Nursing management method, system and equipment based on radio frequency identification and storage medium

Abstract

The invention provides a nursing management method, system and device based on radio frequency identification and a storage medium, and relates to the field of nursing management. The method comprises the following steps: acquiring radio frequency tag information entering a working range, and performing structured processing on the radio frequency tag information to obtain radio frequency tag structured information; performing quantitative analysis on the radio frequency tag structured information based on a preset nursing standard to obtain a quantitative analysis result reflecting a nursing process execution condition, the quantitative analysis result including time deviation data, nursing process matching degree deviation data and nursing action deviation degree data; and performing nursing anomaly detection according to the quantitative analysis result, and generating a nursing anomaly detection report. Through the scheme, the nursing quality can be improved.

Description

Technical Field

[0001] The present application relates to the field of nursing management, and specifically to a nursing management method, system, device and storage medium based on radio frequency identification. Background Art

[0002] With the rapid development of the medical industry and the deepening of the aging population, the demand for nursing services is growing. However, traditional nursing management methods generally have problems such as low efficiency and difficult quality control, and it is difficult to adapt to the requirements of high-quality development of medical services in the new era.

[0003] At present, most medical institutions still use the nursing management model of manual recording and spot check evaluation. Nursing staff record nursing process information through paper forms or simple electronic documents, and managers evaluate nursing implementation through regular or irregular on-site inspections and manual spot checks of medical records. This management method that relies on manual operation and experience judgment has many defects: first, the nursing process records lack real-time and continuity, and it is difficult to fully and objectively reflect the actual implementation of nursing work; second, there is a lack of quantitative analysis and evaluation methods, and it is difficult to accurately identify key issues and potential risks in the nursing process; third, management is post-event and passive, and there is a lack of real-time monitoring and early warning of nursing behavior, which is not conducive to the continuous improvement of nursing quality; fourth, it focuses on experience rather than data, and it is difficult to fully tap the experience and knowledge in excellent nursing practices, which is prone to uneven nursing levels. Summary of the invention

[0004] The present application provides a nursing management method, system, device and storage medium based on radio frequency identification, which can improve the quality of nursing.

[0005] In a first aspect, the present application provides a nursing management method based on radio frequency identification, the method comprising: Acquire the radio frequency tag information that enters the working range, and perform structured processing on the radio frequency tag information to obtain radio frequency tag structured information; Based on the preset nursing standards, the structured information of the radio frequency tag is quantitatively analyzed to obtain a quantitative analysis result reflecting the execution of the nursing process, wherein the quantitative analysis result includes: time deviation data, nursing process matching deviation data and nursing action deviation data; Nursing anomaly detection is performed based on the quantitative analysis results, and a nursing anomaly detection report is generated.

[0006] By adopting the above technical solution, by obtaining the information of the RFID tags that enter the working range and performing structured processing on the RFID tag information, the structured information of the RFID tags is obtained, which lays a data foundation for the subsequent quantitative analysis of the nursing process. The use of RFID technology to automatically collect nursing process data overcomes the limitations of traditional manual recording methods and greatly improves the real-time, continuity and accuracy of data collection. By performing structured processing on the collected RFID tag information, the unstructured raw data is converted into structured information, which is convenient for computer programs to read and analyze efficiently, providing data support for intelligent nursing management.

[0007] After obtaining the structured information of the radio frequency tag, the present invention performs quantitative analysis on the structured information of the radio frequency tag based on the preset nursing standard to obtain the quantitative analysis results reflecting the execution of the nursing process, and the quantitative analysis results include time deviation data, nursing process matching deviation data and nursing action deviation data. Through quantitative analysis, the subjective nursing process evaluation is converted into an objective data metric, and an accurate evaluation of the nursing execution deviation is achieved. The time deviation data reflects the degree of deviation between the actual execution time of the nursing action and the standard duration, the nursing process matching deviation data reflects the degree of consistency between the actual nursing action sequence and the standard process, and the nursing action deviation data reflects the degree of deviation between the key parameters of the nursing action and the standard threshold. These three types of deviation data characterize the deviation of the execution of the nursing process in a multi-dimensional and all-round manner, and provide a quantitative basis for subsequent nursing anomaly detection and quality improvement.

[0008] In a second aspect of the present application, a nursing management system based on radio frequency identification is provided, comprising: A data processing module is used to obtain the radio frequency tag information entering the working range, and perform structured processing on the radio frequency tag information to obtain radio frequency tag structured information; A quantification module is used to perform quantitative analysis on the structured information of the radio frequency tag based on a preset nursing standard to obtain a quantitative analysis result reflecting the execution of the nursing process, wherein the quantitative analysis result includes: time deviation data, nursing process matching deviation data and nursing action deviation data; The anomaly detection module is used to perform nursing anomaly detection based on the quantitative analysis results and generate a nursing anomaly detection report.

[0009] In a third aspect of the present application, a computer storage medium is provided, wherein the computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the above method steps.

[0010] In the fourth aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the above method.

[0011] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. This application obtains the information of radio frequency tags that enter the working range and performs structured processing on the radio frequency tag information to obtain structured information of radio frequency tags, laying a data foundation for the subsequent quantitative analysis of the nursing process. The use of radio frequency identification technology to automatically collect nursing process data overcomes the limitations of traditional manual recording methods and greatly improves the real-time, continuity and accuracy of data collection. By performing structured processing on the collected radio frequency tag information, the unstructured raw data is converted into structured information, which is convenient for computer programs to read and analyze efficiently, providing data support for intelligent nursing management.

[0012] 2. After obtaining the structured information of the radio frequency tag, the present invention performs quantitative analysis on the structured information of the radio frequency tag based on the preset nursing standard to obtain quantitative analysis results reflecting the execution of the nursing process, and the quantitative analysis results include time deviation data, nursing process matching deviation data and nursing action deviation data. Through quantitative analysis, the subjective nursing process evaluation is converted into objective data measurement, and an accurate evaluation of nursing execution deviation is achieved. The time deviation data reflects the degree of deviation between the actual execution time of the nursing action and the standard duration, the nursing process matching deviation data reflects the degree of consistency between the actual nursing action sequence and the standard process, and the nursing action deviation data reflects the degree of deviation between the key parameters of the nursing action and the standard threshold. These three types of deviation data characterize the deviation of the execution of the nursing process in a multi-dimensional and all-round manner, and provide a quantitative basis for subsequent nursing anomaly detection and quality improvement.

[0013] 3. This application mines association rules on the results of quantitative analysis to reveal the intrinsic connections between different deviation data, form association rules for deviation data, and provide a theoretical basis for deviation cause analysis and correction strategy formulation. At the same time, the time deviation data, nursing process matching deviation data, and nursing action deviation data obtained by quantitative analysis are extracted to screen out high-quality nursing execution deviation data with deviations less than the preset threshold. After optimization and refinement, best practice data are formed, and a nursing service best practice knowledge base is constructed based on this. On this basis, the best practice knowledge base, quantitative analysis results, and deviation data association rules are comprehensively used to carry out targeted optimization of the preset nursing standards, and finally obtain the target nursing standards that take into account both standardization and flexibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A flowchart of a nursing management method based on radio frequency identification provided in an embodiment of the present application; Figure 2 An architecture diagram of a radio frequency identification-based nursing management system provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of an electronic device provided in this application. DETAILED DESCRIPTION

[0015] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0016] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0017] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0018] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0019] See also Figure 1 , Figure 1 A flow chart of a nursing management method based on radio frequency identification provided in an embodiment of the present application. The system can be implemented by a computer program or can be run as an independent tool application. Specifically, in an embodiment of the present application, the method can be applied on a server, but can also be applied to electronic devices such as a server. A nursing management method based on radio frequency identification includes the following steps: S101, obtaining radio frequency tag information entering a working range, and performing structured processing on the radio frequency tag information to obtain radio frequency tag structured information; Specifically, the present invention first obtains the information of the radio frequency tags that enter the working range. Specifically, a number of radio frequency identification devices, such as radio frequency readers and writers, antennas, etc., are deployed at the nursing work site of the medical institution. When an object or person with a radio frequency tag enters the working range of the radio frequency identification device, the radio frequency identification device automatically reads the information stored in the radio frequency tag through wireless communication to obtain various data related to the nursing process, such as the identity information of medical staff, drug and equipment information, treatment time and place, operation parameter settings, etc. Compared with the traditional manual scanning and recognition method, radio frequency identification technology can realize non-contact, dynamic and real-time data collection, greatly improve the collection efficiency, and reduce human errors.

[0020] After acquiring the radio frequency tag information, this embodiment performs structured processing on the radio frequency tag information to obtain radio frequency tag structured information. Since the original radio frequency tag information usually exists in an unstructured data format, it is not convenient for subsequent computer automatic analysis. Therefore, it is necessary to perform a series of processing such as data cleaning, format conversion, field extraction, etc. on the original radio frequency tag information to convert it into a structured data form. For example, the radio frequency tag information is classified and summarized according to different dimensions such as time, place, personnel, objects, events, etc., and the key fields are extracted and converted into a structured JSON or XML format. After structured processing, the radio frequency tag information is organized into a standardized structured data set, and each piece of data includes a timestamp, an identification code, key fields, etc., which is convenient for computer programs to read and analyze efficiently.

[0021] S102, quantitatively analyzing the structured information of the radio frequency tag based on a preset nursing standard to obtain a quantitative analysis result reflecting the execution status of the nursing process, wherein the quantitative analysis result includes: time deviation data, nursing process matching deviation data, and nursing action deviation data; Specifically, this embodiment first constructs a nursing standard library, and presets the standard process, key steps, important parameters and other normative contents of various nursing operations. Then, the structured information of the radio frequency tag is matched and compared with the nursing standard library, and the deviation between the actual nursing process reflected by the structured information of the radio frequency tag and the standard requirements is quantitatively evaluated by setting matching rules and calculation formulas. Among them, the following three types of deviation data are analyzed in detail: one is the time deviation data, which evaluates the difference between the actual operation time and the standard duration, and quantifies the timeliness of nursing; the second is the nursing process matching deviation data, which measures the degree of consistency between the actual operation steps and the standard process, and quantifies the standardization of nursing; the third is the nursing action deviation data, which examines the degree of deviation between the key nursing parameters and the standard threshold, and quantifies the accuracy of nursing. By calculating these three types of deviation data, quantitative analysis results reflecting the execution of the nursing process are obtained.

[0022] The effect of quantitative analysis is that it transforms qualitative and perceptual nursing evaluation into quantitative and rational data analysis, so that nursing management can be based on evidence. Through multi-dimensional data such as time deviation, process matching deviation, action deviation, etc., managers can fully and accurately understand the crux of the problem in nursing execution and take targeted management intervention measures. For example, if the time deviation data is too large, it is suggested to strengthen the timeliness of nursing response; if the process matching deviation data is too high, it is suggested to standardize the operation process; if the action deviation is too large, it is suggested to strengthen skill training. Quantitative analysis makes nursing evaluation more objective and accurate, and nursing management more scientific and efficient.

[0023] Based on the above embodiment, as an optional embodiment, the quantitative analysis of the radio frequency tag structured information based on the preset nursing standard is performed to obtain a quantitative analysis result reflecting the execution status of the nursing process, including: S201, parsing the structured information of the radio frequency tag through a preset nursing process engine to obtain a sequence of nursing actions, and matching the sequence of nursing actions with a preset standard nursing process to obtain nursing process matching deviation data; Specifically, the preset nursing process engine reads each piece of data from the structured information of the RFID tag in turn, extracts key fields such as timestamp, personnel ID, action ID, etc., and generates an ordered sequence of nursing actions in the order of timestamps. For example, the extracted action data such as "2023-05-20 08:00:00, Nurse Wang, measuring body temperature", "2023-05-2008:05:00, Nurse Wang, taking oral medication", etc. are organized into a sequence string of "measuring body temperature→taking oral medication". By iteratively analyzing all RFID tag structured information, the nursing process engine finally outputs a complete sequence of nursing actions, objectively recording the actual operation process of nursing work.

[0024] After obtaining the sequence of nursing actions, this embodiment matches it with the preset standard nursing process to obtain the nursing process matching deviation data. The reason for calculating the matching deviation is that by comparing the actual execution process with the standard process, it is possible to quantitatively evaluate the standardization of nursing operations and timely discover process violations. Through the matching deviation data, managers can intuitively understand the compliance of nursing process execution and carry out process reengineering and training improvement in a targeted manner.

[0025] During the matching calculation, this embodiment uses a sequence similarity algorithm to quantitatively evaluate the consistency between the actual process and the standard process. First, the standard process corresponding to the current nursing task is searched in the nursing standard library, and its action sequence is extracted. Then, the similarity scores of the two sequences are calculated using algorithms such as the longest common subsequence and edit distance. The higher the score, the better the match. Finally, the difference between the similarity score and the full score of 100% is used as the matching deviation data to intuitively characterize the standardization level of process execution. For example, if the similarity between the actual process and the standard process is 90%, the matching deviation data is 10%, indicating that there is a certain gap between the process execution and the standard requirements, and optimization and improvement are needed.

[0026] Based on the above embodiment, as an optional implementation, the association rule mining is performed on the quantitative analysis result to obtain the deviation data association rule, including: S501, using an association rule mining algorithm to determine a high-frequency deviation data combination pattern in the quantitative analysis result data to form a frequent deviation item set; Specifically, the system first uses classic association rule mining algorithms such as Apriori and FP-growth to mine frequent itemsets on the deviation data set obtained from the previous quantitative analysis. The core idea is to set a minimum support threshold, iteratively scan the deviation data set, generate various combination patterns from the bottom up, count the support of each pattern, and finally screen out high-frequency deviation combinations above the support threshold to form frequent deviation item sets with different lengths and components. For example, if the frequent deviation item set contains combination patterns such as {night shift missed records, postoperative infection}, {night shift missed records, shift handover omissions, postoperative infection}, it means that deviation factors such as night shift missed records and shift handover omissions may be important causes of postoperative infection, reflecting the chain effect of deviation transmission.

[0027] S502, based on the frequent deviation item set, calculate the confidence of each high-frequency deviation data combination pattern, and according to a preset minimum confidence threshold, screen out high-frequency deviation data combination patterns with high confidence, and extract association rules for the high-frequency deviation data combination patterns with high confidence to obtain the deviation data association rules.

[0028] Specifically, the system builds a transaction database based on the results of quantitative analysis of nursing work, and jointly encodes multiple dimensions such as wards, nurses, time periods, and nursing projects to form a multidimensional attribute matrix of deviation data. On this basis, the system uses classic association rule mining algorithms such as Apriori and FP-growth to generate frequent item sets from bottom to top through iterative scanning. First, the system traverses the attribute matrix and counts the frequency of occurrence of each deviation data, and screens out frequent 1-item sets with the minimum support as the threshold. On this basis, the system iteratively generates candidate k-item sets (k≥2), and also screens frequent k-item sets with the minimum support as the standard until no frequent item sets of higher dimensions can be generated, thereby obtaining all high-frequency deviation data combination patterns. The support here refers to the frequency of occurrence of deviation data combinations, which represents the prevalence of the combination pattern. For example, after mining with the Apriori algorithm, the system found that "intravenous infusion and pipelines not replaced in time" and "irregular registration of drug use" are a high-frequency deviation combination pattern in medical group risk management. The support rate of this combination is as high as 20%, indicating that among all deviation transactions, the probability of two deviations occurring at the same time reaches 20%, reflecting the high correlation and commonality of this deviation combination.

[0029] S202, parsing the radio frequency tag structured information through a preset rule engine to obtain key parameters of each nursing action, and comparing the key parameters with the preset action threshold to obtain nursing action deviation data; Specifically, the rule engine first reads each action in the sequence of nursing actions in turn, and searches for the parameter data corresponding to the action in the structured information of the RFID tag. For example, for the "measure body temperature" action, the rule engine extracts key parameters such as body temperature reading, measurement duration, and measurement site from the RFID tag data. Then, the rule engine cleans, converts, and calculates these parameter data according to the preset extraction rules, and compares them with the parameter requirements of the action in the nursing standard library. For example, the extracted body temperature reading "38.5℃" is compared with the standard threshold "36.0℃-37.2℃", and it is found to be beyond the normal range. By iteratively analyzing the key parameters of each nursing action, the rule engine finally obtains a series of quantitative nursing action deviation data to comprehensively evaluate the standardization and accuracy of nursing operations.

[0030] When calculating the nursing action deviation data, the present embodiment adopts a weighted scoring model, taking into account the importance of different key parameters. First, a weight value is assigned to the key parameters of each action in the nursing standard library. The larger the weight, the more important the parameter, and the more serious the corresponding deviation deduction. Then, when the rule engine finds that a certain parameter deviates from the standard value, the deviation deduction of the parameter is calculated according to the degree of deviation and the parameter weight. Finally, all the parameter deviation deductions of an action are added together, and then the total deduction is subtracted from the full score of 100 to obtain the deviation data of the action. The larger the deviation data, the more irregular the action execution, and the more rectification is needed. For example, if the three key parameter deviation deductions of the "measure body temperature" action are 5 points, 2 points, and 3 points respectively, the nursing action deviation data of the action is 90 points, reflecting that there are certain irregularities in the operation.

[0031] S203, parsing the structured information of the radio frequency tag to obtain the actual execution time of each nursing action, and calculating the time deviation data of the nursing action execution according to the actual execution time and the preset standard nursing duration; Specifically, the system first traverses each action in the sequence of nursing actions, and searches for the earliest and latest timestamps corresponding to the action in the structured information of the RFID tag. The earliest timestamp of the action represents its actual start time, and the latest timestamp represents the actual end time. The difference between the two is the actual execution time of the action. For example, by analyzing the RFID tag data of the "oral medication" action, it is found that its earliest timestamp is "2023-05-20 08:05:00" and the latest timestamp is "2023-05-20 08:10:00", from which the actual execution time of the action is 5 minutes. By iteratively calculating the actual execution time of each nursing action, the system finally obtains a complete nursing action execution time data set, which quantitatively reflects the time investment in nursing work.

[0032] After obtaining the actual execution time data, this embodiment further calculates the time deviation data of the nursing action execution according to the actual execution time and the preset standard nursing duration. The reason for analyzing the time deviation is that the execution time of the nursing action is too long or too short, which may mean nursing quality and safety risks. By calculating the degree to which the actual execution time deviates from the standard duration, the level of nursing timeliness can be quantitatively evaluated to provide a basis for time management decisions. For example, if the standard requires the "oral medication" action to be completed within 3 minutes, and the actual execution time is 5 minutes, the time deviation data is +2 minutes, indicating that the execution efficiency of the action is insufficient and the process needs to be optimized and the method needs to be improved.

[0033] When calculating the time deviation data, this embodiment uses a relative deviation value indicator to quantify the degree to which the actual execution time deviates from the standard duration in the form of a percentage. The calculation formula is: Time Deviation Percentage = (Actual Execution Time - Standard Nursing Duration) ÷ Standard Nursing Duration × 100%. A positive deviation percentage indicates that the actual execution time is longer than the standard duration, and a negative deviation indicates that it is shorter than the standard duration. The larger the absolute value of the deviation, the more serious the deviation, and the more attention needs to be paid. By expressing the time deviation data as a percentage, the deviation comparison under different duration scales can be unified, which is convenient for nursing managers to compare the timeliness performance of different nursing actions horizontally and discover common problems. At the same time, the quantification of time deviation data also helps to track the changing trend of nursing timeliness longitudinally and evaluate management effectiveness.

[0034] Based on the above embodiment, as an optional implementation, the high-quality nursing execution deviation data is optimized and refined to obtain best practice data, including: S601, extracting time series data of nursing action execution from the high-quality nursing execution deviation data, and constructing a nursing execution sequence data set based on the time series data; Specifically, after obtaining high-quality nursing execution deviation data, this embodiment further optimizes and refines it, and finally obtains a data set that reflects the best practices of nursing work. The reason for refining high-quality deviation data is that although the original deviation data represents high-quality cases of nursing execution, its internal laws have not yet been highlighted, and its replicability and generalizability are not strong. Through optimization and refinement, it is possible to sort out the implicit common characteristics and key elements in a large number of high-quality deviation data, abstract personalized execution experience and promote it into a universal best practice paradigm, and solidify the core essence of high-quality nursing in a structured, procedural, and standardized digital form, providing a reference model and digital base for the optimization and reconstruction of nursing processes and intelligent decision-making.

[0035] S602, using a sequence pattern mining algorithm to mine the data in the nursing execution sequence data set to obtain frequent subsequence patterns in the nursing execution sequence data set; Specifically, the system uses classic sequence pattern mining algorithms such as PrefixSpan and SPADE to perform frequent subsequence searches on the nursing execution sequence data set in a bottom-up, incremental, recursive and iterative manner. Taking the PrefixSpan algorithm as an example, its core idea is to first determine the frequent "prefix" subsequences, then divide the sequence data set into several "projection databases" according to the prefix, and then recursively mine local frequent sequences in each projection database, and finally merge and summarize the local mining results into a global frequent subsequence pattern set.

[0036] First, the system traverses each sequence in the nursing execution sequence data set, counts the frequency of each atomic nursing event in all sequences, generates a subsequence of length 1 whose frequency reaches the preset minimum support threshold, and uses it as the initial "prefix" subsequence. For example, it is found through statistics that the "hand hygiene" event appears in 95% of the nursing sequences, and the "local skin disinfection" event appears in 90% of the sequences. The frequency of the remaining events is less than 50% of the data set. The system sets the minimum support to 50%, and thus obtains the frequent 1-prefix sequence set {"hand hygiene", "local skin disinfection"}. Next, the system starts the recursive sequence pattern mining with the above frequent 1-prefix sequence as the starting point. For the candidate prefix "hand hygiene", the system extracts all sequences containing the "hand hygiene" subsequence from the original nursing execution sequence data set to form a projection database of "hand hygiene", and searches for frequent events immediately following "hand hygiene" in the projection database, and adds them after "hand hygiene" to form a 2-prefix sequence. For example, if the event "local skin disinfection" also reaches more than 50% support in the projection database of "hand hygiene", a frequent 2-prefix sequence "hand hygiene ➡ local skin disinfection" is generated. Then, for the newly generated 2-prefix sequence, the system forms its corresponding projection database from the original data set again, and recursively mines the subsequent events that can be added after the prefix to form a longer frequent sequence. This iteration continues until no new high-frequency prefix sequences can be extended, and a frequent subsequence pattern mining branch starting from "hand hygiene" is completed. After that, the system selects another frequent 1-prefix such as "local skin disinfection" and repeats the above recursive mining process until all 1-prefix sequences are mined. Finally, the system aggregates the frequent subsequences of different lengths mined from each prefix branch, removes the redundant and included short sequences, and obtains the final frequent subsequence pattern set. For example, if three frequent sequences are mined, namely "hand hygiene ➡ local skin disinfection", "hand hygiene ➡ local skin disinfection ➡ successful puncture", and "hand hygiene ➡ local skin disinfection ➡ successful puncture ➡ catheter fixation", then only the longest one needs to be retained as the typical best practice pattern for this nursing scenario.

[0037] S603, performing cluster analysis on the frequent subsequence patterns to aggregate similar nursing execution patterns into one category; Specifically, the system uses common algorithms such as hierarchical clustering and density clustering to measure similarity and discover clusters for frequent subsequence pattern sets. Taking the BIRCH algorithm in hierarchical clustering as an example, its core idea is to first use a hierarchical clustering feature tree (CF Tree) to pre-cluster frequent subsequences, and then use the hierarchical clustering method again on the pre-clustering results to form the final clusters.

[0038] First, the system traverses the set of frequent subsequences, inserts each subsequence into the leaf node of CF Tree one by one, and dynamically adjusts the structure of the tree so that similar subsequences can be clustered on one node or adjacent nodes as much as possible. In order to measure the similarity between subsequences, a composite similarity function that comprehensively considers the operation type, operation attribute, and operation sequence is designed. For example, for subsequence A "hand hygiene (45 seconds, seven-step hand washing method) ➡ local skin disinfection (1 minute, iodine cotton ball) ➡ successful puncture (20 seconds, one-time puncture)" and subsequence B "hand hygiene (1 minute, six-step hand washing method) ➡ local skin disinfection (90 seconds, alcohol cotton ball) ➡ successful puncture (30 seconds, two-time puncture)", although the key operation steps and sequence are consistent, there are differences in the specific implementation elements of each step, and the calculated similarity is 0.8. Based on this, the system inserts the two subsequences into the nearest leaf node in CFTree respectively, and updates the cluster center coordinates of the leaf node. When the number of subsequences accommodated by a leaf node reaches the set maximum capacity, the system splits the node and divides its subordinate subsequences into two new leaf nodes. This iteration continues until the CF Tree converges and stabilizes. The hierarchical structure of the CF Tree naturally forms a pre-clustering division of frequent subsequences. Subsequences at the same node or adjacent nodes are grouped into a cluster and become candidate clusters for subsequent fine clustering. Next, the system uses the central subsequence of each pre-clustering cluster as a new clustering unit, calculates the similarity between clusters, and gradually merges the two clusters with the highest similarity, continuously generating higher-level clusters until the preset number of clusters or the minimum similarity threshold between clusters is reached. The merging process uses the shortest distance method, that is, the similarity calculated by the two most similar subsequences in the two clusters is taken as the inter-cluster similarity. Finally, the system outputs the set of clusters obtained by the specified level segmentation of the hierarchical clustering tree, and summarizes the frequent subsequences in each cluster to form a nursing execution mode category that reflects the intrinsic characteristics of the cluster. For example, all frequent variations of the "hand hygiene ➡ local skin disinfection ➡ puncture ➡ needle withdrawal and fixation" process are classified into the nursing execution model category of "venous puncture and catheterization". The differences in various subsequences in each operation step reflect the flexible adaptability of this model.

[0039] S604, for each type of nursing execution mode, select the sample with the shortest duration, the least resource consumption, and the highest patient satisfaction as the best practice path for the corresponding category; Specifically, the system selects the best examples from each category as the best practice path for each category based on the categories of nursing execution modes obtained through clustering. The sample screening adopts a multi-indicator weighted scoring mechanism, which comprehensively considers the performance of the samples in key dimensions such as duration, resource consumption, and patient satisfaction, and performs optimal sorting.

[0040] First, the system statistically analyzes all samples under each pattern category formed by clustering, extracts the original nursing execution sequence corresponding to each sample, calculates the resource consumption indicators such as operation duration, number of equipment used, consumable materials, and manpower input of each sequence, and matches and queries the subjective satisfaction score of the corresponding patient for this nursing. Then, each indicator is dimensionless, dimension differences are eliminated, and uniformly mapped to the interval of 0-100. For example, the total operation time of a sample sequence S1 is 15 minutes, ranking 10th among the 100 samples in this category, and the corresponding percentage score is (1-10 / 100) 100=90 points; the number of special care equipment used by S1 is 2, ranking 30th, with a score of 70; the original score of patient satisfaction is 9 points (10 points), which is directly converted to 90 points. Then, the system assigns weights to each indicator to form a weighted scoring model, and weighted sums the scores of each sample to obtain the comprehensive evaluation score of the sample. Assuming that the duration weight is 40%, resource consumption is 30%, and satisfaction is 30%, the comprehensive score of S1 = 9040% + 7030% + 9030% = 84 points. Finally, the system sorts all the samples under each mode category according to the comprehensive score, and the one with the highest score is used as the best practice path for that category. Taking the category where S1 is located as an example, if its 84 points rank first, the complete nursing execution sequence corresponding to S1 is used as the prototype to refine and form the best practice standard process for this category.

[0041] S605, analyzing the influencing factors of the best practice path to obtain the key factors that affect the formation of best practices, and using ontology engineering methods to perform conceptual abstraction and semantic modeling on the best practice path and the key factors to form a best practice knowledge representation, and using the best practice knowledge representation as the best practice data.

[0042] Specifically, the system takes the best practice paths formed by extracting various nursing execution mode categories as the research object, and uses statistical analysis, expert interviews and other methods from the two perspectives of process structure and operation elements to systematically identify the key factors that have a significant impact on the formation of best practices. On this basis, the concept of ontology engineering is used to abstract the best practice paths and their key influencing factors, construct a hierarchical category system, and formalize semantic modeling through attributes, relationships, etc., to finally form the best practice knowledge ontology.

[0043] First, the system conducts an exploration of the influencing factors of each best practice path. On the one hand, the differences between the best path and other similar samples in terms of process link settings, operation element combinations, etc. are compared and analyzed to reveal the uniqueness of the best practice. For example, "hand hygiene" and "infusion reaction observation" are essential links in the best path for intravenous infusion nursing, while ordinary paths may be omitted; the frequency of the "evaluation" link in the best path is higher than that of other solutions, etc. On the other hand, statistical methods such as variable association analysis and factor analysis are used to determine the contribution of each factor to the nursing effect. For example, by performing multiple regression on the nursing operation variables of different examples and dependent variables such as patient satisfaction and complication rate, it is identified that "puncture success rate" is the biggest factor affecting infusion nursing satisfaction. At the same time, nursing experts are invited to check the relevant conclusions, explore the empirical mechanism behind the best practices, and supplement qualitative insights. Comprehensive quantitative and qualitative analysis is used to form a set of key influencing factors for each category of best paths. For example, the key factors of the best path for intravenous infusion include "hand hygiene compliance", "puncture success rate", and "precision of drip rate control". Next, the system uses ontology engineering methods to abstractly model the best practice path and influencing factors. First, core concepts in the best practice areas such as nursing processes, medical devices, and adverse events are selected, and a hierarchical category system is constructed based on the hierarchical relationship between concepts to form an ontology skeleton. For example, "intravenous infusion" belongs to the "therapeutic operation" category, and "indwelling needle" belongs to "invasive equipment". Then, the semantic features of the concepts are formally defined using ontology description languages ​​(such as OWL), with attributes describing the connotation of the concepts and relationships describing the extension of the concepts. For example, the concept attributes of "intravenous infusion" include "frequency", "drip rate", "duration", etc., and there is a positive correlation between "puncture success rate" and "patient satisfaction". Next, the best practice paths of each category are instantiated as specific nodes of the ontology knowledge graph to form a knowledge base rooted in the ontology framework and associated with actual data. For example, the attribute slots of the "best practice of intravenous indwelling needle infusion" instance include "frequency: 1 time / day", "drip rate: 40 drops / minute", and "duration: 1 hour", and are linked to multiple operation link instances such as "aseptic operation" and "check and verify" through the "include" relationship. Finally, the system outputs the ontological best practice knowledge representation into standardized RDF, JSON-LD and other format files, and incorporates them into the best practice data knowledge base.

[0044] S204, taking the time deviation data, the nursing process matching deviation data and the nursing action deviation data as the quantitative analysis result.

[0045] Specifically, after the system completes the calculation of time deviation, process matching deviation and action deviation, it organizes these three types of deviation data into a structured quantitative analysis result data set. This data set takes nursing actions as the basic unit, and each action entry contains three deviation measurement indicators: time deviation percentage, process matching deviation percentage, and action deviation score. Through data integration and fusion, the three types of deviation data form a "trinity" framework for quantitative evaluation of the nursing process, reflecting the execution status of each nursing action in multiple dimensions. For example, by looking at the quantitative analysis results of the "oral medication" action, it is found that its time deviation is +60%, the process matching deviation is 10%, and the action deviation score is 90 points, which comprehensively reflects that the action has major problems in timeliness, and there are certain deviations in standardization and accuracy, which need to be focused on rectification.

[0046] Taking time deviation data, nursing process matching deviation data and nursing action deviation data as quantitative analysis results is a major feature and advantage of this embodiment. Traditional nursing quality assessment often adopts single-dimensional assessment indicators, such as simply assessing the completion rate of nursing three checks and seven pairs, or simply assessing the incidence of adverse events. This one-sided evaluation method easily ignores the complexity and systematic nature of nursing work, and it is difficult to accurately reflect the nursing quality status. However, this embodiment uses three types of deviation data to cross-verify and complement each other, judge the timeliness, standardization and accuracy of nursing action execution from multiple angles, and build a comprehensive and three-dimensional nursing process quantitative analysis framework. Through comprehensive consideration of the results of quantitative analysis, managers can diagnose the crux of problems in nursing work more objectively, accurately and comprehensively, formulate quality improvement measures in a targeted manner, and ultimately achieve accurate control and continuous improvement of nursing quality.

[0047] S103, performing nursing anomaly detection according to the quantitative analysis results, and generating a nursing anomaly detection report.

[0048] Specifically, this embodiment first sets the nursing abnormality judgment standard, and sets the corresponding normal range threshold for different types of quantitative deviation data. For example, the allowable range of time deviation data is ±5 minutes, the allowable range of process matching deviation data is 80%-100%, and the allowable range of action deviation data is 0-0.1, etc. Then, each quantitative analysis result is compared with the threshold, and the data exceeding the threshold range is judged as abnormal data, indicating that the relevant nursing link is unqualified. When implementing abnormality detection, not only whether a single deviation data exceeds the standard is considered, but also the combined characteristics of multiple deviation data are comprehensively analyzed. For example, if multiple deviation data are close to or exceed the upper threshold limit at the same time, although the single deviation may not constitute an abnormality, it may mean that there are systemic risks in the nursing process, which needs to be paid great attention. By setting flexible abnormality judgment rules and combining cross-analysis of data, various abnormal situations in the nursing process can be fully revealed.

[0049] According to the abnormal detection situation, this embodiment automatically generates a nursing abnormality detection report, lists the detected abnormal data, analyzes the time, location, personnel, cause, etc. of the abnormality, evaluates the degree of harm and scope of impact of the abnormality, and puts forward rectification opinions and disposal suggestions. By timely generating and pushing abnormal detection reports, managers can quickly, accurately and comprehensively grasp the abnormal nursing situation, provide a reference basis for abnormal disposal decisions, thereby minimizing the risk of nursing abnormalities and ensuring the safety and quality of nursing.

[0050] Based on the above embodiment, as an optional embodiment, nursing anomaly detection is performed according to the quantitative analysis result to generate a nursing anomaly detection report, including: According to the abnormal data exceeding the preset deviation threshold in the time deviation data, the nursing process matching deviation data and the nursing action deviation data in the quantitative analysis result, and based on the abnormal data, an abnormal analysis is performed to generate the nursing abnormality detection report.

[0051] Specifically, first, the time deviation data, nursing process matching deviation data and nursing action deviation data are screened one by one against the pre-set deviation threshold. The deviation threshold is a critical value used to define the boundary between normal and abnormal deviation data. For example, the time deviation threshold can be set to ±20%, the process matching deviation threshold to 15%, and the action deviation score threshold to 85 points. When the deviation data of a nursing action exceeds the corresponding threshold, it is marked as abnormal data. Through comprehensive scanning and quantitative analysis results, the system finally screens out a series of time anomalies, process anomalies, and action anomalies data. These abnormal data are like the "physical examination report" of the nursing execution process, which intuitively reflects the weak links and risk points of nursing work.

[0052] After obtaining the abnormal data, this embodiment further conducts abnormal analysis based on the abnormal data and generates a nursing abnormality detection report. The system first performs cluster analysis on the abnormal data according to multiple dimensions such as nursing actions, time, place, and personnel, and identifies the common characteristics and laws of the abnormal data. For example, it is found that the abnormal data is highly concentrated under specific conditions such as night shifts, ICU wards, and newly hired nurses. Then, the system uses intelligent algorithms such as association rule mining and causal analysis to discover the inherent connections between abnormal events from the abnormal data and explore the deep-seated causes of the abnormalities. For example, through analysis, it is found that fatigue of night shift nurses and sudden changes in the condition of critically ill patients are the main reasons for the high incidence of abnormalities. Finally, the system summarizes the results and findings of various abnormal analysis into a nursing abnormality detection report, which not only lists the detection of various types of nursing abnormalities, but also explains the common laws, cause analysis, and improvement suggestions of abnormal data, providing decision-making references for nursing quality and safety management.

[0053] Based on the above embodiment, as an optional embodiment, the nursing management method based on radio frequency identification further includes the following steps: S301, performing association rule mining on the quantitative analysis results to obtain deviation data association rules; Specifically, the system first preprocesses the data of the quantitative analysis results, discretizes continuous variables such as time deviation, process matching deviation, and action deviation into categorical variables, and cleans noise data such as missing values ​​and outliers to make the data set adapt to the input requirements of the association rule mining algorithm. Then, based on the improved Apriori association rule algorithm, the system iteratively searches for frequent item sets and association rules from the preprocessed data set. The so-called frequent item set refers to the combination pattern of deviation data that appears simultaneously in the data set; and the association rule reveals the correlation and causality between the deviation data in the frequent item set. For example, through mining, it is found that "time deviation during the night shift and the action deviation of new nurses often appear at the same time", and this association rule reflects the rule that new nurses are more likely to have abnormal nursing actions during the night shift. Finally, the system evaluates and screens the mined association rules according to indicators such as support and confidence, and outputs the significant association rules with high support and strong confidence as deviation data association rules.

[0054] S302, extracting the time deviation data, the nursing process matching deviation data and the nursing action deviation data in the quantitative analysis result, and determining high-quality nursing execution deviation data whose deviation is less than a preset deviation threshold among the time deviation data, the nursing process matching deviation data and the nursing action deviation data; Specifically, the system first extracts the time deviation data, nursing process matching deviation data and nursing action deviation data in the quantitative analysis result data set to form a nursing execution deviation data subset. Then, the system compares the preset high-quality deviation threshold to determine whether each deviation data meets the high-quality standard. The so-called high-quality deviation threshold refers to the critical value of defining the deviation data as high-quality nursing execution. For example, the high-quality threshold of time deviation data can be set to ±5%, that is, only when the time deviation is within ±5% can it be identified as high-quality nursing; the high-quality thresholds of process matching deviation and action deviation can be set to 5% and 95 points respectively. After a comprehensive scan and comparison of the deviation data subset, the system finally determines the data that meets the conditions of "time deviation <5% and process matching deviation <5% and action deviation >95 points", and marks it as high-quality nursing execution deviation data. These data represent the masterpiece of nursing work, are the concentrated embodiment of the professional quality and professionalism of the nursing team, and are the benchmark and example of nursing quality.

[0055] S303, optimizing and refining the high-quality nursing execution deviation data to obtain best practice data, and building a nursing service best practice knowledge base based on the best practice data; Specifically, the system first classifies and summarizes the quality nursing execution deviation data according to different dimensions such as departments, patients, and nursing projects, and uses statistics such as mean and median to characterize the overall characteristics of each category to remove the interference of outliers. Then, the system uses intelligent algorithms such as sequence pattern mining and frequent subgraph mining to automatically identify common patterns with high frequency and strong stability from the quality deviation sequences of each category, and define them as the best practice sequences of this category. For example, through mining, it was found that "the time deviation and matching deviation of the quality intravenous infusion process are usually kept within 3%, and the action deviation score is stable above 98 points." This best practice model reflects the highest standard of intravenous infusion care. Finally, the system systematically integrates the best practice data extracted from each category, builds a structured and standardized nursing service best practice knowledge base, and forms a searchable, callable, and popularizable quality nursing knowledge resource library.

[0056] S304, optimizing the preset nursing standard based on the nursing service best practice knowledge base, the quantitative analysis result and the deviation data association rule to obtain a target nursing standard.

[0057] Specifically, the system first extracts the structural framework of the preset nursing standards, and maps and aligns data sources such as the best practice knowledge base, quantitative analysis results, and deviation data association rules with it to construct an initial matrix for multi-source data fusion. Then, the system uses machine learning algorithms such as alternating least squares regression and random forest to train the association model between each data source and the preset standard from the initial matrix, and corrects and improves the preset standard based on the model coefficient. For example, if the deviation data association rule shows that "new nurses during the night shift are more likely to have abnormal infusion", the system will automatically increase the infusion standard threshold for night shifts and new nurses, and strengthen the quality control of key time periods and personnel. At the same time, the system will also refer to the quantitative analysis results and the best practice knowledge base, simulate and test the revised standards, and continuously iterate and optimize to form the final target nursing standards.

[0058] Based on the above embodiment, as an optional embodiment, the nursing management method based on radio frequency identification further includes the following steps: S401, determining the nursing staff's work trajectory and nursing task execution status based on the radio frequency tag structured information; Specifically, the system first extracts the spatiotemporal data such as the nursing staff ID, timestamp, and geographic location from the structured information of the radio frequency tag, and constructs the spatiotemporal sequence of each nursing staff's activities in the hospital. Then, the system matches and maps the spatiotemporal sequence with the geographic information of each department and functional area in the hospital, automatically identifies the duration and frequency of the nursing staff's stay in each area, and forms a "personnel-time-place" triple label to intuitively present the work trajectory of each nurse. At the same time, the system will also associate the trajectory label with the nursing task plan, execution record and other data to accurately depict the specific nursing work content of each nurse at different times and places, quantitatively evaluate the completion progress and overtime of each nursing task, and finally form a panoramic view of nursing work that integrates the multi-dimensional information of "personnel-time-place-task". For example, through analysis, it was found that "Nurse Zhang stayed in the cardiology ward from 10:00 to 10:30 that day, completed the vital sign measurement of 2 myocardial infarction patients and 1 postoperative dressing change task", and the manager can clearly grasp the work situation of Nurse Zhang in the morning.

[0059] S402, determining the capability profile of each staff member according to the nursing staff's work trajectory and the nursing task execution status; Specifically, the system first extracts efficiency indicators such as time utilization and path simplification from the work trajectory information of the nursing staff, and extracts quality indicators such as timely completion rate and patient satisfaction from the task execution situation. It performs dimensionless standardization on each indicator from the two dimensions of "fast" and "good", and constructs the initial feature matrix of the individual ability of the nursing staff. Then, the system uses dimensionality reduction algorithms such as principal component analysis and factor analysis to automatically screen out the key factors that contribute the most to individual ability from the high-dimensional feature matrix, and calculates and optimizes the weight coefficients of each factor, and finally forms a set of individual ability portrait models covering multiple dimensions such as communication and coordination, plan execution, and emergency handling. Using this model, the system automatically scores and grades each key ability of each nursing staff, forming a quantitative and intuitive ability portrait radar chart to comprehensively characterize their ability performance. For example, after system analysis and evaluation, Nurse Zhang's communication and coordination ability score is 95 points, plan execution ability score is 90 points, and emergency handling ability score is 85 points. This result clearly reflects that Nurse Zhang has strong planning and outstanding communication skills, but her emergency handling ability needs to be improved.

[0060] S403, optimizing the shift schedule based on the capability profile of each staff member.

[0061] Specifically, the system first decomposes the nursing work tasks in fine granularity, and based on the main requirements of each subtask for the nurses' ability and quality, it profiles the tasks from the dimensions of communication and coordination, plan execution, and emergency handling, forming a "task-ability" demand matrix. Then, the system performs similarity matching analysis on the demand matrix and the nursing staff's ability portrait, and uses combined optimization methods such as the Hungarian algorithm and the ant colony algorithm to automatically generate the optimal personnel combination and task division plan for each shift on the basis of fully considering the hard constraints such as statutory working hours and rest time. For example, for emergency tasks such as sudden cardiac arrest, the system will give priority to matching nurses with higher emergency response ability scores, while for routine tasks such as patient health education, the system will give priority to matching nurses with outstanding communication and coordination skills. At the same time, the system will also dynamically adjust the task division within the shift according to the complementarity of the nurses' abilities in each shift, and promote complementary advantages and teamwork. In addition, the system also supports the continuous optimization of the scheduling plan based on the feedback data of the actual operation situation using the reinforcement learning algorithm, and continuously improves the scientificity and flexibility of the scheduling.

[0062] See also Figure 2 , Figure 2 An architecture diagram of a radio frequency identification-based nursing management system provided in an embodiment of the present application, the radio frequency identification-based nursing management system may include: The data processing module 1 is used to obtain the radio frequency tag information entering the working range, and perform structured processing on the radio frequency tag information to obtain radio frequency tag structured information; Quantification module 2, used for quantitatively analyzing the structured information of the radio frequency tag based on the preset nursing standard, and obtaining the quantitative analysis results reflecting the execution of the nursing process, wherein the quantitative analysis results include: time deviation data, nursing process matching deviation data and nursing action deviation data; The anomaly detection module 3 is used to perform nursing anomaly detection according to the quantitative analysis results and generate a nursing anomaly detection report.

[0063] It should be noted that: when the system provided in the above embodiment realizes its functions, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0064] Please refer to Figure 3 The application also discloses an electronic device. Figure 3The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302 or end-to-end wireless communication.

[0065] The communication bus 302 is used to realize the connection and communication between these components.

[0066] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0067] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0068] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field~Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0069] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read~Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally be at least one storage system located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program of a nursing management method based on radio frequency identification.

[0070] exist Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application of the nursing management method based on radio frequency identification stored in the memory 305. When executed by one or more processors 301, the electronic device 300 executes one or more methods in the above-mentioned embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application. In the above embodiments, the description of each embodiment has its own emphasis. For the parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0071] In the several implementations provided in this application, it should be understood that the disclosed system can be implemented in other ways. For example, the system embodiments described above are only schematic, such as the division of modules, which is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, indirect coupling or communication connection of systems or modules, which can be electrical or other forms.

[0072] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0073] The present application also provides a computer storage medium that can store multiple instructions, which are suitable for being loaded and executed by a processor as described above. Figure 1 The nursing management method based on radio frequency identification in the embodiment shown in the figure can be found in the specific execution process. Figure 1 The specific description of the illustrated embodiment will not be repeated here.

[0074] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or software functional modules.

[0075] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0076] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0077] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A nursing management method based on radio frequency identification, characterized in that: The method comprises: Acquire the radio frequency tag information that enters the working range, and perform structured processing on the radio frequency tag information to obtain radio frequency tag structured information; Based on the preset nursing standards, the structured information of the radio frequency tag is quantitatively analyzed to obtain a quantitative analysis result reflecting the execution of the nursing process, wherein the quantitative analysis result includes: time deviation data, nursing process matching deviation data and nursing action deviation data; Perform nursing anomaly detection based on the quantitative analysis results and generate a nursing anomaly detection report; Performing association rule mining on the quantitative analysis results to obtain deviation data association rules; Extracting the time deviation data, the nursing process matching deviation data and the nursing action deviation data from the quantitative analysis result, and determining high-quality nursing execution deviation data whose deviation is less than a preset deviation threshold among the time deviation data, the nursing process matching deviation data and the nursing action deviation data; Optimizing and refining the quality nursing execution deviation data to obtain best practice data, and building a nursing service best practice knowledge base based on the best practice data; Optimizing the preset nursing standard based on the nursing service best practice knowledge base, the quantitative analysis results and the deviation data association rules to obtain a target nursing standard; Determine the nursing staff's work trajectory and nursing task execution status based on the radio frequency tag structured information; Determine the capability profile of each staff member according to the nursing staff's work trajectory and the nursing task execution status; The shift schedule is optimized based on the capability profile of each staff member.

2. The method according to claim 1, characterized in that The quantitative analysis of the radio frequency tag structured information based on the preset nursing standard to obtain the quantitative analysis results reflecting the execution status of the nursing process includes: The radio frequency tag structured information is parsed by a preset nursing process engine to obtain a nursing action sequence, and the nursing action sequence is matched with a preset standard nursing process to obtain nursing process matching deviation data; The radio frequency tag structured information is parsed by a preset rule engine to obtain key parameters of each nursing action, and the key parameters are compared with the preset action threshold to obtain nursing action deviation data; Parsing the radio frequency tag structured information to obtain the actual execution time of each nursing action, and calculating the time deviation data of the nursing action execution according to the actual execution time and the preset standard nursing duration; The time deviation data, the nursing process matching deviation data and the nursing action deviation data are used as the quantitative analysis results.

3. The method according to claim 1, characterized in that The performing of nursing anomaly detection according to the quantitative analysis result and generating a nursing anomaly detection report includes: According to the abnormal data exceeding the preset deviation threshold in the time deviation data, the nursing process matching deviation data and the nursing action deviation data in the quantitative analysis result, and based on the abnormal data, an abnormal analysis is performed to generate the nursing abnormality detection report.

4. The method according to claim 1, characterized in that The performing association rule mining on the quantitative analysis results to obtain deviation data association rules includes: Adopting an association rule mining algorithm to determine the high-frequency deviation data combination pattern in the quantitative analysis result data to form a frequent deviation item set; Based on the frequent deviation item set, the confidence of each high-frequency deviation data combination pattern is calculated, and according to a preset minimum confidence threshold, the high-frequency deviation data combination pattern with high confidence is screened out, and association rules are extracted for the high-frequency deviation data combination pattern with high confidence to obtain the deviation data association rule.

5. The method according to claim 1, characterized in that The optimization and refinement of the quality care execution deviation data to obtain best practice data includes: Extracting time series data of nursing action execution from the high-quality nursing execution deviation data, and constructing a nursing execution sequence data set based on the time series data; Using a sequence pattern mining algorithm to mine the data in the nursing execution sequence data set to obtain frequent subsequence patterns in the nursing execution sequence data set; Performing cluster analysis on the frequent subsequence patterns to aggregate similar nursing execution patterns into one category; For each type of nursing execution mode, select the sample with the shortest duration, the least resource consumption, and the highest patient satisfaction as the best practice path for the corresponding category; An influencing factor analysis is performed on the best practice path to obtain key factors that affect the formation of best practices, and ontology engineering methods are used to conceptually abstract and semantically model the best practice path and the key factors to form a best practice knowledge representation, and the best practice knowledge representation is used as the best practice data.

6. A nursing management system based on radio frequency identification, characterized in that: The system comprises: A data processing module is used to obtain the radio frequency tag information entering the working range, and perform structured processing on the radio frequency tag information to obtain radio frequency tag structured information; A quantification module is used to perform quantitative analysis on the structured information of the radio frequency tag based on a preset nursing standard to obtain a quantitative analysis result reflecting the execution of the nursing process, wherein the quantitative analysis result includes: time deviation data, nursing process matching deviation data and nursing action deviation data; An anomaly detection module is used to perform nursing anomaly detection according to the quantitative analysis results and generate a nursing anomaly detection report; perform association rule mining on the quantitative analysis results to obtain deviation data association rules; Extracting the time deviation data, the nursing process matching deviation data and the nursing action deviation data from the quantitative analysis result, and determining high-quality nursing execution deviation data whose deviation is less than a preset deviation threshold among the time deviation data, the nursing process matching deviation data and the nursing action deviation data; Optimizing and refining the quality nursing execution deviation data to obtain best practice data, and building a nursing service best practice knowledge base based on the best practice data; Optimizing the preset nursing standard based on the nursing service best practice knowledge base, the quantitative analysis results and the deviation data association rules to obtain a target nursing standard; Determine the nursing staff's work trajectory and nursing task execution status based on the radio frequency tag structured information; Determine the capability profile of each staff member according to the nursing staff's work trajectory and the nursing task execution status; The shift schedule is optimized based on the capability profile of each staff member.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 5.

8. An electronic device, characterized in that: It includes a processor, a memory and a transceiver, the memory is used to store instructions, the transceiver is used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method according to any one of claims 1 to 5.

Images