Fetal heart detection method and apparatus, electronic device, and storage medium

Abstract

The present disclosure provides a fetal heart detection method, device, equipment and medium, the method comprises: obtaining target fetal heart monitoring data in a preset time period before the current acquisition time as the terminal point; based on the target fetal heart monitoring data, determine the target detection baseline matched with the target fetal heart monitoring data, and based on the target detection baseline, the target fetal heart monitoring data is detected abnormally, and the detection result is obtained; in the case where the target detection result indicates that there is abnormal data in the target fetal heart monitoring data, the prompt information is generated based on the abnormal data. The embodiments of the present disclosure are beneficial to improve the detection efficiency and accuracy of fetal heart detection.

Description

Technical Field

[0001] This disclosure relates to the field of medical technology, and more specifically, to a method for detecting fetal heart rate, a device for detecting fetal heart rate, an electronic device, and a storage medium. Background Technology

[0002] Electronic fetal heart rate monitoring, as an important means of assessing fetal condition, is widely used in routine obstetric examinations. Fetal heart rate monitoring data is particularly important for the safety of both the pregnant woman and the fetus. However, current analysis of fetal heart rate monitoring data often relies on the doctor's clinical experience and skill level. This diagnostic method is highly subjective, thus affecting the accuracy of the diagnosis. Summary of the Invention

[0003] This disclosure provides at least one method, device, electronic device, and storage medium for fetal heart rate detection, which can improve the accuracy of fetal heart rate detection.

[0004] This disclosure provides a method for fetal heart rate detection, including:

[0005] Acquire target fetal heart rate monitoring data within a preset time period ending at the current acquisition time;

[0006] Based on the target fetal heart rate monitoring data, a target detection baseline matching the target fetal heart rate monitoring data is determined, and anomaly detection is performed on the target fetal heart rate monitoring data based on the target detection baseline to obtain the target detection result;

[0007] If the target detection result indicates that there is abnormal data in the target fetal heart rate monitoring data, a prompt message is generated based on the abnormal data.

[0008] This disclosure provides a fetal heart rate detection device, comprising:

[0009] The data acquisition module is used to acquire target fetal heart rate monitoring data within a preset time period, with the current acquisition time as the endpoint.

[0010] An anomaly detection module is used to determine a target detection baseline that matches the target fetal heart rate monitoring data based on the target fetal heart rate monitoring data, and to perform anomaly detection on the target fetal heart rate monitoring data based on the target detection baseline to obtain a target detection result;

[0011] An anomaly alert module is used to generate an alert message based on the abnormal data when the target detection result indicates that there is abnormal data in the target fetal heart rate monitoring data.

[0012] This disclosure also provides an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of the fetal heart rate detection method described in any of the above possible embodiments are performed.

[0013] This disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the fetal heart rate detection method described in any of the above possible embodiments.

[0014] The fetal heart rate monitoring method, apparatus, electronic device, and storage medium provided in this application, after acquiring target fetal heart rate monitoring data, can determine a target detection baseline matching the target fetal heart rate monitoring data, and perform anomaly detection on the target fetal heart rate monitoring data based on the target detection baseline to obtain the target detection result. This enables automatic detection of fetal heart rate monitoring data, improving the efficiency and accuracy of fetal heart rate monitoring compared to related technologies that rely on manual analysis of monitoring reports. Furthermore, since the target detection baseline is obtained based on the acquired target fetal heart rate monitoring data, and the detection of the target fetal heart rate monitoring data is performed based on the target detection baseline, the accuracy of anomaly detection can be further improved.

[0015] To make the above-mentioned objects, features and advantages of this disclosure more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the embodiments will be briefly described below. These drawings are incorporated in and constitute a part of this specification. They illustrate embodiments conforming to this disclosure and, together with the specification, serve to explain the technical solutions of this disclosure. It should be understood that the following drawings only show some embodiments of this disclosure and should not be considered as limiting the scope. Those skilled in the art can obtain other related drawings based on these drawings without creative effort.

[0017] Figure 1 A flowchart of a fetal heart rate detection method provided in some embodiments of this disclosure is shown;

[0018] Figure 2 A flowchart illustrating a detailed method for generating detection results provided in some embodiments of this disclosure is shown;

[0019] Figure 3A flowchart is shown illustrating a method for determining a target fetal heart rate detection baseline provided by some embodiments of this disclosure;

[0020] Figure 4 A flowchart is shown illustrating a method for generating alert messages based on abnormal data, provided in some embodiments of this disclosure.

[0021] Figure 5 A flowchart illustrating a method for matching target anomaly information with historical anomaly information provided in some embodiments of this disclosure is shown.

[0022] Figure 6 A schematic diagram illustrating the determination of newly added anomaly information provided by some embodiments of this disclosure is shown;

[0023] Figure 7 A schematic diagram illustrating the determination of newly added anomaly information provided in other embodiments of this disclosure is shown;

[0024] Figure 8 A schematic diagram of a fetal heart rate detection device provided in some embodiments of this disclosure is shown;

[0025] Figure 9 A schematic diagram of an electronic device provided in some embodiments of the present disclosure is shown. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. The components of the embodiments of this disclosure described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this disclosure provided in the accompanying drawings is not intended to limit the scope of the claimed disclosure, but merely represents selected embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without inventive effort are within the scope of protection of this disclosure.

[0027] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0028] In this document, the term "and / or" merely describes a relationship, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0029] Electronic fetal heart rate monitoring is an important means of assessing fetal condition. It can detect the fetal condition in a timely manner, such as whether the fetus is hypoxic. Therefore, the correct analysis of fetal heart rate monitoring data is very important for reducing neonatal seizures, cerebral palsy, intrapartum mortality, predicting neonatal acidosis, and reducing unnecessary medical interventions.

[0030] With the increasing importance of electronic fetal heart rate monitoring, it has been widely used in routine obstetric examinations. Fetal heart rate monitoring data is particularly crucial for the safety of both the pregnant woman and the fetus. However, current analysis of fetal heart rate monitoring data often relies on the doctor's clinical experience and skill level, making this diagnostic method highly subjective and potentially affecting its accuracy.

[0031] Based on the above research, this disclosure provides a fetal heart rate monitoring method, apparatus, device, and storage medium. First, target fetal heart rate monitoring data within a preset time period preceding the current acquisition time is acquired. Then, based on the target fetal heart rate monitoring data, a target detection baseline matching the target fetal heart rate monitoring data is determined, and anomaly detection is performed on the target fetal heart rate monitoring data based on the target detection baseline to obtain a detection result. Finally, if the target detection result indicates the presence of abnormal data in the target fetal heart rate monitoring data, a prompt message is generated based on the abnormal data. This enables automatic detection of fetal heart rate monitoring data, improving the efficiency and accuracy of fetal heart rate monitoring compared to related technologies that rely on manual analysis of monitoring reports. Furthermore, since the target detection baseline is obtained based on the currently acquired target fetal heart rate monitoring data, and the detection of the target fetal heart rate monitoring data is performed based on the target detection baseline, the accuracy of anomaly detection can be further improved.

[0032] To facilitate understanding of this embodiment, the executing entity of the fetal heart rate detection method provided in this disclosure will first be described in detail. The executing entity of the fetal heart rate detection method provided in this disclosure is an electronic device. In this embodiment, the electronic device is a server, which can be an independent physical server, a server cluster composed of multiple physical servers, or a distributed system. It can also be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, big data, and artificial intelligence platforms. In other embodiments, the electronic device can also be a terminal device. This terminal device can be a mobile device, a user terminal, a handheld device, a computing device, or a wearable device. In some other embodiments, the fetal heart rate detection method can also be implemented by a processor calling computer-readable instructions stored in memory.

[0033] The fetal heart rate detection method provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings. See also Figure 1 The diagram shows a flowchart of a fetal heart rate detection method provided in this embodiment of the present disclosure. The method includes steps S101 to S103, wherein:

[0034] S101, acquire the target fetal heart rate monitoring data within the previous preset time period, with the current acquisition time as the endpoint.

[0035] The preset time period can be set according to actual needs. For example, the preset time period can be 30 seconds, 5 minutes, or 10 minutes, etc., and is not limited here. If the current collection time is 10:00 and the preset time period is 5 minutes, then the preset time period before the current collection time can be the period from 9:55 to 10:00, and the target fetal heart rate monitoring data is the fetal heart rate monitoring data within the period from 9:55 to 10:00.

[0036] The target fetal heart rate monitoring data includes target fetal heart rate data and target uterine contraction rate data.

[0037] In this embodiment, fetal heart rate monitoring data can be obtained in real time using a fetal heart rate monitoring device.

[0038] S102, based on the target fetal heart rate monitoring data, determine a target detection baseline that matches the target fetal heart rate monitoring data, and perform anomaly detection on the target fetal heart rate monitoring data based on the target detection baseline to obtain the target detection result.

[0039] The target detection baseline includes benchmark data corresponding to the target fetal heart rate monitoring data.

[0040] Here, after obtaining the target fetal heart rate monitoring data, anomaly detection can be performed through the target monitoring baseline. In this embodiment, a target detection baseline matching the target fetal heart rate monitoring data is determined based on the target fetal heart rate monitoring data. That is, the target detection baseline is determined based on the currently obtained target fetal heart rate monitoring data. In this way, the accuracy of detection can be improved in subsequent detection processes.

[0041] Since the target fetal heart rate monitoring data includes target fetal heart rate data and target uterine contraction rate data, for step S102, when determining a target detection baseline matching the target fetal heart rate monitoring data based on the target fetal heart rate monitoring data, and performing anomaly detection on the target fetal heart rate monitoring data based on the target detection baseline to obtain the target detection result, please refer to [link to relevant documentation]. Figure 2 It may include the following steps S1021 to S1023:

[0042] S1021, Based on the target fetal heart rate data, determine a target fetal heart rate detection baseline that matches the target fetal heart rate data, and based on the target uterine contraction rate data, determine a target uterine contraction detection baseline that matches the target uterine contraction rate data.

[0043] S1022, based on the target fetal heart rate detection baseline, anomaly detection is performed on the target fetal heart rate data to obtain a first detection result of the target fetal heart rate data, and based on the target uterine contraction detection baseline, anomaly detection is performed on the target uterine contraction rate data to obtain a second detection result of the target uterine contraction rate data.

[0044] S1023, Based on the first detection result and the second detection result, generate the target detection result.

[0045] It should be understood that the evaluation and analysis standards for fetal heart rate and uterine contraction rate are different. For example, a normal uterine contraction rate can be greater than 5 times / 10 minutes, while a normal fetal heart rate can be (110 to 160) times / min. Therefore, it is necessary to determine corresponding detection baselines (i.e., target fetal heart rate detection baseline and target uterine contraction detection baseline) for fetal heart rate and uterine contraction rate respectively. In this way, when performing abnormality detection, the target fetal heart rate data can be detected based on the target fetal heart rate detection baseline to obtain a first detection result, and the target uterine contraction rate data can be detected based on the target uterine contraction detection baseline to obtain a second detection result. Finally, based on the first detection result and the second detection result, the target detection result is obtained. This can improve the targeting and accuracy of abnormality detection.

[0046] S103, if the target detection result indicates that there is abnormal data in the target fetal heart rate monitoring data, generate a prompt message based on the abnormal data.

[0047] The prompt information may be text, images, sound, or other information, and is not limited to any particular type.

[0048] It should be understood that the target detection result is used to indicate whether there is abnormal data in the target fetal heart rate monitoring data, and when the target detection result indicates that there is abnormal data in the target fetal heart rate monitoring data, a prompt message is generated based on the abnormal data. In this way, the user (e.g., a doctor) can be notified of the abnormality in the current fetal heart rate monitoring data at the first time.

[0049] In some implementations, for step S102, since the target detection baseline includes reference data corresponding to the target fetal heart rate monitoring data, when determining the target detection baseline matching the target fetal heart rate monitoring data based on the target fetal heart rate monitoring data, please refer to [link to relevant documentation]. Figure 3 It may include the following steps S102a to S102c:

[0050] S102a, based on the target fetal heart rate monitoring data and the first baseline detection algorithm, a first detection baseline is determined, the first detection baseline including first reference data corresponding to the target fetal heart rate monitoring data.

[0051] S102b, Based on the target fetal heart rate monitoring data and the second baseline detection algorithm, a second detection baseline is determined, the second detection baseline including second reference data corresponding to the target fetal heart rate monitoring data.

[0052] S102c, the target detection baseline is determined based on the first reference data in the first detection baseline and the second reference data in the second detection baseline.

[0053] It should be noted that, since the target fetal heart rate monitoring data typically includes fetal heart rate monitoring data from different time points, each data point in the first baseline of the established first detection baseline corresponds one-to-one with the fetal heart rate monitoring data. Similarly, each data point in the second baseline of the second detection baseline also corresponds one-to-one with the fetal heart rate monitoring data.

[0054] It should be understood that since the first baseline monitoring algorithm and the second baseline monitoring algorithm are different, the first detection baseline and the second detection baseline determined based on the above two algorithms may also be different. By determining the target detection baseline based on the first detection baseline and the second detection baseline, the robustness of the target detection baseline can be improved, thereby improving the accuracy of the target detection baseline.

[0055] The specific implementation logic of the first baseline detection algorithm and the second baseline detection algorithm will be described in detail later.

[0056] In some implementations, since the target fetal heart rate monitoring data includes target fetal heart rate data and target uterine contraction rate data, a target fetal heart rate detection baseline corresponding to the target fetal heart rate data can be determined. Specifically, a first fetal heart rate detection baseline corresponding to the target fetal heart rate data and a second fetal heart rate detection baseline corresponding to the target fetal heart rate data can be determined. Thus, the target fetal heart rate detection baseline is obtained based on the first fetal heart rate detection baseline and the second fetal heart rate detection baseline. Similarly, for the target uterine contraction rate data, a target uterine contraction detection baseline corresponding to the target uterine contraction rate data can be determined. Specifically, a first uterine contraction detection baseline corresponding to the target uterine contraction rate data and a second uterine contraction detection baseline corresponding to the target uterine contraction rate data can be determined. Thus, the target uterine contraction detection baseline is obtained based on the first uterine contraction detection baseline and the second uterine contraction detection baseline.

[0057] The following uses the target fetal heart rate data as an example to explain in detail the above steps S102a to S102c. Specifically, the first fetal heart rate detection baseline can be determined based on the target fetal heart rate data and the first baseline detection algorithm, including the following (a) to (d):

[0058] (a) Obtain a preset first fetal heart rate fluctuation parameter, the first fetal heart rate fluctuation parameter including at least a first fetal heart rate fluctuation threshold, a preset lower limit of fetal heart rate, a preset upper limit of fetal heart rate and fetal heart rate baseline distribution data, the fetal heart rate baseline distribution data including different fetal heart rate baseline intervals and the number of distributions corresponding to each fetal heart rate baseline interval.

[0059] The first fetal heart rate fluctuation parameter can be set according to actual needs and is not limited here.

[0060] In some implementations, the first fetal heart rate fluctuation parameter may further include an initial fetal heart rate detection baseline and a data scanning frequency. The initial fetal heart rate detection baseline and the data scanning frequency are used as stable data for an initial preset time period in the fetal heart rate baseline distribution data. For example, if the first fetal heart rate fluctuation threshold is h, the initial fetal heart rate detection baseline is y0, and the data scanning frequency is p, then the fetal heart rate baseline interval for the initial preset time period in the fetal heart rate baseline distribution data is [y0-h:y0+h], and the distribution frequency corresponding to this interval is 1 / p.

[0061] (b) For each fetal heart rate value, a first target fetal heart rate baseline interval is determined based on the first fetal heart rate fluctuation parameter and the fetal heart rate value, and the fetal heart rate baseline distribution data is updated based on the first target fetal heart rate baseline interval.

[0062] Specifically, for each fetal heart rate value, the difference between the fetal heart rate value and the first fetal heart rate fluctuation threshold can be determined first, and the larger value between the difference and the preset lower limit of fetal heart rate can be determined. The sum of the fetal heart rate value and the first fetal heart rate fluctuation threshold can be determined, and the smaller value between the sum and the preset upper limit of fetal heart rate can be determined. Then, a baseline interval is generated based on the larger value and the smaller value, and the baseline interval is added to the fetal heart rate baseline distribution data. The distribution count corresponding to the baseline interval is incremented by 1 to update the fetal heart rate baseline distribution data.

[0063] For example, if the first fetal heart rate fluctuation threshold h = 5, the preset lower fetal heart rate limit A = 90, and the preset upper fetal heart rate limit B = 120, the target fetal heart rate data includes the fetal heart rate value x. i Given [100, 105, 106], for a fetal heart rate value x1 = 100, we can first determine the difference between the fetal heart rate value and the first fetal heart rate fluctuation threshold, mint = x1 - h = 95. The larger value between the difference mint and the preset lower fetal heart rate limit A is mint = 95. Then, we determine the sum of the fetal heart rate value x1 and the first fetal heart rate fluctuation threshold h, maxt = x1 + h = 105. The smaller value between this sum maxt and the preset upper fetal heart rate limit A is maxt = 105. Thus, based on the larger value mint = 95 and the smaller value maxt = 95, we can determine the larger value mint = 95 and the smaller value maxt = 95. 105 can generate a baseline interval [95, 105), and add the generated baseline interval [95, 105) to the fetal heart rate baseline distribution data. Then the distribution frequency corresponding to the baseline interval [95, 105) is 1. It should be noted that before this, the fetal heart rate baseline distribution data does not contain any data by default. Therefore, after adding the baseline interval [95, 105) to the fetal heart rate baseline distribution data, the distribution frequency corresponding to the baseline interval [95, 105) in the fetal heart rate baseline distribution data is 1. That is, the current fetal heart rate baseline distribution data is: [95, 105), and the corresponding distribution frequency is 1.

[0064] For a fetal heart rate value x2 = 105, we can first determine the difference between the fetal heart rate value and the first fetal heart rate fluctuation threshold, mint = x2 - h = 100. The larger value between the difference mint and the preset lower fetal heart rate limit A is mint = 100. Then, we determine the sum of the fetal heart rate value x2 and the first fetal heart rate fluctuation threshold h, maxt = x2 + h = 110. The smaller value between this sum maxt and the preset upper fetal heart rate limit A is maxt = 110. Thus, based on the larger value mint = 100 and the smaller value... The value maxt = 110 can generate the baseline interval [100, 110), and add the generated baseline interval [100:110) to the fetal heart rate baseline distribution data. The distribution frequency corresponding to the baseline interval [100, 110) is increased by 1. Since the fetal heart rate baseline distribution data also includes [95, 105), the updated fetal heart rate baseline distribution data is as follows: the distribution frequency corresponding to [95:100) is 1, the distribution frequency corresponding to [100:105) is 2, and the distribution frequency corresponding to [105:110) is 1.

[0065] Similarly, for a fetal heart rate value x3 = 106, we can determine that mint = x3 - h = 101. The larger value between the difference mint and the preset lower limit of fetal heart rate A is mint = 101, and maxt = x3 + h = 111. Then, we can determine that the smaller value between the sum maxt and the preset upper limit of fetal heart rate A is maxt = 111, generating a baseline interval of [101:111). We increase the distribution frequency of the baseline interval [101:111) by 1 and continue to update the fetal heart rate baseline distribution data. The updated fetal heart rate baseline distribution data are: [95:100), with a distribution frequency of 1; 100, with a distribution frequency of 2; [101:105), with a distribution frequency of 3; [105:110], with a distribution frequency of 2; and 111, with a distribution frequency of 1.

[0066] (c) Determine the second target fetal heart rate baseline interval with the maximum number of distributions in the fetal heart rate baseline distribution data, and determine any one of the fetal heart rate values ​​in the second target fetal heart rate baseline interval as the reference data corresponding to the fetal heart rate value.

[0067] It is understood that for each fetal heart rate value, there is a corresponding updated fetal heart rate baseline distribution data. This data contains at least one baseline interval. Therefore, a second target fetal heart rate baseline interval with the highest distribution frequency can be selected from the baseline distribution intervals. One fetal heart rate value within this second target fetal heart rate baseline interval can be determined as the benchmark data corresponding to the fetal heart rate value. Optionally, when determining the benchmark data, the first fetal heart rate value (lower limit of the interval) within the second target fetal heart rate baseline interval can be selected as the benchmark data. In other embodiments, the last fetal heart rate value (upper limit of the interval) can also be selected as the benchmark data, or an intermediate value can be selected. No limitation is made here. Furthermore, for each second target fetal heart rate baseline interval, the first fetal heart rate value (lower limit of the interval) can be selected as the benchmark data, which can further improve the accuracy of the first fetal heart rate detection baseline.

[0068] Based on the above example, when the fetal heart rate value x1 = 100, the fetal heart rate baseline distribution data is [95, 105), and the corresponding distribution frequency is 1. Since the fetal heart rate baseline distribution data only includes one baseline interval, one of the values ​​in [95, 105) can be selected as the baseline data. For example, 95 can be used as the baseline data. Similarly, for the fetal heart rate value x2 = 105, the updated fetal heart rate baseline distribution data is: [95:100) with a distribution frequency of 1, [100:105) with a distribution frequency of 2, and [105:110) with a distribution frequency of 1. It can be seen that the maximum distribution frequency is 2. Therefore, the second target fetal heart rate baseline interval is [100:105), and 100 can be used as the baseline data. For a fetal heart rate value x3 = 106, the updated fetal heart rate baseline distribution data are: [95:100), corresponding to a distribution frequency of 1; 100, corresponding to a distribution frequency of 2; [101:105), corresponding to a distribution frequency of 3; [105:110], corresponding to a distribution frequency of 2; 111, corresponding to a distribution frequency of 1. It can be seen that the maximum distribution frequency is 3. Therefore, the second target fetal heart rate baseline interval is [101:105), and 101 can be used as the baseline data. Thus, the baseline data corresponding to x1 is determined to be 95, the baseline data corresponding to x2 is 100, and the baseline data corresponding to x3 is 101.

[0069] (d) Based on the baseline data corresponding to each fetal heart rate value, the first fetal heart rate detection baseline is obtained.

[0070] After obtaining the baseline data corresponding to each of the above fetal heart rate values, the first fetal heart rate detection baseline can be obtained as [95, 100, 101].

[0071] Similarly, a second fetal heart rate detection baseline can be determined based on the target fetal heart rate data and the second baseline detection algorithm. Specifically, this can include the following steps:

[0072] (1) Obtain a preset second fetal heart rate fluctuation parameter and a preset multiple fetal heart rate queues, wherein the second fetal heart rate fluctuation parameter includes at least a second fetal heart rate fluctuation threshold.

[0073] The preset multiple fetal heart rate queues include a main fetal heart rate queue, a secondary fetal heart rate queue, and a fetal heart rate average queue.

[0074] (2) For each fetal heart rate value, based on the second fetal heart rate fluctuation threshold, the fetal heart rate value and the target fetal heart rate baseline data, the data of the multiple fetal heart rate queues are updated, and based on the data length of each updated fetal heart rate queue, the second fetal heart rate detection baseline is determined; the target fetal heart rate baseline data refers to the baseline data corresponding to the previous fetal heart rate value adjacent to the fetal heart rate value.

[0075] First, based on the difference between the determined fetal heart rate value and the target fetal heart rate baseline data, if the difference is less than the second fetal heart rate fluctuation threshold, the fetal heart rate value is added to the main fetal heart rate queue. Then, according to the first-in, first-out (FIFO) principle, the fetal heart rate value that entered the queue first is deleted from both the main and secondary fetal heart rate queues to update the data in the multiple fetal heart rate queues. Here, deleting the fetal heart rate value that entered the queue first from both the main and secondary fetal heart rate queues ensures that the data used in subsequent calculations of the second fetal heart rate baseline is the most recently updated data. Thus, even if data from historical periods is abnormal, it will be removed during subsequent calculations of the second fetal heart rate baseline, preventing any impact on the accuracy of the subsequent baseline determination.

[0076] Then, after updating the data of multiple fetal heart rate queues, it can be determined whether the data length of the main fetal heart rate queue is less than the data length of the secondary fetal heart rate queue. If the data length of the main fetal heart rate queue is not less than the data length of the secondary fetal heart rate queue, the average value of each fetal heart rate value currently included in the main fetal heart rate queue is added to the fetal heart rate average queue. The average value of all values ​​currently included in the fetal heart rate average queue is determined as the baseline data corresponding to the fetal heart rate value. Then, based on the baseline data corresponding to each fetal heart rate value, the second fetal heart rate detection baseline is generated.

[0077] In some implementations, if the difference between the fetal heart rate value and the target fetal heart rate baseline is not less than the second fetal heart rate fluctuation threshold, the fetal heart rate value is added to the fetal heart rate sub-queue. Then, it is determined whether the data length of the fetal heart rate main queue is less than the data length of the fetal heart rate sub-queue. If the data length of the fetal heart rate main queue is not less than the data length of the fetal heart rate sub-queue, the average value of all fetal heart rate values ​​currently included in the fetal heart rate main queue is added to the fetal heart rate mean queue. The average value of all values ​​currently included in the fetal heart rate mean queue is determined as the baseline data corresponding to the fetal heart rate value. Based on the baseline data corresponding to each fetal heart rate value, the second fetal heart rate detection baseline is generated. Thus, since the queue supports streaming data processing, data processing efficiency can be improved.

[0078] In other implementations, if the data length of the main fetal heart rate queue is shorter than the data length of the secondary fetal heart rate queue, the main and secondary fetal heart rate queues are swapped to ensure that the data length of the main fetal heart rate queue after the swap is not shorter than that of the secondary fetal heart rate queue. That is, the data in the secondary fetal heart rate queue can be considered to deviate significantly from the baseline data, while the data in the main fetal heart rate queue deviates less significantly from the baseline data. If the data length of the main fetal heart rate queue is shorter than that of the secondary fetal heart rate queue, it indicates that the current baseline data itself is incorrect, and the main and secondary fetal heart rate queues need to be swapped to re-determine the baseline data. This improves the accuracy of the baseline data.

[0079] Similarly, when determining the target detection baseline based on the first reference data in the first detection baseline and the second reference data in the second detection baseline, the target fetal heart rate detection baseline can be determined based on the first reference data in the first fetal heart rate detection baseline and the second reference data in the second fetal heart rate detection baseline.

[0080] In some implementations, the average of the first and second baseline data can be determined and used as the target fetal heart rate detection baseline. It should be noted that since the first and second baseline data may contain multiple data points, it is necessary to average the first and second baseline data for each group corresponding to the same fetal heart rate value. For example, if the first baseline data is [100, 102, 102, 103, 104] and the second baseline data is [100, 104, 103, 105, 106], then the target fetal heart rate detection baseline is [100, 103, 102.5, 104, 105]. In other implementations, a weighted average between the first and second baseline data can also be determined. For example, a first weight is assigned to the first baseline data, a second weight is assigned to the second baseline data, and a weighted average is calculated.

[0081] In this embodiment, two fetal heart rate baseline monitoring algorithms are used to determine the first fetal heart rate detection baseline and the second fetal heart rate detection baseline, respectively. Based on the first reference data in the first fetal heart rate detection baseline and the second reference data in the second fetal heart rate detection baseline, the target fetal heart rate detection baseline is determined. In this way, the robustness of the target fetal heart rate detection baseline can be improved.

[0082] In some optional implementations, when determining a target contraction detection baseline that matches the target contraction rate data, a first contraction detection baseline can be determined based on the target contraction rate data and a preset first baseline detection algorithm. The first contraction detection baseline includes third reference data corresponding to the target contraction rate data. Then, a second contraction detection baseline is determined based on the target contraction rate data and a preset second baseline detection algorithm. The second contraction detection baseline includes fourth reference data corresponding to the target contraction rate data. Finally, the target contraction detection baseline is determined based on the third reference data in the first contraction detection baseline and the fourth reference data in the second contraction detection baseline. This can improve the robustness of the target contraction detection baseline.

[0083] Specifically, the target contraction rate data includes contraction rate values ​​corresponding to different times within the preset time period; when determining the first contraction detection baseline based on the target contraction rate data and a preset first baseline detection algorithm, preset first contraction fluctuation parameters and contraction baseline distribution data can be obtained. The first contraction fluctuation parameters include at least a first contraction fluctuation threshold, a preset lower contraction limit, and a preset upper contraction limit; the contraction baseline distribution data includes different contraction baseline intervals and the distribution frequency corresponding to each contraction baseline interval; then, for each contraction rate value, based on the first contraction fluctuation parameters and the contraction rate value, a first target contraction baseline interval is determined, and the contraction baseline distribution data is updated based on the first contraction fetal heart rate baseline interval; and a second target contraction baseline interval with the maximum distribution frequency is determined in the updated contraction baseline distribution data, and any one of the contraction rate values ​​in the second target contraction baseline interval is determined as the benchmark data corresponding to the contraction rate value; finally, the first contraction detection baseline is obtained based on the benchmark data corresponding to each contraction rate value.

[0084] Optionally, when determining the second detection baseline based on the target fetal heart rate monitoring data and the second baseline detection algorithm, a preset second contraction fluctuation parameter and multiple preset contraction queues can be obtained. The second contraction fluctuation parameter includes at least a second contraction fluctuation threshold. Then, for each contraction rate value, the multiple contraction queues are updated based on the second contraction fluctuation threshold, the contraction rate value, and the target contraction baseline data. Based on the updated data length of each contraction queue, the second contraction detection baseline is determined. The target contraction baseline data refers to the baseline data corresponding to the preceding contraction rate value adjacent to the contraction rate value. The preset multiple contraction queues include a primary contraction queue, a secondary contraction queue, and a contraction mean queue.

[0085] Specifically, when updating the data of the multiple contraction queues based on the second contraction fluctuation threshold, the contraction rate value, and the target contraction baseline data, and determining the second contraction detection baseline based on the updated data length of each contraction queue, for each contraction rate value, if the difference between the contraction rate value and the target contraction baseline data is less than the second contraction fluctuation threshold, the contraction rate value is added to the main contraction queue; according to the first-in-first-out principle, the contraction rate value that entered the queue first is deleted from both the main contraction queue and the secondary contraction queue; and if the data length of the main contraction queue is not less than the data length of the secondary contraction queue, the average value of each contraction rate value in the main contraction queue is added to the contraction average queue, and the average value of all values ​​in the contraction average queue is determined as the baseline data corresponding to the contraction rate value; finally, the second contraction detection baseline is generated based on the baseline data corresponding to each contraction rate value.

[0086] Optionally, if the difference between the contraction rate value and the target contraction baseline data is not less than the second contraction fluctuation threshold, the contraction rate value is added to the contraction sub-queue. If the data length of the contraction sub-queue is greater than the data length of the contraction main queue, the contraction sub-queue is swapped with the contraction main queue so that the data length of the contraction main queue is not less than the data length of the contraction sub-queue. Then, a second contraction detection baseline is generated based on the data in the contraction main queue.

[0087] It should be noted that since the first baseline detection algorithm used to generate the first uterine contraction detection baseline is the same as the first baseline detection algorithm used to generate the first fetal heart rate detection baseline, and the second baseline detection algorithm used to generate the second uterine contraction detection baseline is the same as the second baseline detection algorithm used to generate the second fetal heart rate detection baseline, please refer to the specific description of generating the first fetal heart rate detection baseline in the above embodiments for the specific algorithm implementation logic of generating the first uterine contraction detection baseline, and please refer to the specific description of generating the second fetal heart rate detection baseline in the above embodiments for the specific algorithm implementation logic of generating the second uterine contraction detection baseline, and will not be repeated here.

[0088] In some implementations, regarding step S103, when the target detection result indicates the presence of abnormal data in the fetal heart rate monitoring data, and a prompt message is generated based on the abnormal data, please refer to [link to relevant documentation]. Figure 4 It may include the following steps S1031 to S1035:

[0089] S1031, if the target detection result indicates that there is abnormal data in the fetal heart rate monitoring data, target abnormal information corresponding to the abnormal data is generated based on the abnormal data; the target abnormal information includes the abnormal start time and abnormal type of the target abnormality.

[0090] The abnormal types may include fetal bradycardia without baseline variability, fetal tachycardia, fetal bradycardia, variability (without repetitive decelerations), minimal variability, significant boundary, no acceleration after fetal stimulation, repetitive variable decelerations with minimal or normal baseline variability, prolonged decelerations, repetitive late decelerations with normal variability, variable decelerations with other characteristics (such as slow baseline recovery, "sharp beak" or "double-sharp beak"), repetitive late decelerations, repetitive variable decelerations, and sinusoidal waveforms.

[0091] S1032, determine whether the current acquisition time is the first acquisition time. If yes, proceed to step S1033; otherwise, proceed to step S1034.

[0092] S1033, Based on the target abnormal information corresponding to the abnormal data, generate a prompt message.

[0093] It is understandable that if the current collection time is the first collection time, it means that the abnormal data is appearing for the first time, and a prompt message can be generated based on the target abnormal information corresponding to the abnormal data.

[0094] S1034, Obtain historical anomaly information corresponding to the previous acquisition time adjacent to the current acquisition time.

[0095] Here, the historical abnormal information corresponding to the previous acquisition time adjacent to the current acquisition time refers to the historical abnormal information corresponding to the fetal heart rate monitoring data collected within a preset time period with the previous acquisition time adjacent to the current acquisition time as the time endpoint.

[0096] Specifically, it can be determined in advance whether the fetal heart rate monitoring data obtained at the previous acquisition time adjacent to the current acquisition time contains abnormal data. If abnormal data is contained, the historical abnormal information corresponding to the previous acquisition time adjacent to the current acquisition time can be obtained.

[0097] S1035, the target anomaly information is matched with the historical anomaly information to obtain a matching result, and if the matching result indicates that there is new anomaly information in the target anomaly information relative to the historical anomaly information, the prompt information is generated.

[0098] It should be understood that the persistence of historical anomalies is affected by the time of data collection. That is, the historical anomaly corresponding to the previous data collection time may still exist at the current data collection time. Therefore, if the current data collection time is not the first data collection time, it is necessary to match the target anomaly information with the historical anomaly information to determine whether the target anomaly information is a new anomaly information relative to the historical anomaly information. If so, a prompt message is generated.

[0099] Optionally, regarding step S1035, when matching the target anomaly information with the historical anomaly information to obtain a matching result, and when the matching result indicates that the target anomaly information has newly added anomaly information relative to the historical anomaly information, the prompt information is generated, please refer to [link to relevant documentation]. Figure 5 This may include the following steps:

[0100] S10351, determine whether the time difference between the current acquisition time and the abnormal end time of the target abnormality is less than the first preset time threshold. If yes, execute step S10352; if no, execute step S10356.

[0101] The first preset time threshold can be set according to actual needs, such as 30 seconds, 50 seconds or 1 minute, etc., without limitation.

[0102] In this step, the purpose of determining whether the first time difference between the current acquisition time and the end time of the target anomaly is less than the first preset time threshold is to determine whether the target anomaly has ended by setting the first preset time. That is, if the first time difference between the current acquisition time and the end time of the target anomaly is less than the first preset time threshold, it means that the end time of the target anomaly is close to the current acquisition time. At this time, the target anomaly may not have ended. For the target anomaly in this case, further judgment is needed, that is, step S10352 is executed. In another case, if the first time difference between the current acquisition time and the end time of the target anomaly is not less than the first preset time threshold, it means that the end time of the target anomaly is far from the current acquisition time. It means that the target anomaly has ended at this time, and step S10356 is executed.

[0103] S10352, determine from the historical anomaly information a first historical anomaly information where the time interval between the anomaly end time and the current collection time is less than a second preset time threshold.

[0104] The second preset time threshold can be set according to actual needs, and the second preset time threshold is greater than the first preset time threshold.

[0105] It should be understood that since the target anomaly may be the same as the historical anomaly or it may be a newly added anomaly, it is necessary to determine the first historical anomaly information from the historical anomaly information, which is less than the time interval between the anomaly end time and the current collection time. This first historical anomaly information is then used to determine whether the target anomaly is newly added in subsequent steps.

[0106] For example, please see Figure 6 This is a schematic diagram illustrating the determination of newly added abnormal information provided in some embodiments of this disclosure. Figure 6 In this diagram, line segment X represents the target fetal heart rate monitoring data acquired up to the current acquisition time T_now. T1 represents the first preset time threshold, T2 represents the second preset time threshold, xi represents the target abnormality, and x1, x2, and x3 refer to historical abnormalities. To determine whether xi is a newly added abnormality, it needs to be compared with historical abnormalities. Therefore, by setting the second preset time threshold, the first historical abnormality information (e.g., x1, x2, x3) is determined from the historical abnormality information and compared with xi. It should be noted that the number of abnormalities in the above example is only illustrative.

[0107] S10353, determine whether there is a historical anomaly in the first historical anomaly information that has the same anomaly type as the target anomaly in the target anomaly information. If yes, proceed to step S10354; otherwise, proceed to step S10355.

[0108] S10354, update the end time of the historical anomaly with the same anomaly type as the target anomaly in the first historical anomaly information to the current collection time.

[0109] It is understood that if any historical anomaly in the first historical anomaly information has the same anomaly type as the target anomaly in the target anomaly information, it means that the historical anomaly and the target anomaly are the same anomaly. Furthermore, when this anomaly first appeared as a newly added anomaly, a prompt message was already generated. Therefore, it is not necessary to generate a prompt message again. It is only necessary to update the anomaly end time of the first historical anomaly information to the current collection time. This can avoid repeated prompts for the same anomaly information. Moreover, when performing subsequent anomaly detection based on the anomaly end time of the updated first historical anomaly information, the accuracy of anomaly detection can be improved.

[0110] S10355, the target abnormal information is identified as the newly added abnormal information, and the prompt information is generated.

[0111] If the anomaly type of each historical anomaly in the first historical anomaly information is different from the anomaly type of the target anomaly in the target anomaly information, it indicates that the anomaly is a newly added anomaly. That is, the target anomaly information can be identified as newly added anomaly information, and the prompt information can be generated.

[0112] S10356, determine from the historical anomaly information a second historical anomaly information whose time interval between the anomaly end time and the anomaly end time of the target anomaly information is less than a third preset time threshold.

[0113] The third preset time threshold can also be set according to actual needs, and is not limited here.

[0114] As described in step S10351, if the first time difference between the current acquisition time and the end time of the target anomaly is not less than the first preset time threshold, it indicates that the end time of the target anomaly is far from the current acquisition time, and it can be considered that the target anomaly has ended. Therefore, it can be determined whether the target anomaly is a newly added anomaly.

[0115] For example, please see Figure 7 This is a schematic diagram illustrating the determination of newly added abnormal information provided in other embodiments of this disclosure. Figure 7 The midline segment X represents the target fetal heart rate monitoring data acquired up to the current acquisition time T_now. T1 represents the first preset time threshold, T3 represents the third preset time threshold, and xi represents the target abnormality. At this time, we can use xi as the center and T3 as the filtering condition to determine the second historical abnormality information (e.g., x1, x2, x3) at both ends of the midline segment X.

[0116] In some implementations, if no second historical anomaly information is found in the historical anomaly information, it indicates that the target anomaly information is newly added. A prompt message needs to be generated, and the target anomaly information is written into the historical anomaly information for subsequent anomaly detection.

[0117] S10357, determine whether there is a historical anomaly in the second historical anomaly information that has the same anomaly type as the target anomaly in the target anomaly information. If yes, proceed to step S10358; otherwise, proceed to step S10359.

[0118] S10358, determine that the target abnormal information is not the newly added abnormal information.

[0119] It is understandable that if the anomaly type in the target anomaly information is the same as the anomaly type of one of the historical anomalies in the second historical anomaly information, then it is determined that the target anomaly information is not a newly added anomaly information, and the anomaly information has already generated corresponding prompt information in the historical time, so no other processing is required.

[0120] S10359, the target abnormal information is identified as the newly added abnormal information, the prompt information is generated, and the target abnormal information is added to the historical abnormal information.

[0121] Here, if the anomaly type in the target anomaly information is different from the anomaly type of each historical anomaly in the second historical anomaly information, it means that the target anomaly information is newly added. In this case, a prompt message needs to be generated and the target anomaly information is added to the historical anomaly information for subsequent anomaly detection.

[0122] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0123] Based on the same inventive concept, this disclosure also provides a fetal heart rate detection device corresponding to the fetal heart rate detection method. Since the principle of the device in this disclosure is similar to that of the above-mentioned fetal heart rate detection method in this disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0124] Reference Figure 8 The diagram shown is a schematic of a fetal heart rate monitoring device 800 provided in an embodiment of this disclosure. The device includes:

[0125] Data acquisition module 801 is used to acquire target fetal heart rate monitoring data within a preset time period ending at the current acquisition time.

[0126] Anomaly detection module 802 is used to determine a target detection baseline that matches the target fetal heart rate monitoring data based on the target fetal heart rate monitoring data, and to perform anomaly detection on the target fetal heart rate monitoring data based on the target detection baseline to obtain a target detection result;

[0127] The abnormality alert module 803 is used to generate alert information based on the abnormal data when the target detection result indicates that there is abnormal data in the target fetal heart rate monitoring data.

[0128] In one possible implementation, the target fetal heart rate monitoring data includes target fetal heart rate data and target uterine contraction rate data; the anomaly detection module 802 is specifically used for:

[0129] Based on the target fetal heart rate data, a target fetal heart rate detection baseline matching the target fetal heart rate data is determined; and based on the target uterine contraction rate data, a target uterine contraction detection baseline matching the target uterine contraction rate data is determined.

[0130] Based on the target fetal heart rate detection baseline, anomaly detection is performed on the target fetal heart rate data to obtain a first detection result of the target fetal heart rate data; and based on the target uterine contraction detection baseline, anomaly detection is performed on the target uterine contraction rate data to obtain a second detection result of the target uterine contraction rate data.

[0131] The target detection result is generated based on the first detection result and the second detection result.

[0132] In one possible implementation, the target detection baseline includes benchmark data corresponding to the target fetal heart rate monitoring data; the anomaly detection module 802 is specifically used for:

[0133] Based on the target fetal heart rate monitoring data and the first baseline detection algorithm, a first detection baseline is determined, and the first detection baseline includes first reference data corresponding to the target fetal heart rate monitoring data.

[0134] Based on the target fetal heart rate monitoring data and the second baseline detection algorithm, a second detection baseline is determined, which includes second reference data corresponding to the target fetal heart rate monitoring data.

[0135] The target detection baseline is determined based on the first reference data in the first detection baseline and the second reference data in the second detection baseline.

[0136] In one possible implementation, the target fetal heart rate monitoring data includes target fetal heart rate data, the first detection baseline includes a first fetal heart rate detection baseline, and the target fetal heart rate data includes fetal heart rate values ​​corresponding to different times within the preset time period; the anomaly detection module 802 is specifically used for:

[0137] Acquire preset first fetal heart rate fluctuation parameters and fetal heart rate baseline distribution data. The first fetal heart rate fluctuation parameters include at least a first fetal heart rate fluctuation threshold, a preset lower fetal heart rate limit, and a preset upper fetal heart rate limit. The fetal heart rate baseline distribution data includes different fetal heart rate baseline intervals and the distribution frequency corresponding to each fetal heart rate baseline interval.

[0138] For each fetal heart rate value, a first target fetal heart rate baseline interval is determined based on the first fetal heart rate fluctuation parameter and the fetal heart rate value, and the fetal heart rate baseline distribution data is updated based on the first target fetal heart rate baseline interval.

[0139] Determine the second target fetal heart rate baseline interval with the maximum number of distributions in the updated fetal heart rate baseline distribution data, and determine any one of the fetal heart rate values ​​in the second target fetal heart rate baseline interval as the reference data corresponding to the fetal heart rate value;

[0140] The first fetal heart rate detection baseline is obtained based on the benchmark data corresponding to each fetal heart rate value.

[0141] In one possible implementation, the target fetal heart rate monitoring data includes target fetal heart rate data, the second detection baseline includes a second fetal heart rate detection baseline, and the target fetal heart rate data includes fetal heart rate values ​​corresponding to different times within the preset time period; the anomaly detection module 802 is specifically used for:

[0142] Obtain preset second fetal heart rate fluctuation parameters and preset multiple fetal heart rate queues, wherein the second fetal heart rate fluctuation parameters include at least a second fetal heart rate fluctuation threshold;

[0143] For each fetal heart rate value, the data of the multiple fetal heart rate queues is updated based on the second fetal heart rate fluctuation threshold, the fetal heart rate value, and the target fetal heart rate baseline data. Based on the updated data length of each fetal heart rate queue, the second fetal heart rate detection baseline is determined. The target fetal heart rate baseline data refers to the baseline data corresponding to the previous fetal heart rate value adjacent to the fetal heart rate value.

[0144] In one possible implementation, the preset multiple fetal heart rate queues include a main fetal heart rate queue, a secondary fetal heart rate queue, and a fetal heart rate average queue; the anomaly detection module 802 is specifically used for:

[0145] For each fetal heart rate value, if the difference between the fetal heart rate value and the target fetal heart rate baseline data is less than the second fetal heart rate fluctuation threshold, the fetal heart rate value is added to the fetal heart rate master queue.

[0146] According to the first-in-first-out principle, the fetal heart rate value that entered the queue first is deleted from both the main fetal heart rate queue and the secondary fetal heart rate queue.

[0147] If the data length of the main fetal heart rate queue is not less than the data length of the secondary fetal heart rate queue, the average value of each fetal heart rate in the main fetal heart rate queue is added to the fetal heart rate mean queue, and the average value of all values ​​in the fetal heart rate mean queue is determined as the baseline data corresponding to the fetal heart rate value.

[0148] The second fetal heart rate detection baseline is generated based on the baseline data corresponding to each fetal heart rate value.

[0149] In one possible implementation, the anomaly detection module 802 is further configured to:

[0150] If the difference between the fetal heart rate value and the target fetal heart rate baseline data is not less than the second fetal heart rate fluctuation threshold, the fetal heart rate value is added to the fetal heart rate sub-queue. If the data length of the fetal heart rate sub-queue is greater than the data length of the fetal heart rate main queue, the fetal heart rate sub-queue is swapped with the fetal heart rate main queue so that the data length of the fetal heart rate main queue is not less than the data length of the fetal heart rate sub-queue.

[0151] In one possible implementation, the target fetal heart rate monitoring data includes target uterine contraction rate data, the first detection baseline includes a first uterine contraction detection baseline, and the target uterine contraction rate data includes uterine contraction rate values ​​corresponding to different times within the preset time period; the abnormality detection module 802 is specifically used for:

[0152] Obtain preset first contraction fluctuation parameters and contraction baseline distribution data. The first contraction fluctuation parameters include at least a first contraction fluctuation threshold, a preset lower limit of contractions, and a preset upper limit of contractions. The contraction baseline distribution data includes different contraction baseline intervals and the number of distributions corresponding to each contraction baseline interval.

[0153] For each contraction rate value, a first target contraction baseline interval is determined based on the first contraction fluctuation parameter and the contraction rate value, and the contraction baseline distribution data is updated based on the first contraction fetal heart rate baseline interval.

[0154] Determine the second target uterine contraction baseline interval with the maximum number of distributions in the updated uterine contraction baseline distribution data, and determine any one of the uterine contraction rate values ​​in the second target uterine contraction baseline interval as the baseline data corresponding to the uterine contraction rate value;

[0155] The first uterine contraction detection baseline is obtained based on the benchmark data corresponding to each uterine contraction rate value.

[0156] In one possible implementation, the target fetal heart rate monitoring data includes target uterine contraction rate data, the second detection baseline includes a second uterine contraction detection baseline, and the target uterine contraction rate data includes uterine contraction rate values ​​corresponding to different times within the preset time period; the abnormality detection module 802 is specifically used for:

[0157] Obtain a preset second contraction fluctuation parameter and a preset multiple contraction queues, wherein the second contraction fluctuation parameter includes at least a second contraction fluctuation threshold;

[0158] For each contraction rate value, the multiple contraction queues are updated based on the second contraction fluctuation threshold, the contraction rate value, and the target contraction baseline data. The second contraction detection baseline is determined based on the updated data length of each contraction queue. The target contraction baseline data refers to the baseline data corresponding to the previous contraction rate value adjacent to the contraction rate value.

[0159] In one possible implementation, the preset multiple contraction queues include a main contraction queue, a secondary contraction queue, and a contraction average queue; the anomaly detection module 802 is specifically used for:

[0160] For each contraction rate value, if the difference between the contraction rate value and the target contraction baseline data is less than the second contraction fluctuation threshold, the contraction rate value is added to the main contraction queue.

[0161] According to the first-in, first-out principle, the contraction rate value that entered the queue first is deleted from both the main contraction queue and the secondary contraction queue.

[0162] If the data length of the main contraction queue is not less than the data length of the secondary contraction queue, the average value of each contraction rate in the main contraction queue is added to the average contraction queue, and the average value of all values ​​in the average contraction queue is determined as the baseline data corresponding to the contraction rate value.

[0163] The second uterine contraction detection baseline is generated based on the baseline data corresponding to each uterine contraction rate value.

[0164] In one possible implementation, the anomaly detection module 802 is further configured to:

[0165] If the difference between the contraction rate value and the target contraction baseline data is not less than the second contraction fluctuation threshold, the contraction rate value is added to the contraction sub-queue. If the data length of the contraction sub-queue is greater than the data length of the contraction main queue, the contraction sub-queue is swapped with the contraction main queue so that the data length of the contraction main queue is not less than the data length of the contraction sub-queue.

[0166] In one possible implementation, the time interval between adjacent data collection moments is less than the duration of the preset time period; the anomaly alert module 803 is specifically used for:

[0167] If the target detection result indicates that there is abnormal data in the fetal heart rate monitoring data, target abnormal information corresponding to the abnormal data is generated based on the abnormal data; the target abnormal information includes the abnormal start time and abnormal type of the target abnormality.

[0168] If the current acquisition time is not the first acquisition time, obtain the historical anomaly information corresponding to the previous acquisition time adjacent to the current acquisition time;

[0169] The target anomaly information is matched with the historical anomaly information to obtain a matching result. If the matching result indicates that there is new anomaly information in the target anomaly information relative to the historical anomaly information, the prompt information is generated.

[0170] In one possible implementation, the historical anomaly information includes the anomaly start time and anomaly type; the anomaly notification module 803 is specifically used for:

[0171] If the time difference between the current acquisition time and the end time of the target anomaly is less than a first preset time threshold, first historical anomaly information is determined from the historical anomaly information where the time interval between the end time of the anomaly and the current acquisition time is less than a second preset time threshold; the second preset time threshold is greater than the first preset time threshold.

[0172] If there is no historical anomaly of the same anomaly type as the target anomaly in the target anomaly information in the first historical anomaly information, the target anomaly information is identified as the newly added anomaly information, and the prompt information is generated.

[0173] In one possible implementation, the exception notification module 803 is further configured to:

[0174] If there is a historical anomaly in the first historical anomaly information that has the same anomaly type as the target anomaly in the target anomaly information, the anomaly end time of the historical anomaly in the first historical anomaly information that has the same anomaly type as the target anomaly is updated to the current collection time.

[0175] In one possible implementation, the exception notification module 803 is further configured to:

[0176] If the time difference between the current acquisition time and the end time of the target anomaly is not less than a first preset time threshold, second historical anomaly information is determined from the historical anomaly information. The second historical anomaly information refers to historical anomaly information where the time interval between the anomaly end time and the end time of the target anomaly information is less than a third preset time threshold.

[0177] If there is no historical anomaly of the same anomaly type as the target anomaly in the target anomaly information in the second historical anomaly information, the target anomaly information is identified as the newly added anomaly information, the prompt information is generated, and the target anomaly information is added to the historical anomaly information.

[0178] In one possible implementation, the exception notification module 803 is further configured to:

[0179] If the second historical anomaly information is not present in the historical anomaly information, the target anomaly information is identified as the newly added anomaly information, the prompt information is generated, and the target anomaly information is added to the historical anomaly information.

[0180] The processing flow of each module in the device and the interaction flow between each module can be referred to the relevant descriptions in the above method embodiments, and will not be detailed here.

[0181] Based on the same technical concept, this disclosure also provides an electronic device. (See also...) Figure 9 The diagram shows the structure of an electronic device 900 provided in this embodiment of the present disclosure, including a processor 901, a memory 902, and a bus 903. The memory 902 stores execution instructions and includes a main memory 9021 and an external memory 9022. The main memory 9021, also called internal memory, is used to temporarily store computational data in the processor 901, as well as data exchanged with external memory 9022 such as a hard disk. The processor 901 exchanges data with the external memory 9022 through the main memory 9021.

[0182] In this embodiment, the memory 902 is specifically used to store application code that executes the solution of this application, and its execution is controlled by the processor 901. That is, when the electronic device 900 is running, the processor 901 communicates with the memory 902 through the bus 903, so that the processor 901 executes the application code stored in the memory 902, and then executes the method described in any of the foregoing embodiments.

[0183] The memory 902 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0184] Processor 901 may be an integrated circuit chip with signal processing capabilities. The aforementioned processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application-Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor.

[0185] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the electronic device 900. In other embodiments of this application, the electronic device 900 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0186] This disclosure also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the fetal heart rate detection steps in the above-described method embodiments. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0187] This disclosure also provides a computer program product carrying program code. The program code includes instructions that can be used to execute the fetal heart rate detection steps in the above method embodiments. For details, please refer to the above method embodiments, which will not be repeated here.

[0188] The aforementioned computer program product can be implemented through hardware, software, or a combination thereof. In one optional embodiment, the computer program product is specifically embodied in a computer storage medium; in another optional embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0189] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. In the several embodiments provided in this disclosure, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces; the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms.

[0190] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0191] In addition, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0192] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

[0193] Finally, it should be noted that the above-described embodiments are merely specific implementations of this disclosure, used to illustrate the technical solutions of this disclosure, and not to limit it. The protection scope of this disclosure is not limited thereto. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this disclosure. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure, and should all be covered within the protection scope of this disclosure. Therefore, the protection scope of this disclosure should be determined by the protection scope of the claims.

Claims

1. A method for detecting fetal heart rate, characterized in that, include: Acquire target fetal heart rate monitoring data within a preset time period ending at the current acquisition time; Based on the target fetal heart rate monitoring data, a target detection baseline matching the target fetal heart rate monitoring data is determined, and anomaly detection is performed on the target fetal heart rate monitoring data based on the target detection baseline to obtain the target detection result; If the target detection result indicates that there is abnormal data in the target fetal heart rate monitoring data, a prompt message is generated based on the abnormal data; The target fetal heart rate monitoring data includes target fetal heart rate data or target uterine contraction rate data; the target detection baseline includes benchmark data corresponding to the target fetal heart rate monitoring data; and determining the target detection baseline matching the target fetal heart rate monitoring data based on the target fetal heart rate monitoring data includes: Based on the target fetal heart rate monitoring data and the first baseline detection algorithm, a first detection baseline is determined, and the first detection baseline includes first reference data corresponding to the target fetal heart rate monitoring data. Based on the target fetal heart rate monitoring data and the second baseline detection algorithm, a second detection baseline is determined, which includes second reference data corresponding to the target fetal heart rate monitoring data. The target detection baseline is determined based on the first reference data in the first detection baseline and the second reference data in the second detection baseline.

2. The method according to claim 1, characterized in that, The target detection baseline includes a target fetal heart rate detection baseline that matches the target fetal heart rate data and a target uterine contraction detection baseline that matches the target uterine contraction rate data. The step of performing anomaly detection on the target fetal heart rate monitoring data based on the target detection baseline to obtain the target detection result includes: Based on the target fetal heart rate detection baseline, anomaly detection is performed on the target fetal heart rate data to obtain a first detection result of the target fetal heart rate data; and based on the target uterine contraction detection baseline, anomaly detection is performed on the target uterine contraction rate data to obtain a second detection result of the target uterine contraction rate data. The target detection result is generated based on the first detection result and the second detection result.

3. The method according to claim 1, characterized in that, The target fetal heart rate monitoring data includes target fetal heart rate data, the first detection baseline includes a first fetal heart rate detection baseline, and the target fetal heart rate data includes fetal heart rate values ​​corresponding to different times within the preset time period. The step of determining the first detection baseline based on the target fetal heart rate monitoring data and the first baseline detection algorithm includes: Acquire preset first fetal heart rate fluctuation parameters and fetal heart rate baseline distribution data. The first fetal heart rate fluctuation parameters include at least a first fetal heart rate fluctuation threshold, a preset lower fetal heart rate limit, and a preset upper fetal heart rate limit. The fetal heart rate baseline distribution data includes different fetal heart rate baseline intervals and the distribution frequency corresponding to each fetal heart rate baseline interval. For each fetal heart rate value, a first target fetal heart rate baseline interval is determined based on the first fetal heart rate fluctuation parameter and the fetal heart rate value, and the fetal heart rate baseline distribution data is updated based on the first target fetal heart rate baseline interval. Determine the second target fetal heart rate baseline interval with the maximum number of distributions in the updated fetal heart rate baseline distribution data, and determine any one of the fetal heart rate values ​​in the second target fetal heart rate baseline interval as the reference data corresponding to the fetal heart rate value; The first fetal heart rate detection baseline is obtained based on the benchmark data corresponding to each fetal heart rate value.

4. The method according to claim 1, characterized in that, The target fetal heart rate monitoring data includes target fetal heart rate data, the second detection baseline includes a second fetal heart rate detection baseline, and the target fetal heart rate data includes fetal heart rate values ​​corresponding to different times within the preset time period. The step of determining the second detection baseline based on the target fetal heart rate monitoring data and the second baseline detection algorithm includes: Obtain preset second fetal heart rate fluctuation parameters and preset multiple fetal heart rate queues, wherein the second fetal heart rate fluctuation parameters include at least a second fetal heart rate fluctuation threshold; For each fetal heart rate value, the data of the multiple fetal heart rate queues is updated based on the second fetal heart rate fluctuation threshold, the fetal heart rate value, and the target fetal heart rate baseline data. Based on the updated data length of each fetal heart rate queue, the second fetal heart rate detection baseline is determined. The target fetal heart rate baseline data refers to the baseline data corresponding to the previous fetal heart rate value adjacent to the fetal heart rate value.

5. The method according to claim 4, characterized in that, The preset multiple fetal heart rate queues include a main fetal heart rate queue, a secondary fetal heart rate queue, and a fetal heart rate mean queue; the process of updating the multiple fetal heart rate queues based on the second fetal heart rate fluctuation threshold, the fetal heart rate value, and the target fetal heart rate baseline data, and determining the second fetal heart rate detection baseline based on the updated data length of each fetal heart rate queue, includes: For each fetal heart rate value, if the difference between the fetal heart rate value and the target fetal heart rate baseline data is less than the second fetal heart rate fluctuation threshold, the fetal heart rate value is added to the fetal heart rate master queue. According to the first-in, first-out principle, the fetal heart rate value that entered the queue first is deleted from both the main fetal heart rate queue and the secondary fetal heart rate queue. If the data length of the main fetal heart rate queue is not less than the data length of the secondary fetal heart rate queue, the average value of each fetal heart rate in the main fetal heart rate queue is added to the fetal heart rate mean queue, and the average value of all values ​​in the fetal heart rate mean queue is determined as the baseline data corresponding to the fetal heart rate value. The second fetal heart rate detection baseline is generated based on the baseline data corresponding to each fetal heart rate value.

6. The method according to claim 5, characterized in that, The method further includes: If the difference between the fetal heart rate value and the target fetal heart rate baseline data is not less than the second fetal heart rate fluctuation threshold, the fetal heart rate value is added to the fetal heart rate sub-queue. If the data length of the fetal heart rate sub-queue is greater than the data length of the fetal heart rate main queue, the fetal heart rate sub-queue is swapped with the fetal heart rate main queue so that the data length of the fetal heart rate main queue is not less than the data length of the fetal heart rate sub-queue.

7. The method according to claim 1, characterized in that, The target fetal heart rate monitoring data includes target uterine contraction rate data, the first detection baseline includes a first uterine contraction detection baseline, and the target uterine contraction rate data includes uterine contraction rate values ​​corresponding to different times within the preset time period. The step of determining the first detection baseline based on the target fetal heart rate monitoring data and the first baseline detection algorithm includes: Obtain preset first contraction fluctuation parameters and contraction baseline distribution data. The first contraction fluctuation parameters include at least a first contraction fluctuation threshold, a preset lower limit of contractions, and a preset upper limit of contractions. The contraction baseline distribution data includes different contraction baseline intervals and the number of distributions corresponding to each contraction baseline interval. For each contraction rate value, a first target contraction baseline interval is determined based on the first contraction fluctuation parameter and the contraction rate value, and the contraction baseline distribution data is updated based on the first target contraction baseline interval. Determine the second target uterine contraction baseline interval with the maximum number of distributions in the updated uterine contraction baseline distribution data, and determine any one of the uterine contraction rate values ​​in the second target uterine contraction baseline interval as the baseline data corresponding to the uterine contraction rate value; The first uterine contraction detection baseline is obtained based on the benchmark data corresponding to each uterine contraction rate value.

8. The method according to claim 1, characterized in that, The target fetal heart rate monitoring data includes target uterine contraction rate data, the second detection baseline includes a second uterine contraction detection baseline, and the target uterine contraction rate data includes uterine contraction rate values ​​corresponding to different times within the preset time period. The step of determining the second detection baseline based on the target fetal heart rate monitoring data and the second baseline detection algorithm includes: Obtain a preset second contraction fluctuation parameter and a preset multiple contraction queues, wherein the second contraction fluctuation parameter includes at least a second contraction fluctuation threshold; For each contraction rate value, the multiple contraction queues are updated based on the second contraction fluctuation threshold, the contraction rate value, and the target contraction baseline data. The second contraction detection baseline is determined based on the updated data length of each contraction queue. The target contraction baseline data refers to the baseline data corresponding to the previous contraction rate value adjacent to the contraction rate value.

9. The method according to claim 8, characterized in that, The preset multiple contraction queues include a primary contraction queue, a secondary contraction queue, and a contraction average queue; the process of updating the multiple contraction queues based on the second contraction fluctuation threshold, the contraction rate value, and the target contraction baseline data, and determining the second contraction detection baseline based on the updated data length of each contraction queue, includes: For each contraction rate value, if the difference between the contraction rate value and the target contraction baseline data is less than the second contraction fluctuation threshold, the contraction rate value is added to the main contraction queue. According to the first-in, first-out principle, the contraction rate value that entered the queue first is deleted from both the main contraction queue and the secondary contraction queue. If the data length of the main contraction queue is not less than the data length of the secondary contraction queue, the average value of each contraction rate in the main contraction queue is added to the average contraction queue, and the average value of all values ​​in the average contraction queue is determined as the baseline data corresponding to the contraction rate value. The second uterine contraction detection baseline is generated based on the baseline data corresponding to each uterine contraction rate value.

10. The method according to claim 9, characterized in that, The method further includes: If the difference between the contraction rate value and the target contraction baseline data is not less than the second contraction fluctuation threshold, the contraction rate value is added to the contraction sub-queue. If the data length of the contraction sub-queue is greater than the data length of the contraction main queue, the contraction sub-queue is swapped with the contraction main queue so that the data length of the contraction main queue is not less than the data length of the contraction sub-queue.

11. The method according to claim 1, characterized in that, The time interval between adjacent data collection moments is less than the duration of the preset time period; When the target detection result indicates the presence of abnormal data in the target fetal heart rate monitoring data, a prompt message is generated based on the abnormal data, including: If the target detection result indicates that there is abnormal data in the target fetal heart rate monitoring data, target abnormal information corresponding to the abnormal data is generated based on the abnormal data. The target anomaly information includes the anomaly start time and anomaly type; If the current acquisition time is not the first acquisition time, obtain the historical anomaly information corresponding to the previous acquisition time adjacent to the current acquisition time; The target anomaly information is matched with the historical anomaly information to obtain a matching result. If the matching result indicates that there is new anomaly information in the target anomaly information relative to the historical anomaly information, the prompt information is generated.

12. The method according to claim 11, characterized in that, The historical anomaly information includes the start time and type of the historical anomalies; the step of matching the target anomaly information with the historical anomaly information to obtain a matching result, and generating the prompt information when the matching result indicates that the target anomaly information has new anomaly information relative to the historical anomaly information, includes: If the time difference between the current acquisition time and the end time of the target anomaly is less than a first preset time threshold, first historical anomaly information is determined from the historical anomaly information where the time interval between the end time of the anomaly and the current acquisition time is less than a second preset time threshold; the second preset time threshold is greater than the first preset time threshold. If there is no historical anomaly of the same anomaly type as the target anomaly in the target anomaly information in the first historical anomaly information, the target anomaly information is identified as the newly added anomaly information, and the prompt information is generated.

13. The method according to claim 12, characterized in that, The method further includes: If there is a historical anomaly in the first historical anomaly information that has the same anomaly type as the target anomaly in the target anomaly information, the anomaly end time of the historical anomaly in the first historical anomaly information that has the same anomaly type as the target anomaly is updated to the current collection time.

14. The method according to claim 12, characterized in that, The method further includes: If the time difference between the current acquisition time and the end time of the target anomaly is not less than a first preset time threshold, second historical anomaly information is determined from the historical anomaly information. The second historical anomaly information refers to historical anomaly information where the time interval between the anomaly end time and the end time of the target anomaly information is less than a third preset time threshold. If there is no historical anomaly of the same anomaly type as the target anomaly in the target anomaly information in the second historical anomaly information, the target anomaly information is identified as the newly added anomaly information, the prompt information is generated, and the target anomaly information is added to the historical anomaly information.

15. The method according to claim 14, characterized in that, The method further includes: If the second historical anomaly information is not present in the historical anomaly information, the target anomaly information is identified as the newly added anomaly information, the prompt information is generated, and the target anomaly information is added to the historical anomaly information.

16. A fetal heart rate detection device, characterized in that, include: The data acquisition module is used to acquire target fetal heart rate monitoring data within a preset time period, with the current acquisition time as the endpoint. An anomaly detection module is used to determine a target detection baseline that matches the target fetal heart rate monitoring data based on the target fetal heart rate monitoring data, and to perform anomaly detection on the target fetal heart rate monitoring data based on the target detection baseline to obtain a target detection result; An anomaly alert module is used to generate alert information based on the abnormal data when the target detection result indicates that there is abnormal data in the target fetal heart rate monitoring data; The target fetal heart rate monitoring data includes target fetal heart rate data or target uterine contraction rate data; the abnormality detection module is also used for: Based on the target fetal heart rate monitoring data and the first baseline detection algorithm, a first detection baseline is determined, and the first detection baseline includes first reference data corresponding to the target fetal heart rate monitoring data. Based on the target fetal heart rate monitoring data and the second baseline detection algorithm, a second detection baseline is determined, which includes second reference data corresponding to the target fetal heart rate monitoring data. The target detection baseline is determined based on the first reference data in the first detection baseline and the second reference data in the second detection baseline.

17. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus, wherein the memory stores machine-readable requests executable by the processor, and when the electronic device is running, the processor communicates with the memory via the bus, and when the machine-readable requests are executed by the processor, the steps of the fetal heart rate detection method as described in any one of claims 1 to 15 are performed.

18. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the fetal heart rate detection method as described in any one of claims 1 to 15.

Images