Personalized display method for nurse terminal operation interface, electronic equipment and storage medium

Abstract

The invention discloses a nurse terminal operation interface personalized display method, electronic equipment and a storage medium, and the method comprises the steps: obtaining account identity information in response to a login instruction of a nurse; according to the account identity information, querying to obtain corresponding operation habit information; according to the operation habit information, determining a rendering layout relationship between each display area and each control in a preset display interface; performing rendering in the display interface according to the rendering layout relationship; and obtaining current operation data of the nurse in current login, and updating the operation habit information at a preset first time interval according to the current operation data. According to the invention, nurses can complete work more efficiently and accurately.

Description

Technical Field

[0001] This application relates to the technical field of hospital data management, and particularly to a personalized display method for a nurse terminal operation interface, an electronic device, and a storage medium. Background Art

[0002] In the modern medical environment, nurses need to frequently use terminal devices to query patient information, record nursing conditions, etc. The existing nurse terminal operation interfaces mostly have a unified fixed layout, which cannot take into account the differences in the operation habits of different nurses. In actual work, since the operation habits of each nurse are different, for example, some nurses are used to placing the commonly used patient information query function in a prominent position on the interface, while some nurses prefer to place the nursing record function in a convenient operation place. However, the unified fixed interface layout cannot meet these personalized needs, resulting in nurses having to spend extra time looking for the required controls and frequently switching between different function modules during the operation process. This not only reduces work efficiency but also easily causes problems such as information entry errors or untimely queries due to inconvenient operations, thereby affecting the nursing quality of patients and the timeliness of medical services. Summary of the Invention

[0003] This application aims to at least solve one of the technical problems existing in the prior art. For this reason, this application provides a personalized display method for a nurse terminal operation interface, an electronic device, and a storage medium, which can enable nurses to complete their work more efficiently and accurately.

[0004] In a first aspect, this application provides a personalized display method for a nurse terminal operation interface, including: Responding to the login instruction of the nurse personnel to obtain the account identity information; Querying the corresponding operation habit information according to the account identity information; Determining the rendering layout relationship between each display area and each control in the preset display interface according to the operation habit information; Rendering in the display interface according to the rendering layout relationship; Obtaining the current operation data of the nurse personnel during the current login, and updating the operation habit information at intervals of a preset first time according to the current operation data; Wherein, the operation habit information is obtained according to the following steps: Obtaining the historical operation data corresponding to the account identity information; Inputting the historical operation data into the input layer of a preset perception neural network model, and determining a first scoring set for each display area in the display interface and a second scoring set for each control through multiple hidden layers of the perception neural network model; Input the first scoring set and the second scoring set into the output layer of the perception neural network model to obtain operation habit information.

[0005] According to the nurse terminal operation interface personalized display method of the first aspect embodiment of the present application, it has at least the following beneficial effects: When a nurse issues a login instruction, the system responds quickly and obtains their account identity information. Based on the obtained account identity information, the system queries in the pre-stored database to find the corresponding operation habit information. These operation habit information are obtained by long-term collection of the nurse's historical operation data and analyzed by the perception neural network model. The system further determines the rendering layout relationship between each display area and each control in the preset display interface according to the queried operation habit information. Based on the determined rendering layout relationship, the system renders in the display interface. During the process of the nurse using the terminal device, the system continuously obtains the current operation data of their current login, and at preset first time intervals, the system incorporates these current operation data into the analysis scope to update the original operation habit information. By obtaining and analyzing the nurse's operation habit information, placing the frequently used function controls in the positions where the nurse is used to operating reduces the time for the nurse to search for controls and switch function modules. At the same time, the mechanism of real-time updating of operation habit information can keep up with the possible changes in the nurse's operation habits in a timely manner, further ensuring the convenience of operation and avoiding problems such as information entry errors and untimely queries caused by inconvenient operation. The nurse no longer needs to spend a lot of time looking for the required controls and switching functions in the fixed layout interface, can quickly locate and operate the frequently used functions, saves operation time, enables the nurse to complete more nursing work tasks per unit time. On the other hand, the interface layout that conforms to personal operation habits reduces the risk of information entry errors caused by inconvenient operation. The nurse can focus more on the nursing work itself rather than being disturbed by the inconvenient operation interface, thereby improving the accuracy of nursing records and the reliability of medical information, enabling the nurse to complete the work more efficiently and accurately, and enabling the patient to receive more timely and high-quality nursing services.

[0006] According to some embodiments of the first aspect of the present application, after the step of responding to the login instruction of the nurse personnel and obtaining the account identity information, it further includes: When there is no corresponding operation habit information for the account identity information, generate a questionnaire and render the questionnaire on the display interface; Obtain the survey results filled in by the nurse personnel and generate intention layout information according to the survey results; Render the controls in different display areas of the display interface according to the preset initial layout position.

[0007] According to some embodiments of the first aspect of the present application, inputting the historical operation data into the input layer of a preset perception neural network model, and determining a first score set for each display area of the display interface and a second score set for each of the controls through multiple hidden layers of the perception neural network model includes: Obtain the intended layout information corresponding to the account identity information; Input the historical operation data and the intended layout information into the input layer of a preset perception neural network model, and assign a first confidence level and a second confidence level to the historical operation data and the intended layout information respectively through the input layer; Through multiple hidden layers of the perception neural network model, perform a fusion process on the historical operation data, the first confidence level, the intended layout information, and the second confidence level to obtain a first score set for each display area of the display interface and a second score set for each of the controls.

[0008] According to some embodiments of the first aspect of the present application, the assigning of the first confidence level and the second confidence level to the historical operation data and the intended layout information respectively through the input layer includes: Obtain, through the input layer, a first timestamp of the last update of the historical operation data and a second timestamp for establishing the intended layout information; Establish an assignment rule table; wherein the assignment rule table is used to represent the relationship between the difference between the first timestamp and the second timestamp and the ratio between the first confidence level and the second confidence level; Based on the assignment rule table, determine the first confidence level of the historical operation data and the second confidence level of the intended layout information according to the first timestamp and the second timestamp.

[0009] According to some embodiments of the first aspect of the present application, the historical operation data includes: the historical usage time and historical usage area of each control, and the intended layout information includes control usage requirements and habitual usage areas; The performing of the fusion process on the historical operation data, the first confidence level, the intended layout information, and the second confidence level through multiple hidden layers of the perception neural network model to obtain a first score set for each display area of the display interface and a second score set for each of the controls includes: Determine a first usage score value for each control through the first hidden layer of the perception neural network model according to the historical usage time of each control, the first confidence level, the control usage requirements, and the second confidence level; Determine the second usage score value of each of the display areas through the second hidden layer of the perception neural network model according to the historical usage area, the first confidence level, the habitual usage area, and the second confidence level; Obtain a first score set based on the multiple first usage score values, and obtain a second score set based on the multiple second usage score values.

[0010] According to some embodiments of the first aspect of the present application, the perception neural network model is trained according to the following steps: Establish an initial perception neural network model; Obtain sample operation data and the expected display result corresponding to the sample operation data; Input the sample operation data into the perception neural network model to obtain an actual display result; wherein, the actual display result includes the actual controls to be displayed and the actual display area of each of the actual controls; Obtain a training loss value according to the actual display result and the expected display result; Adjust the parameters of the perception neural network model according to the training loss value until the training loss value meets a preset convergence condition or the number of training times is greater than or equal to a preset number threshold, and stop the training of the perception neural network model to obtain a trained perception neural network model.

[0011] According to some embodiments of the first aspect of the present application, the perception neural network model is also trained according to the following steps: When the training loss value does not meet the convergence condition and the number of training times is less than the number threshold, perform gradient solution on the parameters of the perception neural network model according to a preset gradient algorithm and the training loss value to obtain a gradient vector; Obtain a learning rate parameter according to the number of training times of the perception neural network model and a preset learning rate decay function; Update the gradient vector according to the learning rate parameter; Adjust the parameters of the perception neural network model according to the updated gradient vector.

[0012] According to some embodiments of the first aspect of the present application, determining the rendering layout relationship between each display area and each control in a preset display interface according to the operation habit information includes: Determine the first priority of each control corresponding to the current account identity information and the second priority of each display area according to the operation habit information; Determine the rendering layout relationship between each of the display areas and each of the controls in the preset display interface according to the first priority and the second priority.

[0013] In a second aspect, the present application further provides an electronic device, including: At least one memory; At least one processor; At least one program; The program is stored in the memory, and the processor executes at least one of the programs to implement the personalized display method for the nurse terminal operation interface as described in any embodiment of the first aspect.

[0014] In a third aspect, the present application further provides a computer-readable storage medium, which stores computer-executable signals for executing the personalized display method for the nurse terminal operation interface as described in any embodiment of the first aspect.

[0015] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. Description of the Drawings

[0016] The additional aspects and advantages of the present application will become apparent and be readily understood in conjunction with the following description of the embodiments with reference to the accompanying drawings, where: Figure 1 is a flowchart of the personalized display method for the nurse terminal operation interface provided by an embodiment of the present application; Figure 2 is for the present application Figure 1 a flowchart after step S100; Figure 3 is for the present application Figure 1 a flowchart of step S620; Figure 4 is for the present application Figure 3 a flowchart of step S650; Figure 5 is for the present application Figure 3 a flowchart of step S660; Figure 6 is a flowchart of an embodiment of the training steps of the perception neural network model for the present application; Figure 7 is a flowchart of another embodiment of the training steps of the perception neural network model for the present application; Figure 8 is for the present application Figure 1 a flowchart of step S300; Detailed Embodiments

[0017] Embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present application and should not be construed as a limitation of the present application.

[0018] In the description of the present application, it should be understood that the orientation descriptions, such as up, down, front, back, left, right, etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. This is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of the present application.

[0019] In the description of the present application, if the first and second are described only for the purpose of distinguishing technical features, it should not be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features or implicitly specifying the sequence of the indicated technical features.

[0020] In the description of the present application, unless otherwise clearly defined, words such as setting, installing, connecting, etc. should be understood in a broad sense. Those skilled in the art can reasonably determine the specific meanings of the above words in the present application in combination with the specific content of the technical solution.

[0021] In a modern medical environment, nurses need to frequently use terminal devices to query patient information, record nursing conditions, etc. Most of the existing nurse terminal operation interfaces have a unified fixed layout and cannot take into account the differences in the operation habits of different nurses. In actual work, since the operation habits of each nurse are different, for example, some nurses are used to placing the frequently used patient information query function in a prominent position on the interface, while some nurses prefer to place the nursing record function in a convenient place for operation. However, the unified fixed interface layout cannot meet these personalized needs, resulting in nurses spending extra time looking for the required controls and frequently switching between different function modules during the operation process. This not only reduces work efficiency but also easily causes problems such as incorrect information entry or untimely query due to inconvenient operation, thus affecting the nursing quality of patients and the timeliness of medical services.

[0022] Based on this, the present application provides a personalized display method for a nurse terminal operation interface, an electronic device, and a storage medium to solve the above-mentioned technical problems. The technical solutions provided by the present application will be described in detail one by one below.

[0023] In the first aspect, referring to Figure 1 , the present application provides a personalized display method for a nurse terminal operation interface, which may include but is not limited to the following steps: Step S100: In response to the login instruction of the nurse personnel, obtain the account identity information.

[0024] Step S200: Query and obtain the corresponding operation habit information according to the account identity information.

[0025] Step S300: Determine the rendering layout relationship between each display area and each control in the preset display interface according to the operation habit information.

[0026] Step S400: Perform rendering in the display interface according to the rendering layout relationship.

[0027] Step S500: Obtain the current operation data of the nurse personnel during the current login, and update the operation habit information at intervals of a preset first time according to the current operation data.

[0028] Among them, the operation habit information in Step S300 is obtained according to the following steps: Step S610: Obtain the historical operation data corresponding to the account identity information.

[0029] Step S620: Input the historical operation data into the input layer of the preset perception neural network model, and determine the first scoring set of each display area and the second scoring set of each control in the display interface through multiple hidden layers of the perception neural network model.

[0030] Step S630: Input the first scoring set and the second scoring set into the output layer of the perception neural network model to obtain the operation habit information.

[0031] In steps S100 to S500 and steps S610 to S630, when the nurse issues a login instruction, the system responds quickly and obtains their account identity information. Based on the obtained account identity information, the system queries in the pre-stored database and finds the corresponding operation habit information. These operation habit information are obtained by collecting the nurse's historical operation data over a long period and analyzed by a perception neural network model. According to the queried operation habit information, the system further determines the rendering layout relationship between each display area and each control in the preset display interface. For example, if a certain nurse often uses the patient information query function and is used to placing it in a prominent position on the left side of the screen, the system will determine the rendering layout of this control in the left area of the display interface based on this habit. Based on the determined rendering layout relationship, the system renders in the display interface. During the process of the nurse using the terminal device, the system continuously obtains the current operation data of their current login. And, at a preset first time interval, the system will include these current operation data in the analysis scope to update the original operation habit information. By obtaining and analyzing the nurse's operation habit information and placing the commonly used function controls in the positions where the nurse is used to operating, it reduces the time for the nurse to search for controls and switch function modules. At the same time, the mechanism of real-time updating of operation habit information can keep up with the possible changes in the nurse's operation habits in a timely manner, further ensuring the convenience of operation and avoiding problems such as information entry errors and untimely queries caused by inconvenient operation. The nurse no longer needs to spend a lot of time looking for the required controls and switching function modules in the fixed-layout interface, and can quickly locate and operate the commonly used functions, saving operation time, enabling the nurse to complete more nursing work tasks per unit time. On the other hand, the interface layout that conforms to personal operation habits reduces the risk of information entry errors caused by inconvenient operation. The nurse can focus more on the nursing work itself rather than being disturbed by the inconvenient operation interface, thereby improving the accuracy of nursing records and the reliability of medical information, enabling the nurse to complete the work more efficiently and accurately, and enabling the patient to receive more timely and high-quality nursing services.

[0032] Refer to Figure 2 , after step S100, it may further include but is not limited to the following steps: Step S710: When there is no corresponding operation habit information for the account identity information, generate a questionnaire and render the questionnaire on the display interface.

[0033] Step S720: Obtain the survey results filled in by the nursing staff and generate intention layout information according to the survey results.

[0034] Step S730: Render the controls in different display areas of the display interface according to the preset initial layout position.

[0035] In steps S710 to S730, after the nurse issues a login instruction, the system quickly obtains their account identity information and immediately retrieves it in the database to determine whether there is corresponding operation habit information for this account identity information. If the system determines that there is no corresponding operation habit information for this account identity information, it will automatically generate a questionnaire. The content of the questionnaire focuses on the nurse's layout preferences for the terminal operation interface. For example, it asks which area of the screen the nurse hopes to place the commonly used function buttons (such as patient information query, nursing records, etc.), and the expected arrangement order of different information display areas (such as basic information area, test report area). After generating the questionnaire, the system immediately renders it on the display interface and presents it to the nurse. After the nurse views the questionnaire on the display interface, they fill in the questionnaire according to their own operation intentions and habits, and submit the survey results after completion. The system analyzes and processes the data using a preset algorithm based on the obtained survey results. For example, it counts the selection frequencies of each function button in different position options, and determines the intended position of each function button on the display interface according to the frequency. The system renders each control in different display areas of the display interface according to the preset initial layout position and the generated intended layout information. In the above steps, for newly recruited nurses or nurses who use the terminal system for the first time, through the questionnaire method, their personalized requirements for the operation interface can be quickly collected, avoiding the operation confusion of new users due to facing a strange and non-personalized interface, enabling them to have an interface layout that conforms to their initial operation habits in a short time, and improving the acceptance and usage efficiency of new users for the system. The collected survey results and the generated intended layout information serve as important reference data for the subsequent system to learn the operation habits of this nurse, achieving more accurate learning and optimization of the operation habits of this nurse, and realizing more in-depth personalized customization.

[0036] Referring to Figure 3 , it can be understood that in step S620, it may include but is not limited to the following steps: Step S640: Obtain the intended layout information corresponding to the account identity information; Step S650: Input the historical operation data and the intended layout information into the input layer of the preset perception neural network model, and assign the first confidence level and the second confidence level to the historical operation data and the intended layout information respectively through the input layer; Step S660: Through multiple hidden layers of the perception neural network model, fuse and process the historical operation data, the first confidence level, the intended layout information, and the second confidence level to obtain the first score set for each display area on the display interface and the second score set for each control.

[0037] In steps S640 to S660, before the historical operation data is input into the preset perception neural network model, the system first retrieves the corresponding intended layout information from the database based on the nurse's account identity information. These intended layout information are the expected data on the operation interface layout feedback by the nurse when first using the terminal system by filling out a questionnaire. The system inputs the obtained historical operation data and the intended layout information into the input layer of the preset perception neural network model together. The input layer assigns a first confidence level and a second confidence level to these two different types of data respectively. The first confidence level is used to measure the reliability of the historical operation data in subsequent analysis, and its value setting comprehensively considers factors such as the time span of the data and the stability of the operation frequency. For example, data that is recent and has a stable operation frequency may be assigned a higher first confidence level. The second confidence level is for the intended layout information, and its value is determined considering factors such as the seriousness of the nurse's initial questionnaire filling and the completeness of the questionnaire filling, to reflect the importance of this intended layout information in the model analysis. The data processed by the input layer, that is, the historical operation data with the first confidence level and the intended layout information with the second confidence level, enters multiple hidden layers of the perception neural network model. The hidden layers perform deep fusion processing on these data through a series of complex non-linear transformations and weight adjustments. For example, the neurons in the hidden layer perform weighted summation on the input data according to the preset weight matrix and perform non-linear mapping through the activation function. In this process, the model comprehensively considers the nurse's actual operation habits reflected by the historical operation data and the nurse's initial expectations reflected by the intended layout information, so as to determine the first scoring set for each display area on the display interface and the second scoring set for each control. The first scoring set represents the adaptability score of each display area to the nurse's operation habits, and the second scoring set represents the importance score of each control in the nurse's operation process. Introducing the intended layout information as the model input enables the model to not only rely on the actual operation data but also take into account the personalized needs initially expressed by the nurse when analyzing the nurse's operation habits. By assigning confidence levels to different types of data, the model can more reasonably balance the roles of the historical operation data and the intended layout information in the analysis process, avoid analysis biases caused by the limitations of a single data source, and thus significantly improve the accuracy of determining the scoring set, realizing deep personalized customization from operation habits to interface layout.

[0038] Refer to Figure 4 , it can be understood that in step S650, it may include but is not limited to the following steps: Step S651: Obtain the first timestamp of the last update of the historical operation data and the second timestamp of establishing the intended layout information through the input layer.

[0039] Step S652: Establish an assignment rule table; wherein, the assignment rule table is used to represent the relationship between the difference between the first timestamp and the second timestamp and the ratio between the first confidence level and the second confidence level.

[0040] Step S653: Based on the assignment rule table, determine the first confidence level of the historical operation data and the second confidence level of the intended layout information according to the first timestamp and the second timestamp.

[0041] In steps S651 to S653, the input layer of the system starts to work. It will accurately locate and extract the key time information related to the data. For the historical operation data, obtain the first timestamp of its last update, which records the moment when the nurse last generated an operation behavior and reflects the timeliness of the historical operation data. At the same time, obtain the second timestamp for establishing the intended layout information, which marks the time point when the nurse first expressed the expectation for the interface layout through the questionnaire. A pre-constructed assignment rule table is built inside the system. This rule table is a collection of carefully designed data mapping relationships. It details the corresponding relationship between the difference between the first timestamp and the second timestamp and the ratio between the first confidence level and the second confidence level. For example, when the difference between the first timestamp and the second timestamp is small, it indicates that the time interval between the historical operation data and the intended layout information is short, and their correlation may be high. At this time, the rule table may set the ratio of the first confidence level and the second confidence level to be relatively close to 1 or less than 1; if the difference is large, it means that the time span between the historical operation data and the initial intended layout information is large, and the nurse's operation habits may have changed greatly. The rule table will accordingly adjust the ratio of the two confidence levels, giving a higher confidence level to the more timely historical operation data, that is, the first confidence level is much greater than the second confidence level. Based on the established assignment rule table, the system substitutes the obtained first timestamp and second timestamp into it for calculation and analysis. By looking up the corresponding timestamp difference interval in the rule table, the system can accurately determine the first confidence level of the historical operation data and the second confidence level of the intended layout information. For example, if the calculated timestamp difference falls within a certain specific interval in the rule table, the system sets the confidence level ratio corresponding to this interval and combines the preset confidence level value range (such as 0 - 1) to finally determine the specific values of the first confidence level and the second confidence level. Determining the confidence level through timestamps fully considers the timeliness of the historical operation data and the intended layout information. When the perception neural network model processes data, it can assign different weights according to the freshness of the data, enabling the model to automatically adapt to operation changes and ensuring that the model output result better meets the current actual needs of the nurse.

[0042] Refer to Figure 5, it can be understood that the historical operation data includes: the historical usage time and historical usage area of each control, and the intended layout information includes control usage requirements and habitual usage areas. In step S660, it may include but is not limited to the following steps: Step S661: According to the historical usage time of each control, the first confidence level, the control usage requirements, and the second confidence level, through the first hidden layer of the perception neural network model, determine the first usage score value of each control; Step S662: According to the historical usage area, the first confidence level, the habitual usage area, and the second confidence level, through the second hidden layer of the perception neural network model, determine the second usage score value of each display area; Step S663: Obtain a first score set based on multiple first usage score values, and obtain a second score set based on multiple second usage score values.

[0043] In step S661, the historical usage time of each control, the corresponding first confidence level, the control usage requirements, and the second confidence level are input into the first hidden layer of the perception neural network model together. The historical usage time reflects the actual usage frequency of the control by the nurse, and the first confidence level reflects the reliability of the historical operation data; the control usage requirements represent the nurse's usage expectations for the control in the initial intended layout, and the second confidence level reflects the importance of the intended layout information. In the first hidden layer, the neurons perform weighted summation on the input data according to the preset weight matrix to obtain the first usage score value for each control In step S662, the historical usage area and the first confidence level, as well as the habitual usage area and the second confidence level are input into the second hidden layer. The historical usage area shows the interface positions where the nurse often uses the control in actual operations, and the habitual usage area is the position where the nurse expects to use the control expressed in the questionnaire. The second hidden layer also performs weighted summation on these data according to the weight matrix to obtain the second usage score value for each display area.

[0044] In step S663, the system collects the first usage score values of all controls and organizes them into a first score set according to a specific rule (such as sorting from high to low). This score set comprehensively presents the ranking of the importance of each control in the nurse's operation habits and requirements. The second usage score values of all display areas are processed in the same way to obtain a second score set, which reflects the ranking of the adaptability of each display area to the nurse's operations. Through hierarchical processing and multi-dimensional analysis, the model can better adapt to the diverse operation habits and requirements of different nurses.

[0045] Refer to Figure 6 , it can be understood that the perception neural network model in step S620 can be based on but not limited to the following steps: Step S810: Establish an initial perception neural network model; Step S820: Obtain sample operation data and the expected display results corresponding to the sample operation data; Step S830: Input the sample operation data into the perception neural network model to obtain the actual display results; wherein, the actual display results include the actual controls to be displayed and the actual display areas of each actual control; Step S840: Obtain the training loss value according to the actual display results and the expected display results; Step S850: Adjust the parameters of the perception neural network model according to the training loss value until the training loss value meets the preset convergence condition or the number of training times is greater than or equal to the preset number threshold, stop the training of the perception neural network model, and obtain the trained perception neural network model.

[0046] In steps S810 to S830, during the system development stage, an initial perception neural network model is constructed. This model includes an input layer, multiple hidden layers, and an output layer, and its architecture design is based on the understanding and requirement analysis of the personalized display task of the nurse terminal operation interface. The parameters such as the number of neurons, connection methods, and initial weights of each layer are set according to the preset rules. A large number of sample operation data are collected, which cover various operation behaviors of different nurses during the use of terminal devices, including historical operation data such as the usage time and usage area of each control, as well as the intended layout information such as the control usage requirements and habitual usage areas feedback by nurses through questionnaires. At the same time, obtain the expected display results corresponding to these sample operation data. The expected display results are the ideal interface layouts set according to the professional nursing process analysis and the actual needs of nurses, including the controls to be displayed and the ideal display areas of each control. Input the sample operation data into the initialized perception neural network model. The data starts from the input layer and passes through the processing of multiple hidden layers in turn. In the hidden layer, the neurons perform weighted summation on the input data through the preset weight matrix and perform non-linear transformation through the activation function to extract the key features in the data. Finally, the data processed by the hidden layer reaches the output layer, and the actual display results are output, including the actual controls to be displayed and the actual display areas of each actual control.

[0047] In steps S840 to S850, the actual display result output by the model is compared and analyzed with the expected display result obtained in advance. The difference between the two is calculated through a specific loss function to obtain the training loss value. The training loss value reflects the deviation degree between the current output result of the model and the expected result. The smaller the loss value, the closer the model output is to the expectation. According to the calculated training loss value, the parameters of the perception neural network model are adjusted using the backpropagation algorithm. The backpropagation algorithm will propagate the loss value from the output layer back to the input layer. During the propagation process, the contribution degree of each parameter to the loss value is calculated, and the parameters are adjusted according to the contribution degree, so that the model can output an actual display result closer to the expected display result in the next prediction. Continuously repeat the above steps, that is, input new sample operation data, calculate the actual display result and the training loss value, and then adjust the parameters until the training loss value meets the preset convergence condition, such as the loss value is less than a very small threshold, or the number of training times is greater than or equal to the preset number threshold. At this time, stop the model training to obtain a trained perception neural network model.

[0048] Referring to Figure 7 , it can be understood that the perception neural network model in step S620 can also be based on but not limited to the following steps: Step S860: When the training loss value does not meet the convergence condition and the number of training times is less than the number threshold, according to the preset gradient algorithm and the training loss value, perform gradient solution on the parameters of the perception neural network model to obtain a gradient vector.

[0049] Step S870: According to the number of training times of the perception neural network model and the preset learning rate decay function, obtain the learning rate parameter.

[0050] Step S880: Update the gradient vector according to the learning rate parameter.

[0051] Step S890: Adjust the parameters of the perception neural network model according to the updated gradient vector.

[0052] In step S860, according to the preset gradient algorithm and the training loss value L, perform gradient solution on the parameters θ of the perception neural network model to obtain a gradient vector . In each iteration of the stochastic gradient descent algorithm, a sample (or a small batch of samples) is randomly selected from the training dataset to calculate the gradient. Assume the training dataset is , for the t-th training iteration, a sample is randomly selected, and the gradient calculation formula of the loss function L with respect to the parameter θ is: ; where represents the sample under the parameter θThe corresponding loss value.

[0053] In step S870, according to the number of training times t of the perception neural network model and a preset learning rate decay function, a learning rate parameter η is obtained. t . Here we adopt an exponential decay learning rate function, and its formula is: ; Where: is the initial learning rate, which is a preset constant and controls the step size of parameter update in the initial stage of model training.

[0054] is the decay coefficient, and its value range is usually between, which is used to control the decay speed of the learning rate with the number of training times.

[0055] k is the decay step, that is, every k training iterations, the learning rate decays once.

[0056] represents the floor function.

[0057] In step S880, according to the learning rate parameter the gradient vector is updated to obtain an updated gradient vector, and its calculation formula is: .

[0058] In the above steps S860 to S890, the learning rate parameter is dynamically adjusted according to the number of training times through a preset learning rate decay function. In the initial stage of training, a larger learning rate can make the model parameters updated quickly, accelerate the speed of the model approaching the optimal solution, and reduce the overall training time. As the number of training times increases, the learning rate gradually decreases, avoiding the model skipping the optimal solution due to too large a step size when approaching the optimal solution, thus oscillating near the optimal solution, and ensuring the stability of model convergence. At the same time, using a preset gradient algorithm to calculate the gradient vector can accurately determine the update direction and amplitude of the model parameters in the current state. Adjusting the parameters according to the gradient vector enables the model to be optimized along the direction where the loss function drops fastest, improving the convergence efficiency. In addition, dynamically adjusting the learning rate and gradient-based parameter update helps prevent model overfitting. In the later stage of training, a smaller learning rate makes the update of model parameters more refined, which can, to a certain extent, avoid the model overfitting to the training data, so that the model can also have good performance when facing unseen test data, improving the generalization ability of the model.

[0059] Referring to Figure 8 , it can be understood that in step S300, it may include but is not limited to the following steps: Step S310: Determine the first priority of each control corresponding to the current account identity information and the second priority of each display area according to the operation habit information.

[0060] Step S320: Determine the rendering layout relationship between each display area and each control in the preset display interface according to the first priority and the second priority.

[0061] In steps S310 to S320, the system reads the operation habit information, which includes habit data such as the usage frequency and usage time of each control by the nurse, as well as preference data for different display areas. Based on these data, the system starts to calculate the first priority of each control. For example, if a certain nurse frequently uses the "patient information query" control and the usage time is long, then the first priority of this control will be set relatively high; on the contrary, the priority of a rarely used control is relatively low. The determination of the second priority of each display area also depends on the operation habit information. For example, if a nurse often views important information in the upper left corner area of the screen, then the second priority of the upper left corner display area of the screen will be relatively high. After obtaining the first priority of each control and the second priority of each display area, the system will perform matching. Controls with high priority will be preferentially arranged in display areas with high priority. For example, the "patient information query" control has a high priority, and the upper left corner display area of the screen also has a high priority, so the system will layout the "patient information query" control in the upper left corner area of the screen. For other controls and display areas, matching and layout are also carried out in order from high to low according to the priority, so as to determine the rendering layout relationship between each display area and each control in the preset display interface. Placing the controls most frequently used by the nurse in the high-priority display areas that are easiest to operate and view enables the nurse to quickly find and operate the frequently used functions when using the terminal device, reducing the operation steps and the time to find the controls. For example, in an emergency, the nurse can quickly find the "vital sign record" control in the high-priority area and record the critical information of the patient in time, improving the efficiency of nursing work.

[0062] In a second aspect, the present application also provides an electronic device, including: at least one memory; at least one processor; at least one program; the program is stored in the memory, and the processor executes at least one program to implement the personalized display method of the nurse terminal operation interface according to any one of the embodiments of the first aspect.

[0063] In this electronic device, when a nurse issues a login instruction, the system responds quickly and obtains their account identity information. Based on the obtained account identity information, the system queries in a pre-stored database and finds the corresponding operation habit information. This operation habit information is obtained by long-term collection of the nurse's historical operation data and analyzed by a perception neural network model. According to the queried operation habit information, the system further determines the rendering layout relationship between each display area and each control in the preset display interface. For example, if a certain nurse often uses the patient information query function and is used to placing it in a prominent position on the left side of the screen, the system will determine the rendering layout of this control in the left area of the display interface based on this habit. Based on the determined rendering layout relationship, the system renders in the display interface. During the process of the nurse using the terminal device, the system continuously obtains the current operation data of their current login. And, at a preset first time interval, the system will include these current operation data in the analysis scope to update the original operation habit information. By obtaining and analyzing the nurse's operation habit information and placing the commonly used function controls in the positions where the nurse is used to operating, it reduces the time for the nurse to search for controls and switch function modules. At the same time, the mechanism of real-time updating of operation habit information can keep up with the possible changes in the nurse's operation habits in a timely manner, further ensuring the convenience of operation and avoiding problems such as information entry errors and untimely queries caused by inconvenient operation. The nurse no longer needs to spend a lot of time looking for the required controls and switching functions in the fixed-layout interface, can quickly locate and operate the commonly used functions, saves operation time, enables the nurse to complete more nursing work tasks per unit time. On the other hand, the interface layout that conforms to personal operation habits reduces the risk of information entry errors caused by inconvenient operation. The nurse can focus more on the nursing work itself rather than being disturbed by the inconvenient operation interface, thereby improving the accuracy of nursing records and the reliability of medical information, enabling the nurse to complete the work more efficiently and accurately, and enabling the patient to receive more timely and high-quality nursing services.

[0064] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs, non-transitory computer-executable programs, and signals, such as the program instructions / signals corresponding to the processing module in the embodiments of the present application. The processor executes various functional applications and data processing by running the non-transitory software programs, instructions, and signals stored in the memory, that is, implements the personalized display method of the nurse terminal operation interface in the above method embodiments.

[0065] The memory may include a program storage area and a data storage area. Among them, the program storage area can store the operating system and application programs required for at least one function; the data storage area can store relevant data of the personalized display method of the nurse terminal operation interface described above, etc. In addition, the memory may include a high-speed random access memory and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory may optionally include a memory remotely set relative to the processor, and these remote memories can be connected to the processing module through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0066] One or more signals are stored in the memory and, when executed by one or more processors, implement the personalized display method of the nurse terminal operation interface in any of the above method embodiments.

[0067] In a third aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which, when executed by one or more processors, enables the one or more processors to implement the personalized display method of the nurse terminal operation interface in the above method embodiments.

[0068] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0069] Through the description of the above embodiments, those of ordinary skill in the art can understand that all or some of the steps and systems disclosed above can be implemented as software, firmware, hardware, and their appropriate combinations. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or can be implemented as hardware, or can be implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include a computer storage medium (or non-transitory medium) and a communication medium (or transitory medium). As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable signals, data structures, program modules, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassette, tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those of ordinary skill in the art that a communication medium generally includes computer-readable signals, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and can include any information delivery medium.

[0070] It should be understood that in this application, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects and indicates that three relationships can exist. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one (one) of the following" or its similar expression refers to any combination of these items, including any combination of single items (ones) or plural items (ones). For example, at least one (one) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0071] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the above units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling, direct coupling, or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be in electrical, mechanical, or other forms.

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

[0073] In addition, in each embodiment of the present application, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0074] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, 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. This computer software product is stored in a storage medium and includes multiple instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store programs.

[0075] The above has described the embodiments of the present application in detail with reference to the drawings. However, the present application is not limited to the above embodiments. Within the scope of knowledge possessed by those of ordinary skill in the art to which it pertains, various changes can be made without departing from the purpose of the present application.

Claims

1. A method for personalized display of the operation interface of a nurse terminal, characterized in that, Including: Upon receiving a login instruction from a nurse, obtain the account identity information; Query the corresponding operation habit information according to the account identity information; Determine the rendering layout relationship between each display area and each control in the preset display interface according to the operation habit information; Render in the display interface according to the rendering layout relationship; Obtain the current operation data of the nurse during the current login, and update the operation habit information at a preset first time interval according to the current operation data; Among them, the operation habit information is obtained according to the following steps: Obtain the historical operation data corresponding to the account identity information; Input the historical operation data into the input layer of a preset perception neural network model, and determine a first score set for each display area in the display interface and a second score set for each control through multiple hidden layers of the perception neural network model; Input the first score set and the second score set into the output layer of the perception neural network model to obtain the operation habit information.

2. The method for personalized display of the operation interface of a nurse terminal according to claim 1, characterized in that, After the step of obtaining the account identity information upon receiving the login instruction from the nurse, it further includes: When there is no corresponding operation habit information for the account identity information, generate a questionnaire and render the questionnaire on the display interface; Obtain the survey results filled in by the nurse and generate intention layout information according to the survey results; Render the controls in different display areas of the display interface according to the preset initial layout position.

3. The method for personalized display of the operation interface of a nurse terminal according to claim 2, characterized in that, The step of inputting the historical operation data into the input layer of a preset perception neural network model and determining a first score set for each display area in the display interface and a second score set for each control through multiple hidden layers of the perception neural network model includes: Obtain the intention layout information corresponding to the account identity information; Input the historical operation data and the intention layout information into the input layer of a preset perception neural network model, and assign a first confidence level and a second confidence level to the historical operation data and the intention layout information respectively through the input layer; Through multiple hidden layers of the perception neural network model, perform fusion processing on the historical operation data, the first confidence level, the intention layout information, and the second confidence level to obtain a first score set for each display area in the display interface and a second score set for each control.

4. The method for personalized display of the operation interface of a nurse terminal according to claim 3, characterized in that, The step of assigning a first confidence level and a second confidence level to the historical operation data and the intention layout information respectively through the input layer includes: Obtain the first timestamp of the last update of the historical operation data and the second timestamp of establishing the intention layout information through the input layer; Establish an assignment rule table; wherein, the assignment rule table is used to represent the relationship between the difference between the first timestamp and the second timestamp and the ratio between the first confidence level and the second confidence level; Based on the assignment rule table, determine the first confidence level of the historical operation data and the second confidence level of the intention layout information according to the first timestamp and the second timestamp.

5. The method for personalized display of the operation interface of a nurse terminal according to claim 3, characterized in that, The historical operation data includes: the historical usage time and historical usage area of each of the controls, and the intended layout information includes control usage requirements and habitual usage areas; The fusion processing of the historical operation data, the first confidence level, the intended layout information, and the second confidence level through multiple hidden layers of the perception neural network model to obtain a first scoring set for each display area of the display interface and a second scoring set for each of the controls includes: Determining a first usage scoring value for each of the controls through a first hidden layer of the perception neural network model according to the historical usage time of each of the controls, the first confidence level, the control usage requirements, and the second confidence level; Determining a second usage scoring value for each of the display areas through a second hidden layer of the perception neural network model according to the historical usage area, the first confidence level, the habitual usage area, and the second confidence level; Obtaining a first scoring set based on the multiple first usage scoring values, and obtaining a second scoring set based on the multiple second usage scoring values.

6. The method for personalized display of the operation interface of a nurse terminal according to claim 1, characterized in that, The perception neural network model is trained according to the following steps: Establish an initial perception neural network model; Obtain sample operation data and an expected display result corresponding to the sample operation data; Input the sample operation data into the perception neural network model to obtain an actual display result; wherein, the actual display result includes actual controls to be displayed and actual display areas of each of the actual controls; Obtaining a training loss value according to the actual display result and the expected display result; Adjusting the parameters of the perception neural network model according to the training loss value until the training loss value meets a preset convergence condition or the number of training times is greater than or equal to a preset number threshold, and stopping the training of the perception neural network model to obtain a trained perception neural network model.

7. The personalized display method of the nurse terminal operation interface according to claim 6, characterized in that, The perception neural network model is also trained according to the following steps: When the training loss value does not meet the convergence condition and the number of training times is less than the number threshold, performing gradient solution on the parameters of the perception neural network model according to a preset gradient algorithm and the training loss value to obtain a gradient vector; Obtaining a learning rate parameter according to the number of training times of the perception neural network model and a preset learning rate decay function; Updating the gradient vector according to the learning rate parameter; Adjusting the parameters of the perception neural network model according to the updated gradient vector.

8. The personalized display method of the nurse terminal operation interface according to claim 5, characterized in that, Determining the rendering layout relationship between each display area and each control in a preset display interface according to the operation habit information includes: Determining a first priority for each control corresponding to the current account identity information and a second priority for each display area according to the operation habit information; Determining the rendering layout relationship between each display area and each control in the preset display interface according to the first priority and the second priority.

9. An electronic device, characterized in that, Includes: At least one memory; At least one processor; At least one program; The program is stored in the memory, and the processor executes at least one of the programs to implement the method for personalized display of the nurse terminal operation interface according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable signals for executing the method for personalized display of the nurse terminal operation interface according to any one of claims 1 to 8.

Images