A method, system and device for entering clinical nursing monitoring information

Abstract

The present invention relates to the field of healthcare information technology, and specifically relates to a method, system and device for entering clinical nursing monitoring information. By obtaining the clinical nursing monitoring information to be entered and the historical clinical nursing monitoring information, word segmentation extraction is performed on the monitoring information, so as to obtain the real-time word segmentation of the clinical nursing monitoring information to be entered and the historical word segmentation of the historical clinical nursing monitoring information; by analyzing the real-time word segmentation of the clinical nursing monitoring information to be entered and the historical word segmentation of the historical clinical nursing monitoring information, high-frequency word segments among all the real-time word segments of the descriptive information in the clinical nursing monitoring information to be entered are screened out, and the degree of encryption to be performed on each high-frequency word segment is determined, and then the optimal encryption round number array for each high-frequency word segment is determined; based on the optimal encryption round number array, all the real-time word segments in the clinical nursing monitoring information to be entered are encrypted, and the encrypted data is entered. The present invention effectively improves the encryption and entry efficiency of clinical nursing monitoring information.

Description

Technical Field

[0001] The present invention relates to the field of healthcare information technology, and particularly to a method, system and device for entering clinical nursing monitoring information. Background Art

[0002] The clinical nursing monitoring information of patients provides an important basis for medical decision-making. The clinical nursing monitoring information is often entered into the CIS clinical information system. The entry of detailed and accurate nursing monitoring information can reflect the changes in the patient's condition, treatment response and the effect of nursing measures in real time. By consulting the records of nursing monitoring information, doctors can quickly understand the patient's nursing situation and thus formulate a more accurate treatment plan.

[0003] To ensure the privacy and security of patients' medical data, information encryption processing is usually required during the entry of clinical nursing monitoring information. The traditional AES encryption algorithm is often used to encrypt the content of clinical nursing monitoring information, and a fixed number of encryption rounds are usually used to encrypt all nursing monitoring information during the encryption process, so that all information is equally encrypted within a safe range. However, since the clinical nursing monitoring information usually includes multi-dimensional different types of information, and there are differences in the encryption requirements between different types of information, setting the same encryption level for all monitoring information by using a fixed number of encryption rounds will cause the consumption of redundant encryption computing resources and reduce the encryption entry efficiency of nursing monitoring information. Summary of the Invention

[0004] The purpose of the present invention is to provide a method, system and device for entering clinical nursing monitoring information, which is used to solve the problem that the existing method of setting the same encryption level for all monitoring information by using a fixed number of encryption rounds will reduce the encryption entry efficiency of nursing monitoring information.

[0005] To solve the above technical problems, in the first aspect, the present invention provides a method for entering clinical nursing monitoring information, including the following steps:

[0006] Obtain the clinical nursing monitoring information to be entered and the historical clinical nursing monitoring information, and perform word segmentation extraction on the clinical nursing monitoring information, so as to obtain the real-time word segmentation of the clinical nursing monitoring information to be entered and the historical word segmentation of the historical clinical nursing monitoring information;

[0007] According to the occurrence frequency of each real-time word segmentation of the descriptive information in the clinical nursing monitoring information to be entered in all the historical word segmentations of the historical clinical nursing monitoring information, screen out the high-frequency word segmentations in all the real-time word segmentations of the descriptive information in the clinical nursing monitoring information to be entered;

[0008] Determine the word segmentation sensitivity of each high-frequency word by the similarity between the description segments where each high-frequency word is located in the clinical nursing monitoring information to be entered and the historical clinical nursing monitoring information;

[0009] Determine the degree of encryption to be applied to each high-frequency word based on the word segmentation sensitivity of each high-frequency word and the difference in the frequencies of occurrence of each high-frequency word among all the words segmented under the nursing information dimension in the clinical nursing monitoring information to be entered and the historical clinical nursing monitoring information;

[0010] Determine the optimal encryption round number array for each high-frequency word based on the degree of encryption to be applied to each high-frequency word and the frequency of occurrence of each high-frequency word among all the words segmented in the clinical nursing monitoring information to be encrypted;

[0011] Encrypt all the real-time words segmented in the clinical nursing monitoring information to be entered, and during the encryption process, the encryption round of each high-frequency word is determined by its optimal encryption round number array, so as to obtain encrypted data and enter the encrypted data.

[0012] Combined with the first aspect above, in some possible implementation manners, screen out the high-frequency words among all the real-time words segmented, including:

[0013] Determine the maximum frequency of occurrence of each real-time word of the descriptive information in the clinical nursing monitoring information to be entered among all the historical words segmented in the historical clinical nursing monitoring information, so as to obtain the maximum frequency of occurrence;

[0014] Determine the ratio of the frequency of occurrence of each real-time word of the descriptive information in the clinical nursing monitoring information to be entered among all the historical words segmented in the historical clinical nursing monitoring information to the maximum frequency of occurrence, so as to obtain the high-frequency performance degree;

[0015] Determine the real-time words of the descriptive information in the clinical nursing monitoring information to be entered with a high-frequency performance degree greater than the set high-frequency performance degree threshold as high-frequency words.

[0016] Combined with the first aspect above, in some possible implementation manners, determine the word segmentation sensitivity of each high-frequency word, including:

[0017] Determine the description consistency between each high-frequency word and each of its identical historical words according to the similarity between the description segment where each high-frequency word is located in the clinical nursing monitoring information to be entered and the description segment where each identical historical word is located in the historical clinical nursing monitoring information;

[0018] Determine the confidence index of the description consistency between each high-frequency word and each of its identical historical words according to the similarity between the description segments where each identical historical word of each high-frequency word in the historical clinical nursing monitoring information is located and the description segments where other identical historical words are located;

[0019] Use a confidence index to correct the description consistency between each high-frequency word segment and its respective identical historical word segments, and determine the true description consistency between each high-frequency word segment and its respective identical historical word segments;

[0020] Determine the word segmentation sensitivity of each high-frequency word segment according to the average distribution level of the true description consistency between each high-frequency word segment and its respective identical historical word segments.

[0021] Combined with the above first aspect, in some possible implementation manners, determining the description consistency between each high-frequency word segment and each of its identical historical word segments includes:

[0022] Construct a first sentence segment word segmentation code value sequence according to the code values of each word segment in the description sentence segment where each high-frequency word segment is located in the clinical nursing monitoring information to be entered, and construct a second sentence segment word segmentation code value sequence according to the code values of each word segment in the description sentence segment where each identical historical word segment of each high-frequency word segment in the historical clinical nursing monitoring information is located;

[0023] Determine the number of interval code values between the code value corresponding to each high-frequency word segment in the first sentence segment word segmentation code value sequence and the midpoint code value to obtain a first number of interval code values; and determine the number of interval code values between the code value of each identical historical word segment in the second sentence segment word segmentation sequence and the midpoint code value to obtain a second number of interval code values;

[0024] Determine the difference between the code value of each high-frequency word segment and the average value of the code values of all word segments in the first sentence segment word segmentation sequence to obtain a first code value difference, and determine the difference between the code value of each identical historical word segment of each high-frequency word segment in the historical clinical nursing monitoring information and the average value of the code values of all word segments in the second sentence segment word segmentation sequence to obtain a second code value difference;

[0025] Determine the description consistency between each high-frequency word segment and each of its identical historical word segments according to the difference magnitude between the first number of interval code values and the second number of interval code values, and the difference magnitude between the first code value difference and the second code value difference.

[0026] Combined with the above first aspect, in some possible implementation manners, the confidence index for determining the description consistency between each high-frequency word segment and each identical historical high-frequency word segment includes:

[0027] Determine the distance value between each identical historical high-frequency word segment of each high-frequency word segment and the second sentence segment word segmentation code value sequence corresponding to each other identical historical high-frequency word segment;

[0028] According to each identical historical high-frequency word segment and all other identical historical high-frequency word segments corresponding to Determine the confidence index of the description consistency between each high-frequency word segment and each same historical high-frequency word segment according to the average distribution level of the distance values.

[0029] Combined with the above first aspect, in some possible implementation manners, determining the degree of encryption to be applied to each high-frequency word segment includes:

[0030] Determine the sum of the frequency of occurrence of each high-frequency word segment among all word segments under the nursing information dimension to which it belongs in the historical clinical nursing monitoring information and a set frequency parameter;

[0031] Determine the ratio of the frequency of occurrence of each high-frequency word segment among all word segments under the nursing information dimension to which it belongs in the clinical nursing monitoring information to be entered to the corresponding sum value, and obtain the frequency ratio of each high-frequency word segment;

[0032] Determine the product of the frequency ratio of each high-frequency word segment and the word segment sensitivity degree, so as to obtain the degree of encryption to be applied to each high-frequency word segment.

[0033] Combined with the above first aspect, in some possible implementation manners, determining the optimal encryption round number array for each high-frequency word segment includes:

[0034] Divide the encryption round number range into several encryption round number intervals, each encryption round number interval corresponds to an encryption degree interval, and the larger the encryption round number in the encryption round number interval, the greater the encryption degree in the corresponding encryption degree interval;

[0035] Determine the encryption degree interval to which the degree of encryption to be applied to each high-frequency word segment belongs, and use the encryption round number interval corresponding to the belonging encryption degree interval as the target encryption round number interval;

[0036] Determine several encryption round number arrays in the target encryption round number interval, and the number of encryption round numbers in the encryption round number array is equal to the frequency of occurrence of each high-frequency word segment among all word segments in the clinical nursing monitoring information to be encrypted;

[0037] According to the dispersion degree of all encryption round numbers in each encryption round number array, screen out the optimal encryption round number array from all encryption round number arrays.

[0038] Combined with the above first aspect, in some possible implementation manners, screening out the optimal encryption round number array from all encryption round number arrays includes:

[0039] Determine the variance of all encryption round numbers in each encryption round number array;

[0040] Determine the maximum variance among the variances corresponding to all encryption round number arrays;

[0041] Use the encryption round number array corresponding to the maximum variance as the optimal encryption round number array.

[0042] To solve the above technical problems, in a second aspect, the present invention further provides a clinical nursing monitoring information entry system, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the system executes the method in the above first aspect or any possible implementation manner of the first aspect.

[0043] To solve the above technical problems, in a third aspect, the present invention further provides a clinical nursing monitoring information entry device, and the device includes:

[0044] A data acquisition module, configured to acquire the clinical nursing monitoring information to be entered and the historical clinical nursing monitoring information, perform word segmentation extraction on the clinical nursing monitoring information, so as to obtain the real-time word segmentation of the clinical nursing monitoring information to be entered and the historical word segmentation of the historical clinical nursing monitoring information;

[0045] A high-frequency word segmentation acquisition module, configured to screen out the high-frequency word segmentation among all the real-time word segmentation of the descriptive information in the clinical nursing monitoring information to be entered according to the occurrence frequency of each real-time word segmentation of the descriptive information in the clinical nursing monitoring information to be entered among all the historical word segmentation of the historical clinical nursing monitoring information;

[0046] A word segmentation sensitivity acquisition module, configured to determine the word segmentation sensitivity of each high-frequency word segmentation according to the similarity between the description sentence segments where each high-frequency word segmentation is located in the clinical nursing monitoring information to be entered and the historical clinical nursing monitoring information;

[0047] A degree of encryption to be determined module, configured to determine the degree of encryption to be determined for each high-frequency word segmentation according to the word segmentation sensitivity of each high-frequency word segmentation and the difference in the occurrence frequency of each high-frequency word segmentation among all the word segmentation under the nursing information dimension in the clinical nursing monitoring information to be entered and the historical clinical nursing monitoring information;

[0048] An optimal encryption round number array acquisition module, configured to determine the optimal encryption round number array for each high-frequency word segmentation according to the degree of encryption to be determined for each high-frequency word segmentation and the occurrence frequency of each high-frequency word segmentation among all the word segmentation of the clinical nursing monitoring information to be encrypted;

[0049] An encrypted entry module, configured to encrypt all the real-time word segmentation in the clinical nursing monitoring information to be entered, and the encryption round of each high-frequency word segmentation during the encryption process is determined by its optimal encryption round number array, so as to obtain encrypted data and enter the encrypted data.

[0050] To solve the above technical problems, in a fourth aspect, the present invention further provides a computer program product, which includes: computer program code that, when running on a computer, causes the computer to execute the method in the first aspect or any possible implementation manner of the first aspect above.

[0051] To solve the above technical problems, in a fifth aspect, the present invention further provides a computer-readable storage medium that stores computer program code which, when running on a computer, causes the computer to execute the method in the first aspect or any possible implementation manner of the first aspect above.

[0052] The present invention has the following beneficial effects: By obtaining the real-time word segmentation of the clinical nursing monitoring information to be entered and the historical word segmentation of the historical clinical nursing monitoring information, and based on the occurrence frequency of each real-time word segmentation of the descriptive information in the to-be-entered clinical nursing monitoring information among all the historical word segmentations of the historical clinical nursing monitoring information, high-frequency word segmentations are screened out from all the real-time word segmentations of the descriptive information in the to-be-entered clinical nursing monitoring information; According to the similarity between the descriptive sentence segments where each high-frequency word segmentation is located in the to-be-entered clinical nursing monitoring information and the historical clinical nursing monitoring information, the word segmentation sensitivity degree of each high-frequency word segmentation is determined; According to the word segmentation sensitivity degree of each high-frequency word segmentation and the difference in the occurrence frequency of each high-frequency word segmentation among all the word segmentations under the nursing information dimension to which the to-be-entered clinical nursing monitoring information and the historical clinical nursing monitoring information belong, the degree of encryption to be performed on each high-frequency word segmentation is determined; According to the degree of encryption to be performed on each high-frequency word segmentation and the occurrence frequency of each high-frequency word segmentation among all the word segmentations of the clinical nursing monitoring information to be encrypted, the optimal encryption round number array of each high-frequency word segmentation is determined; Encrypt all the real-time word segmentations in the to-be-entered clinical nursing monitoring information, and during the encryption process, the encryption round of each high-frequency word segmentation is determined by its optimal encryption round number array, thereby obtaining encrypted data, and entering the encrypted data. The present invention determines the degree of encryption to be performed on each high-frequency word segmentation according to the importance performance of each high-frequency word segmentation of the descriptive information in the to-be-entered clinical nursing monitoring information, and adaptively determines the encryption round of each high-frequency word segmentation according to the degree of encryption to be performed. Compared with the traditional encryption algorithm that uses a consistent encryption round for all nursing monitoring information, the encryption and entry efficiency of clinical nursing monitoring information is effectively improved. Description of the Drawings

[0053] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0054] Figure 1 The flowchart of the steps of a clinical nursing monitoring information input method according to an embodiment of the present invention;

[0055] Figure 2 The structural schematic diagram of a clinical nursing monitoring information input system according to an embodiment of the present invention;

[0056] Figure 3 The structural schematic diagram of a clinical nursing monitoring information input device according to an embodiment of the present invention. Detailed implementation manners

[0057] To clearly illustrate the technical features of this solution, the present invention will be described in detail below through specific implementation manners in combination with the drawings.

[0058] The embodiments of the present invention will be described in more detail below with reference to the drawings. Although some embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments described herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not used to limit the protection scope of the present invention.

[0059] It should be understood that the various steps recorded in the method implementation manners of the present invention can be executed in different orders and / or executed in parallel. In addition, the method implementation manners may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this regard.

[0060] The term "including" and its variants used herein are open-ended, that is, "including but not limited to". The term "based on" is "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0061] It should be noted that the concepts such as "first" and "second" mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order of the functions executed by these devices, modules or units or the interdependent relationship.

[0062] In the embodiments of the present invention, although operations or steps are described in a specific order in the drawings, it should not be understood that these operations or steps are required to be performed in the specific order shown or in a serial order, or that all the operations or steps shown are required to obtain the desired result. In the embodiments of the present invention, these operations or steps can be performed serially; they can also be performed in parallel; or a part of these operations or steps can be performed.

[0063] At the same time, it can be understood that the data involved in the technical solution of the present invention (including but not limited to the data itself, the acquisition or use of the data) should comply with the requirements of the corresponding laws, regulations and related provisions. Unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs, and all parameters or indicators in the formulas involved in the present invention are numerical values after normalization that eliminate the influence of dimensions.

[0064] In order to solve the problem that setting the same encryption level for all monitoring information by using a fixed number of encryption rounds in the prior art will reduce the encryption input efficiency of nursing monitoring information, the embodiments of the present invention provide a method, a system and a device for entering clinical nursing monitoring information. By identifying the high-frequency words in the clinical nursing monitoring information and adaptively determining the number of encryption rounds for different high-frequency words, the encryption input efficiency of the clinical nursing monitoring information is effectively improved.

[0065] The following will combine the drawings to introduce in detail a method, a system and a device for entering clinical nursing monitoring information provided by the embodiments of the present invention.

[0066] Figure 1 The basic flowchart of a method for entering clinical nursing monitoring information provided by the embodiments of the present invention is shown, as Figure 1 shown, and the method specifically includes the following steps:

[0067] Step S100: Obtain the clinical nursing monitoring information to be entered and the historical clinical nursing monitoring information, and perform word segmentation extraction on the clinical nursing monitoring information, so as to obtain the real-time words of the clinical nursing monitoring information to be entered and the historical words of the historical clinical nursing monitoring information.

[0068] Specifically, clinically nursing monitoring information of all patients to be entered in each nursing department of the hospital is collected and monitored in real time, and the clinically nursing monitoring information to be entered is preprocessed to obtain real-time word segmentation sequences of all patients in different dimensions. Among them, the preprocessing process includes: for the clinically nursing monitoring information of a single patient, since it includes nursing information in multiple dimensions such as vital signs, patient identity, diagnosis information, medication records, etc., the clinically nursing monitoring information of the single patient is distinguished by nursing information dimension; then, for the clinically nursing monitoring information of a single patient in each dimension, Jieba word segmentation is used to segment and extract the information, and the extracted word segments are recorded as real-time word segments, and all real-time word segments of each patient in each dimension are arranged in the order of speech, so as to obtain the real-time word segmentation sequence of each patient in each dimension.

[0069] Meanwhile, clinically nursing monitoring information of all patients in the monitoring hospital in the past period of time is obtained, and these clinically nursing monitoring information are called historical clinically nursing monitoring information. According to the same preprocessing method as above, the historical clinically nursing monitoring information is preprocessed, and the word segments identified from the historical clinically nursing monitoring information during the preprocessing process are recorded as historical word segments, and then the historical word segmentation sequences of each patient in each dimension are obtained. The length of the past period of time can be reasonably set as needed. In this embodiment, the past period of time refers to the time of the past three months.

[0070] The real-time word segmentation sequences of all patients corresponding to the clinically nursing monitoring information to be entered obtained above in each dimension, and the historical word segmentation sequences of all patients corresponding to the historical clinically nursing monitoring information in each dimension are uploaded to the data acquisition system for subsequent processing.

[0071] Step S200: According to the occurrence frequencies of each real-time word segment of the descriptive information in the clinically nursing monitoring information to be entered in all the historical word segments of the historical clinically nursing monitoring information, high-frequency word segments are screened out from all the real-time word segments of the descriptive information in the clinically nursing monitoring information to be entered.

[0072] Specifically, in this embodiment, the encryption rounds are divided into three preset gears. The highest gear is 50 times, the lowest gear is 10 times, and the intermediate gear in the range of (10, 50) times is the adaptive gear. Since the clinically nursing monitoring information includes both digital form information and descriptive information, and the digital form information may be patient ID information or transaction information, the highest encryption level should be set. And among the descriptive information, high-frequency word segments are more important than non-high-frequency word segments. This is because the word segments with higher occurrence frequencies are more likely to be the symptoms repeatedly appearing in patients or the nursing measures repeatedly emphasized by doctors. Therefore, high-frequency word segments should be analyzed emphatically. Thus, the digital form information is placed in the highest gear, the non-high-frequency word segments in the descriptive information are placed in the lowest gear, and the high-frequency word segments are placed in the intermediate adaptive gear.

[0073] Therefore, determine the descriptive information in the clinical nursing monitoring information to be entered. This descriptive information refers to information in non-numerical form, and obtain the respective real-time word segments of this descriptive information. Based on the occurrence frequencies of the respective real-time word segments in all the historical word segments of the historical clinical nursing monitoring information, judge the high-frequency manifestation degree of each real-time word segment, so that the high-frequency word segments can be extracted therefrom.

[0074] Furthermore, the above-mentioned steps of screening out the high-frequency word segments among all the real-time word segments of the descriptive information in the clinical nursing monitoring information to be entered according to the occurrence frequencies of the respective real-time word segments of the descriptive information in the clinical nursing monitoring information to be entered in all the historical word segments of the historical clinical nursing monitoring information include the following steps:

[0075] Determine the maximum value of the occurrence frequencies of the respective real-time word segments of the descriptive information in the clinical nursing monitoring information to be entered in all the historical word segments of the historical clinical nursing monitoring information to obtain the maximum occurrence frequency;

[0076] Determine the ratio of the occurrence frequency of each real-time word segment of the descriptive information in the clinical nursing monitoring information to be entered in all the historical word segments of the historical clinical nursing monitoring information to the maximum occurrence frequency to obtain the high-frequency manifestation degree;

[0077] Determine the real-time word segments of the descriptive information in the clinical nursing monitoring information to be entered with a high-frequency manifestation degree greater than the set high-frequency manifestation degree threshold as high-frequency word segments.

[0078] For the above steps, read the real-time word segment sequence corresponding to the clinical nursing monitoring information to be entered and the historical word segment sequence corresponding to the historical word segments of the historical clinical nursing monitoring information through the data acquisition system. In the real-time word segment sequence corresponding to the clinical nursing monitoring information to be entered, for a single real-time word segment corresponding to the descriptive information, obtain the occurrence frequency of this real-time word segment in all the historical word segments of the historical clinical nursing monitoring information, and determine the maximum value of the occurrence frequencies of all the real-time word segments corresponding to the descriptive information in the historical word segments. Since the occurrence frequency level of the real-time word segment in the historical word segments can reflect the high-frequency manifestation situation of this word segment, calculate the ratio of the occurrence frequency of a single real-time word segment to the maximum value of the occurrence frequencies of all the real-time word segments in the historical word segments, and use this ratio as the high-frequency manifestation degree of the single real-time word segment. Denote the occurrence frequency of the th real-time word segment in the historical word segments as , denote the maximum value of the occurrence frequencies of all the real-time word segments in the historical word segments as , then the high-frequency manifestation degree of the th real-time word segment.

[0079] Preset a high-frequency performance degree threshold, compare the high-frequency performance degree of each real-time word segment corresponding to the descriptive information in the clinical nursing monitoring information to be entered with this preset high-frequency performance degree threshold, and determine the high-frequency word segments among the real-time word segments whose high-frequency performance degree is greater than the preset high-frequency performance degree threshold. In this way, the high-frequency word segments among all real-time word segments can be screened out. Among them, the specific value of the preset high-frequency performance degree threshold can be reasonably set according to needs. In this embodiment, the value of this preset high-frequency performance degree threshold is set to 0.63.

[0080] Step S300: Determine the word segmentation sensitivity of each high-frequency word segment according to the similarity between the descriptive sentence segments where each high-frequency word segment is located in the clinical nursing monitoring information to be entered and the historical clinical nursing monitoring information.

[0081] Specifically, in order to further determine the specific encryption round range of each high-frequency word segment in the adaptive file, considering that in addition to possibly being the symptoms repeatedly appearing in the clinical nursing monitoring information that need to be encrypted with emphasis for patients or the nursing measures repeatedly emphasized by doctors, high-frequency word segments may also be well-known words commonly used in some medical fields. The former is related to patient privacy and requires more encryption rounds, while the latter is common knowledge and should be encrypted with fewer rounds than the former. And the high-frequency word segments representing common knowledge will have similar sentence segment description performances in the historical clinical nursing monitoring information. Therefore, the word segmentation sensitivity can be obtained according to the comparison characteristics of the high-frequency word segments and the historical clinical nursing monitoring information, and then the encryption round array of the current high-frequency word segment can be obtained in combination with the importance difference between the information dimensions to which the high-frequency word segment belongs.

[0082] Furthermore, the above-mentioned step of determining the word segmentation sensitivity of each high-frequency word segment according to the similarity between the descriptive sentence segments where each high-frequency word segment is located in the clinical nursing monitoring information to be entered and the historical clinical nursing monitoring information includes the following implementation steps:

[0083] Determine the description consistency between each high-frequency word segment and each of its identical historical word segments according to the similarity between the descriptive sentence segment where each high-frequency word segment is located in the clinical nursing monitoring information to be entered and the descriptive sentence segment where each identical historical word segment is located in the historical clinical nursing monitoring information;

[0084] Determine the confidence index of the description consistency between each high-frequency word segment and each of its identical historical word segments according to the similarity between each identical historical word segment of each high-frequency word segment in the historical clinical nursing monitoring information and the descriptive sentence segments where other identical historical word segments are located;

[0085] Use the confidence index to correct the description consistency between each high-frequency word segment and each of its identical historical word segments, and determine the true description consistency between each high-frequency word segment and each of its identical historical word segments;

[0086] Determine the word segmentation sensitivity of each high-frequency word by the average distribution level of the true description consistency between each high-frequency word and its respective identical historical words.

[0087] For the above steps, considering that the encryption level of the words corresponding to the medical common knowledge within all high-frequency words should be lower than that of other high-frequency words, and due to the rigor of medical terms, the descriptive usage of the words corresponding to common knowledge often shows strong consistency in sentence segments, so calculate the nursing description consistency between high-frequency words and the identical historical words in historical clinical nursing monitoring information to distinguish the high-frequency words corresponding to common knowledge.

[0088] Take the th high-frequency word in the descriptive information to be entered into the clinical nursing monitoring information as an example, extract the sentence segment where the th high-frequency word is located, and use this sentence segment as the descriptive sentence segment where the th high-frequency word is located. At the same time, extract each identical historical word of the th high-frequency word in the historical clinical nursing monitoring information. Each identical historical word refers to a word with the same encoding value as the th high-frequency word, and extract the sentence segment where each identical historical word is located in the historical clinical nursing monitoring information, and use this sentence segment as the descriptive sentence segment where each identical historical word is located. When the similarity between the descriptive sentence segment where the th high-frequency word is located in the clinical nursing monitoring information to be entered and the descriptive sentence segments where each identical historical word is located in the historical clinical nursing monitoring information is higher, it indicates that the th high-frequency word is more likely to be a word corresponding to common knowledge.

[0089] Further, the description consistency between each high-frequency word segment and its corresponding same historical word segment is determined based on the similarity between the description sentence segments where each high-frequency word segment is located in the clinical care monitoring information to be entered and the description sentence segments where each same historical word segment is located in the historical clinical care monitoring information, including: constructing a first sentence segment word segment coding value sequence according to the coding values of each word segment in the description sentence segment where each high-frequency word segment is located in the clinical care monitoring information to be entered, and constructing a second sentence segment word segment coding value sequence according to the coding values of each word segment in the description sentence segment where each same historical word segment of each high-frequency word segment is located in the historical clinical care monitoring information; determining the number of interval coding values between the coding value corresponding to each high-frequency word segment in the first sentence segment word segment coding value sequence and the midpoint coding value to obtain a first number of interval coding values; and determining the number of interval coding values between the coding value of each same historical word segment in the second sentence segment word sequence and the midpoint coding value to obtain a second number of interval coding values; determining the difference between the coding value of each high-frequency word segment and the average value of the coding values of all word segments in the first sentence segment word sequence to obtain a first coding value difference, and determining the difference between the coding value of each same historical word segment of each high-frequency word segment in the historical clinical care monitoring information and the average value of the coding values of all word segments in the second sentence segment word sequence to obtain a second coding value difference; determining the description consistency between each high-frequency word segment and its corresponding same historical word segment according to the difference magnitude between the first number of interval coding values and the second number of interval coding values, and the difference magnitude between the first coding value difference and the second coding value difference.

[0090] For the above steps, still taking the th high-frequency word segment in the descriptive information of the clinical care monitoring information to be entered as an example, identify each word segment in the description sentence segment where the th high-frequency word segment is located in the clinical care monitoring information to be entered, determine the coding values of each word segment, and arrange the coding values of each word segment in the order of the word segments in the sentence segment, so as to obtain a first sentence segment word segment coding value sequence. In this embodiment, the word vectors of each word segment are obtained through the word2vec algorithm, and one-dimensional numerical processing is performed on the word vectors, that is, the word vectors are normalized, so as to obtain the coding values of each word segment. At the same time, in the same way, identify each word segment in the description sentence segment where each same historical word segment of the th high-frequency word segment is located in the historical clinical care monitoring information, and obtain a second sentence segment word segment coding value sequence corresponding to each same historical word segment.

[0091] Determine the number of interval coding values between the coding value corresponding to the th high-frequency word segment in the first sentence segment word segment coding value sequence corresponding to the th high-frequency word segment and the midpoint coding value in the first sentence segment word segment coding value sequence, and call this number of interval coding values the first number of interval coding values, and denote it as ; Determine the average value of all the coding values in the first sentence segment tokenization coding value sequence to obtain the coding value average, and extract the difference between the coding value corresponding to the th high-frequency token and the coding value average. Take this difference as the first coding value difference and denote it as .

[0092] In the same way, for each second sentence segment tokenization coding value sequence corresponding to the same historical tokens of the th high-frequency token, taking the second sentence segment tokenization coding value sequence corresponding to the th same historical token as an example, determine the number of interval coding values between the coding value corresponding to the th same historical token in the second sentence segment tokenization coding value sequence and the midpoint coding value in the second sentence segment tokenization coding value sequence. Call this number of interval coding values the second interval coding value number and denote it as ; Determine the average value of all the coding values in the second sentence segment tokenization coding value sequence to obtain the coding value average, and extract the difference between the coding value corresponding to the th same historical token and the coding value average. Take this difference as the second coding value difference and denote it as ; .

[0093] If the differences between the th high-frequency token and its th same historical token in the sentence segment tokenization coding value sequence and , and and are both small, it indicates that the descriptions of the th high-frequency token and its th same historical token in the sentence segment are more similar, which means that the description usage is more consistent. Thus, the description consistency between the th high-frequency token and its th same historical token can be obtained.

[0094] In this embodiment, the calculation formula corresponding to the description consistency between the th high-frequency token and its th same historical token is: ;

[0095] ;

[0096] In the formula: represents the first interval coding value number corresponding to the th high-frequency token; represents the th high-frequency token's The number of second interval coding values corresponding to the same historical participles; Indicates the First coding value difference corresponding to the Indicates the th high-frequency participle Second coding value difference corresponding to the same historical participles of the and Both represent the denominator correction parameter, used to prevent the denominator from being taken as 0. In this embodiment, is set, .

[0097] In the same way as above, the description consistency between each high-frequency participle and each of its same historical participles can be determined.

[0098] Meanwhile, for the set of same historical participles corresponding to a single high-frequency participle, if the performance of the sentence segment to which a certain same historical participle belongs is more similar to the average level of the performance of the sentence segments to which other same historical participles in the set of same historical participles belong, it indicates that the universality of this same historical participle is higher, and then the confidence level of the nursing description consistency obtained from this same historical participle is higher. At this time, combining the sentence segment similarity between each high-frequency participle and each of its same historical participles, the participle sensitivity of each high-frequency participle can be obtained.

[0099] Furthermore, the confidence index for determining the description consistency between each high-frequency participle and each of its same historical participles according to the similarity between each same historical participle of each high-frequency participle in the historical clinical nursing monitoring information and the description sentence segments where other same historical participles are located includes: determining the distance value between the second sentence segment participle coding value sequences corresponding to each same historical high-frequency participle of each high-frequency participle and each other same historical high-frequency participle; determining the confidence index of the description consistency between each high-frequency participle and each same historical high-frequency participle according to the average distribution level of the distance values corresponding to each same historical high-frequency participle and all other same historical high-frequency participles.

[0100] For the above steps, taking the th high-frequency participle and the th same historical participle as an example, calculate the average value of the distance values between the second sentence segment participle coding value sequence of the th same historical participle and the second sentence segment participle coding value sequences of all other same historical participles of the th high-frequency participle, and obtain the average distance value, denoted as . If the average value The higher the universality of the same historical word segmentations, the higher the confidence that can be placed in the description consistency obtained from the same historical word segmentation and the high-frequency word segmentation, that is, the larger the value of the confidence index for the description consistency between the high-frequency word segmentation and its same historical word segmentation. In this embodiment, the sum of the mean value and the correction value is determined, and the reciprocal of this sum is used as the confidence index for the description consistency between the high-frequency word segmentation and its same historical word segmentation. same historical word segmentation. same historical word segmentation.

[0101] In the above manner, the confidence index for the description consistency between each high-frequency word segmentation and each of its same historical word segmentations can be determined. The confidence index is used to correct the description consistency between each high-frequency word segmentation and each of its same historical word segmentations, that is, the product of the confidence index and the corresponding description consistency is calculated, and this product is used as the true description consistency. Thus, the true description consistency between each high-frequency word segmentation and each of its same historical word segmentations can be determined.

[0102] The average value of the true description consistency between each high-frequency word segmentation and each of its same historical word segmentations is determined to obtain the mean value of the true description consistency. Since the lower the true nursing description consistency between a high-frequency word segmentation and all of its same historical word segmentations, the lower the likelihood that the high-frequency word segmentation is common medical knowledge, and the higher the sensitivity of the high-frequency word segmentation. Therefore, the sensitivity of each high-frequency word segmentation can be determined based on the mean value of the true description consistency between each high-frequency word segmentation and each of its same historical word segmentations.

[0103] In this embodiment, taking the th high-frequency word segmentation as an example, the formula for calculating the sensitivity of the th high-frequency word segmentation is as follows:

[0104] ;

[0105] In the formula: represents the average value of the true description consistency between the th high-frequency word segmentation and each of its same historical word segmentations, that is, the mean value of the true description consistency; represents the standard normalization function, which is used to limit the value range of to the range of (0, 1); represents the denominator correction parameter, which is used to prevent the denominator from being zero, .

[0106] In the above manner, the tokenization sensitivity of all high-frequency tokens can be determined.

[0107] Step S400: Determine the degree of encryption to be applied to each high-frequency token based on the tokenization sensitivity of each high-frequency token and the difference in the frequencies of occurrence of each high-frequency token among all the tokens belonging to the nursing information dimension in the clinical nursing monitoring information to be entered and the historical clinical nursing monitoring information.

[0108] Specifically, there are differences in the encryption corresponding to high-frequency tokens in clinical nursing monitoring information of different dimensions. For example, the encryption for the dimension representing patient personal identity information should be higher than that for the diagnosis information dimension. Moreover, compared with high-frequency tokens in other dimensions, the high-frequency characteristics of high-frequency tokens in the dimension representing identity information are mainly manifested in the real-time clinical nursing monitoring information and less in the historical clinical nursing monitoring information. Therefore, based on the tokenization sensitivity of each high-frequency token, the degree of encryption to be applied to the high-frequency token can be further obtained by combining the dimensional differences of the high-frequency tokens.

[0109] Furthermore, the above step of determining the degree of encryption to be applied to each high-frequency token based on the tokenization sensitivity of each high-frequency token and the difference in the frequencies of occurrence of each high-frequency token among all the tokens belonging to the nursing information dimension in the clinical nursing monitoring information to be entered and the historical clinical nursing monitoring information includes the following implementation steps:

[0110] Determine the sum of the frequency of occurrence of each high-frequency token among all the tokens belonging to the nursing information dimension in the historical clinical nursing monitoring information and a set frequency parameter;

[0111] Determine the ratio of the frequency of occurrence of each high-frequency token among all the tokens belonging to the nursing information dimension in the clinical nursing monitoring information to be entered to the corresponding sum value, so as to obtain the frequency ratio of each high-frequency token;

[0112] Determine the product of the frequency ratio of each high-frequency token and the tokenization sensitivity, thereby obtaining the degree of encryption to be applied to each high-frequency token.

[0113] Regarding the above steps, taking the rd high-frequency token as an example, extract the frequency of occurrence of this rd high-frequency token among all the tokens belonging to the nursing information dimension in the clinical nursing monitoring information to be entered and extract the frequency of occurrence of this rd high-frequency token among all the tokens belonging to the nursing information dimension in the historical clinical nursing monitoring information . If the frequency of occurrence of this rd high-frequency token that occurs in real time among all the tokens belonging to the nursing information dimension in the clinical nursing monitoring information to be entered is compared with the frequency of occurrence in the historical clinical nursing monitoring information If it is relatively large, it indicates that the th high-frequency word segment is more likely to be the patient's personal identity information, and thus it requires a higher degree of encryption to be performed.

[0114] In this embodiment, taking the th high-frequency word segment as an example, the degree of encryption required for the th high-frequency word segment corresponds to the following calculation formula:

[0115] ;

[0116] In the formula: represents the frequency of occurrence of the th high-frequency word segment among all the word segments under the nursing information dimension to which the clinical nursing monitoring information to be entered belongs; represents the frequency of occurrence of the th high-frequency word segment among all the word segments under the nursing information dimension to which the historical clinical nursing monitoring information belongs; represents a set frequency parameter, which is used to prevent the denominator from being 0. In this embodiment, is set; represents a standard normalization function, which is used to limit the value range of to the range of (0, 1); represents the sensitivity of the th high-frequency word segment.

[0117] In the above manner, the degree of encryption required for all high-frequency word segments can be determined.

[0118] Step S500: Determine the optimal encryption round number array for each high-frequency word segment according to the degree of encryption required for each high-frequency word segment and the frequency of occurrence of each high-frequency word segment among all the word segments of the clinical nursing monitoring information to be encrypted.

[0119] For each high-frequency word segment to be encrypted, the higher its degree of encryption required, the larger the corresponding encryption round number should be. At the same time, since high-frequency word segments are repeated word segments, in order to prevent the situation where a single high-frequency word segment is decrypted and exposes all high-frequency word segments of this type, the encryption round numbers between high-frequency word segments should be made as different as possible. At this time, each high-frequency word segment will correspond to an optimal encryption round number array composed of multiple encryption round numbers.

[0120] Furthermore, the above-mentioned step of determining the optimal encryption round number array for each high-frequency word segment according to the degree of encryption required for each high-frequency word segment and the frequency of occurrence of each high-frequency word segment among all the word segments of the clinical nursing monitoring information to be encrypted includes the following implementation steps:

[0121] Divide the encryption round range into several encryption round intervals, where each encryption round interval corresponds to an encryption degree interval. The greater the encryption round in the encryption round interval, the greater the encryption degree in the corresponding encryption degree interval.

[0122] Determine the encryption degree interval to which the encryption degree to be encrypted of each high-frequency word segmentation belongs, and use the encryption round interval corresponding to the belonging encryption degree interval as the target encryption round interval.

[0123] Determine several encryption round arrays in the target encryption round interval. The number of encryption rounds in the encryption round array is equal to the frequency of each high-frequency word segmentation in all word segmentations of the clinical nursing monitoring information to be encrypted.

[0124] According to the dispersion degree of all encryption rounds in each encryption round array, screen out the optimal encryption round array from all encryption round arrays.

[0125] For the above steps, in this embodiment, divide the total encryption degree interval (0, 1) into four encryption degree intervals: (0, 0.25), [0.25, 0.5), [0.5, 0.75), [0.75, 1). At the same time, also evenly divide the encryption round range (10, 50) of the adaptive gear into four encryption round intervals, which are (10, 20), [20, 30), [30, 40), [40, 50). At this time, each encryption round interval corresponds to an encryption degree interval. The greater the encryption round in the encryption round interval, the greater the encryption degree in the corresponding encryption degree interval. For example, the encryption degree interval [0.75, 1) corresponds to the encryption round interval [40, 50).

[0126] Taking the th high-frequency word segmentation as an example, determine the encryption degree interval to which the encryption degree to be encrypted of the th high-frequency word segmentation belongs, and use the encryption round interval corresponding to the belonging encryption degree interval as the target encryption round interval. Extract the frequency of the th high-frequency word segmentation in all word segmentations of the clinical nursing monitoring information to be encrypted , taking the target encryption round interval corresponding to the th high-frequency word segmentation as [0.75, 1) as an example, generate random numbers at one time within the encryption round interval [40, 50) through the random number generation algorithm. Take all the random numbers generated at one time for the th high-frequency word segmentation as an encryption round array. In this embodiment, the number of groups of the encryption round array for a single high-frequency word segmentation is the preset value 8.

[0127] In the above manner, multiple encryption round number arrays for each high-frequency segmented word can be determined. Since high-frequency segmented words are repeatedly occurring segmented words, in order to improve the encryption effect, the encryption rounds of the high-frequency segmented word at different positions should be as discretely distributed as possible. Therefore, it is necessary to select the optimal encryption round number array according to the dispersion degree of multiple encryption round number arrays of the high-frequency segmented word.

[0128] Further, the above-mentioned selection of the optimal encryption round number array from all encryption round number arrays according to the dispersion degree of all encryption round numbers in each encryption round number array includes: determining the variance of all encryption round numbers in each encryption round number array;

[0129] determining the maximum variance among the variances corresponding to all encryption round number arrays; and taking the encryption round number array corresponding to the maximum variance as the optimal encryption round number array.

[0130] For ease of understanding, taking the th encryption round number array of the th high-frequency segmented word as an example, calculate the mean value of each encryption round data , and denote the value of the th encryption round of the th encryption round number array of the th high-frequency segmented word as . There are a total of values inside the array. If the dispersion degree of the values of each encryption round in a single encryption round number array of a high-frequency segmented word is greater, the matching degree of the array is higher. Therefore, calculate the encryption matching degree of the th encryption round number array of the th high-frequency segmented word. For all encryption round number arrays of the

[0131] th high-frequency segmented word, select the array with the highest encryption matching degree as the optimal encryption round number array.

[0132] Step S600: Encrypt all real-time segmented words in the clinical nursing monitoring information to be entered, and during the encryption process, the encryption rounds of each high-frequency segmented word are determined by its optimal encryption round number array, so as to obtain encrypted data and enter the encrypted data.

[0133] Specifically, for all the word segments in the real-time word segmentation sequences of each patient in each dimension of the clinical nursing monitoring information to be entered, AES encryption processing is performed according to the allocated number of encryption rounds to obtain the ciphertext of the clinical nursing information. Among them, during the AES encryption processing, for multiple word segments at different positions in each high-frequency word segment in the real-time word segmentation sequence, the encryption rounds in the optimal encryption round array are randomly and non-repeatedly mapped, that is, each word segment randomly determines an encryption round from its optimal encryption round array, and the encryption rounds determined by different word segments are different, thereby realizing the adaptability of the encryption rounds of each high-frequency word segment in the clinical nursing monitoring information to be entered. The ciphertext of the clinical nursing information is compressed and stored in the hospital CIS clinical information system. After the encryption entry of the current batch of clinical nursing monitoring information to be entered in the hospital is completed, the same encryption entry process is performed on the latest batch of clinical nursing monitoring information to be entered that is updated in real time, so as to complete the complete entry process of the clinical nursing monitoring information.

[0134] A method for entering clinical nursing monitoring information provided in this embodiment can adaptively determine the encryption rounds for each high-frequency word segment in the clinical nursing monitoring information to be entered by determining the matching encryption round array. Compared with the traditional encryption algorithm that uses a consistent encryption round for all nursing monitoring information, it can determine the degree of encryption to be performed on each high-frequency word segment in combination with the importance performance of the high-frequency word segments in the patient's clinical nursing monitoring information, and adaptively determine the encryption rounds for each high-frequency word segment according to the degree of encryption to be performed, effectively improving the encryption entry efficiency of the clinical nursing monitoring information.

[0135] Based on the same inventive concept, an embodiment of the present invention also provides a system for entering clinical nursing monitoring information, as Figure 2 shown. The system includes: a memory 201, a processor 202, and a computer program 203 stored in the memory 201 and running on the processor 202. Among them, when the processor 202 executes the computer program 203, the system can execute any one of the methods for entering clinical nursing monitoring information introduced above.

[0136] Embodiments of the present invention can divide the functions of the system according to the above method examples. For example, corresponding to each functional module, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is illustrative, only a logical function division, and there may be other division methods in actual implementation.

[0137] Based on the same inventive concept, an embodiment of the present invention also provides a device for entering clinical nursing monitoring information, as Figure 3 shown. The device includes:

[0138] A data acquisition module, configured to acquire the clinical nursing monitoring information to be entered and the historical clinical nursing monitoring information, perform word segmentation extraction on the clinical nursing monitoring information, so as to obtain the real-time word segmentation of the clinical nursing monitoring information to be entered and the historical word segmentation of the historical clinical nursing monitoring information;

[0139] A high-frequency word segmentation acquisition module, configured to screen out the high-frequency word segments among all the real-time word segments of the descriptive information in the clinical nursing monitoring information to be entered according to the occurrence frequencies of each real-time word segment of the descriptive information in the clinical nursing monitoring information to be entered among all the historical word segments of the historical clinical nursing monitoring information;

[0140] A word segmentation sensitivity acquisition module, configured to determine the word segmentation sensitivity of each high-frequency word segment according to the similarity between the descriptive sentence segments where each high-frequency word segment is located in the clinical nursing monitoring information to be entered and the historical clinical nursing monitoring information;

[0141] A degree of encryption to be determined module, configured to determine the degree of encryption to be determined for each high-frequency word segment according to the word segmentation sensitivity of each high-frequency word segment and the difference in the occurrence frequencies of each high-frequency word segment among all the word segments under the nursing information dimension to which the clinical nursing monitoring information to be entered and the historical clinical nursing monitoring information belong;

[0142] An optimal encryption round number array acquisition module, configured to determine the optimal encryption round number array for each high-frequency word segment according to the degree of encryption to be determined for each high-frequency word segment and the occurrence frequency of each high-frequency word segment among all the word segments of the clinical nursing monitoring information to be encrypted;

[0143] An encrypted entry module, configured to encrypt all the real-time word segments in the clinical nursing monitoring information to be entered, and the encryption round of each high-frequency word segment during the encryption process is determined by its optimal encryption round number array, so as to obtain encrypted data and enter the encrypted data.

[0144] It should be noted that: the device provided in the above embodiment is only illustrated by dividing the above functional modules. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above.

[0145] Based on the same inventive concept, an embodiment of the present invention further provides a computer program product, which includes: computer program code, when the computer program code runs on a computer, enabling the computer to execute any one of the clinical nursing monitoring information entry methods introduced above.

[0146] Based on the same inventive concept, an embodiment of the present invention further provides a computer-readable storage medium storing computer program code, which, when running on a computer, causes the computer to execute any one of the clinical care monitoring information entry methods described above.

[0147] It should be noted that the above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for entering clinical nursing monitoring information, characterized in that, The steps include: Obtain the clinical nursing monitoring information to be entered and the historical clinical nursing monitoring information, perform word segmentation extraction on the clinical nursing monitoring information, so as to obtain the real-time word segmentation of the clinical nursing monitoring information to be entered and the historical word segmentation of the historical clinical nursing monitoring information; According to the occurrence frequency of each real-time word segmentation of the descriptive information in the clinical nursing monitoring information to be entered among all the historical word segmentations of the historical clinical nursing monitoring information, screen out the high-frequency word segmentations among all the real-time word segmentations of the descriptive information in the clinical nursing monitoring information to be entered; According to the similarity between the descriptive sentence segments where each high-frequency word segmentation is located in the clinical nursing monitoring information to be entered and the historical clinical nursing monitoring information, determine the word segmentation sensitivity degree of each high-frequency word segmentation; According to the word segmentation sensitivity degree of each high-frequency word segmentation and the difference in the occurrence frequency of each high-frequency word segmentation among all the word segmentations under the nursing information dimension to which it belongs in the clinical nursing monitoring information to be entered and the historical clinical nursing monitoring information, determine the degree of encryption to be performed on each high-frequency word segmentation; According to the degree of encryption to be performed on each high-frequency word segmentation and the occurrence frequency of each high-frequency word segmentation among all the word segmentations of the clinical nursing monitoring information to be encrypted, determine the optimal encryption round number array for each high-frequency word segmentation; Encrypt all the real-time word segmentations in the clinical nursing monitoring information to be entered, and during the encryption process, the encryption round of each high-frequency word segmentation is determined by its optimal encryption round number array, so as to obtain encrypted data, and enter the encrypted data.

2. The clinical nursing monitoring information entry method according to claim 1, wherein Screen out the high-frequency word segmentations among all the real-time word segmentations, including: Determine the maximum value of the occurrence frequency of each real-time word segmentation of the descriptive information in the clinical nursing monitoring information to be entered among all the historical word segmentations of the historical clinical nursing monitoring information, to obtain the maximum occurrence frequency; Determine the ratio of the occurrence frequency of each real-time word segmentation of the descriptive information in the clinical nursing monitoring information to be entered among all the historical word segmentations of the historical clinical nursing monitoring information to the maximum occurrence frequency, to obtain the high-frequency performance degree; Determine the real-time word segmentations of the descriptive information in the clinical nursing monitoring information to be entered with a high-frequency performance degree greater than the set high-frequency performance degree threshold as high-frequency word segmentations.

3. The method for entering clinical nursing monitoring information according to claim 1, characterized in that Determine the word segmentation sensitivity degree of each high-frequency word segmentation, including: According to the similarity between the descriptive sentence segment where each high-frequency word segmentation is located in the clinical nursing monitoring information to be entered and the descriptive sentence segment where each same historical word segmentation is located in the historical clinical nursing monitoring information, determine the descriptive consistency between each high-frequency word segmentation and each of its same historical word segmentations; According to the similarity between the descriptive sentence segments where each same historical word segmentation of each high-frequency word segmentation in the historical clinical nursing monitoring information is located and the descriptive sentence segments where other same historical word segmentations are located, determine the confidence index of the descriptive consistency between each high-frequency word segmentation and each of its same historical word segmentations; Use the confidence index to correct the descriptive consistency between each high-frequency word segmentation and each of its same historical word segmentations, and determine the true descriptive consistency between each high-frequency word segmentation and each of its same historical word segmentations; According to the average distribution level of the true descriptive consistency between each high-frequency word segmentation and each of its same historical word segmentations, determine the word segmentation sensitivity degree of each high-frequency word segmentation.

4. A method for entering clinical nursing monitoring information according to claim 3, characterized in that, Determine the description consistency between each high-frequency word segment and each of its identical historical word segments, including: Construct a first sentence segment word segment coding value sequence according to the coding values of each word segment in the description sentence segment where each high-frequency word segment is located in the clinical nursing monitoring information to be entered, and construct a second sentence segment word segment coding value sequence according to the coding values of each word segment in the description sentence segment where each identical historical word segment of each high-frequency word segment is located in the historical clinical nursing monitoring information; Determine the number of interval coding values between the coding value corresponding to each high-frequency word segment in the first sentence segment word segment coding value sequence and the midpoint coding value to obtain the first number of interval coding values; and determine the number of interval coding values between the coding value of each identical historical word segment in the second sentence segment word sequence and the midpoint coding value to obtain the second number of interval coding values; Determine the difference between the coding value of each high-frequency word segment and the average value of the coding values of all word segments in the first sentence segment word segment sequence to obtain the first coding value difference, and determine the difference between the coding value of each identical historical word segment of each high-frequency word segment in the historical clinical nursing monitoring information and the average value of the coding values of all word segments in the second sentence segment word segment sequence to obtain the second coding value difference; Determine the description consistency between each high-frequency word segment and each of its identical historical word segments according to the difference magnitude between the first number of interval coding values and the second number of interval coding values, and the difference magnitude between the first coding value difference and the second coding value difference.

5. The clinical nursing monitoring information entry method according to claim 4, wherein Determine the confidence index of the description consistency between each high-frequency word segment and each identical historical high-frequency word segment, including: Determine the distance values between the second segmented sentence code value sequences corresponding to each same historical high-frequency word of each high-frequency segmented word and each other same historical high-frequency word; Based on the average distribution level of the distance values corresponding to each identical historical high-frequency word segmentation and all other identical historical high-frequency word segmentations, a confidence index for the description consistency between each high-frequency word segmentation and each identical historical high-frequency word segmentation is determined. Based on the average distribution level of the distance values corresponding to each identical historical high-frequency word segmentation and all other identical historical high-frequency word segmentations, a confidence index for the description consistency between each high-frequency word segmentation and each identical historical high-frequency word segmentation is determined.

6. The clinical nursing monitoring information entry method according to claim 1, wherein, Determine the degree of encryption required for each high-frequency word segment, including: Determine the sum of the frequency of occurrence of each high-frequency word segment among all word segments in the nursing information dimension to which it belongs in the historical clinical nursing monitoring information and the set frequency parameter; Determine the ratio of the frequency of occurrence of each high-frequency word segment among all word segments in the nursing information dimension to which it belongs in the clinical nursing monitoring information to be entered to the corresponding sum value to obtain the frequency ratio of each high-frequency word segment; Determine the product of the frequency ratio of each high-frequency word segment and the word segment sensitivity degree, thereby obtaining the degree of encryption required for each high-frequency word segment.

7. A method for entering clinical nursing monitoring information according to claim 1, characterized in that, Determine the optimal encryption round number array for each high-frequency word segment, including: Divide the encryption round range into several encryption round intervals, each encryption round interval corresponding to an encryption degree interval, and the larger the encryption round in the encryption round interval, the greater the encryption degree in the corresponding encryption degree interval; Determine the encryption degree interval to which the degree of encryption required for each high-frequency word segment belongs, and use the encryption round interval corresponding to the belonging encryption degree interval as the target encryption round interval; Determine several encryption round number arrays in the target encryption round interval, and the number of encryption rounds in the encryption round number array is equal to the frequency of occurrence of each high-frequency word segment among all word segments in the clinical nursing monitoring information to be encrypted; According to the dispersion degree of all encryption rounds in each encryption round number array, screen out the optimal encryption round number array from all encryption round number arrays.

8. A method for entering clinical nursing monitoring information according to claim 7, characterized in that, Screen out the optimal encryption round number array from all encryption round number arrays, including: Determine the variance of all encryption rounds in each encryption round number array; Determine the maximum variance among the variances corresponding to all encryption round number arrays; The encryption round number array corresponding to the maximum variance is used as the optimal encryption round number array.

9. A clinical nursing monitoring information entry system, characterized in that, It includes a memory, a processor, and an executable computer program stored in the memory and operable on the processor. When the processor executes the computer program, it executes a clinical care monitoring information entry method according to any one of claims 1 to 8.

10. A clinical nursing monitoring information entry device, characterized in that, The device includes: A data acquisition module, configured to acquire the clinical care monitoring information to be entered and the historical clinical care monitoring information, perform word segmentation extraction on the clinical care monitoring information, so as to obtain the real-time word segmentation of the clinical care monitoring information to be entered and the historical word segmentation of the historical clinical care monitoring information; A high-frequency word segmentation acquisition module, configured to screen out the high-frequency word segmentation among all the real-time word segmentation of the descriptive information in the clinical care monitoring information to be entered according to the occurrence frequency of each real-time word segmentation of the descriptive information in the clinical care monitoring information to be entered among all the historical word segmentation of the historical clinical care monitoring information; A word segmentation sensitivity acquisition module, configured to determine the word segmentation sensitivity of each high-frequency word segmentation according to the similarity between the descriptive sentence segments where each high-frequency word segmentation is located in the clinical care monitoring information to be entered and the historical clinical care monitoring information; An encryption degree to be determined acquisition module, configured to determine the encryption degree to be determined for each high-frequency word segmentation according to the word segmentation sensitivity of each high-frequency word segmentation and the difference in the occurrence frequency of each high-frequency word segmentation among all the word segmentation under the nursing information dimension in the clinical care monitoring information to be entered and the historical clinical care monitoring information; An optimal encryption round number array acquisition module, configured to determine the optimal encryption round number array for each high-frequency word segmentation according to the encryption degree to be determined for each high-frequency word segmentation and the occurrence frequency of each high-frequency word segmentation among all the word segmentation of the clinical care monitoring information to be encrypted; An encrypted entry module, configured to encrypt all the real-time word segmentation in the clinical care monitoring information to be entered, and determine the encryption round of each high-frequency word segmentation by its optimal encryption round number array during the encryption process, so as to obtain encrypted data and enter the encrypted data.

Images