Multifunctional integrated intelligent detection method and system for drug-related samples

Abstract

The invention relates to the technical field of sample detection, in particular to a multifunctional integrated intelligent detection method and system for a drug-related sample, and the method comprises the steps: receiving a sample detection instruction, starting a sample detection unit, carrying out identity recognition, obtaining recognition information, obtaining a to-be-detected drug-related sample, and respectively carrying out centrifugation, surface tension detection and conductivity scanning on the to-be-detected drug-related sample. Extracting a detection sample by using a mechanical arm, obtaining a detection card, obtaining a fixed detection card by using the mechanical arm, detecting the detection sample, obtaining a detection chromatic value set, and calculating a chromatic difference value set; and performing judgment based on the chrominance difference value set and a preset chrominance threshold value to obtain a judgment result, and combining the judgment result with the sample feature identification code to obtain identification judgment data. According to the invention, the detection efficiency of the drug-related sample can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of sample detection, and in particular to a multifunctional integrated intelligent detection method and system for drug-related samples. Background Art

[0002] With the continuous advancement of information technology and automated testing, intelligent detection of drug samples has become increasingly important. By using a variety of testing methods, such as centrifugation, surface tension testing, and conductivity scanning, we can comprehensively capture the physical and chemical properties of drug samples. This solution integrates these test data to generate a unique sample signature code, enabling intelligent identification of drug samples.

[0003] Traditional drug-related sample detection methods often rely on single detection indicators and manual judgment, resulting in low detection efficiency and data processing redundancy. Traditional drug-related sample detection methods struggle to fully capture the complex characteristics of samples during data collection, resulting in insufficient ability to identify subtle differences, which affects the accuracy and real-time nature of test results. Furthermore, repeated testing of the same drug-related sample is required, resulting in low detection efficiency. Therefore, improving the efficiency of drug-related sample detection is a critical issue that needs to be addressed. Summary of the Invention

[0004] The present invention provides a multifunctional integrated intelligent detection method and system for drug-related samples, the main purpose of which is to improve the efficiency of drug-related sample detection.

[0005] To achieve the above objectives, the present invention provides a multifunctional integrated intelligent detection method for drug-related samples, comprising:

[0006] receiving a sample detection instruction and starting a sample detection unit based on the sample detection instruction, wherein the sample detection unit includes: a centrifugal detection unit, a tension detection unit, an identity recognition unit, and a conductivity detection unit;

[0007] Performing identity recognition using the identity recognition unit to obtain identification information, wherein the identification information includes: whether the authentication is passed or not;

[0008] When the identification information fails the authentication, the process returns to the above step of performing identity identification using the identity identification unit;

[0009] When the identification information is authenticated, a drug-related sample to be tested is obtained, and a comprehensive test is performed on the drug-related sample to be tested based on the centrifugal detection unit, the tension detection unit, and the conductivity detection unit to obtain the centrifugal sample, characteristic density, characteristic tension, and characteristic conductivity;

[0010] generating a sample characteristic identification code based on the characteristic density, characteristic tension, and characteristic conductivity;

[0011] Using a pre-built robotic arm to extract a test sample from a centrifuged sample to obtain a test card, and using the robotic arm to fix the test card to a pre-built card positioning area to obtain a fixed test card;

[0012] Dropping the test sample into the fixed test card, and testing the test sample based on a preset duration and the test card to obtain a set of test colorimetric values;

[0013] Extracting detection chromaticity values from the detection chromaticity value set in sequence, calculating chromaticity differences using the extracted detection chromaticity values and a preset standard chromaticity, and collecting the chromaticity differences to obtain a chromaticity difference value set;

[0014] The judgment is made based on the chromaticity difference set and the preset chromaticity threshold to obtain the judgment result, which is combined with the sample feature identification code to obtain the identification judgment data, and the intelligent detection of drug-related samples is completed based on the identification judgment data.

[0015] Optionally, the comprehensive detection of the drug-related sample to be tested based on the centrifugal detection unit, the tension detection unit and the conductivity detection unit to obtain the centrifuged sample, characteristic density, characteristic tension and characteristic conductivity includes:

[0016] Setting the centrifugal speed and centrifugal time, and using the centrifugal detection unit, the centrifugal speed and the centrifugal time to perform a centrifugal operation on the drug-related sample to be tested to obtain a centrifuged sample;

[0017] Using a pre-built density sensor and a preset stratification interval to detect the density of the centrifuged sample, a detection density set is obtained;

[0018] The drug-related sample to be tested is tested using a preset detection interval, a preset detection duration, a tension detection unit, a conductivity detection unit, and a preset frequency range to obtain a tension detection moment, a detection tension, a detection frequency, and a detection conductivity. The tension detection moment, the detection tension, the detection frequency, and the detection conductivity are respectively collected to obtain a tension detection moment set, a detection tension set, a detection frequency set, and a detection conductivity set, wherein the tension detection moment and the detection tension correspond one-to-one, the detection frequency and the detection conductivity correspond one-to-one, and the testing of the drug-related sample to be tested and the centrifugation operation of the drug-related sample to be tested are performed simultaneously;

[0019] Based on the detection density set, layer interval, tension detection time set, detection tension set, detection frequency set and detection conductivity set, feature calculation is performed to obtain feature density, feature tension and feature conductivity.

[0020] Optionally, performing feature calculation based on the detection density set, layer interval, tension detection time set, detection tension set, detection frequency set, and detection conductivity set to obtain feature density, feature tension, and feature conductivity includes:

[0021] Calculating the layer height according to the layer interval, and constructing a centrifugal curve using the detection density set and the layer height, wherein the horizontal axis of the centrifugal curve is the layer height and the vertical axis of the centrifugal curve is the detection density;

[0022] Constructing a tension dynamic curve based on the tension detection time set and the detection tension set, wherein the horizontal axis of the tension dynamic curve is the detection time, and the vertical axis of the tension dynamic curve is the detection tension;

[0023] Constructing a conductivity image using the detection frequency set and the detection conductivity set, wherein the horizontal axis of the conductivity image is the detection frequency and the vertical axis of the conductivity image is the detection conductivity;

[0024] Characteristic calculation is performed based on the centrifugal curve, tension dynamic curve and conductivity image to obtain characteristic density, characteristic tension and characteristic conductivity.

[0025] Optionally, performing feature calculation based on the centrifugal curve, the tension dynamic curve, and the conductivity image to obtain the feature density, the feature tension, and the feature conductivity includes:

[0026] Extracting a density peak from the centrifugation curve, and calculating a density mean and a density standard deviation based on the centrifugation curve;

[0027] The standard skewness value is calculated using the density standard deviation, density mean and detection density:

[0028]

[0029] Among them, q refers to the standard skewness value, α refers to the preset density parameter, M refers to the total density, ρ α Refers to the detection density when the density parameter is α, γ refers to the density mean, and β refers to the density standard deviation;

[0030] The characteristic density is formed based on the standard skewness value, density peak value and density mean, wherein the characteristic density is as follows:

[0031] Q=[q,q²,γ]

[0032] Where Q refers to the characteristic density and q2 refers to the density peak;

[0033] Extract the maximum tension, minimum tension, maximum time, and minimum time from the tension dynamic curve, and calculate the tension change rate based on the maximum tension, minimum tension, maximum time, and minimum time:

[0034]

[0035] Where W refers to the rate of change of tension, y1 refers to the maximum tension, y2 refers to the minimum tension, t1 refers to the maximum time, and t2 refers to the minimum time;

[0036] Set a sliding window and calculate the characteristic tension based on the sliding window and the tension change rate;

[0037] Extracting the highest conductance frequency and the lowest conductance frequency from the conductance image, and calculating the conductance change according to the highest conductance frequency and the lowest conductance frequency;

[0038] The frequency rate is calculated based on the highest conductance frequency, the lowest conductance frequency and the conductance change:

[0039]

[0040] Where S refers to the frequency rate, o3 refers to the change in conductance, ln refers to the natural logarithm, o1 refers to the highest conductance frequency, and o2 refers to the lowest conductance frequency;

[0041] The characteristic conductivity is formed according to the highest conductivity frequency, the lowest conductivity frequency and the frequency rate, wherein the characteristic conductivity is as follows:

[0042] Q2=[o1,o2,S]

[0043] Here, Q2 refers to the characteristic conductivity.

[0044] Optionally, calculating the characteristic tension based on the sliding window and the tension change rate includes:

[0045] Using a sliding window to divide the detection tension in the detection tension set, a plurality of window tension sets are obtained;

[0046] Calculating standard deviations of the window tensions in the plurality of window tension sets to obtain a plurality of tension standard deviations, wherein one tension standard deviation corresponds to one window tension set;

[0047] Comparing a plurality of tension standard deviations with a preset tension threshold in sequence;

[0048] If the multiple tension standard deviations are all greater than the tension threshold, the tension threshold is increased to obtain an extended threshold, the tension threshold is updated using the extended threshold, and based on the updated tension threshold, the process returns to the above step of sequentially comparing the multiple tension standard deviations with the preset tension threshold.

[0049] If there is a tension standard deviation less than or equal to the tension threshold among multiple tension standard deviations, then the tension standard deviations less than or equal to the tension threshold are collected to obtain a screening standard deviation set;

[0050] Matching a window tension set based on a screening standard deviation in the screening standard deviation set, and performing mean calculation on the matched window tension set to obtain a stable tension;

[0051] The tension fluctuation amplitude is calculated based on the stable tension, tension detection time and detection tension:

[0052]

[0053] Among them, D refers to the tension fluctuation amplitude, t refers to the preset time parameter, μ refers to the total number of moments, and y t Refers to the detection tension when the moment parameter is t, and y3 refers to the stable tension;

[0054] The tension fluctuation amplitude, stable tension and tension change rate are used to form characteristic tension, where the characteristic tension is as follows:

[0055] Q3=[D,y3,W]

[0056] Among them, Q3 refers to characteristic tension.

[0057] Optionally, generating a sample characteristic identification code based on the characteristic density, characteristic tension, and characteristic conductivity includes:

[0058] The characteristic density, characteristic tension and characteristic conductivity are spliced together to obtain a comprehensive characteristic vector, wherein the comprehensive characteristic vector is as follows:

[0059] Q4=[q,q2,γ,o1,o2,S,D,y3,W] T

[0060] Among them, Q4 refers to the comprehensive eigenvector, and T refers to the matrix transpose symbol;

[0061] Normalizing all components in the comprehensive feature vector to obtain a normalized comprehensive vector;

[0062] The covariance matrix is constructed based on the normalized integrated vector, where the covariance matrix is as follows:

[0063]

[0064] Among them, F refers to the covariance matrix, F1 refers to the normalized integrated vector, Point to the multiplication symbol;

[0065] Performing eigenvalue decomposition on the covariance matrix to obtain a decomposition eigenvalue group and a decomposition eigenvector group, wherein the decomposition eigenvalues correspond to the decomposition eigenvectors in one-to-one correspondence;

[0066] Extracting a first eigenvalue, a second eigenvalue, and a third eigenvalue from the decomposed eigenvalue group, and matching corresponding first eigenvectors, second eigenvectors, and third eigenvectors from the decomposed eigenvector group according to the first eigenvalue, the second eigenvalue, and the third eigenvalue, wherein the first eigenvector corresponds to the first eigenvalue, the second eigenvector corresponds to the second eigenvalue, and the third eigenvector corresponds to the third eigenvalue;

[0067] Constructing a transformation matrix based on the first eigenvector, the second eigenvector, and the third eigenvector, wherein the transformation matrix is a 9×3 matrix, the first eigenvector is the vector in the first column of the transformation matrix, the second eigenvector is the vector in the second column of the transformation matrix, and the third eigenvector is the vector in the third column of the transformation matrix;

[0068] Calculating a dimensionality reduction vector using the transformation matrix and the normalized integrated vector;

[0069] Generate a sample feature identification code based on the dimensionality reduction vector.

[0070] Optionally, the calculation formula of the dimensionality reduction vector is as follows:

[0071]

[0072] Among them, Q5 refers to the dimensionality reduction vector and Q6 refers to the transformation matrix.

[0073] Optionally, generating a sample feature identification code according to the dimensionality reduction vector includes:

[0074] Performing inverse normalization on the dimension-reduced vector to obtain a first inverse normalization value, a second inverse normalization value, and a third inverse normalization value, and setting a first inverse normalization parameter, a second inverse normalization parameter, and a third inverse normalization parameter;

[0075] Constructing a mapping rule, wherein the mapping rule consists of a first rule, a second rule, a third rule, a first regression parameter, a second regression parameter, and a third regression parameter, wherein the first rule is: first regression parameter + first regression value, the second rule is: second regression parameter + second regression value, and the third rule is: third regression parameter + third regression value;

[0076] A sample feature identification code is generated based on the mapping rule, the first inverse value, the second inverse value, the third inverse value, the first inverse parameter, the second inverse parameter, and the third inverse parameter, wherein the sample feature identification code is as follows:

[0077] V=[MD+z1,ZL+z2,DD+z3]

[0078] Among them, V refers to the sample feature identification code, MD refers to the first regression parameter, z1 refers to the first regression value, ZL refers to the second regression parameter, z2 refers to the second regression value, DD refers to the third regression parameter, and z3 refers to the third regression value.

[0079] Optionally, the performing determination based on the chroma difference value set and a preset chroma threshold to obtain a determination result includes:

[0080] Extracting chroma difference values from the chroma difference value set in sequence, and comparing the extracted chroma difference values with a chroma threshold;

[0081] When the chromaticity difference values are all less than the chromaticity threshold, the test sample is confirmed as a preset negative sample;

[0082] When the chromaticity difference is less than the chromaticity threshold, the test sample is confirmed as a preset positive sample, wherein the determination result is that the test sample is a negative sample or the test sample is a positive sample.

[0083] To achieve the above objectives, the present invention further provides a multifunctional integrated intelligent detection system for drug-related samples, comprising:

[0084] An identity authentication module, configured to receive a sample detection instruction and activate a sample detection unit based on the sample detection instruction, wherein the sample detection unit includes: a centrifugal detection unit, a tension detection unit, an identity recognition unit, and a conductivity detection unit;

[0085] Performing identity recognition using the identity recognition unit to obtain identification information, wherein the identification information includes: whether the authentication is passed or not;

[0086] an authentication processing module, configured to return to the above-mentioned step of performing identity identification using the identity identification unit when the identification information fails the authentication;

[0087] When the identification information is authenticated, a drug-related sample to be tested is obtained, and a comprehensive test is performed on the drug-related sample to be tested based on the centrifugal detection unit, the tension detection unit, and the conductivity detection unit to obtain the centrifugal sample, characteristic density, characteristic tension, and characteristic conductivity;

[0088] a chromaticity detection module, configured to generate a sample characteristic identification code based on the characteristic density, characteristic tension, and characteristic conductivity;

[0089] Using a pre-built robotic arm to extract a test sample from a centrifuged sample to obtain a test card, and using the robotic arm to fix the test card to a pre-built card positioning area to obtain a fixed test card;

[0090] Dropping the test sample into the fixed test card, and testing the test sample based on a preset duration and the test card to obtain a set of test colorimetric values;

[0091] A data identification module is used to sequentially extract detection chromaticity values from the detection chromaticity value set, calculate chromaticity differences using the extracted detection chromaticity values and a preset standard chromaticity, and collect the chromaticity differences to obtain a chromaticity difference value set;

[0092] A judgment is made based on the chromaticity difference value set and a preset chromaticity threshold to obtain a judgment result, and the judgment result is combined with the sample feature identification code to obtain identification judgment data.

[0093] In order to solve the above problem, the present invention further provides an electronic device, comprising:

[0094] a memory storing at least one instruction;

[0095] The processor executes the instructions stored in the memory to implement the above-mentioned multifunctional integrated intelligent detection method for drug-related samples.

[0096] In order to solve the above problems, the present invention also provides a computer-readable storage medium, which stores at least one instruction, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned multifunctional integrated intelligent detection method for drug-related samples.

[0097] The present invention solves the problems described in the background technology. First, the identity recognition unit is used to identify the initiator of the sample detection instruction to obtain identification information. When the identification information fails the authentication, the process returns to the step of using the identity recognition unit for identity recognition. When the sample detection unit is started, the identity recognition unit identifies the initiator of the sample detection instruction to ensure that only authorized personnel can perform the detection, reduce the risk of malicious operation, and ensure the confidentiality of drug-related samples and judgment results; secondly, when the identification information passes the authentication, the drug-related sample to be tested is obtained, and the drug-related sample to be tested is centrifuged according to the centrifugation detection unit, and the tension detection unit and the conductivity detection unit are used to perform surface tension detection and conductivity scanning on the drug-related sample to be tested to obtain the centrifuged sample, characteristic density, characteristic tension and characteristic conductivity. The characteristic density, characteristic tension and characteristic conductivity provide information for the subsequent generation of the sample characteristic identification code. Accurate information is obtained; afterwards, a characteristic identification code is generated based on characteristic density, characteristic tension and characteristic conductivity, and multiple detection indicators are combined to form a characteristic identification code, which is convenient for subsequent rapid comparison and archiving, avoids repeated detection, and improves the efficiency of drug-related sample detection; further, a mechanical arm is used to extract the test sample from the centrifuged sample, and the test card is fixed in the card positioning area. The introduction of the mechanical arm ensures the consistency and accuracy of the sample processing, reduces the error caused by human operation, and improves the accuracy of the subsequent detection of colorimetric data; finally, based on the colorimetric difference set and the colorimetric threshold, a judgment result is obtained, and the judgment result is combined with the sample characteristic identification code to obtain identification judgment data, and the judgment result is combined with the sample characteristic identification code. If a drug-related sample with the same sample characteristic identification code is encountered during the detection process, it can be directly retrieved according to the sample characteristic identification code, and there is no need to perform the entire detection process again. Therefore, the present invention can improve the efficiency of drug-related sample detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0098] Figure 1 A schematic diagram of a flow chart of a multifunctional integrated intelligent detection method for drug-related samples provided by one embodiment of the present invention;

[0099] Figure 2 A functional module diagram of a multifunctional integrated intelligent drug-related sample detection system provided by one embodiment of the present invention;

[0100] Figure 3 A schematic structural diagram of an electronic device for implementing the multifunctional integrated intelligent detection method for drug-related samples provided in one embodiment of the present invention.

[0101] Description of reference numerals:

[0102] 1. Electronic device; 10. Processor; 11. Memory; 12. Bus.

[0103] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0104] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0105] The present embodiment provides a multifunctional, integrated intelligent detection method for drug-related samples. The execution entity of this multifunctional, integrated intelligent detection method for drug-related samples includes, but is not limited to, at least one of electronic devices such as a server or a terminal that can be configured to execute the method provided by the present embodiment. In other words, the multifunctional, integrated intelligent detection method for drug-related samples can be executed by software or hardware installed on a terminal device or a server device, where the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0106] Reference Figure 1 FIG. 1 is a flow chart of a multifunctional integrated intelligent detection method for drug-related samples provided by an embodiment of the present invention. In this embodiment, the multifunctional integrated intelligent detection method for drug-related samples includes:

[0107] S1. Receive a sample detection instruction, and start a sample detection unit based on the sample detection instruction, wherein the sample detection unit includes: a centrifugal detection unit, a tension detection unit, an identity recognition unit, and a conductivity detection unit.

[0108] It can be explained that the sample detection instruction refers to an instruction issued manually for testing the drug-related sample to be tested. The sample detection unit refers to a unit activated by the sample detection instruction, which integrates the centrifugation, tension detection, identity recognition and conductivity detection functions. The centrifugation detection unit refers to a unit used to centrifuge the drug-related sample to be tested. The tension detection unit refers to a unit that performs surface tension detection on the drug-related sample to be tested. Optionally, the tension detection unit is: a surface tension meter. The identity recognition unit refers to a unit used to identify the issuer of the sample detection instruction, and the identity recognition unit performs identity recognition by face recognition. The conductivity detection unit refers to a unit used to detect the conductivity of the drug-related sample to be tested.

[0109] S2. Perform identity recognition using the identity recognition unit to obtain identification information, wherein the identification information includes: whether the authentication is passed or not.

[0110] It can be explained that identification information refers to the information obtained after the issuer of the sample testing instruction is identified by the identity identification unit. Passing the authentication means that the issuer of the sample testing instruction has passed the identity identification of the identity identification unit, and failing the authentication means that the issuer of the sample testing instruction has not passed the identity identification of the identity identification unit.

[0111] S3. When the identification information fails the authentication, the process returns to the above step of performing identity identification using the identity identification unit.

[0112] S4. When the identification information is authenticated, obtain the drug-related sample to be tested, and perform comprehensive testing on the drug-related sample to be tested based on the centrifugal detection unit, the tension detection unit and the conductivity detection unit to obtain the centrifugal sample, characteristic density, characteristic tension and characteristic conductivity.

[0113] It can be explained that the drug-related sample to be tested refers to the sample that needs to be tested, and the centrifuged sample refers to the sample obtained after centrifuging the drug-related sample to be tested.

[0114] In detail, the centrifugal detection unit, the tension detection unit and the conductivity detection unit are used to perform comprehensive detection on the drug-related sample to be tested, and obtain the centrifuged sample, characteristic density, characteristic tension and characteristic conductivity, including:

[0115] Setting the centrifugal speed and centrifugal time, and using the centrifugal detection unit, the centrifugal speed and the centrifugal time to perform a centrifugal operation on the drug-related sample to be tested to obtain a centrifuged sample;

[0116] Using a pre-built density sensor and a preset stratification interval to detect the density of the centrifuged sample, a detection density set is obtained;

[0117] The drug-related sample to be tested is tested using a preset detection interval, a preset detection duration, a tension detection unit, a conductivity detection unit, and a preset frequency range to obtain a tension detection moment, a detection tension, a detection frequency, and a detection conductivity. The tension detection moment, the detection tension, the detection frequency, and the detection conductivity are respectively collected to obtain a tension detection moment set, a detection tension set, a detection frequency set, and a detection conductivity set, wherein the tension detection moment and the detection tension correspond one-to-one, the detection frequency and the detection conductivity correspond one-to-one, and the testing of the drug-related sample to be tested and the centrifugation operation of the drug-related sample to be tested are performed simultaneously;

[0118] Based on the detection density set, the layer interval, the tension detection time set, the detection tension set, the detection frequency set and the detection conductivity set, feature calculation is performed to obtain feature density, feature tension and feature conductivity.

[0119] It can be explained that the centrifugal speed refers to the speed at which the centrifugal detection unit centrifuges the drug-related sample to be tested. Optionally, the centrifugal speed is 3000rpm. The centrifugal time refers to the time during which the centrifugal detection unit centrifuges the drug-related sample to be tested. Optionally, the centrifugal time is 3min. The density sensor refers to a device for performing density detection on each layer of the centrifuged sample. Optionally, the density sensor is a vibrating tube densitometer. Each layer of the centrifuged sample is obtained by dividing the centrifuged sample by a layer interval. The layer interval refers to an interval set manually for stratifying the centrifuged sample. For example, if the height of the centrifuged sample is 5cm and the layer interval is set to 1cm, the centrifuged sample is divided once every 1cm to obtain six layers of 0cm, 1cm, 2cm, 3cm, 4cm and 5cm. The detection density set refers to the set composed of the detection density of each layer of the centrifuged sample. The detection density refers to the density of the centrifuged sample detected by the density sensor. The detection interval refers to the time interval for tension detection of the drug-related sample to be tested. For example, if the detection interval is 1s, the tension test of the drug-related sample to be tested is performed every 1s. The detection duration refers to the duration of the tension test on the drug-related sample to be tested. For example, if the detection duration is 2 minutes, the tension test on the drug-related sample to be tested will last for a total of 2 minutes. The frequency range refers to the frequency interval covered when the conductivity test is performed on the drug-related sample to be tested. For example, the frequency interval is [0.1, 10] MHz, and the frequency range is 0.1MHz to 10MHz. The tension detection time refers to the time when the tension test is performed. For example, the time to start the test is 10:00am, and the test interval is 1s, then 10:00:01 is the tension detection time, and 10:00:02 is also the tension detection time. The detection tension refers to the surface tension of the drug-related sample to be tested obtained after the drug-related sample to be tested is tested using the tension detection unit. The detection frequency refers to the frequency in the frequency range. For example, if the frequency range is 0.1MHz to 10MHz, then 0.1MHz is the detection frequency, and 10MHz is also the detection frequency. The "test conductivity" refers to the conductivity of the drug-related sample at the test frequency. For example, if the test frequency is 0.1 MHz, the conductivity of the drug-related sample at that frequency is 0.8 S / m. The "tension test moment set" refers to the set of tension test moments, the "test tension set" refers to the set of tension test times, the "test frequency set" refers to the set of frequency test times, and the "test conductivity set" refers to the set of conductivity test times.

[0120] In detail, the characteristic calculation is performed based on the detection density set, the layer interval, the tension detection time set, the detection tension set, the detection frequency set, and the detection conductivity set to obtain the characteristic density, characteristic tension, and characteristic conductivity, including:

[0121] Calculating the layer height according to the layer interval, and constructing a centrifugal curve using the detection density set and the layer height, wherein the horizontal axis of the centrifugal curve is the layer height and the vertical axis of the centrifugal curve is the detection density;

[0122] Constructing a tension dynamic curve based on the tension detection time set and the detection tension set, wherein the horizontal axis of the tension dynamic curve is the detection time, and the vertical axis of the tension dynamic curve is the detection tension;

[0123] Constructing a conductivity image using the detection frequency set and the detection conductivity set, wherein the horizontal axis of the conductivity image is the detection frequency and the vertical axis of the conductivity image is the detection conductivity;

[0124] Characteristic calculation is performed based on the centrifugal curve, tension dynamic curve and conductivity image to obtain characteristic density, characteristic tension and characteristic conductivity.

[0125] To be clear, the layer height refers to the height calculated based on the layer interval. For example, if the centrifuged sample height is 5 cm and the layer interval is set to 1 cm, then 0 cm, 1 cm, 2 cm, 3 cm, 4 cm, and 5 cm are all layer heights. The centrifugation curve refers to a curve constructed with the layer height as the horizontal axis and the test density as the vertical axis. The tension dynamic curve refers to a curve constructed with the test time as the horizontal axis and the test tension as the vertical axis. The conductivity image refers to a curve constructed with the test frequency as the horizontal axis and the test conductivity as the vertical axis.

[0126] In detail, the characteristic calculation is performed based on the centrifugal curve, the tension dynamic curve and the conductivity image to obtain the characteristic density, characteristic tension and characteristic conductivity, including:

[0127] Extracting a density peak from the centrifugation curve, and calculating a density mean and a density standard deviation based on the centrifugation curve;

[0128] The standard skewness value is calculated using the density standard deviation, density mean and detection density:

[0129]

[0130] Among them, q refers to the standard skewness value, α refers to the preset density parameter, M refers to the total density, ρ α Refers to the detection density when the density parameter is α, γ refers to the density mean, and β refers to the density standard deviation;

[0131] The characteristic density is formed based on the standard skewness value, density peak value and density mean, wherein the characteristic density is as follows:

[0132] Q=[q,q²,γ]

[0133] Where Q refers to the characteristic density and q2 refers to the density peak;

[0134] Extract the maximum tension, minimum tension, maximum time, and minimum time from the tension dynamic curve, and calculate the tension change rate based on the maximum tension, minimum tension, maximum time, and minimum time:

[0135]

[0136] Where W refers to the rate of change of tension, y1 refers to the maximum tension, y2 refers to the minimum tension, t1 refers to the maximum time, and t2 refers to the minimum time;

[0137] Set a sliding window and calculate the characteristic tension based on the sliding window and the tension change rate;

[0138] Extracting the highest conductance frequency and the lowest conductance frequency from the conductance image, and calculating the conductance change according to the highest conductance frequency and the lowest conductance frequency;

[0139] The frequency rate is calculated based on the highest conductance frequency, the lowest conductance frequency and the conductance change:

[0140]

[0141] Where S refers to the frequency rate, o3 refers to the change in conductance, ln refers to the natural logarithm, o1 refers to the highest conductance frequency, and o2 refers to the lowest conductance frequency;

[0142] The characteristic conductivity is formed according to the highest conductivity frequency, the lowest conductivity frequency and the frequency rate, wherein the characteristic conductivity is as follows:

[0143] Q2=[o1,o2,S]

[0144] Here, Q2 refers to the characteristic conductivity.

[0145] It can be explained that the density peak refers to the maximum detection density in the centrifugal curve, the density mean refers to the mean of all detection densities in the centrifugal curve, the density standard deviation refers to the standard deviation of all detection densities in the centrifugal curve, and the standard skewness value refers to the skewness of the detection density, reflecting the distribution of the detection density in the centrifugal curve. The density parameter refers to the parameter used to traverse the detection density, the total density refers to the total number of detection densities in the centrifugal curve, the characteristic density refers to the vector composed of the standard skewness value, the density peak and the density mean, the maximum tension refers to the maximum detection tension in the tension dynamic curve, the minimum tension refers to the minimum detection tension in the tension dynamic curve, the maximum moment refers to the maximum detection moment in the tension dynamic curve, the minimum moment refers to the minimum detection moment in the tension dynamic curve, and the tension change rate refers to the rate of change of the tension of the drug-related sample to be tested calculated based on the maximum tension, minimum tension, maximum moment and minimum moment. The greater the tension change rate, the greater the rate of change of the tension of the drug-related sample to be tested. The sliding window is a manually set value used to divide the test tensions in the test tension set. For example, if the sliding window is 5, the test tensions in the test tension set are divided into groups of 5. Assuming the test tension set is: 1, 2, 3, 4, 5, 6, 7, 8, 9, 2, then 1, 2, 3, 4, 5 is a group, and 6, 7, 8, 9, 2 is another group. The highest conductance frequency refers to the test conductivity corresponding to the maximum test frequency in the conductivity image. The lowest conductance frequency refers to the test conductivity corresponding to the lowest test frequency in the conductivity image. The conductivity change refers to the difference between the highest and lowest conductance frequencies. The frequency rate refers to the rate of change of the test conductivity. The characteristic conductivity refers to the vector consisting of the highest conductance frequency, the lowest conductance frequency, and the frequency rate.

[0146] In detail, the calculation of characteristic tension based on the sliding window and tension change rate includes:

[0147] Using a sliding window to divide the detection tension in the detection tension set, a plurality of window tension sets are obtained;

[0148] Calculating standard deviations of the window tensions in the plurality of window tension sets to obtain a plurality of tension standard deviations, wherein one tension standard deviation corresponds to one window tension set;

[0149] Comparing a plurality of tension standard deviations with a preset tension threshold in sequence;

[0150] If the multiple tension standard deviations are all greater than the tension threshold, the tension threshold is increased to obtain an extended threshold, the tension threshold is updated using the extended threshold, and based on the updated tension threshold, the process returns to the above step of sequentially comparing the multiple tension standard deviations with the preset tension threshold.

[0151] If there is a tension standard deviation less than or equal to the tension threshold among multiple tension standard deviations, then the tension standard deviations less than or equal to the tension threshold are collected to obtain a screening standard deviation set;

[0152] Matching a window tension set based on a screening standard deviation in the screening standard deviation set, and performing mean calculation on the matched window tension set to obtain a stable tension;

[0153] The tension fluctuation amplitude is calculated based on the stable tension, tension detection time and detection tension:

[0154]

[0155] Among them, D refers to the tension fluctuation amplitude, t refers to the preset time parameter, μ refers to the total number of moments, and y t Refers to the detection tension when the moment parameter is t, and y3 refers to the stable tension;

[0156] The tension fluctuation amplitude, stable tension and tension change rate are used to form characteristic tension, where the characteristic tension is as follows:

[0157] Q3=[D,y3,W]

[0158] Among them, Q3 refers to characteristic tension.

[0159] To be explained, the window tension set refers to the set consisting of window tensions. Window tension refers to the detection tension in the sliding window after the detection tension in the detection tension set is divided using a sliding window. The tension standard deviation refers to the standard deviation of the window tension in the window tension set. The tension threshold refers to the manually set threshold used to determine the tension standard deviation. The extended threshold refers to the threshold obtained by increasing the tension threshold by 10%. The screening standard deviation set refers to the set consisting of screening standard deviations. The screening standard deviation refers to the tension standard deviation that is less than or equal to the tension threshold. The stable tension refers to the mean of the window tensions in the window tension set corresponding to the screening standard deviation. The tension fluctuation amplitude refers to the value calculated based on the stable tension, tension detection moment, and detection tension, which is used to reflect the amplitude of the change in the surface tension of the drug-related sample to be tested. The moment parameter refers to the parameter used to traverse the tension detection moments. The total number of moments refers to the total number of tension detection moments. The characteristic tension refers to the vector consisting of the tension fluctuation amplitude, stable tension, and tension change rate.

[0160] S5. Generate a sample characteristic identification code based on the characteristic density, characteristic tension, and characteristic conductivity.

[0161] In detail, generating a sample characteristic identification code based on the characteristic density, characteristic tension, and characteristic conductivity includes:

[0162] The characteristic density, characteristic tension and characteristic conductivity are spliced together to obtain a comprehensive characteristic vector, wherein the comprehensive characteristic vector is as follows:

[0163] Q4=[q,q2,γ,o1,o2,S,D,y3,W] T

[0164] Among them, Q4 refers to the comprehensive eigenvector, and T refers to the matrix transpose symbol;

[0165] Normalizing all components in the comprehensive feature vector to obtain a normalized comprehensive vector;

[0166] The covariance matrix is constructed based on the normalized integrated vector, where the covariance matrix is as follows:

[0167]

[0168] Among them, F refers to the covariance matrix, F1 refers to the normalized integrated vector, Point to the multiplication symbol;

[0169] Performing eigenvalue decomposition on the covariance matrix to obtain a decomposition eigenvalue group and a decomposition eigenvector group, wherein the decomposition eigenvalues correspond to the decomposition eigenvectors in one-to-one correspondence;

[0170] Extracting a first eigenvalue, a second eigenvalue, and a third eigenvalue from the decomposed eigenvalue group, and matching corresponding first eigenvectors, second eigenvectors, and third eigenvectors from the decomposed eigenvector group according to the first eigenvalue, the second eigenvalue, and the third eigenvalue, wherein the first eigenvector corresponds to the first eigenvalue, the second eigenvector corresponds to the second eigenvalue, and the third eigenvector corresponds to the third eigenvalue;

[0171] Constructing a transformation matrix based on the first eigenvector, the second eigenvector, and the third eigenvector, wherein the transformation matrix is a 9×3 matrix, the first eigenvector is the vector in the first column of the transformation matrix, the second eigenvector is the vector in the second column of the transformation matrix, and the third eigenvector is the vector in the third column of the transformation matrix;

[0172] Calculating a dimensionality reduction vector using the transformation matrix and the normalized integrated vector;

[0173] Generate a sample feature identification code based on the dimensionality reduction vector.

[0174] It can be explained that the comprehensive eigenvector refers to the vector obtained by concatenating the characteristic density, characteristic tension and characteristic conductivity, and the normalized comprehensive vector refers to the vector obtained by normalizing all components in the comprehensive eigenvector. Normalization is the prior art and will not be repeated here. The covariance matrix refers to the matrix obtained by multiplying the transpose of the normalized comprehensive vector with the normalized comprehensive vector. The decomposed eigenvalue group refers to the combination of decomposed eigenvalues, the decomposed eigenvalue refers to the value obtained after calculating the eigenvalue of the covariance matrix, the decomposed eigenvector group refers to the combination of decomposed eigenvectors, the decomposed eigenvector refers to the vector obtained after solving the eigenvector according to the decomposed eigenvalue, the eigenvalue calculation and the eigenvector solution are all prior art and will not be repeated here. The first eigenvalue refers to the largest decomposition eigenvalue in the decomposition eigenvalue group, the second eigenvalue refers to the second largest decomposition eigenvalue in the decomposition eigenvalue group, the third eigenvalue refers to the third largest decomposition eigenvalue in the decomposition eigenvalue group, the first eigenvector refers to the eigenvector corresponding to the first eigenvalue, the second eigenvector refers to the eigenvector corresponding to the second eigenvalue, and the third eigenvector refers to the eigenvector corresponding to the third eigenvalue.

[0175] In detail, the calculation formula of the dimensionality reduction vector is as follows:

[0176]

[0177] Among them, Q5 refers to the dimensionality reduction vector and Q6 refers to the transformation matrix.

[0178] Interpretably, the reduced dimensionality vector refers to the eigenvector obtained after projecting the normalized comprehensive vector onto the transformation matrix, and the reduced dimensionality vector is a three-dimensional eigenvector.

[0179] In detail, generating a sample feature identification code according to the dimensionality reduction vector includes:

[0180] Performing inverse normalization on the dimension-reduced vector to obtain a first inverse normalization value, a second inverse normalization value, and a third inverse normalization value, and setting a first inverse normalization parameter, a second inverse normalization parameter, and a third inverse normalization parameter;

[0181] Constructing a mapping rule, wherein the mapping rule consists of a first rule, a second rule, a third rule, a first regression parameter, a second regression parameter, and a third regression parameter, wherein the first rule is: first regression parameter + first regression value, the second rule is: second regression parameter + second regression value, and the third rule is: third regression parameter + third regression value;

[0182] A sample feature identification code is generated based on the mapping rule, the first inverse value, the second inverse value, the third inverse value, the first inverse parameter, the second inverse parameter, and the third inverse parameter, wherein the sample feature identification code is as follows:

[0183] V=[MD+z1,ZL+z2,DD+z3]

[0184] Among them, V refers to the sample feature identification code, MD refers to the first regression parameter, z1 refers to the first regression value, ZL refers to the second regression parameter, z2 refers to the second regression value, DD refers to the third regression parameter, and z3 refers to the third regression value.

[0185] It can be explained that the first inverse value refers to the value obtained after inverse normalization of the components of the first row in the dimensionality reduction vector, the second inverse value refers to the value obtained after inverse normalization of the components of the second row in the dimensionality reduction vector, and the third inverse value refers to the value obtained after inverse normalization of the components of the third row in the dimensionality reduction vector. Inverse normalization is a prior art and will not be described in detail here. The first inverse parameter refers to a parameter set manually for identifying the first inverse value, the second inverse parameter refers to a parameter set manually for identifying the second inverse value, and the third inverse parameter refers to a parameter set manually for identifying the third inverse value. The mapping rule refers to a rule for identifying the drug-related sample to be tested according to the first inverse value, the second inverse value and the third inverse value. The first rule refers to the rule applicable to the first inverse value, the second rule refers to the rule applicable to the second inverse value, and the third rule refers to the rule applicable to the third inverse value. The sample feature identification code refers to the data generated according to the mapping rule, the first inverse value, the second inverse value and the third inverse value for identifying the drug-related sample to be tested.

[0186] S6. Using a pre-built robotic arm to extract a test sample from the centrifuged sample, obtain a test card, and use the robotic arm to fix the test card to a pre-built card positioning area to obtain a fixed test card.

[0187] To be clear, the robotic arm is a six-axis robotic arm, extracting test samples from centrifuged samples refers to extracting test samples from centrifuged samples using the robotic arm and a pipette tip. The test card refers to an 8-strip test card, the card positioning area refers to the area for placing the test card, and the fixed test card refers to the test card obtained after the test card is placed in the card positioning area.

[0188] S7. Dropping the test sample into the fixed test card, and testing the test sample based on a preset duration and the test card to obtain a set of test colorimetric values.

[0189] Explanatory note: Duration refers to the time it takes for the test sample to react with the fixed test card. Optionally, the duration is 3 minutes. A test chromaticity value set refers to a set of test chromaticity values. A test chromaticity value refers to the color value obtained by performing CIELAB color space conversion on the transformed chromaticity value. CIELAB color space conversion is a prior art technique and will not be further described here. A transformed chromaticity value refers to the RGB value obtained from the fixed test card using a color acquisition device after the test sample and the fixed test card react for a duration. Optionally, the color acquisition device is a spectrometer.

[0190] S8. Extract detection chromaticity values from the detection chromaticity value set in sequence, calculate chromaticity differences using the extracted detection chromaticity values and a preset standard chromaticity, and collect the chromaticity differences to obtain a chromaticity difference value set.

[0191] Explainably, standard chromaticity refers to an artificially set chromaticity value, which is used to judge the test chromaticity value. The chromaticity difference refers to the difference between the test chromaticity value and the standard chromaticity. The calculation formula of the chromaticity difference is as follows:

[0192]

[0193] Among them, G refers to the chromaticity difference, τ1 refers to the detected brightness value, τ2 refers to the standard brightness value, θ1 refers to the detected green and red color amplitude value, and θ2 refers to the standard green and red color amplitude value. Refers to detecting the blue and yellow color amplitude value, Refers to the standard blue-yellow color amplitude value.

[0194] It can be understood that the detection brightness value refers to the brightness value in the detection chromaticity value, and the range of brightness value is 0 to 100, where 0 represents the lowest brightness, completely black, and 100 represents the highest brightness, completely white. The standard brightness value refers to the brightness value in the standard chromaticity, and the detection green-red color amplitude value refers to the tendency of color change from green to red. When the detection green-red color amplitude value is negative, the color of the fixed detection card tends to be green. When the detection green-red color amplitude value is positive, the color of the fixed detection card tends to be red. The standard green-red color amplitude value refers to the tendency of color change from green to red in the standard chromaticity. The detection blue-yellow color amplitude value refers to the tendency of color change from blue to yellow. When the detection blue-yellow color amplitude value is negative, the color of the fixed detection card tends to be blue. When the detection blue-yellow color amplitude value is positive, the color of the fixed detection card tends to be yellow. The standard blue-yellow color amplitude value refers to the tendency of color change from blue to yellow in the standard chromaticity.

[0195] S9. Make a judgment based on the chromaticity difference set and the preset chromaticity threshold to obtain a judgment result, combine the judgment result with the sample feature identification code to obtain identification judgment data, and complete intelligent detection of drug-related samples based on the identification judgment data.

[0196] The chromaticity threshold is a manually set threshold for determining chromaticity differences. Optionally, the chromaticity threshold is 15. Determination results include negative and positive. Identification determination data refers to the data obtained by combining the determination result with the sample characteristic identification code. For example, if the determination result is positive and the sample characteristic identification code is [MD+1, ZL+2, DD+3], the identification determination data is: [MD+1, ZL+2, DD+3]: positive.

[0197] In detail, the determination based on the chromaticity difference value set and the preset chromaticity threshold value to obtain the determination result includes:

[0198] Extracting chroma difference values from the chroma difference value set in sequence, and comparing the extracted chroma difference values with a chroma threshold;

[0199] When the chromaticity difference values are all less than the chromaticity threshold, the test sample is confirmed as a preset negative sample;

[0200] When the chromaticity difference is less than the chromaticity threshold, the test sample is confirmed as a preset positive sample, wherein the determination result is that the test sample is a negative sample or the test sample is a positive sample.

[0201] It is explainable that both negative and positive samples are judgment results. Positive samples indicate that the drug-related sample to be tested is poisonous, and negative samples indicate that the drug-related sample to be tested is non-toxic.

[0202] The present invention solves the problems described in the background technology. First, the identity recognition unit is used to identify the initiator of the sample detection instruction to obtain identification information. When the identification information fails the authentication, the process returns to the step of using the identity recognition unit for identity recognition. When the sample detection unit is started, the identity recognition unit identifies the initiator of the sample detection instruction to ensure that only authorized personnel can perform the detection, reduce the risk of malicious operation, and ensure the confidentiality of drug-related samples and judgment results; secondly, when the identification information passes the authentication, the drug-related sample to be tested is obtained, and the drug-related sample to be tested is centrifuged according to the centrifugation detection unit, and the tension detection unit and the conductivity detection unit are used to perform surface tension detection and conductivity scanning on the drug-related sample to be tested to obtain the centrifuged sample, characteristic density, characteristic tension and characteristic conductivity. The characteristic density, characteristic tension and characteristic conductivity provide information for the subsequent generation of the sample characteristic identification code. Accurate information is obtained; afterwards, a characteristic identification code is generated based on characteristic density, characteristic tension and characteristic conductivity, and multiple detection indicators are combined to form a characteristic identification code, which is convenient for subsequent rapid comparison and archiving, avoids repeated detection, and improves the efficiency of drug-related sample detection; further, a mechanical arm is used to extract the test sample from the centrifuged sample, and the test card is fixed in the card positioning area. The introduction of the mechanical arm ensures the consistency and accuracy of the sample processing, reduces the error caused by human operation, and improves the accuracy of the subsequent detection of colorimetric data; finally, based on the colorimetric difference set and the colorimetric threshold, a judgment result is obtained, and the judgment result is combined with the sample characteristic identification code to obtain identification judgment data, and the judgment result is combined with the sample characteristic identification code. If a drug-related sample with the same sample characteristic identification code is encountered during the detection process, it can be directly retrieved according to the sample characteristic identification code, and there is no need to perform the entire detection process again. Therefore, the present invention can improve the efficiency of drug-related sample detection.

[0203] like Figure 2 , which is a functional module diagram of a multifunctional integrated intelligent detection system for drug-related samples provided by one embodiment of the present invention.

[0204] The multifunctional integrated intelligent drug-related sample detection system 100 described in the present invention can be installed in an electronic device. Depending on the functionality implemented, the multifunctional integrated intelligent drug-related sample detection system 100 may include an identity authentication module 101, an authentication processing module 102, a colorimetric detection module 103, and a data identification module 104. A module, also referred to as a unit, is a series of computer program segments that can be executed by an electronic device processor and perform a fixed function, and is stored in the electronic device's memory.

[0205] The identity authentication module 101 is used to receive a sample detection instruction and start a sample detection unit based on the sample detection instruction, wherein the sample detection unit includes: a centrifugal detection unit, a tension detection unit, an identity recognition unit and a conductivity detection unit;

[0206] Performing identity recognition using the identity recognition unit to obtain identification information, wherein the identification information includes: whether the authentication is passed or not;

[0207] The authentication processing module 102 is configured to return to the above-mentioned step of performing identity identification using the identity identification unit when the identification information fails the authentication;

[0208] When the identification information is authenticated, a drug-related sample to be tested is obtained, and a comprehensive test is performed on the drug-related sample to be tested based on the centrifugal detection unit, the tension detection unit, and the conductivity detection unit to obtain the centrifugal sample, characteristic density, characteristic tension, and characteristic conductivity;

[0209] The chromaticity detection module 103 is used to generate a sample characteristic identification code based on the characteristic density, characteristic tension and characteristic conductivity;

[0210] Using a pre-built robotic arm to extract a test sample from a centrifuged sample to obtain a test card, and using the robotic arm to fix the test card to a pre-built card positioning area to obtain a fixed test card;

[0211] Dropping the test sample into the fixed test card, and testing the test sample based on a preset duration and the test card to obtain a set of test colorimetric values;

[0212] The data identification module 104 is used to sequentially extract detection chromaticity values from the detection chromaticity value set, calculate chromaticity differences using the extracted detection chromaticity values and a preset standard chromaticity, and collect the chromaticity differences to obtain a chromaticity difference value set;

[0213] A judgment is made based on the chromaticity difference value set and a preset chromaticity threshold to obtain a judgment result, and the judgment result is combined with the sample feature identification code to obtain identification judgment data.

[0214] In detail, each module in the multifunctional integrated drug-related sample intelligent detection system 100 in the embodiment of the present invention adopts the same Figure 1 The technical means are the same as the multifunctional integrated intelligent detection method for drug-related samples described in, and can produce the same technical effects, so they will not be repeated here.

[0215] like Figure 3 , which is a schematic structural diagram of an electronic device for implementing a multifunctional integrated intelligent detection method for drug-related samples provided by one embodiment of the present invention.

[0216] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a multifunctional integrated intelligent drug-related sample detection method program.

[0217] Among them, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, smart memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash Card), etc. equipped on the electronic device 1. Furthermore, the memory 11 also includes the internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various types of data installed on the electronic device 1, such as the code of the multifunctional integrated drug-related sample intelligent detection method program, etc., but can also be used to temporarily store data that has been output or is to be output.

[0218] In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips. The processor 10 is the control core (Control Unit) of the electronic device, connecting the various components of the entire electronic device using various interfaces and lines, and executing the programs or modules stored in the memory 11 (such as a multifunctional integrated intelligent detection method program for drug-related samples, etc.), as well as calling the data stored in the memory 11, to perform various functions of the electronic device 1 and process data.

[0219] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0220] Figure 3 Only the electronic device with components is shown, and it can be understood by those skilled in the art that Figure 3 The structure shown does not constitute a limitation on the electronic device 1 , and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0221] For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for powering the various components. Preferably, the power source may be logically connected to the at least one processor 10 via a power management device, thereby implementing functions such as charging management, discharging management, and power consumption management through the power management device. The power source may further include any components such as one or more DC or AC power sources, a recharging device, a power failure detection circuit, a power converter or inverter, a power status indicator, etc. The electronic device 1 may further include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0222] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0223] Optionally, the electronic device 1 may further include a user interface, which may be a display or an input unit (such as a keyboard). Optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0224] The multifunctional integrated intelligent drug-related sample detection method program stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve the following:

[0225] receiving a sample detection instruction and starting a sample detection unit based on the sample detection instruction, wherein the sample detection unit includes: a centrifugal detection unit, a tension detection unit, an identity recognition unit, and a conductivity detection unit;

[0226] Performing identity recognition using the identity recognition unit to obtain identification information, wherein the identification information includes: whether the authentication is passed or not;

[0227] When the identification information fails the authentication, the process returns to the above step of performing identity identification using the identity identification unit;

[0228] When the identification information is authenticated, a drug-related sample to be tested is obtained, and a comprehensive test is performed on the drug-related sample to be tested based on the centrifugal detection unit, the tension detection unit, and the conductivity detection unit to obtain the centrifugal sample, characteristic density, characteristic tension, and characteristic conductivity;

[0229] generating a sample characteristic identification code based on the characteristic density, characteristic tension, and characteristic conductivity;

[0230] Using a pre-built robotic arm to extract a test sample from a centrifuged sample to obtain a test card, and using the robotic arm to fix the test card to a pre-built card positioning area to obtain a fixed test card;

[0231] Dropping the test sample into the fixed test card, and testing the test sample based on a preset duration and the test card to obtain a set of test colorimetric values;

[0232] Extracting detection chromaticity values from the detection chromaticity value set in sequence, calculating chromaticity differences using the extracted detection chromaticity values and a preset standard chromaticity, and collecting the chromaticity differences to obtain a chromaticity difference value set;

[0233] The judgment is made based on the chromaticity difference set and the preset chromaticity threshold to obtain the judgment result, which is combined with the sample feature identification code to obtain the identification judgment data, and the intelligent detection of drug-related samples is completed based on the identification judgment data.

[0234] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0235] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0236] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program. When the computer program is executed by a processor of an electronic device, the computer program can implement:

[0237] receiving a sample detection instruction and starting a sample detection unit based on the sample detection instruction, wherein the sample detection unit includes: a centrifugal detection unit, a tension detection unit, an identity recognition unit, and a conductivity detection unit;

[0238] Performing identity recognition using the identity recognition unit to obtain identification information, wherein the identification information includes: whether the authentication is passed or not;

[0239] When the identification information fails the authentication, the process returns to the above step of performing identity identification using the identity identification unit;

[0240] When the identification information is authenticated, a drug-related sample to be tested is obtained, and a comprehensive test is performed on the drug-related sample to be tested based on the centrifugal detection unit, the tension detection unit, and the conductivity detection unit to obtain the centrifugal sample, characteristic density, characteristic tension, and characteristic conductivity;

[0241] generating a sample characteristic identification code based on the characteristic density, characteristic tension, and characteristic conductivity;

[0242] Using a pre-built robotic arm to extract a test sample from a centrifuged sample to obtain a test card, and using the robotic arm to fix the test card to a pre-built card positioning area to obtain a fixed test card;

[0243] Dropping the test sample into the fixed test card, and testing the test sample based on a preset duration and the test card to obtain a set of test colorimetric values;

[0244] Extracting detection chromaticity values from the detection chromaticity value set in sequence, calculating chromaticity differences using the extracted detection chromaticity values and a preset standard chromaticity, and collecting the chromaticity differences to obtain a chromaticity difference value set;

[0245] The judgment is made based on the chromaticity difference set and the preset chromaticity threshold to obtain the judgment result, which is combined with the sample feature identification code to obtain the identification judgment data, and the intelligent detection of drug-related samples is completed based on the identification judgment data.

[0246] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only exemplary, and actual implementations may have other division methods.

[0247] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0248] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0249] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0250] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A multifunctional integrated intelligent detection method for drug-related samples, characterized in that: The method comprises: receiving a sample detection instruction and starting a sample detection unit based on the sample detection instruction, wherein the sample detection unit includes: a centrifugal detection unit, a tension detection unit, an identity recognition unit, and a conductivity detection unit; Performing identity recognition using the identity recognition unit to obtain identification information, wherein the identification information includes: whether the authentication is passed or not; When the identification information fails the authentication, the process returns to the above step of performing identity identification using the identity identification unit; When the identification information is authenticated, a drug-related sample to be tested is obtained, and a comprehensive test is performed on the drug-related sample to be tested based on the centrifugal detection unit, the tension detection unit, and the conductivity detection unit to obtain the centrifugal sample, characteristic density, characteristic tension, and characteristic conductivity; generating a sample characteristic identification code based on the characteristic density, characteristic tension, and characteristic conductivity; Using a pre-built robotic arm to extract a test sample from a centrifuged sample to obtain a test card, and using the robotic arm to fix the test card to a pre-built card positioning area to obtain a fixed test card; Dropping the test sample into the fixed test card, and testing the test sample based on a preset duration and the test card to obtain a set of test colorimetric values; Extracting detection chromaticity values from the detection chromaticity value set in sequence, calculating chromaticity differences using the extracted detection chromaticity values and a preset standard chromaticity, and collecting the chromaticity differences to obtain a chromaticity difference value set; The judgment is made based on the chromaticity difference set and the preset chromaticity threshold to obtain the judgment result, which is combined with the sample feature identification code to obtain the identification judgment data, and the intelligent detection of drug-related samples is completed based on the identification judgment data.

2. The multifunctional integrated intelligent detection method for drug-related samples according to claim 1, characterized in that: The centrifugal detection unit, the tension detection unit, and the conductivity detection unit are used to perform comprehensive detection on the drug-related sample to be tested, and obtain the centrifuged sample, characteristic density, characteristic tension, and characteristic conductivity, including: Setting the centrifugal speed and centrifugal time, and using the centrifugal detection unit, the centrifugal speed and the centrifugal time to perform a centrifugal operation on the drug-related sample to be tested to obtain a centrifuged sample; Using a pre-built density sensor and a preset stratification interval to detect the density of the centrifuged sample, a detection density set is obtained; The drug-related sample to be tested is tested using a preset detection interval, a preset detection duration, a tension detection unit, a conductivity detection unit, and a preset frequency range to obtain a tension detection moment, a detection tension, a detection frequency, and a detection conductivity. The tension detection moment, the detection tension, the detection frequency, and the detection conductivity are respectively collected to obtain a tension detection moment set, a detection tension set, a detection frequency set, and a detection conductivity set, wherein the tension detection moment and the detection tension correspond one-to-one, the detection frequency and the detection conductivity correspond one-to-one, and the testing of the drug-related sample to be tested and the centrifugation operation of the drug-related sample to be tested are performed simultaneously; Based on the detection density set, the layer interval, the tension detection time set, the detection tension set, the detection frequency set and the detection conductivity set, feature calculation is performed to obtain feature density, feature tension and feature conductivity.

3. The multifunctional integrated intelligent detection method for drug-related samples according to claim 2, characterized in that: The characteristic calculation based on the detection density set, the layer interval, the tension detection time set, the detection tension set, the detection frequency set and the detection conductivity set to obtain the characteristic density, the characteristic tension and the characteristic conductivity includes: Calculating the layer height according to the layer interval, and constructing a centrifugal curve using the detection density set and the layer height, wherein the horizontal axis of the centrifugal curve is the layer height and the vertical axis of the centrifugal curve is the detection density; Constructing a tension dynamic curve based on the tension detection time set and the detection tension set, wherein the horizontal axis of the tension dynamic curve is the detection time, and the vertical axis of the tension dynamic curve is the detection tension; Constructing a conductivity image using the detection frequency set and the detection conductivity set, wherein the horizontal axis of the conductivity image is the detection frequency and the vertical axis of the conductivity image is the detection conductivity; Characteristic calculation is performed based on the centrifugal curve, tension dynamic curve and conductivity image to obtain characteristic density, characteristic tension and characteristic conductivity.

4. The multifunctional integrated intelligent detection method for drug-related samples according to claim 3, characterized in that: The characteristic calculation is performed based on the centrifugal curve, the tension dynamic curve and the conductivity image to obtain the characteristic density, the characteristic tension and the characteristic conductivity, including: Extracting a density peak from the centrifugation curve, and calculating a density mean and a density standard deviation based on the centrifugation curve; The standard skewness value is calculated using the density standard deviation, density mean and detection density: Among them, q refers to the standard skewness value, α refers to the preset density parameter, M refers to the total density, ρ α Refers to the detection density when the density parameter is α, γ refers to the density mean, and β refers to the density standard deviation; The characteristic density is formed based on the standard skewness value, density peak value and density mean, wherein the characteristic density is as follows: Q=[q,q²,γ] Where Q refers to the characteristic density, and q2 refers to the density peak; Extract the maximum tension, minimum tension, maximum time, and minimum time from the tension dynamic curve, and calculate the tension change rate based on the maximum tension, minimum tension, maximum time, and minimum time: Where W refers to the rate of change of tension, y1 refers to the maximum tension, y2 refers to the minimum tension, t1 refers to the maximum time, and t2 refers to the minimum time; Set a sliding window and calculate the characteristic tension based on the sliding window and the tension change rate; Extracting the highest conductance frequency and the lowest conductance frequency from the conductance image, and calculating the conductance change according to the highest conductance frequency and the lowest conductance frequency; The frequency rate is calculated based on the highest conductance frequency, the lowest conductance frequency and the conductance change: Where S refers to the frequency rate, o3 refers to the change in conductance, ln refers to the natural logarithm, o1 refers to the highest conductance frequency, and o2 refers to the lowest conductance frequency; The characteristic conductivity is formed according to the highest conductivity frequency, the lowest conductivity frequency and the frequency rate, wherein the characteristic conductivity is as follows: Q2=[o1,o2,S] Here, Q2 refers to the characteristic conductivity.

5. The multifunctional integrated intelligent detection method for drug-related samples according to claim 4, characterized in that: The calculating characteristic tension based on the sliding window and the tension change rate includes: Using a sliding window to divide the detection tension in the detection tension set, a plurality of window tension sets are obtained; Calculating standard deviations of the window tensions in the plurality of window tension sets to obtain a plurality of tension standard deviations, wherein one tension standard deviation corresponds to one window tension set; Comparing a plurality of tension standard deviations with a preset tension threshold in sequence; If the multiple tension standard deviations are all greater than the tension threshold, the tension threshold is increased to obtain an extended threshold, the tension threshold is updated using the extended threshold, and based on the updated tension threshold, the process returns to the above step of sequentially comparing the multiple tension standard deviations with the preset tension threshold. If there is a tension standard deviation less than or equal to the tension threshold among multiple tension standard deviations, then the tension standard deviations less than or equal to the tension threshold are aggregated to obtain a screening standard deviation set; Matching a window tension set based on a screening standard deviation in the screening standard deviation set, and performing mean calculation on the matched window tension set to obtain a stable tension; The tension fluctuation amplitude is calculated based on the stable tension, tension detection time and detection tension: Among them, D refers to the tension fluctuation amplitude, t refers to the preset time parameter, μ refers to the total number of moments, and y t Refers to the detection tension when the moment parameter is t, and y3 refers to the stable tension; The tension fluctuation amplitude, stable tension and tension change rate are used to form characteristic tension, where the characteristic tension is as follows: Q3=[D,y3,W] Among them, Q3 refers to characteristic tension.

6. The multifunctional integrated intelligent detection method for drug-related samples according to claim 5, characterized in that: The generating of the sample characteristic identification code based on the characteristic density, characteristic tension and characteristic conductivity includes: The characteristic density, characteristic tension and characteristic conductivity are spliced together to obtain a comprehensive characteristic vector, wherein the comprehensive characteristic vector is as follows: Q4=[q,q2,γ,o1,o2,S,D,y3,W] T Among them, Q4 refers to the comprehensive eigenvector, and T refers to the matrix transpose symbol; Normalizing all components in the comprehensive feature vector to obtain a normalized comprehensive vector; The covariance matrix is constructed based on the normalized integrated vector, where the covariance matrix is as follows: Among them, F refers to the covariance matrix, F1 refers to the normalized integrated vector, Point to the multiplication symbol; Performing eigenvalue decomposition on the covariance matrix to obtain a decomposition eigenvalue group and a decomposition eigenvector group, wherein the decomposition eigenvalues correspond to the decomposition eigenvectors in one-to-one correspondence; Extracting a first eigenvalue, a second eigenvalue, and a third eigenvalue from the decomposed eigenvalue group, and matching corresponding first eigenvectors, second eigenvectors, and third eigenvectors from the decomposed eigenvector group according to the first eigenvalue, the second eigenvalue, and the third eigenvalue, wherein the first eigenvector corresponds to the first eigenvalue, the second eigenvector corresponds to the second eigenvalue, and the third eigenvector corresponds to the third eigenvalue; Constructing a transformation matrix based on the first eigenvector, the second eigenvector, and the third eigenvector, wherein the transformation matrix is a 9×3 matrix, the first eigenvector is the vector in the first column of the transformation matrix, the second eigenvector is the vector in the second column of the transformation matrix, and the third eigenvector is the vector in the third column of the transformation matrix; Calculating a dimensionality reduction vector using the transformation matrix and the normalized integrated vector; Generate a sample feature identification code based on the dimensionality reduction vector.

7. The multifunctional integrated intelligent detection method for drug-related samples according to claim 6, characterized in that: The calculation formula of the dimensionality reduction vector is as follows: Among them, Q5 refers to the dimensionality reduction vector and Q6 refers to the transformation matrix.

8. The multifunctional integrated intelligent detection method for drug-related samples according to claim 7, characterized in that: Generating a sample feature identification code according to the dimensionality reduction vector includes: Performing inverse normalization on the dimension-reduced vector to obtain a first inverse normalization value, a second inverse normalization value, and a third inverse normalization value, and setting a first inverse normalization parameter, a second inverse normalization parameter, and a third inverse normalization parameter; Constructing a mapping rule, wherein the mapping rule consists of a first rule, a second rule, a third rule, a first regression parameter, a second regression parameter, and a third regression parameter, wherein the first rule is: first regression parameter + first regression value, the second rule is: second regression parameter + second regression value, and the third rule is: third regression parameter + third regression value; A sample feature identification code is generated based on the mapping rule, the first inverse value, the second inverse value, the third inverse value, the first inverse parameter, the second inverse parameter, and the third inverse parameter, wherein the sample feature identification code is as follows: V=[MD+z1,ZL+z2,DD+z3] Among them, V refers to the sample feature identification code, MD refers to the first regression parameter, z1 refers to the first regression value, ZL refers to the second regression parameter, z2 refers to the second regression value, DD refers to the third regression parameter, and z3 refers to the third regression value.

9. The multifunctional integrated intelligent detection method for drug-related samples according to claim 8, characterized in that: The determination based on the chromaticity difference value set and the preset chromaticity threshold value to obtain the determination result includes: Extracting chroma difference values from the chroma difference value set in sequence, and comparing the extracted chroma difference values with a chroma threshold; When the chromaticity difference values are all less than the chromaticity threshold, the test sample is confirmed as a preset negative sample; When the chromaticity difference is less than the chromaticity threshold, the test sample is confirmed as a preset positive sample, wherein the determination result is that the test sample is a negative sample or the test sample is a positive sample.

10. A multifunctional integrated intelligent drug-related sample detection system, characterized in that: The system comprises: An identity authentication module, configured to receive a sample detection instruction and activate a sample detection unit based on the sample detection instruction, wherein the sample detection unit includes: a centrifugal detection unit, a tension detection unit, an identity recognition unit, and a conductivity detection unit; Performing identity recognition using the identity recognition unit to obtain identification information, wherein the identification information includes: whether the authentication is passed or not; an authentication processing module, configured to return to the above-mentioned step of performing identity identification using the identity identification unit when the identification information fails the authentication; When the identification information is authenticated, a drug-related sample to be tested is obtained, and a comprehensive test is performed on the drug-related sample to be tested based on the centrifugal detection unit, the tension detection unit, and the conductivity detection unit to obtain the centrifugal sample, characteristic density, characteristic tension, and characteristic conductivity; a chromaticity detection module, configured to generate a sample characteristic identification code based on the characteristic density, characteristic tension, and characteristic conductivity; Using a pre-built robotic arm to extract a test sample from a centrifuged sample to obtain a test card, and using the robotic arm to fix the test card to a pre-built card positioning area to obtain a fixed test card; Dropping the test sample into the fixed test card, and testing the test sample based on a preset duration and the test card to obtain a set of test colorimetric values; A data identification module is used to sequentially extract detection chromaticity values from the detection chromaticity value set, calculate chromaticity differences using the extracted detection chromaticity values and a preset standard chromaticity, and collect the chromaticity differences to obtain a chromaticity difference value set; A judgment is made based on the chromaticity difference value set and a preset chromaticity threshold to obtain a judgment result, and the judgment result is combined with the sample feature identification code to obtain identification judgment data.

Images