Digital medical instrument quality data intelligent management platform

Abstract

The invention relates to the technical field of data processing, in particular to a digital medical instrument quality data intelligent management platform, which comprises a processor and a memory, and the processor executes a computer program of the memory to realize the following steps: acquiring a sample set of any type of medical instrument, classifying the sample set, and storing the classified sample set into a database; obtaining a fault-free sample set, an unknown fault sample set and a known fault sample set; obtaining the reasonable degree of each K value in a preset K value range when each sample in the unknown fault sample set is classified by using a K nearest neighbor algorithm, and obtaining a new unknown fault sample set and a new known fault sample set; according to the method, the optimal K value of each sample in a new unknown fault sample set is acquired, the optimal K value is acquired according to the classification accuracy of each optimal K value, and the samples monitored in real time are classified by using the K nearest neighbor algorithm, so that the fault classification result of the medical instrument is more accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to an intelligent management platform for digital medical device quality data. Background Art

[0002] With the rapid development of medical technology and the continuous growth of medical needs, medical devices play a crucial role in medical diagnosis and treatment. However, traditional medical device management methods face many challenges, such as incomplete equipment information records, difficult traceability, high maintenance costs, and data islands. These problems not only affect the use efficiency and safety of medical devices but also bring great inconvenience to the management of medical institutions. To solve these problems, an intelligent management platform for digital medical device quality data has emerged, which uses modern information technology to comprehensively and intelligently manage the entire life cycle of medical devices from procurement, warehousing, use, maintenance to scrapping.

[0003] The intelligent management platform for digital medical device quality data usually uses the PHM algorithm to monitor various parameters of medical devices, analyze the quality of medical devices, predict the health status and fault problems of medical devices, so that medical staff can timely discover the quality problems of medical devices and facilitate the repair or replacement of medical devices.

[0004] In order to better identify the fault problems of medical devices and take corresponding measures in a timely manner, the existing intelligent management platform for digital medical device quality data constructs a fault database based on historical fault data, and obtains the K fault data closest to the real-time monitoring data in the fault database through the K-nearest neighbor algorithm, and obtains the fault type with the most fault data among the K fault data, so as to obtain the fault identification type result of the real-time monitored medical device, and take corresponding measures through the classification result. However, since the K value in the K-nearest neighbor algorithm is artificially specified, the selection of the K value will have a significant impact on the result of the K-nearest neighbor algorithm. If the K value is too small, the classification result may be affected by a small amount of data, resulting in inaccurate classification. If the K value is too large, it may lead to too much data volume and ineffective differentiation, resulting in inaccurate classification of the fault problems of medical devices.

[0005] Therefore, how to obtain the optimal K value in the K-nearest neighbor algorithm to make the fault classification of medical devices more accurate has become an urgent problem to be solved. Summary of the Invention

[0006] In view of this, an embodiment of the present invention provides an intelligent management platform for digital medical device quality data to solve the problem of how to obtain the optimal K value in the K-nearest neighbor algorithm to make the fault classification of medical devices more accurate.

[0007] In an embodiment of the present invention, an intelligent management platform for digital medical device quality data is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the following method is implemented:

[0008] For any type of medical device, taking the multi-dimensional historical parameter data of each medical device at each sampling moment as a sample, a sample set is obtained;

[0009] Classify the samples in the sample set to obtain a faulty sample set and a non-faulty sample set. According to the similarity degree between the samples in the faulty sample set, the faulty sample set is divided into an unknown fault sample set and a known fault sample set;

[0010] Denote any sample in the unknown fault sample set as an unknown fault sample. According to the distance difference between the unknown fault sample and the samples in the known fault sample set, respectively obtain the rationality degree of each K value within the preset K value range when using the K-nearest neighbor algorithm to classify the unknown fault sample, obtain the rationality degree of each K value corresponding to each unknown fault sample, update the unknown fault sample set and the known fault sample set to obtain a new unknown fault sample set and a new known fault sample set;

[0011] According to the distance difference between each sample in the new unknown fault sample set and the samples in the new known fault sample set, respectively obtain the rationality degree of each K value corresponding to each sample. According to the rationality degree of each K value corresponding to each sample, respectively obtain the optimal K value of each sample;

[0012] According to the accuracy rate when classifying according to each optimal K value, obtain the optimal K value. According to the non-faulty sample set and the new known fault sample set, use the optimal K value as the value of K in the K-nearest neighbor algorithm to classify each sample of real-time monitoring.

[0013] The beneficial effects of the embodiment of the present invention compared with the prior art are:

[0014] For any type of medical device, the multi-dimensional historical parameter data of each medical device at each sampling moment is taken as a sample to obtain a sample set; the samples in the sample set are classified to obtain a faulty sample set and a fault-free sample set, and according to the similarity degree between the samples in the faulty sample set, the faulty sample set is divided into an unknown fault sample set and a known fault sample set; any sample in the unknown fault sample set is denoted as an unknown fault sample, and according to the distance difference between the unknown fault sample and the samples in the known fault sample set, the rationality degree of each K value within the preset K value range when classifying the unknown fault sample using the K-nearest neighbor algorithm is obtained respectively, the rationality degree of each K value corresponding to each unknown fault sample is obtained, the unknown fault sample set and the known fault sample set are updated to obtain a new unknown fault sample set and a new known fault sample set; according to the distance difference between each sample in the new unknown fault sample set and the samples in the new known fault sample set, the rationality degree of each K value corresponding to each sample is obtained respectively, and according to the rationality degree of each K value corresponding to each sample, the optimal K value of each sample is obtained respectively; according to the accuracy rate when classifying using each optimal K value, the optimal K value is obtained, and according to the fault-free sample set and the new known fault sample set, the optimal K value is used as the value of K in the K-nearest neighbor algorithm to classify each sample monitored in real time. Among them, according to the rationality degree of each K value corresponding to each sample, the unknown fault sample set and the faulty sample set are updated, so that the classification of the faulty samples in the new known fault sample set is more accurate; furthermore, the optimal K value of each sample is obtained, and according to the accuracy rate when classifying using each optimal K value, the optimal K value for fault classification of the samples most in line with this type of medical device is obtained, so that the result of classifying the samples monitored in real time using the optimal K value with the K-nearest neighbor algorithm is more accurate. Description of the Drawings

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 It is a flowchart of a method for intelligent management of digital medical device quality data provided in Embodiment 1 of the present invention;

[0017] Figure 2 It is a scatter diagram provided in Embodiment 1 of the present invention. Detailed Embodiments

[0018] Embodiments of the present disclosure will be described in detail below, and examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present disclosure, and should not be construed as a limitation of the present disclosure.

[0019] It should be noted that the terms "first", "second", etc. in the specification of the present disclosure and the above-mentioned accompanying drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments of the present disclosure described here can be implemented in an order other than those illustrated or described here. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure.

[0020] In order to illustrate the technical solution of the present invention, specific embodiments will be used for illustration below.

[0021] An embodiment of the present invention provides an intelligent management platform for digital medical device quality data, including a processor and a memory. The processor executes the computer program of the memory to implement an intelligent management method for digital medical device quality data, as Figure 1 shown. The method includes the following steps:

[0022] Step S101, for any type of medical device, taking the multi-dimensional historical parameter data of each medical device at each sampling moment as a sample, and obtaining a sample set.

[0023] The intelligent management platform for digital medical device quality data uses modern information technology to conduct all-round and intelligent management of the entire life cycle of medical devices from procurement, warehousing, use, maintenance to scrapping. In order to better identify the fault problems of medical devices, a fault database is usually constructed based on historical fault data, and the fault problem identification type results of the medical devices under real-time monitoring are obtained through the K-nearest neighbor algorithm. Therefore, it is necessary to collect the multi-dimensional historical parameter data of medical devices to obtain the fault database.

[0024] The intelligent management platform for the quality data of digital medical devices collects the multi-dimensional historical parameter data of each medical device at each sampling moment. The medical devices include, but are not limited to, ultrasonic physiotherapy apparatus, gravity infusion set, digital radiography X-ray machine, ultrasonic Doppler fetal monitor, high-frequency electrocautery therapeutic apparatus. The multi-dimensional parameters include, but are not limited to, transmission power, operating frequency, beam uniformity. The multi-dimensional historical parameter data of each medical device at each sampling moment is taken as a sample. Since the purpose of collecting samples is to obtain a fault database, in order to make the fault types included in the fault database more comprehensive, it is necessary to collect enough samples to cover more comprehensive fault types. Therefore, for any type of medical device, the collection frequency is set to once per minute, and the samples of each medical device within 30 days are collected to form a sample set. There is no restriction here and it can be set according to the specific implementation scenario.

[0025] Step S102: Classify the samples in the sample set to obtain a fault sample set and a non-fault sample set. According to the similarity degree between the samples in the fault sample set, the fault sample set is divided into an unknown fault sample set and a known fault sample set.

[0026] In order to better identify the fault problems of medical devices, a fault database is usually constructed based on historical fault data. The K nearest neighbor algorithm is used to obtain the K fault data closest to the real-time monitoring data in the fault database, and the fault type with the most fault data among the K fault data is obtained to get the fault identification type result of the real-time monitored medical device.

[0027] Therefore, it is necessary to classify the obtained sample set to obtain a fault database. Since the samples in the sample set are not classified, the sample set includes fault samples and non-fault samples, and the fault database is obtained by classifying the fault samples. Therefore, it is necessary to first classify the sample set to obtain a fault sample set and a non-fault sample set.

[0028] Since there are multiple parameter data in a sample, normally, each parameter data of a medical device should be within the normal parameter range, and within a certain period of time, the parameter data will not change significantly. Therefore, it is possible to judge whether the parameter data is fault parameter data according to the difference between the parameter data and its corresponding parameter range, and the fluctuation characteristics of the parameter data within a certain time range, and then obtain a fault sample set and a non-fault sample set.

[0029] Denote any sample in the sample set as the target sample, obtain samples in the sample set that belong to the same medical device as the target sample, and form a reference sample set. According to the difference between the parameter data in the target sample and its corresponding parameter range, as well as the fluctuation characteristics of the parameter data in the parameter sample set, determine whether each parameter data in the target sample is faulty parameter data, so as to determine whether the target sample is a faulty sample. The specific judgment method is as follows:

[0030] (1) According to the fluctuation characteristics of the parameter data within a certain time range, obtain the change difference value of each parameter data in the target sample.

[0031] Specifically, for any parameter data in the target sample, obtain the parameter data that belongs to the same parameter as the any parameter data in the reference sample set, and form a parameter data sequence with the any parameter data. In the parameter data sequence, with the any parameter data as the center, construct a target window of a preset size. Using the preset size as the sliding step, slide the target window to the left to obtain the first window, and slide the target window to the right to obtain the second window;

[0032] Respectively obtain the variance of the parameter data in the target window, the first window, and the second window, obtain the mean of the variance of the parameter data between the first window and the second window, obtain the absolute value of the difference between the variance of the parameter data in the target window and the mean, obtain the fluctuation degree of the any parameter data, obtain the sum result of the fluctuation degree and the constant 1, and obtain the change difference value of the any parameter data according to the difference between the constant 1 and the reciprocal of the sum result.

[0033] In an embodiment, taking the i-th parameter data in the target sample as an example, the formula for calculating the change difference value of the i-th parameter data is:

[0034]

[0035] Among them, θ is the change difference value of the i-th parameter data; S is the variance of the parameter data in the target window; S1 is the variance of the parameter data in the first window; S2 is the variance of the parameter data in the second window; || is the absolute value symbol; 1 is a constant.

[0036] It should be noted that the preset size of the target window is 3, which is not limited here and can be set according to the specific implementation scenario. represents the fluctuation degree of the i-th parameter data. The larger it is, the greater the fluctuation degree of the i-th parameter data within a certain time range, the more the i-th parameter data conforms to the fault parameter data, and the greater the change difference value of the i-th parameter data; in the parameter data sequence, if the i-th parameter data is the first parameter data, then the i-th parameter data and the next two consecutive parameter data are combined to form a target window, It becomes |S - S2)|; if the i-th parameter data is the last parameter data, then the i-th parameter data and the previous two consecutive parameter data are combined to form a target window, It becomes |S - S1)|; if there are less than 3 parameter data before or after the target window, then It becomes |S - S2)| or |S - S1)|.

[0037] (2) According to the change difference value of each parameter data in the target sample and the difference between the parameter data and its corresponding parameter range, determine whether the target sample is a non-fault sample.

[0038] Specifically, obtain the parameter range of the i-th parameter data, set the change difference threshold to 0.1, which is not limited here and can be set according to the specific implementation scenario. If the i-th parameter data is not within the parameter range, or the change difference value of the i-th parameter data is greater than or equal to 0.1, then confirm that the i-th parameter data is a fault parameter data.

[0039] Furthermore, traverse each parameter data in the target sample. Specifically, according to the judgment method of the i-th parameter data, detect the fault parameter data in the target sample data. If there is at least one fault parameter data in the target sample, then confirm that the target sample is a fault sample.

[0040] According to the judgment method of the fault sample, judge each sample in the sample set, obtain all the fault samples in the sample set to form a fault sample set, and form a non-fault sample set for the non-fault samples in the sample set.

[0041] After obtaining the fault sample set, it is necessary to classify the fault samples in the fault sample set to form a fault database with samples under different fault types, so as to facilitate the use of the K-nearest neighbor algorithm to classify the samples. Since the fault samples under the same fault type have a certain similarity, the fault samples in the fault sample set can be classified according to the similarity degree between the fault samples to obtain the fault database.

[0042] For any two fault samples in the fault sample, when the fault degrees of the two fault samples are the same, it means that the two fault samples may be of the same fault type. Therefore, the similarity degree between the fault samples can be obtained according to the difference in the fault degrees between the fault samples.

[0043] For any fault sample in the fault sample set, when the change outlier of the parameter data in the fault sample is large, or the parameter data deviates greatly from its corresponding parameter range, it indicates that the fault degree of this fault sample is relatively serious. Therefore, any parameter data in the any fault sample can be recorded as target parameter data, and the overall difference degree of the fault sample can be obtained according to the change difference value of the fault parameter data in the fault sample and the deviation degree of the fault parameter data from its corresponding parameter range, and then the similarity degree between the fault samples can be obtained according to the overall difference degree of the fault sample.

[0044] Among them, the method for obtaining the overall difference degree of the fault sample according to the change difference value of the fault parameter data in the fault sample and the deviation degree of the fault parameter data from its corresponding parameter range is as follows:

[0045] (1) Obtain the numerical difference value of the target parameter data according to the deviation degree of the target parameter data from its corresponding parameter range.

[0046] Specifically, obtain the parameter range of the target parameter data, obtain the maximum value and the minimum value within the parameter range of the target parameter data, and obtain the second difference value between the maximum value and the minimum value;

[0047] When the target parameter data is less than the minimum value, obtain the first difference value between the minimum value and the target parameter data, and obtain the numerical difference value of the target parameter data according to the ratio of the first difference value and the second difference value;

[0048] When the target parameter data is greater than the maximum value, obtain the third difference value between the target parameter data and the maximum value, and obtain the numerical difference value of the target parameter data according to the ratio of the third difference value and the second difference value;

[0049] When the target parameter data is within the parameter range of the target parameter data, set the numerical difference value of the target parameter to a preset value.

[0050] In an embodiment, the calculation formula for the numerical difference value of the target parameter data is:

[0051]

[0052] Among them, f is the numerical difference value of the target parameter data; x is the target parameter data; x min is the minimum value within the parameter range of the target parameter data; x max is the maximum value within the parameter range of the target parameter data; 0 is the preset value.

[0053] It should be noted that the greater the difference between the target parameter data and the maximum or minimum value within its parameter range, the more the target parameter data deviates from its parameter range, and the greater the numerical difference value of the target parameter data; when the target parameter data is within its parameter range, it indicates that the target parameter data does not deviate from its parameter range. Therefore, the numerical difference value of the target parameter data is set to 0.

[0054] (2) Obtain the abnormality degree of the target parameter data based on the average value between the numerical difference value and the change difference value of the target parameter data.

[0055] In one embodiment, according to the method for obtaining the change difference value of the i-th parameter data above, obtain the change difference value of the target parameter data, and in combination with the numerical difference value of the target parameter data, the formula for calculating the abnormality degree of the target parameter data is:

[0056]

[0057] where β is the abnormality degree of the target parameter data; f is the numerical difference value of the target parameter data; θ is the change difference value of the target parameter data.

[0058] It should be noted that the greater the numerical difference value of the target parameter data, the more the target parameter data deviates from its parameter range, the more likely the target parameter data is to be abnormal, and the greater the abnormality degree of the target parameter data; the greater the change difference value of the target parameter data, the greater the fluctuation degree of the target parameter data, the more likely the target parameter data is to be abnormal, and the greater the abnormality degree of the target parameter data.

[0059] (3) According to the method for obtaining the abnormality degree of the target parameter data above, respectively obtain the abnormality degree of each parameter data in any one of the fault samples, and then use the sum of the abnormality degrees of each parameter data in any one of the fault samples as the overall abnormality degree of any one of the fault samples.

[0060] Furthermore, if the overall abnormality degrees of two fault samples are the same, but the parameters corresponding to the fault parameter data in the two fault samples are different, it does not mean that the two fault samples are similar. When the parameters corresponding to the fault parameter data in the two fault samples are the same, it indicates that the two fault samples are similar. Therefore, the similarity degree between the fault samples can be obtained based on the similarity of the parameters corresponding to the fault parameter data between the fault samples and in combination with the overall difference degree between the fault samples.

[0061] Since there may be associations between the corresponding parameters in the fault parameter data of the same fault sample, that is, when one parameter fails, it may cause other parameters to fail as well. Therefore, the degree of parameter association in the fault sample can be obtained according to the degree of correlation between the parameters in the fault sample. When the parameters corresponding to the fault parameter data in two fault samples are the same, the degree of parameter association between the two fault samples is also the same. Therefore, the degree of parameter association between two fault samples can be used to reflect the similarity of the parameters corresponding to the fault parameter data between the two fault samples.

[0062] Among them, the method for obtaining the degree of parameter association in the fault sample according to the degree of correlation between the parameters in the fault sample is as follows:

[0063] (1) For any dimension parameter under any type of medical device, obtain, in the fault sample set, the fault samples whose parameter data corresponding to the any dimension parameter are fault parameter data as the fault sample mapping set of the any dimension parameter. According to the intersection between the fault sample mapping sets of all dimension parameters, obtain the association probability between each dimension parameter and other dimension parameters, and correspondingly obtain the association probability sequence corresponding to each dimension parameter.

[0064] Illustrative example: Denote any dimension parameter under any type of medical device as type I parameter. Obtain, in the fault sample set, the fault samples whose parameter data corresponding to the type I parameter are fault parameter data. All the fault samples whose parameter data corresponding to the type I parameter are fault parameter data form the fault sample mapping set of the type I parameter. Similarly, the fault sample mapping set of type II parameter can be obtained; Take the number of samples in the fault sample mapping set of the type I parameter as the denominator, obtain the intersection between the fault sample mapping sets of the type I parameter and the type II parameter, take the number of samples in the intersection between the fault sample mapping sets of the type I parameter and the type II parameter as the numerator, and take the ratio of the numerator to the denominator as the association probability between the type I parameter and the type II parameter. Similarly, the association probability between the type I parameter and each other type of parameter can be obtained. The association probabilities between the type I parameter and each other type of parameter form the association probability sequence of the type I parameter. Similarly, obtain the association probability sequence corresponding to each type of parameter.

[0065] (2) If there are at least two fault parameter data in any fault sample, denote the dimension parameters corresponding to the fault parameter data in the any fault sample as associated parameters. According to the association probability between the associated parameters in any fault sample, obtain the degree of parameter association of any fault sample.

[0066] Specifically, according to the number of associated parameters in the any fault sample, obtain the proportion of associated parameters in the any fault sample;

[0067] In the correlation probability sequence corresponding to each dimensional parameter of any one of the fault samples, obtain the correlation probability of any two associated parameters in any one of the fault samples, and correspondingly obtain a correlation probability accumulation value;

[0068] Obtain the parameter correlation degree of any one of the fault samples according to the product between the associated parameter ratio and the correlation probability accumulation value.

[0069] In one embodiment, taking the t-th fault sample in the fault sample set as an example, the correlation probabilities of every two associated parameters in the t-th fault sample form the correlation parameter probability sequence of the t-th fault sample. The calculation formula for the parameter correlation degree of the t-th fault sample is:

[0070]

[0071] where γ is the parameter correlation degree of the t-th fault sample; n is the number of associated parameters in the t-th fault sample; N is the number of all parameters in the t-th fault sample; P j is the j-th correlation probability in the correlation parameter probability sequence of the t-th fault sample; j is the serial number of the correlation probability in the correlation parameter probability sequence of the t-th fault sample; is the number of correlation probabilities in the correlation parameter probability sequence of the t-th fault sample.

[0072] It should be noted that is the associated parameter ratio in the t-th fault sample, The larger it is, the more the number of associated parameters in the t-th fault sample, and the greater the parameter correlation degree of the t-th fault sample; is the correlation probability accumulation value between the associated parameters in the t-th fault sample, The larger it is, the greater the correlation probability between the associated parameters in the t-th fault sample, and the greater the parameter correlation degree of the t-th fault sample.

[0073] (3) If there are less than two fault parameter data in the t-th fault sample, it means that the fault parameter data in the t-th fault sample will not affect other parameter data. Then, there are no associated parameters in the t-th fault sample, that is, the number of associated parameters in the t-th fault sample is 0, the associated parameter ratio in the t-th fault sample is 0, and the parameter correlation degree of the t-th fault sample is also 0.

[0074] Further, obtain the overall abnormality degree and parameter correlation degree of each fault sample in the fault sample set. Take the fault samples in the fault sample set except the any one fault sample as other fault samples. According to the differences in the overall abnormality degree and parameter correlation degree between the any one fault sample and each other fault sample, obtain the similarity degree between the any one fault sample and each other fault sample. Then, classify the fault samples in the fault sample set according to the similarity degree between the fault samples, and obtain a fault database according to the classification result.

[0075] Among them, the method for obtaining the similarity degree between the any one fault sample and each other fault sample according to the differences in the overall abnormality degree and parameter correlation degree between the any one fault sample and each other fault sample is as follows:

[0076] For any other fault sample, obtain the absolute value of the difference in the overall abnormality degree between the any one fault sample and the any other fault sample to obtain the overall abnormality degree difference. Obtain the reciprocal of the sum of the overall abnormality degree difference and the constant 1 to obtain the overall abnormality degree similarity value between the any one fault sample and the any other fault sample;

[0077] Obtain the absolute value of the difference in the parameter correlation degree between the any one fault sample and the any other fault sample to obtain the parameter correlation degree difference. Obtain the reciprocal of the sum of the parameter correlation degree difference and the constant 1 to obtain the parameter correlation degree similarity value between the any one fault sample and the any other fault sample;

[0078] According to the mean value between the overall abnormality degree similarity value and the parameter correlation degree similarity value between the any one fault sample and the any other fault sample, obtain the similarity degree between the fault sample and the any other fault sample.

[0079] In an embodiment, taking the t-th fault sample and the u-th fault sample in the fault sample set as an example, the formula for calculating the similarity degree between the t-th fault sample and the u-th fault sample is:

[0080]

[0081] Among them, σ tu is the similarity degree between the t-th fault sample and the u-th fault sample; β' t is the overall abnormality degree of the t-th fault sample; β' u is the overall abnormality degree of the u-th fault sample; γ t is the parameter correlation degree of the t-th fault sample; γ u is the parameter correlation degree of the u-th fault sample; || is the absolute value symbol; 1 is a constant.

[0082] It should be noted that is the overall abnormality similarity value between the t-th fault sample and the u-th fault sample The larger it is, the more similar the overall abnormality degree of the t-th fault sample and the u-th fault sample is, and the greater the similarity degree between the t-th fault sample and the u-th fault sample; is the parameter correlation similarity value between the t-th fault sample and the u-th fault sample The larger it is, the more similar the parameter correlation degree of the t-th fault sample and the u-th fault sample is, and the greater the similarity degree between the t-th fault sample and the u-th fault sample.

[0083] According to the above method for obtaining the similarity degree between the t-th fault sample and the u-th fault sample, obtain the similarity degree between every two fault samples in the fault sample set, classify the fault samples in the fault sample set. To ensure the correctness of the fault sample classification, a high similarity degree threshold needs to be set. According to the results calculated by experimental statistics, the similarity degree threshold is set to 0.9. There is no limitation here and it can be set according to the specific implementation scenario. Combine the other fault samples whose similarity degree is greater than or equal to 0.9 and any one of the fault samples to form the initial fault sample subset corresponding to any one of the fault samples, obtain the initial fault sample subset corresponding to each fault sample in the fault sample set, divide the two initial fault sample subsets with an intersection into one category, use the recursive algorithm to merge all categories, obtain at least one fault sample subset, one fault sample subset corresponds to one fault type, form the known fault sample set with all the fault sample subsets, and form the unknown fault sample set with the fault samples in the fault sample set that do not belong to the known fault sample set.

[0084] Example: Suppose the fault sample set is {A, B, C, D, E, F, G, H}, where A, B, C, D, E, F, G, H are fault samples. For fault sample A, if the similarity between A and B is greater than 0.9 and the similarity between A and C is greater than 0.9, then A, B, and C are grouped into the initial fault sample subset corresponding to A, i.e., {A, B, C}. Similarly, the initial fault sample subset corresponding to B is {A, B}, the initial fault sample subset corresponding to C is {A, C, F}, the initial fault sample subset corresponding to D is {D, F}, the initial fault sample subset corresponding to E is {D, E}, the initial fault sample subset corresponding to F is {F, C, G}, the initial fault sample subset corresponding to G is {F, G}, and H has no corresponding initial fault sample subset. Since both the initial fault sample subset {A, B} corresponding to B and the initial fault sample subset {A, C, F} corresponding to C contain A, {A, B} and {A, C, F} are classified into one category, and {A, B} and {A, C, F} are combined into the set {A, B, C, F}. Since both the set {A, B, C, F} and the initial fault sample subset {F, C, G} corresponding to F contain C and F, {A, B, C, F} and {F, C, G} are classified into one category, and {A, B, C, F} and {F, C, G} are combined into the set {A, B, C, F, G}. Two fault sample subsets {A, B, C, F, G} and {D, E} are obtained. The set {A, B, C, F, G} corresponds to fault type 1, and the set {D, E} corresponds to fault type 2. The fault sample subsets {A, B, C, F, G} and {D, E} form the known fault sample set, and G forms the unknown fault sample set.

[0085] Thus, the unknown fault sample set and the known fault sample set are obtained, and the known fault sample set is used as the fault database.

[0086] Step S103: Denote any sample in the unknown fault sample set as an unknown fault sample. According to the distance difference between the unknown fault sample and the samples in the known fault sample set, respectively obtain the rationality degree of each K value within the preset K value range when using the K-nearest neighbor algorithm to classify the unknown fault sample, obtain the rationality degree of each K value corresponding to each unknown fault sample, update the unknown fault sample set and the known fault sample set, and obtain a new unknown fault sample set and a new known fault sample set.

[0087] Since the fault database is obtained based on a high similarity degree, there may be some fault samples with a similarity degree not as high as the similarity degree threshold but belonging to the same type of fault that are not classified into the fault database. Therefore, it may be unreasonable to directly use the K-nearest neighbor algorithm according to the fault database for classification.

[0088] To solve the above problems, it is necessary to determine whether the fault database is reasonable. When the fault database is unreasonable, it needs to be modified so that the optimal classification result can be obtained when using the K-nearest neighbor algorithm for classification according to the fault database.

[0089] Since when the fault database is unreasonable, regardless of the value of K in the K-nearest neighbor algorithm, the final classification result will be unreasonable. Therefore, any sample in the set of unknown fault samples can be recorded as an unknown fault sample. The rationality of the classification result when using the K-nearest neighbor algorithm to classify the unknown fault sample reflects the rationality of each K value when using the K-nearest neighbor algorithm to classify the unknown fault sample. Furthermore, according to the rationality of each K value corresponding to each unknown fault sample, it is determined whether the fault database is reasonable. When the fault database is unreasonable, the fault database is modified.

[0090] Since the classification result of the K-nearest neighbor algorithm is affected by the selection of the K value. After the K value is selected, the classification result of the K-nearest neighbor algorithm is related to the number of fault samples of each fault type within the range corresponding to the K value and the distance from the fault samples of each fault type. Therefore, according to the distance difference between the unknown fault sample and the samples in the known fault sample set, the rationality of each K value within the preset K value range when using the K-nearest neighbor algorithm to classify the unknown fault sample can be obtained respectively.

[0091] Specifically, according to the overall abnormality degree and parameter correlation degree of all fault samples in the fault sample set, a scatter plot is constructed, as Figure 2 shown, where the abscissa of the scatter plot is the parameter correlation degree, and the ordinate is the overall abnormality degree. Figure 2 The points of different shapes in it are samples of different fault types. The samples in the known fault sample set are recorded as known fault samples. In the scatter plot, calculate the Euclidean distance between the unknown fault sample and each known fault sample, and sort all the Euclidean distances in ascending order to obtain a distance sequence. The Euclidean distance belongs to the prior art and will not be elaborated here.

[0092] For any K value within the preset K value range, obtain the Kth distance in the distance sequence. In the scatter plot, with the unknown fault sample as the center and the Kth distance as the radius, construct a first circular region.

[0093] According to the number of known fault samples in the first circular region, obtain the proportion of known fault samples in the first circular region; count the number of fault samples of each fault type in the first circular region, and form a target set with all the fault samples corresponding to the fault type with the largest number.

[0094] Obtain the number of faulty samples in the target set, calculate the fourth difference between the constant 1 and the reciprocal of the number of faulty samples in the target set, respectively obtain the Euclidean distances between the unknown faulty sample and each faulty sample in the target set, correspondingly obtain the distance mean value, and calculate the average value of the fourth difference and the reciprocal of the distance mean value to obtain the classification rationality coefficient of the unknown faulty sample within the first circular region;

[0095] Based on the average value between the proportion of known faulty samples in the first circular region and the classification rationality coefficient, obtain the rationality degree of any K value.

[0096] In an embodiment, since the K-nearest neighbor algorithm follows the principle of the minority obeying the majority in classification judgment, the K value in the K-nearest neighbor algorithm is generally an odd number. Count the number of faulty samples in each faulty sample subset, and set the range of the K value corresponding to the unknown faulty sample as (3, 5, 7, 9, …, Q), where Q is less than the number of faulty samples in the faulty sample subset with the largest number of faulty samples in the known faulty set. Taking the m-th K value corresponding to the unknown faulty sample as an example, the calculation formula for the rationality degree of the m-th K value is:

[0097]

[0098] where, μ m is the rationality degree of the m-th K value; d' is the number of known faulty samples in the first circular region; d is the number of all samples in the first circular region; max(d') is the number of faulty samples in the target set; V max(d')r is the Euclidean distance between the unknown faulty sample and the r-th faulty sample in the target set; r is the serial number of the faulty sample in the target set; 1 is a constant.

[0099] It should be noted that is the proportion of known faulty samples in the first circular region, the smaller it is, the fewer known faulty samples there are in the first circular region, there are more unknown faulty samples in the first circular region, the more unreasonable the classification of the unknown faulty sample within the first circular region is, and the smaller the rationality degree of the m-th K value corresponding to the unknown faulty sample is; represents the classification rationality coefficient of the unknown faulty sample, the smaller it is, the farther the distance between the known faulty samples and the unknown faulty sample in the target set within the first circular region is, the more unreasonable the classification of the unknown faulty sample within the first circular region is, and the smaller the rationality degree of the m-th K value corresponding to the unknown faulty sample is.

[0100] According to the method for obtaining the rationality degree of the m-th K value corresponding to the unknown fault sample, obtain the rationality degree of each K value corresponding to the unknown fault sample. Set the rationality degree threshold to 0.4 according to the results calculated by experimental statistics. There is no limit here and it can be set according to the specific implementation scenario. When there are at least 3 K values in the unknown fault sample whose rationality degrees are less than or equal to 0.4, it indicates that it is unreasonable to classify the unknown fault sample using the K-nearest neighbor algorithm based on the fault database. Among them, 3 is the first preset quantity, which is obtained by experimental statistics and is not limited here and can be set according to the specific implementation scenario. Further, obtain the rationality degree of each K value corresponding to each unknown fault sample in the unknown fault sample set.

[0101] When there is no unknown fault sample in the unknown fault sample set whose rationality degree of at least 3 K values is less than or equal to 0.4, it indicates that it is reasonable to classify the unknown fault sample using the K-nearest neighbor algorithm based on the fault database, that is, the fault database is reasonable. Therefore, there is no need to modify the fault database. Take the unknown fault sample set as the new unknown fault sample set and the known fault sample set as the new known fault sample set.

[0102] When there is an unreasonable classification of an unknown fault sample in the unknown fault sample set, it indicates that the fault database is unreasonable. At this time, the fault database needs to be modified.

[0103] Since there are some fault samples with a similarity that is not as high as the similarity degree threshold but belong to the same type of fault that are not classified into the fault database, resulting in an unreasonable classification of the unknown fault sample using the K-nearest neighbor algorithm based on the fault database. Therefore, in the unknown fault sample set, according to the rationality degree of each K value corresponding to each unknown fault sample, obtain the fault samples belonging to the same fault type in the unknown fault sample set, and update the unknown fault sample set and the known fault sample set to obtain a new unknown fault sample set and a new known fault sample set. The specific method for updating the unknown fault sample set and the known fault sample set is as follows:

[0104] For any unknown fault sample in the unknown fault sample set, when the classification of the any unknown fault sample is unreasonable, record the any unknown fault sample as the target unknown fault sample, and obtain all the target unknown fault samples in the unknown fault sample set;

[0105] For any target unknown fault sample in the unknown fault sample set, obtain the minimum distance in the distance sequence. In the scatter plot, with the any target unknown fault sample as the center and the minimum distance as the radius, construct a second circular region;

[0106] For any three unknown fault samples in the second circular region, if the difference in the similarity degree between one of the three unknown fault samples and the other two unknown fault samples is less than or equal to a preset similarity degree difference threshold, then the three unknown fault samples are combined into a new initial fault sample subset. All new initial fault sample subsets in the second circular region are obtained. Two new initial fault sample subsets with an intersection are classified into one category, and all categories are merged using a recursive algorithm to obtain at least one new fault sample subset, and one new fault sample subset corresponds to one fault type.

[0107] Illustrate with an example: Taking the w-th target unknown fault sample as an example, a second circular region is constructed. The unknown fault samples in the second circular region form a set {I, J, K, L, M, N, O, P}, where I, J, K, L, M, N, O, P are unknown fault samples. For the three unknown fault samples I, J, and K, if the difference between the similarity degree of I and J and the similarity degree of I and K is less than or equal to 0.2, then the three unknown fault samples I, J, and K are combined into a new initial fault sample subset {I, J, K}. Similarly, new initial fault sample subsets {J, K, L} and {L, M, N} are obtained. {I, J, K} and {J, K, L} with an intersection are merged to obtain {I, J, K, L}. All categories are merged using a recursive algorithm to obtain a new fault sample subset {I, J, K, L, M, N}. The new fault sample subset {I, J, K, L, M, N} corresponds to a new fault type. Here, 0.2 is the similarity degree difference threshold, which is obtained through experimental statistics and is not limited here and can be set according to specific implementation scenarios.

[0108] Further, all new fault sample subsets are combined into the new known fault sample subset corresponding to any target unknown fault sample. The new known fault sample subsets corresponding to each target unknown fault sample are obtained. All new known fault sample subsets are added to the known fault sample set to obtain an initial known fault sample set. The fault samples in the unknown fault sample set that are the same as all new known fault sample subsets are removed to obtain an initial unknown fault sample set.

[0109] When there is no target unknown fault sample in the initial unknown fault sample set, the initial known fault sample set is used as the new known fault sample set, and the initial unknown fault sample set is used as the new unknown fault sample set.

[0110] When there is a target unknown fault sample in the initial set of unknown fault samples, any target unknown fault sample in the initial fault sample set is denoted as a new target unknown fault sample, the third circular region corresponding to the new target unknown fault sample is obtained, and according to the method for obtaining a new set of known fault samples, a new set of known fault samples corresponding to the new target unknown fault sample is obtained in the third circular region. The new sets of known fault samples corresponding to each new target unknown fault sample in the initial fault sample set are obtained, all the new sets of known fault samples are added to the initial set of known fault samples to obtain a new initial set of known fault samples, and the fault samples in the initial set of unknown fault samples that are the same as all the new sets of known fault samples are removed to obtain a new initial set of unknown fault samples. The method for obtaining the new set of known fault samples is repeated until there is no target unknown fault sample in the initial set of unknown fault samples, and a new set of unknown fault samples and a new set of known fault samples are obtained.

[0111] So far, a new set of unknown fault samples and a new set of known fault samples are obtained, and the new set of known fault samples is used as a new fault database.

[0112] Step S104: According to the distance difference between each sample in the new set of unknown fault samples and the samples in the new set of known fault samples, the rationality degree of each K value corresponding to each sample is obtained respectively, and according to the rationality degree of each K value corresponding to each sample, the optimal K value of each sample is obtained respectively.

[0113] Since the K value in the K-nearest neighbor algorithm is artificially specified, the selection of the K value will have a significant impact on the result of the K-nearest neighbor algorithm. If the K value is too small, the classification result may be affected by a small amount of data, resulting in inaccurate classification. If the K value is too large, it may lead to an excessive amount of data and ineffective differentiation, resulting in inaccurate classification of the fault problems of medical devices. Therefore, an optimal K value needs to be obtained for classifying real-time samples.

[0114] Because each K value has its rationality degree, and the rationality degree can reflect whether the current K value conforms to the optimal result for classification. Therefore, for any sample in the new set of unknown fault samples, according to the rationality degree of each K value corresponding to the sample, the K value with the maximum rationality degree is used as the optimal K value of the sample, and then the optimal K value is obtained according to the optimal K value of each sample.

[0115] So far, the optimal K value of each sample in the new set of unknown fault samples is obtained.

[0116] Step S105: Obtain the optimal K value according to the accuracy rate when classifying based on each optimal K value. Based on the fault-free sample set and the newly known fault sample set, use the optimal K value as the value of K in the K-nearest neighbor algorithm to classify each real-time monitored sample.

[0117] Since each sample in the newly unknown fault sample set has its corresponding optimal K value, it is necessary to select an optimal K value from all the optimal K values as the optimal K value corresponding to this type of medical device to classify the subsequent real-time samples of this type of medical device.

[0118] Since the fault samples in the newly known fault sample set have their corresponding fault types, each optimal K value can be used to classify the fault samples of different fault types in the newly known fault sample set to obtain the accuracy rate of its classification. According to the accuracy rate corresponding to each optimal K value, obtain the optimal K value for classifying real-time samples.

[0119] Since there may be a large number of fault samples of a certain fault type, which affects the accuracy rate of classifying each optimal K value, 10 fault samples are selected from the fault samples corresponding to each fault type to form a comparison fault sample set. 10 is the second preset quantity, which is obtained through experimental statistics and is not limited here. It can be set according to the specific implementation scenario. Record the fault type of each fault sample in the comparison fault sample set as the initial fault type, and form an optimal K value set with the optimal K value of each sample in the newly unknown fault sample set.

[0120] Further, for any optimal K value in the optimal K value set, record any optimal K value as the target K value. When the classification result of any fault sample in the comparison fault sample set using the target K value is the same as its initial fault type, confirm that the classification result of any sample in the comparison fault sample set using the target K value is accurate. In the comparison fault sample set, obtain the number of samples with accurate classification results when using the target K value, denoted as the correct sample number, and calculate the ratio of the correct sample number to all the fault sample numbers in the comparison fault sample set to obtain the accuracy rate when using the target K value to classify each fault sample in the comparison fault sample set.

[0121] According to the accuracy rate when using the target K value to classify each fault sample in the comparison fault sample set, respectively obtain the accuracy rate corresponding to each optimal K value in the optimal K value set, and take the optimal K value corresponding to the maximum accuracy rate as the optimal K value.

[0122] After obtaining the optimal K value, the real-time samples of medical devices of the same type corresponding to the optimal K value can be classified. Since the real-time samples may not have faults, the fault-free sample set and the newly known fault sample set are jointly used to form a reference database. According to the reference database, the optimal K value is used as the K value in the K-nearest neighbor algorithm to classify the real-time samples of medical devices of the same type, and accurate classification results can be obtained. When the classification result of the real-time sample is a fault, corresponding measures such as repair or replacement are taken according to the corresponding fault type.

[0123] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A digital medical device quality data intelligent management platform, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the following method is implemented: For any type of medical device, the multi-dimensional historical parameter data of each medical device at each sampling time is taken as a sample to obtain a sample set; Classifying the samples in the sample set to obtain a fault sample set and a non-fault sample set, and dividing the fault sample set into an unknown fault sample set and a known fault sample set according to the similarity between the samples in the fault sample set; Any sample in the unknown fault sample set is recorded as an unknown fault sample, and according to the distance difference between the unknown fault sample and the samples in the known fault sample set, the rationality of each K value within the preset K value range when the unknown fault sample is classified by using the K nearest neighbor algorithm is obtained, and the rationality of each K value corresponding to each unknown fault sample is obtained, and the unknown fault sample set and the known fault sample set are updated to obtain a new unknown fault sample set and a new known fault sample set; According to the distance difference between each sample in the new unknown fault sample set and the samples in the new known fault sample set, respectively obtain the rationality of each K value corresponding to each sample, and according to the rationality of each K value corresponding to each sample, respectively obtain the optimal K value of each sample; The optimal K value is obtained according to the accuracy of classification for each optimal K value, and each sample monitored in real time is classified using the optimal K value as the value of K in the K nearest neighbor algorithm according to the fault-free sample set and the new known fault sample set.

2. A digital medical device quality data intelligent management platform according to claim 1, characterized in that: The classifying the samples in the sample set to obtain a fault sample set and a non-fault sample set includes: Record any sample in the sample set as a target sample, and obtain samples from the sample set that belong to the same medical device as the target sample to form a reference sample set; For any parameter data in the target sample, parameter data belonging to the same parameter as the any parameter data is obtained in the reference sample set, and the parameter data sequence is formed with the any parameter data; in the parameter data sequence, a target window of a preset size is constructed with the any parameter data as the center, and the preset size is used as the sliding step, and the target window is slid to the left to obtain a first window, and the target window is slid to the right to obtain a second window; respectively obtaining the variances of the parameter data in the target window, the first window and the second window, obtaining the mean of the variances of the parameter data between the first window and the second window, obtaining the absolute value of the difference between the variance of the parameter data in the target window and the mean, obtaining the degree of fluctuation of any parameter data, obtaining the sum of the degree of fluctuation and a constant 1, and obtaining the change difference value of any parameter data according to the difference between constant 1 and the reciprocal of the summed result; Obtaining a parameter range of any parameter data, if any parameter data is not within the parameter range, or a change difference value of any parameter data is greater than or equal to a preset change difference threshold, confirming that any parameter data is faulty parameter data, traversing each parameter data in the target sample, and if there is at least one faulty parameter data in the target sample, confirming that the target sample is a faulty sample; All faulty samples in the sample set are acquired to form a faulty sample set, and non-faulty samples in the sample set are acquired to form a non-faulty sample set.

3. A digital medical device quality data intelligent management platform according to claim 2, characterized in that: The step of dividing the fault sample set into an unknown fault sample set and a known fault sample set according to the similarity between samples in the fault sample set comprises: For any fault sample in the fault sample set, according to the difference and fluctuation characteristics between the parameter data of any fault sample, the overall abnormality degree of any fault sample is obtained, and according to the correlation degree between the parameter data of any fault sample, the parameter correlation degree of any fault sample is obtained; Obtaining the overall abnormality degree and parameter correlation degree of each fault sample in the fault sample set, taking the fault samples in the fault sample set other than the any fault sample as other fault samples, and obtaining the similarity between the any fault sample and each other fault sample according to the overall abnormality degree difference and parameter correlation degree difference between the any fault sample and each other fault sample; The other fault samples corresponding to the similarity greater than or equal to the preset similarity threshold and the any fault sample form an initial fault sample subset corresponding to the any fault sample, obtain an initial fault sample subset corresponding to each fault sample in the fault sample set, divide two initial fault sample subsets with intersection into one category, merge all categories using a recursive algorithm to obtain at least one fault sample subset, and one fault sample subset corresponds to one fault type; All fault sample subsets are grouped into a known fault sample set, and the fault samples in the fault sample set that do not belong to the known fault sample set are grouped into an unknown fault sample set.

4. A digital medical device quality data intelligent management platform according to claim 3, characterized in that: The obtaining the overall abnormality degree of any fault sample according to the differences and fluctuation characteristics between the parameter data of any fault sample includes: Record any parameter data in any fault sample as target parameter data, obtain a parameter range of the target parameter data, obtain a maximum value and a minimum value within the parameter range of the target parameter data, and obtain a second difference between the maximum value and the minimum value; When the target parameter data is less than the minimum value, obtaining a first difference between the minimum value and the target parameter data, and obtaining a numerical difference value of the target parameter data according to a ratio of the first difference to the second difference; When the target parameter data is greater than the maximum value, obtaining a third difference between the target parameter data and the maximum value, and obtaining a numerical difference value of the target parameter according to a ratio of the third difference to the second difference; When the target parameter data is within the parameter range of the target parameter data, setting the numerical difference value of the target parameter to a preset value; The abnormality degree of the target parameter data is obtained according to the average value between the numerical difference value and the change difference value of the target parameter data, and the overall abnormality degree of any fault sample is obtained according to the sum of the abnormality degrees of each parameter data in any fault sample.

5. A digital medical device quality data intelligent management platform according to claim 3, characterized in that: The obtaining the parameter correlation degree of any fault sample according to the correlation degree between each parameter data of any fault sample includes: For any dimensional parameter under any type of medical device, obtain a fault sample whose parameter data corresponding to any dimensional parameter is fault parameter data in the fault sample set as a fault sample mapping set of any dimensional parameter, and obtain the association probability of each dimensional parameter with other dimensional parameters according to the intersection between the fault sample mapping sets of all dimensional parameters, and obtain the association probability sequence corresponding to each dimensional parameter; If there are at least two fault parameter data in any of the fault samples, the dimension parameters corresponding to the fault parameter data in any of the fault samples are recorded as associated parameters, and according to the number of associated parameters in any of the fault samples, the proportion of associated parameters in any of the fault samples is obtained; If there are less than two fault parameter data in any of the fault samples, the proportion of the associated parameters in any of the fault samples is 0; In the association probability sequence corresponding to each dimensional parameter of any fault sample, the association probability of any two association parameters in any fault sample is obtained, and the corresponding association probability cumulative value is obtained; The parameter correlation degree of any fault sample is obtained according to the product of the correlation parameter proportion and the correlation probability cumulative value.

6. A digital medical device quality data intelligent management platform according to claim 3, characterized in that: The obtaining the similarity between any fault sample and each other fault sample according to the overall abnormality difference and parameter correlation difference between any fault sample and each other fault sample respectively includes: For any other fault sample, obtain the absolute value of the difference between the overall abnormality degree of any fault sample and any other fault sample to obtain the overall abnormality degree difference, obtain the reciprocal of the sum of the overall abnormality degree difference and a constant 1, and obtain the overall abnormality degree similarity value between any fault sample and any other fault sample; Obtaining the absolute value of the difference between the parameter correlation degree of any one of the fault samples and any other fault samples to obtain the parameter correlation degree difference, obtaining the inverse of the sum of the parameter correlation degree difference and a constant 1 to obtain the parameter correlation degree similarity value between any one of the fault samples and any other fault samples; The similarity between the fault sample and any other fault sample is obtained according to the average of the overall abnormality similarity value and the parameter association similarity value between the fault sample and any other fault sample.

7. A digital medical device quality data intelligent management platform according to claim 3, characterized in that: The obtaining, according to the distance difference between the unknown fault sample and the samples in the known fault sample set, respectively the rationality of each K value within a preset K value range when classifying the unknown fault sample using the K nearest neighbor algorithm, comprises: According to the overall abnormality degree and parameter correlation degree of all fault samples in the fault sample set, a scatter plot is constructed, wherein the horizontal axis of the scatter plot is the parameter correlation degree, and the vertical axis is the overall abnormality degree. In the scatter plot, the Euclidean distance between the unknown fault sample and each known fault sample is calculated, and all Euclidean distances are sorted in ascending order to obtain a distance sequence, and the known fault sample refers to a sample in the known fault sample set; For any K value within the preset K value range, obtain the Kth distance in the distance sequence, and in the scatter plot, construct a first circular area with the unknown fault sample as the center and the Kth distance as the radius; According to the number of known fault samples in the first circular area, the proportion of known fault samples in the first circular area is obtained; the number of fault samples under each fault type is counted in the first circular area, and all fault samples under the fault type corresponding to the largest number are combined into a target set; Obtain the number of fault samples in the target set, calculate the fourth difference between the constant 1 and the reciprocal of the number of fault samples in the target set, respectively obtain the Euclidean distance between the unknown fault sample and each fault sample in the target set, obtain the corresponding distance mean, calculate the average of the fourth difference and the reciprocal of the distance mean, and obtain the classification rationality coefficient of the unknown fault sample in the first circular area; The rationality of any K value is obtained based on the average value between the proportion of known fault samples in the first circular area and the classification rationality coefficient.

8. A digital medical device quality data intelligent management platform according to claim 7, characterized in that: The updating of the unknown fault sample set and the known fault sample set to obtain a new unknown fault sample set and a new known fault sample set includes: For any unknown fault sample in the unknown fault sample set, when there are at least a first preset number of K values ​​in any unknown fault sample whose reasonableness is less than or equal to a preset reasonableness threshold, any unknown fault sample is recorded as a target unknown fault sample, and all target unknown fault samples in the unknown fault sample set are obtained; For any target unknown fault sample in the unknown fault sample set, obtain the minimum distance in the distance sequence, and construct a second circular area in the scatter plot with the any target unknown fault sample as the center and the minimum distance as the radius; For any three unknown fault samples in the second circular area, if the difference in similarity between one of the unknown fault samples and the other two unknown fault samples among the any three unknown fault samples is less than or equal to a preset similarity difference threshold, the any three unknown fault samples are formed into a new initial fault sample subset, all new initial fault sample subsets in the second circular area are obtained, two new initial fault sample subsets with intersection are divided into one category, and all categories are merged by using a recursive algorithm to obtain at least one new fault sample subset, and one new fault sample subset corresponds to one fault type; All new fault sample subsets are combined into a new known fault sample subset corresponding to any target unknown fault sample, a new known fault sample subset corresponding to each target unknown fault sample is obtained, all new known fault sample subsets are added to the known fault sample set to obtain an initial known fault sample set, and fault samples in the unknown fault sample set that are the same as all new known fault sample subsets are removed to obtain an initial unknown fault sample set; When there is no target unknown fault sample in the initial unknown fault sample set, taking the initial known fault sample set as a new known fault sample set, and taking the initial unknown fault sample set as a new unknown fault sample set; When the target unknown fault sample exists in the initial unknown fault sample set, repeat the method for obtaining the new known fault sample subset until the target unknown fault sample does not exist in the initial unknown fault sample set, thereby obtaining a new unknown fault sample set and a new known fault sample set; If the target unknown fault sample does not exist in the unknown fault sample set, the unknown fault sample set is used as a new unknown fault sample set, and the known fault sample set is used as a new known fault sample set.

9. A digital medical device quality data intelligent management platform according to claim 1, characterized in that: The obtaining of the optimal K value for each sample according to the rationality of each K value corresponding to each sample includes: For any sample in the new unknown fault sample set, according to the rationality of each K value corresponding to the any sample, the K value with the greatest rationality is taken as the optimal K value of the any sample.

10. A digital medical device quality data intelligent management platform according to claim 8, characterized in that: The step of obtaining the optimal K value according to the accuracy of classification performed on each optimal K value includes: Selecting a second preset number of fault samples from the fault samples corresponding to each fault type to form a comparison fault sample set, and forming an optimal K value set from the best K value of each sample in the new unknown fault sample set; For any optimal K value in the optimal K value set, obtaining an accuracy rate when using the any optimal K value to classify each fault sample in the comparison fault sample set; The accuracy corresponding to each best K value in the best K value set is obtained, and the best K value corresponding to the maximum accuracy is used as the best K value.

Images