Mapping data determination method, apparatus, computer device and system

Abstract

The application relates to a mapping data determination method, device, computer equipment and system. The method comprises the following steps: acquiring template heartbeat data and actual heartbeat data, wherein the template heartbeat data comprises template heartbeat signals corresponding to at least two leads respectively, and the actual heartbeat data comprises actual heartbeat signals corresponding to the leads respectively; for each lead, a waveform similarity value between the actual heartbeat signal corresponding to the lead and the template heartbeat signal corresponding to the lead is determined; according to the template heartbeat signals corresponding to the leads and the actual heartbeat signals corresponding to the leads, weights corresponding to the waveform similarities are determined; according to the weights and the waveform similarity values, an overall similarity value between the template heartbeat data and the actual heartbeat data is obtained; in the case that the overall similarity value is greater than or equal to a preset similarity threshold, the actual heartbeat data is determined as valid mapping data. The method can improve the quality of the mapping data.

Description

Technical Field

[0001] This application relates to the field of cardiac electrophysiological mapping technology, and in particular to a method, apparatus, computer equipment, and system for determining mapping data. Background Technology

[0002] Cardiac electrophysiology mapping (CEM) is a core tool for modern diagnosis and interventional treatment of arrhythmias. It mainly collects electrical activity signals from multiple parts of the heart to provide precise localization for interventional treatments such as ablation.

[0003] Currently, the main approach is to collect mapping data for cardiac electrophysiological mapping based on the heartbeat morphology matching mechanism. This involves pre-collecting a template heartbeat for a certain lead and comparing the actual heartbeat in that lead with the template heartbeat. Only when the similarity meets the standard is the actual heartbeat data used as the mapping data.

[0004] However, using only heart rate data from a single lead as mapping data while ignoring heart rate data from other leads reduces the accuracy of the mapping data, thus affecting the precision of the 3D mapping system. Summary of the Invention

[0005] In some embodiments, this application provides a method for determining calibration data, the method comprising:

[0006] Acquire template heartbeat data and actual heartbeat data, wherein the template heartbeat data includes template heartbeat signals corresponding to at least two leads, and the actual heartbeat data includes actual heartbeat signals corresponding to each lead.

[0007] For each lead, determine the waveform similarity value between the actual heartbeat signal corresponding to the lead and the template heartbeat signal corresponding to the lead;

[0008] Based on the template heartbeat signal and the actual heartbeat signal corresponding to each lead, the weights of each waveform similarity are determined, where the weights are positively correlated with the ability of the actual heartbeat signal to represent cardiac electrical activity.

[0009] Based on each weight and each waveform similarity value, the overall similarity value between the template heartbeat data and the actual heartbeat data is obtained;

[0010] If the overall similarity value is greater than or equal to the preset similarity threshold, the actual heartbeat data will be determined as valid labeled data.

[0011] In this implementation, template heartbeat data and actual heartbeat data of the target object are acquired. The template heartbeat data includes template heartbeat signals from at least two leads, and the actual heartbeat data includes actual heartbeat signals from each lead. Then, for each lead, a waveform similarity value between the actual heartbeat signal and the corresponding template heartbeat signal is determined, as well as a weight for the waveform similarity of each lead. The weight is positively correlated with the ability of the actual heartbeat signal to represent cardiac electrical activity. Based on the weights and waveform similarity values, an overall similarity value between the template heartbeat data and the actual heartbeat data is obtained. This application considers that in real electrocardiogram (ECG) signals, the ability of actual heartbeat signals acquired from different leads to represent cardiac electrical activity varies significantly. Therefore, a weight is assigned to the waveform similarity value corresponding to each lead. The weight is positively correlated with the ability to represent cardiac electrical activity, thereby adjusting the influence of actual heartbeat signals acquired from different leads on the overall similarity value. This allows the actual heartbeat signal, which has a stronger ability to represent cardiac electrical activity, to have a greater impact, thus improving the rationality and accuracy of the overall similarity value and helping to improve the accuracy of matching between actual and template heartbeats. Furthermore, if the overall similarity value is greater than or equal to the preset similarity threshold, the actual heartbeat data is determined as valid mapping data. This overall similarity value, which can more accurately reflect the true electrical activity characteristics of the heart, serves as the criterion for whether the actual heartbeat data can be used as valid mapping data, which helps to improve the data quality of the mapping data.

[0012] In some embodiments, this application also provides a calibration data determination apparatus, the apparatus comprising:

[0013] The data acquisition module is used to acquire template heartbeat data and actual heartbeat data, wherein the template heartbeat data includes template heartbeat signals corresponding to at least two leads, and the actual heartbeat data includes actual heartbeat signals corresponding to each lead.

[0014] The similarity determination module is used to determine the waveform similarity value between the actual heartbeat signal corresponding to the lead and the template heartbeat signal corresponding to the lead for each lead.

[0015] The weight determination module is used to determine the weight corresponding to each waveform similarity based on the template heartbeat signal and the actual heartbeat signal corresponding to each lead. The weight is positively correlated with the ability of the actual heartbeat signal to represent cardiac electrical activity.

[0016] The overall calculation module is used to obtain the overall similarity value between the template heartbeat data and the actual heartbeat data based on each weight and the corresponding waveform similarity value;

[0017] The data determination module is used to determine the actual heartbeat data as valid labeled data when the overall similarity value is greater than or equal to a preset similarity threshold.

[0018] In some embodiments, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0019] Acquire template heartbeat data and actual heartbeat data, wherein the template heartbeat data includes template heartbeat signals corresponding to at least two leads, and the actual heartbeat data includes actual heartbeat signals corresponding to each lead.

[0020] For each lead, determine the waveform similarity value between the actual heartbeat signal corresponding to the lead and the template heartbeat signal corresponding to the lead;

[0021] Based on the template heartbeat signal and the actual heartbeat signal corresponding to each lead, the weights of each waveform similarity are determined, where the weights are positively correlated with the ability of the actual heartbeat signal to represent cardiac electrical activity.

[0022] Based on each weight and each waveform similarity value, the overall similarity value between the template heartbeat data and the actual heartbeat data is obtained;

[0023] If the overall similarity value is greater than or equal to the preset similarity threshold, the actual heartbeat data will be determined as valid labeled data.

[0024] In some embodiments, this application also provides a mapping data determination system, which includes an electrocardiogram (ECG) acquisition device and a computer device connected to the ECG acquisition device;

[0025] ECG acquisition equipment is used to collect the actual heartbeat data of a target object and transmit the actual heartbeat data to a computer device;

[0026] A computer device is used to acquire template heartbeat data and actual heartbeat data. The template heartbeat data includes template heartbeat signals corresponding to at least two leads, and the actual heartbeat data includes actual heartbeat signals corresponding to each lead. For each lead, a waveform similarity value is determined between the actual heartbeat signal and the template heartbeat signal corresponding to the lead. Based on the template heartbeat signal and the actual heartbeat signal for each lead, a weight is determined for each waveform similarity, where the weight is positively correlated with the ability of the actual heartbeat signal to represent cardiac electrical activity. Based on each weight and each waveform similarity value, an overall similarity value between the template heartbeat data and the actual heartbeat data is obtained. If the overall similarity value is greater than or equal to a preset similarity threshold, the actual heartbeat data is determined as valid mapping data. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a flowchart illustrating the method for determining calibration data in an embodiment of this application;

[0029] Figure 2 This is a schematic diagram illustrating the scenario of determining the waveform similarity value corresponding to each lead in an embodiment of this application;

[0030] Figure 3 This is a schematic diagram illustrating the scenario for determining the overall similarity value in an embodiment of this application;

[0031] Figure 4 This is a flowchart illustrating a method for determining calibration data in another embodiment of this application;

[0032] Figure 5 This is a schematic diagram illustrating a scenario where actual heartbeat data is offset in an embodiment of this application.

[0033] Figure 6 This is a flowchart illustrating the method for determining calibration data in a specific embodiment of this application;

[0034] Figure 7 This is a structural block diagram of the measurement data determination device in the embodiments of this application;

[0035] Figure 8 This is an internal structural diagram of the computer device in the embodiments of this application;

[0036] Figure 9 This is a system architecture diagram of the calibration data determination system in the embodiments of this application. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0038] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0039] In some exemplary embodiments, such as Figure 1 As shown, a method for determining calibration data is provided, including the following steps S110 to S150. Wherein:

[0040] Step S110: Obtain template heartbeat data and actual heartbeat data, wherein the template heartbeat data includes template heartbeat signals corresponding to at least two leads, and the actual heartbeat data includes actual heartbeat signals corresponding to each lead.

[0041] For example, the template heartbeat data is pre-selected reference heartbeat waveform data, while the actual heartbeat data is the heartbeat waveform data actually collected for the target object. The template heartbeat data includes template heartbeat signals corresponding to at least two leads, and the actual heartbeat data includes the actual heartbeat signals corresponding to each lead. A lead is the cardiac electrical activity on the measurement axis corresponding to that lead, calculated or derived from the voltage difference between two points on the target object's body. It is understood that the spatial azimuth angle of the measurement axis corresponding to different leads is different in space.

[0042] For example, typical heartbeat segments from surface electrocardiogram waveforms can be selected as template heartbeat data, such as QRS complexes with relatively clear waveform characteristics, or a cardiac cycle containing complete electrocardiographic morphological features. Alternatively, data can be acquired from the target object using an electrocardiogram acquisition device to obtain actual heartbeat data. It is understood that the number and type of leads included in the actual heartbeat data are consistent with the number and type of leads in the template heartbeat data. For example, if the template heartbeat data includes template heartbeat signals corresponding to leads I, II, and III, the actual heartbeat data should also include actual heartbeat signals corresponding to leads I, II, and III.

[0043] Step S120: For each lead, determine the waveform similarity value between the actual heartbeat signal corresponding to the lead and the template heartbeat signal corresponding to the lead.

[0044] In some implementations, the waveform similarity value corresponding to each lead is a measure describing the degree of waveform similarity between the actual heartbeat signal and the template heartbeat signal corresponding to that lead.

[0045] For example, time alignment is performed between each template heartbeat signal and its corresponding actual heartbeat signal. This involves aligning the sampling points of the template heartbeat signal with those of the actual heartbeat signal (aligning the i-th sampling point in the template heartbeat signal with the i-th sampling point in the actual heartbeat signal aligns all sampling points). Then, for each lead, after aligning the actual heartbeat signal corresponding to the lead with the template heartbeat signal corresponding to the lead in time, the waveform similarity value between the actual heartbeat signal and the corresponding template heartbeat signal can be calculated. For example, the waveform similarity value can be calculated using metrics describing the degree of similarity, such as the Pearson correlation coefficient, normalized cross-correlation, or Euclidean distance. Taking the Pearson correlation coefficient as an example, the actual amplitude sequence of the actual heartbeat signal and the template amplitude sequence of the template heartbeat signal can be determined. The actual mean amplitude of the actual heartbeat signal can be determined based on the actual amplitude sequence, and the template mean amplitude of the template heartbeat signal can be determined based on the template amplitude sequence. Based on the actual amplitude sequence, template amplitude sequence, actual mean amplitude, and template mean amplitude, the Pearson correlation coefficient between the actual amplitude sequence and the template amplitude sequence is calculated by using a preset Pearson correlation coefficient operation function. The Pearson correlation coefficient is then determined as the waveform similarity value between the actual heartbeat signal and the corresponding template heartbeat signal.

[0046] In some embodiments, determining the waveform similarity value between the actual heartbeat signal corresponding to the lead and the template heartbeat signal corresponding to the lead includes:

[0047] Step S121: Determine the actual amplitude sequence of the actual heartbeat signal and the template amplitude sequence of the template heartbeat signal.

[0048] Step S122: Determine the actual mean amplitude of the actual heartbeat signal based on the actual amplitude sequence, and determine the template mean amplitude of the template heartbeat signal based on the template amplitude sequence.

[0049] Step S123: Based on the actual amplitude sequence, the template amplitude sequence, the average actual amplitude, and the average template amplitude, obtain the waveform similarity value between the actual heartbeat signal and the corresponding template heartbeat signal.

[0050] For example, the actual amplitude sequence is a sequence formed by the amplitudes of each actual sampling point in the actual heartbeat signal, and the template amplitude sequence is a sequence formed by the amplitudes of each actual sampling point in the template heartbeat signal. For instance, the template amplitude sequence is... The corresponding real-time amplitude sequence is , where n represents the number of sampling points involved in the calculation.

[0051] The actual heartbeat signal and the template heartbeat signal can be processed to obtain the actual amplitude sequence of the actual heartbeat signal and the template amplitude sequence of the template heartbeat signal. For example, the amplitudes of each actual sampling point in the actual heartbeat signal are sorted by time to obtain the actual amplitude sequence of the actual heartbeat signal, and the amplitudes of each actual sampling point in the template heartbeat signal are sorted by time to obtain the template amplitude sequence of the template heartbeat signal. Then, the mean of each amplitude in the actual amplitude sequence is calculated to obtain the mean actual amplitude of the actual heartbeat signal, and the mean of each amplitude in the template amplitude sequence is calculated to obtain the mean template amplitude of the template heartbeat signal. Then, based on the actual amplitude sequence, the template amplitude sequence, the mean actual amplitude, and the mean template amplitude, a preset Pearson correlation coefficient operation function is used to calculate the Pearson correlation coefficient between the actual amplitude sequence and the template amplitude sequence, and the Pearson correlation coefficient is determined as the waveform similarity value between the actual heartbeat signal and the corresponding template heartbeat signal. For example, the preset Pearson correlation coefficient operation function can be expressed as follows:

[0052]

[0053] Where ρ is the Pearson correlation coefficient. This represents the i-th amplitude in the actual amplitude sequence. The template amplitude mean of the template heartbeat signal. For the i-th amplitude in the template amplitude sequence, The average amplitude of the actual heartbeat signal is denoted as ρ, and n is the number of sampling points. The Pearson correlation coefficient ρ typically ranges from -1 to 1. When ρ is closer to 1, it indicates that the template heartbeat signal and the actual heartbeat signal under that lead are more similar in waveform shape; when ρ is closer to 0, it indicates that the correlation between the template heartbeat signal and the actual heartbeat signal under that lead is weaker; when ρ is closer to -1, it indicates that the waveform change trends of the template heartbeat signal and the actual heartbeat signal under that lead are opposite.

[0054] like Figure 2 As shown, taking leads I, II, III, aVR, aVL, aVF, V1, V2, V3, V4, V5, and V6 as an example, both the template heartbeat data and the actual heartbeat data include the ECG signals corresponding to these 12 leads. This application calculates the correlation between the template heartbeat signal and the actual heartbeat signal for each lead, thereby obtaining the Pearson correlation coefficient ρ for the 12 leads.

[0055] Step S130: Based on the template heartbeat signal corresponding to each lead and the actual heartbeat signal corresponding to each lead, determine the weight corresponding to each waveform similarity, wherein the weight is positively correlated with the ability of the actual heartbeat signal to represent cardiac electrical activity.

[0056] In practical electrocardiogram (ECG) signal analysis, the ability of ECG signals corresponding to different leads to represent cardiac electrical activity varies significantly. Therefore, the weights corresponding to each waveform similarity can be determined based on the template heartbeat signals and the actual heartbeat signals corresponding to each lead. The weights are positively correlated with the ability of the actual heartbeat signals to represent cardiac electrical activity. For example, actual heartbeat signals with lower amplitudes typically contain fewer effective morphological features and are easily affected by noise, baseline drift, or localized minor fluctuations. Heartbeat signals with higher amplitudes, on the other hand, often have clearer and more stable QRS complexes or cardiac morphological features, and can more effectively reflect the propagation direction and morphological changes of cardiac electrical activity. Therefore, the actual amplitude of the actual heartbeat signals corresponding to each lead and the template amplitude of the template heartbeat signals corresponding to each lead can be obtained. Based on these actual and template amplitudes, the weights corresponding to each waveform similarity can be determined, where the weights are positively correlated with the actual amplitude and / or the template amplitude. In another example, since the ECG signals corresponding to different leads have a relatively fixed ability to represent cardiac electrical activity, in order to improve computational efficiency, the weights corresponding to each waveform similarity can be directly determined. That is, the corresponding lead weight values ​​can be set for different leads in advance, and the lead weight values ​​corresponding to each lead can be determined as the weights of the waveform similarity corresponding to each lead. For example, the correspondence between the amplitude of the template heartbeat signal and the amplitude of the actual heartbeat signal and the weights can be established.

[0057] In some embodiments, the weights corresponding to each waveform similarity are determined based on the template heartbeat signal corresponding to each lead and the actual heartbeat signal corresponding to each lead, including:

[0058] Step S131: Obtain the actual amplitude of the actual heartbeat signal corresponding to each lead, and the template amplitude of the template heartbeat signal corresponding to each lead.

[0059] Step S132: Determine the weight corresponding to each waveform similarity based on each actual amplitude and each template amplitude, wherein the weight is positively correlated with the actual amplitude and / or the template amplitude.

[0060] In some embodiments, the actual amplitude can be the maximum amplitude of each actual sampling point in the actual heartbeat signal, or it can be a representation of the amplitude of the actual heartbeat signal, such as the average amplitude of each actual sampling point or a weighted average amplitude. The template amplitude can be the maximum amplitude of each template sampling point in the template heartbeat signal, or it can be a representation of the amplitude of the template heartbeat signal, such as the average amplitude of each template sampling point or a weighted average amplitude.

[0061] Although the ability of ECG signals corresponding to different leads to represent cardiac electrical activity is relatively fixed, in actual use, factors such as individual differences and electrode attachment deviations may cause fluctuations in the ability of the ECG signals corresponding to those leads to represent cardiac electrical activity. Furthermore, actual heartbeat signals with lower amplitudes typically contain fewer effective morphological features and are easily affected by noise, baseline drift, or localized minor fluctuations. Heartbeat signals with higher amplitudes, on the other hand, often have clearer and more stable QRS complexes or cardiac morphological features, and can more effectively reflect the propagation direction and morphological changes of cardiac electrical activity. In some implementations, the actual amplitude of the actual heartbeat signal corresponding to each lead and the template amplitude of the template heartbeat signal corresponding to each lead can be obtained. Based on each actual amplitude and each template amplitude, the weight corresponding to each waveform similarity is determined. The weight can be positively correlated with the actual amplitude, positively correlated with the template amplitude, or positively correlated with both the actual amplitude and the template amplitude. Taking a positive correlation between weights and both actual and template amplitudes as an example, for each lead, the representational amplitude corresponding to that lead can be determined based on the actual and template amplitudes; the overall representational amplitude can be determined based on the representational amplitudes of all leads; and the ratio between the representational amplitude of each lead and the overall representational amplitude can be determined as the weight corresponding to each waveform similarity. Alternatively, taking a positive correlation between weights and actual amplitudes as an example, for each lead, the ratio of the actual amplitude to the sum of all actual amplitudes can be determined as the weight of the waveform similarity corresponding to that lead. Similarly, taking a positive correlation between weights and template amplitudes as an example, for each lead, the ratio of the template amplitude to the sum of all template amplitudes can be determined as the weight of the waveform similarity corresponding to that lead.

[0062] In some implementations, the weights corresponding to the similarity of each waveform are determined based on the amplitude of the actual heartbeat signal and the template heartbeat data corresponding to each lead. Compared with fixed weight values, the weights can be adjusted adaptively to fit the changes in the real heartbeat signal, making the weights closer to the real representation of cardiac electrical activity of the lead, which helps to improve the rationality and accuracy of the overall similarity value.

[0063] In some embodiments, the weights corresponding to each waveform similarity are determined based on each actual amplitude and each template amplitude, including:

[0064] Step S210: For each lead, determine the characteristic amplitude corresponding to the lead based on the actual amplitude and template amplitude.

[0065] Step S220: Determine the overall characteristic amplitude based on the characteristic amplitude corresponding to each lead.

[0066] Step S230: The ratio between the characteristic amplitude of each lead and the overall characteristic amplitude is determined as the weight corresponding to each waveform similarity.

[0067] In some implementations, for each lead, the actual amplitude and template amplitude corresponding to the lead can be synthesized to obtain the characteristic amplitude corresponding to the lead. For example, the actual amplitude and template amplitude corresponding to the lead can be directly summed to obtain the characteristic amplitude corresponding to the lead. Then, the characteristic amplitudes corresponding to all leads are summed to obtain the overall characteristic amplitude.

[0068] By using the actual amplitude and template amplitude corresponding to each lead, the representative amplitude corresponding to the lead is determined, and then the weight is determined based on this. Compared with determining the weight solely based on the actual amplitude or template amplitude, using the representative amplitude that integrates the actual amplitude and template amplitude can make the weight closer to the true representation ability of the lead for cardiac electrical activity, which helps to improve the rationality and accuracy of the overall similarity value.

[0069] Step S140: Based on each weight and each waveform similarity value, obtain the overall similarity value between the template heartbeat data and the actual heartbeat data.

[0070] In some implementations, the waveform similarity value corresponding to the lead can be multiplied by its corresponding weight to obtain the weighted contribution value of the lead. Then, the weighted contribution values ​​of all leads are summed to obtain the overall similarity value between the template heartbeat data and the actual heartbeat data. For example... Figure 3 As shown, taking leads I, II, III, aVR, aVL, aVF, V1, V2, V3, V4, V5, and V6 as an example, given the waveform similarity values ​​(Pearson correlation coefficient ρ) between the actual heartbeat signals and the template heartbeat signals for each of the 12 leads, the weights corresponding to each waveform similarity can be determined. Multiplying the weights corresponding to each waveform similarity with the respective waveform similarity yields the weighted contribution value for each lead. Summing these weighted contribution values ​​then yields the overall similarity value between the template heartbeat data and the actual heartbeat data.

[0071] Step S150: If the overall similarity value is greater than or equal to the preset similarity threshold, the actual heartbeat data is determined as valid labeled data.

[0072] In some implementations, the preset similarity threshold is a pre-set similarity value for determining whether data can be used as valid mapping data. This preset similarity threshold can be pre-set according to specific application scenarios, signal quality requirements, mapping accuracy requirements, or clinical strategies.

[0073] For example, if the overall similarity value is greater than or equal to a preset similarity threshold, it indicates that the actual heartbeat data and the template heartbeat data are highly similar in waveform morphology, and the actual heartbeat data can be directly identified as valid mapping data. If the overall similarity value is less than the preset similarity threshold, it indicates that the actual heartbeat data and the template heartbeat data are not highly similar in waveform morphology, and the actual heartbeat data can be discarded and not used as valid mapping data. Then, new actual heartbeat data is obtained, and the step of determining the waveform similarity value between the actual heartbeat signal corresponding to each lead and the template heartbeat signal corresponding to the lead is performed.

[0074] In the aforementioned method for determining mapping data, template heartbeat data and actual heartbeat data of the target object are acquired. The template heartbeat data includes template heartbeat signals from at least two leads, while the actual heartbeat data includes actual heartbeat signals from each lead. For each lead, a waveform similarity value is determined between the actual heartbeat signal and the corresponding template heartbeat signal, and a weight is assigned to the waveform similarity for each lead. This weight is positively correlated with the actual heartbeat signal's ability to represent cardiac electrical activity. Based on these weights and waveform similarity values, an overall similarity value between the template heartbeat data and the actual heartbeat data is obtained. Considering that the ability of actual heartbeat signals from different leads to represent cardiac electrical activity varies significantly in real electrocardiogram (ECG) signals, a weight positively correlated with the representation ability of each lead's waveform similarity value is assigned. This adjusts the impact of actual heartbeat signals from different leads on the overall similarity value, allowing the actual heartbeat signal with stronger ECG representation ability to have a greater influence, thereby improving the rationality and accuracy of the overall similarity value and contributing to the accuracy of matching actual heartbeats with template heartbeats. Furthermore, if the overall similarity value is greater than or equal to the preset similarity threshold, the actual heartbeat data is determined as valid mapping data. This overall similarity value, which can more accurately reflect the true electrical activity characteristics of the heart, serves as the criterion for whether the actual heartbeat data can be used as valid mapping data, which helps to improve the data quality of the mapping data.

[0075] In some exemplary embodiments, such as Figure 4 As shown, before determining the actual heartbeat data as valid labeled data when the overall similarity value is greater than or equal to a preset similarity threshold, the method further includes steps S310 to S320. Wherein:

[0076] Step S310: Based on the overall similarity value and the overall similarity values ​​between the actual heartbeat data and the template heartbeat data after multiple offsets, determine the maximum overall similarity value.

[0077] Step S320: Determine the maximum overall similarity value as the new overall similarity value.

[0078] In some implementations, each actual heartbeat signal includes multiple actual sampling points, and the offset actual heartbeat data is obtained by offsetting the actual sampling points of each actual heartbeat signal in the actual heartbeat data; the offset amount corresponding to different offset actual heartbeat data is different; and the offset amount of each actual sampling point in each actual heartbeat signal in the actual heartbeat data is the same during each offset.

[0079] Even though the template heartbeat signal and the actual heartbeat signal have a high degree of similarity in overall shape, when there is a slight time offset between the actual heartbeat signal and the template heartbeat signal due to the difference in acquisition timing, the waveform correlation coefficient calculated at a fixed position will be significantly lower than the true shape similarity. This will lead to the actual heartbeat signal, which is essentially the same as the template signal in shape, being misjudged as a mismatch, thus affecting the integrity and reliability of the calibration data. As an example, to improve the robustness of matching template heartbeat data with actual heartbeat data, the overall similarity value can be determined as the maximum overall similarity value. Following a preset offset step, the actual sampling points in each actual heartbeat signal are offset to obtain the offset actual heartbeat signals, which are then determined as the offset actual heartbeat data. Based on each template heartbeat signal and each offset actual heartbeat signal, the offset overall similarity value between the template heartbeat data and the offset actual heartbeat data is determined. If the offset overall similarity value is greater than the maximum overall similarity value, the offset overall similarity value is determined as the maximum overall similarity value. The process then returns to the step of offsetting the actual sampling points in each actual heartbeat signal according to the preset offset step, until the offset amount of the actual sampling points in the actual heartbeat signal exceeds the preset offset range, thus obtaining the maximum overall similarity value.

[0080] As another embodiment, the actual heartbeat data can be offset by different amounts within a preset offset range to obtain multiple offset actual heartbeat data. Then, the overall offset similarity value between the template heartbeat data and each offset actual heartbeat data is calculated, and the maximum value among the overall similarity value and the overall offset similarity value is determined as the new overall similarity value.

[0081] Therefore, by finding the maximum overall similarity value between the template heartbeat data and the actual heartbeat data after offset at different offsets, it helps to reduce the deviation between the overall similarity value and the true similarity caused by time offset.

[0082] In some embodiments, each template heartbeat signal includes multiple template sampling points; based on the overall similarity value and the offset overall similarity values ​​between the actual heartbeat data and the template heartbeat data after multiple offsets, the maximum overall similarity value is determined, including:

[0083] Step S311: Determine the overall similarity value as the maximum overall similarity value.

[0084] Step S312: According to the preset offset step, the actual sampling points in each actual heartbeat signal are offset to obtain each actual heartbeat signal after offset, and the offset actual heartbeat data is determined.

[0085] Step S313: Based on the template heartbeat signals and the offset actual heartbeat signals, determine the overall similarity value between the template heartbeat data and the offset actual heartbeat data.

[0086] Step S314: If the overall similarity value after offset is greater than the maximum overall similarity value, the overall similarity value after offset is determined as the maximum overall similarity value.

[0087] Step S315: Return to the step of offsetting the actual sampling points in each actual heartbeat signal according to the preset offset step, until the offset of the actual sampling points in the actual heartbeat signal exceeds the preset offset range, and obtain the maximum overall similarity value.

[0088] In some implementations, each template heartbeat signal includes multiple template sampling points, and each actual heartbeat signal includes multiple actual sampling points. These sampling points are data points obtained by collecting heartbeat data from the target object at predetermined time intervals.

[0089] like Figure 5 As shown, taking leads I, II, III, aVR, aVL, aVF, V1, V2, V3, V4, V5, and V6 as an example, the overall similarity value between the actual heartbeat signals (yellow curves) and the template heartbeat signals (blue curves) corresponding to the 12 leads is calculated. Figure 5 In the case of 0.246, the overall similarity value can be determined as the maximum overall similarity value. Then, according to the preset offset step, the actual sampling points in each actual heartbeat signal are offset to obtain the offset actual heartbeat signals, which are determined as the offset actual heartbeat data. For example, the preset offset step can be the number of sampling points, the time interval between sampling points, or a multiple of the time interval to complete each offset. It is understood that empty sampling points in the offset actual heartbeat data that do not align with the template sampling points can be zeroed out. Then, based on each template heartbeat signal and each offset actual heartbeat signal, the offset overall similarity value between the template heartbeat data and the offset actual heartbeat data is determined. Figure 5(0.532 in the original text). If the overall similarity value after offset is greater than the maximum overall similarity value, the overall similarity value after offset is determined as the maximum overall similarity value. Return to the step of offsetting the actual sampling points in each actual heartbeat signal according to the preset offset step, so that the actual heartbeat data after offset can be offset again to obtain the overall similarity value after offset between the template heartbeat data and the new actual heartbeat data. Until the offset of the actual sampling points in the actual heartbeat signal exceeds the preset offset range, the maximum overall similarity value within the preset offset range can be obtained. It can be understood that the preset offset range can be less than or equal to the number of sampling points of the template heartbeat signal. For example, if the number of sampling points of the template heartbeat signal is 81, then the preset offset range can be [-40, 40]. The preset offset range can also be less than or equal to the time span of the template heartbeat signal. For example, if the time span of the template heartbeat signal is 61 seconds, then the preset offset range can be [-30s, 30s].

[0090] By employing a local time search mechanism, the maximum overall similarity value between the template heartbeat data and the actual heartbeat data after offset at different offsets is obtained by iterating through the template heartbeat data one by one. This effectively reduces the impact of heartbeat truncation error, peak positioning error, or sampling time difference on the correlation calculation results (i.e., waveform similarity value). The resulting weighted correlation coefficient (i.e., overall similarity value) better reflects the true morphological similarity between the template heartbeat and the actual heartbeat under optimal alignment conditions. This helps reduce the deviation between the overall similarity value and the true similarity due to time offset. Furthermore, the iterative approach also reduces the computational resource requirements within the same time period.

[0091] In some embodiments, determining actual heart rate data as valid mapping data includes:

[0092] Step S410: Determine the target offset corresponding to the maximum overall similarity value.

[0093] Step S420: According to the target offset, offset the actual sampling points in each actual heartbeat signal to obtain each actual heartbeat signal after offset, so as to obtain the target heartbeat data.

[0094] Step S430: Determine the target heartbeat data as valid calibration data.

[0095] In some implementations, the target offset is the offset of the actual heartbeat data after the offset corresponding to the maximum overall similarity value.

[0096] After determining the target offset corresponding to the maximum overall similarity value, the actual sampling points in each actual heartbeat signal can be offset according to the target offset to obtain each offset actual heartbeat signal. This yields target heartbeat data including multiple offset actual heartbeat signals. Alternatively, the portion of each offset actual heartbeat signal that aligns with the corresponding template heartbeat data in the time dimension can be identified as target heartbeat data. This target heartbeat data can then be determined as valid calibration data, thereby reducing the impact of time offset and making the time of each sampling point in the valid calibration data closer to the actual time of heartbeat signal generation.

[0097] As a specific example, such as Figure 6 As shown, the input consists of template heartbeat data and actual heartbeat data. The template heartbeat data includes template heartbeat signals corresponding to multiple leads, and the actual heartbeat data includes the actual heartbeat signals corresponding to these leads. The lead type and number of leads corresponding to the template heartbeat signals in the template heartbeat data correspond one-to-one with the lead type and number of leads corresponding to the actual heartbeat signals in the actual heartbeat data. Time alignment is performed on each template heartbeat signal and its corresponding actual heartbeat signal, i.e., aligning the sampling points of the template heartbeat signal with the sampling points of the actual heartbeat signal (aligning the i-th sampling point in the template heartbeat signal with the i-th sampling point in the actual heartbeat signal aligns all sampling points). Then, for each lead, the waveform similarity value between the actual heartbeat signal and the template heartbeat signal is calculated. In some implementations, the Pearson correlation coefficient can be used as the waveform similarity value. Then, based on the template heartbeat signal and the actual heartbeat signal corresponding to each lead, different weights are assigned to different leads, and the waveform similarity values ​​corresponding to each lead are weighted according to their respective weights to obtain the overall similarity value between the template heartbeat data and the actual heartbeat data. Next, within a preset offset range, a sliding search is performed to find the maximum overall similarity value between the template heartbeat data and the actual heartbeat data after offset at different offset amounts. This maximum overall similarity value is then compared with a preset similarity threshold. If the maximum overall similarity value is greater than or equal to the preset similarity threshold, the actual heartbeat data is determined as valid mapping data.

[0098] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0099] Based on the same inventive concept, this application also provides a calibration data determination apparatus for implementing the calibration data determination method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more calibration data determination apparatus embodiments provided below can be found in the limitations of the calibration data determination method described above, and will not be repeated here.

[0100] In one exemplary embodiment, such as Figure 7 As shown, a calibration data determination device 500 is provided, including: a data acquisition module 510, a similarity determination module 520, a weight determination module 530, an overall calculation module 540, and a data determination module 550, wherein:

[0101] The data acquisition module 510 is used to acquire template heartbeat data and actual heartbeat data, wherein the template heartbeat data includes template heartbeat signals corresponding to at least two leads, and the actual heartbeat data includes actual heartbeat signals corresponding to each lead.

[0102] The similarity determination module 520 is used to determine the waveform similarity value between the actual heartbeat signal corresponding to the lead and the template heartbeat signal corresponding to the lead for each lead;

[0103] The weight determination module 530 is used to determine the weight corresponding to each waveform similarity based on the template heartbeat signal corresponding to each lead and the actual heartbeat signal corresponding to each lead. The weight is positively correlated with the ability of the actual heartbeat signal to represent cardiac electrical activity.

[0104] The overall calculation module 540 is used to obtain the overall similarity value between the template heartbeat data and the actual heartbeat data based on each weight and the corresponding waveform similarity value;

[0105] The data determination module 550 is used to determine the actual heartbeat data as valid labeled data when the overall similarity value is greater than or equal to a preset similarity threshold.

[0106] In some embodiments, the calibration data determination device 500 further includes a data offset module, used for:

[0107] Based on the overall similarity value and the overall similarity value between the actual heartbeat data and the template heartbeat data after multiple offsets, the maximum overall similarity value is determined. Each actual heartbeat signal includes multiple actual sampling points. The actual heartbeat data after offset is obtained by offsetting the actual sampling points in each actual heartbeat signal in the actual heartbeat data. Different offsets correspond to different offsets of the actual heartbeat data.

[0108] In some embodiments, each template heartbeat signal includes multiple template sampling points; the data offset module is further used for:

[0109] The overall similarity value is determined as the maximum overall similarity value. The actual sampling points in each actual heartbeat signal are offset according to the preset offset step to obtain the offset actual heartbeat signals, which are determined as the offset actual heartbeat data. Based on each template heartbeat signal and each offset actual heartbeat signal, the offset overall similarity value between the template heartbeat data and the offset actual heartbeat data is determined. If the offset overall similarity value is greater than the maximum overall similarity value, the offset overall similarity value is determined as the maximum overall similarity value. The process of offsetting the actual sampling points in each actual heartbeat signal according to the preset offset step is returned until the offset amount of the actual sampling points in the actual heartbeat signal exceeds the preset offset range, thus obtaining the maximum overall similarity value.

[0110] In some embodiments, the data determination module 550 is further configured to:

[0111] Determine the target offset corresponding to the maximum overall similarity value. Based on the target offset, offset the actual sampling points in each actual heartbeat signal to obtain each actual heartbeat signal after offset, so as to obtain the target heartbeat data. The target heartbeat data is determined as the valid calibration data.

[0112] In some embodiments, the similarity determination module 520 is further configured to:

[0113] The actual amplitude sequence of the actual heartbeat signal and the template amplitude sequence of the template heartbeat signal are determined. The actual mean amplitude of the actual heartbeat signal is determined based on the actual amplitude sequence, and the template mean amplitude of the template heartbeat signal is determined based on the template amplitude sequence. Based on the actual amplitude sequence, template amplitude sequence, actual mean amplitude, and template mean amplitude, the waveform similarity value between the actual heartbeat signal and the corresponding template heartbeat signal is obtained.

[0114] In some embodiments, the weight determination module 530 is further configured to:

[0115] Obtain the actual amplitude of the actual heartbeat signal corresponding to each lead, and the template amplitude of the template heartbeat signal corresponding to each lead. Based on each actual amplitude and each template amplitude, determine the weight corresponding to each waveform similarity, wherein the weight is positively correlated with the actual amplitude and / or the template amplitude.

[0116] In some embodiments, the weight determination module 530 is further configured to:

[0117] For each lead, the characteristic amplitude corresponding to the lead is determined based on the actual amplitude and template amplitude corresponding to the lead. The overall characteristic amplitude is determined based on the characteristic amplitude corresponding to each lead. The ratio between the characteristic amplitude corresponding to each lead and the overall characteristic amplitude is determined as the weight corresponding to each waveform similarity.

[0118] Each module in the aforementioned calibration data determination device 500 can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0119] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 8As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for determining measurement data. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, a trackball, or a touchpad provided on the casing of the computer device, or an external keyboard, touchpad, or mouse, etc. In some exemplary embodiments, this application provides a computer device including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of the above embodiments.

[0120] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0121] The calibration data determination method provided in this application embodiment can be applied to, for example... Figure 9The application environment is shown. In some exemplary embodiments, this application also provides a mapping data determination system, including an electrocardiogram (ECG) acquisition device 102 and a computer device 104 connected to the ECG acquisition device, wherein the ECG acquisition device 102 and the computer device 104 are connected by wired or wireless communication. The ECG acquisition device 102 acquires the actual heartbeat data of the target object and transmits the actual heartbeat data to the computer device 104. Computer device 104 acquires template heartbeat data and actual heartbeat data. The template heartbeat data includes template heartbeat signals corresponding to at least two leads, and the actual heartbeat data includes actual heartbeat signals corresponding to each lead. For each lead, a waveform similarity value is determined between the actual heartbeat signal and the template heartbeat signal. Based on the template and actual heartbeat signals for each lead, a weight is determined for each waveform similarity, where the weight is positively correlated with the ability of the actual heartbeat signal to represent cardiac electrical activity. Based on the weights and waveform similarity values, an overall similarity value is obtained between the template heartbeat data and the actual heartbeat data. If the overall similarity value is greater than or equal to a preset similarity threshold, the actual heartbeat data is determined as valid mapping data. ECG acquisition device 102 is an electrocardiograph capable of acquiring ECG signals from at least two leads, such as a 3-lead, 6-lead, 12-lead, 15-lead, or 18-lead multi-lead ECG machine. Computer equipment 104 may be, but is not limited to, various personal computers, laptops, smartphones, tablets and other terminal devices with computing capabilities, or it may be a server. The server may be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0122] In some embodiments, the mapping data determination system further includes electrodes connected to an electrocardiogram (ECG) acquisition device;

[0123] Electrodes are placed at designated locations on the target object and transmit the received electrical signals to the electrocardiogram (ECG) acquisition device.

[0124] Electrocardiogram (ECG) acquisition equipment is used to process the electrical signals transmitted by each electrode to obtain the actual heartbeat data of the target object.

[0125] For example, the electrodes can be surface electrode pads or electrodes on catheters. Taking the mapping data determination system as an example, it also includes multiple electrode pads, each of which is attached to a designated location corresponding to the target. The received electrical signals can then be transmitted to an ECG acquisition device, which processes the electrical signals transmitted by each electrode to obtain the actual heartbeat data of the target object.

[0126] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the above embodiments.

[0127] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the above embodiments.

[0128] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0129] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0130] The above embodiments merely illustrate several implementation methods of this application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of this application's patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining calibration data, characterized in that, The method includes: Acquire template heartbeat data and actual heartbeat data, wherein the template heartbeat data includes template heartbeat signals corresponding to at least two leads, and the actual heartbeat data includes actual heartbeat signals corresponding to each of the leads; For each lead, determine the waveform similarity value between the actual heartbeat signal corresponding to the lead and the template heartbeat signal corresponding to the lead; Based on the template heartbeat signal corresponding to each lead and the actual heartbeat signal corresponding to each lead, the weights corresponding to the waveform similarity are determined, wherein the weights are positively correlated with the ability of the actual heartbeat signal to represent cardiac electrical activity. Based on the weights and waveform similarity values, the overall similarity value between the template heartbeat data and the actual heartbeat data is obtained. If the overall similarity value is greater than or equal to a preset similarity threshold, the actual heartbeat data is determined as valid labeled data.

2. The method according to claim 1, characterized in that, Before determining the actual heartbeat data as valid labeled data when the overall similarity value is greater than or equal to a preset similarity threshold, the method further includes: Based on the overall similarity value and the overall similarity values ​​between the actual heartbeat data after multiple offsets and the template heartbeat data, the maximum overall similarity value is determined. Each actual heartbeat signal includes multiple actual sampling points. The actual heartbeat data after offset is obtained by offsetting the actual sampling points in each actual heartbeat signal in the actual heartbeat data. Different offset amounts correspond to different offset amounts for different actual heartbeat data. The maximum overall similarity value is determined as the new overall similarity value.

3. The method according to claim 2, characterized in that, Each template heartbeat signal includes multiple template sampling points; The determination of the maximum overall similarity value based on the overall similarity value and the offset overall similarity values ​​between multiple offset actual heartbeat data and the template heartbeat data includes: The overall similarity value is determined as the maximum overall similarity value; According to the preset offset step, the actual sampling points in each actual heartbeat signal are offset to obtain each actual heartbeat signal after offset, which is determined as the actual heartbeat data after offset. Based on the template heartbeat signals and the offset actual heartbeat signals, determine the overall similarity value between the template heartbeat data and the offset actual heartbeat data; If the overall similarity value after the offset is greater than the maximum overall similarity value, the overall similarity value after the offset shall be determined as the maximum overall similarity value. Return to the step of offsetting the actual sampling points in each actual heartbeat signal according to the preset offset step, until the offset of the actual sampling points in the actual heartbeat signal exceeds the preset offset range, and obtain the maximum overall similarity value.

4. The method according to claim 2, characterized in that, The step of determining the actual heartbeat data as valid calibration data includes: Determine the target offset corresponding to the maximum overall similarity value; According to the target offset, the actual sampling points in each actual heartbeat signal are offset to obtain each actual heartbeat signal after offset, so as to obtain the target heartbeat data; The target heartbeat data is determined as valid calibration data.

5. The method according to claim 1, characterized in that, Determining the waveform similarity value between the actual heartbeat signal corresponding to the lead and the template heartbeat signal corresponding to the lead includes: Determine the actual amplitude sequence of the actual heartbeat signal and the template amplitude sequence of the template heartbeat signal; The actual mean amplitude of the actual heartbeat signal is determined based on the actual amplitude sequence, and the template mean amplitude of the template heartbeat signal is determined based on the template amplitude sequence. Based on the actual amplitude sequence, the template amplitude sequence, the average actual amplitude, and the average template amplitude, the waveform similarity value between the actual heartbeat signal and the corresponding template heartbeat signal is obtained.

6. The method according to claim 1, characterized in that, The step of determining the weight corresponding to each waveform similarity based on the template heartbeat signal corresponding to each lead and the actual heartbeat signal corresponding to each lead includes: Obtain the actual amplitude of the actual heartbeat signal corresponding to each lead, and the template amplitude of the template heartbeat signal corresponding to each lead; Based on each actual amplitude and each template amplitude, a weight corresponding to each waveform similarity is determined, wherein the weight is positively correlated with the actual amplitude and / or the template amplitude.

7. The method according to claim 6, characterized in that, The step of determining the weight corresponding to each waveform similarity based on each actual amplitude and each template amplitude includes: For each lead, the characteristic amplitude corresponding to the lead is determined based on the actual amplitude and the template amplitude corresponding to the lead; The overall amplitude is determined based on the amplitude of each lead. The ratio between the characteristic amplitude corresponding to each lead and the overall characteristic amplitude is determined as the weight corresponding to each waveform similarity.

8. A calibration data determination device, characterized in that, The device includes: The data acquisition module is used to acquire template heartbeat data and actual heartbeat data, wherein the template heartbeat data includes template heartbeat signals corresponding to at least two leads, and the actual heartbeat data includes actual heartbeat signals corresponding to each of the leads. The similarity determination module is used to determine the waveform similarity value between the actual heartbeat signal corresponding to the lead and the template heartbeat signal corresponding to the lead for each lead; The weight determination module is used to determine the weight corresponding to each waveform similarity based on the template heartbeat signal corresponding to each lead and the actual heartbeat signal corresponding to each lead, wherein the weight is positively correlated with the ability of the actual heartbeat signal to represent cardiac electrical activity; The overall calculation module is used to obtain the overall similarity value between the template heartbeat data and the actual heartbeat data based on each weight and the corresponding waveform similarity value. The data determination module is used to determine the actual heartbeat data as valid labeled data when the overall similarity value is greater than or equal to a preset similarity threshold.

9. A computer device, characterized in that, The device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program, wherein the computer program executes the measurement data determination method according to any one of claims 1 to 7.

10. A system for determining calibration data, characterized in that, The mapping data determination system includes an electrocardiogram (ECG) acquisition device and a computer device connected to the ECG acquisition device; An electrocardiogram (ECG) acquisition device is used to collect the actual heartbeat data of a target object and transmit the actual heartbeat data to a computer device. A computer device is used to acquire template heartbeat data and actual heartbeat data, wherein the template heartbeat data includes template heartbeat signals corresponding to at least two leads, and the actual heartbeat data includes actual heartbeat signals corresponding to each of the leads; for each lead, a waveform similarity value is determined between the actual heartbeat signal corresponding to the lead and the template heartbeat signal corresponding to the lead; based on the template heartbeat signal and the actual heartbeat signal corresponding to each lead, a weight is determined for each waveform similarity, wherein the weight is positively correlated with the ability of the actual heartbeat signal to represent cardiac electrical activity; and based on each weight and each waveform similarity value, an overall similarity value between the template heartbeat data and the actual heartbeat data is obtained. If the overall similarity value is greater than or equal to a preset similarity threshold, the actual heartbeat data is determined as valid labeled data.

11. The system according to claim 10, characterized in that, The mapping data determination system also includes electrodes, which are connected to the electrocardiogram acquisition device; The electrodes are used to be placed at a designated location on the target object and to transmit the received electrical signals to the electrocardiogram (ECG) acquisition device. The electrocardiogram (ECG) acquisition device is used to process the electrical signals transmitted by each electrode to obtain the actual heartbeat data of the target object.

Images