Signal change point detection method, device, equipment and medium

Abstract

The invention discloses a signal change point detection method and device, equipment and a medium, and relates to the technical field of signal processing. The method comprises the following steps: acquiring a to-be-detected signal, wherein the to-be-detected signal consists of a plurality of signal points which are continuous on a time sequence; respectively determining a radial basis function value between any one signal point and any one signal point; for any one of a plurality of durations, according to a radial basis function value between any one signal point in the duration and any one signal point in the duration, determining a signal similarity corresponding to the duration, the plurality of durations including an initial duration and durations obtained by sequentially increasing according to a preset duration increment on the initial duration; the signal similarity is used for describing the similarity between the signal points within the duration and / or the similarity between the signal points outside the duration and the signal points within the corresponding duration; and determining a change point position in the to-be-detected signal according to the signal similarities corresponding to the plurality of durations. Through the change point detection method, accurate detection of the change point in the signal can be realized.

Description

Technical Field

[0001] The present application relates to the field of signal processing technology, and more specifically, to a signal change point detection method, device, equipment and medium. Background Art

[0002] A change point in a signal is a moment or location where the statistical characteristics of the signal change significantly. Statistical characteristics can be described by means of mean, variance, frequency, and phase.

[0003] Change point detection is used to identify change points in signals and is a key technology for identifying signal changes or anomalies. Therefore, how to provide a signal change point detection method has become a technical problem that needs to be solved urgently. Summary of the Invention

[0004] One purpose of this application is to provide a new technical solution for signal change point detection.

[0005] According to a first aspect of the present application, a signal change point detection method is provided, the method comprising:

[0006] Acquire a signal to be detected, where the signal to be detected consists of a plurality of signal points that are continuous in time sequence;

[0007] respectively determining radial basis function values ​​between any of the signal points and any of the signal points;

[0008] determining, for any one of a plurality of time durations, a signal similarity corresponding to the time duration based on a radial basis function value between any one of the signal points within the time duration and any one of the signal points within the time duration, the plurality of time durations including an initial time duration and time durations obtained by sequentially increasing the initial time duration by a preset time duration increment, the signal similarity being used to describe the similarity between the signal points within the time duration and / or the similarity between a signal point outside the time duration and a signal point within the corresponding time duration;

[0009] The position of the change point in the signal to be detected is determined according to the signal similarities respectively corresponding to the multiple time lengths.

[0010] Optionally, determining the signal similarity corresponding to the duration according to a radial basis function value between any signal point in the duration and any signal point in the duration includes:

[0011] determining a first signal similarity between signal points within the time span according to a radial basis function value between any signal point within the time span and any signal point within the time span;

[0012] and / or, determining a second similarity between the signal point outside the duration and the signal point within the duration based on a radial basis function value of any signal point outside the duration and any signal point within the duration;

[0013] The determining, based on the signal similarities corresponding to the plurality of time durations, the position of the change point in the signal to be detected includes:

[0014] The position of a change point in the signal to be detected is determined according to the first signal similarities and / or the second signal similarities respectively corresponding to the multiple time lengths.

[0015] Optionally, determining the position of the change point in the signal to be detected according to the first signal similarities and / or the second signal similarities respectively corresponding to the multiple time lengths includes:

[0016] Performing a weighted summation process on the first signal similarity and the second signal similarity corresponding to any of the time lengths to obtain a weighted sum value;

[0017] The position of the signal point corresponding to the cutoff time of the minimum weighted sum signal value corresponding to the duration is determined as the change point position.

[0018] Optionally, obtaining the signal to be detected includes:

[0019] Acquire the initial signal to be detected, where the initial signal to be detected is composed of a plurality of initial signal points that are continuous in time sequence;

[0020] Performing a preprocessing operation on the initial signal to be detected to obtain a signal to be detected;

[0021] The preprocessing operation at least includes a filtering operation or a baseline removal operation.

[0022] Optionally, respectively determining radial basis function values ​​between any of the signal points and any of the signal points includes:

[0023] respectively determining initial values ​​of radial basis functions between any of the signal points and any of the signal points;

[0024] Normalization processing is performed on initial values ​​of radial basis functions between any of the signal points to obtain radial basis function values ​​between any of the signal points.

[0025] Optionally, respectively determining radial basis function values ​​between any of the signal points and any of the signal points includes:

[0026] Determining a signal-to-noise ratio of the signal to be detected according to the signal to be detected;

[0027] Determining a target kernel width value of a radial basis function according to the signal-to-noise ratio;

[0028] According to the radial basis function whose kernel width is the target kernel width value, radial basis function values ​​between any of the signal points and any of the signal points are determined respectively.

[0029] According to a second aspect of the present application, a signal change point detection device is provided, the device comprising:

[0030] An acquisition module, configured to acquire a signal to be detected, wherein the signal to be detected is composed of a plurality of signal points that are continuous in time sequence;

[0031] A first determining module, configured to respectively determine a radial basis function value between any of the signal points and any of the signal points;

[0032] a second determining module configured to determine, for any one of a plurality of durations, a signal similarity corresponding to the duration based on a radial basis function value between any one of the signal points within the duration and any one of the signal points within the duration, the plurality of durations including an initial duration and durations obtained by sequentially increasing the initial duration by a preset duration increment, the signal similarity being used to describe the similarity between signal points within the duration and / or the similarity between a signal point outside the duration and a signal point within the corresponding duration;

[0033] The third determining module is configured to determine a position of a change point in the signal to be detected according to the signal similarities respectively corresponding to the multiple time lengths.

[0034] Optionally, the second determining module is specifically configured to:

[0035] determining a first signal similarity between signal points within the time span according to a radial basis function value between any signal point within the time span and any signal point within the time span;

[0036] and / or, determining a second similarity between the signal point outside the duration and the signal point within the duration based on a radial basis function value of any signal point outside the duration and any signal point within the duration;

[0037] The third determining module is specifically configured to:

[0038] The position of a change point in the signal to be detected is determined according to the first signal similarities and / or the second signal similarities respectively corresponding to the multiple time lengths.

[0039] According to a third aspect of the present application, an electronic device is provided, comprising the apparatus according to any one of the second aspects;

[0040] Alternatively, the electronic device includes a memory and a processor, the memory is used to store computer instructions, and the processor is used to call the computer instructions from the memory to execute the method as described in any one of the first aspects.

[0041] According to a fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method according to any one of the first aspects is implemented.

[0042] The present application provides a signal change point detection method, which includes: a signal change point detection method, which includes: obtaining a signal to be detected, the signal to be detected is composed of multiple continuous signal points in time sequence; respectively determining the radial basis function value between any signal point and any signal point; for any time length in multiple time lengths, according to the radial basis function value between any signal point in the time length and any signal point in the time length, determining the signal similarity corresponding to the time length, the multiple time lengths include an initial time length and a time length obtained by increasing the initial time length in sequence according to a preset time length increment, the signal similarity is used to describe the similarity between signal points in the time length and / or the similarity between signal points outside the time length and signal points in the corresponding time length; according to the signal similarities corresponding to the multiple time lengths, determining the position of the change point in the signal to be detected. This method is based on the radial basis function, which is a nonlinear kernel function based on the similarity between sample points. It can map the signal to a high-dimensional feature space and capture complex patterns that are difficult to represent by traditional linear methods, thereby achieving effective classification and regression in a higher-dimensional space. This method uses the spatial mapping capability of radial basis functions to map the high-dimensional features (similarity) between the signals to be detected into a matrix. Therefore, the change point detection method provided by this application can accurately detect change points in the signal.

[0043] Other features and advantages of the present application will become apparent from the following detailed description of exemplary embodiments of the present application with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the application and, together with the description, serve to explain the principles of the application.

[0045] Figure 1 The present invention provides a hardware configuration framework for an electronic device that implements a signal change point detection method. Figure 1 ;

[0046] Figure 2 This is a flow chart of a method for detecting signal change points according to an embodiment of the present application;

[0047] Figure 3This is a schematic structural diagram of a signal change point detection device provided in accordance with an embodiment of the present application;

[0048] Figure 4 The present invention provides a hardware configuration framework for an electronic device that implements a signal change point detection method. Figure 2 . DETAILED DESCRIPTION

[0049] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present application.

[0050] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0051] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0052] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0053] It should be noted that like reference numerals and letters refer to like items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0054] Figure 1 The present invention provides a hardware configuration framework for an electronic device that implements a signal change point detection method. Figure 1 .

[0055] The electronic device 1000 may be a terminal or a server. Further, the terminal may be a head-mounted device (such as an AR device, an MR device, and a VR device), a portable computer, a tablet computer, a PDA, etc. The server may be a cloud server, etc.

[0056] Electronic device 1000 may include a processor 1100, a memory 1200, an interface device 1300, a communication device 1400, a display device 1500, an input device 1600, a speaker 1700, a microphone 1800, and the like. Processor 1100 may be a central processing unit (CPU), a microprocessor (MCU), or the like. Memory 1200 may include, for example, a ROM (read-only memory), a RAM (random access memory), or a non-volatile memory such as a hard disk. Interface device 1300 may include, for example, a USB interface or a headphone jack. Communication device 1400 may be capable of wired or wireless communication. Display device 1500 may be, for example, an LCD display or a touchscreen display. Input device 1600 may include, for example, a touchscreen or a keyboard. A user may input / output voice information through speaker 1700 and microphone 1800.

[0057] Despite Figure 1 Multiple devices are shown for the electronic device 1000, but the present application may only involve some of the devices, for example, the electronic device 1000 only involves the memory 1200 and the processor 1100.

[0058] In the embodiment of the present application, the memory 1200 of the electronic device 1000 is used to store instructions, which are used to control the processor 1100 to execute the signal change point detection method provided in the embodiment of the present application.

[0059] In the above description, a person skilled in the art can design instructions according to the solution disclosed in this application. How instructions control the operation of a processor is well known in the art and will not be described in detail here.

[0060] This application provides a signal change point detection method, which is applied to Figure 1 The electronic equipment shown. Figure 2 As shown, it includes the following steps S2100 to S2400.

[0061] Step S2100: Acquire the signal to be detected.

[0062] The signal to be detected is composed of a plurality of signal points that are continuous in time sequence.

[0063] In one embodiment of the present application, the signal to be detected may be, for example, a motion signal, a biochemical marker signal, and an environmental interaction signal. Among them, the motion signal may be, for example, a signal characterizing a motion trajectory or posture change collected by sensors such as an accelerometer, a gyroscope, and an inertial measurement unit. Biochemical marker signals may be, for example, lactic acid and sodium ion concentrations in sweat, and dynamic change signals of metabolites such as uric acid and cortisol in saliva. Environmental interaction signals may be, for example, mechanical feedback signals (such as pressure and torque) of sports equipment and ambient temperature and humidity signals. It should be noted that the present application does not limit the type of signal to be detected, that is, the signal change point detection provided by the present application is a general signal change point detection method.

[0064] In addition, in this embodiment, the signal to be detected X is represented as X=(x0, x1, x2, . . . , x N ), the signal change point detection method provided by this application will be explained below using this as an example.

[0065] Step S2200 , determining radial basis function values ​​between any signal point and any signal point.

[0066] The signal points are x i and x j For example, the radial basis function (RBF) value between one signal point and another signal point is calculated by the following radial basis function (RBF) formula 1.

[0067]

[0068] Among them, K(x i , x j ) represents the signal point x i With signal point x j The radial basis function value between the two points; i and j represent the time sequence numbers corresponding to the signal points; ||x i -x j || represents the signal point x i With signal point x j ; σ represents the target kernel width value, which is used to control the similarity decay rate and can be set based on experience.

[0069] Through the above step S2200, the radial basis function values ​​shown in the following matrix can be calculated.

[0070]

[0071] in,<x0,x0> represents the radial basis function value between the signal point x0 and the signal point x0. And, the first row in the above matrix represents the radial basis function value between the signal point x0 and any signal point (i.e. x0, x1, ..., xN ) between the radial basis function values.

[0072] It should be noted that step S2200 satisfies the three necessary conditions for a Gram matrix: symmetry, positive semidefiniteness, and dimensionality. Therefore, the matrix constructed in step S2200 is a Gram matrix. Based on this, and in combination with the matrix, step S2200 can be implemented by multiplying the matrix corresponding to the signal to be detected by the transpose of the matrix corresponding to the signal to be detected.

[0073] Furthermore, the radial basis function is a nonlinear kernel function based on the similarity between sample points. It can map signals into a high-dimensional feature space, capturing complex patterns that are difficult to characterize using traditional linear methods, thereby enabling effective classification and regression in a higher-dimensional space. In this embodiment, the spatial mapping capability of the radial basis function is applied to map the high-dimensional features (similarity) between the signals to be detected into a matrix.

[0074] Step S2300 : For any duration among the multiple durations, determine the signal similarity corresponding to the duration according to the radial basis function value between any signal point in the duration and any signal point in the duration.

[0075] Among them, multiple time lengths include an initial time length and a time length obtained by increasing the initial time length in sequence according to a preset time length increment. The signal similarity is used to describe the similarity between signal points within the time length and / or the similarity between signal points outside the time length and signal points within the corresponding time length.

[0076] In this embodiment, the initial duration begins at the duration corresponding to the first signal point in the signal to be detected. The initial duration is [0, L-1], where L is the duration corresponding to the initial duration and can be set based on experience. It should be noted that in this embodiment, the durations involved are represented by the number of signal points included. This is because the signal to be detected is obtained by periodically acquiring signal points. For example, if L is 10, the initial duration corresponds to 10 consecutive signal points, and the initial duration is from the first to the tenth signal point in the signal to be detected.

[0077] Furthermore, the preset time increment may be specifically a preset number of signals.

[0078] In one example, the preset duration is 5. Based on this, the multiple durations are: [0, L-1], [0, L-1+5], [0, L-1+5*2], [0, L-1+5*3], etc. That is to say, in this embodiment, the multiple durations are incremented in sequence.

[0079] It is understood that a change point in a signal is distinguished from a non-change point in the signal. Based on this, the location of the change point can be determined based on the similarity between signal points. In one embodiment of the present application, step S2300 is specifically implemented through the following steps S2310 and / or S2320.

[0080] Step S2310 : determining a first similarity corresponding to the duration according to a radial basis function value between any signal point in the duration and any signal point in the duration.

[0081] In this embodiment, the above step S2310 is specifically implemented by the following formula 2.

[0082]

[0083] Among them, the value range of t is [L-1, N], LowCost(t) represents the first similarity, which is used to describe the similarity between signal points within the time length, also known as the static cost. G(i,j) represents the signal point x i With signal point x j The radial basis function value between G(i,j) and LowCost(t) is the value of the i-th row and j-th column in the above matrix. As G(i,j)→1, the smaller the LowCost(t) value, the higher the similarity of the signal points within the time span, and the signal pattern is stable and unchanged. Conversely, as G(i,j)→0, the larger the LowCost(t) value, indicating that the signal points within the time span contain noise or are in the transition zone after the change point. Positions with low stationary costs usually correspond to stable regions before the change point, such as the stable segment of the IMU signal that is not disturbed by motion artifacts.

[0084] Step S2320 : determining a second similarity between a signal point outside the duration and a signal point within the duration based on the radial basis function values ​​of any signal point outside the duration and any signal point within the duration.

[0085] In this embodiment, the above step S2320 is specifically implemented by the following formula 3.

[0086]

[0087] Among them, HighCost(t) represents the second similarity, which is used to describe the similarity between the signal points outside the duration and the signal points within the corresponding duration, also known as the active cost. I(·) represents the indicator function. When j is not within the duration [t+1, N], the value is 0, otherwise it is 1. G(i,j)→0, the larger the HighCost(t), the greater the difference between the signal points outside the duration and the signal points within the duration, and the time period may be the state after the change point. G(i,j)→1, the smaller the HighCost(t), the greater the similarity between the signal points outside the duration and the signal points within the duration, and the signal pattern has not changed significantly. Positions with low active costs usually correspond to the transition zone after the change point.

[0088] In one embodiment of the present application, the first similarity or the second similarity is used as the signal similarity corresponding to the duration, or the joint similarity corresponding to the first similarity and the second similarity is used to describe the signal similarity corresponding to the duration.

[0089] Step S2400 : determining the position of a change point in the signal to be detected according to the signal similarities corresponding to the multiple time lengths.

[0090] In one embodiment of the present application, based on the above-mentioned step S2310 and step S2320, the above-mentioned step S2400 is specifically implemented through the following step S2410.

[0091] S2410 : Determine a change point position in the signal to be detected according to first signal similarities and / or second signal similarities corresponding to a plurality of time lengths.

[0092] In this embodiment, based on the above description of the first similarity, it can be seen that when the first similarity is used as the signal similarity corresponding to the time length, the specific implementation of the above step S2410 is: among the first signal similarities corresponding to multiple time lengths, the signal point corresponding to the end moment of the time length corresponding to the smallest first signal similarity is used as the change point position in the signal to be detected.

[0093] Based on the above description of the second similarity, it can be seen that when the second similarity is used as the signal similarity corresponding to the time length, the specific implementation of the above step S2410 is: among the second signal similarities corresponding to multiple time lengths, the starting time of the time length corresponding to the smallest second signal similarity is used as the change point position in the signal to be detected.

[0094] Based on the above description of the first similarity and the second similarity, it can be seen that when the joint similarity corresponding to the first similarity and the second similarity is used as the signal similarity corresponding to the time length, the specific implementation of the above step S2410 can be: calculate the sum of the first similarity and the second similarity corresponding to the same time length, and take the signal point corresponding to the end time of the time length corresponding to the minimum sum as the change point position in the signal to be detected.

[0095] In the case where the comprehensive similarity corresponding to the first similarity and the second similarity is used as the signal similarity corresponding to the duration, the above-mentioned step S2410 may be specifically implemented through the following steps S2411 and S2412.

[0096] Step S2411 : performing weighted summation processing on the first signal similarity and the second signal similarity corresponding to any time length to obtain a weighted sum value.

[0097] The above step S2411 is specifically implemented through the following formula 4.

[0098] TotalCost(t)=ω1LowCost(t)+ω2HighCost(t) (Formula 4)

[0099] Among them, TotalCost(t) represents the weighted sum value; ω1 and ω2 are weights, the sum of ω1 and ω2 is 1, and the specific value is set based on experience.

[0100] Step S2412: Determine the position of the signal point at the end time of the minimum weighted sum signal value corresponding to the duration as the change point position.

[0101] It can be understood that the change point is located at the intersection of the stable range before the change point and the transition zone after the change point. Based on the meaning of the first similarity and the second similarity, it can be seen that the minimum weighted sum value corresponding to the first similarity and the second similarity corresponds to the signal point at the end of the duration as the location of the change point.

[0102] Based on steps S2411 and S2412, a dual-dimensional evaluation of the first similarity (static cost) and the second similarity (active cost) can be achieved, overcoming the limitations of a single metric. In signals with motion artifacts and noise interference, steps S2411 and S2412 can be used to more accurately determine change points.

[0103] In addition, it can be seen from the above steps S2100 to S2400 that the change point detection method provided in this application does not involve deep learning, etc. Therefore, the required computing power is small and it has lightweight cross-platform deployment capabilities.

[0104] In summary, the present application provides a signal change point detection method, which includes: a signal change point detection method, which includes: obtaining a signal to be detected, the signal to be detected is composed of multiple continuous signal points in time sequence; respectively determining the radial basis function value between any signal point and any signal point; for any time length in multiple time lengths, according to the radial basis function value between any signal point in the time length and any signal point in the time length, determining the signal similarity corresponding to the time length, the multiple time lengths include an initial time length and a time length obtained by increasing the initial time length in sequence according to a preset time length increment, the signal similarity is used to describe the similarity between signal points in the time length and / or the similarity between signal points outside the time length and signal points in the corresponding time length; according to the signal similarities corresponding to the multiple time lengths, determining the change point position in the signal to be detected. This method is based on the radial basis function, which is a nonlinear kernel function based on the similarity between sample points. It can map the signal to a high-dimensional feature space and capture complex patterns that are difficult to represent by traditional linear methods, thereby achieving effective classification and regression in a higher-dimensional space. This method uses the spatial mapping capability of radial basis functions to map the high-dimensional features (similarity) between the signals to be detected into a matrix. Therefore, the change point detection method provided by this application can accurately detect change points in the signal.

[0105] In one embodiment of the present application, the above-mentioned step S2100 is specifically implemented through the following steps S2110 and S2120.

[0106] Step S2110: Acquire the initial signal to be detected.

[0107] The initial signal to be detected is composed of a plurality of initial signal points that are continuous in time sequence.

[0108] In this embodiment, the initial signal to be detected is a signal to be subjected to change point detection obtained under initial conditions, such as an acceleration signal directly output by an accelerometer.

[0109] Step S2120: performing a preprocessing operation on the initial signal to be detected to obtain a signal to be detected.

[0110] The pre-processing operation may include a filtering operation or a baseline removal operation.

[0111] In this embodiment, if the preprocessing operation includes filtering, the preprocessing operation can be performed on the initial signal to be detected using a filter such as a bandpass filter. This can remove high-frequency noise and low-frequency drift while retaining key features of the initial signal to be detected. If the preprocessing operation includes baseline removal, the baseline component of the initial signal to be detected can be removed using a moving average filter, for example. This can effectively remove baseline drift in the initial signal to be detected while retaining key features of the initial signal to be detected.

[0112] It should be noted that, in this embodiment, there is no limitation on the specific implementation of the filtering operation and the baseline removal operation.

[0113] Through the above steps S2110 and S2120, a basis is provided for the following step S2200 to accurately determine the radial basis function value between any signal point and any signal point.

[0114] In one embodiment of the present application, the above-mentioned step S2200 is specifically implemented through the following steps S2210 and S2220.

[0115] Step S2210 , determining initial values ​​of radial basis functions between any signal point and any signal point.

[0116] In this embodiment, the signal point x i With signal point x j For example, the K(x i , x j ) is recorded as the initial value of the radial basis function.

[0117] Step S2220 , performing normalization processing on the initial values ​​of the radial basis functions between any signal point and any signal point, to obtain the radial basis function values ​​between any signal point and any signal point.

[0118] In this application example, normalization processing is performed on each initial value of the radial basis function calculated based on the above step S2110. This not only reduces the amount of data, but also converts features of different scales to the same scale, which can improve the speed of subsequent search for change point positions.

[0119] In one embodiment of the present application, the above-mentioned step S2200 can be specifically implemented through the following steps S2230 to S2250.

[0120] Step S2230: Determine the signal-to-noise ratio of the signal to be detected according to the signal to be detected.

[0121] In this embodiment, the signal-to-noise ratio of the signal to be detected is determined by the following formula 5. Wherein, a higher signal-to-noise ratio indicates better signal quality and less impact of noise on the signal.

[0122]

[0123] Among them, SNR(t) represents the signal-to-noise ratio of the signal to be detected, P signal It represents the signal power of the signal to be detected, P noise It represents the noise power of the signal to be detected.

[0124] Step S2240: Determine a target kernel width value of the radial basis function according to the signal-to-noise ratio.

[0125] In this embodiment, the target kernel width value of the radial basis function is determined by the following formula 6.

[0126] σ(t)=α*SNR(t) -1 +β (Formula 6)

[0127] Among them, σ(t) represents the target kernel width value of the radial basis function, α and β represent empirical coefficients, α can be specifically taken as 0.5, and β can be specifically taken as 0.1.

[0128] Through the above step S2240, it is possible to increase σ(t) to suppress noise when the SNR(t) is small, and to reduce σ(t) to retain details when the SNR(t) is large.

[0129] Through the above steps S2230 and S2240, the target kernel width value of the radial basis function can be dynamically determined, so that the subsequent step S2250 can obtain a more accurate radial basis function value between any signal point and any signal point.

[0130] Step S2250 , determining radial basis function values ​​between any signal point and any signal point according to the radial basis function whose kernel width is the target kernel width value.

[0131] In this embodiment, the signal point x i With signal point x j For example, the specific implementation of the above step S2250 is: i With signal point x j Substitute the kernel width into the radial basis function with the target kernel width value to obtain the signal point x i With signal point x j The radial basis function value between .

[0132] This application also provides a signal change point detection device 300, such as Figure 3 As shown, the device 300 includes:

[0133] An acquisition module 310 is configured to acquire a signal to be detected, where the signal to be detected is composed of a plurality of sequentially continuous signal points;

[0134] A first determining module 320 is configured to determine radial basis function values ​​between any of the signal points and any of the signal points;

[0135] a second determining module 330 configured to determine, for any one of a plurality of durations, a signal similarity corresponding to the duration based on a radial basis function value between any one of the signal points within the duration and any one of the signal points within the duration, wherein the plurality of durations include an initial duration and durations obtained by sequentially increasing the initial duration by a preset duration increment, the signal similarity being used to describe the similarity between signal points within the duration and / or the similarity between a signal point outside the duration and a signal point within the corresponding duration;

[0136] The third determining module 340 is configured to determine a change point position in the signal to be detected according to the signal similarities corresponding to the multiple time lengths.

[0137] In one embodiment of the present application, the second determining module 330 is specifically configured to:

[0138] determining a first signal similarity between signal points within the time span according to a radial basis function value between any signal point within the time span and any signal point within the time span;

[0139] and / or, determining a second similarity between the signal point outside the duration and the signal point within the duration based on a radial basis function value of any signal point outside the duration and any signal point within the duration;

[0140] The third determining module 340 is specifically configured to:

[0141] The position of a change point in the signal to be detected is determined according to the first signal similarities and / or the second signal similarities respectively corresponding to the multiple time lengths.

[0142] In one embodiment of the present application, the third determining module 340 is specifically configured to: perform weighted sum processing on the first signal similarity and the second signal similarity corresponding to any of the time lengths to obtain a weighted sum value;

[0143] The position of the signal point corresponding to the cutoff time of the minimum weighted sum signal value corresponding to the duration is determined as the change point position.

[0144] In one embodiment of the present application, the acquisition module 310 is specifically configured to:

[0145] Acquire the initial signal to be detected, where the initial signal to be detected is composed of a plurality of initial signal points that are continuous in time sequence;

[0146] Performing a preprocessing operation on the initial signal to be detected to obtain a signal to be detected;

[0147] The preprocessing operation at least includes a filtering operation or a baseline removal operation.

[0148] In one embodiment of the present application, the first determining module 320 is specifically configured to respectively determine an initial value of a radial basis function between any of the signal points and any of the signal points;

[0149] Normalization processing is performed on initial values ​​of radial basis functions between any of the signal points to obtain radial basis function values ​​between any of the signal points.

[0150] In one embodiment of the present application, the first determining module 320 is specifically configured to determine a signal-to-noise ratio of the signal to be detected based on the signal to be detected;

[0151] Determining a target kernel width value of a radial basis function according to the signal-to-noise ratio;

[0152] According to the radial basis function whose kernel width is the target kernel width value, radial basis function values ​​between any of the signal points and any of the signal points are determined respectively.

[0153] The present application also provides an electronic device, which includes any one of the signal change point detection devices 300 provided in the above device embodiments.

[0154] Or, as Figure 4 As shown, the electronic device 400 includes a memory 410 and a processor 420, wherein the memory 410 is used to store computer instructions, and the processor 420 is used to call the computer instructions from the memory 410 to execute any one of the methods provided in the above embodiments.

[0155] The present application also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method according to any one of the above method embodiments is implemented.

[0156] The present application may be a system, method and / or computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present application.

[0157] A computer-readable storage medium can be a tangible device that can hold and store instructions for use by an instruction execution device. A computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination thereof. As used herein, a computer-readable storage medium is not to be construed as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through an electrical wire.

[0158] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in the computer-readable storage medium in each computing / processing device.

[0159] The computer program instructions for performing the operation of the present application can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data or source code or object code written in any combination of one or more programming languages, wherein the programming language includes object-oriented programming languages ​​such as Smalltalk, C++, and conventional procedural programming languages ​​such as "C" language or similar programming languages. Computer-readable program instructions can be executed completely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or executed completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer by any type of network including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (such as by using an Internet service provider to connect to the Internet). In certain embodiments, by utilizing the state information of computer-readable program instructions to personalize electronic circuits, such as programmable logic circuits, field programmable gate arrays (FPGAs) or programmable logic arrays (PLAs), the electronic circuits can execute computer-readable program instructions, thereby realizing various aspects of the present application.

[0160] Various aspects of the present application are described herein with reference to flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0161] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0162] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0163] The flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a part of a module, program segment or instruction, and the part of the module, program segment or instruction contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are all equivalent.

[0164] The embodiments of the present application have been described above. The above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terms used herein are selected to best explain the principles of the embodiments, practical applications, or technical improvements to technologies in the market, or to enable other persons skilled in the art to understand the embodiments disclosed herein. The scope of this application is defined by the appended claims.

Claims

1. A signal change point detection method, characterized in that: The method comprises: Acquire a signal to be detected, where the signal to be detected consists of a plurality of signal points that are continuous in time sequence; respectively determining radial basis function values ​​between any of the signal points and any of the signal points; determining, for any one of a plurality of time durations, a signal similarity corresponding to the time duration based on a radial basis function value between any one of the signal points within the time duration and any one of the signal points within the time duration, the plurality of time durations including an initial time duration and time durations obtained by sequentially increasing the initial time duration by a preset time duration increment, the signal similarity being used to describe the similarity between the signal points within the time duration and / or the similarity between a signal point outside the time duration and a signal point within the corresponding time duration; The position of the change point in the signal to be detected is determined according to the signal similarities respectively corresponding to the multiple time lengths.

2. The method according to claim 1, characterized in that The determining, based on a radial basis function value between any signal point in the time span and any signal point in the time span, a signal similarity corresponding to the time span includes: determining a first signal similarity between signal points within the time span according to a radial basis function value between any signal point within the time span and any signal point within the time span; and / or, determining a second similarity between the signal point outside the duration and the signal point within the duration based on a radial basis function value of any signal point outside the duration and any signal point within the duration; The determining, based on the signal similarities corresponding to the plurality of time durations, the position of the change point in the signal to be detected includes: The position of a change point in the signal to be detected is determined according to the first signal similarities and / or the second signal similarities respectively corresponding to the multiple time lengths.

3. The method according to claim 2, characterized in that The determining, based on the first signal similarities and / or the second signal similarities respectively corresponding to the multiple time lengths, a change point position in the signal to be detected includes: Performing a weighted summation process on the first signal similarity and the second signal similarity corresponding to any of the time lengths to obtain a weighted sum value; The position of the signal point corresponding to the cutoff time of the minimum weighted sum signal value corresponding to the duration is determined as the change point position.

4. The method according to claim 1, wherein The obtaining of the signal to be detected includes: Acquire the initial signal to be detected, where the initial signal to be detected is composed of a plurality of initial signal points that are continuous in time sequence; Performing a preprocessing operation on the initial signal to be detected to obtain a signal to be detected; The preprocessing operation at least includes a filtering operation or a baseline removal operation.

5. The method according to claim 1, characterized in that The respectively determining the radial basis function value between any one of the signal points and any one of the signal points comprises: respectively determining initial values ​​of radial basis functions between any of the signal points and any of the signal points; Normalization processing is performed on initial values ​​of radial basis functions between any of the signal points to obtain radial basis function values ​​between any of the signal points.

6. The method according to claim 1, characterized in that The respectively determining the radial basis function value between any one of the signal points and any one of the signal points comprises: Determining a signal-to-noise ratio of the signal to be detected according to the signal to be detected; Determining a target kernel width value of a radial basis function according to the signal-to-noise ratio; According to the radial basis function whose kernel width is the target kernel width value, radial basis function values ​​between any of the signal points and any of the signal points are determined respectively.

7. A signal change point detection device, characterized in that: The device comprises: An acquisition module, configured to acquire a signal to be detected, wherein the signal to be detected is composed of a plurality of signal points that are continuous in time sequence; A first determining module, configured to respectively determine a radial basis function value between any of the signal points and any of the signal points; a second determining module configured to determine, for any one of a plurality of durations, a signal similarity corresponding to the duration based on a radial basis function value between any one of the signal points within the duration and any one of the signal points within the duration, the plurality of durations including an initial duration and durations obtained by sequentially increasing the initial duration by a preset duration increment, the signal similarity being used to describe the similarity between signal points within the duration and / or the similarity between a signal point outside the duration and a signal point within the corresponding duration; The third determining module is configured to determine a position of a change point in the signal to be detected according to the signal similarities respectively corresponding to the multiple time lengths.

8. The device according to claim 7, characterized in that The second determining module is specifically configured to: determining a first signal similarity between signal points within the time span according to a radial basis function value between any signal point within the time span and any signal point within the time span; and / or, determining a second similarity between the signal point outside the duration and the signal point within the duration based on a radial basis function value of any signal point outside the duration and any signal point within the duration; The third determining module is specifically configured to: The position of a change point in the signal to be detected is determined according to the first signal similarities and / or the second signal similarities respectively corresponding to the multiple time lengths.

9. An electronic device, characterized in that: The electronic device comprises the apparatus according to claim 7 or 8; Alternatively, the electronic device includes a memory and a processor, the memory is used to store computer instructions, and the processor is used to call the computer instructions from the memory to execute the method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that A computer program is stored thereon, which implements the method according to any one of claims 1 to 6 when executed by a processor.

Images