Electrochemical sensor-based current prediction method and system, concentration determination method

Abstract

The application relates to the technical field of biomedical detection, and discloses a current prediction method and system based on an electrochemical sensor and a concentration determination method. The prediction method comprises the following steps: acquiring a current sequence of a target analyte, the current sequence being in an electrochemical reaction process; judging whether the current sequence is abnormal; and in the case that it is determined that the current sequence is abnormal, determining a predicted current value based on a current value corresponding to a preset characteristic position and a pre-constructed current prediction model. The application discards the data processing mode of traditional smoothing filtering, retains original sampling data and real signal characteristics throughout the whole process, and does not cause effective information loss. After it is confirmed that the current sequence is abnormal, a distorted and distorted measured end-point current is no longer used, but a pre-selected and undisturbed current value of the preset characteristic position is relied on, a standard end-point current is accurately predicted through a current prediction model, the end-point current is corrected, and the accuracy and stability of a subsequent target analyte concentration detection result are significantly improved.

Description

Technical Field

[0001] This invention relates to the field of biomedical detection technology, specifically to a current prediction method and system based on electrochemical sensors, and a concentration determination method. Background Technology

[0002] Electrochemical biosensors combine biorecognition materials with electrochemical detection technology, utilizing the specific recognition between biomolecules to convert reaction signals into electrical signals, thereby enabling qualitative or quantitative detection of target analytes.

[0003] When electrochemical biosensors detect target analytes, their output current signals typically exhibit a monotonically decreasing trend over time. However, in real-world detection scenarios, factors such as environmental interference, complex sample matrices, electrode surface contamination, and transient electrical noise can cause the acquired current curve to exhibit localized abnormal increases or non-monotonic changes, leading to significant deviations in the target analyte concentration calculations. Traditional signal processing methods often rely on filtering or smoothing techniques to correct abnormal fluctuations in the current curve, but this can easily damage the original signal characteristics, causing distortion of key current parameters used for concentration calculations, ultimately resulting in large deviations and insufficient accuracy in the target analyte concentration detection results. Summary of the Invention

[0004] This invention provides a current prediction method and system based on electrochemical sensors, as well as a concentration determination method, to solve the problem in the prior art that it is difficult to effectively identify current curve anomalies and perform endpoint current correction while preserving the true signal characteristics.

[0005] In a first aspect, the present invention provides a current prediction method based on an electrochemical sensor, the method comprising: The current sequence of the target analyte is obtained. The current sequence is a discrete current value sequence collected at preset time intervals and periods during the electrochemical reaction. Determine if the current sequence is abnormal; this includes: according to the acquisition time sequence of the current sequence, when the current value of the preceding acquisition point is less than the current value of the adjacent subsequent acquisition point for the first time, the current sequence is determined to be abnormal; When an anomaly in the current sequence is determined, the predicted current value is determined based on the current value corresponding to the preset feature location and the pre-built current prediction model.

[0006] The current prediction method provided by this invention detects monotonicity anomalies in current sequences in real time. When an abnormal signal that violates the normal decay law is identified, the current prediction model directly predicts the endpoint current based on the current value corresponding to a preset feature position. This invention abandons the traditional data processing method of smoothing filtering, preserving the original sampled data and true signal characteristics throughout the process, without causing the loss of effective information. After confirming that an anomaly has occurred in the current sequence, instead of using the distorted measured endpoint current, it relies on the pre-selected, undisturbed current value at a preset feature position to accurately predict the standard endpoint current through the current prediction model, thereby achieving endpoint current correction and significantly improving the accuracy and stability of subsequent target analyte concentration detection results.

[0007] In one optional implementation, the current sequence is determined to be normal when the current values ​​of all preceding acquisition points are greater than or equal to the current values ​​of adjacent subsequent acquisition points.

[0008] In this embodiment, the first occurrence of the preceding current being less than the following current is used as the criterion for anomaly determination. This allows for the accurate capture of the earliest distortion node in the timing current and the early identification of signal anomalies.

[0009] In one alternative implementation, the preset feature locations correspond to the feature locations collected when constructing the current prediction model.

[0010] In one optional implementation, the preset feature position is located before the abnormal acquisition point, and the preset feature position is selected from the range of preset acquisition points, with the end of the range of preset acquisition points being the endpoint acquisition point; the endpoint acquisition point is the endpoint acquisition point corresponding to the current sequence.

[0011] In this embodiment, the preset feature position is the preceding acquisition point of the abnormal acquisition point and is located within the preset acquisition point range. This ensures that the selected current data is before the signal abnormality occurs, so that the acquired current data is not contaminated by the distorted signal and is real and valid data. Moreover, the two are close in time and the current change trend is highly consistent, which can accurately reflect the latest effective attenuation law. Furthermore, the closer the normal current is to the endpoint, the stronger the correlation with the change trend of the real endpoint current. Using the preset feature point close to the endpoint to predict the endpoint current results in higher prediction accuracy.

[0012] In one optional implementation, if an abnormal sampling point appears before or at the same location as a preset feature position, an abnormal prompt is generated; the abnormal sampling point is the sampling point corresponding to the determination of an abnormal current sequence.

[0013] In one alternative implementation, the current prediction model is obtained by training a first objective function based on a set of historical normal current sequences; This includes: for the same historical normal current sequence in the set of historical normal current sequences, selecting the characteristic current value corresponding to the preset characteristic position as the input of the first objective function and the corresponding endpoint current value as the output of the first objective function.

[0014] In this embodiment, when an anomaly occurs at or before a preset feature position, a timely error warning is issued, which can avoid using invalid data that has been interfered with in the prediction and ensure the accuracy of the prediction results from the source.

[0015] Secondly, the present invention provides a concentration determination method based on an electrochemical sensor, the method comprising: The current sequence of the target analyte is obtained. The current sequence is a discrete current value sequence collected at preset time intervals and periods during the electrochemical reaction. Based on the first aspect above or any corresponding embodiment of the current prediction method based on electrochemical sensors, it is determined whether the current sequence is abnormal. If the current sequence is abnormal, the predicted current value is determined according to the current prediction method, and the predicted current value is used as the target current value. If the current sequence is within the normal range, then the target current value is taken as the current value at the end of the current sequence. The target current value is input into a pre-built concentration calculation model to determine the concentration of the target analyte.

[0016] In one alternative implementation, the concentration calculation model is obtained by fitting a second objective function based on standard sample data; wherein, the standard sample data includes the endpoint current value and concentration value of the current sequence of the standard sample.

[0017] The concentration determination method based on electrochemical sensors provided by this invention first systematically collects discrete current data throughout the entire electrochemical reaction process, then determines whether there are temporal anomalies in the current sequence, and selects the predicted current value or the measured endpoint current value as the effective target current based on the determination result. Finally, it substitutes the current into the concentration model to complete the concentration calculation. This method can directly use measured data to ensure the efficiency of concentration calculation when the signal is normal, and can also rely on reliable characteristic data to complete the endpoint current correction when the signal is abnormal, avoiding the calculation error caused by abnormal current. The entire process does not require modification of the original acquisition signal. Under the premise of ensuring the authenticity of the data, it significantly improves the accuracy and stability of the target analyte concentration detection results in complex environments.

[0018] Thirdly, the present invention provides a current prediction system based on an electrochemical sensor, the system comprising: The current acquisition module is used to acquire the current sequence of the target analyte. The current sequence is a discrete current value sequence acquired at preset time intervals and periods during the electrochemical reaction process. The anomaly detection module is used to determine whether the current sequence is abnormal. This includes: according to the acquisition timing of the current sequence, when the current value of the preceding acquisition point is less than the current value of the adjacent subsequent acquisition point for the first time, the current sequence is determined to be abnormal. The prediction compensation module is used to determine the predicted current value based on the current value corresponding to the preset feature position and the pre-built current prediction model when the current sequence is determined to be abnormal.

[0019] Fourthly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the current prediction method based on an electrochemical sensor as described in the first aspect or any corresponding embodiment thereof.

[0020] Fifthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the current prediction method based on an electrochemical sensor according to the first aspect or any corresponding embodiment described above.

[0021] In a sixth aspect, the present invention provides a computer program product, including computer instructions for causing a computer to execute the current prediction method based on an electrochemical sensor according to the first aspect or any corresponding embodiment described above.

[0022] It should be noted that, since the current prediction system based on electrochemical sensors provided by this invention, the electronic device, the computer-readable storage medium, and the computer program product correspond to the current prediction method based on electrochemical sensors described above, the beneficial effects of the current prediction device, electronic device, computer-readable storage medium, and computer program product based on electrochemical sensors can be found in the description of the corresponding beneficial effects of the current prediction method based on electrochemical sensors above, and will not be repeated here. Attached Figure Description

[0023] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0024] Figure 1 This is a schematic flowchart of a current prediction method based on an electrochemical sensor according to an embodiment of the present invention; Figure 2 This is a schematic diagram comparing current curves according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the concentration determination based on an electrochemical sensor according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the prediction comparison results according to an embodiment of the present invention; Figure 5 This is a structural block diagram of a current prediction system based on an electrochemical sensor according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0027] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0028] Traditional smoothing filtering techniques, when abnormal distortion occurs in the current signal, weaken abnormal fluctuations by smoothing out the original sampling data. However, this not only easily tampers with the true electrochemical response signal, causing the signal itself to be distorted, but also causes the final measured endpoint current value to deviate from the actual operating conditions, seriously reducing the accuracy of the endpoint current value and thus affecting the subsequent concentration detection results.

[0029] In view of this, according to an embodiment of the present invention, a current prediction method based on an electrochemical sensor is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0030] This embodiment provides a current prediction method based on electrochemical sensors, which can be used in servers, terminals, mobile terminals, etc. Figure 1 This is a flowchart of a current prediction method based on an electrochemical sensor according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps: Step S101: Obtain the current sequence of the target analyte. The current sequence is a discrete current value sequence collected at preset time intervals and periods during the electrochemical reaction process.

[0031] The target analyte is the object to be quantitatively / qualitatively analyzed in the detection process of the electrochemical biosensor. That is, it is a substance that can specifically react with the biorecognition elements (such as enzymes, antibodies, nucleic acid aptamers, etc.) on the sensor and produce a detectable electrochemical signal (such as current).

[0032] Specifically, the target analyte can be immersed in an electrochemical biosensor equipped with a biorecognition sensing element. Under a set constant detection potential, the biorecognition components inside the sensor undergo a specific biochemical reaction with the target analyte, causing electron transfer on the electrode surface and generating a continuously changing response current. An external electrochemical detection circuit then collects real-time current values ​​corresponding to different reaction moments at preset fixed time intervals (e.g., once every 0.1 seconds) and preset collection periods (e.g., collecting data at 100 time points). These values ​​are then stored and organized chronologically, ultimately forming a complete discrete current sequence that dynamically changes with reaction time and is arranged sequentially, such as a current sequence. .

[0033] In this embodiment, the current sequence can be a complete current sequence that has already been acquired, or a partial current sequence acquired in real time.

[0034] Step S102: Determine if the current sequence is abnormal.

[0035] Anomalies in a current sequence can be determined by comparing the current difference between two adjacent sampling points. Specifically, the current values ​​of each group of adjacent sampling points are compared sequentially according to the sampling time sequence. If the current value of a preceding sampling point is less than the current value of a subsequent sampling point, then... ,in If the time interval is [not specified], it indicates a reverse current rise, violating the normal monotonic decay law of the response, and the current sequence is judged to be abnormal; if the current values ​​of all preceding acquisition points are greater than or equal to the current values ​​of adjacent subsequent acquisition points, i.e. If so, the current sequence is considered normal. (Refer to...) Figure 2 The diagram shown is a comparison of the normal current curve and the abnormal current curve.

[0036] In some optional implementations, according to the acquisition timing of the current sequence, when the current value of the preceding acquisition point is less than the current value of the adjacent subsequent acquisition point for the first time, the current sequence is determined to be abnormal.

[0037] In this embodiment, the first occurrence of the preceding current being less than the following current is used as the criterion for anomaly determination. This allows for the accurate capture of the earliest distortion node in the timing current and the early identification of signal anomalies.

[0038] If the current sequence is a complete current sequence that has already been collected, the analysis can continue even after an anomaly is first detected, until the current sequence analysis is complete. If the current sequence is a partial current sequence acquired in real time, the analysis can continue even after an anomaly is first detected, until the current sequence acquisition and analysis are complete. This approach allows for a comprehensive understanding of the distribution of signal anomalies throughout the entire time period and ensures the complete retention of all sampled data, providing robust data support for subsequent source tracing analysis and current prediction model calibration.

[0039] Step S103: In the case of determining that the current sequence is abnormal, the predicted current value is determined based on the current value corresponding to the preset feature position and the pre-built current prediction model.

[0040] In this embodiment, the preset feature locations correspond to the feature locations collected during the construction of the current prediction model. That is, during the training and determination of the current prediction model, the current values ​​at the selected collection points (preset feature locations) are used to determine the actual predicted current value; these are the current values ​​at the same collection points, i.e., the current values ​​at the preset feature locations. Then, the current values ​​at the preset feature locations are substituted into the pre-constructed current prediction model to obtain the predicted current value. This predicted current value is the endpoint current of the predicted current sequence.

[0041] Before constructing the current prediction model, tests are conducted under different abnormal conditions to collect and analyze a large amount of test current data, determining the distribution of different anomalies. Then, based on the anomaly distribution, sampling points less likely to generate anomalies are selected, and these selected sampling points are used as preset feature locations.

[0042] When training the current prediction model, it can be trained based on a large set of historical normal current sequences. That is, the characteristic current value corresponding to the preset characteristic position in the same normal current sequence is used as input, and the terminal current value corresponding to the sequence is used as output to fit a quadratic polynomial model.

[0043] The current prediction model in this embodiment can also be obtained through machine learning regression training. That is, models such as random forest, support vector regression, and lightweight neural networks are used, with the current at the previous normal sampling points as input, to train the model to predict the final current (predicted current value). In this case, the preset feature location is the normal sampling point before the current sequence abnormality occurs.

[0044] The current prediction method provided by this invention detects monotonicity anomalies in current sequences in real time. When an abnormal signal that violates the normal decay law is identified, the current prediction model directly predicts the endpoint current based on the current value corresponding to a preset feature position. This invention abandons the traditional data processing method of smoothing filtering, preserving the original sampled data and true signal characteristics throughout the process, without causing the loss of effective information. After confirming that an anomaly has occurred in the current sequence, instead of using the distorted measured endpoint current, it relies on the pre-selected, undisturbed current value at a preset feature position to accurately predict the standard endpoint current through the current prediction model, thereby achieving endpoint current correction and significantly improving the accuracy and stability of subsequent target analyte concentration detection results.

[0045] In some optional implementations, the preset feature position is located before the abnormal acquisition point, and the preset feature position is selected from the preset acquisition point range before the endpoint acquisition point, with the end of the preset acquisition point range being the endpoint acquisition point; the endpoint acquisition point is the endpoint acquisition point corresponding to the current sequence.

[0046] In this embodiment, the preset feature location is preferably a preceding acquisition point adjacent to the abnormal acquisition point and located within the preset acquisition point range. This ensures that the selected current data is before the signal abnormality occurs, so that the acquired current data is not contaminated by distorted signals and is real and valid data. Moreover, the two are close in time and the current change trend is highly consistent, which can accurately reflect the latest effective attenuation law. Furthermore, the closer the normal current is to the endpoint, the stronger the correlation with the change trend of the real endpoint current. Using the preset feature point close to the endpoint to predict the endpoint current results in higher prediction accuracy.

[0047] In this embodiment, the abnormal acquisition points can be those obtained through testing under different abnormal conditions before training the current prediction model, or they can be the abnormal acquisition points determined during the actual current sequence abnormality judgment.

[0048] In some optional implementations, if an abnormal sampling point appears before or at the same location as a preset feature position, an abnormal prompt is generated; the abnormal sampling point is the sampling point corresponding to the determination of an abnormal current sequence.

[0049] During the early R&D and calibration phase, researchers will construct test scenarios for different types of abnormal interference, collect massive amounts of measured current sequence data under various abnormal causes, and conduct statistical analysis to determine the distribution of various abnormal signals. Based on the abnormal distribution, preset feature locations will be selected. If the abnormal acquisition point appears before or at the same preset feature location, it indicates that current distortion has already occurred before or at the preset feature location, making it impossible to obtain clean, normal, and effective current data, and an abnormal error will be triggered. If the abnormal acquisition point appears after the preset feature location, it means that complete and normal current data has been acquired at the preset feature location, with only subsequent timing signal distortion. Current prediction can then be performed based on the effective feature data to complete the correction of the endpoint current.

[0050] In this embodiment, when an anomaly occurs at or before a preset feature position, a timely error warning is issued, which can avoid using invalid data that has been interfered with in the prediction and ensure the accuracy of the prediction results from the source.

[0051] In some alternative implementations, the current prediction model is obtained by training a first objective function based on a set of historical normal current sequences; This includes: for the same historical normal current sequence in the set of historical normal current sequences, selecting the characteristic current value corresponding to the preset characteristic position as the input of the first objective function and the corresponding endpoint current value as the output of the first objective function.

[0052] In this embodiment, the first objective function is a quadratic polynomial function, namely: ; in, To predict the current value, The current value is the value corresponding to the preset feature position, and a, b, and c are weighting parameters.

[0053] The following provides a complete embodiment.

[0054] In this embodiment, a large amount of current sequence data of normal responses was collected, and the current corresponding to the feature positions was extracted. (For example, the current at the 10th time point) ) and corresponding endpoint current (For example, the current at the 100th time point) ).

[0055] Current corresponding to the characteristic position As input, the endpoint current under normal reaction conditions. For the output, fit a quadratic polynomial: ; The weight parameters are obtained through fitting: , , .

[0056] Then, calculate the current difference between adjacent time intervals, for example: ; If any If so, the current sequence is determined to be abnormal.

[0057] In this embodiment, the current sequence anomaly is determined by the first objective function. If the anomaly flag is 1, prediction compensation is performed, i.e., the characteristic current is taken. Substituting into the following prediction model, we obtain the predicted current value: .

[0058] This invention detects the monotonicity anomaly of the current curve in real time and uses a prediction model trained on historical data for intelligent compensation. It abandons the traditional method of filtering and correcting the original data, fully preserves the real sampling signal, and effectively solves the problem of large error in the measured endpoint current under complex environments. This improves the robustness and accuracy of electrochemical sensors under complex environments, as well as the accuracy and reliability of subsequent target substance concentration detection.

[0059] This embodiment provides a concentration determination method based on an electrochemical sensor, which can be used in servers, terminals, mobile terminals, etc. Figure 3 This is a flowchart of concentration determination based on an electrochemical sensor according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps: Step S201: Obtain the current sequence of the target analyte. The current sequence is a discrete current value sequence collected at preset time intervals and periods during the electrochemical reaction. For details, please refer to [link to relevant documentation]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0060] Step S202: Based on the current prediction method based on electrochemical sensors in the above embodiments, determine whether the current sequence is abnormal. For details, please refer to the embodiments corresponding to the current prediction method based on electrochemical sensors, which will not be repeated here.

[0061] Step S203: If the current sequence is abnormal, determine the predicted current value according to the current prediction method, and use the predicted current value as the target current value. For details, please refer to the corresponding embodiment of the current prediction method based on electrochemical sensors, which will not be repeated here.

[0062] Step S204: If the current sequence is normal, the target current value is taken as the end current value of the current sequence.

[0063] Step S205: Input the target current value into the pre-built concentration calculation model to determine the concentration of the target analyte.

[0064] In some alternative implementations, the concentration calculation model is obtained by fitting a second objective function based on standard sample data; wherein, the standard sample data includes the endpoint current value and concentration value of the current sequence of the standard sample.

[0065] In this embodiment, the second objective function can be a quadratic polynomial function, that is: ; in, For the concentration of the target analyte, Let p be the endpoint current, and q and r be weighting parameters.

[0066] The following provides a complete embodiment.

[0067] In this embodiment, a large amount of current sequence data of normal responses from standard samples were collected, and the corresponding endpoint current was extracted. (For example, the current at the 100th time point) ), and the concentration of each standard sample.

[0068] With the endpoint current Given the input and the known concentration as the output, fit a quadratic polynomial: ; The fitted weight parameters are: , , ; Predict the current value Substituting into the following concentration calculation model, the predicted concentration is obtained: .

[0069] If the current sequence is normal (abnormal flag is 0), then the endpoint current can be used directly. Substitute the values ​​into the concentration calculation model to calculate the concentration.

[0070] Reference Figure 4 As shown, the deviations (columns CZ and DE) of the normal algorithm output (CY column) and the predicted algorithm output (DD column) relative to the true concentration (DA column) are compared. Experimental results show that, under abnormal current curve conditions, the predictive compensation algorithm significantly reduces the concentration calculation deviation and improves the stability of the measurement results.

[0071] The concentration determination method based on electrochemical sensors provided by this invention first systematically collects discrete current data throughout the entire electrochemical reaction process, then determines whether there are temporal anomalies in the current sequence, and selects the predicted current value or the measured endpoint current value as the effective target current based on the determination result. Finally, it substitutes the current into the concentration model to complete the concentration calculation. This method can directly use measured data to ensure the efficiency of concentration calculation when the signal is normal, and can also rely on reliable characteristic data to complete the endpoint current correction when the signal is abnormal, avoiding the calculation error caused by abnormal current. The entire process does not require modification of the original acquisition signal. Under the premise of ensuring the authenticity of the data, it significantly improves the accuracy and stability of the target analyte concentration detection results in complex environments.

[0072] This embodiment also provides a current prediction system based on an electrochemical sensor, which is used to implement the above-described embodiments and preferred implementations of the current prediction method based on an electrochemical sensor. Details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0073] This embodiment provides a current prediction system based on an electrochemical sensor, such as... Figure 5 As shown, it includes: The current acquisition module 501 is used to acquire the current sequence of the target analyte. The current sequence is a discrete current value sequence acquired at preset time intervals and periods during the electrochemical reaction process. Anomaly detection module 502 is used to determine whether the current sequence is abnormal; The prediction compensation module 503 is used to determine the predicted current value based on the current value corresponding to the preset feature position and the pre-built current prediction model when the current sequence is determined to be abnormal.

[0074] In one optional implementation, the anomaly detection module 502 is specifically used for: Based on the current difference between two adjacent acquisition points in the current sequence, it is determined whether the current sequence is abnormal. This includes: according to the acquisition sequence of the current sequence, when the current value of the preceding acquisition point is less than the current value of the subsequent acquisition point for the first time, the current sequence is determined to be abnormal; when the current values ​​of all preceding acquisition points are greater than or equal to the current values ​​of all subsequent acquisition points, the current sequence is determined to be normal.

[0075] In one alternative implementation, the preset feature locations correspond to the feature locations collected when constructing the current prediction model.

[0076] In one optional implementation, the preset feature position is located before the abnormal acquisition point, and the preset feature position is selected from the range of preset acquisition points, with the end of the range of preset acquisition points being the endpoint acquisition point; the endpoint acquisition point is the endpoint acquisition point corresponding to the current sequence.

[0077] In one alternative implementation, the system further includes: The early warning module is used to generate an abnormal prompt if an abnormal sampling point appears before or at the same location as the preset feature position; the abnormal sampling point is the sampling point corresponding to the current sequence when it is determined to be abnormal.

[0078] In one optional implementation, the current prediction model is obtained by training a first objective function based on a set of historical normal current sequences; the system further includes: The module is used to select the characteristic current value corresponding to the preset characteristic position as the input of the first objective function and the corresponding endpoint current value as the output of the first objective function for the same historical normal current sequence in the set of historical normal current sequences.

[0079] The current prediction system based on electrochemical sensors provided in this invention can execute the current prediction method based on electrochemical sensors provided in any embodiment of this invention, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the various modules and units described above are the same as in the corresponding embodiments described above, and will not be repeated here.

[0080] This embodiment also provides a concentration determination system based on an electrochemical sensor, which is used to implement the above-described concentration determination method based on an electrochemical sensor, as well as its preferred embodiments. Details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0081] This embodiment provides a concentration determination system based on an electrochemical sensor, including: The acquisition module is used to acquire the current sequence of the target analyte. The current sequence is a discrete current value sequence collected at preset time intervals and periods during the electrochemical reaction process. The current value determination module is used to determine whether the current sequence is abnormal based on the current prediction method of the electrochemical sensor. If the current sequence is abnormal, the predicted current value is determined according to the current prediction method and used as the target current value. If the current sequence is normal, the end current value of the current sequence is used as the target current value. The concentration determination module is used to input the target current value into a pre-built concentration calculation model to determine the concentration of the target analyte.

[0082] In one alternative implementation, the concentration calculation model is obtained by fitting a second objective function based on standard sample data; wherein, the standard sample data includes the endpoint current value and concentration value of the current sequence of the standard sample.

[0083] The concentration determination system based on an electrochemical sensor provided in this embodiment of the invention can execute the concentration determination method based on an electrochemical sensor provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the various modules and units described above are the same as in the corresponding embodiments described above, and will not be repeated here.

[0084] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0085] The following is a detailed reference. Figure 6 This diagram illustrates a suitable structural design for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 601, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 602 or a program loaded from memory 608 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of the electronic device. The processor 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0086] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0087] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a memory 608, or installed from a ROM 602. When the computer program is executed by the processor 601, it performs the functions defined in the current prediction method based on an electrochemical sensor according to embodiments of the present invention.

[0088] Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.

[0089] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the current prediction method based on an electrochemical sensor shown in the above embodiments is implemented.

[0090] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0091] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A current prediction method based on an electrochemical sensor, characterized in that, The method includes: Obtain the current sequence of the target analyte, wherein the current sequence is a discrete current value sequence collected at preset time intervals and periods during the electrochemical reaction process; Determining whether the current sequence is abnormal includes: according to the acquisition timing of the current sequence, when the current value of the preceding acquisition point is less than the current value of the adjacent subsequent acquisition point for the first time, the current sequence is determined to be abnormal; If the current sequence is determined to be abnormal, a predicted current value is determined based on the current value corresponding to a preset feature location and a pre-built current prediction model; the preset feature location corresponds to the feature location collected when the current prediction model is built.

2. The method according to claim 1, characterized in that, The current sequence is considered normal when the current values ​​of all preceding acquisition points are greater than or equal to the current values ​​of adjacent subsequent acquisition points.

3. The method according to claim 1, characterized in that, The preset feature position is located before the abnormal acquisition point, and the preset feature position is selected from the range of preset acquisition points, with the end of the range of preset acquisition points being the endpoint acquisition point; the endpoint acquisition point is the endpoint acquisition point corresponding to the current sequence.

4. The method according to claim 1, characterized in that, If an abnormal sampling point appears before or at the same location as the preset feature position, an abnormality prompt is generated; the abnormal sampling point is the sampling point corresponding to the determination that the current sequence is abnormal.

5. The method according to claim 1, characterized in that, The current prediction model is obtained by training a first objective function based on a set of historical normal current sequences. This includes: for the same historical normal current sequence in the set of historical normal current sequences, selecting the feature current value corresponding to the preset feature position as the input of the first objective function and the corresponding endpoint current value as the output of the first objective function.

6. A concentration determination method based on an electrochemical sensor, characterized in that, The method includes: Obtain the current sequence of the target analyte, wherein the current sequence is a discrete current value sequence collected at preset time intervals and periods during the electrochemical reaction process; Based on the current prediction method based on electrochemical sensors according to any one of claims 1 to 5, determine whether the current sequence is abnormal; If the current sequence is abnormal, the predicted current value is determined according to the current prediction method, and the predicted current value is used as the target current value. If the current sequence is within the normal range, then the target current value is taken as the current value at the end of the current sequence. The target current value is input into a pre-built concentration calculation model to determine the concentration of the target analyte.

7. The method according to claim 6, characterized in that, The concentration calculation model is obtained by fitting a second objective function based on standard sample data; wherein, the standard sample data includes the endpoint current value and concentration value of the current sequence of the standard sample.

8. A current prediction system based on an electrochemical sensor, characterized in that, The system includes: The current acquisition module is used to acquire the current sequence of the target analyte, which is a discrete current value sequence acquired at preset time intervals and periods during the electrochemical reaction process. An anomaly detection module is used to determine whether the current sequence is abnormal; including: according to the acquisition timing of the current sequence, when the current value of the preceding acquisition point is less than the current value of the adjacent subsequent acquisition point for the first time, the current sequence is determined to be abnormal; The prediction compensation module is used to determine the predicted current value based on the current value corresponding to the preset feature position and the pre-built current prediction model when the current sequence is determined to be abnormal; the preset feature position corresponds to the feature position collected when the current prediction model is constructed.

Images