A service optimization management system for remote medical services

Abstract

The present invention provides a service optimization management system for telemedicine services, which relates to the field of data processing technology. The system includes: retrieving multiple queue information sets based on the reception window, extracting multiple queue personnel characteristics for differential identification of consultation time, generating multiple consultation time prediction data, monitoring queue conflicts based on the appointment queue information set and the online queue information set, building a queue time prediction model, generating a consultation queue time data set, formulating multiple exclusive channels, performing feedback response through the user terminal, optimizing the multiple consultation time prediction data according to the feedback response results, updating the consultation queue time data set, and realizing the optimization management of telemedicine services. The technical effects of more accurate resource allocation and service optimization, improving service efficiency and quality, reducing patient waiting time, and improving patient satisfaction are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a service optimization management system for remote medical services. Background Art

[0002] With the rapid development of information technology and the growing demand for medical care, telemedicine service platforms have become an important innovation direction in the field of medical services. By integrating information technology and medical resources, telemedicine service platforms have achieved cross-regional and cross-time medical service provision, greatly improving the accessibility and efficiency of medical services. However, the operation of telemedicine service systems involves multiple complex links and factors, resulting in problems such as uneven distribution of medical resources, low service quality and efficiency.

[0003] Among the current related technologies, the telemedicine service system has technical problems such as uneven distribution of medical resources, low service quality and efficiency. Summary of the invention

[0004] The present application provides a service optimization management system for telemedicine services, which is used to solve the technical problems in the current related technologies, such as uneven distribution of medical resources, low service quality and efficiency in telemedicine service systems.

[0005] In view of the above problems, the present application provides a service optimization management system for telemedicine services, the system comprising:

[0006] An information retrieval module, the information retrieval module is used to retrieve multiple queue information sets based on the reception window, the multiple queue information sets include an appointment queue information set and an online queue information set;

[0007] A feature extraction module, wherein the feature extraction module is used to extract features of multiple queue personnel to perform differentiated identification of consultation duration and generate multiple consultation duration prediction data, wherein the multiple consultation duration prediction data correspond to the multiple queue personnel;

[0008] A prediction model building module, the prediction model building module is used to monitor queue conflicts based on the appointment queue information set and the online queue information set, build a queue duration prediction model, dynamically adjust the queue duration data set according to the monitoring results combined with the multiple consultation duration prediction data, and generate a consultation queue duration data set;

[0009] A channel formulation module, the channel formulation module is used to traverse the consultation queue time data set to formulate multiple exclusive channels, and formulate a queue optimization strategy through the multiple exclusive channels;

[0010] An optimization result transmission module is used to execute the queue optimization strategy and transmit the optimization results to the user terminal, perform feedback response through the user terminal, optimize the multiple consultation time prediction data according to the feedback response results, update the consultation queue time data set, and realize the optimized management of telemedicine services.

[0011] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0012] The embodiment of the present application provides a service optimization management system for telemedicine services, which retrieves multiple queue information sets based on the reception window, wherein the multiple queue information sets include an appointment queue information set and an online queue information set, extracts multiple queue personnel characteristics for differential identification of consultation time, generates multiple consultation time prediction data, and the multiple consultation time prediction data correspond to multiple queue personnel, performs queue conflict monitoring based on the appointment queue information set and the online queue information set, constructs a queue time prediction model, dynamically adjusts the queue time data set according to the monitoring results combined with the multiple consultation time prediction data, generates a reception queue time data set, traverses the reception queue time data set to formulate multiple exclusive channels, formulates a queue optimization strategy through the multiple exclusive channels, executes the queue optimization strategy and transmits the optimization result to the user terminal, performs feedback response through the user terminal, optimizes the multiple consultation time prediction data according to the feedback response result, updates the reception queue time data set, and realizes the optimization management of telemedicine services. The technical effects of more accurate resource allocation and service optimization, improving service efficiency and quality, reducing patient waiting time, and improving patient satisfaction are achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0014] Figure 1 A schematic diagram of the structure of a service optimization management system for telemedicine services provided in this application.

[0015] Figure 2 A schematic diagram of the structure of a feature extraction module of a service optimization management system for telemedicine services provided in this application.

[0016] Explanation of the accompanying drawings: information retrieval module 10, feature extraction module 20, prediction model construction module 30, channel formulation module 40, optimization result transmission module 50, personnel information retrieval unit 21, consultation group division unit 22, consultation time acquisition unit 23, prediction channel construction unit 24. DETAILED DESCRIPTION

[0017] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0018] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0019] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0020] The present application embodiment provides a service optimization management system for telemedicine services, such as Figure 1 As shown, the system includes:

[0021] The information retrieval module 10 is used to retrieve multiple queue information sets based on the reception window, and the multiple queue information sets include an appointment queue information set and an online queue information set.

[0022] Specifically, in the medical service management system, the information retrieval module 10 is a key component for collecting, organizing and displaying user queue-related information. The information retrieval module 10 retrieves multiple queue information sets from the reception window. The reception window refers to the online registration and number-taking platform, which stores relevant information about patients online or on appointment. The multiple queue information sets include an appointment queue information set and an online queue information set. The appointment queue information set refers to the appointment registration queue information from the online platform, and the online queue information set refers to real-time online registration or number-taking information. By extracting the appointment queue and online queue information, decision support is provided for hospital optimization management.

[0023] The feature extraction module 20 is used to extract features of multiple queue personnel to perform differentiated identification of consultation duration and generate multiple consultation duration prediction data, wherein the multiple consultation duration prediction data correspond to multiple queue personnel.

[0024] Specifically, the feature extraction module is mainly responsible for extracting personnel features, such as age, health status, number of historical visits, etc., from multiple queue information sets collected by the reception window, and using machine learning or statistical methods based on the extracted personnel features to identify the differences in consultation time between different queue personnel. For example, the consultation time of elderly patients is generally longer because they may have multiple health problems and limited processing speed and comprehension ability. Based on the above differentiated identification, multiple consultation time prediction data of multiple queue personnel are obtained, and the multiple consultation time prediction data correspond to the multiple queue personnel, that is, each generated consultation time prediction data corresponds to the corresponding queue personnel. Based on this, it can help medical institutions better predict and manage patients' waiting time, thereby optimizing resource allocation.

[0025] In one embodiment, Figure 2 As shown, the feature extraction module 20 further includes: a personnel information retrieval unit 21, the personnel information retrieval unit 21 is used to retrieve the information of multiple queue personnel at the reception window, perform feature analysis based on the information of the multiple queue personnel, and determine the characteristics of the multiple queue personnel; a consultation group division unit 22, the consultation group division unit 22 is used to divide the multiple consultation groups based on the characteristics of the multiple queue personnel by feature coding; a consultation time acquisition unit 23, the consultation time acquisition unit 23 is used to obtain multiple consultation time data by clustering analysis of the historical consultation time of the multiple consultation groups; a prediction channel construction unit 24, the prediction channel construction unit 24 is used to construct a time prediction channel based on the multiple consultation time data, predict the consultation time of multiple queue personnel through the time prediction channel, and generate the multiple consultation time prediction data.

[0026] Specifically, the personnel information retrieval unit 21 is responsible for retrieving multiple queue personnel information from the reception window system, and the queue personnel information includes the patient's age, gender, health status and language ability, etc., and according to the age, gender, health status and language ability of multiple queue patients, combined with historical data and medical expertise, the consultation time characteristics of different patient groups are analyzed to obtain the time characteristics of each of the multiple queue personnel, for example, age: the elderly and young people may have different processing speeds and understanding abilities of information; gender: some health problems may differ between genders, thus affecting the consultation time; health status: the patient's health status, such as chronic diseases, acute diseases, etc., may affect the depth and duration of the consultation; language ability: non-native patients may need longer time to communicate. The consultation group division unit 22 performs feature coding and divides the multiple queue personnel features extracted by the personnel information retrieval unit into multiple consultation groups, that is, converting the collected data into a format suitable for analysis, for example, age can be a continuous variable, while gender and health status can be categorical variables, and different consultation groups are divided according to the encoded multiple queue personnel features using clustering algorithms or rules.

[0027] Next, the historical consultation time data of each consultation group is extracted from the medical system database, and the consultation time acquisition unit 23 processes the historical consultation time data of each consultation group through cluster analysis to identify the consultation time data of different consultation groups, that is, multiple consultation time data. Through the multiple consultation time data provided by the consultation time acquisition unit 23, the prediction channel construction unit 24 uses machine learning or statistical methods to construct a time prediction channel based on multiple consultation time data and multiple queue personnel characteristics. Through the time prediction channel, the consultation group to which the multiple queue personnel belong is determined according to the personnel characteristics of the multiple queue personnel, and the consultation time prediction data of the corresponding personnel is generated, so as to achieve the technical effect of accurately obtaining the consultation time of the queue personnel and facilitating the subsequent medical service management of the hospital.

[0028] The prediction model building module 30 is used to monitor queue conflicts based on the appointment queue information set and the online queue information set, build a queue duration prediction model, dynamically adjust the queue duration data set according to the monitoring results and the multiple consultation duration prediction data, and generate a consultation queue duration data set.

[0029] Specifically, the prediction model construction module 30 receives the appointment queue information set and the online queue information set retrieved by the information retrieval module 10, and performs queue conflict monitoring on the appointment queue information set and the online queue information set. The queue conflict monitoring refers to monitoring whether the online queue is exceeded. When the online queue is exceeded, the appointment is retained. When the online queue is reached, it is decided whether to retain the appointment based on user feedback. According to the queue conflict monitoring, the monitoring results are obtained, and a queue time prediction model is constructed based on multiple queue time information sets using machine learning algorithms, such as neural networks, random forests, etc. The queue time prediction model is used to predict the queue time of patients after appointment registration. The monitoring results are then combined with the multiple consultation time prediction data to more accurately estimate the actual waiting time and consultation time required by the patients. When it is found after combination that the actual waiting time of the patients may be long or there are other emergency situations, the queuing time data set is dynamically adjusted to generate a consultation queuing time data set. The dynamically adjusted queuing time data set is adjusted in a manner such as adjusting the number of people in the channel to reallocate patients with longer waiting times to windows with shorter waiting times. The consultation queuing time data set refers to a new consultation queuing time data set that has been dynamically adjusted to achieve the optimal queuing time after the first adjustment.

[0030] In a possible implementation, the prediction model building module 30 further includes: an information set matching unit, the information set matching unit is used to match the appointment queue information set with the online queue information set to generate a two-way queue matching information set; an information monitoring unit, the information monitoring unit is used to activate a conflict monitoring mechanism to perform real-time monitoring on the appointment queue information set and the online queue information set based on the two-way queue matching information set, and when the online queue information of the target user arrives at the consulting service window, detect whether the target user arrives at the consulting service window within a specified time; a first preset waiting time judgment unit, the first preset waiting time judgment unit is used to, if the target user arrives at the consulting service window within a preset waiting time interval, The appointment queuing information of the target user is then obtained, and the target user is prompted to determine whether to retain the appointment queuing information. If retained, the appointment queuing information is stored and appointment retention information is generated. If not retained, appointment cancellation information is generated and the appointment queuing information of the target user is deleted; a second preset waiting time judgment unit, the second preset waiting time judgment unit is used to extract the online queuing information of the target user based on the next user in the online queuing information set to the consultation service window if the target user does not arrive at the consultation service window within the preset waiting time interval, automatically retain the appointment queuing information of the target user, and send reminder information to the target user, the reminder information including overdue reminder information and appointment retention information.

[0031] Specifically, the information set matching unit matches the appointment queue information set and the online queue information set to obtain a two-way queue matching information set, which refers to a patient data set that has both appointments and online queues. The information monitoring unit activates a conflict monitoring mechanism based on the obtained two-way queue matching information set, which monitors the appointment queue information set and the online queue information set of the patients in the two-way matching information set in real time, and when it is detected that the target user's online queue information arrives at the consultation service window, it detects and determines whether the target user arrives at the consultation service window within a specified time, which refers to a preset maximum time range that allows the target user to delay arriving after its online queue information arrives at the consultation service window.

[0032] When the first preset waiting time judgment unit determines that the target user arrives at the consulting service window within the preset waiting time interval, the target user's appointment queuing information is obtained, and the target user is prompted to see whether the target user retains the appointment queuing information. If the target user chooses to retain the appointment queuing information, the appointment queuing information is stored and appointment reservation information is generated. If the user chooses not to retain, appointment cancellation information is generated and the target user's appointment queuing information is deleted.

[0033] When the second preset waiting time judgment unit determines that the target user has not arrived at the consultation service window within the preset waiting time interval, the current target user is processed as overdue, and then the queue information of the next user in the online queue information set is extracted to the consultation service window, so that the next patient of the target user can consult, and the target user's appointment queue information is automatically retained, and a reminder message containing an overdue reminder and an appointment reservation is sent to the target user to remind the target user that the consultation service desk has overdue the appointment, but the appointment number is still there. The information matching unit matches the two-way queue matching information set, the information monitoring unit monitors and triggers subsequent operations in real time, and the first preset waiting time judgment unit and the second preset waiting time judgment unit respond according to the user's arrival situation, which can optimize the allocation of medical resources, reduce the patient's waiting time, and improve the efficiency of medical treatment.

[0034] In a possible implementation, the prediction model construction module 30 further includes: a queue time information calculation unit, which is used to calculate and obtain multiple queue time information sets based on the multiple queue time information sets; a data partitioning unit, which is used to perform data partitioning according to the multiple queue time information sets to obtain target independent variables and target dependent variables; a long short-term memory network generation unit, which is used to construct a training set, a supervision set, and a test set based on the target independent variable and the target dependent variable, and perform supervised training through the training set and the supervision set to generate a long short-term memory network; a queue time prediction model output unit, which is used to test and verify the long short-term memory network through the test set, and output the queue time prediction model.

[0035] Specifically, the queuing time information calculation unit extracts and calculates multiple queuing time information of the multiple queuing time information sets from the multiple queuing time information sets, that is, calculates and integrates the queuing time of each patient in the multiple queuing time information sets to generate multiple queuing time information sets. The data division unit reads the multiple queuing time information sets, analyzes the data in the multiple queuing time information sets, determines which variables can be used as independent variables and which variables can be used as dependent variables, and then divides the queuing time data into target independent variables and target dependent variables. The target independent variables refer to variable information that affects the multiple queuing time information sets. Optionally, the target independent variables include categorical independent variables and weather independent variables. The categorical variables are, for example, working days, weekends, holidays, etc. The weather independent variables can be converted into numerical variables, such as temperature, humidity, etc. The target dependent variable refers to the dependent variable that changes due to the change of the target independent variable, that is, the target dependent variable is the queuing time. Then, the LSTM network generation unit constructs a training set, a supervision set, and a test set according to the target independent variable and the target dependent variable, initializes the structure and parameters of the LSTM network, uses the training set and the supervision set to train the LSTM network, and monitors the training process, such as the decrease of the loss function. When the preset number of training rounds is reached or the performance of the validation set is no longer improved, the training is stopped and the model is saved to generate the LSTM network. The queue time prediction model output unit uses the test set to test and verify the trained LSTM network, and evaluates the network performance. If the model performance meets the requirements, the final queue time prediction model is output. Otherwise, the model structure or parameters are adjusted, and the training is re-performed to output the final queue time prediction model, which can provide accurate and reliable queue time prediction services, and thus can optimize resource allocation and service processes in a targeted manner.

[0036] In one possible implementation, the prediction model construction module 30 further includes: a queuing time data set output unit, which is used to synchronize the multiple queuing information sets to the queuing time prediction model for prediction, and output the queuing time data set; a queuing conflict analysis unit, which is used to analyze whether there is a queuing conflict in the monitoring result, and if so, obtain the appointment cancellation information and the overdue number reminder information, and dynamically adjust the queuing time data set based on the appointment cancellation information, the overdue number reminder information, and the multiple consultation time prediction data to generate the consultation queuing time data set; a data set dynamic adjustment unit, which is used to automatically allocate consultation time periods to multiple queuing personnel in combination with the multiple consultation time prediction data if there is no queuing conflict in the monitoring result, and dynamically adjust the queuing time data set according to the allocation result to generate the consultation queuing time data set.

[0037] Specifically, the queue time data output unit synchronizes the obtained multiple queue information sets to the trained queue time prediction model for prediction, and outputs the queue time data set predicted by the model. The queue conflict analysis unit analyzes whether there is a queue conflict in the real-time monitoring results, which is that there is both an appointment and an online queue. When this happens, the appointment cancellation information and the over-number reminder information are obtained, and then the queue time data set is dynamically adjusted according to the appointment cancellation information, the over-number reminder information and the multiple consultation time prediction data, such as updating the queue order, etc., to generate the consultation queue time data set, so as to achieve the optimal queue time after the first adjustment. When there is no queue conflict in the real-time monitoring results, the data set dynamic adjustment unit combines the consultation time prediction data, and automatically allocates consultation time periods to multiple queue personnel according to the prediction data and the current service window status, and then dynamically adjusts the queue time data set according to the allocation results, updates the queue order and waiting time of each patient, and generates an adjusted consultation queue time data set. Through the coordinated work of these three units, a complete queue time prediction and management system is formed, which can monitor the queue situation in real time, predict the queue time, and then dynamically adjust the queue data set to improve service efficiency and optimize resource allocation and service processes.

[0038] The channel formulation module 40 is used to traverse the consultation queuing time data set to formulate multiple exclusive channels, and formulate a queuing optimization strategy through the multiple exclusive channels.

[0039] Specifically, the channel formulation module 40 formulates multiple exclusive channels based on the consultation queue time data set, and formulates a queue optimization strategy through these exclusive channels. The channel formulation module 40 first traverses the consultation queue time data set to understand the current queue status, the patient's expected consultation time, waiting time and other information, and based on the traversed data, formulates multiple exclusive channels according to patient needs, service type, expected waiting time and other information, and then formulates a queue optimization strategy based on the exclusive channels. The queue optimization strategy includes but is not limited to: giving priority to patients with longer expected waiting times, providing fast channels for specific types of patients, adjusting service personnel or equipment allocation to optimize resource utilization, etc. The channel formulation module can effectively use the consultation queue time data set to optimize the queue management process, improve service efficiency, reduce patient waiting time, and improve patient satisfaction.

[0040] In a possible implementation, the channel formulation module 40 further includes: a queuing data acquisition unit, the queuing data acquisition unit is used to acquire queuing data of multiple time periods based on the consultation queuing time data set; a queuing data analysis unit, the queuing data analysis unit is used to analyze the queuing data of the multiple time periods to identify and extract peak time periods, and the peak time periods include peak time periods and off-peak time periods; a queuing time feature generation unit, the queuing time feature generation unit is used to extract queuing time features based on the peak time periods and the off-peak time periods, and generate peak queuing time features and off-peak queuing time features; an exclusive channel formulation unit, the exclusive channel formulation unit is used to formulate multiple exclusive channels according to the peak queuing time features and the off-peak queuing time features, and the multiple exclusive channels include multiple ordinary channels, multiple fast channels, and multiple emergency channels.

[0041] Specifically, the queue data acquisition unit extracts and organizes the queue data of multiple time periods from the consultation queue time data set to obtain the queue data of each time period and the busyness of the service window, etc. The time period can be divided according to actual needs, such as half an hour, two hours, etc. The queue data analysis unit receives the queue data of multiple time periods from the queue data acquisition unit, and uses statistical analysis methods, such as moving average, peak detection algorithm, etc., to analyze the queue data of multiple time periods, identify and extract peak time periods, including peak time periods and off-peak time periods. The queue time feature generation unit extracts the queue data of the corresponding time periods, such as waiting time, average waiting time, maximum waiting time, etc., based on the queue data of the peak time periods and off-peak time periods, and generates peak queue time features and off-peak queue time features according to the queue data of the corresponding time periods, such as the average waiting time and expected consultation speed of the peak time period, the average waiting time and expected consultation speed of the off-peak time period, etc. The exclusive channel formulation unit formulates multiple exclusive channels according to the characteristics of peak queuing time and off-peak queuing time, including multiple ordinary channels, multiple fast channels and multiple emergency channels. When there are important but non-urgent patients, such as chronic major diseases, slow-developing but serious fatal diseases, unimportant but urgent patients, such as acute minor diseases, such as patients with minor diseases but severe pain, and urgent and important patients, corresponding exclusive channels can be used. For example, acute minor diseases can go through the fast channel, which has the second highest priority after the emergency channel, and the priority of urgent and important ones is the highest, and the emergency channel has the highest priority. Increasing the number of fast channels during peak hours according to multiple exclusive channels can alleviate the congestion of ordinary channels, adjusting resource allocation during off-peak hours, optimizing the reception efficiency of ordinary channels, and reducing the waiting time of patients in emergency situations through emergency channels. By formulating and adjusting exclusive channels, the technical effects of improving service efficiency, reducing patient waiting time, and improving patient satisfaction can be achieved.

[0042] The optimization result transmission module 50 is used to execute the queue optimization strategy and transmit the optimization result to the user terminal, perform feedback response through the user terminal, optimize the multiple consultation time prediction data according to the feedback response results, update the consultation queue time data set, and realize the optimized management of telemedicine services.

[0043] Specifically, the optimization result transmission module 50 receives the queue optimization strategy formulated by the channel formulation module 40, executes the queue optimization strategy, and transmits the optimization strategy result to the user terminal in real time. After receiving the optimization result, the user terminal responds with feedback and provides real-time feedback data. The optimization result transmission module 50 then optimizes the consultation time prediction data according to the feedback response result, and updates the consultation queue time data set, thereby realizing the continuous optimization management of telemedicine services, thereby improving the efficiency and quality of telemedicine services.

[0044] In a possible implementation, the optimization result transmission module 50 further includes: an optimization result receiving unit, which is used to receive the optimization result through the user terminal and generate a pre-filled instruction; a feedback information generating unit, which is used to prompt the user of the user terminal to provide feedback through the pre-filled instruction and generate pre-filled feedback information; a feedback response result generating unit, which is used to establish an electronic medical record sharing platform, transmit the pre-filled feedback information to the electronic medical record sharing platform for response, and generate the feedback response result.

[0045] Specifically, the optimization result receiving unit receives the optimization result through the user terminal, and parses the received optimization result, including information about service optimization, channel configuration, waiting time, etc. Based on the parsed optimization result, a pre-filled instruction is generated. The feedback information generating unit prompts the user to provide feedback through the pre-filled instruction, receives the feedback provided by the user based on the pre-filled instruction, generates pre-filled feedback information, shortens the consultation time through the pre-filled information, and gradually improves the efficiency and accuracy of the entire telemedicine service service optimization management system by continuously receiving optimization results, generating pre-filled instructions, collecting user feedback and optimizing. The feedback response result generating unit establishes or accesses an existing electronic medical record sharing platform, and requires ensuring the security and stability of the sharing platform, and then transmits the pre-filled feedback information generated by the feedback information generating unit to the electronic medical record sharing platform, processes and analyzes the received pre-filled feedback information on the electronic medical record sharing platform, generates a feedback response result, and applies the generated feedback response result to actual medical services, such as optimizing service processes, realizing continuous improvement of telemedicine services, thereby improving service quality, reducing patient waiting time, and improving patient satisfaction.

[0046] In a possible implementation, the optimization result transmission module 50 further includes: a consultation prediction data generation unit, which is used to traverse multiple queue personnel to retrieve historical consultation information, and generate a consultation prediction data set in combination with the feedback response results; a prediction data optimization unit, which is used to formulate multiple consultation suggestions based on the consultation prediction data set, and transmit the multiple consultation suggestions to the electronic medical record sharing platform to optimize the multiple consultation time prediction data to generate multiple consultation time optimization data; a data update unit, which is used to update the consultation queue time data set according to the multiple consultation time optimization data.

[0047] Specifically, the consultation prediction data generation unit traverses multiple queue records and retrieves the historical consultation information of the queue, including the consultation type, duration, frequency, etc. Then, the retrieved historical consultation information is combined with the feedback response results obtained from the electronic medical record sharing platform to generate a consultation prediction data set, that is, based on the patient's previous historical consultation duration, the condition and frequency of the consultation, combined with the consultation information filled in by the patient, the consultation content is predicted, and a consultation prediction data set is generated based on the predicted consultation content, thereby shortening the duration of online consultation. The prediction data optimization unit formulates multiple consultation suggestions based on the consultation prediction data set, combined with expert experience and historical data, such as suggestions to optimize service processes, adjust the configuration of consultants, etc. Each of the multiple queues has an electronic shared medical record, which can be established by previous consultations or newly added by this consultation. Multiple consultation suggestions corresponding to multiple patients are transmitted to the corresponding sub-medical record sharing platform to optimize the consultation duration prediction data. Through this process, multiple consultation time optimization data can be generated so that patients can improve the doctor's consultation and diagnosis speed during later consultations, thereby shortening the time. Finally, the data update unit uses the received multiple consultation time optimization data to update the consultation queue time data set, and applies the updated consultation queue time data set to the actual queue management system, achieving more accurate resource allocation and service optimization, and improving service efficiency and patient satisfaction. Technical effect.

[0048] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0049] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A service optimization management system for telemedicine services, characterized in that: The system comprises: An information retrieval module, the information retrieval module is used to retrieve multiple queue information sets based on the reception window, the multiple queue information sets include an appointment queue information set and an online queue information set; A feature extraction module, wherein the feature extraction module is used to extract features of multiple queue personnel to perform differentiated identification of consultation duration and generate multiple consultation duration prediction data, wherein the multiple consultation duration prediction data correspond to the multiple queue personnel; A prediction model building module, the prediction model building module is used to perform queue conflict monitoring based on the appointment queue information set and the online queue information set, obtain monitoring results according to the queue conflict monitoring, build a queue duration prediction model, and dynamically adjust the queue duration data set according to the monitoring results combined with the multiple consultation duration prediction data to generate a consultation queue duration data set; A channel formulation module, the channel formulation module is used to traverse the consultation queue time data set to formulate multiple exclusive channels, and formulate a queue optimization strategy through the multiple exclusive channels; An optimization result transmission module is used to execute the queue optimization strategy and transmit the optimization results to the user terminal, perform feedback response through the user terminal, optimize the multiple consultation time prediction data according to the feedback response results, update the consultation queue time data set, and realize the optimized management of telemedicine services.

2. A service optimization management system for remote medical services as claimed in claim 1, characterized in that: The feature extraction module comprises: A personnel information retrieving unit, the personnel information retrieving unit is used to retrieve information of multiple queued personnel at the reception window, perform feature analysis based on the information of multiple queued personnel, and determine features of the multiple queued personnel; A consulting group division unit, the consulting group division unit is used to divide a plurality of consulting groups based on the characteristics of the plurality of queue personnel by feature coding; A consultation duration acquisition unit, the consultation duration acquisition unit is used to acquire a plurality of consultation duration data by performing cluster analysis on the historical consultation time of the plurality of consultation groups; A prediction channel construction unit is used to construct a duration prediction channel based on the multiple consultation duration data, predict the consultation duration of multiple queue persons through the duration prediction channel, and generate the multiple consultation duration prediction data.

3. A service optimization management system for remote medical services as claimed in claim 1, characterized in that: The prediction model building module includes: An information set matching unit, the information set matching unit is used to match the reservation queue information set with the online queue information set to generate a two-way queue matching information set; An information monitoring unit, the information monitoring unit is used to activate a conflict monitoring mechanism to perform real-time monitoring on the reservation queue information set and the online queue information set based on the two-way queue matching information set, and when the online queue information of the target user arrives at the consulting service window, detect whether the target user arrives at the consulting service window within a specified time; A first preset waiting time determination unit, wherein the first preset waiting time determination unit is used to obtain the target user's appointment queue information if the target user arrives at the consulting service window within a preset waiting time interval, and prompt the target user to determine whether to retain the appointment queue information; if retained, store the appointment queue information and generate appointment reservation information; if not retained, generate appointment cancellation information and delete the target user's appointment queue information; A second preset waiting time judgment unit, the second preset waiting time judgment unit is used to extract the online queuing information of the target user based on the next user in the online queuing information set to the consultation service window if the target user does not arrive at the consultation service window within the preset waiting time interval, automatically retain the appointment queuing information of the target user, and send reminder information to the target user, the reminder information including overdue reminder information and appointment reservation information.

4. A service optimization management system for remote medical services as claimed in claim 1, characterized in that: The prediction model building module also includes: A queuing duration information calculation unit, the queuing duration information calculation unit is used to calculate and obtain multiple queuing duration information sets based on the multiple queuing information sets; A data partitioning unit, the data partitioning unit is used to perform data partitioning according to the multiple queuing duration information sets to obtain a target independent variable and a target dependent variable; A long short-term memory network generation unit, the long short-term memory network generation unit is used to construct a training set, a supervision set, and a test set based on the target independent variable and the target dependent variable, and to perform supervised training through the training set and the supervision set to generate a long short-term memory network; A queue length prediction model output unit is used to test and verify the long short-term memory network through the test set and output the queue length prediction model.

5. A service optimization management system for remote medical services as claimed in claim 3, characterized in that: The prediction model building module also includes: A queue time data set output unit, the queue time data set output unit is used to synchronize the multiple queue information sets to the queue time prediction model for prediction, and output the queue time data set; A queue conflict analysis unit, the queue conflict analysis unit is used to analyze whether there is a queue conflict in the monitoring result, and if so, obtain the appointment cancellation information and the overdue reminder information, dynamically adjust the queue duration data set based on the appointment cancellation information, the overdue reminder information, and the multiple consultation duration prediction data, and generate the consultation queue duration data set; A data set dynamic adjustment unit is used to automatically allocate consultation time periods to multiple queueing personnel based on the multiple consultation time prediction data if there is no queue conflict in the monitoring results, and dynamically adjust the queue time data set according to the allocation results to generate the consultation queue time data set.

6. A service optimization management system for remote medical services as claimed in claim 1, characterized in that: The channel formulation module includes: A queuing data acquisition unit, the queuing data acquisition unit is used to acquire queuing data of multiple time periods based on the consultation queuing time data set; A queuing data analysis unit, the queuing data analysis unit is used to analyze the queuing data of the multiple time periods to identify and extract peak time periods, wherein the peak time periods include peak time periods and off-peak time periods; A queue duration feature generating unit, the queue duration feature generating unit is used to extract queue duration features based on the peak time period and the off-peak time period, and generate peak queue duration features and off-peak queue duration features; An exclusive channel formulation unit is used to formulate multiple exclusive channels according to the peak queue duration characteristics and the off-peak queue duration characteristics, and the multiple exclusive channels include multiple ordinary channels, multiple fast channels, and multiple emergency channels.

7. A service optimization management system for remote medical services as claimed in claim 1, characterized in that: The optimization result transmission module includes: An optimization result receiving unit, the optimization result receiving unit is used to receive the optimization result through the user terminal and generate a pre-fill instruction; A feedback information generating unit, the feedback information generating unit is used to prompt the user of the user terminal to provide feedback through the pre-filled instruction, and generate pre-filled feedback information; A feedback response result generating unit is used to establish an electronic medical record sharing platform, transmit the pre-filled feedback information to the electronic medical record sharing platform for response, and generate the feedback response result.

8. A service optimization management system for remote medical services as claimed in claim 7, characterized in that: The optimization result transmission module also includes: A consultation prediction data generation unit, the consultation prediction data generation unit is used to traverse multiple queue personnel to retrieve historical consultation information, and generate a consultation prediction data set in combination with the feedback response results; A prediction data optimization unit, the prediction data optimization unit is used to formulate a plurality of consultation suggestions based on the consultation prediction data set, transmit the plurality of consultation suggestions to the electronic medical record sharing platform to optimize the plurality of consultation duration prediction data, and generate a plurality of consultation duration optimization data; A data updating unit, the data updating unit is used to update the consultation queuing time data set according to the multiple consultation time optimization data.

Images