Nursing service process dynamic scheduling method based on big data processing

Abstract

The present application relates to the medical care technical field, disclose a kind of nursing service process dynamic scheduling method based on big data processing, comprising the following steps: the demand information of current nursing service scene is collected, based on the demand information, identify the service scene with the commonality of this scene and differentiating service scene, based on the commonality service scene identified, its resource allocation condition is summarized to form resource configuration condition set;To commonality service scene, its service demand sequence data and resource configuration time series data are divided according to preset historical period, the correlation coefficient of two groups of sequences is calculated, generate first dynamic correlation index;From differentiating service scene, match out historical difference case, after calculating the correlation coefficient of the demand and resource configuration trend change of corresponding case before and after the same period, generate second dynamic correlation index.The present application makes resource reasonable configuration and scientific scheduling, can reduce the uneven problem of nurse work load.

Description

Technical Field

[0001] This invention relates to the field of medical and nursing technology, and in particular to a method for dynamic scheduling of nursing service processes based on big data processing. Background Technology

[0002] In modern healthcare systems, nursing services are a crucial link in ensuring patient recovery and improving the quality of medical care. However, nursing scenarios are complex and diverse, and patients' conditions and nursing needs change dynamically. Scenario such as postoperative rehabilitation, chronic disease management, and emergency care have vastly different requirements for manpower, equipment, and supplies. It is difficult for humans to accurately predict resource allocation, often resulting in a situation where resources are both idle and scarce. For example, in high-demand scenarios like the ICU, resources are scarce, while in ordinary wards, there is a waste of nursing manpower, leading to low nursing efficiency and affecting patient treatment and experience.

[0003] Traditional scheduling does not make full use of big data analysis and cannot extract demand-resource allocation patterns from historical scenarios. It is difficult to quickly reuse experience and optimize strategies when facing similar or different scenarios, resulting in delayed scheduling decisions and difficulty in adapting to nursing requirements. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a dynamic scheduling method for nursing service processes based on big data processing, which can solve the problems of traditional scheduling not making full use of big data analysis, failing to extract demand-resource allocation patterns from historical scenarios, and being unable to quickly reuse experience and optimize strategies in the face of similar or different scenarios, resulting in delayed scheduling decisions and difficulty in adapting to nursing requirements.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a method for dynamic scheduling of nursing service processes based on big data processing, comprising the following steps:

[0008] Collect demand information for the current nursing service scenario; based on the demand information, identify service scenarios that are common to the current scenario and service scenarios that are different from the current scenario; based on the identified common service scenarios, summarize their resource allocation status to form a resource configuration status set.

[0009] For common service scenarios, the service demand sequence data and resource allocation time series data are divided according to preset historical time periods, the correlation coefficient between the two sets of sequences is calculated, and the first dynamic correlation index is generated.

[0010] By matching historical difference cases from the difference service scenarios, calculating the correlation coefficient of the change in demand and resource allocation trends of the corresponding cases before and after the same period, a second dynamic correlation indicator is generated.

[0011] A dynamic scheduling prediction model for nursing services is constructed based on the resource allocation status set, the first dynamic correlation index, and the second dynamic correlation index, generating a set of predicted scheduling schemes that includes overlapping schemes and differential schemes.

[0012] The differences in the predicted scheduling scheme set are verified based on the first and second dynamic correlation indicators. An optimized scheduling scheme is generated and integrated with the overlapping schemes to output the final scheduling decision.

[0013] As a preferred embodiment of the dynamic scheduling method for nursing service processes based on big data processing described in this invention, the resource allocation status is summarized to form a resource configuration status set, specifically including the following steps:

[0014] After extracting at least two scheduling scenarios with independent nursing characteristics from the current nursing service scenario based on nursing demand information, the first structured scheduling scenario set is output.

[0015] The resource allocation status of corresponding nursing services is obtained based on the characteristic information of each scheduling scenario in the first structured scheduling scenario set;

[0016] The resource allocation status of common service scenarios is statistically analyzed, and the resource allocation status set is obtained by statistically analyzing the configuration characteristics of sparse and dense nursing resource allocation scenarios based on the resource allocation status.

[0017] As a preferred embodiment of the dynamic scheduling method for nursing service processes based on big data processing described in this invention, a first dynamic correlation index is generated after calculating the correlation coefficient of the changes in service demand and resource allocation trends of common service scenarios before and after a preset historical period. This specifically includes the following steps:

[0018] Obtain feature information of historically similar scenarios and resource configuration feature information of historically similar scenarios in common service scenarios before a preset historical time period;

[0019] The first scenario change difference trend value is obtained by processing and analyzing the feature information of historical similar scenarios, and the first resource allocation change difference trend value is obtained by processing and analyzing the resource allocation feature information of historical similar scenarios.

[0020] Extract the first dynamic correlation index between the trend value of the first scenario change difference and the trend value of the first resource allocation change difference.

[0021] As a preferred embodiment of the dynamic scheduling method for nursing service processes based on big data processing described in this invention, the method involves processing and analyzing historical similar scenario feature information to obtain a first scenario change difference trend value, and processing and analyzing historical similar scenario resource allocation feature information to obtain a first resource allocation change difference trend value. Specifically, this includes the following steps:

[0022] Extract the actual similar scene features that have changed after a preset historical time period;

[0023] Extract the actual similar scene resource configuration feature information that changes after a preset historical time period;

[0024] Calculate the trend value of the first scene change difference between the feature information of the actual similar scene and the feature information of the historical similar scene;

[0025] Calculate the first resource allocation change difference trend value between the resource allocation feature information of actual similar scenarios and the resource allocation feature information of historical similar scenarios.

[0026] As a preferred embodiment of the dynamic scheduling method for nursing service processes based on big data processing described in this invention, matching historical difference cases from difference service scenarios specifically includes the following steps:

[0027] Obtain all service cases in the differentiated service scenarios that are scheduled;

[0028] Based on the service cases of different scenarios, historical cases with the same resource configuration feature information in the different service scenarios and the common service scenarios are selected.

[0029] As a preferred embodiment of the dynamic scheduling method for nursing service processes based on big data processing described in this invention, a second dynamic correlation index is generated after calculating the correlation coefficient of the changes in demand and resource allocation trends of corresponding cases before and after the same time period. This specifically includes the following steps:

[0030] Obtain the historical difference scenario feature information and historical difference scenario resource configuration feature information to which the historical difference cases belong;

[0031] The characteristic information of historical difference scenarios is processed and analyzed to obtain the trend value of the second scenario change difference, and the characteristic information of resource allocation in historical difference scenarios is processed and analyzed to obtain the trend value of the second resource allocation change difference.

[0032] Extract a second dynamic correlation index between the trend value of the second scenario change difference and the trend value of the second resource allocation change difference.

[0033] As a preferred embodiment of the dynamic scheduling method for nursing service processes based on big data processing described in this invention, the method involves processing and analyzing historical difference scenario feature information to obtain a second scenario change difference trend value, and processing and analyzing historical difference scenario resource allocation feature information to obtain a second resource allocation change difference trend value. Specifically, this includes the following steps:

[0034] The statistical analysis of historical differences in scene characteristics shows the actual changes in scene characteristics over a preset historical time period.

[0035] The actual resource allocation characteristics of the statistically differentiated scenarios are analyzed after a preset historical time period, showing how these characteristics have changed.

[0036] Calculate the trend value of the second scene change difference between the actual difference scene feature information and the historical difference scene feature information;

[0037] Calculate the second resource allocation change trend value between the actual difference scenario resource allocation feature information and the historical difference scenario resource allocation feature information.

[0038] As a preferred embodiment of the dynamic scheduling method for nursing service processes based on big data processing described in this invention, a dynamic scheduling prediction model for nursing services is constructed based on a resource allocation status set, a first dynamic correlation index, and a second dynamic correlation index, generating a set of predicted scheduling schemes that includes overlapping and differing schemes. Specifically, the method includes the following steps:

[0039] A dynamic scheduling and prediction model for nursing services is constructed based on the resource allocation status set, the first dynamic correlation index, and the second dynamic correlation index.

[0040] Obtain the feature information set of the predetermined scheduling scheme for each scheduling scenario in the first structured scheduling scenario set;

[0041] The second structured scheduling scenario set is obtained by inputting the feature information set of the predetermined scheduling scheme and the resource allocation status into the dynamic scheduling prediction model of nursing services.

[0042] The second set of structured scheduling scenarios is compared with the first set of structured scheduling scenarios to extract overlapping and different schemes.

[0043] As a preferred embodiment of the dynamic scheduling method for nursing service processes based on big data processing described in this invention, the method verifies the differences in the predicted scheduling scheme set based on the first dynamic correlation index and the second dynamic correlation index, generates an optimized scheduling scheme, integrates it with overlapping schemes, and outputs the final scheduling decision. Specifically, the method includes the following steps:

[0044] The first dynamic correlation index predicts the degree of loss of nursing service resources in the differential scheme and outputs the first resource loss dataset.

[0045] Based on the second dynamic correlation index, the degree of loss of nursing service resources in the differential scheme is predicted and the second resource loss dataset is output.

[0046] The first resource depletion dataset and the second resource depletion dataset are sorted in ascending order of numerical values ​​to obtain the depletion ranking result.

[0047] After selecting the nursing service scheduling schemes corresponding to the differential scheduling scenarios from the loss degree ranking results, the verification nursing service scheduling scheme part is output.

[0048] The dynamic scheduling result of nursing services is obtained by integrating the verification of the nursing service scheduling scheme and the overlapping scheme into the nursing service resource scheduling and distribution scheme.

[0049] In a second aspect, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the dynamic scheduling method for nursing service processes based on big data processing.

[0050] Compared with existing technologies, the beneficial effects of this invention are as follows: In optimizing resource allocation, this invention collects nursing needs, identifies similar and different scenarios, and statistically analyzes resource allocation to construct a resource allocation status set, enabling insights into resource demand patterns in different scenarios (such as sparse and dense nursing resource scenarios). Utilizing dynamic correlation indicators, the model can predict the matching trend between resources and needs. For example, the first dynamic correlation indicator mines the relationship between needs and resource allocation in similar scenarios, while the second dynamic correlation indicator focuses on the characteristics of different scenarios. This shifts the allocation of resources such as manpower and equipment from experience-driven to data-driven, reducing resource idleness or overload, improving resource utilization, and alleviating the problem of nursing resource shortages. By verifying differentiated solutions through dual dynamic correlation indicators, resource losses are quantified and the optimal solution is selected, ensuring that scheduling schemes meet both common needs and individual scenarios. Dynamic scheduling can be optimized in real time according to scenario changes, responding promptly to patient needs. Simultaneously, reasonable resource allocation and scientific scheduling can reduce uneven workloads for nurses, improve their work experience, allow them to focus more on patient care, thereby enhancing patient satisfaction and promoting a positive nurse-patient relationship. Attached Figure Description

[0051] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 This is a schematic diagram illustrating the dynamic scheduling method for nursing service processes based on big data processing proposed in this invention;

[0053] Figure 2 This is a schematic diagram illustrating the steps in the dynamic scheduling method for nursing service processes based on big data processing proposed in this invention to obtain a resource allocation status set;

[0054] Figure 3 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention.

[0055] 610. Processor; 620. Communication interface; 630. Memory; 640. Communication bus. Detailed Implementation

[0056] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0057] Example 1, referring to Figures 1-3 This is the first embodiment of the present invention, which provides a method for dynamic scheduling of nursing service processes based on big data processing, including the following steps:

[0058] Collect demand information for the current nursing service scenario; based on the demand information, identify service scenarios that are common to the current scenario and service scenarios that are different from the current scenario; based on the identified common service scenarios, summarize their resource allocation status to form a resource configuration status set.

[0059] For common service scenarios, the service demand sequence data and resource allocation time series data are divided according to preset historical time periods, the correlation coefficient between the two sets of sequences is calculated, and the first dynamic correlation index is generated.

[0060] By matching historical difference cases from the difference service scenarios, calculating the correlation coefficient of the change in demand and resource allocation trends of the corresponding cases before and after the same period, a second dynamic correlation indicator is generated.

[0061] A dynamic scheduling prediction model for nursing services is constructed based on the resource allocation status set, the first dynamic correlation index, and the second dynamic correlation index, generating a set of predicted scheduling schemes that includes overlapping schemes and differential schemes.

[0062] The differences in the predicted scheduling scheme set are verified based on the first and second dynamic correlation indicators. An optimized scheduling scheme is generated and integrated with the overlapping schemes to output the final scheduling decision.

[0063] This application focuses on current nursing service scenarios, collecting nursing demand information, covering patient conditions, nursing procedures, and required manpower and resources. Based on this demand information, common service scenarios (scenarios with similar past nursing needs and processes) and differentiated service scenarios (scenarios with significantly different needs and characteristics) are identified. Simultaneously, the resource allocation status of manpower (number of nurses, qualifications, etc.) and resources (equipment, medicines, etc.) in common service scenarios is statistically analyzed, and the patterns and characteristics of resource allocation under different scenarios are summarized to form a resource allocation status set, providing basic data support for subsequent scheduling.

[0064] For common service scenarios, a preset historical time period is selected, and service demand change data and resource allocation trend data for similar scenarios before and after that period are extracted. The correlation between demand changes and resource allocation adjustments is analyzed, the dynamic relationship between the two is quantified, and a first dynamic correlation index is generated to reflect the adaptation pattern of demand-resource allocation under similar scenarios.

[0065] Starting with differentiated service scenarios, historical cases that are related to the current differentiated scenario in terms of basic characteristics are screened out through case matching technology. Similarly, for the same period, the changes in demand and resource allocation trends in these cases are analyzed, and the correlation coefficient between the two is calculated to generate a second dynamic correlation index. This uncovers the special correlation logic between demand and resource allocation under differentiated scenarios and supplements scheduling reference dimensions not covered by similar scenarios.

[0066] The model integrates resource allocation status sets, first dynamic correlation indicators, and second dynamic correlation indicators as input. A dynamic scheduling prediction model for nursing services is constructed using machine learning algorithms. The model learns the correspondence between demand, resources, and scheduling schemes in historical scenarios and generates a set of predicted scheduling schemes based on current scenario data. Among these, overlapping schemes are scheduling strategies that the model determines are general and adaptable across different scenarios; differentiated schemes are strategies that require further verification and optimization to address specific needs in the current scenario, thus covering both routine and special nursing scheduling requirements.

[0067] The first and second dynamic correlation indicators are used to validate the differential scheduling schemes in the predicted scheduling scheme set. Based on the demand-resource correlation patterns reflected by the indicators, the performance of the differential schemes in terms of resource utilization efficiency and nursing demand satisfaction is evaluated, and the schemes are optimized and adjusted to generate more realistic optimized scheduling schemes. The optimized differential schemes are integrated with overlapping schemes, and factors such as reasonable resource allocation and smooth nursing processes are comprehensively considered to output the final nursing service scheduling decision, guiding the actual nursing work and achieving dynamic and precise scheduling.

[0068] This method is based on big data collection and analysis. It uses correlation indicators to explore the relationship between demand and resource allocation, generates solutions with the help of predictive models, and then verifies and optimizes the output decisions. This allows nursing scheduling to adapt to dynamically changing service demands and improves the efficiency of nursing work.

[0069] The resource allocation status is summarized to form a resource allocation status set, which includes the following steps:

[0070] After extracting at least two scheduling scenarios with independent nursing characteristics from the current nursing service scenario based on nursing demand information, the first structured scheduling scenario set is output.

[0071] The resource allocation status of corresponding nursing services is obtained based on the characteristic information of each scheduling scenario in the first structured scheduling scenario set;

[0072] The resource allocation status of common service scenarios is statistically analyzed, and the resource allocation status set is obtained by statistically analyzing the configuration characteristics of sparse and dense nursing resource allocation scenarios based on the resource allocation status.

[0073] This application extracts at least two scheduling scenarios with independent nursing characteristics from current nursing service scenarios based on nursing demand information. Based on the characteristic information of each scheduling scenario in this set, it analyzes the actual resource allocation of the corresponding nursing services, clarifying how human, material, and other resources are allocated in each scenario. It statistically analyzes these resource allocation statuses of common service scenarios, distinguishing between sparse and dense nursing resource configuration scenarios according to the density of resource allocation. It then summarizes the configuration characteristics of each type of scenario, ultimately integrating this information to form a resource configuration status set. This provides accurate and detailed resource configuration data references for subsequent dynamic scheduling of nursing services, enabling scheduling to allocate resources according to the resource demand characteristics of different scenarios.

[0074] After calculating the correlation coefficient between the changes in service demand and resource allocation trends in common service scenarios before and after a preset historical period, a first dynamic correlation indicator is generated, which specifically includes the following steps:

[0075] Obtain feature information of historically similar scenarios and resource configuration feature information of historically similar scenarios in common service scenarios before a preset historical time period;

[0076] The first scenario change difference trend value is obtained by processing and analyzing the feature information of historical similar scenarios, and the first resource allocation change difference trend value is obtained by processing and analyzing the resource allocation feature information of historical similar scenarios.

[0077] Extract the first dynamic correlation index between the trend value of the first scenario change difference and the trend value of the first resource allocation change difference.

[0078] In order to explore the dynamic correlation of common service scenarios in the time dimension, this application needs to obtain two types of basic information about common service scenarios before a preset historical time period, namely, the feature information of historical similar scenarios and the resource configuration feature information of historical similar scenarios.

[0079] These two types of historical information are processed and analyzed separately. For historically similar scene feature information, we track its actual changes after a preset historical time period. By comparing the features before and after the changes, we calculate the first scene change trend value, which reflects the direction and magnitude of scene feature changes over time. Similarly, for historically similar scene resource allocation feature information, we observe its actual changes after that time period and calculate the first resource allocation change trend value, reflecting the dynamic adjustment of resource allocation.

[0080] To clarify the relationship between service demand and resource allocation trends, we extract the relationship between the trend value of the first scenario change difference and the trend value of the first resource allocation change difference. We then use the first dynamic correlation index to quantify this relationship. This allows us to understand how demand changes and resource allocation adjustments influence and relate to each other in common service scenarios. This provides crucial correlation data support for the subsequent dynamic scheduling model of nursing services, helping to more accurately predict and optimize scheduling strategies.

[0081] The process involves processing and analyzing historical similar scene feature information to obtain the first scene change difference trend value, and processing and analyzing historical similar scene resource allocation feature information to obtain the first resource allocation change difference trend value. Specifically, this includes the following steps:

[0082] Extract the actual similar scene features that have changed after a preset historical time period;

[0083] Extract the actual similar scene resource configuration feature information that changes after a preset historical time period;

[0084] Calculate the trend value of the first scene change difference between the feature information of the actual similar scene and the feature information of the historical similar scene;

[0085] Calculate the first resource allocation change difference trend value between the resource allocation feature information of actual similar scenarios and the resource allocation feature information of historical similar scenarios.

[0086] This application tracks the changes of two core dimensions in historically similar nursing scenarios over a preset historical time period, extracts the feature information of historically similar scenarios, and then obtains the feature information of actual similar scenarios after these features have passed through a preset historical time period, such as the scenario attributes after the increase or decrease in the number of patients and the change in the severity of the illness.

[0087] Similarly, extract the resource allocation feature information of similar historical scenarios, and then obtain the actual similar scenario resource allocation feature information after a preset historical time period, such as the resource allocation situation after adjustments in nursing staff and changes in equipment input.

[0088] Based on the aforementioned historical initial data and actual change data, the difference trend values ​​for the two dimensions are calculated respectively. By comparing the characteristic information of the actual similar scenario with that of the historical similar scenario, the difference trend value of the first scenario change is calculated using statistical methods (such as difference calculation and rate of change analysis). For example, if the number of patients in the historical scenario was 50 and the actual number after the change is 60, the change trend of scenario demand (demand growth) can be reflected by the growth rate of "(60-50) / 50=20%".

[0089] Similarly, by comparing the resource allocation characteristics of similar actual scenarios with those of similar historical scenarios, the first resource allocation change difference trend value is calculated. For example, the number of nurses in the historical scenario was 10, and the actual number after the change was 12. The adjustment trend of resource allocation is reflected by the growth rate of "(12-10) / 10=20%".

[0090] By calculating the trend values ​​of changes in scenario characteristics and resource allocation, the study clearly presents the patterns of demand changes and resource adjustment in similar scenarios over time. This data is used to subsequently analyze the dynamic correlation between changes in scenario demand and resource allocation adjustments, ultimately providing data support for the dynamic scheduling of nursing services—enabling scheduling decisions to accurately match the trends of changing scenario demand and resource allocation adjustments, thereby achieving effective allocation of nursing resources.

[0091] The process of matching historical difference cases from different service scenarios includes the following steps:

[0092] Obtain all service cases in the differentiated service scenarios that are scheduled;

[0093] Based on the service cases of different scenarios, historical cases with the same resource configuration feature information in the different service scenarios and the common service scenarios are selected.

[0094] This application identifies historical case studies from differentiated service scenarios, collecting all cases where scheduling services have actually been implemented within these scenarios—essentially acquiring differentiated service case studies. These cases contain various information about nursing services within each differentiated scenario. Then, these cases are compared with historically similar scenario resource allocation characteristics in common service scenarios to filter out those cases that share the same resource allocation characteristics. This comparison better reflects the uniqueness of differentiated service scenarios when analyzing the correlation between demand and resource allocation trends. These filtered cases constitute the historical differentiated case studies, which can then be used to calculate relevant dynamic correlation indicators to assist in dynamic scheduling decisions for nursing services.

[0095] After calculating the correlation coefficient of the changes in demand and resource allocation trends in corresponding cases before and after the same time period, a second dynamic correlation indicator is generated, which includes the following steps:

[0096] Obtain the historical difference scenario feature information and historical difference scenario resource configuration feature information to which the historical difference cases belong;

[0097] The characteristic information of historical difference scenarios is processed and analyzed to obtain the trend value of the second scenario change difference, and the characteristic information of resource allocation in historical difference scenarios is processed and analyzed to obtain the trend value of the second resource allocation change difference.

[0098] Extract a second dynamic correlation index between the trend value of the second scenario change difference and the trend value of the second resource allocation change difference.

[0099] This application collects historical difference scenario feature information and historical difference scenario resource allocation feature information corresponding to historical difference cases. Then, these two types of information are processed separately, similar to the previous analysis of similar scenarios, to calculate the second scenario change difference trend value. Similarly, the resource allocation feature information of historical difference scenarios is processed to obtain the second resource allocation change difference trend value, clarifying the direction and magnitude of resource allocation adjustments. Finally, these two trend values ​​are correlated to extract the relationship between them, quantified using a second dynamic correlation index. This clarifies how demand changes and resource allocation adjustments influence each other, providing correlation data under difference scenarios for dynamic scheduling of nursing services, allowing scheduling schemes to take into account the different situations of similar and difference scenarios, making them more scientific and reasonable.

[0100] The process involves processing and analyzing historical difference scenario feature information to obtain the second scenario change difference trend value, and processing and analyzing historical difference scenario resource allocation feature information to obtain the second resource allocation change difference trend value. Specifically, this includes the following steps:

[0101] The statistical analysis of historical differences in scene characteristics shows the actual changes in scene characteristics over a preset historical time period.

[0102] The actual resource allocation characteristics of the statistically differentiated scenarios are analyzed after a preset historical time period, showing how these characteristics have changed.

[0103] Calculate the trend value of the second scene change difference between the actual difference scene feature information and the historical difference scene feature information;

[0104] Calculate the second resource allocation change trend value between the actual difference scenario resource allocation feature information and the historical difference scenario resource allocation feature information.

[0105] This application focuses on two core dimensions in historical difference nursing scenarios: scenario characteristics and resource allocation characteristics. It tracks their dynamic changes within a preset historical time period and statistically analyzes the actual difference scenario characteristics after the preset historical difference scenario characteristics have passed, such as the scenario attributes after the patient's condition worsens / improves and the nursing process is adjusted.

[0106] The statistical analysis of resource allocation characteristics in historical difference scenarios is based on the actual resource allocation characteristics in actual difference scenarios after a preset historical time period, such as the resource allocation situation after changes in nurse allocation and special equipment input.

[0107] Based on the aforementioned historical initial data and actual change data, the difference trend values ​​for the two dimensions are calculated respectively. By comparing the characteristic information of the actual difference scenario with the characteristic information of the historical difference scenario, the difference trend value of the second scenario change is calculated. For example, in the historical difference scenario, the proportion of patients requiring special care was 30%, and after a preset period of time, it actually increased to 40%. This can be reflected by the growth rate of "(40%-30%) / 30%≈33.3%" to show the changing trend of scenario demand.

[0108] Similarly, by comparing the resource allocation characteristics of the actual difference scenario with those of the historical difference scenario, the second resource allocation change trend value is calculated. For example, in the historical difference scenario, the proportion of special-grade nursing staff was 20%, and after the actual change, it became 25%. The adjustment trend of resource allocation is reflected by the growth rate of "(25%-20%) / 20%=25%".

[0109] By calculating the trend values ​​of changes in scenario characteristics and resource allocation, the study clearly presents the patterns of demand changes and resource adjustment over time in different scenarios. This data will serve as the foundation for subsequent analysis of the dynamic correlation between demand changes and resource allocation adjustments in different scenarios, ultimately providing dedicated data support for the dynamic scheduling of nursing services—allowing scheduling decisions to both reuse experience from similar scenarios and accurately adapt to the specific needs of different scenarios.

[0110] A dynamic scheduling prediction model for nursing services is constructed based on the resource allocation status set, the first dynamic correlation index, and the second dynamic correlation index. This model generates a set of predicted scheduling schemes that includes overlapping and differing schemes. The specific steps include:

[0111] A dynamic scheduling and prediction model for nursing services is constructed based on the resource allocation status set, the first dynamic correlation index, and the second dynamic correlation index.

[0112] Obtain the feature information set of the predetermined scheduling scheme for each scheduling scenario in the first structured scheduling scenario set;

[0113] The second structured scheduling scenario set is obtained by inputting the feature information set of the predetermined scheduling scheme and the resource allocation status into the dynamic scheduling prediction model of nursing services.

[0114] The second set of structured scheduling scenarios is compared with the first set of structured scheduling scenarios to extract overlapping and different schemes.

[0115] This application's resource allocation status set (denoted as...) ): Includes resource sparsity and density configuration characteristics in similar scenarios (such as the number of nurses, equipment type, etc., which can be quantified as , (Represents the configuration parameters for the i-th type of resource).

[0116] The first dynamic correlation indicator (denoted as) ): Correlation coefficients of "demand-resource allocation trends" in similar scenarios (e.g., Pearson correlation coefficient) , In response to changing demands, (For changes in resource allocation).

[0117] The second dynamic correlation indicator (denoted as) ): Correlation coefficient of "demand-resource allocation trend" in different scenarios (calculation logic is the same) However, this is based on data from different scenarios.

[0118] The resource allocation status set, the first dynamic correlation index, and the second dynamic correlation index are integrated as the input foundation for the model. Using this multi-dimensional data, a dynamic scheduling prediction model for nursing services is established through appropriate algorithms, enabling the model to learn the patterns between resource allocation and dynamic correlation. Then, the feature information of the originally planned scheduling scheme for each scheduling scenario in the first structured scheduling scenario set is obtained. This information records how resources will be allocated and nursing work will be arranged for that scenario. Next, the feature information of the planned scheduling scheme, along with the current actual resource allocation status, is input into the newly built prediction model. Based on the learned patterns, the model outputs the second structured scheduling scenario set, which is the set of predicted scheduling schemes. Finally, the predicted second structured scheduling scenario set is compared with the initial first structured scheduling scenario set. Schemes with the same scheduling scheme are identified as overlapping schemes, while those that are different are identified as differential schemes. This yields a set of predicted scheduling schemes containing both types of schemes. Overlapping schemes can reuse previously effective scheduling strategies, while differential schemes are optimized and adjusted by the model based on current data, providing a more practical choice for dynamic scheduling of nursing services. The whole process involves training a model with data, using the model to predict new solutions, and finally comparing different types of solutions to achieve scientific and dynamic nursing scheduling.

[0119] The differences in the predicted scheduling scheme set are verified based on the first and second dynamic correlation indicators. An optimized scheduling scheme is generated and integrated with the overlapping schemes to output the final scheduling decision. The specific steps include:

[0120] The first dynamic correlation index predicts the degree of loss of nursing service resources in the differential scheme and outputs the first resource loss dataset.

[0121] Table 1 shows the first resource loss level output after the first dynamic correlation index predicts the degree of loss of nursing service resources in the differential scheme.

[0122] Difference scheme Human resource allocation characteristics (number of nurses) in similar historical scenarios Actual staffing (number of nurses) after changes Human resource attrition forecast (overtime hours / day) First resource depletion D1 Regular 3 people Actual number of people: 5 (to handle complex needs) 10 hours 10 D2 Regular 3 people Actual number of people: 4 (equipment collaboration optimization) 6 hours 6 D3 Regular 3 people Actual 3 people (frequency precisely adjusted) 3 hours 3

[0123] Table 1

[0124] Based on the second dynamic correlation index, the degree of loss of nursing service resources in the differential scheme is predicted and the second resource loss dataset is output.

[0125] Table 2 shows the first resource loss value output after the second dynamic correlation index predicts the degree of loss of nursing service resources in the differential scheme.

[0126] Difference scheme Historical differences in equipment configuration characteristics (number of patient monitors) Actual equipment configuration after changes (number of patient monitors) Equipment wear and tear prediction (idle / excessive time / day) Second resource depletion level L2 D1 2 standard units Actual 4 units (high-risk monitoring) 8 hours (overuse) 8 D2 2 standard units Actual 3 units (rotation optimization) 4 hours (idle time reduced) 4 D3 2 standard units Two units actually used (accurate frequency matching). 2 hours (matching needs) 2

[0127] Table 2

[0128] The first and second resource depletion datasets are sorted in ascending order of numerical values ​​to obtain the depletion ranking result.

[0129] After filtering out the nursing service scheduling schemes corresponding to the differential scheduling scenarios from the loss degree ranking results, the validated nursing service scheduling scheme section is output.

[0130] The dynamic scheduling result of nursing services is obtained by integrating the verification of the nursing service scheduling scheme and the overlapping scheme into the nursing service resource scheduling and distribution scheme.

[0131] This application first utilizes a first dynamic correlation indicator, which reflects the correlation between demand and resource allocation trends in common service scenarios, to predict the degree of resource depletion in differentiated solutions, such as additional consumption of nursing staff and overuse of equipment. These prediction results are compiled into a first resource depletion dataset. Similarly, a second dynamic correlation indicator (reflecting the demand-resource allocation correlation in differentiated service scenarios) is used to predict resource depletion in differentiated solutions, resulting in a second resource depletion dataset. The depletion values ​​in both datasets are then sorted in ascending order, clearly showing the varying levels of resource depletion across different differentiated solutions, yielding a depletion ranking result. Based on the actual characteristics of differentiated scheduling scenarios, suitable nursing service scheduling solutions are selected from the ranking results; this constitutes the validated nursing service scheduling solution. Finally, the validated differentiated solutions are integrated with previously validated and universally effective overlapping solutions. The combination of these two solutions forms a complete nursing service resource scheduling distribution scheme, which is the final dynamic scheduling result for nursing services. This result retains reliable conventional scheduling strategies while optimizing scheduling in differentiated scenarios, making nursing resource allocation more scientific, depletion more reasonable, and improving the efficiency and quality of nursing services.

[0132] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements a method for dynamic scheduling of nursing service processes based on big data processing.

[0133] like Figure 3 As shown, the electronic device may include a processor 610, a communications interface 620, a memory 630, and a communication bus 640. The processor 610, communications interface 620, and memory 630 communicate with each other via the communication bus 640. The processor 610 can call logical instructions from the memory 630 to execute a dynamic scheduling method for nursing service processes based on big data processing.

[0134] Furthermore, the logical instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0135] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute a dynamic scheduling method for nursing service processes based on big data processing.

[0136] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform a dynamic scheduling method for nursing service processes based on big data processing.

[0137] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0138] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0139] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0140] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for dynamic scheduling of nursing service processes based on big data processing, characterized in that, The method includes the following steps: Collect demand information for the current nursing service scenario, including patient condition, nursing items, and required manpower and resources. Based on this demand information, identify service scenarios that are common to this scenario and service scenarios that are different. Based on the identified common service scenarios, summarize their resource allocation status to form a resource allocation status set. Specifically, this includes the following steps: After extracting at least two scheduling scenarios with independent nursing characteristics from the current nursing service scenario based on nursing demand information, the first structured scheduling scenario set is output. The resource allocation status of corresponding nursing services is obtained based on the characteristic information of each scheduling scenario in the first structured scheduling scenario set; The resource allocation status of common service scenarios is statistically analyzed, and the resource allocation status set is obtained by statistically analyzing the configuration characteristics of sparse and dense nursing resource allocation scenarios based on the resource allocation status. For common service scenarios, the service demand sequence data and resource allocation time series data are divided according to preset historical time periods, the correlation coefficient between the two sets of sequences is calculated, and the first dynamic correlation index is generated. By matching historical difference cases from the difference service scenarios, calculating the correlation coefficient of the change in demand and resource allocation trends of the corresponding cases before and after the same period, a second dynamic correlation indicator is generated. A dynamic scheduling prediction model for nursing services is constructed based on the resource allocation status set, the first dynamic correlation index, and the second dynamic correlation index. This model generates a set of predicted scheduling schemes that includes overlapping and differing schemes. The specific steps include: A dynamic scheduling and prediction model for nursing services is constructed based on the resource allocation status set, the first dynamic correlation index, and the second dynamic correlation index. Obtain the feature information set of the predetermined scheduling scheme for each scheduling scenario in the first structured scheduling scenario set; The second structured scheduling scenario set is obtained by inputting the feature information set of the predetermined scheduling scheme and the resource allocation status into the dynamic scheduling prediction model of nursing services. The second set of structured scheduling scenarios is compared with the first set of structured scheduling scenarios to extract overlapping and different schemes. The differences in the predicted scheduling scheme set are verified based on the first and second dynamic correlation indicators. An optimized scheduling scheme is generated and integrated with the overlapping schemes to output the final scheduling decision.

2. The method for dynamic scheduling of nursing service processes based on big data processing according to claim 1, characterized in that, After calculating the correlation coefficient between the changes in service demand and resource allocation trends in common service scenarios before and after a preset historical period, a first dynamic correlation indicator is generated, which specifically includes the following steps: Obtain feature information of historically similar scenarios and resource configuration feature information of historically similar scenarios in common service scenarios before a preset historical time period; The first scenario change difference trend value is obtained by processing and analyzing the feature information of historical similar scenarios, and the first resource allocation change difference trend value is obtained by processing and analyzing the resource allocation feature information of historical similar scenarios. Extract the first dynamic correlation index between the trend value of the first scenario change difference and the trend value of the first resource allocation change difference.

3. The method for dynamic scheduling of nursing service processes based on big data processing according to claim 2, characterized in that, The process involves processing and analyzing historical similar scene feature information to obtain the first scene change difference trend value, and processing and analyzing historical similar scene resource allocation feature information to obtain the first resource allocation change difference trend value. Specifically, this includes the following steps: Extract the actual similar scene features that have changed after a preset historical time period; Extract the actual similar scene resource configuration feature information that changes after a preset historical time period; Calculate the trend value of the first scene change difference between the feature information of the actual similar scene and the feature information of the historical similar scene; Calculate the first resource allocation change difference trend value between the resource allocation feature information of actual similar scenarios and the resource allocation feature information of historical similar scenarios.

4. The method for dynamic scheduling of nursing service processes based on big data processing according to claim 3, characterized in that, The process of matching historical difference cases from different service scenarios includes the following steps: Obtain all service cases in the differentiated service scenarios that are scheduled; Based on the service cases of different scenarios, historical cases with the same resource configuration feature information in the different service scenarios and the common service scenarios are selected.

5. The method for dynamic scheduling of nursing service processes based on big data processing according to claim 4, characterized in that, After calculating the correlation coefficient of the changes in demand and resource allocation trends in corresponding cases before and after the same time period, a second dynamic correlation indicator is generated, which includes the following steps: Obtain the historical difference scenario feature information and historical difference scenario resource configuration feature information to which the historical difference cases belong; The characteristic information of historical difference scenarios is processed and analyzed to obtain the trend value of the second scenario change difference, and the characteristic information of resource allocation in historical difference scenarios is processed and analyzed to obtain the trend value of the second resource allocation change difference. Extract a second dynamic correlation index between the trend value of the second scenario change difference and the trend value of the second resource allocation change difference.

6. The method for dynamic scheduling of nursing service processes based on big data processing according to claim 5, characterized in that, The process involves processing and analyzing historical difference scenario feature information to obtain the second scenario change difference trend value, and processing and analyzing historical difference scenario resource allocation feature information to obtain the second resource allocation change difference trend value. Specifically, this includes the following steps: The statistical analysis of historical differences in scene characteristics shows the actual changes in scene characteristics over a preset historical time period. The actual resource allocation characteristics of the statistically differentiated scenarios are analyzed after a preset historical time period, showing how these characteristics have changed. Calculate the trend value of the second scene change difference between the actual difference scene feature information and the historical difference scene feature information; Calculate the second resource allocation change trend value between the actual difference scenario resource allocation feature information and the historical difference scenario resource allocation feature information.

7. The method for dynamic scheduling of nursing service processes based on big data processing according to claim 6, characterized in that, The differences in the predicted scheduling scheme set are verified based on the first and second dynamic correlation indicators. An optimized scheduling scheme is generated and integrated with the overlapping schemes to output the final scheduling decision. The specific steps include: The first dynamic correlation index predicts the degree of loss of nursing service resources in the differential scheme and outputs the first resource loss dataset. Based on the second dynamic correlation index, the degree of loss of nursing service resources in the differential scheme is predicted and the second resource loss dataset is output. The first resource depletion dataset and the second resource depletion dataset are sorted in ascending order of numerical values ​​to obtain the depletion ranking result. After selecting the nursing service scheduling schemes corresponding to the differential scheduling scenarios from the loss degree ranking results, the verification nursing service scheduling scheme part is output. The dynamic scheduling result of nursing services is obtained by integrating the verification of the nursing service scheduling scheme and the overlapping scheme into the nursing service resource scheduling and distribution scheme.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the dynamic scheduling method for nursing service processes based on big data processing as described in any one of claims 1 to 7.

Images