustering the multiple medical texts; determining the correlation between each two medical texts according to the words in each medical text of the same category; judging whether there is a correlation relationship between any two medical texts in the same category of medical texts according to the correlation between each two medical texts; when the judgment result is yes, the words with correlation relationship are stored in association. The words with correlation relationship in the medical text can be mined more accurately and comprehensively, so that the medical word library constructed based on the words with correlation relationship is more accurate and comprehensive.

[0005] Based on the above solution, it is found that the existing hospital information data management methods usually adopt fixed information storage strategies, which leads to unreasonable allocation of hospital information data storage resources and poor flexibility in adjusting storage strategies, thereby affecting the integrity of hospital information data and failing to improve the efficiency and effectiveness of hospital information data security management. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a hospital information data security management method and system, which can effectively solve the problems involved in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: The first aspect of the present invention provides a hospital information data security management method, including: S1. Statistical medical information: Statistical basic feature parameters and historical access information of each existing medical information from the medical information management platform, and analyze the historical access information of each existing medical information to obtain the access feature value of each existing medical information; S2. Similarity determination of medical information to be stored: Obtain the basic feature parameters of the medical information to be stored, and perform similarity determination with the basic feature parameters of each existing medical information to obtain the basic feature similarity index between the medical information to be stored and each existing medical information, thereby obtaining reference existing medical information through processing, and statistically obtaining the access feature value of the reference existing medical information as the expected access feature value of the medical information to be stored; S3. Medical information storage: Compare the access feature value of each existing medical information and the expected access feature value of the medical information to be stored with the access reference feature value preset in the medical information library, and finally complete the storage management of each existing medical information and the medical information to be stored.

[0008] As a further method, the access characteristic values ​​of each existing medical information are specifically analyzed as follows: The historical access times, historical access durations, and historical access maximum response durations of each piece of existing medical information are comprehensively analyzed to obtain the access characteristic values ​​of each piece of existing medical information. The specific analysis formula is: In the formula, is the access characteristic value of the i-th existing medical information, is the number of each existing medical information, i=1,2,3...j, j is the total number of existing medical information, e is a natural constant, The impact factor corresponding to the historical access number unit value preset in the medical information database, is the historical access count of the i-th existing medical information, is the impact factor corresponding to the historical access time unit value preset in the medical information database, is the historical access duration of the i-th existing medical information, The impact factor corresponding to the unit value of the maximum response time of historical access preset in the medical information database, is the maximum historical response time for accessing the i-th existing medical information, The reference time for access response preset in the medical information database.

[0009] As a further method, the basic feature similarity index between the medical information to be stored and each existing medical information is specifically analyzed as follows: The length of the text corresponding to each existing medical information is ratioed to the number of sentences in the text corresponding to each existing medical information to obtain the average length of the sentence corresponding to each existing medical information.

[0010] The number of occurrences of each text word corresponding to each existing medical information is counted respectively to obtain the number of occurrences of each text word corresponding to each existing medical information, and the number of occurrences of each text word is arranged in descending order. The total number of text words corresponding to the top three occurrences is counted and recorded as the number of high-frequency words in the text corresponding to each existing medical information.

[0011] The text words corresponding to the top three occurrences in each of the existing medical information are recorded as the text high-frequency word set corresponding to each of the existing medical information.

[0012] The number of text words corresponding to each existing medical information is counted, and the number of high-frequency words in the text corresponding to each existing medical information is ratio-processed with the number of text words corresponding to each existing medical information to obtain the proportion of high-frequency words corresponding to each existing medical information.

[0013] The length of the text corresponding to the medical information to be stored is ratioed to the number of sentences in the text corresponding to the medical information to be stored to obtain the average length of the sentences corresponding to the medical information to be stored.

[0014] The number of occurrences of each text word corresponding to the medical information to be stored is counted respectively to obtain the number of occurrences of each text word corresponding to the medical information to be stored, and the number of occurrences of each text word is arranged in descending order. The total number of text words corresponding to the top three occurrences is counted and recorded as the number of high-frequency words in the text corresponding to the medical information to be stored.

[0015] The text words corresponding to the top three occurrences in the obtained medical information to be stored are recorded as the text high-frequency word set corresponding to the medical information to be stored.

[0016] The number of text words corresponding to the medical information to be stored is counted, and the number of high-frequency words in the text corresponding to the medical information to be stored is ratio-processed with the number of text words corresponding to the medical information to be stored to obtain the corresponding high-frequency word ratio of the medical information to be stored.

[0017] A comprehensive analysis is performed on the average sentence length, high-frequency word ratio, and text high-frequency word set corresponding to each existing medical information and the average sentence length, high-frequency word ratio, and text high-frequency word set corresponding to the medical information to be stored to obtain the basic feature similarity index between the medical information to be stored and each existing medical information.

[0018] As a further method, the estimated access characteristic value of the medical information to be stored, the specific process is: The basic feature similarity indexes between the medical information to be stored and each piece of existing medical information are arranged in descending order, and the existing medical information corresponding to the basic feature similarity index ranked first is recorded as the reference existing medical information.

[0019] The access feature values ​​of the referenced existing medical information are extracted as the estimated access feature values ​​of the medical information to be stored.

[0020] As a further method, the access characteristic values ​​of each existing medical information and the estimated access characteristic values ​​of the medical information to be stored are compared with the access reference characteristic values ​​preset in the medical information database, and the specific comparison process is: If the access characteristic value of a piece of existing medical information is greater than or equal to the access reference characteristic value preset in the medical information library, then the piece of existing medical information is recorded as the first stored medical information, and the existing medical information corresponding to each piece of access characteristic value greater than or equal to the access reference characteristic value preset in the medical information library is counted and recorded as the first stored medical information data set.

[0021] If the access characteristic value of a piece of existing medical information is smaller than the access reference characteristic value preset in the medical information library, the piece of existing medical information is recorded as the second stored medical information, and the existing medical information corresponding to each piece of access characteristic value smaller than the access reference characteristic value preset in the medical information library is counted and recorded as the second stored medical information data set.

[0022] If the expected access characteristic value of the medical information to be stored is greater than or equal to the access reference characteristic value preset in the medical information database, the medical information to be stored will be recorded as the first medical information to be stored; if the expected access characteristic value of the medical information to be stored is less than the access reference characteristic value preset in the medical information database, the medical information to be stored will be recorded as the second medical information to be stored.

[0023] As a further method, the storage management of each existing medical information and the medical information to be stored is completed, and the specific analysis process is as follows: The first stored medical information data set is stored in a first storage location, and the second stored medical information data set is stored in a second storage location.

[0024] The first medical information to be stored is stored in a first storage location, or the second medical information to be stored is stored in a second storage location.

[0025] The second aspect of the present invention provides a system for a hospital information data security management method, including: a medical information statistics module, which is used to count the basic characteristic parameters and historical access information of each existing medical information from a medical information management platform, and analyze the historical access information of each existing medical information to obtain the access characteristic value of each existing medical information.

[0026] The similarity determination module for the medical information to be stored is used to obtain the basic characteristic parameters of the medical information to be stored, and to determine the similarity with the basic characteristic parameters of each existing medical information, so as to obtain the basic characteristic similarity index between the medical information to be stored and each existing medical information, thereby obtaining the reference existing medical information through processing, and calculating the access characteristic value of the reference existing medical information as the estimated access characteristic value of the medical information to be stored.

[0027] The medical information storage module is used to compare the access characteristic values ​​of each existing medical information and the expected access characteristic values ​​of the medical information to be stored with the access reference characteristic values ​​preset in the medical information library, and finally complete the storage management of each existing medical information and the medical information to be stored.

[0028] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects: (1) By analyzing the historical access information of each piece of existing medical information, the present invention can timely understand the existing medical information that is frequently accessed, which helps to store and manage the existing medical information, ensure that the existing medical information that is frequently accessed is stored and accessed more efficiently, and improve the overall utilization efficiency of medical information.

[0029] (2) The present invention can obtain the estimated access information of the medical information to be stored by determining the similarity between the basic characteristic parameters of the medical information to be stored and the basic characteristic parameters of each piece of existing medical information, thereby providing a basis for the subsequent storage of the medical information to be stored.

[0030] (3) The present invention can maximize the utilization of storage resources, reduce storage costs, and solve the problems of unreasonable utilization of medical information storage resources and poor flexibility of storage strategies through storage management of various existing medical information and medical information to be stored, thereby ensuring the security of hospital information data. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0032] Figure 1 The figure is a schematic flow chart of the method steps of the present invention.

[0033] Figure 2 It is a schematic diagram of system module connection of the present invention.

[0034] Figure 3 It is a simulation curve diagram of the historical access times and the historical access duration involved in the present invention. DETAILED DESCRIPTION

[0035] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0036] Reference Figure 1 As shown, the first aspect of the present invention provides a hospital information data security management method, including: S1. Statistical medical information: Statistically obtain basic characteristic parameters and historical access information of each existing medical information from the medical information management platform, and analyze the historical access information of each existing medical information to obtain the access characteristic value of each existing medical information; S2. Determination of similarity of medical information to be stored: obtain the basic characteristic parameters of the medical information to be stored, and determine the similarity with the basic characteristic parameters of each existing medical information to obtain the basic characteristic similarity index between the medical information to be stored and each existing medical information, thereby obtaining the reference existing medical information through processing, and statistically obtain the access characteristic value of the reference existing medical information as the expected access characteristic value of the medical information to be stored; S3. Storage of medical information: compare the access characteristic value of each existing medical information and the expected access characteristic value of the medical information to be stored with the access reference characteristic value preset in the medical information library, and finally complete the storage management of each existing medical information and the medical information to be stored.

[0037] In this embodiment, the above-mentioned medical information management platform is a system that can integrate massive data from different medical institutions, including patients' electronic medical records, medical images, laboratory test results, etc., to achieve data standardization and unified management. Using the medical information management platform to manage medical information can provide a safe and reliable medical information management method for medical information, improve the efficiency of medical information processing and analysis, and ensure the integrity and consistency of medical information. The smart hospital platform can count and process medical data from the medical information management platform. The above-mentioned smart hospital platform has the ability to store data in different locations to meet the requirements of cross-border medical cooperation and data security regulations.

[0038] In this embodiment, the above-mentioned storage management of medical information is a key component of the hospital information data security management method. At the same time, the storage management of medical information can better organize and manage data. Through storage management, the allocation and use of storage resources can be optimized, and related data can be stored in a centralized manner to facilitate subsequent data management and analysis, thereby improving the reading and writing speed and response time of hospital information. The scope of data security management is wider, including storage management and other necessary measures to protect data security.

[0039] Specifically, the historical access information of each piece of existing medical information includes the historical access times, historical access duration and historical maximum response duration of each piece of existing medical information.

[0040] It should be explained that the historical number of visits, historical visit duration and historical maximum response time of the above-mentioned existing medical information can be analyzed by professional log analysis tools built into the smart hospital platform, such as Logwatch (system log analyzer), on the access log records in the medical information management platform, thereby obtaining the historical number of visits, historical visit duration and historical maximum response time of each existing medical information.

[0041] Specifically, the access characteristic values ​​of each existing medical information are analyzed in the following process: The historical access times, historical access durations, and historical access maximum response durations of each piece of existing medical information are comprehensively analyzed to obtain the access characteristic values ​​of each piece of existing medical information. The specific analysis formula is: In the formula, is the access characteristic value of the i-th existing medical information, is the number of each existing medical information, i=1,2,3...j, j is the total number of existing medical information, and e is a natural constant.

[0042] The impact factor corresponding to the unit value of the historical number of visits preset in the medical information database is formed. A mapping set is formed according to the historical number of visits and the impact factor corresponding to the unit value of the historical number of visits preset in the medical information database. The relationship between the access feature values ​​​​constructs a mapping set between the number of visits and its corresponding impact factor, and the real-time historical number of visits mapping set is used to obtain the impact factor corresponding to the historical number of visits. The mapping relationship can be one-to-one or many-to-one. At the same time, in this example, its value range is [0, 1].

[0043] is the historical access count of the i-th existing medical information, which refers to the total number of times this medical information is accessed by users (such as doctors, patients, etc.) in the medical information management system.

[0044] The influencing factor corresponding to the unit value of the historical access time preset in the medical information database is formed into a mapping set according to the access time and the influencing factor corresponding to the unit value of the access time preset in the medical information database, and the real-time historical access time mapping set is used to obtain the influencing factor corresponding to the historical access time. The mapping relationship can be one-to-one or many-to-one. At the same time, in this example, its value range is [0, 1].

[0045] is the historical access duration of the i-th existing medical information, which refers to the length of time from when the user starts accessing the medical information to when the user ends the access.

[0046] It is the impact factor corresponding to the unit value of the historical maximum access response time preset in the medical information database. A mapping set is formed according to the historical maximum access response time and the impact factor corresponding to the unit value of the historical maximum access response time preset in the medical information database, and the real-time historical maximum access response time mapping set is used to obtain the impact factor corresponding to the historical maximum access response time. The mapping relationship can be one-to-one or many-to-one. At the same time, in this example, its value range is [0, 1].

[0047] is the maximum historical access response time for the i-th existing medical information, which refers to the longest time required for the system to return the information when a user accesses the medical information.

[0048] The reference time for access response preset in the medical information database refers to the expected response time set in medical information management to achieve efficient data access.

[0049] In this embodiment, a small number of historical access times means that the existing medical information has not been widely consulted or discussed for a period of time, thereby reducing the activity of the existing medical information in the information system, further resulting in a small number of historical access times. If the historical access time of a piece of medical information is small, it may mean that the information it contains is no longer the latest or most relevant, which will cause the timeliness of the information to be weakened, thereby affecting its access characteristic value. If the maximum response time of historical access deviates greatly from the preset access response reference time, it means that the medical information system or server has performance bottlenecks, network problems or insufficient data processing capabilities. These problems will not only affect the user's access experience to the current information, but may also affect the stability and reliability of the entire medical information system, thereby causing users to question the availability and reliability of medical information, thereby reducing the number of accesses to the information. Therefore, by analyzing the various data of the access characteristic values ​​of the existing medical information, it is possible to timely understand which existing medical information is frequently accessed and which existing medical information is less concerned, which is helpful for the storage management of the existing medical information, and can ensure that the existing medical information that is frequently accessed is more efficiently stored and accessed, thereby improving the overall utilization efficiency of the medical information.

[0050] In this embodiment, by performing a nonlinear comprehensive analysis on the historical number of visits, historical visit duration, and historical maximum response time of each existing medical information, the access characteristic value of each existing medical information is obtained, which can more comprehensively evaluate multiple dimensions of each existing medical information, such as popularity (through number of visits), user attention (through visit duration), and system performance (through maximum response time). This comprehensive evaluation helps to more accurately reflect the true value of medical information and user experience. At the same time, nonlinear analysis can reveal hidden patterns and trends in the data, which may be ignored or misunderstood in linear analysis. For example, some existing medical information may not be outstanding in terms of number of visits, but the visit duration is very long, indicating that users have a deep interest and attention to its content. Through nonlinear analysis, this subtle but important difference can be captured, thereby more accurately obtaining the access characteristic value of the existing medical information.

[0051] In this embodiment, the impact factor corresponding to the above-mentioned preset unit value of the number of historical visits is set to 0.5, the impact factor corresponding to the preset unit value of the historical access duration is set to 0.1, the impact factor corresponding to the unit value of the historical access maximum response duration is set to 0.4, and the preset access response reference time is 3 seconds. Thus, a table of the data relationship between the access characteristic values ​​of each existing medical information and each parameter can be obtained, as shown in Table 1, the change table between the access characteristic values ​​and the corresponding parameters.

[0052] Table 1 Access characteristic values ​​and changes between corresponding parameters By observing the data in the access characteristic value table in Table 1 above, it is found that the access characteristic value of each existing medical information will change according to the changes in the historical number of visits, historical visit duration and historical maximum response time of each existing medical information. When the historical number of visits, historical visit duration and historical maximum response time of each existing medical information increase, the access characteristic value of each existing medical information will also increase accordingly.

[0053] In this embodiment, there is a close data relationship between the historical access times and the historical access durations of the above-mentioned existing medical information. Existing medical information with a large number of historical access times is often accompanied by a long historical access duration. Therefore, a simulation curve between the historical access times and the historical access duration can be constructed. Specifically, Figure 3 The simulation curve diagram of historical access times and historical access duration is shown in which the horizontal axis is the historical access times, unit: times, and the vertical axis is the historical access duration, unit: minutes.

[0054] By observation Figure 3 The simulation curve diagram of historical visit times and historical visit duration shows that as the historical visit times increase, the historical visit duration also becomes relatively longer, so the historical visit times and historical visit duration show a positive correlation.

[0055] Furthermore, the basic characteristic parameters of each existing medical information specifically include the text length corresponding to each existing medical information, each text vocabulary, and the number of sentences in the text.

[0056] It should be explained that the basic characteristic parameters of the above-mentioned existing medical information, including the text length corresponding to each existing medical information, each text vocabulary, and the number of sentences in the text, can use the natural language processing (NLP) technology built into the smart hospital platform to extract and analyze the text content of each existing medical information, and accurately obtain the text length, extracted vocabulary and the number of sentences in the text.

[0057] Specifically, the basic characteristic parameters of the medical information to be stored include the text length, each text vocabulary, and the number of sentences in the text corresponding to the medical information to be stored.

[0058] It should be explained that the text length, vocabulary of each text, and the number of sentences in the text corresponding to the above-mentioned medical information to be stored are also obtained by using the natural language processing (NLP) technology built into the smart hospital platform. The text content of the medical information to be stored is extracted and analyzed, and the length of the text, the vocabulary in the extracted text, and the number of sentences can be accurately obtained.

[0059] In this embodiment, similarity analysis is mainly performed on the text data of each existing medical information and the text data of the medical information to be stored.

[0060] Specifically, the basic feature similarity index between the medical information to be stored and each existing medical information is analyzed in the following process: The length of the text corresponding to each existing medical information is ratioed to the number of sentences in the text corresponding to each existing medical information to obtain the average length of the sentence corresponding to each existing medical information.

[0061] It should be explained that the above-mentioned ratio processing of the text length corresponding to each existing medical information and the number of sentences in the text corresponding to each existing medical information is specifically to divide the text length corresponding to each existing medical information by the number of sentences in the text corresponding to each existing medical information, so as to obtain the average length of the sentences corresponding to each existing medical information.

[0062] The number of occurrences of each text word corresponding to each existing medical information is counted respectively to obtain the number of occurrences of each text word corresponding to each existing medical information, and the number of occurrences of each text word is arranged in descending order. The total number of text words corresponding to the top three occurrences is counted and recorded as the number of high-frequency words in the text corresponding to each existing medical information.

[0063] The text words corresponding to the top three occurrences in each of the existing medical information are recorded as the text high-frequency word set corresponding to each of the existing medical information.

[0064] In a specific embodiment, the top three high-frequency words can often directly reflect the core theme or main content of the medical information. For example, in a text describing a disease, the disease name, symptom description and treatment method will be high-frequency words. These words provide a quick channel for understanding the text. Compared with counting all words, focusing on the top three high-frequency words can effectively reduce the amount of data processing while retaining the most critical information points.

[0065] The number of text words corresponding to each existing medical information is counted, and the number of high-frequency words in the text corresponding to each existing medical information is ratio-processed with the number of text words corresponding to each existing medical information to obtain the proportion of high-frequency words corresponding to each existing medical information.

[0066] It needs to be explained that the number of text words corresponding to the above-mentioned existing medical information refers to the total number of text words corresponding to each existing medical information, which can be calculated by summing up the number of occurrences of each text word, and ratio processing is performed on the number of high-frequency words in the text corresponding to each existing medical information and the number of text words corresponding to each existing medical information, specifically, the number of high-frequency words in the text corresponding to each existing medical information is divided by the number of text words corresponding to each existing medical information, to obtain the ratio of high-frequency words corresponding to each existing medical information.

[0067] The length of the text corresponding to the medical information to be stored is ratioed to the number of sentences in the text corresponding to the medical information to be stored to obtain the average length of the sentences corresponding to the medical information to be stored.

[0068] It should be explained that the above ratio processing of the text length corresponding to the medical information to be stored and the number of sentences in the text corresponding to the medical information to be stored is specifically the text length corresponding to the medical information to be stored divided by the number of sentences in the text corresponding to the medical information to be stored, to obtain the average length of the sentences corresponding to the medical information to be stored.

[0069] The number of occurrences of each text word corresponding to the medical information to be stored is counted respectively to obtain the number of occurrences of each text word corresponding to the medical information to be stored, and the number of occurrences of each text word is arranged in descending order. The total number of text words corresponding to the top three occurrences is counted and recorded as the number of high-frequency words in the text corresponding to the medical information to be stored.

[0070] The text words corresponding to the top three occurrences in the obtained medical information to be stored are recorded as the text high-frequency word set corresponding to the medical information to be stored.

[0071] In a specific embodiment, by counting the top three high-frequency words in the medical information to be stored, the key content in the medical information to be stored can be quickly identified. These words are often closely related to core information such as disease diagnosis, treatment, symptoms or drugs. At the same time, when processing a large amount of medical information, paying attention to high-frequency words can significantly reduce the amount of data to be processed while retaining the most important information points. This helps to speed up information processing and improve overall work efficiency.

[0072] The number of text words corresponding to the medical information to be stored is counted, and the number of high-frequency words in the text corresponding to the medical information to be stored is ratio-processed with the number of text words corresponding to the medical information to be stored to obtain the corresponding high-frequency word ratio of the medical information to be stored.

[0073] It should be explained that the number of text words corresponding to the medical information to be stored refers to the total number of text words corresponding to the medical information to be stored, which can be calculated by summing up the number of occurrences of each text word corresponding to the medical information to be stored, and ratio processing is performed on the number of high-frequency words in the text corresponding to the medical information to be stored and the number of text words corresponding to the medical information to be stored, specifically, the number of high-frequency words in the text corresponding to the medical information to be stored is divided by the number of text words corresponding to the medical information to be stored, to obtain the corresponding high-frequency word ratio of the medical information to be stored.

[0074] The average sentence length, high-frequency word ratio, and high-frequency word set of each existing medical information are comprehensively analyzed with the average sentence length, high-frequency word ratio, and high-frequency word set of the medical information to be stored, and the basic feature similarity index between the medical information to be stored and each existing medical information is obtained. The specific analysis formula is: ; In the formula, is the basic feature similarity index between the medical information to be stored and the i-th existing medical information, is the number of each existing medical information, i=1,2,3...j, j is the total number of existing medical information.

[0075] The average length of sentences corresponding to the medical information to be stored refers to the average number of words or characters contained in each sentence when processing the medical information to be stored.

[0076] is the average length of the sentence corresponding to the i-th existing medical information, which refers to the average number of words or characters contained in the sentence for the existing medical information data when processing the existing medical information.

[0077] The influence factor corresponding to the unit value of the average sentence length similarity preset in the medical information database is formed into a mapping set according to the average sentence length and the influence factor corresponding to the unit value of the average sentence length similarity preset in the medical information database. The real-time average sentence length mapping set is used to obtain the influence factor corresponding to the unit value of the average sentence length similarity. The mapping relationship can be one-to-one or many-to-one. In this example, its value range is [0,1].

[0078] The high-frequency word ratio corresponding to the medical information to be stored refers to the ratio of words that appear frequently in the processing of the medical information to be stored.

[0079] is the proportion of high-frequency words corresponding to the i-th existing medical information, which refers to the proportion of words that appear frequently for the existing medical information data when processing the existing medical information.

[0080] The influencing factors corresponding to the high-frequency word ratio similarity unit values ​​preset in the medical information database are formed into a mapping set according to the high-frequency word ratio and the influencing factors corresponding to the high-frequency word ratio similarity unit values ​​preset in the medical information database. The real-time high-frequency word ratio mapping set is used to obtain the influencing factors corresponding to the high-frequency word ratio similarity unit values. The mapping relationship can be one-to-one or many-to-one. In this example, its value range is [0,1].

[0081] is the high-frequency vocabulary set similarity between the high-frequency vocabulary set of the text corresponding to the i-th existing medical information and the high-frequency vocabulary set of the text corresponding to the medical information to be stored, is the set of high-frequency words in the text corresponding to the i-th existing medical information, It is a set of high-frequency words in the text corresponding to the medical information to be stored.

[0082] In this embodiment, when the average length of sentences corresponding to the medical information to be stored deviates greatly from the average length of sentences corresponding to the existing medical information, this means that the difference in sentence length between the medical information to be stored and the existing medical information is large, which in turn leads to semantic and structural differences. When the proportion of high-frequency words corresponding to the medical information to be stored deviates greatly from the proportion of high-frequency words corresponding to the existing medical information, it means that the source of the medical information to be stored is significantly different from that of the existing information. For example, the information to be stored may come from a specific clinical study or case analysis of a specific disease, while the existing information is based on a wider range of case types. This difference in sources may lead to differences in high-frequency words. When the similarity between the high-frequency word set of the text corresponding to each existing medical information and the high-frequency word set of the text corresponding to the medical information to be stored is low, it means that there are significant differences in the main content or focus between the medical information to be stored and the existing medical information. This difference may be due to different disease types, treatment methods or research directions. Therefore, by analyzing the data in the basic feature similarity index between the medical information to be stored and the existing medical information, the similarity between the medical information to be stored and each existing medical information can be obtained, and then the expected access information of the medical information to be stored can be obtained, and at the same time, a basis for the subsequent storage of the medical information to be stored can be provided.

[0083] In this embodiment, the average sentence length, high-frequency word set and high-frequency word ratio are important aspects of the medical information text features. The average sentence length reflects the level of detail and complexity of expression of the information, while the high-frequency word set and high-frequency word ratio reveal the main content and focus of the information. Therefore, by performing nonlinear comprehensive analysis on the medical information text features, the similarity between the medical information to be stored and the existing medical information can be more comprehensively evaluated, which not only considers the similarity in content, but also the similarity in expression form. At the same time, the nonlinear analysis method can capture the complex relationship between features, rather than just a simple linear relationship. This method can more accurately reflect the actual similarity between the medical information to be stored and the existing medical information, and reduce the error caused by the simplification of the linear model. Therefore, the calculated basic feature similarity index is more reliable and accurate.

[0084] In this embodiment, the influence factor corresponding to the above-mentioned preset sentence average length similarity unit value is set to 0.6, and the influence factor corresponding to the preset high-frequency word ratio similarity unit value is set to 0.4. At the same time, the average sentence length corresponding to the medical information to be stored in this example is 25, and the high-frequency word ratio corresponding to the medical information to be stored is 35%. The text high-frequency word set corresponding to the medical information to be stored is {depression, psychology, emotion}, the text high-frequency word set corresponding to the first existing medical information is {lung cancer, chemotherapy, surgery}, the text high-frequency word set corresponding to the second existing medical information is {mental health, depression, emotion}, and the text high-frequency word set corresponding to the third existing medical information is {stroke, smoking, hypertension}. From this, the basic feature similarity index between the medical information to be stored and each existing medical information and the data relationship table between each parameter can be obtained, as shown in Table 2 Similarity index and corresponding parameter change table.

[0085] Table 2 Similarity index and changes between corresponding parameters By observing the data in the similarity index table in Table 2 above, it is found that the greater the deviation between the average sentence length and high-frequency vocabulary ratio corresponding to each existing medical information and the average sentence length and high-frequency vocabulary ratio corresponding to the medical information to be stored, the smaller the similarity of the high-frequency vocabulary set, and the lower the similarity index obtained. In this example, the average sentence length corresponding to the second existing medical information is 20 words, and the high-frequency vocabulary ratio is 30%, which has the smallest deviation from the average sentence length and high-frequency vocabulary ratio corresponding to the medical information to be stored, and the high-frequency vocabulary set similarity between the high-frequency vocabulary set of the text corresponding to the second existing medical information and the high-frequency vocabulary set of the text corresponding to the medical information to be stored is 33.33%. Therefore, the basic feature similarity index between the medical information to be stored and the second existing medical information is the highest, which is 83.21%.

[0086] Furthermore, the estimated access characteristic value of the medical information to be stored is specifically processed as follows: The basic feature similarity indexes between the medical information to be stored and each piece of existing medical information are arranged in descending order, and the existing medical information corresponding to the basic feature similarity index ranked first is recorded as the reference existing medical information.

[0087] The access feature values ​​of the referenced existing medical information are extracted as the estimated access feature values ​​of the medical information to be stored.

[0088] It should be explained that the estimated access characteristic value of the medical information to be stored is obtained by analyzing the basic characteristic similarity index between the medical information to be stored and each existing medical information. In this embodiment, according to the data in the similarity index in Table 2 and the change table between the corresponding parameters, the basic characteristic similarity index between the medical information to be stored and the second existing medical information is as high as 83.21%. Therefore, the second existing medical information is the reference existing medical information, and the access characteristic value of the second existing medical information is the estimated access characteristic value of the medical information to be stored.

[0089] Specifically, the access characteristic values ​​of each existing medical information and the estimated access characteristic values ​​of the medical information to be stored are compared with the access reference characteristic values ​​preset in the medical information database, and the specific comparison process is: If the access characteristic value of a piece of existing medical information is greater than or equal to the access reference characteristic value preset in the medical information library, then the piece of existing medical information is recorded as the first stored medical information, and the existing medical information corresponding to each piece of access characteristic value greater than or equal to the access reference characteristic value preset in the medical information library is counted and recorded as the first stored medical information data set.

[0090] It needs to be explained that if the access characteristic value of a certain existing medical information is greater than or equal to the access reference characteristic value preset in the medical information database, it means that the existing medical information has a higher degree of attention in the medical information, the existing medical information is frequently accessed and the response time requirement for the existing medical information is higher.

[0091] If the access characteristic value of a piece of existing medical information is smaller than the access reference characteristic value preset in the medical information library, the piece of existing medical information is recorded as the second stored medical information, and the existing medical information corresponding to each piece of access characteristic value smaller than the access reference characteristic value preset in the medical information library is counted and recorded as the second stored medical information data set.

[0092] It should be explained that if the access characteristic value of a certain existing medical information is less than the access reference characteristic value preset in the medical information database, it means that the existing medical information has a lower degree of attention in the medical information and the access to the existing medical information is less.

[0093] If the expected access characteristic value of the medical information to be stored is greater than or equal to the access reference characteristic value preset in the medical information database, the medical information to be stored will be recorded as the first medical information to be stored; if the expected access characteristic value of the medical information to be stored is less than the access reference characteristic value preset in the medical information database, the medical information to be stored will be recorded as the second medical information to be stored.

[0094] It should be explained that if the expected access characteristic value of the medical information to be stored is greater than or equal to the access reference characteristic value preset in the medical information database, it means that the medical information to be stored may be frequently accessed in the future and a timely response to the medical information to be stored is required. If the expected access characteristic value of the medical information to be stored is less than the access reference characteristic value preset in the medical information database, it means that the medical information to be stored may be accessed less frequently in the future.

[0095] Specifically, the storage management of each existing medical information and the medical information to be stored is completed, and the specific analysis process is as follows: The first stored medical information data set is stored in a first storage location, and the second stored medical information data set is stored in a second storage location.

[0096] The first medical information to be stored is stored in a first storage location, or the second medical information to be stored is stored in a second storage location.

[0097] In this embodiment, the above-mentioned first storage location is set as a local memory, and the second storage location is a cloud memory. Therefore, if the access characteristic value of a certain existing medical information is greater than or equal to the access reference characteristic value preset in the medical information library, the existing medical information is stored in the local memory; if the estimated access characteristic value of the medical information to be stored is greater than or equal to the access reference characteristic value preset in the medical information library, the medical information to be stored is stored in the local memory; if the access characteristic value of a certain existing medical information is less than the access reference characteristic value preset in the medical information library, the existing medical information is stored in the cloud memory; if the estimated access characteristic value of the medical information to be stored is less than the access reference characteristic value preset in the medical information library, the medical information to be stored is stored in the cloud memory.

[0098] Reference Figure 2 As shown, the second aspect of the present invention provides a system for a hospital information data security management method, including: a medical information statistics module, a medical information similarity determination module to be stored, a medical information storage module and a medical information database.

[0099] The medical information module is connected to the medical information similarity determination module to be stored, the medical information similarity determination module to be stored is connected to the medical information storage module, and the statistical medical information module, the medical information similarity determination module to be stored, and the medical information storage module are all connected to the medical information database.

[0100] The medical information statistics module is used to count the basic characteristic parameters and historical access information of each existing medical information from the medical information management platform, and analyze the historical access information of each existing medical information to obtain the access characteristic value of each existing medical information.

[0101] The similarity determination module for the medical information to be stored is used to obtain the basic characteristic parameters of the medical information to be stored, and to determine the similarity with the basic characteristic parameters of each existing medical information, so as to obtain the basic characteristic similarity index between the medical information to be stored and each existing medical information, thereby obtaining the reference existing medical information through processing, and calculating the access characteristic value of the reference existing medical information as the estimated access characteristic value of the medical information to be stored.

[0102] The medical information storage module is used to compare the access characteristic values ​​of each existing medical information and the expected access characteristic values ​​of the medical information to be stored with the access reference characteristic values ​​preset in the medical information library, and finally complete the storage management of each existing medical information and the medical information to be stored.

[0103] The medical information database is used to store preset access reference feature values, impact factors corresponding to preset historical access number unit values, impact factors corresponding to preset historical access duration unit values, impact factors corresponding to preset historical access maximum response duration unit values, preset access response reference duration, impact factors corresponding to preset sentence average length similarity unit values, and impact factors corresponding to preset high-frequency vocabulary ratio similarity unit values.

[0104] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined in this specification, they should all fall within the protection scope of the present invention.

Claims

1. A hospital information data security management method, characterized in that: include: S1. Statistical medical information: Statistic the basic characteristic parameters and historical access information of each existing medical information from the medical information management platform, and analyze the historical access information of each existing medical information to obtain the access characteristic value of each existing medical information; S2. Determination of similarity of the medical information to be stored: obtaining basic characteristic parameters of the medical information to be stored, and determining similarity with basic characteristic parameters of each piece of existing medical information, obtaining a basic characteristic similarity index between the medical information to be stored and each piece of existing medical information, thereby obtaining reference existing medical information through processing, and calculating access characteristic values ​​of the reference existing medical information as estimated access characteristic values ​​of the medical information to be stored; S3. Medical information storage: Compare the access characteristic values ​​of each existing medical information and the estimated access characteristic values ​​of the medical information to be stored with the preset access reference characteristic values ​​in the medical information database, and finally complete the storage management of each existing medical information and the medical information to be stored.

2. A hospital information data security management method according to claim 1, characterized in that: The historical access information of each piece of existing medical information specifically includes the historical access times, historical access duration and historical maximum response duration of each piece of existing medical information.

3. A hospital information data security management method according to claim 2, characterized in that: The specific analysis process of the access characteristic values ​​of each existing medical information is as follows: The historical access times, historical access durations, and historical access maximum response durations of each piece of existing medical information are comprehensively analyzed to obtain the access characteristic values ​​of each piece of existing medical information. The specific analysis formula is: In the formula, is the access characteristic value of the i-th existing medical information, is the number of each existing medical information, i=1,2,3...j, j is the total number of existing medical information, e is a natural constant, The impact factor corresponding to the historical access number unit value preset in the medical information database, is the historical access count of the i-th existing medical information, is the impact factor corresponding to the historical access time unit value preset in the medical information database, is the historical access duration of the i-th existing medical information, The impact factor corresponding to the unit value of the maximum response time of historical access preset in the medical information database, is the maximum historical response time for accessing the i-th existing medical information, The reference time for access response preset in the medical information database.

4. A hospital information data security management method according to claim 1, characterized in that: The basic characteristic parameters of each existing medical information specifically include the text length corresponding to each existing medical information, each text vocabulary, and the number of sentences in the text.

5. A hospital information data security management method according to claim 1, characterized in that: The basic characteristic parameters of the medical information to be stored specifically include the text length, each text vocabulary, and the number of sentences in the text corresponding to the medical information to be stored.

6. A hospital information data security management method according to claim 1, characterized in that: The basic feature similarity index between the medical information to be stored and each existing medical information, the specific analysis process is: The length of the text corresponding to each existing medical information is processed by ratio with the number of sentences in the text corresponding to each existing medical information to obtain the average length of the sentence corresponding to each existing medical information; The number of occurrences of each text word corresponding to each existing medical information is counted respectively to obtain the number of occurrences of each text word corresponding to each existing medical information, and the number of occurrences of each text word is arranged in descending order, thereby counting the total number of text words corresponding to the top three occurrences, which is recorded as the number of high-frequency words in the text corresponding to each existing medical information; The text words corresponding to the top three occurrences in each of the existing medical information are recorded as the text high-frequency word set corresponding to each of the existing medical information; Counting the number of text words corresponding to each existing medical information, performing ratio processing on the number of high-frequency words in the text corresponding to each existing medical information and the number of text words corresponding to each existing medical information, to obtain the ratio of high-frequency words corresponding to each existing medical information; Performing ratio processing on the length of the text corresponding to the medical information to be stored and the number of sentences in the text corresponding to the medical information to be stored, to obtain the average length of the sentences corresponding to the medical information to be stored; The number of occurrences of each text word corresponding to the medical information to be stored is counted respectively to obtain the number of occurrences of each text word corresponding to the medical information to be stored, and the number of occurrences of each text word is arranged in descending order, thereby counting the total number of text words corresponding to the top three occurrences, which is recorded as the number of high-frequency words in the text corresponding to the medical information to be stored; The text words corresponding to the top three occurrences in the obtained medical information to be stored are recorded as the text high-frequency word set corresponding to the medical information to be stored; Counting the number of text words corresponding to the medical information to be stored, performing ratio processing on the number of high-frequency words in the text corresponding to the medical information to be stored and the number of text words corresponding to the medical information to be stored, to obtain the corresponding high-frequency word ratio of the medical information to be stored; A comprehensive analysis is performed on the average sentence length, high-frequency word ratio, and text high-frequency word set corresponding to each existing medical information and the average sentence length, high-frequency word ratio, and text high-frequency word set corresponding to the medical information to be stored to obtain the basic feature similarity index between the medical information to be stored and each existing medical information.

7. A hospital information data security management method according to claim 6, characterized in that: The estimated access characteristic value of the medical information to be stored is specifically processed as follows: The basic feature similarity indexes between the medical information to be stored and the existing medical information are arranged in descending order, and the existing medical information corresponding to the basic feature similarity index ranked first is recorded as the reference existing medical information; The access feature values ​​of the referenced existing medical information are extracted as the estimated access feature values ​​of the medical information to be stored.

8. A hospital information data security management method according to claim 1, characterized in that: The access characteristic values ​​of each existing medical information and the estimated access characteristic values ​​of the medical information to be stored are compared with the access reference characteristic values ​​preset in the medical information database, and the specific comparison process is: If the access characteristic value of a certain existing medical information is greater than or equal to the access reference characteristic value preset in the medical information database, the existing medical information is recorded as the first stored medical information, and the existing medical information corresponding to each piece of access characteristic value greater than or equal to the access reference characteristic value preset in the medical information database is counted and recorded as the first stored medical information data set; If the access characteristic value of a certain existing medical information is less than the access reference characteristic value preset in the medical information database, the existing medical information is recorded as the second stored medical information, and the existing medical information corresponding to each access characteristic value less than the access reference characteristic value preset in the medical information database is counted and recorded as the second stored medical information data set; If the expected access characteristic value of the medical information to be stored is greater than or equal to the access reference characteristic value preset in the medical information database, the medical information to be stored will be recorded as the first medical information to be stored; if the expected access characteristic value of the medical information to be stored is less than the access reference characteristic value preset in the medical information database, the medical information to be stored will be recorded as the second medical information to be stored.

9. A hospital information data security management method according to claim 8, characterized in that: The storage management of each existing medical information and the medical information to be stored is completed, and the specific analysis process is as follows: storing the first stored medical information data set in a first storage location, and storing the second stored medical information data set in a second storage location; The first medical information to be stored is stored in a first storage location, or the second medical information to be stored is stored in a second storage location.

10. A system using a hospital information data security management method as claimed in any one of claims 1 to 9, characterized in that: include: The medical information statistics module is used to count the basic characteristic parameters and historical access information of each existing medical information from the medical information management platform, and analyze the historical access information of each existing medical information to obtain the access characteristic value of each existing medical information; The similarity determination module of the medical information to be stored is used to obtain the basic characteristic parameters of the medical information to be stored, and to determine the similarity with the basic characteristic parameters of each existing medical information, so as to obtain the basic characteristic similarity index between the medical information to be stored and each existing medical information, thereby obtaining the reference existing medical information through processing, and calculating the access characteristic value of the reference existing medical information as the estimated access characteristic value of the medical information to be stored; The medical information storage module is used to compare the access characteristic values ​​of each existing medical information and the expected access characteristic values ​​of the medical information to be stored with the access reference characteristic values ​​preset in the medical information library, and finally complete the storage management of each existing medical information and the medical information to be stored.

Images