Nursing information processing method, device and system based on medical data mining

By segmenting and weight calculation of nursing information, screening the best segmentation method to build the Hoffman coding table, solving the problem of low Hoffman coding compression efficiency and achieving more efficient nursing information compression and storage.

CN118631261BActive Publication Date: 2024-11-15FOURTH MILITARY MEDICAL UNIVERSITY
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
CN202411095899.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-12
Publication Date
2024-11-15
Estimated Expiration
2044-08-12

AI Technical Summary

Technical Problem

The prior art uses Hoffman encoding to compress care information, and the compression efficiency is low, mainly due to the high similarity of care information, the frequency construction of Hoffman encoding tables is inefficient.

Method used

By extracting nursing information and preprocessing it, it is divided into substrings of different lengths according to different segmentation methods, the information weight, information correlation coefficient and information occupancy coefficient are calculated, and the best segmentation method is filtered to construct the Hoffman coding table , optimize the compression efficiency of Hoffman encoding.

Benefits of technology

Improves the compression efficiency of nursing information, reduces storage space requirements, and speeds up data access and decoding.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118631261B_ABST
    Figure CN118631261B_ABST
Patent Text Reader

Abstract

The present application relates to the field of nursing information mining, and specifically to a nursing information processing method, device and system based on medical data mining, the method comprising: extracting nursing information, obtaining nursing information fragments, and dividing the nursing information fragments according to different segmentation methods; for each segmentation method, determining the nursing information string and obtaining the information volume weight; for each nursing information string, obtaining the information correlation coefficient; obtaining the information volume coefficient, using the information volume coefficient as a node, using Huffman coding to obtain the Huffman coding table, and calculating the compressed information volume of the nursing information fragment; selecting the best segmentation method according to the compressed information volume obtained by each segmentation method, using the Huffman coding table obtained by the best segmentation method as a method for encoding and compressing the nursing information, storing the encoded data, and obtaining the processing result of the nursing information. The present application solves the problem of low compression efficiency of nursing information when it is compressed only based on frequency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of nursing information mining, and specifically to a nursing information processing method, device and system based on medical data mining. Background Art

[0002] A huge amount of nursing information and medical data will be generated during the medical treatment process. In order to ensure timely and effective treatment of patients, it is necessary to save the historical medical data of all patients. Since the amount of nursing information and medical data is large, direct storage is prone to loss. Therefore, a coding compression algorithm is generally used to compress the nursing information and medical data, and then the compressed information is saved.

[0003] The nursing information of the same patient is highly similar. When the conditions of different patients are similar, the nursing information is also highly similar. Therefore, Huffman coding is generally used to compress nursing information. When Huffman coding is used to compress nursing information, Huffman coding constructs a Huffman coding table by the frequency of characters. Due to the high similarity of nursing information, the compression efficiency of constructing a Huffman coding table by frequency is low. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of this application is to provide a nursing information processing method, device and system based on medical data mining. The technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present application provides a nursing information processing method based on medical data mining, the method comprising the following steps:

[0006] Extracting and preprocessing nursing information, obtaining nursing information fragments, and dividing the nursing information fragments into substrings of different lengths according to different segmentation methods;

[0007] Record any segmentation method as a target segmentation method, record all substrings of different lengths of the nursing information fragment under the target segmentation method as nursing information strings, and obtain the information weight of the nursing information string according to the number of times a single character contained in the nursing information string is repeated in a single-character substring and the total number of single-character substrings;

[0008] For each nursing information string, obtaining an information correlation coefficient of the nursing information string according to the information weights of all nursing information strings having the same appearance frequency as the nursing information string and the appearance frequency of the nursing information string;

[0009] According to the information association coefficient of the nursing information string, the length of the nursing information string and the frequency of occurrence of the nursing information string in the nursing information segment, the information occupation coefficient of the nursing information string is obtained, and the information occupation coefficient of the nursing information string is used as a node, and the Huffman coding is used to obtain the Huffman coding table, and the compressed information volume of the nursing information segment under the target segmentation method is calculated in combination with the length and frequency of occurrence of the nursing information string;

[0010] The best segmentation method is selected according to the compressed information amount of the nursing information fragments under different segmentation methods, and the Huffman coding table obtained by the best segmentation method is used as a method for encoding and compressing the nursing information. The encoded data is stored to obtain the processing result of the nursing information.

[0011] Furthermore, the specific process of dividing the nursing information fragment into substrings of different lengths according to different segmentation methods is as follows:

[0012] Starting from the first character of the nursing information fragment, N characters are divided into a group to obtain substrings, and the last characters of the nursing information fragment that are less than N characters are taken as a substring separately, where the value range of N is all integers greater than or equal to 2 and less than or equal to N1, and N1 is the number of characters contained in the nursing information fragment.

[0013] Furthermore, the construction process of the information weight of the nursing information character string is as follows:

[0014] The number of times each single character contained in the nursing information string appears repeatedly in the single-character substring is recorded as the word repetition number of the single character; the sum of the word repetition numbers of all single characters contained in the nursing information string is recorded as the character display information volume of the nursing information string; the ratio of the character display information volume of the nursing information string to the total number of single-character substrings is recorded as the information volume weight of the nursing information string.

[0015] Further, for each nursing information string, the information correlation coefficient of the nursing information string is obtained according to the information weight of all nursing information strings with the same occurrence frequency as the nursing information string and the occurrence frequency of the nursing information string. The specific process of obtaining is:

[0016] Record the mean of the information weights of all nursing information strings with the same appearance frequency as the nursing information string as the first mean of the nursing information string, and record the product of the appearance frequency of the nursing information string and the first mean as the same-level association coefficient of the nursing information string;

[0017] Recording the sum of the occurrence frequencies of two different nursing information character strings as the associated frequencies of the two different nursing information character strings, and for each nursing information character string, recording the two different nursing information character strings corresponding to the same associated frequencies as the occurrence frequency of the nursing information character string as the associated nursing information character strings;

[0018] Obtaining a pre-association coefficient of the nursing information string according to the number of associated nursing information strings, the frequency of occurrence of the nursing information string, and the information amount weight of the nursing information string;

[0019] According to the same level association coefficient and the previous association coefficient of the nursing information string, the information association coefficient of the nursing information string is obtained, and the information association coefficient of the nursing information string is positively correlated with the same level association coefficient and the previous association coefficient of the nursing information string respectively.

[0020] Furthermore, the process of determining the pre-association coefficient of the nursing information character string is as follows:

[0021] The product of the information weight of the nursing information string and the frequency of occurrence of the nursing information string is recorded as the first product of the nursing information string, and the ratio of the first product of the nursing information string to the number of associated nursing information strings of the nursing information string is recorded as the pre-association coefficient of the nursing information string.

[0022] Furthermore, the process of determining the information occupation coefficient of the nursing information character string is as follows:

[0023] The product of the information relevance coefficient of the nursing information string, the length of the nursing information string and the frequency of occurrence of the nursing information string in the nursing information segment is recorded as the information occupation coefficient of the nursing information string.

[0024] Furthermore, the process of determining the amount of compressed information of the nursing information segment in the target segmentation mode is as follows:

[0025] The product of the frequency of occurrence of the nursing information character string in the nursing information segment and the length of the nursing information character string is recorded as the information coding length of the nursing information character string, and the cumulative sum of the information coding lengths of all nursing information character strings in the nursing information segment under the target segmentation mode is recorded as the first coding length of the nursing information segment under the target segmentation mode;

[0026] The sum of the length of the nursing information character string and the length of the nursing information character string in the Huffman coding table is recorded as the second coding length of the nursing information character string;

[0027] According to the first coding length and the second coding length of all nursing information character strings of the nursing information segments under the target segmentation method, the compressed information amount of the nursing information segments under the target segmentation method is obtained, and the compressed information amount of the nursing information segments is positively correlated with the first coding length and the second coding length of all nursing information character strings of the nursing information segments under the target segmentation method.

[0028] Furthermore, the specific process of selecting the best segmentation method according to the compressed information amount of the nursing information fragments under different segmentation methods is as follows:

[0029] The segmentation method corresponding to the minimum value of the compressed information amount is taken as the optimal segmentation method.

[0030] In a second aspect, an embodiment of the present application provides a nursing information processing device based on medical data mining, wherein the nursing information processing device includes: a nursing information acquisition module, a nursing information segmentation and analysis module, and a nursing information compression module.

[0031] The nursing information acquisition module is used to extract and pre-process the nursing information, obtain the nursing information fragments, and divide the nursing information fragments into substrings of different lengths according to different segmentation methods;

[0032] Nursing information segmentation analysis module: used to record any segmentation method as a target segmentation method, record all substrings of different lengths of the nursing information fragment under the target segmentation method as nursing information strings, and obtain the information weight of the nursing information string according to the number of times a single character contained in the nursing information string is repeated in a single-character substring and the total number of single-character substrings;

[0033] For each nursing information string, obtaining an information correlation coefficient of the nursing information string according to the information weights of all nursing information strings having the same appearance frequency as the nursing information string and the appearance frequency of the nursing information string;

[0034] According to the information association coefficient of the nursing information string, the length of the nursing information string and the frequency of occurrence of the nursing information string in the nursing information segment, the information occupation coefficient of the nursing information string is obtained, and the information occupation coefficient of the nursing information string is used as a node, and the Huffman coding is used to obtain the Huffman coding table, and the compressed information volume of the nursing information segment under the target segmentation method is calculated in combination with the length and frequency of occurrence of the nursing information string;

[0035] Nursing information compression module: used to select the best segmentation method according to the amount of compressed information of the nursing information fragments under different segmentation methods, use the Huffman coding table obtained by the best segmentation method as a method for encoding and compressing the nursing information, store the encoded data, and obtain the processing results of the nursing information.

[0036] In a third aspect, an embodiment of the present application also provides a nursing information processing system based on medical data mining, the system comprising a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of any one of the above methods when executing the computer program.

[0037] It can be seen from the above embodiments that the nursing information processing method, device and system based on medical data mining provided in the embodiments of the present application have at least the following beneficial effects:

[0038] The present application extracts nursing information and segments it according to different segmentation methods, and analyzes the compression degree of the nursing information character string obtained by each segmentation method. First, the weight of the amount of information contained in the nursing information character string is evaluated to obtain the information weight of the nursing information character string; then, according to the correlation between the front character and the back character in the adjacent characters, and the correlation between the back character and the front character in the adjacent characters, the information correlation coefficient of the nursing information character string is obtained. The information correlation coefficient of the nursing information character string is a comprehensive evaluation of the significance of similarity between nursing information; according to the process of compressing and decompressing data using Huffman coding, the closer the information code is to the root node, the shorter the access and The faster the decoding speed is, the information occupancy coefficient of the nursing information string is calculated according to the frequency of occurrence of the nursing information string in the nursing information fragment, the length of the nursing information string, and the information correlation coefficient of the nursing information string. The information occupancy coefficient of the nursing information string is used as a node, and Huffman coding is used to obtain the Huffman coding table. According to the Huffman coding table, the compression effect of the corresponding segmentation method on the nursing information fragment is evaluated, and the best segmentation method is selected according to the compression effect. The Huffman coding table obtained by the best segmentation method is used as a method for compressing the nursing information encoding, the encoded data is stored, and the processing result of the nursing information is obtained, so as to solve the problem of low compression efficiency of nursing information based on frequency alone. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 A flowchart of the steps of a nursing information processing method based on medical data mining provided in one embodiment of the present application;

[0041] Figure 2A flowchart for obtaining information correlation coefficients provided for one embodiment of the present application;

[0042] Figure 3 A flowchart for obtaining the information occupation coefficient provided for one embodiment of the present application;

[0043] Figure 4 A schematic diagram of the structure of a nursing information processing device provided for one embodiment of the present application. DETAILED DESCRIPTION

[0044] In conjunction with the accompanying drawings and preferred embodiments, the nursing information processing method, device and system based on medical data mining proposed in this application, its specific implementation, structure, features and functions are described in detail as follows. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0045] Unless otherwise specified and limited, terms such as "comprises", "comprising" or any other variants thereof are intended to cover non-exclusive inclusion, so that a circuit structure, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such articles or devices. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the article or device including the element. In addition, the term "and\or" used herein includes any and all combinations of one or more related listed items. All technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of this application.

[0046] The specific solutions of the nursing information processing method, device and system based on medical data mining provided by the present application are described in detail below with reference to the accompanying drawings.

[0047] See also Figure 1 , which shows a flowchart of a nursing information processing method based on medical data mining provided by an embodiment of the present application, the method comprising the following steps:

[0048] Step 1: Extract nursing information and preprocess it to obtain nursing information fragments, and divide the nursing information fragments into substrings of different lengths according to different segmentation methods; record any segmentation method as the target segmentation method, and record all substrings of different lengths of the nursing information fragments under the target segmentation method as nursing information strings, and obtain the information weight of the nursing information string based on the number of times a single character contained in the nursing information string is repeated in the single-character substring and the total number of single-character substrings.

[0049] Extract the nursing information of all patients from the medical nursing information database storing nursing information. The nursing information in this embodiment includes basic patient information, nursing staff information, and nursing detection information. The implementer can also determine the type of data included in the nursing information according to the type of nursing information to be saved, and this application does not impose any special restrictions.

[0050] Using punctuation marks as segmentation conditions, the patient's nursing information is segmented using regular expressions to obtain nursing information fragments. The nursing information fragments are converted into hexadecimal data for subsequent storage.

[0051] The hexadecimal data is data composed of 16 characters from 0 to F. This embodiment uses the UTF-16 encoding method to convert the nursing information fragment into binary data, and then converts the binary data into hexadecimal data. Under the premise of achieving the purpose of converting the nursing information fragment into hexadecimal data, the implementer can use other hexadecimal conversion methods in the prior art, which are not limited here.

[0052] At this point, the nursing information fragment is obtained.

[0053] The nursing information fragment is segmented, starting from the first character of the nursing information fragment, N characters are segmented into a group, substrings are obtained, and the last characters of the nursing information fragment that are less than N characters are taken as a substring. The value range of N is all integers greater than or equal to 2 and less than or equal to N1, and N1 is the number of characters contained in the nursing information fragment.

[0054] For example, when the nursing information segment is scfga and N is 2, the substrings obtained by segmenting the nursing information segment are sc, fg, and a.

[0055] Any segmentation method is recorded as a target segmentation method, and this embodiment is described by taking any segmentation method as an example.

[0056] Huffman coding constructs a Huffman coding table based on the frequency of characters. Therefore, traditional Huffman coding requires a separate encoding for substrings that appear only once, which wastes a lot of memory space. In order to improve coding efficiency and compression efficiency, substrings that appear only once are split into single-character substrings.

[0057] Record all substrings as nursing information strings.

[0058] Since nursing information has high similarity, there will be a large number of identical nursing information strings. When encoding nursing information strings according to nursing information strings, the length of the nursing information strings needs to be as small as possible. Therefore, the weight of the amount of information contained in the nursing information strings is evaluated.

[0059] The information amount weight of the nursing information character string is obtained according to the number of times a single character contained in the nursing information character string appears repeatedly in the single-character substring and the total number of the single-character substrings.

[0060] For example, when the nursing information string is 123, the single characters contained in the nursing information string are 1, 2, and 3 respectively, and the single-character substring is a substring containing only one character. The number of times the single character contained in the nursing information string is repeated in the single-character substring is the number of times 1, 2, and 3 appear in all the single-character substrings. If all the single-character substrings are 1, 2, 2, 3, 4, 4, 4, 5, 5, then the number of times the single character 1 contained in the nursing information string is repeated in the single-character substring is 1, the number of times the single character 2 contained in the nursing information string is repeated in the single-character substring is 2, and the number of times the single character 3 contained in the nursing information string is repeated in the single-character substring is 1.

[0061] Preferably, as an embodiment of the present application, the number of times each single character contained in the nursing information string appears repeatedly in the single-character substring is recorded as the word repetition number of the single character; the sum of the word repetition numbers of all single characters contained in the nursing information string is recorded as the character display information volume of the nursing information string; the ratio of the character display information volume of the nursing information string to the total number of single-character substrings is recorded as the information volume weight of the nursing information string.

[0062] The greater the number of times a single character contained in a nursing information string is repeated in a substring of a single character, the higher the frequency of occurrence of the single character contained in the nursing information string in the nursing information fragment, and the more information is contained in the nursing information string. At this time, the weight of the amount of information contained in the nursing information string is greater, that is, the weight of the amount of information in the nursing information string is greater.

[0063] At this point, the information weight of the nursing information character string is obtained.

[0064] Step 2: For each nursing information string, the information relevance coefficient of the nursing information string is obtained according to the information weights of all nursing information strings with the same occurrence frequency as the nursing information string and the occurrence frequency of the nursing information string.

[0065] Nursing information has a high degree of similarity, and there is a certain correlation between the nursing information of different patients. For example, in 2024, if the number 202 appears in the nursing information, the probability of the subsequent appearance of the number 4 is extremely high. However, since the number 4 may also correspond to information such as month, date, and bed number, the probability that the number before 4 is 202 is relatively small.

[0066] When the correlation between nursing information is stronger, the amount of information contained in the nursing information string is more. When constructing a Huffman tree, the nursing information string should be closer to the root node of the Huffman tree to make the encoding and decoding data more efficient. Therefore, analyze the correlation between nursing information.

[0067] Obtain the co - level correlation coefficient of the nursing information string according to the information volume weight of all nursing information strings with the same occurrence frequency as the nursing information string and the occurrence frequency of the nursing information string.

[0068] Preferably, as an embodiment of the present application, analyze each nursing information string separately. Denote the average value of the information volume weights of all nursing information strings with the same occurrence frequency as the nursing information string as the first average value of the nursing information string, and denote the product of the occurrence frequency of the nursing information string and the first average value as the co - level correlation coefficient of the nursing information string.

[0069] Preferably, as another embodiment of the present application, denote the sum of the occurrence frequency of the nursing information string and the first average value as the co - level correlation coefficient of the nursing information string.

[0070] When the co - level correlation coefficient of the nursing information string is larger, the correlation between nursing information is greater.

[0071] For two adjacent characters, if, on the premise that the latter character appears, the probability that the former character appears before this character is extremely high, it indicates that the degree of association between these two adjacent characters is very high.

[0072] For example, the character "砦" is generally used in personal names and place names. The place name "Wangzhai" in Zhengzhou City contains the character "砦". When the address information in the patient's basic information appears the place name "Wangzhai", if the character "砦" appears in the nursing information, the probability that "王" appears before "砦" is extremely high. That is, the degree of association between the two characters "王" and "砦" is very high.

[0073] The sum of the frequencies of occurrence of every two different nursing information character strings is calculated respectively, and the sum of the frequencies of occurrence of two different nursing information character strings is recorded as the associated frequency of the two different nursing information character strings. For each nursing information character string, two different nursing information character strings corresponding to the same associated frequency as the occurrence frequency of the nursing information character string are both recorded as the associated nursing information character strings of the nursing information character string.

[0074] For example, when the nursing information string is abc, if the occurrence frequency of the nursing information string abc is 5, the occurrence frequency of the nursing information string ab is 3, and the occurrence frequency of the nursing information string c is 2, then the associated frequency of the nursing information strings ab and c is 5. Therefore, the associated frequency of the nursing information strings ab and c is equal to the occurrence frequency of the nursing information string abc. Therefore, the nursing information strings ab and c are both associated nursing information strings of the nursing information string abc.

[0075] The pre-association coefficient of the nursing information string is obtained according to the number of associated nursing information strings, the frequency of occurrence of the nursing information string, and the information amount weight of the nursing information string.

[0076] Preferably, as an embodiment of the present application, the product of the information amount weight of the nursing information string and the frequency of occurrence of the nursing information string is recorded as the first product of the nursing information string, and the ratio of the first product of the nursing information string to the number of associated nursing information strings of the nursing information string is recorded as the pre-association coefficient of the nursing information string.

[0077] Preferably, as another embodiment of the present application, the sum of the information amount weight of the nursing information string and the frequency of occurrence of the nursing information string is recorded as the first sum value of the nursing information string, and the ratio of the first sum value of the nursing information string to the number of associated nursing information strings of the nursing information string is recorded as the pre-association coefficient of the nursing information string.

[0078] When the frequency of occurrence of the nursing information string and the information weight of the nursing information string are greater, and the number of nursing information strings is smaller, the pre-association coefficient of the nursing information string is greater. At this time, the degree of correlation between the information contained in the nursing information string and other information is more significant.

[0079] According to the same-level association coefficient and previous association coefficient of the nursing information string, the information association coefficient of the nursing information string is obtained. The information association coefficient acquisition flow chart is as follows: Figure 2 shown.

[0080] Preferably, as an embodiment of the present application, the product of the same-level association coefficient and the previous association coefficient of the nursing information character string is recorded as the information association coefficient of the nursing information character string.

[0081] Preferably, as another embodiment of the present application, the sum of the same-level association coefficient and the previous association coefficient of the nursing information character string is recorded as the information association coefficient of the nursing information character string.

[0082] When the information correlation coefficient of the nursing information string is larger, the more times the nursing information string appears in the nursing information segment, the closer the correlation between the information corresponding to the nursing information string and other information in the nursing information segment is, and at this time, the information corresponding to the nursing information string in the nursing information segment is more critical and important.

[0083] At this point, the information relevance coefficient of the nursing information character string is obtained.

[0084] Step three: According to the information correlation coefficient of the nursing information string, the length of the nursing information string and the frequency of occurrence of the nursing information string in the nursing information segment, the information occupancy coefficient of the nursing information string is obtained, and the information occupancy coefficient of the nursing information string is used as a node. Huffman coding is used to obtain the Huffman coding table, and the length and frequency of occurrence of the nursing information string are combined to calculate the compressed information volume of the nursing information segment under the target segmentation method; the best segmentation method is selected according to the compressed information volume of the nursing information segment under different segmentation methods, and the Huffman coding table obtained by the best segmentation method is used as a method for compressing the nursing information encoding, the encoded data is stored, and the processing result of the nursing information is obtained.

[0085] In the process of compressing and decompressing data using Huffman coding, the closer the information code is to the root node, the shorter it is, and the faster it is to access and decode. When the nursing information string appears more frequently in the nursing information segment, the longer the length of the nursing information string is, and the greater the information correlation coefficient of the nursing information string is, in the process of constructing the Huffman coding table using Huffman coding, the nursing information string should be closer to the root node of the Huffman tree.

[0086] According to the information correlation coefficient of the nursing information string, the length of the nursing information string and the frequency of occurrence of the nursing information string in the nursing information segment, the information occupation coefficient of the nursing information string is obtained. The information occupation coefficient acquisition flow chart is as follows: Figure 3 shown.

[0087] Preferably, as an embodiment of the present application, the information occupancy coefficient of the nursing information string is the product of the information relevance coefficient of the nursing information string, the length of the nursing information string and the frequency of occurrence of the nursing information string in the nursing information segment.

[0088] When the information correlation coefficient of the nursing information string, the length of the nursing information string and the frequency of occurrence of the nursing information string in the nursing information segment are all larger, the information occupancy coefficient of the nursing information string is larger, and at this time, the nursing information string should be closer to the root node of the Huffman tree.

[0089] The information content coefficient of the nursing information string is used as a node, and Huffman coding is used to construct a Huffman tree to obtain a Huffman coding table.

[0090] According to the length and occurrence frequency of the nursing information character string and the length of the nursing information character string in the Huffman coding table, the compressed information amount of the nursing information segment under the target segmentation method is calculated.

[0091] Preferably, as an embodiment of the present application, the product of the frequency of occurrence of the nursing information string in the nursing information segment and the length of the nursing information string is recorded as the information coding length of the nursing information string, and the cumulative sum of the information coding lengths of all nursing information strings in the target segmentation mode of the nursing information segment is recorded as the first coding length of the nursing information segment in the target segmentation mode. The sum of the length of the nursing information string and the length of the nursing information string in the Huffman coding table is recorded as the second coding length of the nursing information string, and the cumulative sum of the second coding lengths of all nursing information strings in the target segmentation mode of the nursing information segment is recorded as the second coding length of the nursing information segment in the target segmentation mode. The sum of the first coding length and the second coding length of the nursing information segment in the target segmentation mode is recorded as the compressed information amount of the nursing information segment in the target segmentation mode.

[0092] Preferably, as another embodiment of the present application, the amount of compressed information of the nursing information segment in the target segmentation method is the product of the first coding length and the second coding length of the nursing information segment in the target segmentation method.

[0093] The compressed information volume of the nursing information segment evaluates the compression effect of the nursing information segment. When the compressed information volume of the nursing information segment is smaller, the compression efficiency of the nursing information segment is higher, the storage space required is less, and at this time, the compression and decompression speed of the nursing information segment is faster and the energy consumption is lower.

[0094] At this point, the compressed information volume of the nursing information segment under the target segmentation method is obtained.

[0095] It should be noted that the compressed information amount of the nursing information segment in each segmentation method can be obtained in the same way, that is, when the nursing information segment is segmented using each different segmentation method, there is a corresponding compressed information amount.

[0096] The compressed information amounts corresponding to all the segmentation methods for segmenting the nursing information fragments are compared, and the segmentation method corresponding to the minimum value of the compressed information amount is taken as the optimal segmentation method. The Huffman coding table obtained by the optimal segmentation method is used as the method for encoding and compressing the nursing information. The encoded data is stored to obtain the processing results of the nursing information.

[0097] At this point, the processing result of the nursing information is obtained.

[0098] See also Figure 4 , Figure 4 1 is a schematic diagram of the structure of a nursing information processing device based on medical data mining provided by an embodiment of the present application. In this embodiment, the various units included in the device are used to execute the various steps in the embodiment corresponding to the nursing information processing method based on medical data mining. Figure 4 ,The nursing information processing device includes: a nursing information acquisition module, a nursing information segmentation and analysis module, and a nursing information compression module.

[0099] The nursing information acquisition module is used to extract and pre-process the nursing information, obtain the nursing information fragments, and divide the nursing information fragments into substrings of different lengths according to different segmentation methods;

[0100] Nursing information segmentation analysis module: used to record any segmentation method as a target segmentation method, record all substrings of different lengths of the nursing information fragment under the target segmentation method as nursing information strings, and obtain the information weight of the nursing information string according to the number of times a single character contained in the nursing information string is repeated in a single-character substring and the total number of single-character substrings;

[0101] For each nursing information string, obtaining an information correlation coefficient of the nursing information string according to the information weights of all nursing information strings having the same appearance frequency as the nursing information string and the appearance frequency of the nursing information string;

[0102] According to the information association coefficient of the nursing information string, the length of the nursing information string and the frequency of occurrence of the nursing information string in the nursing information segment, the information occupation coefficient of the nursing information string is obtained, and the information occupation coefficient of the nursing information string is used as a node, and the Huffman coding is used to obtain the Huffman coding table, and the compressed information volume of the nursing information segment under the target segmentation method is calculated in combination with the length and frequency of occurrence of the nursing information string;

[0103] Nursing information compression module: used to select the best segmentation method according to the amount of compressed information of the nursing information fragments under different segmentation methods, use the Huffman coding table obtained by the best segmentation method as a method for encoding and compressing the nursing information, store the encoded data, and obtain the processing results of the nursing information.

[0104] Based on the same inventive concept as the above method, an embodiment of the present application also provides a nursing information processing system based on medical data mining, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the steps of any one of the above-mentioned nursing information processing methods based on medical data mining are implemented.

[0105] It is to be understood that the sequence of the embodiments of the present application described above is for description only and does not represent the advantages and disadvantages of the embodiments. The above describes specific embodiments of the present specification. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0106] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0107] The above content is only an implementation method of the present application and is not intended to limit the scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the protection scope of the present application.

Claims

1. A nursing information processing method based on medical data mining, characterized in that: The method comprises the following steps: Extracting and preprocessing nursing information, obtaining nursing information fragments, and dividing the nursing information fragments into substrings of different lengths according to different segmentation methods; Record any segmentation method as a target segmentation method, record all substrings of different lengths of the nursing information fragment under the target segmentation method as nursing information strings, and obtain the information weight of the nursing information string according to the number of times a single character contained in the nursing information string is repeated in a single-character substring and the total number of single-character substrings; For each nursing information string, obtaining an information relevance coefficient of the nursing information string according to the information weights of all nursing information strings with the same appearance frequency as the nursing information string and the appearance frequency of the nursing information string in the nursing information segment; According to the information association coefficient of the nursing information string, the length of the nursing information string and the frequency of occurrence of the nursing information string in the nursing information segment, the information occupation coefficient of the nursing information string is obtained, and the information occupation coefficient of the nursing information string is used as a node, and the Huffman coding is used to obtain the Huffman coding table, and the compressed information volume of the nursing information segment under the target segmentation method is calculated in combination with the length and frequency of occurrence of the nursing information string; The best segmentation method is selected according to the compressed information amount of the nursing information fragments under different segmentation methods, and the Huffman coding table obtained by the best segmentation method is used as a method for encoding and compressing the nursing information. The encoded data is stored to obtain the processing result of the nursing information.

2. The nursing information processing method based on medical data mining according to claim 1, characterized in that: The specific process of dividing the nursing information fragment into substrings of different lengths according to different segmentation methods is as follows: Starting from the first character of the nursing information fragment, N characters are divided into a group to obtain substrings, and the last characters of the nursing information fragment that are less than N characters are taken as a substring separately, where the value range of N is all integers greater than or equal to 2 and less than or equal to N1, and N1 is the number of characters contained in the nursing information fragment.

3. The nursing information processing method based on medical data mining according to claim 1, characterized in that: The construction process of the information weight of the nursing information character string is as follows: The number of times each single character contained in the nursing information string appears repeatedly in the single-character substring is recorded as the word repetition number of the single character; the sum of the word repetition numbers of all single characters contained in the nursing information string is recorded as the character display information volume of the nursing information string; the ratio of the character display information volume of the nursing information string to the total number of single-character substrings is recorded as the information volume weight of the nursing information string.

4. The nursing information processing method based on medical data mining according to claim 1, characterized in that: For each nursing information string, the information correlation coefficient of the nursing information string is obtained according to the information weights of all nursing information strings with the same appearance frequency as the nursing information string and the appearance frequency of the nursing information string in the nursing information segment. The specific process of obtaining is: The mean of the information weights of all nursing information strings with the same appearance frequency as the nursing information string is recorded as the first mean of the nursing information string, and the product of the appearance frequency of the nursing information string in the nursing information segment and the first mean is recorded as the same-level association coefficient of the nursing information string; Recording the sum of the frequencies of occurrence of two different nursing information character strings as the associated frequencies of the two different nursing information character strings, and for each nursing information character string, recording the two different nursing information character strings corresponding to the associated frequencies having the same occurrence frequency of the nursing information character string in the nursing information segment as the associated nursing information character strings of the nursing information character string; Obtaining a pre-association coefficient of the nursing information string according to the number of associated nursing information strings, the frequency of occurrence of the nursing information string, and the information amount weight of the nursing information string; According to the same level association coefficient and the previous association coefficient of the nursing information string, the information association coefficient of the nursing information string is obtained, and the information association coefficient of the nursing information string is positively correlated with the same level association coefficient and the previous association coefficient of the nursing information string respectively.

5. The nursing information processing method based on medical data mining according to claim 4, characterized in that: The process of determining the pre-association coefficient of the nursing information string is as follows: The product of the information weight of the nursing information string and the frequency of occurrence of the nursing information string is recorded as the first product of the nursing information string, and the ratio of the first product of the nursing information string to the number of associated nursing information strings of the nursing information string is recorded as the pre-association coefficient of the nursing information string.

6. The nursing information processing method based on medical data mining according to claim 1, characterized in that: The process of determining the information occupation coefficient of the nursing information character string is as follows: The product of the information relevance coefficient of the nursing information string, the length of the nursing information string and the frequency of occurrence of the nursing information string in the nursing information segment is recorded as the information occupation coefficient of the nursing information string.

7. The nursing information processing method based on medical data mining according to claim 1, characterized in that: The process of determining the compressed information amount of the nursing information segment in the target segmentation mode is as follows: The product of the frequency of occurrence of the nursing information character string in the nursing information segment and the length of the nursing information character string is recorded as the information coding length of the nursing information character string, and the cumulative sum of the information coding lengths of all nursing information character strings in the nursing information segment under the target segmentation mode is recorded as the first coding length of the nursing information segment under the target segmentation mode; The sum of the length of the nursing information character string and the length of the nursing information character string in the Huffman coding table is recorded as the second coding length of the nursing information character string; According to the first coding length and the second coding length of all nursing information character strings of the nursing information segments under the target segmentation method, the compressed information amount of the nursing information segments under the target segmentation method is obtained, and the compressed information amount of the nursing information segments is positively correlated with the first coding length and the second coding length of all nursing information character strings of the nursing information segments under the target segmentation method.

8. The nursing information processing method based on medical data mining according to claim 1, characterized in that: The specific process of selecting the best segmentation method according to the amount of compressed information of the nursing information fragments under different segmentation methods is as follows: The segmentation method corresponding to the minimum value of the compressed information amount is taken as the optimal segmentation method.

9. Nursing information processing equipment based on medical data mining, characterized in that: include: The nursing information acquisition module is used to extract and pre-process the nursing information, obtain the nursing information fragments, and divide the nursing information fragments into substrings of different lengths according to different segmentation methods; Nursing information segmentation analysis module: used to record any segmentation method as a target segmentation method, record all substrings of different lengths of the nursing information fragment under the target segmentation method as nursing information strings, and obtain the information weight of the nursing information string according to the number of times a single character contained in the nursing information string is repeated in a single-character substring and the total number of single-character substrings; For each nursing information string, obtaining an information relevance coefficient of the nursing information string according to the information weights of all nursing information strings with the same appearance frequency as the nursing information string and the appearance frequency of the nursing information string in the nursing information segment; According to the information association coefficient of the nursing information string, the length of the nursing information string and the frequency of occurrence of the nursing information string in the nursing information segment, the information occupation coefficient of the nursing information string is obtained, and the information occupation coefficient of the nursing information string is used as a node, and the Huffman coding is used to obtain the Huffman coding table, and the compressed information volume of the nursing information segment under the target segmentation method is calculated in combination with the length and frequency of occurrence of the nursing information string; Nursing information compression module: used to select the best segmentation method according to the amount of compressed information of the nursing information fragments under different segmentation methods, use the Huffman coding table obtained by the best segmentation method as a method for encoding and compressing the nursing information, store the encoded data, and obtain the processing results of the nursing information.

10. A nursing information processing system based on medical data mining, characterized in that: The nursing information processing system includes a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of the method according to any one of claims 1 to 8 when executing the computer program.

Citation Information

Patent Citations

  • Financial financing service digital intelligent management system

    CN116318173A

  • Social security information processing method and system

    CN117278056A

  • Call bill data compression transmission method, apparatus and device, and storage medium

    CN117294764A

  • Intelligent data analysis method and system

    CN117807425A

  • Vehicle path planning method and system based on cloud network side end

    CN118376258A