Intelligent management method for head and neck surgical patient medical record data

Abstract

The application provides a kind of intelligent management method for head and neck surgical patient medical record data, belong to data processing field, this method includes: obtain the final word unit in each historical medical record of head and neck surgical patient with search content;Using search algorithm, get the historical medical record needed by the doctor;According to the distribution of each final word unit in search content and the historical medical record needed by the doctor, get the priority of each historical medical record needed by the doctor;If using search algorithm, the medical record is not searched out;According to the distribution of each final word unit in historical medical record, get the historical medical record needed by the doctor, and then get the priority.The application aims to solve the problem that when the current search algorithm based on Boolean logic is used to search the medical record needed by the doctor from several historical medical records of head and neck surgical patients, the current search algorithm can only search the medical record needed by the doctor, but cannot get the priority of the searched medical record.

Description

Technical Field

[0001] This invention belongs to the field of data processing, specifically relating to an intelligent management method for head and neck surgery patient medical record data. Background Technology

[0002] Treatment for head and neck surgery patients is often lengthy and involves multidisciplinary collaboration. An efficient retrieval system allows doctors to quickly access necessary disease information, such as past surgical records, pathology results, radiotherapy and chemotherapy regimens, and recent imaging changes during relapse visits. This significantly reduces the risk of misdiagnosis due to missing information. Therefore, improving the efficiency of retrieving head and neck surgery patient medical records not only enhances clinical diagnostic and treatment efficiency but also supports precision medicine decision-making, making it a crucial element in the digital transformation of head and neck surgery.

[0003] Because head and neck surgery patients' medical records typically contain a large amount of technical terminology and related medical information, Boolean-based retrieval algorithms are used to precisely match the desired content and retrieve the medical records needed by doctors. However, when using Boolean-based retrieval algorithms to search for medical records, only the medical records needed by doctors can be retrieved from all medical records; it is impossible to prioritize the retrieved medical records, which reduces the efficiency of clinical diagnosis and treatment. Summary of the Invention

[0004] To address the problem that current Boolean-based retrieval algorithms can only retrieve the medical records doctors need from patients' historical medical records without prioritizing them, thus reducing clinical diagnostic efficiency, this invention proposes an intelligent management method for head and neck surgery patient medical record data.

[0005] To achieve the above objectives, the present invention provides the following technical solution: obtaining the retrieval time, word units in the retrieval content, word units in each historical medical record of a head and neck surgery patient, and the collection time; the word units include independent word units and combined word units composed of multiple independent word units; comparing different combined word units containing the same independent word unit within all combined word units in the historical medical records of head and neck surgery patients, and combining the date difference between the collection time and retrieval time of each historical medical record containing each independent word unit, the isolation degree of each independent word unit is obtained; based on the independent word units in each historical medical record of a head and neck surgery patient and the retrieval content, and the isolation degree of each independent word unit within the combined word unit, the following is obtained: The process involves: retrieving the final word units; using a Boolean logic-based retrieval algorithm, obtaining the necessary medical records from the head and neck surgery patients' historical medical records based on the search content and the final word units in those records; prioritizing each medical record based on the distribution of final word units in the search content and the time interval between the collection and retrieval of each required medical record; if the Boolean logic-based retrieval algorithm fails to retrieve the required medical records; identifying important word units based on their distribution in the head and neck surgery patients' historical medical records; and finally, determining the medical records required by the doctor and their priorities based on the important word units in the search content.

[0006] Further, the specific steps for obtaining the retrieval time, the word units in the retrieval content, the word units in each historical medical record of a head and neck surgery patient, and the collection time are as follows: Obtain all historical medical records of head and neck surgery patients and the content entered by the doctor when searching for the historical medical records of head and neck surgery patients; record the content entered by the doctor when searching for the historical medical records of head and neck surgery patients as the retrieval content; obtain the collection time of each historical medical record of head and neck surgery patients, and record the time when the doctor searched for the historical medical records of head and neck surgery patients as the retrieval time; use... Word segmentation divides the search content into several word units, resulting in independent word units and combined word units within the search content; using Word segmentation divides the content of each historical medical record of a head and neck surgery patient into several word units, resulting in independent word units and combined word units in each historical medical record of a head and neck surgery patient.

[0007] Furthermore, the specific steps for obtaining the isolation degree of each independent word unit are as follows: Obtain the isolation degree of all combined word units within the historical medical records of head and neck surgery patients. The different combined word units where each independent word unit belongs Encoding; where, if a compound word unit contains the first... The number of independent word units is then the number of combined word units. The unit containing the individual word unit; the unit containing all the combined word units in the historical medical records of head and neck surgery patients. The different combined word units where each independent word unit belongs The codes are compared to obtain the first one. The similarity between the different subsequent adjacent combinations of the first independent word unit and the first... The similarity of the different preceding adjacent combinations of each independent word unit; according to the first The first independent word unit is located in the first The first adjacent combination and the first The similarity of the other preceding adjacent combinations of the individual word units, the first The first independent word unit is located in the first The next adjacent combination and the first The similarity of the other adjacent combinations to the first independent word unit is used to obtain the first... The first independent word unit belongs to its corresponding first... The membership degree of the first combined word unit; according to the first The first independent word unit belongs to its corresponding first... The membership degree of each combined word unit, the first The isolation degree of each independent word unit is obtained by calculating the date difference between the collection time and the retrieval time of the historical medical records in which each combined word unit belongs to the first independent word unit; the isolation degree of each independent word unit is obtained by calculating the date difference between the collection time and the retrieval time of the historical medical records in the first combined word unit. The first independent word unit belongs to its corresponding first... The specific steps for calculating the membership degree of the first combined word unit are as follows: [The text abruptly ends here, likely due to an incomplete sentence or a formatting error.] The first independent word unit is located in the first The first adjacent combination and the first The first independent word unit is located in the first The similarity of the nth preceding adjacent combinations is denoted as the i-th The first independent word unit is located in the first An initial representative of the first adjacent combinations; the first... The first independent word unit is located in the first The next adjacent combination and the first The first independent word unit is located in the first The similarity of the next adjacent combinations is denoted as the i-th. The first independent word unit is located in the first An initial representative of the next adjacent combinations; obtain the first... The first independent word unit belongs to its corresponding first... The specific formula for calculating the membership degree of a combined word unit is as follows: In the formula, Indicates the first The first independent word unit belongs to its corresponding first... The membership degree of each compound word unit. Indicates the first The first independent word unit is located in the first All initial representative sums of the first adjacent combinations, Indicates the first The first independent word unit is located in the first The sum of all initial representative values ​​of the next adjacent combinations.

[0008] Furthermore, the obtained first The similarity between the different subsequent adjacent combinations of the first independent word unit and the first... The specific steps for determining the similarity of different preceding adjacent combinations within each independent word unit are as follows: Within all combined word units in the head and neck surgery patient's medical history... The first independent word unit is located in the first In the word combination unit, remove the first one. All independent word units after the first independent word unit result in the first independent word unit. The first independent word unit is located in the first The first adjacent combination; within all combination word units in the medical history of head and neck surgery patients. The first independent word unit is located in the first In the word combination unit, remove the first one. All independent word units preceding the first independent word unit are obtained, resulting in the first independent word unit. The first independent word unit is located in the first The next adjacent combination is obtained; The first independent word unit is located in the first Each independent word unit within the next adjacent combination. Encoding and the The first independent word unit is located in the first Each independent word unit within each preceding adjacent combination Encoding; encoding each individual word unit The set of elements within the encoding is denoted as the element set of each independent word unit; the first... The first independent word unit is located in the first Each subsequent adjacent combination contains independent word units. Encoding and the The first independent word unit is located in the first Each subsequent adjacent combination contains independent word units. The codes are compared to obtain the first one. The first independent word unit is located in the first The next adjacent combination and the first The first independent word unit is located in the first The similarity of the next adjacent combinations after the first one; obtain the similarity of the first one. The first independent word unit is located in the first The next adjacent combination and the first The first independent word unit is located in the first The specific formula for calculating the similarity of adjacent combinations is as follows: In the formula, Indicates the first The first independent word unit is located in the first The next adjacent combination and the first The first independent word unit is located in the first The similarity of adjacent combinations after each iteration Indicates the first The first independent word unit is located in the first The number of independent word units in the next adjacent combination is the same as the number of words in the first combination. The first independent word unit is located in the first The minimum number of independent word units in adjacent combinations. Indicates the first The first independent word unit is located in the first The th next adjacent combination The set of elements of the first independent word unit and the first The th next adjacent combination The number of elements contained in the union of the sets of elements of individual word units. Indicates the first The first independent word unit is located in the first The th next adjacent combination The set of elements of the first independent word unit and the first The th next adjacent combination The number of elements contained in the intersection of the element sets of each independent word unit; the number of elements contained in the intersection of the element sets of each independent word unit; The first independent word unit is located in the first Independent word units within each preceding adjacent combination Encoding and the The first independent word unit is located in the first Independent word units within each preceding adjacent combination The codes are compared to obtain the first one. The first independent word unit is located in the first The first adjacent combination and the first The first independent word unit is located in the first The similarity of the nth preceding adjacent combinations; obtain the similarity of the nth... The first independent word unit is located in the first The first adjacent combination and the first The first independent word unit is located in the first The specific formula for calculating the similarity of the first two adjacent combinations is as follows: In the formula, Indicates the first The first independent word unit is located in the first The first adjacent combination and the first The first independent word unit is located in the first Similarity of the first adjacent combinations, Indicates the first The first independent word unit is located in the first The number of independent word units in the preceding adjacent combinations and the number of words in the first... The first independent word unit is located in the first The minimum number of independent word units in the preceding adjacent combinations. Indicates the first The first independent word unit is located in the first The last one in the preceding adjacent combinations The set of elements of the first independent word unit and the first The last one in the preceding adjacent combinations The number of elements contained in the union of the sets of elements of individual word units. Indicates the first The first independent word unit is located in the first The last one in the preceding adjacent combinations The set of elements of the first independent word unit and the first The last one in the preceding adjacent combinations The number of elements contained in the intersection of the element sets of each independent word unit.

[0009] Furthermore, the statement based on the first The first independent word unit belongs to its corresponding first... The membership degree of each combined word unit, the first The specific steps for obtaining the isolation degree of each independent term unit by comparing the date difference between the collection time and the retrieval time of the historical medical records of each combined term unit containing the independent term unit are as follows: The date within the collection time of the first historical medical record of the head and neck surgery patient is recorded as the first day of treatment for the head and neck surgery patient; the day after the first day of treatment for the head and neck surgery patient is recorded as the second day of treatment for the head and neck surgery patient; the day after the second day of treatment for the head and neck surgery patient is recorded as the third day of treatment for the head and neck surgery patient; and so on, obtaining each day of treatment for the head and neck surgery patient sequentially; obtaining the order value of the number of days of treatment for the head and neck surgery patient corresponding to the retrieval time; obtaining the... The specific formula for calculating the isolation degree of an independent word unit is as follows: In the formula, Indicates the first The isolation degree of each independent word unit This represents the ordinal value indicating the number of days of treatment for head and neck surgery patients corresponding to the search time. Represents an ordinal value. Represents an ordinal value. This indicates the first treatment of head and neck surgery patients. All medical histories of head and neck surgery patients within 3 days contain the first The number of combined word units of independent word units, Indicates the first The first independent term unit belongs to the treatment of head and neck surgery patients. The first unit of combined words in all the medical history of head and neck surgery patients within 3 days The first independent word unit is located in the first The membership degree of each compound word unit. It is an exponential function with the natural constant as its base. Represents the sigmoid function; where, if the th... The first independent word unit is located in the first The first compound word unit is for the treatment of head and neck surgery patients. The first of all historical medical records of head and neck surgery patients within 3 days in the compound word unit The first independent word unit is located in the first The first combined word unit; then the first The first independent term unit belongs to the treatment of head and neck surgery patients. The first unit of combined words in all the medical history of head and neck surgery patients within 3 days The first independent word unit is located in the first The membership degree of the first combined word unit is the first... The first independent word unit belongs to its corresponding first... The membership degree of each compound word unit.

[0010] Furthermore, the specific steps for obtaining the final word unit are as follows: preset an isolation threshold. If the isolation degree of all independent word units within a compound word unit is greater than the isolation degree threshold... If a combined word unit contains one or more independent word units, then the word unit is split into multiple independent word units; if the isolation degree of one or more independent word units within a combined word unit is less than or equal to the isolation degree threshold... If the combined word unit is not split, then the independent word unit in the search content, the independent word unit in each historical medical record of the head and neck surgery patient, the independent word unit split from the combined word unit, and the combined word unit that has not been split are all recorded as the final word unit.

[0011] Furthermore, the specific steps for obtaining the medical history required by the doctor from the medical history of a head and neck surgery patient are as follows: if all the final word units in a medical history of a head and neck surgery patient contain all the final word units in the search content, then the medical history is the medical history required by the doctor.

[0012] Furthermore, the specific calculation steps for obtaining the priority of each historical medical record needed by the doctor are as follows: If the first... If the final word unit is one of the final word units in the search content, then the first final word unit will be... When the final term unit first appears in the search results, it is located at the [number]th [position] in the search results. The sum of the number of categories of the final word units to the left of the first final word unit plus 1 is denoted as the first final word unit. The order value of the final word unit in the search results; add 1 to the number of categories of the final word units in the search results and then subtract the order value of the final word unit. The result after the order value of the final word unit in the search content is denoted as the first... The importance of each final word unit; if the first If the first final word unit is not a final word unit in the search content, then the second final word unit is not a final word unit in the search content. The importance of the final word unit is 0; to obtain the first word unit needed by the doctor The specific formula for calculating the priority of each historical medical record is as follows: In the formula, This indicates the doctor's need for the first Priority of historical medical records This indicates the search time and the number of times the doctor needs to search. The time interval between the collection of historical medical records Indicates the number of types of the final word unit. Indicates the first The final word unit is the one needed by the doctor. The number of times it appears in a historical medical record Indicates the first The importance of each final word unit It is an exponential function with the natural constant as its base. This represents the weight normalization function.

[0013] Furthermore, the specific steps for obtaining important word units from the final word units are as follows: If the first... The final term unit is for head and neck surgery patients. A final word unit in a historical medical record, then the first The final term unit in head and neck surgery patients When it first appeared in a historical medical record, it was the first time a head and neck surgery patient... In the historical medical records, located at number The sum of the number of categories of the final word units to the left of the first final word unit plus 1 is denoted as the first final word unit. The final term unit in head and neck surgery patients The order value in the historical medical records; the first order value of head and neck surgery patients. The number of final word units in each historical medical record is increased by 1, then the number of words in the record is decreased. The final term unit in head and neck surgery patients The result after the order value in the historical medical records is the first one. The historical significance of the final word unit; obtaining the first The specific formula for calculating the final importance of each final word unit is as follows:

[0014] ;

[0015] In the formula, Indicates the first The final term unit in the treatment of head and neck surgery patients The importance of the sky Indicates the first The final importance of each final word unit, This indicates the first treatment of head and neck surgery patients. The number of final word units in all historical medical records of head and neck surgery patients within a day. Indicates the first The final term unit in the treatment of head and neck surgery patients The number of times a head and neck surgery patient appears in all their medical history records within a day. This indicates the first stage of treatment for head and neck surgery patients. The first of all medical histories of head and neck surgery patients within 3 days The final term unit in the treatment of head and neck surgery patients The number of times a head and neck surgery patient appears in all their medical history records within a day. This indicates the first stage of treatment for head and neck surgery patients. The first of all medical histories of head and neck surgery patients within 3 days The final term unit in the treatment of head and neck surgery patients The number of times a head and neck surgery patient appears in all their medical history records within a day. This represents the ordinal value indicating the number of days of treatment for head and neck surgery patients corresponding to the search time. Indicates the first The mean of all historical importance of each final word unit, The brackets represent Iverson's brackets; based on the final importance of each final word unit, the final word unit is divided into two clusters using the Otsu threshold method; the cluster with the largest mean final importance of the final word units contained therein is designated as the important cluster; the other cluster is designated as the non-important cluster; and the final word units within the important cluster are designated as important word units.

[0016] Furthermore, the specific steps for obtaining the medical records needed by the doctor and their priorities based on important terms in the search content are as follows: If the first patient in a head and neck surgery... Within all final word units of the historical medical records, including all important word units of the search content, the first word unit of the head and neck surgery patient... Each historical medical record is recorded as a record needed by the doctor. Based on the position of each final term unit in the search content, its quantity in the historical medical records needed by the doctor, and the time interval between the collection time and the retrieval time for each historical medical record needed by the doctor, the record is determined by the number of historical medical records needed by the doctor. The method for obtaining the priority of each historical medical record is to obtain the priority of each historical medical record needed by the doctor.

[0017] The intelligent management method for head and neck surgery patient medical record data provided by this invention has the following beneficial effects: This invention uses a Boolean logic-based retrieval algorithm to obtain the historical medical records needed by doctors from all of the patient's historical medical records to assist doctors in treating patients. Based on the characteristics of doctors writing medical records and retrieving required medical records, this invention prioritizes key content, with subsequent inputs supplementing the prioritized key content. Furthermore, considering the strong time characteristics of head and neck surgery diagnosis and treatment, the method prioritizes each retrieved historical medical record based on the position of each final word unit in the input content during retrieval, the frequency of each final word unit in the patient's historical medical records, and the collection time of each patient's historical medical record. This allows doctors to obtain more relevant historical medical records more quickly when treating patients based on the retrieved records, improving the efficiency of doctor treatment. Currently, when using a Boolean logic-based retrieval algorithm to retrieve the historical medical records needed by doctors from all of the patient's historical medical records, it is necessary to use... Word segmentation is performed on the search content and historical medical records, dividing them into independent word units and combined word units. This is because the currently used... The word segmentation did not take into account the medical context and the patient's physical condition, resulting in... After word segmentation, some combined word units can be further segmented. Therefore, this invention, based on the characteristic that if a combined word unit containing an independent word unit cannot be further segmented, then the distribution of independent word units within different combined word units containing that independent word unit is relatively similar, determines whether the combined word unit containing each independent word unit can be further segmented. This lays the groundwork for improving the retrieval algorithm when Boolean logic-based retrieval algorithms cannot retrieve the doctor's required medical records from the patient's historical medical records. Furthermore, to address the issue that when doctors input a large amount of retrieval content, Boolean logic-based retrieval algorithms may not be able to retrieve the doctor's required medical records from the patient's historical medical records, this invention aims to address the problem that when doctors input a large amount of retrieval content, Boolean logic-based retrieval algorithms may not be able to retrieve the doctor's required medical records from the patient's historical medical records. To address the issue of obtaining important medical records, this invention is based on the characteristic that if a final term is important, it will appear multiple times in the patient's medical records. According to the distribution of each final term in the patient's medical records, important terms are obtained from the final terms in the patient's search content. Then, when using a Boolean logic-based retrieval algorithm to obtain the medical records needed by the doctor from the patient's medical records, if all the final terms in a patient's medical records contain all the important terms in the patient's search content, then that medical record is recorded as the patient's medical records. This maximizes retrieval accuracy while improving retrieval coverage. Attached Figure Description

[0018] To more clearly illustrate the embodiments and design schemes of the present invention, the accompanying drawings required for this embodiment will be briefly described below. The drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating an intelligent management method for head and neck surgery patient medical record data according to an embodiment of the present invention. Detailed Implementation

[0020] To enable those skilled in the art to better understand and implement the technical solutions of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and should not be construed as limiting the scope of protection of the present invention.

[0021] Example 1: This invention provides an intelligent management method for head and neck surgery patient medical record data, specifically as follows: Figure 1 As shown, it includes: Step S001: Obtain the retrieval time, word units in the retrieval content, word units in each historical medical record of head and neck surgery patients and the collection time.

[0022] Specifically, all historical medical records of head and neck surgery patients are retrieved, along with the content entered by doctors when searching these records. The content entered by doctors when searching the historical medical records of head and neck surgery patients is recorded as the search content. The historical medical records of head and neck surgery patients are textual descriptions of the patient's condition, treatment plans, and other disease-related information. Furthermore, in this embodiment, all head and neck surgery patients are the same individual patient.

[0023] Furthermore, the time of collection for each historical medical record of a head and neck surgery patient is obtained. The time when the doctor retrieves the historical medical records of a head and neck surgery patient is recorded as the retrieval time.

[0024] Furthermore, using Word segmentation divides the search content into several word units, thus obtaining the word units within the search content. Using... Word segmentation divides the content of each historical medical record of a head and neck surgery patient into several word units, resulting in the word units within each historical medical record of a head and neck surgery patient. Among these, the use of... Word segmentation, which divides a text into several word units, is a well-known existing technology, and will not be described in detail in this embodiment.

[0025] Thus, we obtained the retrieval time, the word units in the retrieval content, and the collection time and word units in each historical medical record of head and neck surgery patients.

[0026] Step S002: Compare different combined word units containing the same independent word unit within all combined word units in the historical medical records of head and neck surgery patients. Combine the date difference between the collection time and the retrieval time of the historical medical records containing each independent word unit to obtain the isolation degree of each independent word unit. Based on the independent word units in each historical medical record of head and neck surgery patients and the retrieval content, as well as the isolation degree of each independent word unit within the combined word unit, the final word unit is obtained.

[0027] It should be noted that when retrieving the necessary medical records from all of the patient's historical medical records using a Boolean model-based retrieval algorithm, if all the word units in the retrieval content are word units from a single historical medical record of the patient, then that historical medical record is the one the doctor needs. In other words, dividing the retrieval content and the patient's historical medical records into several word units is a crucial preprocessing step when retrieving the necessary historical medical records from all of the patient's historical medical records.

[0028] It should be further explained that the use When word segmentation divides a text into several word units, these word units can be categorized into independent word units that cannot be further subdivided using segmentation tools, and combined word units composed of an indefinite number of independent word units. For example, the combined word unit "nasopharyngeal carcinoma" is composed of the independent word units "nasopharynx," "cell," and "carcinoma." Therefore, when using a retrieval algorithm to obtain the necessary medical records from a patient's historical medical history, it's crucial to first determine whether each combined word unit can be further subdivided into several independent word units, performing further segmentation on some combined word units before conducting the retrieval.

[0029] It's important to further clarify that when determining whether a compound word unit can be further divided into multiple independent word units, the likelihood of it being divided into multiple independent word units is low if it appears multiple times simultaneously in a patient's medical history. For example, in the treatment of cancer patients, the probability of classifying the compound word unit "cancer cells" into the independent word units "cancer" and "cells" is low. Therefore, the isolation degree of each independent word unit is obtained by comparing the different compound word units to which it belongs. Based on the isolation degree of each independent word unit, the compound word unit is further subdivided.

[0030] It should be further explained that when an independent word unit cannot appear independently in a patient's medical history, the different word units containing that independent word unit are relatively similar. That is, an independent word unit in a combined word unit may appear multiple times in other combined word units along with several independent word units before or after it. Therefore, each independent word unit in each combined word unit is combined with all independent word units to its left to form a preceding adjacent combination of that independent word unit, and each independent word unit in each combined word unit is combined with all independent word units to its right to form a following adjacent combination of that independent word unit. For example, assuming there is a combined word unit ABCDEFG, where A, B, C, D, E, F, and G are each an independent word unit, then the preceding adjacent combination of independent word unit B is AB, and the following adjacent combination is BCDEFG. Then, a similarity judgment is performed on all preceding adjacent combinations and all following adjacent combinations of each independent word unit to obtain the isolation degree of each independent word unit.

[0031] It should be further noted that when judging the similarity between each preceding adjacent combination of each independent word unit and other preceding adjacent combinations of that independent word unit, the closer the similarity of the independent word units in different preceding adjacent combinations of that independent word unit, the stronger the similarity between the two preceding adjacent combinations of that independent word unit. Furthermore, when the similarity between two independent word units... The more common elements in the encoding, the closer the meanings of the two independent word units are. Therefore, we obtain the first adjacent combination of each independent word unit. Encoding, based on the different preceding adjacent combinations of each independent word unit The differences in encoding are used to obtain the similarity between each preceding adjacent combination and other preceding adjacent combinations for each independent word unit.

[0032] It should be further noted that the number of independent word units contained in different preceding adjacent combinations of each independent word unit may vary. Therefore, the different preceding adjacent combinations of each independent word unit... When comparing the encodings to obtain the similarity of different preceding adjacent combinations for each independent word unit, it is necessary to separate the encodings of two different preceding adjacent combinations. Alignment is performed on the encoding. That is, the first independent word unit B is calculated. The first adjacent combination and the first When calculating the similarity of the first adjacent combinations, it is necessary to consider the first independent word unit B. The last one in the preceding adjacent combinations Each independent word unit Encoding and the The last one in the preceding adjacent combinations Each independent word unit The encodings are compared to obtain the similarity between two preceding adjacent combinations. Specifically, in the combined word unit QWABCD and the combined word unit DGBAF, the preceding adjacent combinations of independent word unit B are QWAB and DGB, respectively. Therefore, when calculating the similarity between the preceding adjacent combinations QWAB and DGB of independent word unit B, the similarity between independent word unit A and independent word unit G is compared. Differences in encoding: Comparison of independent word unit W and independent word unit D Differences in encoding.

[0033] It should be further noted that, in the analysis of different independent word units... When performing similarity comparisons in encoding, when two independent word units... The more identical content exists in the codes, the closer the meanings of the two independent word units are. Therefore, when comparing the similarity of the codes of two independent word units, the similarity should be based on the... The similarity between two independent word units is obtained by calculating the number of elements in the intersection and union of the encoded elements, and then the similarity between the two preceding adjacent combinations of each independent word unit. Using the same calculation method, the similarity is further calculated based on the number of independent word units in different following adjacent combinations of each independent word unit. By analyzing the differences in encoding, the similarity of different subsequent adjacent combinations of each independent word unit is obtained. Based on the similarity of each preceding adjacent combination of each independent word unit with other preceding adjacent combinations, and the similarity of each subsequent adjacent combination of each independent word unit with other subsequent adjacent combinations, the membership degree of each independent word unit in each combined word unit is obtained.

[0034] Further, it should be noted that since each combined word unit where each independent word unit is located may appear in different historical medical records of the patient, and the collection times of each historical medical record of the patient are different. When obtaining the isolation degree of each independent word unit according to the membership degree of each independent word unit in each combined word unit, different weights need to be assigned to the membership degree of the independent word unit in each combined word unit, and then the isolation degree of each independent word unit is obtained.

[0035] Specifically, in the th combined word unit where the th independent word unit is located among all the combined word units in the historical medical records of the patients in the department of head and neck surgery, all the independent word units after removing the th independent word unit are removed to obtain the th previous adjacent combination where the

[0036] th independent word unit is located. th combined word unit where the th independent word unit is located among all the combined word units in the historical medical records of the patients in the department of head and neck surgery, all the independent word units before removing the th independent word unit are removed to obtain the th subsequent adjacent combination where the th independent word unit is located. Among them, if a combined word unit contains the th independent word unit, then this combined word unit is the combined word unit where the

[0037] th independent word unit is located. th subsequent adjacent combination where the th independent word unit is located, and obtain the th previous adjacent combination where the th independent word unit is located. Since the coding of each independent word unit can be regarded as composed of several elements. The set composed of the elements in the coding of each independent word unit is denoted as the element set of each independent word unit. For example, the coding of the Chinese character "cancer" is 80DE, then the coding of the Chinese character "cancer" is composed of the element 8, the element 0, the element D, and the element E. The element set of the Chinese character "cancer" includes: the element 8, the element 0, the element D, and the element E.

[0038] Further, obtain the th subsequent adjacent combination where the The first independent word unit is located in the first The specific formula for calculating the similarity of adjacent combinations is as follows: In the formula, Indicates the first The first independent word unit is located in the first The next adjacent combination and the first The first independent word unit is located in the first The similarity of adjacent combinations after each iteration Indicates the first The first independent word unit is located in the first The number of independent word units in the next adjacent combination is the same as the number of words in the first combination. The first independent word unit is located in the first The minimum number of independent word units in adjacent combinations. Indicates the first The first independent word unit is located in the first The th next adjacent combination The set of elements of the first independent word unit and the first The th next adjacent combination The number of elements contained in the union of the sets of elements of individual word units. Indicates the first The first independent word unit is located in the first The th next adjacent combination The set of elements of the first independent word unit and the first The th next adjacent combination The number of elements contained in the intersection of the element sets of each independent word unit.

[0039] It should be noted that, The larger the value, the more significant the [value]. The first independent word unit is located in the first The th next adjacent combination Each independent word unit Encoding and the The first independent word unit is located in the first The th next adjacent combination Each independent word unit The more identical elements in the encoding, the more it illustrates the point. The first independent word unit is located in the first The next adjacent combination and the first The th next adjacent combination The smaller the difference between individual word units; The larger the value, the more significant the [value]. The first independent word unit is located in the first The next adjacent combination and the first The first independent word unit is located in the first The stronger the similarity between adjacent combinations.

[0040] Furthermore, obtain the first The first independent word unit is located in the first The first adjacent combination and the first The first independent word unit is located in the first The specific formula for calculating the similarity of the first two adjacent combinations is as follows: In the formula, Indicates the first The first independent word unit is located in the first The first adjacent combination and the first The first independent word unit is located in the first Similarity of the first adjacent combinations, Indicates the first The first independent word unit is located in the first The number of independent word units in the preceding adjacent combinations and the number of words in the first... The first independent word unit is located in the first The minimum number of independent word units in the preceding adjacent combinations. Indicates the first The first independent word unit is located in the first The last one in the preceding adjacent combinations The set of elements of the first independent word unit and the first The last one in the preceding adjacent combinations The number of elements contained in the union of the sets of elements of individual word units. Indicates the first The first independent word unit is located in the first The last one in the preceding adjacent combinations The set of elements of the first independent word unit and the first The last one in the preceding adjacent combinations The number of elements contained in the intersection of the element sets of each independent word unit.

[0041] It should be noted that, The larger the value, the more significant the [value]. The first independent word unit is located in the first The first adjacent combination and the first The first independent word unit is located in the first The last one in the preceding adjacent combinations Each independent word unit The more identical elements there are in the encoding, the more it illustrates the point. The first independent word unit is located in the first The first adjacent combination and the first The first of the preceding adjacent combinations The individual word units are quite similar; The larger the value, the more significant the [value]. The first independent word unit is located in the first The first adjacent combination and the first The first independent word unit is located in the first The stronger the similarity between the previous adjacent combinations.

[0042] Furthermore, the date within the collection period of the first historical medical record of the head and neck surgery patient is recorded as the first day of treatment for the head and neck surgery patient; the day after the first day of treatment for the head and neck surgery patient is recorded as the second day of treatment for the head and neck surgery patient; the day after the second day of treatment for the head and neck surgery patient is recorded as the third day of treatment for the head and neck surgery patient; and so on, each day of treatment for the head and neck surgery patient is obtained step by step.

[0043] Furthermore, the order value of the number of days of treatment for head and neck surgery patients corresponding to the retrieval time is obtained. That is, if the date of the collection time of the first historical medical record of a head and neck surgery patient is October 15, 2021, and the date when the doctor conducts the retrieval is October 25, 2021, then the order value of the number of days of treatment for head and neck surgery patients corresponding to the retrieval time is 11.

[0044] Furthermore, the first The first independent word unit is located in the first The first adjacent combination and the first The first independent word unit is located in the first The similarity of the nth preceding adjacent combinations is denoted as the i-th The first independent word unit is located in the first An initial representative of the first adjacent combinations. The first... The first independent word unit is located in the first The next adjacent combination and the first The first independent word unit is located in the first The similarity of the next adjacent combinations is denoted as the i-th. The first independent word unit is located in the first An initial representative of the next adjacent combinations.

[0045] Furthermore, obtain the first The first independent word unit belongs to its corresponding first... The specific formula for calculating the membership degree of a combined word unit is as follows: In the formula, Indicates the first The first independent word unit belongs to its corresponding first... The membership degree of each compound word unit. Indicates the first The first independent word unit is located in the first All initial representative sums of the first adjacent combinations, Indicates the first The first independent word unit is located in the first The sum of all initial representative values ​​of the next adjacent combinations.

[0046] It should be noted that, The larger the value, the more significant the [value]. The first independent word unit is located in the first The greater the sum of the similarities between the nth preceding neighbor combination and all its preceding neighbor combinations, the higher the similarity among different word units located at the th position. The distribution of independent word units preceding the first independent word unit exhibits a strong regularity. If a compound word unit contains the first independent word unit... When there are individual word units, it is more likely that the combined word unit cannot be further subdivided. The larger the value, the more significant the [value]. The first independent word unit is located in the first The greater the sum of the similarities between the i-th subsequent adjacent combination and all its subsequent adjacent combinations, the higher the similarity among different word units located at the i-th position. The distribution of independent word units after the first independent word unit shows a strong regularity. If a compound word unit contains the first independent word unit... When there are individual word units, it is more likely that the combined word unit cannot be further subdivided.

[0047] Furthermore, obtain the first The specific formula for calculating the isolation degree of an independent word unit is as follows: In the formula, Indicates the first The isolation degree of each independent word unit This represents the ordinal value indicating the number of days of treatment for head and neck surgery patients corresponding to the search time. Represents an ordinal value. Represents an ordinal value. This indicates the first treatment of head and neck surgery patients. All medical histories of head and neck surgery patients within 3 days contain the first The number of combined word units of independent word units, Indicates the first The first independent term unit belongs to the treatment of head and neck surgery patients. The first unit of combined words in all the medical history of head and neck surgery patients within 3 days The first independent word unit is located in the first The membership degree of each compound word unit. As an exponential function with the natural constant as its base, this embodiment uses it to represent an inverse proportional relationship; This represents the sigmoid function, used in this embodiment for normalization. That is, assuming the... The first independent word unit is located in the first The first combined word unit, for the treatment of head and neck surgery patients. The first of all historical medical records of head and neck surgery patients within 3 days in the compound word unit The first independent word unit is located in the first The first combined word unit; then the first The first independent term unit belongs to the treatment of head and neck surgery patients. The first unit of combined words in all the medical history of head and neck surgery patients within 3 days The first independent word unit is located in the first The membership degree of the first combined word unit is the first... The first independent word unit belongs to its corresponding first... The membership degree of each compound word unit.

[0048] It should be noted that the closer the date a historical medical record was collected is to the date the doctor conducted the search, the better. The larger the value, the better. The smaller the value, the better. The larger the value, the more... right The greater the impact; The larger the value, the more significant the [value]. The distribution of independent word units varies considerably within different combined word units, further illustrating that the distribution of the first independent word unit within the first independent word unit... There is a high probability that the combined word units containing individual word units will be further subdivided. The larger the value, the more significant the [value]. The greater the likelihood that an individual word unit can appear as an independent word unit in a patient's medical history.

[0049] Furthermore, a preset isolation threshold is set. If the isolation degree of all independent word units within a compound word unit is greater than the isolation degree threshold... If a combined word unit contains one or more independent word units, then the isolation degree of that combined word unit is further broken down into multiple independent word units. If the word combination is not split, then the word combination unit will not be split. The isolation threshold preset in this embodiment... This example is used to illustrate the concept; other values ​​can be set in other implementations.

[0050] Furthermore, the independent word units in the search content, the independent word units in each historical medical record of head and neck surgery patients, the independent word units split from the combined word units, and the combined word units that have not been split are all recorded as the final word units.

[0051] Thus, the final word unit is obtained.

[0052] Step S003: Using a Boolean logic-based retrieval algorithm, based on the retrieval content and the final word units in the historical medical records of head and neck surgery patients, obtain the historical medical records needed by the doctor from the historical medical records of head and neck surgery patients; based on the distribution of the final word units in the retrieval content and the historical medical records needed by the doctor, as well as the time interval between the collection time and the retrieval time of each historical medical record needed by the doctor, obtain the priority of each historical medical record needed by the doctor.

[0053] It should be noted that when using a Boolean logic-based retrieval algorithm to obtain the historical medical records required by the doctor based on the doctor's input, only a limited number of historical medical records can be obtained. It is not possible to prioritize all the historical medical records required by the doctor. Therefore, this invention prioritizes the retrieved medical records, specifically the historical medical records required by the doctor.

[0054] It's important to further clarify that, due to the highly specialized nature of head and neck surgery, doctors tend to prioritize key information or diagnostic dimensions when inputting their searches, with subsequent input serving as supplementary information. In other words, when searching for historical medical records of head and neck surgery patients, the order in which words appear in the input reflects the doctor's emphasis on the desired results. Therefore, the retrieved medical records are sorted based on the distribution of the final words in the search query.

[0055] It should be further noted that, since the diagnosis and treatment process of head and neck surgical diseases has a strong time characteristic, the retrieved medical records are prioritized according to the collection time of each record.

[0056] Specifically, when retrieving the required historical medical records from all historical medical records of head and neck surgery patients using a Boolean logic-based retrieval algorithm, if all the final word units in a historical medical record of a head and neck surgery patient contain all the final word units of the search content, then that historical medical record is the one the doctor needs. The use of a Boolean logic-based retrieval algorithm to retrieve the required data from multiple datasets is a well-known existing technique and will not be described in detail in this embodiment.

[0057] Furthermore, if the first If the final word unit is one of the final word units in the search content, then the first final word unit will be... When the final term unit first appears in the search results, it is located at the [number]th [position] in the search results. The sum of the number of categories of the final word units to the left of the first final word unit plus 1 is denoted as the first final word unit. The order value of the final word unit in the search results. Increment the number of final word unit categories in the search results by 1, then subtract the order value of the final word unit. The result after the order value of the final word unit in the search content is denoted as the first... The importance of each final word unit. That is, if each letter is considered as a final word unit, and QWWERT is used as the search content, then the order values ​​of the letters Q, W, E, R, and T are 1, 2, 3, 4, and 5, respectively, and their importance values ​​are 5, 4, 3, 5, and 1.

[0058] Furthermore, if the first If the first final word unit is not a final word unit in the search content, then the second final word unit is not a final word unit in the search content. The importance of each final word unit is 0.

[0059] Furthermore, obtaining the first [item / condition] needed by doctors The specific formula for calculating the priority of each historical medical record is as follows: In the formula, This indicates the doctor's need for the first Priority of historical medical records This indicates the search time and the number of times the doctor needs to search. The time interval between the collection of historical medical records Indicates the number of types of the final word unit. Indicates the first The final word unit is the one needed by the doctor. The number of times it appears in a historical medical record Indicates the first The importance of each final word unit As an exponential function with the natural constant as its base, this embodiment uses it to represent an inverse proportional relationship; For the doctor's needs Priority of historical medical records; This represents the weight normalization function, whose input is the priority of all historical medical records required by the doctor.

[0060] It should be noted that, A smaller value indicates that the doctor needs the first... The timing of the first historical medical record was close to the doctor's search time, making it easier for the doctor to find the first... Historical medical records should have a higher priority at this time. The value is relatively large; A larger value indicates that the most important final term in the doctor's search is the one that the doctor needs most. This has appeared multiple times in historical medical records; at this point, the doctor needs to... The priority of the first historical medical record is also relatively high; the softmax function is used to ensure that the sum of the priorities of all historical medical records needed by the doctor is 1; and when the doctor needs the first one... The higher the priority of a historical medical record, the more likely the doctor needs it. The more historical medical records a doctor has, the more valuable they are for the doctor's reference.

[0061] This allows us to prioritize each historical medical record that the doctor needs.

[0062] Step S004: If the Boolean logic-based retrieval algorithm cannot obtain the historical medical records needed by the doctor, important word units are obtained from the final word units based on the distribution of the final word units in the historical medical records of head and neck surgery patients. Based on the important word units in the retrieval content, the medical records needed by the doctor and their priorities are obtained.

[0063] It's important to note that when using a Boolean logic-based retrieval algorithm to retrieve the necessary medical records from a patient's entire medical history, the record can only be retrieved if all final units within the search terms contain all the final units of the search content. If a doctor inputs too much search content into the Boolean logic-based algorithm to obtain more accurate records, it may fail to retrieve any records. In other words, the robustness of Boolean logic-based retrieval algorithms for medical records is relatively low. Therefore, if the existing Boolean logic-based retrieval algorithm fails to retrieve any records, the relationship between some final units in the doctor's search content should be changed... Relationship transformed This relationship allows for maximizing search accuracy while improving search coverage. Specifically, if the first element in the search content... The relationship between the final word units is as follows: Transform into In such cases, the final word unit in the medical records retrieved using the retrieval algorithm may not contain the first word in the search content. The final word unit.

[0064] It should be further explained that the relationship between some final word units in the search results is... Transform into At this time, it is necessary to first determine which final word units' relationships will be changed by... Transform into In the medical history of head and neck surgery patients, if a final term consistently appears alongside other final terms, it indicates a strong connection between that term and the others. Therefore, the final importance of each final term is determined based on its frequency of occurrence across all patient medical history records for each day. Based on this final importance, it is then determined which final term matching relationships will be adjusted. Transform into relation.

[0065] It should be further noted that, due to the highly specialized nature of head and neck surgery, doctors tend to prioritize key information when entering data into patient records, with subsequent entries supplementing this key information. Therefore, the final importance of each final term is calculated based on its position within the patient's medical record.

[0066] It should be further clarified that when calculating the final importance of each final word unit based on its frequency of occurrence across all of the patient's medical records for each day, a higher frequency is indicated when the frequency of a final word unit across all of the patient's medical records for that day is greater than the average frequency of all final word units appearing in those records for that day. Therefore, the final importance of each final word unit is calculated based on the difference between its frequency across all of the patient's medical records for that day and the average frequency of final word units appearing in those records for that day across all of the patient's medical records for that day.

[0067] Specifically, if the first The final term unit is for head and neck surgery patients. A final word unit in a historical medical record, then the first The final term unit in head and neck surgery patients When it first appeared in a historical medical record, it was the first time a head and neck surgery patient... In the historical medical records, located at number The sum of the number of categories of the final word units to the left of the first final word unit plus 1 is denoted as the first final word unit. The final term unit in head and neck surgery patients The order value in the historical medical records. The first [number] [item] of the head and neck surgery patient. The number of final word units in each historical medical record is increased by 1, then the number of words in the record is decreased. The final term unit in head and neck surgery patients The result after the order value in the historical medical records is denoted as the first. The historical importance of each final word unit. That is, if each letter is regarded as a final word unit, and WQWERT is regarded as the content in a historical medical record, then the order values ​​of the letters W, Q, E, R, T are 1, 2, 3, 4, 5 respectively, and their historical importance is 5, 4, 3, 2, 1 respectively.

[0068] Furthermore, obtain the first The specific formula for calculating the final importance of each final word unit is as follows:

[0069] ;

[0070] In the formula, Indicates the first The final term unit in the treatment of head and neck surgery patients The importance of the sky Indicates the first The final importance of each final word unit, This indicates the first treatment of head and neck surgery patients. The number of final word units in all historical medical records of head and neck surgery patients within a day. Indicates the first The final term unit in the treatment of head and neck surgery patients The number of times a head and neck surgery patient appears in all their medical history records within a day. This indicates the first stage of treatment for head and neck surgery patients. The first of all medical histories of head and neck surgery patients within 3 days The final term unit in the treatment of head and neck surgery patients The number of times a head and neck surgery patient appears in all their medical history records within a day. This indicates the first stage of treatment for head and neck surgery patients. The first of all medical histories of head and neck surgery patients within 3 days The final term unit in the treatment of head and neck surgery patients The number of times a head and neck surgery patient appears in all their medical history records within a day. This represents the ordinal value indicating the number of days of treatment for head and neck surgery patients corresponding to the search time. Indicates the first The mean of all historical importance of each final word unit, The brackets represent Iverson's condition, which is true when the condition within the brackets is true. When the condition in parentheses is not true, And the first The final word unit and the first Each final word unit is a different final word unit.

[0071] It should be noted that, The quantification is the first The final term unit in the treatment of head and neck surgery patients Frequency of occurrence in all historical medical records within the day The quantification refers to the treatment of head and neck surgery patients. The final word unit appearing in all historical medical records within a day, in the head and neck surgery patient's first... Frequency of occurrence in historical medical records within a day; when When, explain the first The final term unit in the treatment of head and neck surgery patients It appears frequently in the patient's medical history within the past day, at this time ;when hour, ; The larger the value, the more significant the [value]. The fact that the final word unit appears relatively early in the patient's medical history further illustrates that the... The final term unit is quite important in describing the condition, that is, the first... The final word unit is quite important; The higher the value, the better the outcome of the treatment of head and neck surgery patients over multiple days. The final word unit is quite important in the patient's medical history.

[0072] Thus, the importance of each final word unit is determined.

[0073] Furthermore, based on the final importance of each final word unit, the Otsu thresholding method is used to divide the final word units into two clusters. The cluster with the highest mean final importance of the final word units is designated as the important cluster. The other cluster is designated as the non-important cluster.

[0074] Furthermore, the final word unit within the important cluster is denoted as the important word unit.

[0075] Furthermore, when retrieving the historical medical records needed by doctors using a Boolean logic-based retrieval algorithm, if the first... Within all final word units of the historical medical records, including all important word units of the search content, the first word unit of the head and neck surgery patient... Each historical medical record is recorded as a historical medical record needed by the doctor.

[0076] At this point, all the historical medical records the doctor needed were obtained.

[0077] Furthermore, based on the position of each final word unit in the search content and the number of historical medical records needed by the doctor, as well as the time interval between the collection time and the retrieval time of each historical medical record needed by the doctor, the priority of each historical medical record needed by the doctor is obtained using the method in step S003.

[0078] This concludes the embodiment.

Claims

1. An intelligent management method for head and neck surgery patient medical record data, characterized in that, include: Obtain the retrieval time, the word units in the retrieval content, and the word units and collection time in each historical medical record of head and neck surgery patients; The term units include independent term units and combined term units composed of multiple independent term units. The isolation degree of each independent term unit is obtained by comparing different combined term units containing the same independent term unit within all combined term units in the historical medical records of head and neck surgery patients, and by considering the date difference between the collection time and retrieval time of the historical medical records containing each independent term unit. Based on the independent term units in each historical medical record of head and neck surgery patients and the retrieval content, as well as the isolation degree of each independent term unit within a combined term unit, the final term unit is obtained. Using a Boolean logic-based retrieval algorithm, based on the retrieval content and the final term units in the historical medical records of head and neck surgery patients, the final term unit is obtained from the head and neck surgery patients' historical medical records. The process involves obtaining the necessary historical medical records from the patient's medical history; determining the priority of each necessary historical medical record based on the distribution of final word units in the search content and the historical medical records required by the doctor, as well as the time interval between the collection and retrieval times of each necessary historical medical record; if a Boolean logic-based retrieval algorithm is used, the necessary historical medical records cannot be obtained; based on the distribution of final word units in the historical medical records of head and neck surgery patients, important word units are obtained from the final word units; based on the important word units in the search content, the necessary medical records and their priorities are obtained; the specific steps for obtaining the isolation degree of each independent word unit are as follows: obtaining the first word unit within all combined word units in the historical medical records of head and neck surgery patients. The different combined word units where each independent word unit belongs Encoding; where, if a compound word unit contains the first... The number of independent word units is then the number of combined word units. The unit containing the individual word unit; the unit containing all the combined word units in the historical medical records of head and neck surgery patients. The different combined word units where each independent word unit belongs The codes are compared to obtain the first one. The similarity between the different subsequent adjacent combinations of the first independent word unit and the first... The similarity of the different preceding adjacent combinations of each independent word unit; according to the first The first independent word unit is located in the first The first adjacent combination and the first The similarity of the other preceding adjacent combinations of the individual word units, the first The first independent word unit is located in the first The next adjacent combination and the first The similarity of the other adjacent combinations to the first independent word unit is used to obtain the first... The first independent word unit belongs to its corresponding first... The membership degree of the first combined word unit; according to the first The first independent word unit belongs to its corresponding first... The membership degree of each combined word unit, the first The isolation degree of each independent word unit is obtained by comparing the date difference between the collection time and the retrieval time of the historical medical records of each combined word unit containing the independent word unit.

2. The intelligent management method for head and neck surgery patient medical record data according to claim 1, characterized in that, The specific steps for obtaining the retrieval time, the word units in the retrieval content, the word units in each historical medical record of a head and neck surgery patient, and the collection time are as follows: Obtain all historical medical records of head and neck surgery patients and the content entered by the doctor when searching for these records; record the content entered by the doctor when searching for these records as the retrieval content; obtain the collection time of each historical medical record of a head and neck surgery patient, and record the time when the doctor searched for these records as the retrieval time; use... Word segmentation divides the search content into several word units, resulting in independent word units and combined word units within the search content; using Word segmentation divides the content of each historical medical record of a head and neck surgery patient into several word units, resulting in independent word units and combined word units in each historical medical record of a head and neck surgery patient.

3. The intelligent management method for head and neck surgery patient medical record data according to claim 1, characterized in that, Get the The first independent word unit belongs to its corresponding first... The specific steps for calculating the membership degree of the first combined word unit are as follows: [The text abruptly ends here, likely due to an incomplete sentence or a formatting error.] The first independent word unit is located in the first The first adjacent combination and the first The first independent word unit is located in the first The similarity of the nth preceding adjacent combinations is denoted as the i-th The first independent word unit is located in the first An initial representative of the preceding adjacent combinations; The first The first independent word unit is located in the first The next adjacent combination and the first The first independent word unit is located in the first The similarity of the next adjacent combinations is denoted as the i-th. The first independent word unit is located in the first An initial representative of the next adjacent combinations; Get the The first independent word unit belongs to its corresponding first... The specific formula for calculating the membership degree of a combined word unit is as follows: In the formula, Indicates the first The first independent word unit belongs to its corresponding first... The membership degree of each compound word unit. Indicates the first The first independent word unit is located in the first All initial representative sums of the first adjacent combinations, Indicates the first The first independent word unit is located in the first The sum of all initial representative values ​​of the next adjacent combinations.

4. The intelligent management method for head and neck surgery patient medical record data according to claim 3, characterized in that, The obtained number The similarity between the different subsequent adjacent combinations of the first independent word unit and the first... The specific steps for determining the similarity of different preceding adjacent combinations within each independent word unit are as follows: Within all combined word units in the head and neck surgery patient's medical history... The first independent word unit is located in the first In the word combination unit, remove the first one. All independent word units after the first independent word unit result in the first independent word unit. The first independent word unit is located in the first The first adjacent combination; within all combination word units in the medical history of head and neck surgery patients. The first independent word unit is located in the first In the word combination unit, remove the first one. All independent word units preceding the first independent word unit are obtained, resulting in the first independent word unit. The first independent word unit is located in the first The next adjacent combination is obtained; The first independent word unit is located in the first Each independent word unit within the next adjacent combination. Encoding and the The first independent word unit is located in the first Each independent word unit within each preceding adjacent combination coding; Each independent word unit The set of elements within the encoding is denoted as the element set of each independent word unit; the first... The first independent word unit is located in the first Each subsequent adjacent combination contains independent word units. Encoding and the The first independent word unit is located in the first Each subsequent adjacent combination contains independent word units. The codes are compared to obtain the first one. The first independent word unit is located in the first The next adjacent combination and the first The first independent word unit is located in the first The similarity of adjacent combinations after each step; Get the The first independent word unit is located in the first The next adjacent combination and the first The first independent word unit is located in the first The specific formula for calculating the similarity of adjacent combinations is as follows: In the formula, Indicates the first The first independent word unit is located in the first The next adjacent combination and the first The first independent word unit is located in the first The similarity of adjacent combinations after each iteration Indicates the first The first independent word unit is located in the first The number of independent word units in the next adjacent combination is the same as the number of words in the first... The first independent word unit is located in the first The minimum number of independent word units in adjacent combinations. Indicates the first The first independent word unit is located in the first The th next adjacent combination The set of elements of the first independent word unit and the first The th next adjacent combination The number of elements contained in the union of the sets of elements of individual word units. Indicates the first The first independent word unit is located in the first The th next adjacent combination The set of elements of the first independent word unit and the first The th next adjacent combination The number of elements contained in the intersection of the element sets of each independent word unit; the number of elements contained in the intersection of the element sets of each independent word unit; The first independent word unit is located in the first Independent word units within each preceding adjacent combination Encoding and the The first independent word unit is located in the first Independent word units within each preceding adjacent combination The codes are compared to obtain the first one. The first independent word unit is located in the first The first adjacent combination and the first The first independent word unit is located in the first Similarity of the previous adjacent combinations; Get the The first independent word unit is located in the first The first adjacent combination and the first The first independent word unit is located in the first The specific formula for calculating the similarity of the first two adjacent combinations is as follows: In the formula, Indicates the first The first independent word unit is located in the first The first adjacent combination and the first The first independent word unit is located in the first Similarity of the first adjacent combinations, Indicates the first The first independent word unit is located in the first The number of independent word units in the preceding adjacent combinations and the number of words in the first... The first independent word unit is located in the first The minimum number of independent word units in the preceding adjacent combinations. Indicates the first The first independent word unit is located in the first The last one in the preceding adjacent combinations The set of elements of the first independent word unit and the first The last one in the preceding adjacent combinations The number of elements contained in the union of the sets of elements of individual word units. Indicates the first The first independent word unit is located in the first The last one in the preceding adjacent combinations The set of elements of the first independent word unit and the first The last one in the preceding adjacent combinations The number of elements contained in the intersection of the element sets of each independent word unit.

5. The intelligent management method for head and neck surgery patient medical record data according to claim 3, characterized in that, According to the first The first independent word unit belongs to its corresponding first... The membership degree of each combined word unit, the first The specific steps to obtain the isolation degree of each independent word unit by the difference between the collection time and the retrieval time of the historical medical records of each combined word unit containing the independent word unit are as follows: the date within the collection time of the first historical medical record of the head and neck surgery patient is recorded as the first day of treatment for the head and neck surgery patient; the day after the first day of treatment for the head and neck surgery patient is recorded as the second day of treatment for the head and neck surgery patient. The day following the second day of treatment for a head and neck surgery patient is designated as the third day of treatment for a head and neck surgery patient; and so on, each day of treatment for a head and neck surgery patient is obtained sequentially thereafter. Retrieve the order value of the number of days of treatment for head and neck surgery patients corresponding to the search time; retrieve the order value of the first... The specific formula for calculating the isolation degree of an independent word unit is as follows: In the formula, Indicates the first The isolation degree of each independent word unit This represents the ordinal value indicating the number of days of treatment for head and neck surgery patients corresponding to the search time. Represents an ordinal value. Represents an ordinal value. This indicates the first treatment of head and neck surgery patients. All medical histories of head and neck surgery patients within 3 days contain the first The number of combined word units of independent word units, Indicates the first The first independent term unit belongs to the treatment of head and neck surgery patients. The first unit of combined words in all the medical history of head and neck surgery patients within 3 days The first independent word unit is located in the first The membership degree of each compound word unit. It is an exponential function with the natural constant as its base. Represents the sigmoid function; where, if the th... The first independent word unit is located in the first The first compound word unit is for the treatment of head and neck surgery patients. The first of all historical medical records of head and neck surgery patients within 3 days in the compound word unit The first independent word unit is located in the first The first combined word unit; then the first The first independent term unit belongs to the treatment of head and neck surgery patients. The first unit of combined words in all the medical history of head and neck surgery patients within 3 days The first independent word unit is located in the first The membership degree of the first combined word unit is the first... The first independent word unit belongs to its corresponding first... The membership degree of each compound word unit.

6. The intelligent management method for head and neck surgery patient medical record data according to claim 1, characterized in that, The specific steps for obtaining the final word unit are as follows: Preset isolation threshold. If the isolation degree of all independent word units within a compound word unit is greater than the isolation degree threshold... If a combined word unit contains one or more independent word units, then the word unit is split into multiple independent word units; if the isolation degree of one or more independent word units within a combined word unit is less than or equal to the isolation degree threshold... If the combined word unit is not split, then the independent word unit in the search content, the independent word unit in each historical medical record of the head and neck surgery patient, the independent word unit split from the combined word unit, and the combined word unit that has not been split are all recorded as the final word unit.

7. The intelligent management method for head and neck surgery patient medical record data according to claim 1, characterized in that, The specific steps for obtaining the medical history required by the doctor from the medical history of a head and neck surgery patient are as follows: If all the final word units in a medical history of a head and neck surgery patient contain all the final word units in the search content, then the medical history is the medical history required by the doctor.

8. The intelligent management method for head and neck surgery patient medical record data according to claim 1, characterized in that, The specific calculation steps for obtaining the priority of each historical medical record needed by the doctor are as follows: If the first... If the final word unit is one of the final word units in the search content, then the first final word unit will be... When the final term unit first appears in the search results, it is located at the [number]th [position] in the search results. The sum of the number of categories of the final word units to the left of the first final word unit plus 1 is denoted as the first final word unit. The order value of the final word unit in the search results; add 1 to the number of categories of the final word units in the search results and then subtract the order value of the final word unit. The result after the order value of the final word unit in the search content is denoted as the first... The importance of each final word unit; if the first If the first final word unit is not a final word unit in the search content, then the second final word unit is not a final word unit in the search content. The importance of the final word unit is 0; to obtain the first word unit needed by the doctor The specific formula for calculating the priority of each historical medical record is as follows: In the formula, This indicates the doctor's need for the first Priority of historical medical records This indicates the search time and the number of times the doctor needs to search. The time interval between the collection of historical medical records Indicates the number of types of the final word unit. Indicates the first The final word unit is the one needed by the doctor. The number of times it appears in a historical medical record Indicates the first The importance of each final word unit It is an exponential function with the natural constant as its base. This represents the weight normalization function.

9. The intelligent management method for head and neck surgery patient medical record data according to claim 5, characterized in that, The specific steps for obtaining important word units from the final word unit are as follows: If the first... The final term unit is for head and neck surgery patients. A final word unit in a historical medical record, then the first The final term unit in head and neck surgery patients When it first appeared in a historical medical record, it was the first time a head and neck surgery patient... In the historical medical records, located at number The sum of the number of categories of the final word units to the left of the first final word unit plus 1 is denoted as the first final word unit. The final term unit in head and neck surgery patients The order value in the historical medical records; the first order value of head and neck surgery patients. The number of final word units in each historical medical record is increased by 1, then the number of words in the record is decreased. The final term unit in head and neck surgery patients The result after the order value in the historical medical records is the first one. The historical significance of the final word unit; obtaining the first The specific formula for calculating the final importance of each final word unit is as follows: ; In the formula, Indicates the first The final term unit in the treatment of head and neck surgery patients The importance of the sky Indicates the first The final importance of each final word unit, This indicates the first treatment of head and neck surgery patients. The number of final word units in all historical medical records of head and neck surgery patients within a day. Indicates the first The final term unit in the treatment of head and neck surgery patients The number of times a head and neck surgery patient appears in all their medical history records within a day. This indicates the first stage of treatment for head and neck surgery patients. The first of all medical histories of head and neck surgery patients within 3 days The final term unit in the treatment of head and neck surgery patients The number of times a head and neck surgery patient appears in all their medical history records within a day. This indicates the first stage of treatment for head and neck surgery patients. The first of all medical histories of head and neck surgery patients within 3 days The final term unit in the treatment of head and neck surgery patients The number of times a head and neck surgery patient appears in all their medical history records within a day. This represents the ordinal value indicating the number of days of treatment for head and neck surgery patients corresponding to the search time. Indicates the first The mean of all historical importance of each final word unit, Parentheses indicating Iverson; Based on the final importance of each final word unit, the final word unit is divided into two clusters using the Otsu threshold method. The cluster with the highest mean final importance of the final word units contained therein is designated as the important cluster. The other cluster is designated as the non-important cluster. The final word units within the important cluster are designated as important word units.

10. The intelligent management method for head and neck surgery patient medical record data according to claim 8, characterized in that, The specific steps for obtaining the medical records needed by the doctor and their priorities based on important keywords in the search content are as follows: If the first patient in a head and neck surgery... Within all final word units of the historical medical records, including all important word units of the search content, the first word unit of the head and neck surgery patient... Each historical medical record is recorded as a record needed by the doctor. Based on the position of each final term unit in the search content, its quantity in the historical medical records needed by the doctor, and the time interval between the collection time and the retrieval time for each historical medical record needed by the doctor, the record is determined by the number of historical medical records needed by the doctor. The method for obtaining the priority of each historical medical record is to obtain the priority of each historical medical record needed by the doctor.

Images