Digital regional consumption and supply management platform

Through the image data analysis and neural network model of the digital regional disinfection management platform, the disinfection parameters of medical devices are optimized, and the problem of insufficient intelligence of the medical device disinfection management platform is solved, efficient and energy-saving disinfection management is achieved, and disinfection quality is improved. and reduce costs.

CN118588265BActive Publication Date: 2024-11-05NANJING XIYUE IRRADIATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411068025.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-06
Publication Date
2024-11-05
Estimated Expiration
2044-08-06

AI Technical Summary

Technical Problem

The medical device disinfection management platform is relatively intelligent, resulting in high cost of disinfection solutions and low efficiency in handling disinfection supply processes.

Method used

Provide a digital regional disinfection management platform, including device classification data acquisition module, pollutant distribution analysis module, disinfection parameter optimization analysis module, composite disinfection classification management module and supply identification module, and generate the most through image data analysis and neural network model. Optimize disinfection parameters and classification instructions to optimize the disinfection process.

Benefits of technology

An efficient and energy-saving disinfection management strategy has been realized, which has improved the disinfection quality of the equipment, reduced the energy consumption of the disinfection process, and saved costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118588265B_ABST
    Figure CN118588265B_ABST
Patent Text Reader

Abstract

The present invention discloses a digital regional disinfection and supply management platform, which relates to data processing related fields. The device includes: obtaining the image data of the initial recovery instrument and the instrument, performing the distribution analysis of the instrument pollutants, and obtaining multiple distribution characteristics of the instrument pollutants. Performing disinfection quality difference and disinfection energy loss analysis, generating the optimal composite disinfection parameters, and the corresponding first disinfection difference risk index and the first energy loss index and performing index judgment, generating secondary classification instructions, performing composite disinfection classification on the instrument, and obtaining multiple optimal classification composite disinfection parameters and multiple classified instruments. Classification disinfection is performed, and each classification result is marked with a supply identification label. The technical problem that the intelligence of the medical device disinfection and supply management platform in the prior art is low, resulting in high execution cost of the disinfection plan and low processing efficiency of the disinfection supply process is solved. An efficient and energy-saving disinfection management strategy is provided for the disinfection supply center.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to data processing related fields, and in particular to a digital regional power supply management platform. Background Art

[0002] The medical disinfection supply center plays a vital role in hospital operations. It is responsible for cleaning, disinfecting, sterilizing medical devices and supplying sterile items. These processes are key links in hospital infection control and medical quality safety. The traditional disinfection supply process usually includes classified packaging and unified disinfection of medical devices. However, since the distribution of pollutants on different medical devices may vary, in order to ensure the disinfection effect, a high-cost disinfection plan needs to be set up to meet the disinfection requirements.

[0003] Therefore, in the prior art, the intelligence of the medical device supply and disinfection management platform is relatively low, resulting in technical problems such as high execution costs of disinfection plans and low efficiency in the disinfection supply process. Summary of the invention

[0004] This application solves the technical problems in the prior art that the medical device disinfection and supply management platform is not intelligent enough, resulting in high execution costs of disinfection plans and low disinfection supply process processing efficiency by providing a digital regional disinfection and supply management platform. It provides a highly efficient and energy-saving disinfection management strategy for the disinfection supply center, improves the disinfection quality of the equipment, and reduces energy consumption and saves costs during the disinfection process.

[0005] The present application provides a digital regional disinfection and supply management platform, which includes: an instrument classification data acquisition module, which is used to obtain the initial recovery instruments of the first disinfection and supply center, classify the initial recovery instruments, and collect the first instrument image data of the first type of instruments. A pollutant distribution analysis module, which is used to perform instrument pollutant distribution analysis based on the first instrument image data to obtain multiple instrument pollutant distribution characteristics. A disinfection parameter optimization analysis module, which is used to perform disinfection quality difference and disinfection energy loss analysis based on the multiple instrument pollutant distribution characteristics, generate optimal composite disinfection parameters, and the corresponding first disinfection difference risk index and first energy loss index, wherein the optimal composite disinfection parameters include cleaning control parameters and disinfection control parameters. A secondary classification analysis module, which is used to generate a secondary classification instruction if the first disinfection difference risk index is less than the predetermined difference risk index or the first energy loss index is greater than or equal to the predetermined energy loss index. A composite disinfection classification management module, which is used to perform composite disinfection classification on the first type of instruments through the secondary classification instruction, and obtain multiple optimal classification composite disinfection parameters and multiple classified instruments. The supply identification module is used to classify and disinfect the multiple classified instruments according to multiple optimal classification composite disinfection parameters, and mark each classification result with a supply identification label, and the supply identification label stores the supply object, disinfection parameters, disinfection location and disinfection time node.

[0006] In a possible implementation, the disinfection parameter optimization analysis module is also used to perform the following processing: construct a composite disinfection space and a parameter selection probability space, wherein the composite disinfection space includes multiple composite disinfection parameter groups, and the parameter selection probability space includes the selection probability of the multiple composite disinfection parameter groups. Perform iterative optimization of composite disinfection parameter groups based on the parameter selection probability space and the composite disinfection space until the preset optimization constraints are met to obtain the optimal composite disinfection parameters. Perform disinfection quality difference and disinfection energy loss analysis on the optimal composite disinfection parameters to generate the first disinfection difference risk index and the first energy loss index.

[0007] In a possible implementation, the disinfection parameter optimization analysis module is also used to perform the following processing: centrally classify the distribution characteristics of the multiple equipment pollutants according to the pollutant consistency deviation threshold to obtain the distribution characteristics of multiple clusters of equipment pollutants. Identify the clustering quantity proportion coefficients of the distribution characteristics of the multiple clusters of equipment pollutants to generate multiple cluster proportion coefficients. Using the distribution characteristics of the multiple clusters of equipment pollutants as constraints, obtain the multiple composite disinfection parameter groups based on the historical disinfection record log index, construct the composite disinfection space, and configure the selection probability based on the multiple cluster proportion coefficients to generate the parameter selection probability space.

[0008] In a possible implementation, the disinfection parameter optimization analysis module is also used to perform the following processing: based on the parameter selection probability space, extract the first composite disinfection parameter group with the highest parameter selection probability in the composite disinfection space, identify the pollutant removal rate in combination with the distribution characteristics of the pollutants of the multiple instruments, and obtain multiple first pollutant removal rates. Based on the multiple first pollutant removal rates, the first instrument proportion coefficient greater than or equal to the preset pollutant removal rate is statistically calculated to calculate the first disinfection fitness. Based on the parameter selection probability space, extract the second composite disinfection parameter group in the composite disinfection space according to the preset optimization direction, identify the pollutant removal rate in combination with the distribution characteristics of the pollutants of the multiple instruments, and calculate the second disinfection fitness. Repeat the extraction of composite disinfection parameter groups in the composite disinfection space for analysis until the preset optimization constraints are reached, and obtain the composite disinfection parameter group with the largest disinfection fitness as the optimal composite disinfection parameter. Among them, the preset optimization constraints include instrument proportion coefficient constraints and selection probability constraints.

[0009] In a possible implementation, the disinfection parameter optimization analysis module is further used to perform the following processing: performing a difference analysis on multiple pollutant removal rates corresponding to the optimal composite disinfection parameter to generate the first disinfection difference risk index. Performing an energy consumption difference identification on the optimal composite disinfection parameter and the first composite disinfection parameter group to generate the first energy consumption loss index.

[0010] In a possible implementation, the pollutant distribution analysis module is further used to perform the following processing: obtaining a preset application scenario of the first type of equipment. Based on the preset application scenario, collecting equipment image samples and pollutant distribution feature sample sets. Based on a convolutional neural network, constructing a pollutant distribution analyzer with the equipment image samples and the pollutant distribution feature sample sets. Performing equipment pollutant distribution analysis on the first equipment image data through the pollutant distribution analyzer, and outputting the plurality of equipment pollutant distribution features.

[0011] In a possible implementation, the composite disinfection classification management module is also used to perform the following processing: configure the upward merging distance of the composite disinfection parameters. Obtain multiple classified composite disinfection parameters according to the distribution characteristics of the pollutants of the multi-cluster equipment. Merge the multiple classified composite disinfection parameters according to the upward merging distance of the composite disinfection parameters to generate multiple optimal classified composite disinfection parameters. Classify the first type of equipment according to the multiple optimal classified composite disinfection parameters to generate the multiple classified equipment.

[0012] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0013] The digital regional disinfection and supply management platform provided by the present application includes: obtaining the initial recovery equipment of the first disinfection supply center, classifying the initial recovery equipment, and collecting the first equipment image data of the first type of equipment. Based on the first equipment image data, the equipment pollutant distribution analysis is performed to obtain multiple equipment pollutant distribution characteristics. Based on the multiple equipment pollutant distribution characteristics, the disinfection quality difference and disinfection energy loss analysis are performed to generate the optimal composite disinfection parameter, as well as the corresponding first disinfection difference risk index and the first energy loss index, wherein the optimal composite disinfection parameter includes a cleaning control parameter and a disinfection control parameter. If the first disinfection difference risk index is less than the predetermined difference risk index or the first energy loss index is greater than or equal to the predetermined energy loss index, a secondary classification instruction is generated. Through the secondary classification instruction, the first type of equipment is subjected to composite disinfection classification to obtain multiple optimal classification composite disinfection parameters and multiple classified equipment. The multiple classified equipment is classified and disinfected according to the multiple optimal classification composite disinfection parameters, and each classification result is marked with a supply identification tag, and the supply identification tag stores the supply object, disinfection parameter, disinfection location and disinfection time node. The invention solves the technical problems in the prior art that the medical device disinfection and supply management platform is not intelligent enough, resulting in high execution cost of disinfection scheme and low processing efficiency of disinfection supply process. The invention provides a highly efficient and energy-saving disinfection management strategy for the disinfection supply center, improves the disinfection quality of the equipment, and reduces energy consumption and costs in the disinfection process. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] 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 device according to the embodiment of the present application. It should be understood that the previous 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.

[0015] Figure 1 A schematic diagram of the structure of a digital regional power supply management platform provided in an embodiment of the present application;

[0016] Figure 2 A schematic diagram of the process of generating the first disinfection difference risk index and the first energy consumption loss index for the disinfection parameter optimization analysis module in the digital regional disinfection management platform of this application.

[0017] Explanation of the accompanying drawings: equipment classification data collection module 11, pollutant distribution analysis module 12, disinfection parameter optimization analysis module 13, secondary classification analysis module 14, composite disinfection classification management module 15, supply identification module 16. DETAILED DESCRIPTION

[0018] 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.

[0019] 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.

[0020] 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 are intended to cover non-exclusive inclusions, for example, a process, device, 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, devices, products, or equipment. 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.

[0021] The present application embodiment provides a digital regional consumption management platform, such as Figure 1 As shown, the device comprises:

[0022] The instrument classification data acquisition module 11 is used to obtain the initial recovered instruments of the first disinfection supply center, classify the initial recovered instruments, and collect first instrument image data of the first type of instruments.

[0023] The disinfection and supply of medical devices refers to the process of cleaning, disinfecting, sterilizing and supplying sterile items for medical devices, which is an important part of hospital infection control and medical quality safety. In the prior art, when performing instrument disinfection, the disinfection instruments are generally classified and packaged before disinfection. However, the distribution of pollutants in the same medical device may be different. In order to ensure the consistency of the actual disinfection effect, it is necessary to increase the parameters such as the duration of disinfection and sterilization, such as increasing the duration of irradiation sterilization and the duration of high-temperature steam sterilization. In order to improve the energy efficiency ratio of disinfection and sterilization, this embodiment provides a digital regional disinfection and supply management platform, which provides access to the initial recovery instruments of the first disinfection supply center. The initial recovery instruments are instrument objects that need to be processed by the disinfection supply center, generally reusable diagnostic and treatment instruments, instruments, clean surgical gowns, surgical covers and other items, and the initial recovery instruments are classified. The specific classification category can be classified according to the specific instrument category, and the first instrument image data of the first type of instrument is collected, wherein the first type of instrument is a random category in the classification category of the initial recovery instrument.

[0024] The pollutant distribution analysis module 12 is used to perform equipment pollutant distribution analysis based on the first equipment image data to obtain a plurality of equipment pollutant distribution features.

[0025] Furthermore, the pollutant distribution analysis module 12 in the device provided in the embodiment of the application is also used for:

[0026] Obtain a preset application scenario of the first type of device. Collect device image samples and a pollutant distribution feature sample set based on the preset application scenario. Construct a pollutant distribution analyzer based on the device image samples and the pollutant distribution feature sample set based on a convolutional neural network. Perform device pollutant distribution analysis on the first device image data through the pollutant distribution analyzer, and output the multiple device pollutant distribution features.

[0027] When performing instrument pollutant distribution analysis on the first instrument image data and obtaining multiple instrument pollutant distribution features, the preset application scenario of the first type of instrument is obtained. The preset application scenario is the actual application scenario of the first type of instrument. For example, taking surgical gowns as an example, its preset application scenario is the surgical scenario. By obtaining the preset application scenario, it is convenient to quickly obtain the pollutant distribution feature samples of the sample acquisition instrument in the corresponding scenario, so that the acquired sample data is more targeted and can better represent the first type of instrument. Based on the preset application scenario, the corresponding acquisition instrument image samples and pollutant distribution feature sample sets are obtained. The acquisition instrument image samples are instrument samples of the same type as the first type of instrument. The pollutant distribution feature samples are pollutant distribution features corresponding to the acquisition instrument image samples. The pollutant distribution features include: pollutant distribution area, distribution position and other features. The specific pollutant distribution features can be manually marked, or an image recognition algorithm can be used, such as a feature point detection algorithm (such as SIFT, SURF, ORB, etc.) to identify key points in the image, and then determine the location of the pollutant based on these key points. Combined with the Canny edge detector and Sobel operator in the edge detection algorithm, the pollutant distribution area corresponding to the location of the pollutant is obtained, thereby obtaining the pollutant distribution features of the sample.

[0028] Based on the convolutional neural network, the neural network model is supervised and trained with the instrument image samples and the pollutant distribution feature sample set as training data until the model converges and the construction of the pollutant distribution analyzer is completed. The processing flow of the first instrument image data is further simplified by constructing the pollutant distribution analyzer, and the neural network model can provide better generalization ability after training, so that the acquisition of image features is more accurate and reliable. The first instrument image data is used as input data and input into the pollutant distribution analyzer, and the instrument pollutant distribution analysis is performed through the pollutant distribution analyzer, and the multiple instrument pollutant distribution features are output. By acquiring multiple instrument pollutant distribution features, the original first instrument image data is converted into processable feature parameters, which provides technical support for the subsequent cluster classification of features and the acquisition of composite disinfection parameters.

[0029] The disinfection parameter optimization analysis module 13 is used to perform disinfection quality difference and disinfection energy loss analysis based on the distribution characteristics of pollutants in the multiple instruments, generate optimal composite disinfection parameters, and the corresponding first disinfection difference risk index and first energy loss index, wherein the optimal composite disinfection parameters include cleaning control parameters and disinfection control parameters.

[0030] like Figure 2As shown, the disinfection parameter optimization analysis module 13 is also used to: construct a composite disinfection space and a parameter selection probability space, wherein the composite disinfection space includes multiple composite disinfection parameter groups, and the parameter selection probability space includes the selection probability of the multiple composite disinfection parameter groups. Based on the parameter selection probability space and the composite disinfection space, iterative optimization of the composite disinfection parameter group is performed until the preset optimization constraints are reached to obtain the optimal composite disinfection parameters. The disinfection quality difference and disinfection energy loss analysis are performed on the optimal composite disinfection parameters to generate the first disinfection difference risk index and the first energy loss index.

[0031] Based on the distribution characteristics of the multiple equipment pollutants, the disinfection quality difference and disinfection energy loss analysis are performed to generate the optimal composite disinfection parameters, as well as the corresponding first disinfection difference risk index and the first energy loss index, including: constructing a composite disinfection space and a parameter selection probability space, the composite disinfection space is a parameter selection space composed of composite disinfection parameter groups corresponding to the distribution characteristics of each type of cluster equipment pollutants. Among them, the composite disinfection space includes multiple composite disinfection parameter groups, and the parameter selection probability space includes the selection probability of the multiple composite disinfection parameter groups, and corresponds to each composite disinfection parameter group one by one. Based on the parameter selection probability space and the composite disinfection space, iterative optimization of the composite disinfection parameter group is performed until the preset optimization constraint is reached. The preset optimization constraint includes the equipment proportion coefficient constraint and the selection probability constraint. When the preset optimization constraint is reached, the fewer the corresponding precision analysis equipment is, the lower the adaptability of the corresponding parameters is, and the optimal composite disinfection parameter is obtained. The optimal composite disinfection parameter includes cleaning control parameters and disinfection control parameters. The cleaning control parameters include control parameters such as water temperature, water pressure, and cleaning time, and the disinfection control parameters include parameters such as irradiation intensity and disinfectant category concentration. The optimal composite disinfection parameters are analyzed for disinfection quality differences and disinfection energy loss, and the performance comparison between the optimal composite disinfection parameters and the first composite disinfection parameter group is completed to generate the first disinfection difference risk index and the first energy loss index. This facilitates the subsequent determination of the adaptability of the optimal composite disinfection parameters based on the first disinfection difference risk index and the first energy loss index.

[0032] Furthermore, the disinfection parameter optimization analysis module 13 is also used to: based on the parameter selection probability space, extract the first composite disinfection parameter group with the highest parameter selection probability in the composite disinfection space, identify the pollutant removal rate in combination with the distribution characteristics of the pollutants of the multiple instruments, and obtain multiple first pollutant removal rates. Based on the multiple first pollutant removal rates, the first instrument proportion coefficient greater than or equal to the preset pollutant removal rate is statistically calculated to calculate the first disinfection fitness. Based on the parameter selection probability space, extract the second composite disinfection parameter group in the composite disinfection space according to the preset optimization direction, identify the pollutant removal rate in combination with the distribution characteristics of the pollutants of the multiple instruments, and calculate the second disinfection fitness. Repeat the extraction of composite disinfection parameter groups in the composite disinfection space for analysis until the preset optimization constraints are reached, and obtain the composite disinfection parameter group with the largest disinfection fitness as the optimal composite disinfection parameter. Among them, the preset optimization constraints include instrument proportion coefficient constraints and selection probability constraints.

[0033] When obtaining the optimal composite disinfection parameters, based on the parameter selection probability space, the first composite disinfection parameter group with the highest parameter selection probability is extracted in the space, that is, the composite disinfection parameter group corresponding to the highest probability in the parameter selection probability space. When the probability is the largest, the number of corresponding pollutant clusters is the largest, and the first parameter group selected according to the pollutant characteristics can disinfect the most equipment, and this composite disinfection parameter group is used as the standard for energy loss analysis.

[0034] Combined with the pollutant distribution characteristics of the multiple instruments, the pollutant removal rate is identified to obtain multiple first pollutant removal rates. The pollutant removal rate is obtained based on the analysis of the pollution removal model. The pollution removal model is a removal prediction model constructed based on the neural network model. The model is constructed through a large number of sample instrument pollutant distribution characteristic data and the corresponding sample composite disinfection parameters and the pollutant removal rate data obtained after the disinfection is completed. The training process is supervised training until the trained model output meets the preset accuracy rate, and the removal prediction model is obtained. The removal prediction model realizes the acquisition of pollutant removal rate data according to the removal prediction model and the corresponding composite disinfection parameters. Based on the multiple first pollutant removal rates, the first instrument proportion coefficient greater than or equal to the preset pollutant removal rate is statistically calculated. The preset pollutant removal rate is the preset minimum removal rate parameter. When it is less than this parameter, the removal effect is poor, otherwise the removal effect is good. The ratio of the first instrument greater than or equal to the preset pollutant removal rate to the total instrument is calculated to obtain the first disinfection fitness.

[0035] Based on the parameter selection probability space, the second composite disinfection parameter group is extracted in the composite disinfection space according to the preset optimization direction, and the optimization direction is the direction with large to small probability in the parameter selection probability space. The second composite disinfection parameter group is a composite disinfection parameter group with a selection probability less than the first composite disinfection parameter group. By removing the prediction model, the pollutant removal rate is identified in combination with the distribution characteristics of the pollutants of the multiple instruments, and the second disinfection fitness is calculated. The disinfection fitness is obtained by calculating the disinfection fitness to achieve the acquisition of the advantages and disadvantages of the composite disinfection parameter group, which is convenient for the subsequent comparison and judgment of the parameter adaptability. Further, the same processing method is adopted to repeatedly extract the composite disinfection parameter group in the composite disinfection space and obtain the disinfection fitness parameter until the preset optimization constraint is reached. The preset optimization constraint includes the instrument proportion coefficient constraint and the selection probability constraint. The proportion coefficient constraint and the selection probability constraint are both specific constraint thresholds. When the proportion coefficient of the optimization object is lower than the threshold and the selection probability is lower than the threshold, the corresponding parameter adaptation disinfection instrument is less, the parameter audience is lower, and the precision analysis of the instrument is less. Finally, the composite disinfection parameter group with the largest disinfection fitness is obtained as the optimal composite disinfection parameter.

[0036] Furthermore, the distribution characteristics of the multiple equipment pollutants are centrally classified according to the pollutant consistency deviation threshold to obtain the distribution characteristics of multiple clusters of equipment pollutants. The coefficients of the proportion of cluster quantity in the cluster are identified for the distribution characteristics of the multiple clusters of equipment pollutants to generate multiple intra-cluster proportion coefficients. The distribution characteristics of the multiple clusters of equipment pollutants are used as constraints, and the multiple composite disinfection parameter groups are obtained based on the historical disinfection record log index, the composite disinfection space is constructed, and the selection probability is configured based on the multiple intra-cluster proportion coefficients to generate the parameter selection probability space.

[0037] The generation parameter selection probability space includes: centrally classifying the pollutant distribution characteristics of the multiple devices according to the pollutant consistency deviation threshold, the pollutant consistency deviation threshold is the minimum deviation threshold set for classifying the devices into one category, when it is less than the threshold, the corresponding devices can be classified into one category, otherwise they do not belong to the same category. The pollutant consistency deviation is calculated based on the total distribution area in the pollutant distribution characteristics. The total distribution area in the pollutant distribution characteristics of a device is randomly obtained as the classification standard, and the deviation between the total distribution area of ​​pollutants of other devices and the classification standard is calculated. The ratio of the deviation calculation result to the classification standard is obtained to obtain the pollutant consistency deviation. When the pollutant consistency deviation is within the pollutant consistency deviation threshold, the corresponding device and the classification standard device are classified into one category, otherwise the corresponding device is classified into a new category, and classification is continued according to the pollutant consistency deviation until all devices are traversed and classified. After the centralized classification is completed, the pollutant distribution characteristics of multiple clusters of devices are obtained. The pollutant distribution characteristics of multiple clusters of devices are the distribution characteristics of the device data of the classification group. For example, there are three distribution characteristics in the pollutant distribution characteristics of multiple clusters of devices, which are 10, 5, and 5 respectively, and the proportion coefficients are 0.5, 0.25 and 0.25, and multiple intra-cluster proportion coefficients are generated. The intra-cluster proportion coefficient is the ratio of the number of devices in each cluster to the total number of devices. Subsequently, the plurality of composite disinfection parameter groups are obtained from the historical disinfection record log index using the distribution characteristics of the multiple clusters of equipment pollutants as constraints. The composite disinfection parameters corresponding to the distribution characteristics of different equipment pollutants are recorded in the historical disinfection record log. The composite disinfection parameters with the most records of the equipment pollutant distribution characteristics in the historical disinfection record log are obtained as composite disinfection parameter groups. Each composite disinfection parameter group corresponds to a distribution characteristic of equipment pollutants. The composite disinfection space is constructed through multiple composite disinfection parameter groups. The selection probability of each composite disinfection parameter group is configured based on the multiple cluster proportion coefficients to generate the parameter selection probability space.

[0038] Furthermore, the composite disinfection classification management module 15 is also used to: configure the upward merging distance of composite disinfection parameters. Acquire multiple classified composite disinfection parameters according to the distribution characteristics of pollutants in the multi-cluster equipment. Merge the multiple classified composite disinfection parameters according to the upward merging distance of composite disinfection parameters to generate multiple optimal classified composite disinfection parameters and multiple classified disinfection pollutant concentration thresholds. Classify the first type of equipment according to the multiple optimal classified composite disinfection parameters and the multiple classified disinfection pollutant concentration thresholds to generate the multiple classified equipment.

[0039] Configure the upward merging distance of the composite disinfection parameters. The upward merging distance is the merging distance of the composite disinfection parameters. The upward merging distance is a pre-set merging parameter. Taking the power parameter as an example, there are two power parameters in the composite disinfection parameters, which are 1.1kw and 1.15kw respectively. At this time, the upward merging distance is 100w. Then, the two power parameters in the verification disinfection parameters can be merged into one, and the larger parameter is retained as the merging result. Subsequently, multiple classified composite disinfection parameters are obtained according to the distribution characteristics of the multi-cluster equipment pollutants. The multiple classified composite disinfection parameters are merged according to the upward merging distance of the composite disinfection parameters to generate multiple optimal classified composite disinfection parameters. Finally, the first type of equipment is classified according to the distribution characteristics of the multi-cluster equipment pollutants corresponding to the multiple optimal classified composite disinfection parameters to generate the multiple classified equipment. After the disinfection parameters are merged upward, the classification categories of the classified equipment are reduced, thereby reducing the setting of the classified composite disinfection parameters and improving the disinfection efficiency.

[0040] Furthermore, a difference analysis is performed on multiple pollutant removal rates corresponding to the optimal composite disinfection parameter to generate the first disinfection difference risk index. Energy consumption differences are identified between the optimal composite disinfection parameter and the first composite disinfection parameter group to generate the first energy consumption loss index.

[0041] Perform a difference analysis on the multiple pollutant removal rates corresponding to the optimal composite disinfection parameters. When performing the difference analysis, obtain the pollutant removal rates corresponding to the pollutant distribution characteristics of multiple instruments, calculate the mean of all pollutant removal rates, and generate the first disinfection difference risk index. The first disinfection difference risk index is used to reflect the average removal effect of the current optimal composite disinfection parameters on all multiple instrument pollutant distribution characteristics. The higher the first disinfection difference risk index parameter, the better the corresponding pollutant removal effect. Subsequently, identify the energy consumption difference between the optimal composite disinfection parameters and the first composite disinfection parameter group, obtain the energy consumption difference between the optimal composite disinfection parameters and the first composite disinfection parameter group, and generate the first energy consumption loss index. The higher the first energy consumption loss index, the higher the energy consumption of the corresponding optimal composite disinfection parameters compared to the energy consumption of the first composite disinfection parameter group. When the first disinfection difference risk index is greater than or equal to the predetermined difference risk index, the corresponding optimal composite disinfection parameter meets the requirements for the removal effect of pollutants, and the first energy loss index is less than the predetermined energy loss index, and the energy consumption is better than the energy consumption of the first composite disinfection parameter group, then the first type of equipment is uniformly disinfected and managed according to the optimal composite disinfection parameter. This provides a highly efficient and energy-saving disinfection management strategy for the disinfection supply center, improves the disinfection quality of the equipment, and reduces the energy consumption and cost of the disinfection process.

[0042] The secondary classification analysis module 14 is used to generate a secondary classification instruction if the first disinfection difference risk index is less than a predetermined difference risk index or the first energy consumption loss index is greater than or equal to a predetermined energy consumption loss index.

[0043] The composite disinfection classification management module 15 is used to perform composite disinfection classification on the first type of equipment through the secondary classification instruction, and obtain multiple optimal classification composite disinfection parameters and multiple classification equipment.

[0044] The supply identification module 16 is used to classify and disinfect the multiple classified instruments according to multiple optimal classification composite disinfection parameters, and mark each classification result with a supply identification label, and the supply identification label stores the supply object, disinfection parameters, disinfection location and disinfection time node.

[0045] If the first disinfection difference risk index is less than the predetermined difference risk index, the pollutant removal of the first disinfection difference risk index cannot meet the requirements at this time, and the predetermined difference risk index is the pre-set minimum requirement for the pollutant removal rate. Or the first energy loss index is greater than or equal to the predetermined energy loss index, and the predetermined energy loss index is the minimum requirement parameter of the energy consumption parameter of the optimal composite disinfection parameter and the energy consumption parameter of the first composite disinfection parameter group. When the first energy loss index is greater than or equal to the predetermined energy loss index, the currently acquired optimal composite disinfection parameter has higher energy consumption than the first composite disinfection parameter group, and a secondary classification instruction is generated. Based on the secondary classification instruction, the first type of equipment is subjected to composite disinfection classification according to the distribution characteristics of the pollutants in the equipment, and the same acquisition method of the composite disinfection parameter group is adopted to obtain multiple optimal classification composite disinfection parameters and multiple classification equipment. Preferably, the optimal classification composite disinfection parameters can be merged upward, and multiple classification equipment can be merged at the same time to generate multiple merged optimal classification composite disinfection parameters and multiple classification equipment. Finally, the multiple classified instruments are classified and disinfected according to multiple optimal classification composite disinfection parameters, that is, the different classified instruments are disinfected with the corresponding composite disinfection parameters, and each classification result is marked with a supply identification label, and the supply identification label stores the supply object, disinfection parameters, disinfection location and disinfection time node, so as to realize efficient disinfection and supply management of the instruments. The recycled instruments are analyzed through innovative image recognition and data analysis methods, and the optimal classification composite disinfection parameters are obtained in a targeted manner, which improves the disinfection quality of the instruments, reduces the energy consumption and saves costs during the disinfection process, and realizes efficient disinfection and supply management of the instruments.

[0046] In the embodiment of the present application, by acquiring the initial recovery instruments of the first disinfection supply center, the initial recovery instruments are classified, and the first instrument image data of the first type of instruments are collected. Based on the first instrument image data, the instrument pollutant distribution analysis is performed to obtain multiple instrument pollutant distribution characteristics. Based on the multiple instrument pollutant distribution characteristics, the disinfection quality difference and disinfection energy loss analysis are performed to generate the optimal composite disinfection parameters, as well as the corresponding first disinfection difference risk index and the first energy loss index, wherein the optimal composite disinfection parameters include cleaning control parameters and disinfection control parameters. If the first disinfection difference risk index is less than the predetermined difference risk index or the first energy loss index is greater than or equal to the predetermined energy loss index, a secondary classification instruction is generated. Through the secondary classification instruction, the first type of instruments are subjected to composite disinfection classification to obtain multiple optimal classification composite disinfection parameters and multiple classified instruments. The multiple classified instruments are classified and disinfected according to the multiple optimal classification composite disinfection parameters, and each classification result is marked with a supply identification tag, and the supply identification tag stores the supply object, disinfection parameters, disinfection location and disinfection time node. The invention solves the technical problems in the prior art that the medical device disinfection and supply management platform is not intelligent enough, resulting in high execution cost of disinfection scheme and low processing efficiency of disinfection supply process. The invention provides a highly efficient and energy-saving disinfection management strategy for the disinfection supply center, improves the disinfection quality of the equipment, and reduces energy consumption and costs in the disinfection process.

[0047] 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. Digital regional consumption and supply management platform, characterized by: The platform includes: An instrument classification data acquisition module is used to obtain initial recovered instruments from a first sterilization supply center, classify the initial recovered instruments, and collect first instrument image data of first type instruments; A pollutant distribution analysis module, configured to perform an equipment pollutant distribution analysis based on the first equipment image data to obtain a plurality of equipment pollutant distribution features; A disinfection parameter optimization analysis module, used to analyze the disinfection quality difference and disinfection energy loss based on the distribution characteristics of the multiple equipment pollutants, generate the optimal composite disinfection parameter, and the corresponding first disinfection difference risk index and first energy loss index, wherein the optimal composite disinfection parameter includes a cleaning control parameter and a disinfection control parameter; A secondary classification analysis module, configured to generate a secondary classification instruction if the first disinfection difference risk index is less than a predetermined difference risk index or the first energy consumption loss index is greater than or equal to a predetermined energy consumption loss index; A composite disinfection classification management module, used to perform composite disinfection classification on the first type of equipment through the secondary classification instruction, and obtain multiple optimal classification composite disinfection parameters and multiple classification equipment; A supply identification module, used to classify and disinfect the multiple classified instruments according to multiple optimal classification composite disinfection parameters, and mark each classification result with a supply identification tag, wherein the supply identification tag stores the supply object, disinfection parameters, disinfection location and disinfection time node; The disinfection parameter optimization analysis module is used for: Constructing a composite disinfection space and a parameter selection probability space, wherein the composite disinfection space includes a plurality of composite disinfection parameter groups, and the parameter selection probability space includes the selection probabilities of the plurality of composite disinfection parameter groups; Iteratively optimizing the composite disinfection parameter group based on the parameter selection probability space and the composite disinfection space until the preset optimization constraints are met to obtain the optimal composite disinfection parameter; Perform disinfection quality difference and disinfection energy loss analysis on the optimal composite disinfection parameters to generate the first disinfection difference risk index and the first energy loss index; The disinfection parameter optimization analysis module is used for: Centrally classify the multiple equipment pollutant distribution characteristics according to the pollutant consistent deviation threshold to obtain multiple clusters of equipment pollutant distribution characteristics; Identify the intra-cluster clustering quantity ratio coefficients for the distribution characteristics of the multiple clusters of equipment pollutants, and generate multiple intra-cluster ratio coefficients; Taking the distribution characteristics of the multiple clusters of equipment pollutants as constraints, the multiple composite disinfection parameter groups are obtained based on the historical disinfection record log index, the composite disinfection space is constructed, and the selection probability is configured based on the multiple cluster proportion coefficients to generate the parameter selection probability space; The platform includes: If the first disinfection difference risk index is greater than or equal to a predetermined difference risk index, and the first energy consumption loss index is less than a predetermined energy consumption loss index, the first type of equipment is uniformly disinfected and managed according to the optimal composite disinfection parameters.

2. The platform according to claim 1, characterized in that The disinfection parameter optimization analysis module is also used for: Based on the parameter selection probability space, extract the first composite disinfection parameter group with the highest parameter selection probability in the composite disinfection space, identify the pollutant removal rate in combination with the distribution characteristics of the pollutants of the multiple instruments, and obtain multiple first pollutant removal rates; Based on the multiple first pollutant removal rates, a first equipment ratio coefficient greater than or equal to a preset pollutant removal rate is counted to calculate a first disinfection fitness; Based on the parameter selection probability space, extract the second composite disinfection parameter group in the composite disinfection space according to the preset optimization direction, identify the pollutant removal rate in combination with the distribution characteristics of the pollutants of the multiple instruments, and calculate the second disinfection fitness; Repeatedly extracting composite disinfection parameter groups in the composite disinfection space for analysis until the preset optimization constraints are met, and obtaining the composite disinfection parameter group with the maximum disinfection fitness as the optimal composite disinfection parameter; Among them, the preset optimization constraints include equipment proportion coefficient constraints and selection probability constraints.

3. The platform according to claim 2, characterized in that The disinfection parameter optimization analysis module is also used for: Performing difference analysis on multiple pollutant removal rates corresponding to the optimal composite disinfection parameters to generate the first disinfection difference risk index; The energy consumption difference between the optimal composite disinfection parameter and the first composite disinfection parameter group is identified to generate the first energy consumption loss index.

4. The platform according to claim 1, characterized in that The pollutant distribution analysis module is also used for: Obtaining a preset application scenario of the first type of device; Collecting equipment image samples and pollutant distribution feature sample sets based on the preset application scenario; Based on a convolutional neural network, a pollutant distribution analyzer is constructed using the instrument image samples and the pollutant distribution feature sample set; The contaminant distribution analyzer performs an instrument contaminant distribution analysis on the first instrument image data, and outputs the plurality of instrument contaminant distribution features.

5. The platform according to claim 1, characterized in that The composite disinfection classification management module is also used for: Configure the upward merging distance of the composite disinfection parameters; Acquire multiple classification composite disinfection parameters according to the distribution characteristics of the multiple clusters of equipment pollutants; The multiple classified composite disinfection parameters are merged according to the upward merging distance of the composite disinfection parameters to generate multiple optimal classified composite disinfection parameters; The first type of equipment is classified according to the multiple optimal classification and composite disinfection parameters to generate the multiple classified equipment.