Tumor MDT diagnosis and treatment process intelligent scheduling method, system and equipment based on 5G and medium

Abstract

The invention relates to a 5G-based tumor MDT diagnosis and treatment process intelligent scheduling method, system and device and a medium. The method comprises the steps that preliminary diagnosis and treatment information is acquired through a 5G network, and the expert matching degree of the preliminary diagnosis and treatment information and all expert label data in a preset multidisciplinary team expert database is calculated; constructing a multidisciplinary team expert candidate set based on the expert label data of which the expert matching degree exceeds a preset matching degree threshold value; constructing a multidisciplinary team expert benefit model of multidisciplinary team experts corresponding to the expert label data according to the expert matching degree, the expert scheduling vacancy rate and the expert historical experience degree; and obtaining multidisciplinary team expert scheduling result information based on the multidisciplinary team expert benefit model in combination with a target optimization algorithm. By adopting the method, multi-dimensional data can be integrated through an intelligent algorithm, and an intelligent expert scheduling system is established, so that the benefit of tumor MDT diagnosis and treatment is improved.

Description

Technical Field

[0001] This application belongs to the field of intelligent scheduling of tumor MDT diagnosis and treatment process based on 5G, and specifically relates to a method, system, device and medium for intelligent scheduling of tumor MDT diagnosis and treatment process based on 5G. Background Technology

[0002] Multidisciplinary treatment of cancer can be traced back to case discussions in the 1960s. After 60 years of integration and development, it has gradually evolved into the multidisciplinary team (MDT) treatment model that is widely accepted in countries around the world today. The MDT treatment model is an organic combination of various treatment models centered on the patient and based on a multidisciplinary expert group. It can ensure the implementation of the best treatment plan for cancer patients, promote communication and understanding between disciplines, and improve the patient's medical experience.

[0003] In traditional MDT (Multidisciplinary Team) diagnostic and treatment processes, multidisciplinary expert teams rely on in-person meetings for case discussions and treatment plans. Patient information needs to be manually compiled and transmitted based on paper documents, leading to delayed information sharing and low decision-making efficiency. Furthermore, current technologies primarily rely on manual coordination for the participation and scheduling of experts in multidisciplinary teams, lacking quantitative analysis of professional expertise, available availability, and historical experience, making precise matching difficult. Summary of the Invention

[0004] Therefore, it is necessary to provide a 5G-based intelligent scheduling method, system, equipment, and medium for tumor MDT diagnosis and treatment processes, which can integrate multi-dimensional data through intelligent algorithms, establish an intelligent expert scheduling system, and thus improve the efficiency of tumor MDT diagnosis and treatment.

[0005] Firstly, this application provides a 5G-based intelligent scheduling method for tumor MDT diagnosis and treatment processes, including:

[0006] Preliminary diagnostic information is obtained through the 5G network, and the expert matching degree between the preliminary diagnostic information and the expert tag data in the preset multidisciplinary team expert database is calculated.

[0007] Based on expert tag data whose expert matching degree exceeds a preset matching degree threshold, a multidisciplinary team expert candidate set is constructed.

[0008] A multidisciplinary team expert benefit model is constructed based on expert matching degree, expert scheduling idle rate, and expert historical experience.

[0009] Based on the multidisciplinary team expert benefit model and combined with the objective optimization algorithm, expert label data is selected from the multidisciplinary team expert candidate set to obtain multidisciplinary team expert scheduling result information.

[0010] In one embodiment, the 5G-based intelligent scheduling method for tumor MDT diagnosis and treatment processes further includes:

[0011] The consultation agenda is initiated based on the information from the multidisciplinary team of experts, and the preliminary diagnosis information is pushed to the virtual discussion space;

[0012] The discussion tag data of multidisciplinary team experts corresponding to the scheduling results information of multidisciplinary team experts are obtained through 5G network;

[0013] In the virtual discussion space, combined with preliminary diagnosis and treatment information, discussion tags and data are labeled to obtain enhanced diagnosis and treatment information.

[0014] In one embodiment, the discussion tag data includes discussion content tag data, discussion participant tag data, and discussion time tag data.

[0015] In one embodiment, the 5G-based intelligent scheduling method for tumor MDT diagnosis and treatment processes further includes:

[0016] The weekly time slot availability rate of attending physicians and multidisciplinary team experts is obtained. The weekly time slot availability rate is used to characterize the time slot availability rate of multidisciplinary team experts for each day of the week.

[0017] The expert scheduling idle rate is set based on the weekly time slot idle rate of attending physicians and the weekly time slot idle rate of multidisciplinary team experts.

[0018] Obtain the multidisciplinary team participation frequency of experts corresponding to expert tag data;

[0019] The historical experience level of experts is set based on the frequency of multidisciplinary team participation.

[0020] The expression for the weekly time slot vacancy rate is as follows:

[0021]

[0022] In the formula, This refers to the weekly time slot vacancy rate. For the week The first day The vacancy rate during the scheduling period. This represents the total number of shifts.

[0023] In one embodiment, calculating the expert matching degree between preliminary diagnosis information and expert tag data in a pre-defined multidisciplinary team expert database includes:

[0024] The expert matching degree between preliminary diagnosis information and expert tag data in the multidisciplinary team expert database is calculated based on the term frequency-inverse document frequency model.

[0025] The expression for the multidisciplinary team expert benefit model is as follows:

[0026]

[0027] In the formula, For the number Multidisciplinary team expert benefit model. , and These are the weights for expert matching degree, expert scheduling availability rate, and expert historical experience, respectively. This is a term frequency-inverse document frequency model. For the number The expert tag data of multidisciplinary team experts. For preliminary diagnosis and treatment information, For the number Weekly time slot availability of multidisciplinary team experts. The weekly time slot availability rate for attending physicians. For the Frobenius norm, For the number The frequency of multidisciplinary team participation of experts from multidisciplinary teams.

[0028] In one embodiment, the objective optimization algorithm is a genetic algorithm, and the fitness function of the genetic algorithm is expressed as follows:

[0029]

[0030] In the formula, For the fitness function, Chromosomes The length of the chromosome. For chromosome number The gene corresponding to the position is numbered as follows: Multidisciplinary team expert benefit model.

[0031] In one embodiment, the multidisciplinary team expert database includes a remote multidisciplinary team expert database and a local multidisciplinary team expert database.

[0032] Secondly, this application also provides a 5G-based intelligent scheduling system for tumor MDT diagnosis and treatment processes, including:

[0033] The preliminary diagnosis information acquisition module is used to acquire preliminary diagnosis information through the 5G network and calculate the expert matching degree between the preliminary diagnosis information and the expert tag data in the preset multidisciplinary team expert database.

[0034] The expert candidate set construction module is used to construct a multidisciplinary team expert candidate set based on expert tag data whose matching degree exceeds a preset matching degree threshold;

[0035] The expert benefit model construction module is used to construct a multidisciplinary team expert benefit model corresponding to the expert tag data based on the expert matching degree, expert scheduling idle rate and expert historical experience.

[0036] The expert scheduling result generation module is used to select expert label data from the multidisciplinary team expert candidate set based on the multidisciplinary team expert benefit model and combined with the objective optimization algorithm, and obtain multidisciplinary team expert scheduling result information.

[0037] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method as described in any of the first aspects of this application.

[0038] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method as described in any of the first aspects of this application.

[0039] The aforementioned intelligent scheduling methods, systems, equipment, and media for tumor MDT diagnosis and treatment processes based on 5G, through the deep integration of 5G networks and intelligent algorithms, can achieve real-time and efficient tumor MDT diagnosis and treatment processes. This avoids expert scheduling delays, shortens the MDT decision-making cycle, and promotes dynamic optimization of treatment plans. Through multi-dimensional benefit models and target optimization algorithms, it can achieve scientific allocation of MDT expert resources, thereby balancing the participation of MDT experts, improving the utilization rate of MDT expert resources, and enhancing the quality of MDT diagnosis and treatment and patient satisfaction. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 A schematic diagram illustrating the application environment of a 5G-based intelligent scheduling method for tumor MDT diagnosis and treatment workflow, provided in one embodiment of this application;

[0042] Figure 2 A flowchart illustrating a 5G-based intelligent scheduling method for tumor MDT diagnosis and treatment workflow provided in one embodiment of this application. Figure 1 ;

[0043] Figure 3 A flowchart illustrating a 5G-based intelligent scheduling method for tumor MDT diagnosis and treatment workflow provided in one embodiment of this application. Figure 2 ;

[0044] Figure 4 This is a schematic diagram of the structure of a 5G-based intelligent scheduling system for tumor MDT diagnosis and treatment processes, provided as an embodiment of this application. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0046] The intelligent scheduling method for tumor MDT diagnosis and treatment workflow based on 5G provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, the attending physician terminal 102 and the multidisciplinary team expert treatment terminal 103 can communicate with the intelligent scheduling computing platform 101 via a network. The database 104 can store the data that the intelligent scheduling computing platform 101 needs to process. The database 104 can be integrated into the intelligent scheduling computing platform 101 or placed in the cloud or on other network servers. The attending physician terminal 102 can upload the patient's tumor medical record information to the intelligent scheduling computing platform 101. The intelligent scheduling computing platform 101 can generate tumor MDT treatment process scheduling information based on the patient's tumor medical record information and send the tumor MDT treatment process scheduling information to the corresponding multidisciplinary team expert treatment terminal 103. The multidisciplinary team expert treatment terminal 103 and the attending physician terminal 102 can be, but are not limited to, various medical computers, laptops, smartphones, tablets, and medical IoT devices. The intelligent scheduling computing platform 101 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0047] In one exemplary embodiment of this application, such as Figure 2 As shown, a 5G-based intelligent scheduling method for tumor MDT diagnosis and treatment workflow is provided, which is then applied to... Figure 1 The following explanation uses the intelligent scheduling computing platform 101 as an example, including the following steps S201 to S204. Wherein:

[0048] Step S201: Obtain preliminary diagnosis and treatment information through the 5G network, and calculate the expert matching degree between the preliminary diagnosis and treatment information and the expert tag data in the preset multidisciplinary team expert database.

[0049] Specifically, the intelligent scheduling computing platform 101 can obtain preliminary diagnosis and treatment information from the attending physician's terminal via a 5G network, and can calculate the expert matching degree between the preliminary diagnosis and treatment information and the expert tag data in the preset multidisciplinary team expert database. Among them, the preliminary diagnosis and treatment information can be used to characterize the patient's tumor condition based on the preliminary analysis of the current diagnosis and treatment information.

[0050] Optionally, the multidisciplinary team expert database may include, but is not limited to, one or both of the remote multidisciplinary team expert database and the local multidisciplinary team expert database. Correspondingly, the multidisciplinary team expert diagnosis and treatment terminal may also include, but is not limited to, one or both of the remote multidisciplinary team expert diagnosis and treatment terminal and the local multidisciplinary team expert diagnosis and treatment terminal.

[0051] Optionally, a remote multidisciplinary team expert database can refer to a collection of expert information, leveraging 5G networks and an identity authentication system to aggregate expert tag data from multidisciplinary teams across different medical institutions, all possessing relevant disciplinary qualifications. This database can store structured expert tag data containing the experts' areas of expertise, real-time schedules, and historical experience, supporting cross-hospital real-time retrieval, dynamic updates, and unified scheduling. It can be used to provide remote consultation and decision support when local resources are insufficient or when special case requirements necessitate remote consultations.

[0052] Optionally, a local multidisciplinary team expert database can refer to an information collection consisting of expert tag data from multidisciplinary teams of various oncology-related departments within the same medical institution. This database can include the expert's department affiliation, hospital scheduling, real-time workload, and hospital performance records. It can prioritize serving the multidisciplinary treatment needs of patients within the hospital, enabling rapid matching of hospital resources and on-site collaboration.

[0053] Step S202: Based on the expert label data whose expert matching degree exceeds the preset matching degree threshold, a multidisciplinary team expert candidate set is constructed.

[0054] Specifically, the intelligent scheduling computing platform 101 can construct a multidisciplinary team expert candidate set based on expert tag data in the multidisciplinary team expert database where the expert matching degree exceeds a preset matching degree threshold.

[0055] Optionally, the multidisciplinary team expert candidate set may include a subset of multidisciplinary team subject expert candidates from various related disciplines. These related disciplines may include, but are not limited to, one or more of the following: radiology, pathology, endoscopy, medical oncology, surgical oncology, radiation oncology, and interventional radiology.

[0056] Step S203: Construct a multidisciplinary team expert benefit model for multidisciplinary team experts corresponding to expert tag data based on expert matching degree, expert scheduling idle rate, and expert historical experience.

[0057] Specifically, the intelligent scheduling computing platform 101 can construct a multidisciplinary team expert benefit model based on the expert matching degree, expert scheduling idle rate, and expert historical experience of the multidisciplinary team experts corresponding to the expert tag data. This multidisciplinary team expert benefit model can intelligently solve for the optimal scheduling scheme of the oncology multidisciplinary team by integrating expert matching degree, weekly time-slot scheduling idle rate, and historical experience in real time, thereby achieving efficient scheduling of the oncology MDT diagnosis and treatment process.

[0058] Step S204: Based on the multidisciplinary team expert benefit model and combined with the objective optimization algorithm, select expert label data from the multidisciplinary team expert candidate set to obtain multidisciplinary team expert scheduling result information.

[0059] Specifically, the intelligent scheduling computing platform 101 can select expert label data from the multidisciplinary team expert candidate set based on the constructed multidisciplinary team expert benefit model and combined with the objective optimization algorithm to obtain multidisciplinary team expert scheduling result information. The intelligent scheduling computing platform 101 can send the multidisciplinary team expert scheduling result information to the corresponding multidisciplinary team expert diagnosis and treatment terminals via 5G network.

[0060] Optionally, the objective optimization algorithm may include, but is not limited to, one or more of the following: greedy algorithm, integer programming algorithm, particle swarm optimization algorithm, simulated annealing algorithm, and genetic algorithm.

[0061] The aforementioned intelligent scheduling method for tumor MDT diagnosis and treatment processes based on 5G achieves real-time and efficient scheduling by acquiring preliminary diagnosis and treatment information through the 5G network, thereby avoiding expert scheduling delays and shortening the MDT decision-making cycle. Through a tag-based expert precision matching mechanism, preliminary diagnosis and treatment information and expert tag data can be intelligently matched to accurately identify the expert group most suitable for the patient's condition, thus constructing a highly targeted expert candidate set and improving the scientific rigor and relevance of multidisciplinary team formation. A multi-dimensional parameter-integrated expert benefit evaluation model comprehensively considers expert capabilities and scheduling feasibility, balancing expert professional suitability, time availability, and clinical experience, enhancing the professional capabilities and scheduling efficiency of multidisciplinary team formation. A dynamic scheduling engine based on intelligent optimization algorithms efficiently selects the expert combination that maximizes treatment benefits from the expert candidate set, shortening expert scheduling time and enabling rapid organization and implementation of multidisciplinary team consultations, thus improving the operational efficiency of MDT diagnosis and treatment.

[0062] In an optional embodiment of this application, please refer to Figure 3 The intelligent scheduling method for tumor MDT diagnosis and treatment processes based on 5G may also include:

[0063] Step S309: Initiate the consultation agenda based on the results of the multidisciplinary team expert scheduling and push the preliminary diagnosis information to the virtual discussion space.

[0064] Specifically, the information on the scheduling results of multidisciplinary team experts can include consultation time information and consultation expert information. The intelligent scheduling computing platform can initiate the consultation agenda based on the consultation time information and consultation expert information in the information on the scheduling results of multidisciplinary team experts, and push the preliminary diagnosis and treatment information to the virtual discussion space on the intelligent scheduling computing platform that is connected to the attending physician's terminal and the diagnosis and treatment terminals of various multidisciplinary team experts through the 5G network.

[0065] Step S310: Obtain the discussion tag data of the multidisciplinary team experts corresponding to the multidisciplinary team expert scheduling result information through the 5G network.

[0066] Specifically, the intelligent scheduling computing platform can obtain the discussion tag data of multidisciplinary team experts corresponding to the scheduling results information of multidisciplinary team experts from the attending physician terminal and the expert diagnosis and treatment terminals of various multidisciplinary teams through the 5G network.

[0067] Step S311: In the virtual discussion space, combine the preliminary diagnosis and treatment information, label the discussion data, and obtain enhanced diagnosis and treatment information.

[0068] Specifically, the intelligent scheduling computing platform can combine preliminary diagnosis and treatment information with discussion tags and data annotation in the virtual discussion space built on the intelligent scheduling computing platform to obtain enhanced diagnosis and treatment information.

[0069] In the aforementioned intelligent scheduling method for tumor MDT diagnosis and treatment processes based on 5G, the consultation agenda can be intelligently initiated through a consultation agenda initiation and information push mechanism based on scheduling results, thereby improving the efficiency of MDT diagnosis and treatment process scheduling. By pushing preliminary diagnosis and treatment information to a preset virtual discussion space, it can ensure that all participating experts can simultaneously obtain complete real-time preliminary diagnosis and treatment information when accessing the virtual discussion space, thus improving consultation efficiency. By collecting discussion tag data through the 5G network, it can instantly capture and record key viewpoints and analytical conclusions generated by multidisciplinary experts during the consultation process, thereby improving the efficiency of consultation record organization. By enhancing diagnosis and treatment information, it can organically integrate preliminary diagnosis and treatment information with expert discussion tag data, providing a structured data foundation for diagnosis and treatment analysis and forming a traceable and complete chain of evidence. By dynamically sharing enhanced diagnosis and treatment information, it can realize real-time updates and multi-terminal synchronization of diagnosis and treatment data during the consultation process, ensuring that participating multidisciplinary team experts can obtain the latest enhanced diagnosis and treatment information in a timely manner, thereby improving the comprehensiveness and accuracy of the diagnosis and treatment plan.

[0070] In an optional embodiment of this application, the discussion tag data may include discussion content tag data, discussion participant tag data, and discussion time tag data.

[0071] In an optional embodiment of this application, please refer to Figure 3 The intelligent scheduling method for tumor MDT diagnosis and treatment processes based on 5G may also include:

[0072] Step S301: Obtain the weekly time slot availability rate of attending physicians and the weekly time slot availability rate of multidisciplinary team experts.

[0073] Optionally, the weekly time slot availability rate can be used to characterize the time slot availability rate of multidisciplinary team experts for each day of the week.

[0074] Optionally, the expression for the weekly time slot vacancy rate can be:

[0075]

[0076] In the formula, This refers to the weekly time slot vacancy rate. For the week The first day The vacancy rate during the scheduling period. This represents the total number of shifts.

[0077] For example, when the first The first day When the scheduling status of the shift is idle, the first shift... The first day Shift idle rate during scheduling It can be set to 1. When the first The first day When the scheduling status of the shift is occupied, the first shift... The first day Shift idle rate during scheduling It can be set to 0.

[0078] Step S302: Set the expert scheduling idle rate based on the weekly time slot idle rate of attending physicians and the weekly time slot idle rate of multidisciplinary team experts.

[0079] Step S303: Obtain the multidisciplinary team participation frequency of the multidisciplinary team experts corresponding to the expert tag data.

[0080] Step S304: Set the expert's historical experience level based on the frequency of multidisciplinary team participation.

[0081] The aforementioned intelligent scheduling method for tumor MDT diagnosis and treatment processes based on 5G enables comprehensive and refined analysis of the scheduling time characteristics of attending physicians and multidisciplinary team experts by using weekly time-slot idle rates, thus avoiding time conflicts between multidisciplinary team experts and attending physicians. By considering the overall weekly cycle, it avoids short-term time mismatches that may occur in a single scheduling session, making expert scheduling more aligned with the actual time coordination needs of the diagnosis and treatment process, thereby improving the success rate of multidisciplinary consultations. Furthermore, by monitoring the frequency of multidisciplinary team participation, it can assess the diagnostic and treatment experience of multidisciplinary team experts, reflect their latest practical status, improve the real-time nature of experience evaluation, and enhance the overall efficiency and decision-making quality of multidisciplinary consultations.

[0082] In an optional embodiment of this application, calculating the expert matching degree between preliminary diagnosis information and the expert tag data in a preset multidisciplinary team expert database may include:

[0083] Specifically, the intelligent scheduling computing platform can calculate the expert matching degree of preliminary diagnosis information and expert tag data in the multidisciplinary team expert database based on the word frequency-inverse document frequency model.

[0084] Optionally, the expression for the multidisciplinary team expert benefit model can be:

[0085]

[0086] In the formula, For the number Multidisciplinary team expert benefit model. , and These are the weights for expert matching degree, expert scheduling availability rate, and expert historical experience, respectively. This is a term frequency-inverse document frequency model. For the number The expert tag data of multidisciplinary team experts. For preliminary diagnosis and treatment information, For the number Weekly time slot availability of multidisciplinary team experts. The weekly time slot availability rate for attending physicians. For the Frobenius norm, For the number The frequency of multidisciplinary team participation of experts from multidisciplinary teams.

[0087] Optionally, the Frobenius norm can be used to measure the number of... Weekly time slot availability of multidisciplinary team experts Weekly shift availability rate of attending physicians The differences between them.

[0088] In an optional embodiment of this application, the objective optimization algorithm can be a genetic algorithm, and the expression for the fitness function of the genetic algorithm can be:

[0089]

[0090] In the formula, For the fitness function, Chromosomes The length of the chromosome. For chromosome number The gene corresponding to the position is numbered as follows: Multidisciplinary team expert benefit model.

[0091] In one optional embodiment of this application, the multidisciplinary team expert database may include a remote multidisciplinary team expert database and a local multidisciplinary team expert database.

[0092] In one exemplary embodiment of this application, such as Figure 3 As shown, a 5G-based intelligent scheduling method for tumor MDT diagnosis and treatment workflow is provided, including:

[0093] Step S301: Obtain the weekly time slot availability rate of attending physicians and the weekly time slot availability rate of multidisciplinary team experts.

[0094] Step S302: Set the expert scheduling idle rate based on the weekly time slot idle rate of attending physicians and the weekly time slot idle rate of multidisciplinary team experts.

[0095] Step S303: Obtain the multidisciplinary team participation frequency of the multidisciplinary team experts corresponding to the expert tag data.

[0096] Step S304: Set the expert's historical experience level based on the frequency of multidisciplinary team participation.

[0097] Step S305: Obtain preliminary diagnosis and treatment information through the 5G network, and calculate the expert matching degree between the preliminary diagnosis and treatment information and the expert tag data in the preset multidisciplinary team expert database.

[0098] Step S306: Based on the expert tag data whose expert matching degree exceeds the preset matching degree threshold, construct a multidisciplinary team expert candidate set.

[0099] Step S307: Construct a multidisciplinary team expert benefit model for multidisciplinary team experts corresponding to expert tag data based on expert matching degree, expert scheduling idle rate, and expert historical experience.

[0100] Step S308: Based on the multidisciplinary team expert benefit model and combined with the objective optimization algorithm, select expert label data from the multidisciplinary team expert candidate set to obtain multidisciplinary team expert scheduling result information.

[0101] Step S309: Initiate the consultation agenda based on the results of the multidisciplinary team expert scheduling and push the preliminary diagnosis information to the virtual discussion space.

[0102] Step S310: Obtain the discussion tag data of the multidisciplinary team experts corresponding to the multidisciplinary team expert scheduling result information through the 5G network.

[0103] Step S311: In the virtual discussion space, combine the preliminary diagnosis and treatment information, label the discussion data, and obtain enhanced diagnosis and treatment information.

[0104] The aforementioned intelligent scheduling method for oncology MDT diagnosis and treatment processes based on 5G enables precise allocation of multidisciplinary team resources through dynamic optimization of expert scheduling strategies. This avoids redundant expert scheduling, improves collaboration efficiency, and promotes efficient collaboration and real-time response in the diagnosis and treatment process. Furthermore, the integration of virtual discussion spaces with 5G-based data dynamically enhances diagnostic and treatment information, enabling real-time interaction of multidisciplinary expert opinions and ensuring deep collaboration and scientific decision-making in the diagnosis and treatment process. Finally, the deep integration of 5G networks and multi-objective optimization algorithms enables intelligent scheduling of the diagnosis and treatment process, thereby improving the management efficiency of MDT diagnosis and treatment processes and promoting the balanced and efficient utilization of medical resources.

[0105] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0106] Based on the same inventive concept, this application also provides a 5G-based intelligent scheduling system for tumor MDT diagnosis and treatment process, used to implement the aforementioned intelligent scheduling method for 5G-based tumor MDT diagnosis and treatment process. The solution provided by this system is similar to the implementation scheme described in the above method. Therefore, the specific limitations of one or more embodiments of the 5G-based intelligent scheduling system for tumor MDT diagnosis and treatment process provided below can be found in the limitations of the 5G-based intelligent scheduling method for tumor MDT diagnosis and treatment process described above, and will not be repeated here.

[0107] In one exemplary embodiment, such as Figure 4 As shown, a 5G-based intelligent scheduling system 400 for tumor MDT diagnosis and treatment workflow is provided, including:

[0108] The preliminary diagnosis information acquisition module 401 can be used to acquire preliminary diagnosis information through a 5G network and calculate the expert matching degree between the preliminary diagnosis information and the expert tag data in the preset multidisciplinary team expert database.

[0109] The expert candidate set construction module 402 can be used to construct a multidisciplinary team expert candidate set based on expert tag data whose expert matching degree exceeds a preset matching degree threshold.

[0110] The expert benefit model construction module 403 can be used to construct a multidisciplinary team expert benefit model corresponding to expert tag data based on expert matching degree, expert scheduling idle rate and expert historical experience.

[0111] The expert scheduling result generation module 404 can be used to select expert label data from the multidisciplinary team expert candidate set based on the multidisciplinary team expert benefit model and combined with the objective optimization algorithm to obtain multidisciplinary team expert scheduling result information.

[0112] In an optional embodiment of this application, the 5G-based intelligent scheduling system 400 for tumor MDT diagnosis and treatment processes can also be used for:

[0113] The consultation agenda is initiated based on the information from the multidisciplinary team of experts, and the preliminary diagnosis and treatment information is pushed to the virtual discussion space.

[0114] The discussion tag data of multidisciplinary team experts corresponding to the scheduling results information of multidisciplinary team experts are obtained through 5G networks.

[0115] In the virtual discussion space, combined with preliminary diagnosis and treatment information, discussion tags and data are labeled to obtain enhanced diagnosis and treatment information.

[0116] In an optional embodiment of this application, the 5G-based intelligent scheduling system 400 for tumor MDT diagnosis and treatment processes can also be used for:

[0117] The weekly time slot availability rate of attending physicians and multidisciplinary team experts is obtained. The weekly time slot availability rate is used to characterize the availability rate of multidisciplinary team experts for each time slot on each day of the week.

[0118] The expert scheduling idle rate is set based on the weekly time slot idle rate of attending physicians and the weekly time slot idle rate of multidisciplinary team experts.

[0119] Obtain the multidisciplinary team participation frequency of experts corresponding to expert tag data.

[0120] The historical experience level of experts is set based on the frequency of multidisciplinary team participation.

[0121] In an optional embodiment of this application, the preliminary diagnosis information acquisition module 401 can also be used for:

[0122] The degree of expert matching between preliminary diagnosis information and expert tag data in the multidisciplinary team expert database is calculated based on the term frequency-inverse document frequency model.

[0123] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the intelligent scheduling method for a 5G-based tumor MDT diagnosis and treatment process as described above.

[0124] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0125] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The components described as separate parts may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0126] The above-described embodiments are merely illustrative of several implementation methods of the embodiments of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the embodiments of this application, and these modifications and improvements all fall within the protection scope of the embodiments of this application.

Claims

1. A 5G-based intelligent scheduling method for tumor MDT diagnosis and treatment process, characterized in that, The method comprises: obtaining preliminary diagnosis and treatment information through a 5G network, and calculating an expert matching degree of the preliminary diagnosis and treatment information and each expert tag data in a preset multidisciplinary team expert library; based on the expert matching degree exceeding a preset matching degree threshold, constructing a multidisciplinary team expert candidate set; constructing a multidisciplinary team expert benefit model of the multidisciplinary team expert corresponding to the expert tag data according to the expert matching degree, an expert scheduling idle rate and an expert historical experience degree; based on the multidisciplinary team expert benefit model, combining a target optimization algorithm, selecting the expert tag data from the multidisciplinary team expert candidate set to obtain multidisciplinary team expert scheduling result information.

2. The method of claim 1, wherein, The method further comprises: based on the multidisciplinary team expert scheduling result information, starting a consultation agenda, and pushing the preliminary diagnosis and treatment information to a virtual discussion space; obtaining discussion tag data of the multidisciplinary team expert corresponding to the multidisciplinary team expert scheduling result information through a 5G network; in the virtual discussion space, combining the preliminary diagnosis and treatment information, labeling the discussion tag data to obtain enhanced diagnosis and treatment information.

3. The method of claim 2, wherein: the discussion tag data comprises discussion content tag data, discussion personnel tag data and discussion time tag data.

4. The method of claim 1, wherein, The method further comprises: obtaining a weekly time period scheduling idle rate of a attending physician and the weekly time period scheduling idle rate of the multidisciplinary team expert, the weekly time period scheduling idle rate representing the scheduling idle rate of each scheduling time period of each day in a week of the multidisciplinary team expert; based on the weekly time period scheduling idle rate of the attending physician and the weekly time period scheduling idle rate of the multidisciplinary team expert, setting the expert scheduling idle rate; obtaining a multidisciplinary team participation frequency of the multidisciplinary team expert corresponding to the expert tag data; based on the multidisciplinary team participation frequency, setting the expert historical experience degree; wherein the expression of the weekly time period scheduling idle rate is: wherein is the shift idle rate for the weekly period, is the day of the week, is the shift idle rate for the shift period, is the shift idle rate for the shift period, is the total number of shift periods.

5. The method of claim 4, wherein, the calculation of the expert matching degree of the preliminary diagnosis and treatment information and each expert tag data in the preset multidisciplinary team expert library comprises: based on a term frequency-inverse document frequency model, calculating the expert matching degree of the preliminary diagnosis and treatment information and each expert tag data in the multidisciplinary team expert library; the expression of the multidisciplinary team expert benefit model is: In the formula, is the multidisciplinary team expert benefit model of the multidisciplinary team expert numbered , , and are respectively an expert matching degree weight, an expert scheduling idle rate weight and an expert historical experience degree weight, is the term frequency-inverse document frequency model, is the expert tag data of the multidisciplinary team expert numbered , is the preliminary diagnosis and treatment information, is the weekly period scheduling idle rate of the multidisciplinary team expert numbered , is the weekly period scheduling idle rate of the attending physician, is the Frobenius norm, is the multidisciplinary team participation frequency of the multidisciplinary team expert numbered .

6. The method of claim 5, wherein, the target optimization algorithm is a genetic algorithm, and the expression of the fitness function of the genetic algorithm is: wherein, is the fitness function, is a chromosome, is the length of the chromosome, is the gene at position of the chromosome corresponds to the number is the multi-disciplinary team expert benefit model of the multi-disciplinary team expert.

7. The method of any one of claims 1 to 6, wherein: the multidisciplinary team expert library comprises a remote multidisciplinary team expert library and a local multidisciplinary team expert library.

8. A 5G-based tumor MDT diagnosis and treatment process intelligent scheduling system, characterized in that, The system comprises: a preliminary diagnosis and treatment information acquisition module for obtaining preliminary diagnosis and treatment information through a 5G network, and calculating an expert matching degree of the preliminary diagnosis and treatment information and each expert tag data in a preset multidisciplinary team expert library; an expert candidate set construction module for constructing a multidisciplinary team expert candidate set based on the expert matching degree exceeding a preset matching degree threshold; An expert benefit model construction module is configured to construct a multidisciplinary team expert benefit model of the multidisciplinary team experts corresponding to the expert tag data according to the expert matching degree, the expert scheduling idle rate and the expert historical experience degree. An expert scheduling result generation module is configured to select the expert tag data from the multidisciplinary team expert candidate set based on the multidisciplinary team expert benefit model and in combination with a target optimization algorithm to obtain multidisciplinary team expert scheduling result information. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor executes the computer program to implement the method in any one of claims 1 to 7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the method in any one of claims 1 to 7.

Images