Waste medical data processing method and device and computing equipment

Abstract

The invention provides a medical waste data processing method and apparatus, and a computing device. The medical waste data processing method comprises the steps of obtaining various medical waste data; preprocessing the various medical waste data to obtain medical waste preprocessed data; performing feature extraction on the medical waste preprocessing data to obtain feature vector data; inputting the feature vector data into a trained waste medical data classification model for classification processing to obtain classification result data; the medical waste data classification model is obtained by training according to a medical waste data training set, and the medical waste data training set comprises chemical waste data, drug waste data, injury waste data, pathological waste data and infectious waste data in a historical time period; and carrying out visual display on the classification result data. According to the invention, the classification accuracy, efficiency and environmental safety of medical waste treatment can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical waste treatment, and in particular to a method, device and computing equipment for processing medical waste data. Background Art

[0002] Large general hospitals generate a large amount of medical waste every day, including medical waste from different departments such as operating rooms, wards, and laboratories. There are many types of medical waste, such as infectious waste (used syringes, blood-contaminated dressings, etc.), pathological waste (surgical removal of tissue, pathological specimens, etc.), and traumatic waste (surgical blades, needles, etc.). For these medical wastes, hospitals currently generally use manual sorting methods, which has low processing efficiency, high environmental risks, and is prone to errors. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a method, device and computing equipment for processing medical waste data, which can improve the classification accuracy, efficiency and environmental safety of medical waste treatment.

[0004] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0005] A method for processing medical waste data, comprising:

[0006] Obtain various medical waste data;

[0007] Preprocessing the multiple medical waste data to obtain medical waste preprocessing data;

[0008] Extracting features from the medical waste pretreatment data to obtain feature vector data;

[0009] Inputting the feature vector data into a trained medical waste data classification model for classification processing to obtain classification result data; the medical waste data classification model is trained based on a medical waste data training set, and the medical waste data training set includes chemical waste data, pharmaceutical waste data, injury waste data, pathological waste data, and infectious waste data within a historical period of time;

[0010] The classification result data is visualized and displayed.

[0011] Optionally, preprocessing the multiple medical waste data to obtain medical waste preprocessing data includes:

[0012] Performing format conversion processing on the multiple medical waste data to obtain intermediate data;

[0013] The intermediate data is persistently processed to obtain medical waste preprocessing data.

[0014] Optionally, feature extraction is performed on the medical waste pretreatment data to obtain feature vector data, including:

[0015] Performing data labeling on the medical waste pretreatment data to obtain labeled data;

[0016] Feature extraction is performed on the labeled data to obtain feature vector data.

[0017] Optionally, the feature vector data is input into a trained medical waste data classification model for classification processing to obtain classification result data, including:

[0018] Inputting the feature vector data into a first processing module of a medical waste data classification model for processing to obtain a first output;

[0019] The first output is input into the second processing module of the medical waste data classification model for processing to obtain classification result data.

[0020] Optionally, the first output is input into a second processing module of a medical waste data classification model for processing to obtain classification result data, including:

[0021] Inputting the first output into a second processing module of a medical waste data classification model for processing to obtain a second output;

[0022] The second output is input into the second processing module of the medical waste data classification model for processing to obtain classification result data.

[0023] Optionally, the training process of the medical waste data classification model includes:

[0024] Inputting the medical waste data training set into a first processing module of a medical waste data classification model for processing to obtain a first processing result;

[0025] The first processing result is input into the second processing module of the medical waste data classification model for processing to obtain the medical waste data classification model.

[0026] Optionally, visually displaying the classification result data includes:

[0027] Obtain a visual carrier for displaying medical waste treatment data;

[0028] Binding the analysis report to the visualization carrier;

[0029] The visualization carrier is rendered to obtain a visualization graph of medical waste treatment data.

[0030] An embodiment of the present invention further provides a device for processing medical waste data, comprising:

[0031] Acquisition module, used to obtain various medical waste data;

[0032] The processing module is used to pre-process the multiple medical waste data to obtain medical waste pre-processed data; extract features from the medical waste pre-processed data to obtain feature vector data; input the feature vector data into a trained medical waste data classification model for classification processing to obtain classification result data; the medical waste data classification model is trained based on a medical waste data training set, and the medical waste data training set includes chemical waste data, pharmaceutical waste data, injury waste data, pathological waste data, and infectious waste data within a historical time period; and visualize the classification result data.

[0033] An embodiment of the present invention further provides a computing device, comprising:

[0034] one or more processors;

[0035] A storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the medical waste data processing method described in the present invention.

[0036] An embodiment of the present invention further provides a computer-readable storage medium, wherein a program is stored in the computer-readable storage medium, and when the program is executed by a processor, the method for processing medical waste data of the present invention is implemented.

[0037] The above technical solution of the present invention has at least the following technical effects:

[0038] The medical waste data processing method of the present invention obtains a variety of medical waste data; pre-processes the multiple medical waste data to obtain medical waste pre-processed data; extracts features from the medical waste pre-processed data to obtain feature vector data; inputs the feature vector data into a trained medical waste data classification model for classification processing to obtain classification result data; the medical waste data classification model is trained based on a medical waste data training set, and the medical waste data training set includes chemical waste data, drug waste data, injury waste data, pathological waste data, and infectious waste data within a historical period; and the classification result data is visualized. It can improve the classification accuracy, efficiency, and environmental safety of medical waste treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a flow chart of a method for processing medical waste data of the present invention;

[0040] Figure 2 It is a schematic diagram of the medical waste data processing device of the present invention. DETAILED DESCRIPTION

[0041] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0042] like Figure 1 As shown, an embodiment of the present invention provides a method for processing medical waste data, including:

[0043] Step S1, obtaining various medical waste data;

[0044] Step S2, preprocessing the multiple medical waste data to obtain medical waste preprocessing data;

[0045] Step S3, extracting features from the medical waste pretreatment data to obtain feature vector data;

[0046] Step S4, inputting the feature vector data into a trained medical waste data classification model for classification processing to obtain classification result data; the medical waste data classification model is trained based on a medical waste data training set, and the medical waste data training set includes chemical waste data, pharmaceutical waste data, injury waste data, pathological waste data, and infectious waste data within a historical period of time;

[0047] Step S5: Visually display the classification result data.

[0048] In this embodiment, Figure 1As shown, the medical waste data processing method of the present invention judges the classification result of medical waste based on the obtained multiple medical waste original data; firstly, the source department, physical characteristics, chemical characteristics and other data of the medical waste are obtained, and the acquisition method can be obtained by manual recording, sensor detection and other methods. For example, by installing a sensor on the waste collection container to detect whether the waste is liquid, or recording the source department of the waste through the hospital information system, the source department is the operating room, the laboratory, the ward, etc., the physical characteristics are whether it is a sharp instrument, whether it is liquid, etc., and the chemical characteristics are whether it contains harmful substances, whether it is a drug, etc.; then the multiple medical waste data are formatted and normalized First, the medical waste pretreatment data is obtained by pre-processing such as chemical treatment; secondly, the medical waste pre-treatment data is subjected to feature extraction in terms of source department, physical characteristics, chemical characteristics, etc., to obtain feature vector data; thirdly, the feature vector data is input into the trained medical waste data classification model for classification processing to obtain classification result data; wherein, the medical waste data classification model is trained based on the medical waste data training set, and the medical waste data training set includes chemical waste data, drug waste data, injury waste data, pathological waste data, and infectious waste data accumulated within a certain historical period; finally, the classification result data is visualized using visualization means. The method of the invention can improve the classification accuracy, efficiency, and environmental safety of medical waste treatment.

[0049] In an optional embodiment of the present invention, in step S2, the plurality of medical waste data are preprocessed to obtain medical waste preprocessed data, including:

[0050] Step S21, performing format conversion processing on the multiple medical waste data to obtain intermediate data;

[0051] Step S22, performing persistence processing on the intermediate data to obtain medical waste preprocessing data.

[0052] In this embodiment, the obtained multiple medical waste data are preprocessed; first, the data formats of the multiple medical waste data are converted, and the data collected by different sensors are uniformly converted into a standard format, for example, the time data is converted into a YYYY-MM-DD HH:MM:SS format, and the length data is converted into centimeters to obtain intermediate data; then, the intermediate data is encoded, the data collected by different sensors are integrated and encoded to form a complete medical waste data record, and the medical waste data record is stored in a database for persistent storage to obtain medical waste preprocessing data; among them, the time series database is specially used to store and process time series data, emphasizing high-performance time range query, aggregation and analysis, and is particularly suitable for scenarios such as sensor data that require processing of a large amount of time series data. In this solution, it is used to store data collected by sensors in real time.

[0053] In an optional embodiment of the present invention, in step S3, feature extraction is performed on the medical waste pretreatment data to obtain feature vector data, including:

[0054] Step S31, annotating the medical waste pretreatment data to obtain annotated data;

[0055] Step S32, extracting features from the labeled data to obtain feature vector data.

[0056] In this embodiment, feature extraction is performed on the medical waste pretreatment data; first, data annotation is performed on the medical waste pretreatment data to determine the category to which each data sample belongs. According to the classification standard of medical waste (such as infectious, pathological, damaging, medicinal, chemical, etc.), professionals analyze and annotate the medical waste data to obtain annotated data;

[0057] Infectious waste refers to medical waste that carries pathogenic microorganisms and has the risk of causing the spread of infectious diseases. It mainly comes from wards, operating rooms, laboratories and other departments of medical institutions. For example, various dressings (such as gauze, cotton balls, etc.) contaminated by patients' blood, body fluids, and excrement; used disposable medical supplies, such as disposable syringes and infusion sets, which may be contaminated by pathogens after use; and domestic waste generated by isolated infectious disease patients or suspected infectious disease patients. Specific items include instruments: such as used surgical instruments such as scalpels, scissors, and tweezers, which come into contact with the patient's tissues, blood, etc. during the operation and may carry various pathogens; if these instruments are not handled properly, they can easily cause disease transmission. Dressings: including bandages and Band-Aids contaminated with blood, pus, etc. Taking wound dressing changes as an example, used gauze with pus and blood is a typical infectious waste; laboratory waste: blood, urine, feces and other specimens after laboratory testing, as well as disposable straws, test tubes, etc. used in the testing process; for example, in the hospital laboratory, blood specimens containing pathogens such as hepatitis virus and HIV virus after testing are infectious waste.

[0058] Pathological waste refers to human waste and animal carcasses generated during the diagnosis and treatment process. It mainly comes from operating rooms, pathology departments and other departments. These wastes often contain a large number of pathogens and harmful cells. Specific items include human tissues: human tissues removed or discarded during surgery and other diagnosis and treatment processes, such as placentas, dead fetuses, and limbs after amputation. For example, the placenta after delivery in the obstetrics and gynecology department is pathological waste if the mother suffers from an infectious disease; there are also tumor tissues removed during surgery. The remaining tissue after pathological sections: During the pathological examination, the human tissue remaining after making pathological sections is also pathological waste. For example, a small piece of tissue removed from a human organ is the remaining part after slicing. Medical experimental animal carcasses and tissues: In medical research experiments, the carcasses of experimental animals (such as mice, rabbits, etc.) after death, as well as animal tissues cut during the experiment, are all pathological waste.

[0059] Injurious waste refers to discarded medical sharps that can stab or cut the human body. They mainly come from various clinical departments, injection rooms, etc. If these sharps are mixed with domestic garbage or other waste, they can easily cause personal injury and may spread diseases through blood. Specific items include medical needles: including injection needles, suture needles, etc. For example, in the injection room of a hospital, the sharp part of a used disposable syringe needle may pierce the garbage bag and stab the person who comes into contact with it, and if the needle carries pathogens, it will cause infection. Medical sharps: such as scalpels, skin preparation knives, glass ampoules, etc. The scalpels used during surgery are very sharp. Once discarded at will, they may cut medical staff or cleaning staff. After the glass ampoule is broken, the edges of its fragments are sharp and it is also considered as damaging waste.

[0060] Pharmaceutical waste refers to discarded drugs that are expired, obsolete, deteriorated or contaminated. They mainly come from pharmacies, wards, treatment rooms, etc. If these drugs are not properly handled, they may pollute the environment, and some of the drug ingredients may enter the human body through various channels and cause harm. Specific items include: expired drugs: expired oral drugs, injectable drugs, etc. that are regularly cleared out by hospital pharmacies. For example, expired antibiotic capsules, expired injections, etc. Obsolete drugs: With the development of medical technology and the replacement of drugs, some obsolete drugs are also pharmaceutical waste. For example, after some previously used drugs with greater side effects are replaced by new drugs, the old drugs in stock need to be treated as waste. Deteriorated drugs: During the storage of drugs, the drugs deteriorate due to improper storage conditions (such as inappropriate temperature and humidity). For example, some vaccines that need to be refrigerated will become ineffective and deteriorate when the temperature is too high, and become pharmaceutical waste. Contaminated drugs: Drugs are contaminated during transportation or use. For example, in a ward, if a bottle of infusion medicine is opened and other impurities fall into it, it cannot be used anymore and should be treated as pharmaceutical waste.

[0061] Chemical waste refers to discarded chemicals that are toxic, corrosive, flammable and explosive. They mainly come from the hospital's laboratory, disinfection supply room, operating room and other departments. If these chemical wastes leak or are improperly handled, they will cause serious harm to the environment and human health. Specific items include disinfectants: such as expired glutaraldehyde, peracetic acid and other disinfectants. The chemical properties of these disinfectants may change after they expire, which not only reduces the disinfection effect, but also may produce harmful chemicals. Mercury and its compounds: Medical devices such as thermometers and sphygmomanometers in hospitals contain mercury. If these devices are damaged and mercury leaks out, mercury and its compounds are chemical waste. Mercury is a toxic heavy metal that can cause damage to the human nervous system. Chemical reagents discarded in laboratories: In laboratories such as the laboratory, some discarded chemical reagents, such as strong acids (sulfuric acid, hydrochloric acid, etc.), strong alkalis (sodium hydroxide, etc.), organic solvents (ethanol, acetone, etc.), etc. If these chemical reagents are dumped at will, they will corrode sewers and pollute soil and water bodies. For example, for a blood-contaminated gauze sample from an operating room, label it as infectious waste;

[0062] Then, based on the labeled data, feature extraction is performed on the required data attributes, and the attributes that can be used to obtain classification results are extracted and combined together in the form of vectors to obtain feature vector data.

[0063] In an optional embodiment of the present invention, in step S4, the feature vector data is input into a trained medical waste data classification model for classification processing to obtain classification result data, including:

[0064] Step S41, inputting the feature vector data into a first processing module of a medical waste data classification model for processing to obtain a first output;

[0065] Step S42: input the first output into the second processing module of the medical waste data classification model for processing to obtain classification result data.

[0066] In this embodiment, the medical waste data classification model is used to classify the feature vector data. First, the feature vector data is input into the first processing module of the medical waste data classification model for processing to obtain a first output. Specifically, the feature vector data is input into the first processing module of the medical waste data classification model. After being processed by the first processing module, the edge probability of the feature vector data is obtained. For example, the feature vector data X = {x1, x2, ...x n The marginal probability of} is P(X), where P(X) is the element x1, x2, ...x in the feature vector data X. n The sum of the occurrence probabilities, that is Where P(x i ) is the element xi Probability of occurrence.

[0067] In an optional embodiment of the present invention, in step S42, the first output is input into a second processing module of the medical waste data classification model for processing to obtain classification result data, including:

[0068] Step S421, inputting the first output into a second processing module of the medical waste data classification model for processing to obtain a second output;

[0069] Step S422: input the second output into the second processing module of the medical waste data classification model for processing to obtain classification result data.

[0070] In this embodiment, the first output is processed by the second processing module of the medical waste data classification model to obtain classification result data; first, the first output is processed by the second processing module of the medical waste data classification model to obtain the second output. Specifically, the first output obtains the feature vector data X={x1, x2, ...x n The edge probability P(X) of} is input into the second processing module of the medical waste data classification model for processing. The second output can be obtained by calculating the following formula:

[0071]

[0072] Among them, X represents the feature vector data, C is the medical waste classification result, P(X|C) is the likelihood probability, μ is the mean of the feature data, σ 2 is the variance of the characteristic data, π is the circumference of a circle;

[0073] Then, the likelihood probability P(X|C) is input into the second processing module of the medical waste data classification model to obtain the classification probability, that is, the classification result data. The classification probability can be calculated by the following formula:

[0074] P(C|X)=P(X|C)P(C) / P(X)

[0075] Among them, P(C|X) is the classification result data, P(X|C) is the likelihood probability, P(C) is the prior probability, and P(X) is the marginal probability; the prior probability P(C) is obtained through training.

[0076] In an optional embodiment of the present invention, in step S4, the training process of the medical waste data classification model includes:

[0077] Step S43, inputting the medical waste data training set into the first processing module of the medical waste data classification model for processing to obtain a first processing result;

[0078] Step S44: input the first processing result into the second processing module of the medical waste data classification model for processing to obtain the medical waste data classification model.

[0079] In this embodiment, the medical waste data training set is first input into the first processing module of the medical waste data classification model for processing. The medical waste data training set is feature vector data containing classification result data. After being processed by the first processing module, the prior probability P(C) of the medical waste classification result C is obtained. Specifically, the frequency of occurrence of each category of medical waste in the training data set is statistically analyzed to estimate the prior probability. For example, if there are 300 samples of infectious waste and 200 samples of pathological waste in the training data set, and the total number of samples is 1000, then the prior probability of infectious waste is 0.3, and the prior probability of pathological waste is 0.2. Then, the first processing result is input into the second processing module of the medical waste data classification model for processing, and the medical waste data classification model is obtained as follows:

[0080] P(C|X)=P(X|C)P(C) / P(X)

[0081] Among them, P(C|X) is the classification result data, P(X|C) is the likelihood probability, P(C) is the prior probability, and P(X) is the marginal probability.

[0082] In an optional embodiment of the present invention, in step S5, visually displaying the classification result data includes:

[0083] Step S51, obtaining a visual carrier for displaying medical waste treatment data;

[0084] Step S52, binding the analysis report to the visualization carrier;

[0085] Step S53, rendering the visualization carrier to obtain a visualization graph of medical waste treatment data.

[0086] In this embodiment, the classification result data is visualized; first, a visualization carrier for displaying the medical waste treatment data is obtained, such as a chart as the visualization carrier, and then the position, size and arrangement of each chart is determined; then the classification result data is bound to the visualization carrier, and suitable graphic elements (such as points, lines, surfaces, and bodies) are selected to represent data attributes; finally, the visualization carrier is rendered, and suitable colors are selected to distinguish different data categories and levels. The visualization carrier is rendered using a graphics rendering engine to obtain a visualization graphic of the medical waste treatment data.

[0087] The specific implementation process of the above method of the present invention is described below:

[0088] Step S111, obtaining a variety of medical waste data; specifically, the smart medical waste collection barrel can be equipped with sensors (such as weight sensors, liquid level sensors, etc.) to monitor the type, quantity and status of the waste in the barrel in real time; the smart medical waste collection vehicle is equipped with an automatic navigation system and a GPS positioning system, which can automatically collect the smart medical waste collection barrels of each department according to a preset route; the smart medical waste collection and transfer vehicle transports the collected medical waste to local treatment equipment or a centralized treatment center for classification and treatment;

[0089] Step S112, performing format conversion processing on the multiple medical waste data to obtain intermediate data;

[0090] Step S113, performing persistence processing on the intermediate data to obtain medical waste preprocessing data.

[0091] Step S114, annotating the medical waste pretreatment data to obtain annotated data;

[0092] Step S115, extracting features from the labeled data to obtain feature vector data;

[0093] Step S116, inputting the medical waste data training set into the first processing module of the medical waste data classification model for processing to obtain a first processing result;

[0094] Step S117, inputting the first processing result into the second processing module of the medical waste data classification model for processing to obtain the medical waste data classification model;

[0095] Step S118, inputting the feature vector data into a first processing module of a medical waste data classification model for processing to obtain a first output;

[0096] Step S119, inputting the first output into a second processing module of the medical waste data classification model for processing to obtain a second output;

[0097] Step S1110, inputting the second output into a second processing module of the medical waste data classification model for processing to obtain classification result data;

[0098] Step S1111, obtaining a visualization carrier for displaying medical waste treatment data; the visualization carrier may be, for example, a remote server or a cloud platform;

[0099] Step S1112, binding the analysis report to the visualization carrier;

[0100] Step S1113, rendering the visualization carrier to obtain a visualization graph of the medical waste treatment data, so as to intuitively view the status and situation of the medical waste treatment data and facilitate management personnel to make decisions and supervision.

[0101] The above scheme of the present invention extracts feature vector data based on the acquired multiple medical waste data, uses the trained medical waste data classification model to classify the medical waste data, and visualizes the classification result data, which significantly improves the treatment efficiency of medical waste, reduces the risk of environmental pollution, and realizes the effective use of resources. At the same time, through intelligent equipment and integrated systems, the speed of waste treatment is accelerated, manual operations are reduced, and the risk of cross contamination is reduced. Through automated separation and resource recycling lines, the recovery rate of recyclable materials is improved and the cost of waste treatment is reduced. The Internet of Things medical waste treatment big data cloud platform is used to achieve comprehensive supervision and data management of the entire treatment process, ensuring the efficiency and transparency of the entire treatment process. It can monitor the position and weight of the waste in the collection barrel in real time, and then use the collection vehicle and transfer vehicle to automatically collect medical waste from each department according to the preset route, and transport the collected medical waste to the local treatment equipment or centralized treatment center for centralized crushing and high-temperature sterilization. Finally, the separated recyclable materials are sent to the factory to be made into industrial products for resource recycling.

[0102] like Figure 2 As shown, an embodiment of the present invention further provides a medical waste data processing device 20, comprising:

[0103] An acquisition module 21, used to acquire various medical waste data;

[0104] The processing module 22 is used to pre-process the multiple medical waste data to obtain medical waste pre-processed data; perform feature extraction on the medical waste pre-processed data to obtain feature vector data; input the feature vector data into a trained medical waste data classification model for classification processing to obtain classification result data; the medical waste data classification model is trained based on a medical waste data training set, and the medical waste data training set includes chemical waste data, drug waste data, injury waste data, pathological waste data and infectious waste data within a historical time period; and visualize the classification result data.

[0105] Optionally, preprocessing the multiple medical waste data to obtain medical waste preprocessing data includes:

[0106] Performing format conversion processing on the multiple medical waste data to obtain intermediate data;

[0107] The intermediate data is persistently processed to obtain medical waste preprocessing data.

[0108] Optionally, feature extraction is performed on the medical waste pretreatment data to obtain feature vector data, including:

[0109] Performing data labeling on the medical waste pretreatment data to obtain labeled data;

[0110] Feature extraction is performed on the labeled data to obtain feature vector data.

[0111] Optionally, the feature vector data is input into a trained medical waste data classification model for classification processing to obtain classification result data, including:

[0112] Inputting the feature vector data into a first processing module of a medical waste data classification model for processing to obtain a first output;

[0113] The first output is input into the second processing module of the medical waste data classification model for processing to obtain classification result data.

[0114] Optionally, the first output is input into a second processing module of a medical waste data classification model for processing to obtain classification result data, including:

[0115] Inputting the first output into a second processing module of a medical waste data classification model for processing to obtain a second output;

[0116] The second output is input into the second processing module of the medical waste data classification model for processing to obtain classification result data.

[0117] Optionally, the training process of the medical waste data classification model includes:

[0118] Inputting the medical waste data training set into a first processing module of a medical waste data classification model for processing to obtain a first processing result;

[0119] The first processing result is input into the second processing module of the medical waste data classification model for processing to obtain the medical waste data classification model.

[0120] Optionally, visually displaying the classification result data includes:

[0121] Obtain a visual carrier for displaying medical waste treatment data;

[0122] Binding the analysis report to the visualization carrier;

[0123] The visualization carrier is rendered to obtain a visualization graph of medical waste treatment data.

[0124] It should be noted that the device is a device that corresponds one-to-one to the above method, and all implementation methods in the above method embodiments can be applied to the embodiments of the device and can achieve the same technical effects.

[0125] An embodiment of the present invention further provides a computing device, comprising:

[0126] one or more processors;

[0127] The storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the medical waste data processing method of the present invention. All implementation methods in the above method embodiments are applicable to the embodiments of the device and can achieve the same technical effect.

[0128] An embodiment of the present invention further provides a computing device readable storage medium, comprising:

[0129] The computing device readable storage medium stores a program, which, when executed by the processor, implements the medical waste data processing method of the present invention. All implementations in the above method embodiments are applicable to the computing device readable storage medium embodiments, and can achieve the same technical effects.

[0130] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0131] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0132] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0133] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0134] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0135] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical disks.

[0136] In addition, it should be noted that in the apparatus and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. Moreover, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it is understood that all or any steps or components of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in hardware, firmware, software or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

[0137] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing device. The computing device can be a well-known general-purpose device. Therefore, the purpose of the present invention can also be achieved by simply providing a program product containing a program code for implementing a method or device. That is to say, such a program product also constitutes the present invention, and a storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order. Some steps can be performed in parallel or independently of each other.

[0138] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for processing medical waste data, characterized in that: include: Obtain various medical waste data; Preprocessing the multiple medical waste data to obtain medical waste preprocessing data; Extracting features from the medical waste pretreatment data to obtain feature vector data; Inputting the feature vector data into a trained medical waste data classification model for classification processing to obtain classification result data; the medical waste data classification model is trained based on a medical waste data training set, and the medical waste data training set includes chemical waste data, pharmaceutical waste data, injury waste data, pathological waste data, and infectious waste data within a historical period of time; The classification result data is visualized and displayed.

2. The method for processing medical waste data according to claim 1, characterized in that: Preprocessing the multiple medical waste data to obtain medical waste preprocessing data includes: Performing format conversion processing on the multiple medical waste data to obtain intermediate data; The intermediate data is persistently processed to obtain medical waste preprocessing data.

3. The method for processing medical waste data according to claim 1, characterized in that: Feature extraction is performed on the medical waste pretreatment data to obtain feature vector data, including: Performing data labeling on the medical waste pretreatment data to obtain labeled data; Feature extraction is performed on the labeled data to obtain feature vector data.

4. The method for processing medical waste data according to claim 1, characterized in that: The feature vector data is input into the trained medical waste data classification model for classification processing to obtain classification result data, including: Inputting the feature vector data into a first processing module of a medical waste data classification model for processing to obtain a first output; The first output is input into the second processing module of the medical waste data classification model for processing to obtain classification result data.

5. The method for processing medical waste data according to claim 4, characterized in that: The first output is input into the second processing module of the medical waste data classification model for processing to obtain classification result data, including: Inputting the first output into a second processing module of a medical waste data classification model for processing to obtain a second output; The second output is input into the second processing module of the medical waste data classification model for processing to obtain classification result data.

6. The method for processing medical waste data according to claim 1, characterized in that: The training process of the medical waste data classification model includes: Inputting the medical waste data training set into a first processing module of a medical waste data classification model for processing to obtain a first processing result; The first processing result is input into the second processing module of the medical waste data classification model for processing to obtain the medical waste data classification model.

7. The method for processing medical waste data according to claim 1, characterized in that: Visualizing the classification result data includes: Obtain a visual carrier for displaying medical waste treatment data; Binding the analysis report to the visualization carrier; The visualization carrier is rendered to obtain a visualization graph of medical waste treatment data.

8. A device for processing medical waste data, characterized in that: include: Acquisition module, used to obtain various medical waste data; A processing module, used for preprocessing the multiple medical waste data to obtain medical waste preprocessing data; Extracting features from the medical waste pretreatment data to obtain feature vector data; The feature vector data is input into a trained medical waste data classification model for classification processing to obtain classification result data; the medical waste data classification model is trained based on a medical waste data training set, and the medical waste data training set includes chemical waste data, pharmaceutical waste data, injury waste data, pathological waste data and infectious waste data within a historical time period; the classification result data is visualized.

9. A computing device, characterized in that include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computing device readable storage medium stores a program, which implements the method according to any one of claims 1 to 7 when executed by a processor.

Images