A method for order service management of medical products

Abstract

The present invention discloses an order service management method for medical products, and specifically relates to the technical field of medical order management, comprising the following steps: collecting order management information of each medical product and preprocessing it to generate an order service management information set; performing management monitoring degree analysis on the information set to determine whether there are early signs of insufficient monitoring degree; if early signs are found, extracting order management feature data and evaluating the management situation to provide a basis for classification; importing the feature data into a pre-trained machine learning model to classify the orders into low-quality and high-quality visual orders according to the management situation; for low-quality visual orders, regulating the information update frequency to ensure efficient information flow and transparency optimization, and summarizing the update frequency after application regulation; the present invention can effectively reduce misunderstandings and delays caused by information asymmetry, enhance the ability to control orders, and ensure the timeliness and reliability of information flow.

Description

Technical Field

[0001] The present invention relates to the technical field of medical order management, and more specifically, to an order service management method for medical products. Background Art

[0002] In the current medical industry, order management of medical products involves complex information flows and data processing processes. Medical product orders often include a variety of materials such as equipment, drugs, and consumables, which require high precision, timeliness, and tracking. The management of these orders directly affects the continuity of medical services and the safety of medical products. Traditional order management methods mainly rely on manual monitoring and regular updates, which are difficult to meet the high requirements of modern medical institutions for real-time and transparency. In this case, problems such as information lag and lack of transparency affect the efficiency and accuracy of order management, and reduce customer experience and trust.

[0003] Existing medical product order management systems usually rely on manual records, periodic updates or limited automated processes, which are inefficient when dealing with large order volumes and frequent updates. In particular, traditional systems lack transparency and traceability, making it difficult to respond to changes in order status in a timely manner, and are prone to problems such as delayed order information updates and untimely feedback. This makes it difficult for medical institutions to grasp the order status in real time, affecting the effective management of supplies and the continuity of patient services.

[0004] Although some order management systems have begun to introduce information functions, most of them remain at the level of basic data display and regular updates, lack the ability of intelligent analysis and dynamic optimization, find it difficult to automatically identify low-quality visual orders, and cannot flexibly adjust the update frequency of various types of order information, and cannot effectively improve order transparency and tracking effects. Therefore, an order service management method for medical products is proposed here. Summary of the invention

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for managing order services for medical products, comprising the following steps:

[0007] Collect and pre-process the order service management information of each medical product to obtain an order service management information set;

[0008] Conduct management monitoring analysis based on the order service management information set, and use the management monitoring analysis results to determine whether there are early signs of insufficient monitoring in order service management;

[0009] After early signs of insufficient monitoring are discovered, order service management feature extraction is performed first, and then the management status of order service management is evaluated to provide feature data for subsequent classification;

[0010] For each medical product order service management process, the characteristic data obtained after the management situation analysis is imported into the pre-trained machine learning model, and the medical product order service management process is divided into low-quality visual orders and high-quality visual orders according to the degree of perfection of the management situation;

[0011] For low-quality visualized orders, the update frequency of each order information is adjusted to ensure efficient flow and transparent optimization of information, and the update frequency of each order information after the adjustment is summarized and applied.

[0012] In a preferred embodiment, management monitoring analysis refers to:

[0013] Obtain the time series of various preset monitoring parameters from the order service management information set, and then calculate the average value and standard deviation corresponding to the time series of various preset monitoring parameters;

[0014] Then calculate the deviation value of each preset monitoring parameter:

[0015] ; t represents the serial number in the time series of the monitoring parameter, i represents the type of the preset monitoring parameter, Represents the sampling data of each item in the time series of the monitoring parameter corresponding to type i, represents the average value of the time series of the monitoring parameters corresponding to type i, represents the standard deviation of the time series of the monitoring parameters corresponding to type i, Indicates the deviation value corresponding to each sampling data in the time series of the monitoring parameter corresponding to type i;

[0016] Then calculate the order monitoring degree corresponding to various monitoring parameters in the entire monitoring period from the start of the order to the current time. The calculation formula is:

[0017] ; It represents the order monitoring degree of the monitoring parameter corresponding to type i, and N represents the total length of the time series.

[0018] In a preferred embodiment, judging whether there are early signs of insufficient monitoring during order service management through management monitoring analysis results refers to:

[0019] The order monitoring degree of the monitoring parameters corresponding to type i is Compare with the monitoring threshold corresponding to type i. If the order monitoring degree of the monitoring parameter corresponding to type i is If the order monitoring degree of the monitoring parameter corresponding to type i is greater than the monitoring threshold corresponding to type i, an abnormal signal is generated. If it is less than or equal to the monitoring threshold corresponding to type i, a normal signal is generated. When an abnormal signal exists, it indicates an early sign of insufficient monitoring.

[0020] In a preferred embodiment, order service management feature extraction includes order tracking information and order transparency information, and then an order tracking index is generated based on the order tracking information. The order tracking index is used to evaluate the traceability of each link in the process from order generation to completion. An order transparency index is generated based on the order transparency information. The order transparency index is used to evaluate the degree of acquisition of order information by order users. The order tracking index and the order transparency index are used together to reflect the management status of order service management.

[0021] In a preferred embodiment, the logic for obtaining the order tracking index is:

[0022] From the order tracking information, obtain the number of order status changes from order creation to the current stage, as well as the total time taken for the order to be created to the current stage, and then calculate the status change coefficient, which is obtained by dividing the number of order status changes by the total time taken;

[0023] Obtain the expected delivery time of the order at each stage from the creation of the order to the current stage, as well as the actual delivery time at each stage, calculate the absolute value of the difference between the expected delivery time and the actual delivery time of the order at each stage, and then multiply the absolute value by the preset timeliness adjustment coefficient of the corresponding stage to obtain the timeliness fluctuation value of each stage, and then calculate the average of all timeliness fluctuation values ​​to obtain the timeliness fluctuation coefficient;

[0024] Obtain the feedback data of order users from the creation of the order to the current stage and divide it into positive feedback, negative feedback, and neutral feedback according to the preset standards. Calculate the difference between the number of positive feedback and the number of negative feedback, and then divide the difference by the total number of all feedback to obtain the feedback satisfaction coefficient;

[0025] The formula for calculating the order tracking index is:

[0026] ; is a preset constant, represents the state change coefficient, represents the time-sensitive volatility coefficient, It represents the feedback satisfaction coefficient. Denotes the Order Tracking Index.

[0027] In a preferred embodiment, the logic for obtaining the order transparency index is:

[0028] From the order transparency information, obtain the frequency of logistics status updates and the total number of logistics information updates from the order creation to the current stage, and then calculate the logistics transparency. The logistics transparency is obtained by calculating the ratio of the logistics status update frequency to the total number of logistics information updates;

[0029] Obtain the average response time of order user feedback and the preset standard response time, and then calculate the feedback response transparency. The feedback response transparency is obtained by calculating the ratio of the average response time of order user feedback to the preset standard response time;

[0030] Obtain the status change data of the order during processing, count the number of recorded change events and the total number of actual change events, and then calculate the order change transparency. The order change transparency is calculated by calculating the ratio of the number of recorded change events to the total number of actual change events.

[0031] The formula for calculating the order transparency index is:

[0032] ; Indicates logistics transparency, Indicates feedback response transparency, Indicates order change transparency, Indicates the order transparency index.

[0033] In a preferred embodiment, the characteristic data obtained after the management situation analysis is imported into a pre-trained machine learning model, and the order service management process of medical products is divided into low-quality visual orders and high-quality visual orders according to the degree of perfection of the management situation.

[0034] The characteristic data obtained after the management situation analysis, namely the order transparency index and the order tracking index, are imported into the pre-trained convolutional neural network model. The output result of the convolutional neural network model is 0 or 1, 0 represents a low-quality visualized order, and 1 represents a high-quality visualized order.

[0035] In a preferred embodiment, for low-quality visual orders, regulating the update frequency of each order information refers to:

[0036] Get the preset basic update frequency of each order information and mark it as , Indicates the type of order information. The control formula is:

[0037] ; Indicates the order information type The corresponding adjustment factor, Indicates the order information type The corresponding priority coefficient is Represents the preset nonlinear growth coefficient, Indicates the order information type The corresponding impact value is calculated by the information type The ratio of the number of missing updates in the historical data to the total number of missing updates for all information types is obtained. Indicates the order information type The corresponding basic update frequency, Indicates the order information type The corresponding adjusted update frequency.

[0038] Technical effects and advantages of the present invention:

[0039] The present invention comprehensively improves the transparency of order management by introducing the order transparency index and the order tracking index, so that the status of each link can be tracked in real time. Order management personnel and customers, i.e. order users, can obtain key information such as logistics status, customer feedback, and order changes in a timely manner, effectively reducing misunderstandings and delays caused by information asymmetry, enhancing the ability to control orders, and ensuring the timeliness and reliability of information flow.

[0040] The present invention can automatically identify low-quality visual orders based on the tracking index and transparency index of the order, and dynamically adjust the information update frequency according to management needs. The key information of low-quality orders is updated more promptly, avoiding management risks caused by information lag. At the same time, the update frequency can be dynamically adjusted according to the missing and priority of historical data to ensure that important information is delivered first. Medical product order management is directly related to the supply of materials in hospitals and clinics. The present invention can ensure the timely and accurate delivery of medical products, avoid shortages or delays of key materials such as medicines and equipment, and help improve the continuity and safety of medical services. Especially in emergency situations, timely information updates and traceability can effectively support the emergency response capabilities of medical institutions.

[0041] When using the present invention, customers can understand the status and changes of orders in real time and gain a higher transparency experience. In addition, the feedback response transparency of the present invention ensures that customer feedback can be quickly processed and responded to, effectively improving customer satisfaction. For medical institutions, the timely update of information also reduces the workload of information query and improves the customer service experience. The present invention reduces the need for manual intervention and the labor cost of order management through automated analysis and intelligent decision-making. It can automatically identify and optimize low-quality orders, ensure the efficiency and accuracy of information updates without manual intervention, greatly reduce the workload of managers, and optimize the allocation of management resources.

[0042] By dynamically adjusting the frequency of order information updates, the present invention effectively improves the efficiency of order processing. High-quality orders are completed smoothly, low-quality orders are effectively improved, and resources are used more efficiently. Especially in medical product order management, the timeliness and accuracy of information directly affect the allocation and utilization efficiency of resources, thereby improving the overall management level. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0044] Figure 1 This is a schematic diagram of an order service management method for medical products in the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] Reference Figure 1 The following embodiments are obtained:

[0047] Embodiment 1: A method for order service management of medical products, comprising the following steps:

[0048] Collect and preprocess the order service management information of each medical product to obtain the order service management information set; in the order service management process, data collection and preprocessing are the basis. By collecting the service management information of each order, a complete information set of the order can be obtained, including the order status, logistics information, customer feedback, etc. This information set is the basis for subsequent analysis and decision-making. Preprocessing can clean and standardize the data, remove noise and invalid data, and ensure the accuracy of the analysis results.

[0049] Management monitoring degree analysis is performed based on the order service management information set. The results of the management monitoring degree analysis are used to determine whether there are early signs of insufficient monitoring in order service management. The purpose of management monitoring degree analysis is to detect potential problems in the order service management process. Through time series analysis of monitoring parameters (such as order processing time, status update frequency, etc.), the deviation value, average value, and standard deviation of each monitoring indicator can be calculated. Then, these indicators are used to determine whether there are early signs of insufficient monitoring. This analysis helps to identify possible anomalies in order management in advance and prevent order delays or customer dissatisfaction caused by poor management.

[0050] After early signs of insufficient monitoring are discovered, order service management features are extracted first, and then the management of order service management is evaluated to provide feature data for subsequent classification; once early signs of insufficient monitoring are found, the specific features of order management need to be further analyzed. Feature extraction includes order tracking information and order transparency information, which helps users to comprehensively evaluate the management of orders. The extracted feature data provides key data support for subsequent classification operations, ensuring the accuracy and pertinence of the classification results.

[0051] For each medical product order service management process, the characteristic data obtained after the management situation analysis will be imported into the pre-trained machine learning model, and the medical product order service management process will be divided into low-quality visual orders and high-quality visual orders according to the degree of perfection of the management situation; the characteristic data obtained from the management situation analysis will be input into the pre-trained machine learning model, and the orders will be divided into low-quality visual orders and high-quality visual orders through automatic classification of the model. This classification can help managers identify poorly managed orders and improve them, while efficiently processing well-managed orders. This intelligent classification method improves order management efficiency and allows resources to be focused on low-quality orders that need to be improved.

[0052] For low-quality visual orders, adjust the update frequency of each order information to ensure efficient information flow and transparent optimization, and summarize and apply the adjusted update frequency of each order information. For orders identified as low-quality visualization, improve transparency and information flow efficiency by adjusting the update frequency of their order information. This step adjusts the update frequency to ensure that order information is fed back to customers, i.e. order users and managers, more promptly and accurately during the management process, thereby improving the visualization of low-quality orders and ultimately making these orders meet high-quality management standards. By summarizing and applying the adjusted update frequency, the system can optimize the order management process in real time and improve the overall management quality and customer satisfaction.

[0053] In medical product order service management, "visualization" refers to the transparency and traceability of order information. Specifically, it includes the following aspects:

[0054] Information transparency: refers to whether all kinds of order information are clearly visible to customers and managers. For example, whether customers can check key information such as order status, logistics progress, and estimated arrival time at any time. The higher the transparency, the more comprehensive the user's understanding of the order, which can effectively reduce uncertainty.

[0055] Data traceability: refers to whether the information of each link in the order creation to completion process is fully recorded and traceable. For example, whether the status change of the order, logistics node information, and the time record of each link are accurately saved and presented by the system. High traceability means that every status and operation of the order is well documented, which is convenient for monitoring and auditing.

[0056] Real-time update and feedback: refers to whether the system can update order information in a timely manner, so that customers and managers can understand the current status, location and problems (such as delays, anomalies) of the order at the first time. If order information can be updated and fed back in real time, then the "visualization" level of the order is higher.

[0057] Lack of order tracking and transparency may lead to the following impacts:

[0058] Poor customer experience: Lack of order tracking function will cause customers to be unable to understand the processing and shipping progress of their orders in real time, which will make them feel uneasy or anxious, affecting customer satisfaction. For e-commerce platforms or supply chain companies, transparency is a key factor in maintaining customer trust. If customers do not have enough information, they may doubt the service and even lose customers.

[0059] Increase customer service burden: When customers cannot track their orders through self-service tools, they will seek help from customer service in large numbers. This not only increases the workload of customer service, but may also cause customers to wait too long, further reducing customer satisfaction and business operational efficiency.

[0060] Failure to detect problems in a timely manner: If the order tracking function is not comprehensive or real-time, there may be a delay in discovering problems that occur during the shipping process (such as delays, loss, damage, etc.). If the problem is not resolved in a timely manner, it may lead to customer complaints, affecting brand reputation and long-term customer relationships.

[0061] Reduced operational efficiency: Transparent order tracking helps monitor and optimize the supply chain in real time. Without real-time tracking information, companies cannot adjust inventory, production plans and logistics arrangements in a timely manner, resulting in inventory backlogs, order delays or excessive transportation costs.

[0062] Therefore, the real-time and comprehensive nature of order tracking is crucial, specifically:

[0063] Enhance customer trust and satisfaction: The real-time order tracking function allows customers to understand the latest status of their orders at any time, enhance customer trust and satisfaction with the company, and thus improve customer loyalty and repurchase rate.

[0064] Optimize supply chain management: Comprehensive order tracking allows companies to better control the entire supply chain process, identify potential delays or problems in a timely manner, and take quick remedial measures to reduce operational risks and improve efficiency.

[0065] Reduce customer service costs: The order tracking function can effectively reduce customers' dependence on customer service, reduce the burden of manual service through self-service inquiry, improve operational efficiency and reduce costs.

[0066] Improve problem handling speed: Real-time tracking information can help companies identify potential risks and problems during the order process, so that they can respond and resolve them quickly, avoiding delays and customer complaints.

[0067] Management monitoring analysis refers to:

[0068] The time series of various preset monitoring parameters are obtained from the order service management information set, and then the mean value and standard deviation corresponding to the time series of various preset monitoring parameters are calculated respectively; the time series set of monitoring parameters represents the time series data of various monitoring parameters obtained from the order service management information set, which is used to analyze the temporal variation trend of each monitoring parameter; the mean value is used to measure the average state of the corresponding monitoring parameter within the monitoring period, and the standard deviation reflects the volatility of the corresponding monitoring parameter, that is, the degree of dispersion of the data around the mean value.

[0069] Then calculate the deviation value of each preset monitoring parameter:

[0070] ; t represents the serial number in the time series of the monitoring parameter, i represents the type of the preset monitoring parameter, Represents the sampling data of each item in the time series of the monitoring parameter corresponding to type i, represents the average value of the time series of the monitoring parameters corresponding to type i, represents the standard deviation of the time series of the monitoring parameters corresponding to type i, It represents the deviation value corresponding to each sampling data in the time series of the monitoring parameters corresponding to type i. The deviation value is obtained by dividing the difference between the data and the average value by the standard deviation, which indicates the relative deviation degree of each sampling data from the overall mean. The larger the deviation value, the more the data deviates from the average value, which may indicate an abnormality.

[0071] Then calculate the order monitoring degree corresponding to various monitoring parameters in the entire monitoring period from the start of the order to the current time. The calculation formula is:

[0072] ; It represents the order monitoring degree of the monitoring parameter corresponding to type i. N represents the total length of the time series, that is, the number of sampled data in the entire monitoring period. It is used to calculate the mean of the deviation value to obtain the overall order monitoring degree. The order monitoring degree is calculated based on the average of the deviation value in the entire monitoring period. It is used to reflect the overall fluctuation degree of the corresponding monitoring parameters in the monitoring process, that is, the stability and consistency of the corresponding monitoring parameters in the entire period. A higher monitoring degree indicates that the data fluctuates greatly and there may be anomalies.

[0073] Early signs of insufficient monitoring in order service management can be determined through management monitoring analysis results:

[0074] The order monitoring degree of the monitoring parameters corresponding to type i is This comparison can identify whether the current monitoring parameters meet the expected monitoring standards, helping the system to detect potential management problems in advance. If the value of the monitoring parameter corresponding to type i is greater than the monitoring threshold corresponding to type i, an abnormal signal is generated, which indicates that the fluctuation of the monitoring parameter is large and there is an abnormality, which requires further attention. The generation of abnormal signals helps to identify the weak links in the management process in a timely manner. If the order monitoring degree of the monitoring parameter corresponding to type i is If the value is less than or equal to the monitoring threshold corresponding to type i, a normal signal is generated, indicating that the monitoring parameters are within the expected range and the order management process is normal. When there is an abnormal signal, it indicates that there are early signs of insufficient monitoring, indicating that potential problems may occur in the management process. By identifying early signs, you can respond before formal problems occur, optimize order service management, and reduce subsequent risks.

[0075] The order service management feature extraction includes order tracking information and order transparency information. Then, an order tracking index is generated based on the order tracking information. The order tracking index is used to evaluate the traceability of each link in the order generation to completion process. An order transparency index is generated based on the order transparency information. The order transparency index is used to evaluate the degree of acquisition of order information by order users. The order tracking index and the order transparency index are used together to reflect the management status of order service management.

[0076] Order tracking information refers to information such as status changes, delivery progress, and customer feedback during the entire life cycle of an order (from generation to completion). This information records each link of the order processing and provides a data basis for subsequent management and tracking. The order tracking index can help managers evaluate the degree of visualization of the order management process and ensure that each link from order generation to delivery is accurately and real-timely recorded. A high tracking index indicates that the order is traceable at every link, which helps to improve management transparency and reduce customer dissatisfaction and misunderstanding. Order transparency information includes the order status update frequency, customer feedback response time, change records, etc., which are directly related to whether users can obtain order-related information in a timely and accurate manner. The order transparency index helps evaluate the system's information disclosure and ensures that customers can keep abreast of order progress. A high transparency index indicates that information is transmitted smoothly and customers can obtain order status in a timely manner, which helps to enhance customer trust and satisfaction with the service.

[0077] The logic for obtaining the order tracking index is:

[0078] From the order tracking information, obtain the number of order status changes from order creation to the current stage, as well as the total time taken for the order from creation to the current stage, and then calculate the status change coefficient, which is obtained by dividing the number of order status changes by the total time taken; the status change coefficient can reveal the degree of dynamic change of the order in the entire management process. Frequent status updates can indicate that the order has been effectively tracked at different stages, while a lower status update frequency may indicate that the order status is unclear and the tracking is insufficient.

[0079] Obtain the expected delivery time of the order at each stage from the creation to the current stage, as well as the actual delivery time at each stage, calculate the absolute value of the difference between the expected delivery time and the actual delivery time of the order at each stage, and then multiply the absolute value by the preset timeliness adjustment coefficient of the corresponding stage to obtain the timeliness fluctuation value of each stage, and then calculate the average of all timeliness fluctuation values ​​to obtain the timeliness fluctuation coefficient; the timeliness fluctuation coefficient is used to evaluate the time consistency of the order throughout the delivery process. If the coefficient is low, it means that the order can be delivered on time and the timeliness is good; if the fluctuation coefficient is high, it means that the delivery time has a large fluctuation, which may cause order delays and affect customer satisfaction.

[0080] Obtain the feedback data of order users from the creation of the order to the current stage and divide it into positive feedback, negative feedback, and neutral feedback according to the preset standards. Calculate the difference between the number of positive feedback and the number of negative feedback, and then divide the difference by the total number of all feedback to obtain the feedback satisfaction coefficient; the feedback satisfaction coefficient helps measure the customer's evaluation and feedback on the order service. If the coefficient is high, it means that the overall customer satisfaction is high and the service quality is good; if the coefficient is low, it means that there are many negative comments in the customer feedback, and there may be service quality problems.

[0081] The formula for calculating the order tracking index is:

[0082] ; is a preset constant, represents the state change coefficient, represents the time-sensitive volatility coefficient, It represents the feedback satisfaction coefficient. Represents the order tracking index. By summing the squares of each coefficient and taking the square root, we ensure that each dimension contributes to the index in a balanced manner. This nonlinear processing method can effectively amplify the impact of fluctuations in different dimensions and emphasize the independence of each coefficient. If one of the coefficients fluctuates greatly, it will significantly affect the result of the order tracking index, thereby helping to identify tracking problems in specific aspects. By taking the logarithm of the result after summing the exponent and the constant, the difference in the final calculated order tracking index is further amplified. Logarithmic amplification can enhance the discrimination of the order tracking index at larger values ​​while avoiding over-amplification of smaller values, which also enables the order tracking index to more sensitively reflect the quality of the order tracking status. Logarithmic amplification of the calculation item can also avoid excessive expansion of the order tracking index, thereby maintaining a reasonable value range.

[0083] The logic for obtaining the order transparency index is:

[0084] From the order transparency information, we obtain the frequency of logistics status updates and the total number of logistics information updates from the order creation to the current stage, and then calculate the logistics transparency. The logistics transparency is obtained by calculating the ratio of the logistics status update frequency to the total number of logistics information updates; logistics transparency reflects whether the logistics information of the order is updated frequently and transparently. High logistics transparency indicates that logistics information is communicated in a timely manner, which helps customers and managers to grasp the logistics status of the order in real time, and improves customer experience and order management efficiency.

[0085] Get the average response time of order user feedback and the preset standard response time, and then calculate the feedback response transparency. The feedback response transparency is obtained by calculating the ratio of the average response time of order user feedback to the preset standard response time; feedback response transparency is used to evaluate the processing speed and transparency of customer feedback. If the value is high, it means that customer feedback can be responded to in a timely manner, the information transmission efficiency is high, and customer satisfaction and trust can be improved.

[0086] Obtain the status change data of the order during processing, count the number of recorded change events and the total number of actual change events, and then calculate the order change transparency. The order change transparency is obtained by calculating the ratio of the number of recorded change events to the total number of actual change events; order change transparency helps measure whether the information is recorded completely and timely when the order changes. High change transparency means that any order change will be fully recorded, providing clear traceability, which helps to improve the transparency of order management and the customer's right to know.

[0087] The formula for calculating the order transparency index is:

[0088] ; Indicates logistics transparency, Indicates feedback response transparency, Indicates order change transparency, Represents the order transparency index. Logarithmic term In the formula, the square of logistics transparency T1 and the product of feedback response transparency T2, plus the logarithmic term, can amplify the impact of high transparency values ​​while preventing low transparency from being overly amplified. The logarithmic term provides a nonlinear growth, making logistics and feedback transparency have a more significant impact on the overall transparency index, especially when both transparency levels are high. The formula can effectively distinguish high transparency orders. Square root term In the example, the cube of order change transparency T3 and the sum of logistics transparency T1 are squared to further increase the level of transparency. The cube term can amplify the impact of change transparency, so that transparency is enhanced for orders with frequent changes. The square root term increases the impact weight of order changes to ensure that the system can effectively reflect the transparency of orders with multiple changes or frequent status changes. This design is suitable for scenarios where strict tracking of change information is required, and helps to improve information transparency in complex order management.

[0089] Importing the characteristic data obtained after the management situation analysis into the pre-trained machine learning model, the order service management process of medical products is divided into low-quality visual orders and high-quality visual orders according to the degree of perfection of the management situation.

[0090] The characteristic data obtained after the management situation analysis, namely the order transparency index and the order tracking index, are imported into the pre-trained convolutional neural network model. The output result of the convolutional neural network model is 0 or 1, 0 represents a low-quality visualized order, and 1 represents a high-quality visualized order.

[0091] The order transparency index and order tracking index are input into the convolutional neural network model, and the order quality is classified through machine learning technology. This process is automated and intelligent, which helps to reduce the subjectivity and errors of manual judgment and improve the efficiency of order management. By automatically identifying low-quality visual orders, the management system can allocate more resources to these orders and improve their transparency and traceability. At the same time, automatic identification of high-quality visual orders means that these orders do not require too much intervention, which helps optimize resources. High-quality visual orders can provide customers with clear and traceable information, reducing customer dissatisfaction and complaints. By improving the transparency and traceability of low-quality visual orders, customer trust and satisfaction can be enhanced, and the overall service quality can be improved.

[0092] The convolutional neural network model works as follows:

[0093] Step 1: Input data preprocessing, converting the order transparency index and order tracking index into an input format acceptable to the model to form a two-dimensional feature matrix, similar to the format of image data. This matrix will be input to the convolution layer to facilitate the CNN model to extract feature patterns from the data.

[0094] Step 2: Convolutional layer extracts features. Convolution operation: In the convolutional layer, the model applies multiple filters (or convolution kernels) to perform sliding calculations on the input data to extract data features at different scales. For example, changes in order tracking and fluctuations in transparency may appear in filters in different areas. Nonlinear activation: Through activation functions (such as ReLU), nonlinearity is introduced to enable the model to handle more complex feature combinations.

[0095] Step 3: Pooling layer dimensionality reduction. In the pooling layer, by taking the maximum or average value of the data, the model reduces the dimension of the feature map, reduces the number of parameters and calculations, retains important features, and suppresses noise. The data after dimensionality reduction retains the core information, which is convenient for subsequent classification.

[0096] Step 4: Fully connected layer for classification, the output of the convolution and pooling layers is passed to the fully connected layer to map the high-dimensional features into a vector. In the last layer, the fully connected layer uses an activation function (such as softmax) to output the classification result: 0 represents a low-quality visualization order and 1 represents a high-quality visualization order.

[0097] Step 5: Output results. The CNN model will output 0 or 1, indicating low-quality and high-quality visual orders, respectively. Based on the output of the model, the orders can be automatically classified and corresponding management optimization measures can be implemented.

[0098] For low-quality visual orders, the update frequency of each order information is regulated as follows:

[0099] Get the preset basic update frequency of each order information and mark it as , which ensures that all items, i.e. order information of all types, have a basic update frequency that will not be lower than this value, Indicates the type of order information. For example, order information types may include logistics information, customer feedback, status changes, etc. Each type of information has different update requirements and importance. The control formula is:

[0100] ; Indicates the order information type The corresponding adjustment factor is used to adjust the update frequency of different information types. For example, some information types may need to be updated more frequently, so the adjustment factor can take a larger value. Indicates the order information type The corresponding priority coefficient indicates the importance or priority of the information type. Information types with higher priority will be updated more frequently, thereby improving their transparency. Represents the preset nonlinear growth coefficient, which is used to control the nonlinear growth of the update frequency. At higher values, the increase in update frequency is more significant. Indicates the order information type The corresponding impact value reflects the historical update missing ratio of the information type. The ratio of the number of missing updates in the historical data to the total number of missing updates for all information types is obtained, indicating the importance of the information type in the historical data. Indicates the order information type The corresponding basic update frequency, Indicates the order information type The corresponding update frequency after regulation can optimize the information update of low-quality orders through the adjustment of this frequency, improve its transparency and visualization, and finally summarize and apply the update frequency of each order information after regulation.

[0101] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0102] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0103] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0104] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0105] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for order service management of medical products, characterized in that: The following steps are involved: Collect and pre-process the order service management information of each medical product to obtain an order service management information set; Conduct management monitoring analysis based on the order service management information set, and use the management monitoring analysis results to determine whether there are early signs of insufficient monitoring in order service management; After early signs of insufficient monitoring are discovered, order service management feature extraction is performed first, and then the management status of order service management is evaluated to provide feature data for subsequent classification; For each medical product order service management process, the characteristic data obtained after the management situation analysis is imported into the pre-trained machine learning model, and the medical product order service management process is divided into low-quality visual orders and high-quality visual orders according to the degree of perfection of the management situation; For low-quality visual orders, adjust the update frequency of each order information to ensure efficient flow and transparent optimization of information, and summarize and apply the adjusted update frequency of each order information; Management monitoring analysis refers to: Obtain the time series of various preset monitoring parameters from the order service management information set, and then calculate the average value and standard deviation corresponding to the time series of various preset monitoring parameters; Then calculate the deviation value of each preset monitoring parameter: ; t represents the serial number in the time series of the monitoring parameter, i represents the type of the preset monitoring parameter, Represents the sampling data of each item in the time series of the monitoring parameter corresponding to type i, represents the average value of the time series of the monitoring parameters corresponding to type i, represents the standard deviation of the time series of the monitoring parameters corresponding to type i, Indicates the deviation value corresponding to each sampling data in the time series of the monitoring parameter corresponding to type i; Then calculate the order monitoring degree corresponding to various monitoring parameters in the entire monitoring period from the start of the order to the current time. The calculation formula is: ; represents the order monitoring degree of the monitoring parameter corresponding to type i, and N represents the total length of the time series; The order service management feature extraction includes order tracking information and order transparency information. Then, an order tracking index is generated based on the order tracking information. The order tracking index is used to evaluate the traceability of each link in the order generation to completion process. An order transparency index is generated based on the order transparency information. The order transparency index is used to evaluate the degree of acquisition of order information by order users. The order tracking index and the order transparency index are used together to reflect the management status of order service management.

2. The order service management method for medical products according to claim 1, characterized in that: Early signs of insufficient monitoring in order service management can be determined through management monitoring analysis results: The order monitoring degree of the monitoring parameters corresponding to type i is Compare with the monitoring threshold corresponding to type i. If the order monitoring degree of the monitoring parameter corresponding to type i is If the order monitoring degree of the monitoring parameter corresponding to type i is greater than the monitoring threshold corresponding to type i, an abnormal signal is generated. If it is less than or equal to the monitoring threshold corresponding to type i, a normal signal is generated. When an abnormal signal exists, it indicates an early sign of insufficient monitoring.

3. The order service management method for medical products according to claim 2, characterized in that: The logic for obtaining the order tracking index is: From the order tracking information, obtain the number of order status changes from order creation to the current stage, as well as the total time taken for the order to be created to the current stage, and then calculate the status change coefficient, which is obtained by dividing the number of order status changes by the total time taken; Obtain the expected delivery time of the order at each stage from the creation of the order to the current stage, as well as the actual delivery time at each stage, calculate the absolute value of the difference between the expected delivery time and the actual delivery time of the order at each stage, and then multiply the absolute value by the preset timeliness adjustment coefficient of the corresponding stage to obtain the timeliness fluctuation value of each stage, and then calculate the average of all timeliness fluctuation values ​​to obtain the timeliness fluctuation coefficient; Obtain the feedback data of order users from the creation of the order to the current stage and divide it into positive feedback, negative feedback, and neutral feedback according to the preset standards. Calculate the difference between the number of positive feedback and the number of negative feedback, and then divide the difference by the total number of all feedback to obtain the feedback satisfaction coefficient; The formula for calculating the order tracking index is: ; is a preset constant, represents the state change coefficient, represents the time-sensitive volatility coefficient, It represents the feedback satisfaction coefficient, Denotes the Order Tracking Index.

4. The order service management method for medical products according to claim 3, characterized in that: The logic for obtaining the order transparency index is: From the order transparency information, obtain the frequency of logistics status updates and the total number of logistics information updates from the order creation to the current stage, and then calculate the logistics transparency. The logistics transparency is obtained by calculating the ratio of the logistics status update frequency to the total number of logistics information updates; Obtain the average response time of order user feedback and the preset standard response time, and then calculate the feedback response transparency. The feedback response transparency is obtained by calculating the ratio of the average response time of order user feedback to the preset standard response time; Obtain the status change data of the order during processing, count the number of recorded change events and the total number of actual change events, and then calculate the order change transparency. The order change transparency is calculated by calculating the ratio of the number of recorded change events to the total number of actual change events. The formula for calculating the order transparency index is: ; Indicates logistics transparency, Indicates feedback response transparency, Indicates order change transparency, Indicates the order transparency index.

5. The order service management method for medical products according to claim 4, characterized in that: Importing the characteristic data obtained after the management situation analysis into the pre-trained machine learning model, the order service management process of medical products is divided into low-quality visual orders and high-quality visual orders according to the degree of perfection of the management situation. The characteristic data obtained after the management situation analysis, namely the order transparency index and the order tracking index, are imported into the pre-trained convolutional neural network model. The output result of the convolutional neural network model is 0 or 1, 0 represents a low-quality visualized order, and 1 represents a high-quality visualized order.

6. The order service management method for medical products according to claim 5, characterized in that: For low-quality visual orders, the update frequency of each order information is regulated as follows: Get the preset basic update frequency of each order information and mark it as , Indicates the type of order information. The control formula is: ; Indicates the order information type The corresponding adjustment factor, Indicates the order information type The corresponding priority coefficient is Represents the preset nonlinear growth coefficient, Indicates the order information type The corresponding impact value is calculated by the information type The ratio of the number of missing updates in the historical data to the total number of missing updates for all information types is obtained. Indicates the order information type The corresponding basic update frequency, Indicates the order information type The corresponding adjusted update frequency.

Images